diff --git "a/checkpoint-2136960/trainer_state.json" "b/checkpoint-2136960/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2136960/trainer_state.json" @@ -0,0 +1,25287 @@ +{ + "best_metric": 3.9902238845825195, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/lstm/2/checkpoints/checkpoint-2136960", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2136960, + "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": 10.8198, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5561, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0558, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9947, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9451, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.923, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7606, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6438, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5402, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.454, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3949, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3237, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2535, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.189, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1376, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0803, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0409, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 6.0043, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9607, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9188, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.893, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.853, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8304, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.794, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7784, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7408, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7192, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6908, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6758, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6486, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.6382, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6197, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5953, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5807, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5663, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5425, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5386, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.5052, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4923, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4631, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4621, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4461, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4415, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.4144, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963110020355577e-05, + "loss": 5.404, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.4009, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3945, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.381, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3626, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3469, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3626, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3489, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3284, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.3075, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3174, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.294, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2996, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2685, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2806, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.2643, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2474, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2337, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2449, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.2028, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.2163, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2246, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.2079, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1992, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1745, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1702, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.166, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 5.1767, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1567, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1663, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1557, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1539, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1299, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1271, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1187, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1164, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.1144, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0977, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.0996, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0962, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0728, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.0795, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0776, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.08, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.06, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0568, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.0434, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 5.039, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.0406, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0381, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.029, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0322, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.0215, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0058, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 5.0024, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 5.0052, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 5.0003, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 5.0045, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9868, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9794, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9832, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.9631, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9681, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9584, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9591, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9464, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9484, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9386, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9421, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9367, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.927, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9373, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9338, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.9236, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.9101, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9111, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.9091, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.9107, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.9052, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.8941, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8986, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8847, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.889, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8754, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8818, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.8703, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8784, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8776, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.875, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8523, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8577, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8557, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.8574, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.8464, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.8519, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.8397, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8558, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8237, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8432, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.827, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.8225, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.8226, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8076, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.813, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.8204, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.8075, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.7714524269104, + "eval_runtime": 297.4083, + "eval_samples_per_second": 1283.054, + "eval_steps_per_second": 40.096, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.8051, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.7996, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.8108, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.8001, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.8071, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.7815, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.7906, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7736, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7786, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.782, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.7786, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.7811, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.761, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.7732, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.7569, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.761, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.7635, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.7539, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.7551, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.7697, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.746, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.7513, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.7453, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7533, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.7423, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.7422, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.7251, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.7336, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.85078090860431e-05, + "loss": 4.7199, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849942313853258e-05, + "loss": 4.7314, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849103719102206e-05, + "loss": 4.7279, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.7248, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847428167480475e-05, + "loss": 4.7293, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846589572729423e-05, + "loss": 4.7181, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.7254, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.7171, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.7077, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.7007, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.6898, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.6999, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.6986, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.7042, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6884, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.6896, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6927, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.6852, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.6927, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.6781, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.6691, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.6965, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6895, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.6757, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.6713, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6792, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.6635, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.6807, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6521, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.677, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.669, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6524, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6486, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6627, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6256, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.6472, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.6587, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.6504, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.6407, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180888163562664e-05, + "loss": 4.6285, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6327, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6339, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.6428, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.6313, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.638, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.6433, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.6405, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811383334108597e-05, + "loss": 4.6222, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810544739357545e-05, + "loss": 4.6286, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809706144606493e-05, + "loss": 4.6278, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808867549855441e-05, + "loss": 4.6192, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.6248, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.6148, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.6226, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.6214, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.6005, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.614, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803000662358823e-05, + "loss": 4.6118, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802162067607771e-05, + "loss": 4.6202, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801323472856719e-05, + "loss": 4.6118, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800484878105667e-05, + "loss": 4.6056, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799646283354615e-05, + "loss": 4.5995, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.5938, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.6004, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.6043, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.6009, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795456585360101e-05, + "loss": 4.6045, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794617990609049e-05, + "loss": 4.5968, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793779395857997e-05, + "loss": 4.5897, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792940801106946e-05, + "loss": 4.5867, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792102206355894e-05, + "loss": 4.5917, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5963, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904282926145356e-05, + "loss": 4.5962, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895896978634836e-05, + "loss": 4.585, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.5777, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.5882, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5702, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5784, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5739, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5743, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5636, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5747, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.5618, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812037503529635e-05, + "loss": 4.5674, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.571, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.5585, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.5787, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5747, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5666, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.5572, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.5557, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.5621, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.5557, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5652, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5484, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5556, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5533, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.5587, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.5406, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.5523, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5481, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.76611559635552e-05, + "loss": 4.5486, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765277001604468e-05, + "loss": 4.5538, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764438406853416e-05, + "loss": 4.5594, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763599812102364e-05, + "loss": 4.5343, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762761217351312e-05, + "loss": 4.5419, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.547, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5437, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.5403, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.5432, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5348, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757731286725373e-05, + "loss": 4.5525, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568926919743206e-05, + "loss": 4.5264, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5426, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5311, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5255, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.528, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5229, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751864399228755e-05, + "loss": 4.5232, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751025804477703e-05, + "loss": 4.5281, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750187209726651e-05, + "loss": 4.5233, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.489068508148193, + "eval_runtime": 296.8327, + "eval_samples_per_second": 1285.542, + "eval_steps_per_second": 40.174, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749348614975599e-05, + "loss": 4.5204, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748510020224547e-05, + "loss": 4.5122, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747671425473495e-05, + "loss": 4.5327, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746832830722443e-05, + "loss": 4.5205, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745994235971391e-05, + "loss": 4.532, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745155641220339e-05, + "loss": 4.508, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744317046469287e-05, + "loss": 4.5194, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743478451718235e-05, + "loss": 4.5033, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742639856967183e-05, + "loss": 4.5144, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741801262216131e-05, + "loss": 4.5129, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740962667465079e-05, + "loss": 4.5112, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401240727140264e-05, + "loss": 4.5215, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.4955, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384485210922966e-05, + "loss": 4.5135, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376099263412446e-05, + "loss": 4.497, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736771331590192e-05, + "loss": 4.4978, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4982, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.5054, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4969, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.5152, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.5, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4987, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4979, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.5085, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4942, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728390297720791e-05, + "loss": 4.4973, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727551702969739e-05, + "loss": 4.4848, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726714746099061e-05, + "loss": 4.4904, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725876151348009e-05, + "loss": 4.4794, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725037556596957e-05, + "loss": 4.4949, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724198961845904e-05, + "loss": 4.4925, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723360367094852e-05, + "loss": 4.4892, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225217723438e-05, + "loss": 4.496, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721683177592748e-05, + "loss": 4.4847, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720844582841696e-05, + "loss": 4.4851, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720005988090644e-05, + "loss": 4.4873, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719167393339592e-05, + "loss": 4.4811, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71832879858854e-05, + "loss": 4.4732, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717490203837488e-05, + "loss": 4.462, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716651609086437e-05, + "loss": 4.4739, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715814652215758e-05, + "loss": 4.4764, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4798, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4697, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4661, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712461911091923e-05, + "loss": 4.4793, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.4693, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4708, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4641, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091091699680876e-05, + "loss": 4.4519, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082705752170356e-05, + "loss": 4.4816, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4749, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4641, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705756428844253e-05, + "loss": 4.4603, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704917834093201e-05, + "loss": 4.4713, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4507, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.4724, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702402049840045e-05, + "loss": 4.4463, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015634550889924e-05, + "loss": 4.4641, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4698, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4497, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.69904930871621e-05, + "loss": 4.4432, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982107139651573e-05, + "loss": 4.4605, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697372119214106e-05, + "loss": 4.4298, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.4479, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.455, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694857972841323e-05, + "loss": 4.455, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4463, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693180783339219e-05, + "loss": 4.4331, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692342188588167e-05, + "loss": 4.4348, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691505231717488e-05, + "loss": 4.4361, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690666636966436e-05, + "loss": 4.449, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689828042215384e-05, + "loss": 4.4406, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4477, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688152490593653e-05, + "loss": 4.4537, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873138958426014e-05, + "loss": 4.4491, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864753010915494e-05, + "loss": 4.4319, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4385, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4463, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.432, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683124197848087e-05, + "loss": 4.4382, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682285603097035e-05, + "loss": 4.4331, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681447008345983e-05, + "loss": 4.4322, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680608413594931e-05, + "loss": 4.4413, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.4172, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4358, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4258, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.4398, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4308, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675576845088619e-05, + "loss": 4.4277, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674738250337568e-05, + "loss": 4.4228, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.4175, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673061060835464e-05, + "loss": 4.4187, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672222466084412e-05, + "loss": 4.427, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.4356, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4283, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4206, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668869724960576e-05, + "loss": 4.4162, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668031130209524e-05, + "loss": 4.4171, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.4181, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663555785877936e-05, + "loss": 4.4276, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655169838367416e-05, + "loss": 4.4241, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646783890856896e-05, + "loss": 4.4167, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638397943346376e-05, + "loss": 4.4085, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.424, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.4045, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.4138, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.4062, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.4125, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588098637086985e-05, + "loss": 4.4023, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.4137, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.4016, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656297355216288e-05, + "loss": 4.3996, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.4151, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.3968, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.4194, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652944614092454e-05, + "loss": 4.4155, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652106019341402e-05, + "loss": 4.4105, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.65126742459035e-05, + "loss": 4.4003, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650430467719671e-05, + "loss": 4.3991, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649591872968619e-05, + "loss": 4.4015, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648753278217567e-05, + "loss": 4.4004, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.4089, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.393, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646237493964411e-05, + "loss": 4.4033, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645398899213359e-05, + "loss": 4.4014, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644560304462307e-05, + "loss": 4.403, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.3904, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642884752840576e-05, + "loss": 4.3978, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642046158089524e-05, + "loss": 4.3953, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641207563338472e-05, + "loss": 4.3987, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64036896858742e-05, + "loss": 4.3996, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.4078, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638691779085316e-05, + "loss": 4.382, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.3961, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.3993, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.3931, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.3911, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.4002, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633661848459377e-05, + "loss": 4.3903, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632824891588699e-05, + "loss": 4.4058, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631986296837647e-05, + "loss": 4.3805, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631147702086595e-05, + "loss": 4.3939, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630309107335542e-05, + "loss": 4.3899, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629472150464864e-05, + "loss": 4.385, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628633555713812e-05, + "loss": 4.3829, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277949609627597e-05, + "loss": 4.3812, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626956366211707e-05, + "loss": 4.3776, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.3839, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.3831, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.353968620300293, + "eval_runtime": 291.6765, + "eval_samples_per_second": 1308.268, + "eval_steps_per_second": 40.884, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244422198389246e-05, + "loss": 4.3856, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236036250878726e-05, + "loss": 4.3704, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227650303368205e-05, + "loss": 4.3917, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219264355857685e-05, + "loss": 4.3768, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210878408347165e-05, + "loss": 4.3941, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202492460836645e-05, + "loss": 4.3722, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194122892129854e-05, + "loss": 4.381, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185736944619334e-05, + "loss": 4.3631, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.3786, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.3783, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3739, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152193154577254e-05, + "loss": 4.38, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614382358587046e-05, + "loss": 4.3649, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613543763835994e-05, + "loss": 4.3784, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612705169084942e-05, + "loss": 4.3655, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611866574333891e-05, + "loss": 4.3611, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611027979582839e-05, + "loss": 4.3671, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610189384831787e-05, + "loss": 4.371, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609352427961108e-05, + "loss": 4.3658, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608513833210056e-05, + "loss": 4.3813, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607676876339377e-05, + "loss": 4.3698, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606838281588325e-05, + "loss": 4.3733, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605999686837273e-05, + "loss": 4.3646, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605161092086221e-05, + "loss": 4.3745, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604322497335169e-05, + "loss": 4.364, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.60348554046449e-05, + "loss": 4.3688, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602646945713438e-05, + "loss": 4.359, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018083509623864e-05, + "loss": 4.3553, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009697562113344e-05, + "loss": 4.3562, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3639, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.3663, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984539719581783e-05, + "loss": 4.3609, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976153772071257e-05, + "loss": 4.3714, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967767824560737e-05, + "loss": 4.3605, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595939825585395e-05, + "loss": 4.357, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595101230834343e-05, + "loss": 4.3613, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594264273963664e-05, + "loss": 4.3637, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593425679212612e-05, + "loss": 4.345, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.59258708446156e-05, + "loss": 4.3387, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591748489710508e-05, + "loss": 4.3466, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590909894959456e-05, + "loss": 4.3566, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590071300208404e-05, + "loss": 4.3549, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589232705457352e-05, + "loss": 4.3498, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.3399, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587555515955248e-05, + "loss": 4.3559, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586716921204196e-05, + "loss": 4.3499, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585878326453144e-05, + "loss": 4.3505, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585039731702092e-05, + "loss": 4.343, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584204412711786e-05, + "loss": 4.3271, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583365817960734e-05, + "loss": 4.3699, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582527223209682e-05, + "loss": 4.3525, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58168862845863e-05, + "loss": 4.3469, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808500337075786e-05, + "loss": 4.3454, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.3476, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791728442054746e-05, + "loss": 4.3368, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.3501, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774989304641164e-05, + "loss": 4.3313, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766603357130644e-05, + "loss": 4.3431, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758217409620124e-05, + "loss": 4.3573, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3329, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741445514599084e-05, + "loss": 4.3225, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733059567088564e-05, + "loss": 4.3489, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724673619578044e-05, + "loss": 4.3159, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.33, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707901724557004e-05, + "loss": 4.3422, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699515777046484e-05, + "loss": 4.339, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691129829535963e-05, + "loss": 4.3338, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.325, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.3162, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566600474461187e-05, + "loss": 4.3237, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565761879710135e-05, + "loss": 4.3395, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564923284959083e-05, + "loss": 4.3244, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564084690208031e-05, + "loss": 4.3379, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563246095456979e-05, + "loss": 4.3374, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562407500705927e-05, + "loss": 4.3423, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561568905954874e-05, + "loss": 4.3243, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560730311203822e-05, + "loss": 4.3248, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559893354333144e-05, + "loss": 4.337, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559054759582092e-05, + "loss": 4.3201, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.55821616483104e-05, + "loss": 4.3362, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557379207960361e-05, + "loss": 4.3227, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556540613209309e-05, + "loss": 4.3241, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557020184582566e-05, + "loss": 4.3332, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548634237072046e-05, + "loss": 4.3125, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540248289561526e-05, + "loss": 4.3257, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553187872085474e-05, + "loss": 4.3223, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523492773344215e-05, + "loss": 4.33, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515106825833695e-05, + "loss": 4.321, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.3238, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.314, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548996536210587e-05, + "loss": 4.3112, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548157941459535e-05, + "loss": 4.3142, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547319346708483e-05, + "loss": 4.3197, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546480751957431e-05, + "loss": 4.33, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545642157206379e-05, + "loss": 4.3257, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544803562455327e-05, + "loss": 4.3186, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543964967704275e-05, + "loss": 4.3111, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543128010833596e-05, + "loss": 4.3124, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542289416082544e-05, + "loss": 4.3177, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541450821331492e-05, + "loss": 4.3206, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.54061222658044e-05, + "loss": 4.3212, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539773631829388e-05, + "loss": 4.3137, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538935037078336e-05, + "loss": 4.3046, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538096442327284e-05, + "loss": 4.3235, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372578475762326e-05, + "loss": 4.2993, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364208907055535e-05, + "loss": 4.316, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355822959545015e-05, + "loss": 4.303, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347453390838224e-05, + "loss": 4.3123, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339067443327704e-05, + "loss": 4.3023, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330681495817184e-05, + "loss": 4.3106, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532231192711039e-05, + "loss": 4.3046, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531392597959987e-05, + "loss": 4.3015, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530554003208935e-05, + "loss": 4.312, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529715408457883e-05, + "loss": 4.2975, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528876813706831e-05, + "loss": 4.3188, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528038218955779e-05, + "loss": 4.3192, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527199624204728e-05, + "loss": 4.3131, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526361029453675e-05, + "loss": 4.3023, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525524072582997e-05, + "loss": 4.303, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524685477831945e-05, + "loss": 4.3004, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523846883080893e-05, + "loss": 4.3025, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52300828832984e-05, + "loss": 4.3132, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.2911, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521331098827736e-05, + "loss": 4.3057, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.3016, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519655547206005e-05, + "loss": 4.3071, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518816952454953e-05, + "loss": 4.2939, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517978357703902e-05, + "loss": 4.3035, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.51713976295285e-05, + "loss": 4.2952, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516301168201798e-05, + "loss": 4.3089, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515462573450746e-05, + "loss": 4.3023, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146256165800667e-05, + "loss": 4.3134, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137870218290147e-05, + "loss": 4.2867, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129484270779626e-05, + "loss": 4.3027, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121098323269106e-05, + "loss": 4.3068, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.2925, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104342807051795e-05, + "loss": 4.2974, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095956859541275e-05, + "loss": 4.3068, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087570912030755e-05, + "loss": 4.3005, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.3141, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070799017009715e-05, + "loss": 4.2859, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062413069499195e-05, + "loss": 4.3035, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505402712198868e-05, + "loss": 4.2913, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504564117447816e-05, + "loss": 4.2948, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503727160577137e-05, + "loss": 4.294, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502888565826085e-05, + "loss": 4.2873, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502051608955406e-05, + "loss": 4.2857, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501213014204354e-05, + "loss": 4.292, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500374419453302e-05, + "loss": 4.2934, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.271243572235107, + "eval_runtime": 291.4111, + "eval_samples_per_second": 1309.459, + "eval_steps_per_second": 40.922, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49953582470225e-05, + "loss": 4.2932, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498697229951198e-05, + "loss": 4.2801, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497858635200146e-05, + "loss": 4.3016, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497020040449093e-05, + "loss": 4.2886, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496181445698042e-05, + "loss": 4.2995, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.49534285094699e-05, + "loss": 4.2889, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494504256195938e-05, + "loss": 4.2892, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493665661444886e-05, + "loss": 4.2762, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492827066693834e-05, + "loss": 4.2867, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491988471942782e-05, + "loss": 4.2881, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.49114987719173e-05, + "loss": 4.2887, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490311282440678e-05, + "loss": 4.2904, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489474325569999e-05, + "loss": 4.2762, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488635730818947e-05, + "loss": 4.2924, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487797136067895e-05, + "loss": 4.2772, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2724, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2776, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.2844, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2784, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.293, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.2844, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2887, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481088378059479e-05, + "loss": 4.2778, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480249783308427e-05, + "loss": 4.2856, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479414464318121e-05, + "loss": 4.2778, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478575869567069e-05, + "loss": 4.2862, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477737274816017e-05, + "loss": 4.2747, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476898680064965e-05, + "loss": 4.2733, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760600853139126e-05, + "loss": 4.2694, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752214905628606e-05, + "loss": 4.2786, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743828958118086e-05, + "loss": 4.2827, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47354593894113e-05, + "loss": 4.2775, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472707344190078e-05, + "loss": 4.284, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471868749439026e-05, + "loss": 4.2731, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471030154687974e-05, + "loss": 4.2745, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470193197817295e-05, + "loss": 4.2842, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469354603066243e-05, + "loss": 4.2806, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468516008315191e-05, + "loss": 4.2584, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467677413564139e-05, + "loss": 4.2626, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466838818813087e-05, + "loss": 4.2621, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2675, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2785, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2661, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2628, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2737, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461807250306775e-05, + "loss": 4.2665, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.2713, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601316986850446e-05, + "loss": 4.2637, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592947418143655e-05, + "loss": 4.2416, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584561470633135e-05, + "loss": 4.2894, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576191901926344e-05, + "loss": 4.2717, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567805954415824e-05, + "loss": 4.2721, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559420006905304e-05, + "loss": 4.2654, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551034059394784e-05, + "loss": 4.2641, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542648111884264e-05, + "loss": 4.2577, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2664, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525876216863224e-05, + "loss": 4.256, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451750664815644e-05, + "loss": 4.2613, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450912070064592e-05, + "loss": 4.2791, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45007347531354e-05, + "loss": 4.2552, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449234880562488e-05, + "loss": 4.2475, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448396285811436e-05, + "loss": 4.2707, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447557691060384e-05, + "loss": 4.2409, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446719096309331e-05, + "loss": 4.2536, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445880501558279e-05, + "loss": 4.2599, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.2627, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.2553, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2505, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2361, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441690803563766e-05, + "loss": 4.2488, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2598, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2511, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2582, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2631, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2695, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436660872937827e-05, + "loss": 4.2488, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358222781867747e-05, + "loss": 4.2456, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2629, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2404, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2631, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324695370629396e-05, + "loss": 4.2474, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431630942311888e-05, + "loss": 4.2492, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430792347560836e-05, + "loss": 4.2602, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2386, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429115158058732e-05, + "loss": 4.2496, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42827656330768e-05, + "loss": 4.2467, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427437968556628e-05, + "loss": 4.2568, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426599373805576e-05, + "loss": 4.2428, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42576405481527e-05, + "loss": 4.2531, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.2407, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424086865313166e-05, + "loss": 4.2407, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.2375, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2493, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157108106001e-05, + "loss": 4.2561, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.2498, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419893891557907e-05, + "loss": 4.2513, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190569346872276e-05, + "loss": 4.2378, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182199778165485e-05, + "loss": 4.2388, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173813830654965e-05, + "loss": 4.2435, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165427883144445e-05, + "loss": 4.2516, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157041935633925e-05, + "loss": 4.2481, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148655988123405e-05, + "loss": 4.2421, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140270040612885e-05, + "loss": 4.2367, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131884093102365e-05, + "loss": 4.2529, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123498145591845e-05, + "loss": 4.2287, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411511219808132e-05, + "loss": 4.2424, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106742629374534e-05, + "loss": 4.233, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409835668186402e-05, + "loss": 4.2407, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408998711315723e-05, + "loss": 4.2305, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408160116564671e-05, + "loss": 4.2421, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407321521813619e-05, + "loss": 4.2325, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406482927062567e-05, + "loss": 4.2331, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405644332311514e-05, + "loss": 4.2405, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404805737560462e-05, + "loss": 4.2311, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40396714280941e-05, + "loss": 4.2465, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403128548058358e-05, + "loss": 4.25, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402291591187679e-05, + "loss": 4.2409, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401452996436627e-05, + "loss": 4.2378, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400614401685576e-05, + "loss": 4.228, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399775806934524e-05, + "loss": 4.2353, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398937212183472e-05, + "loss": 4.2336, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.39809861743242e-05, + "loss": 4.2487, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397260022681368e-05, + "loss": 4.2197, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396423065810689e-05, + "loss": 4.2393, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395584471059637e-05, + "loss": 4.2333, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394745876308585e-05, + "loss": 4.2381, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393907281557533e-05, + "loss": 4.2288, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930703246868536e-05, + "loss": 4.2359, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922317299358016e-05, + "loss": 4.2263, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913931351847496e-05, + "loss": 4.2402, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905545404336976e-05, + "loss": 4.2385, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389717583563019e-05, + "loss": 4.2419, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388878988811967e-05, + "loss": 4.2223, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388040394060915e-05, + "loss": 4.2366, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387201799309863e-05, + "loss": 4.2404, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386363204558811e-05, + "loss": 4.2278, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385524609807759e-05, + "loss": 4.2323, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.2396, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383847420305655e-05, + "loss": 4.23, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383010463434976e-05, + "loss": 4.2509, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382171868683924e-05, + "loss": 4.223, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381333273932872e-05, + "loss": 4.2361, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.38049467918182e-05, + "loss": 4.2258, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379657722311141e-05, + "loss": 4.2262, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378819127560089e-05, + "loss": 4.2293, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779805328090376e-05, + "loss": 4.2224, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771435759383585e-05, + "loss": 4.2248, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763049811873065e-05, + "loss": 4.2178, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754663864362545e-05, + "loss": 4.2326, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.2147417068481445, + "eval_runtime": 301.4435, + "eval_samples_per_second": 1265.879, + "eval_steps_per_second": 39.56, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746277916852025e-05, + "loss": 4.2297, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737891969341505e-05, + "loss": 4.2153, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372950602183098e-05, + "loss": 4.2339, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721136453124194e-05, + "loss": 4.2283, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712750505613674e-05, + "loss": 4.2325, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370438093690688e-05, + "loss": 4.2232, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369599498939636e-05, + "loss": 4.225, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368760904188584e-05, + "loss": 4.2134, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367922309437533e-05, + "loss": 4.2228, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367083714686481e-05, + "loss": 4.2252, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366245119935428e-05, + "loss": 4.2275, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365406525184376e-05, + "loss": 4.2213, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364569568313698e-05, + "loss": 4.2185, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363730973562645e-05, + "loss": 4.2235, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362892378811593e-05, + "loss": 4.2174, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362053784060541e-05, + "loss": 4.2059, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361215189309489e-05, + "loss": 4.2173, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360376594558437e-05, + "loss": 4.2229, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359537999807385e-05, + "loss": 4.2168, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358699405056333e-05, + "loss": 4.2309, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357860810305281e-05, + "loss": 4.2248, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.35702221555423e-05, + "loss": 4.2285, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356183620803178e-05, + "loss": 4.2146, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355345026052126e-05, + "loss": 4.2214, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354508069181447e-05, + "loss": 4.2157, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536711123107677e-05, + "loss": 4.2268, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528325175597157e-05, + "loss": 4.2138, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519939228086636e-05, + "loss": 4.2101, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511553280576116e-05, + "loss": 4.2091, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503167333065596e-05, + "loss": 4.2192, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494797764358805e-05, + "loss": 4.2181, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486411816848285e-05, + "loss": 4.2198, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478025869337765e-05, + "loss": 4.2215, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346963992182725e-05, + "loss": 4.2167, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346127035312046e-05, + "loss": 4.2153, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345290078441367e-05, + "loss": 4.222, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344451483690315e-05, + "loss": 4.2187, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343612888939263e-05, + "loss": 4.2018, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342774294188211e-05, + "loss": 4.2034, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341935699437159e-05, + "loss": 4.2008, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341097104686107e-05, + "loss": 4.2057, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340258509935055e-05, + "loss": 4.2193, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339419915184003e-05, + "loss": 4.2084, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338581320432951e-05, + "loss": 4.2027, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337744363562272e-05, + "loss": 4.2129, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.33690576881122e-05, + "loss": 4.2043, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360671740601686e-05, + "loss": 4.2132, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352285793091166e-05, + "loss": 4.204, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334389984558064e-05, + "loss": 4.1831, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333551389807012e-05, + "loss": 4.2315, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.33271279505596e-05, + "loss": 4.211, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331874200304908e-05, + "loss": 4.2166, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331037243434229e-05, + "loss": 4.2023, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302002865635504e-05, + "loss": 4.2099, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329363329692871e-05, + "loss": 4.1988, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328524734941819e-05, + "loss": 4.2048, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327687778071141e-05, + "loss": 4.2038, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326849183320089e-05, + "loss": 4.202, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326010588569037e-05, + "loss": 4.2224, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325171993817985e-05, + "loss": 4.1964, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324333399066933e-05, + "loss": 4.1885, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323494804315881e-05, + "loss": 4.2147, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322656209564829e-05, + "loss": 4.1832, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321817614813776e-05, + "loss": 4.1919, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320979020062724e-05, + "loss": 4.2063, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320140425311672e-05, + "loss": 4.2089, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.31930183056062e-05, + "loss": 4.1922, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318463235809568e-05, + "loss": 4.2003, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317624641058516e-05, + "loss": 4.1779, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316787684187838e-05, + "loss": 4.1948, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315949089436786e-05, + "loss": 4.2024, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315110494685734e-05, + "loss": 4.1914, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314271899934682e-05, + "loss": 4.2027, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.31343330518363e-05, + "loss": 4.2037, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312594710432578e-05, + "loss": 4.215, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311756115681526e-05, + "loss": 4.1897, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310917520930474e-05, + "loss": 4.1948, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310078926179422e-05, + "loss": 4.2071, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30924033142837e-05, + "loss": 4.1853, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308401736677318e-05, + "loss": 4.2024, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075647798066386e-05, + "loss": 4.195, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067261850555866e-05, + "loss": 4.192, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058875903045346e-05, + "loss": 4.2059, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050489955534826e-05, + "loss": 4.1845, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042104008024306e-05, + "loss": 4.1904, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033718060513786e-05, + "loss": 4.1949, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025332113003266e-05, + "loss": 4.2008, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016946165492746e-05, + "loss": 4.1893, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008576596785955e-05, + "loss": 4.1969, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000190649275435e-05, + "loss": 4.1806, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991804701764915e-05, + "loss": 4.1878, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983435133058124e-05, + "loss": 4.1848, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975049185547604e-05, + "loss": 4.1929, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966663238037084e-05, + "loss": 4.2058, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958277290526564e-05, + "loss": 4.1926, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294990772181978e-05, + "loss": 4.1963, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294152177430926e-05, + "loss": 4.184, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293313582679874e-05, + "loss": 4.1842, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292474987928822e-05, + "loss": 4.1908, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.29163639317777e-05, + "loss": 4.1984, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290797798426718e-05, + "loss": 4.1919, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289960841556039e-05, + "loss": 4.1953, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289122246804987e-05, + "loss": 4.1845, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288283652053935e-05, + "loss": 4.197, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287445057302883e-05, + "loss": 4.1782, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286606462551831e-05, + "loss": 4.1897, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285769505681152e-05, + "loss": 4.1757, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849309109301e-05, + "loss": 4.192, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284092316179048e-05, + "loss": 4.1791, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832537214279964e-05, + "loss": 4.1857, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824151266769444e-05, + "loss": 4.1799, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2815765319258924e-05, + "loss": 4.1819, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807379371748404e-05, + "loss": 4.1845, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798993424237884e-05, + "loss": 4.1803, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279064023433482e-05, + "loss": 4.1931, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.27822542868243e-05, + "loss": 4.1964, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277388471811751e-05, + "loss": 4.1898, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276549877060699e-05, + "loss": 4.1902, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275711282309647e-05, + "loss": 4.1737, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274872687558595e-05, + "loss": 4.1827, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274034092807543e-05, + "loss": 4.1836, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273195498056492e-05, + "loss": 4.1934, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.27235690330544e-05, + "loss": 4.1665, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271518308554388e-05, + "loss": 4.1865, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270679713803336e-05, + "loss": 4.1842, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269841119052284e-05, + "loss": 4.181, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269002524301231e-05, + "loss": 4.1787, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268163929550179e-05, + "loss": 4.1868, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673286105598735e-05, + "loss": 4.1758, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664900158088215e-05, + "loss": 4.1904, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656514210577695e-05, + "loss": 4.1878, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648128263067175e-05, + "loss": 4.1891, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639742315556655e-05, + "loss": 4.171, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631356368046135e-05, + "loss": 4.184, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622970420535615e-05, + "loss": 4.1881, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614584473025095e-05, + "loss": 4.1772, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260621490431831e-05, + "loss": 4.1814, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597828956807784e-05, + "loss": 4.1867, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589443009297264e-05, + "loss": 4.1836, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581057061786744e-05, + "loss": 4.1958, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572671114276224e-05, + "loss": 4.1768, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256430154556943e-05, + "loss": 4.1831, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255591559805891e-05, + "loss": 4.1776, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254752965054839e-05, + "loss": 4.1794, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253916008184161e-05, + "loss": 4.1755, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253077413433109e-05, + "loss": 4.1722, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252238818682057e-05, + "loss": 4.1775, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251400223931005e-05, + "loss": 4.1676, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250561629179953e-05, + "loss": 4.1845, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.1723713874816895, + "eval_runtime": 299.6223, + "eval_samples_per_second": 1273.573, + "eval_steps_per_second": 39.8, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249723034428901e-05, + "loss": 4.1851, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248884439677849e-05, + "loss": 4.167, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248045844926797e-05, + "loss": 4.1824, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247207250175745e-05, + "loss": 4.1766, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246368655424693e-05, + "loss": 4.1861, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245530060673641e-05, + "loss": 4.175, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244691465922589e-05, + "loss": 4.1773, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243852871171537e-05, + "loss": 4.1632, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243014276420485e-05, + "loss": 4.1741, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242175681669432e-05, + "loss": 4.1754, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241337086918381e-05, + "loss": 4.1779, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240498492167329e-05, + "loss": 4.1733, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.23966153529665e-05, + "loss": 4.1686, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238822940545598e-05, + "loss": 4.1749, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237984345794546e-05, + "loss": 4.1721, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237145751043494e-05, + "loss": 4.1575, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236307156292442e-05, + "loss": 4.1694, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23546856154139e-05, + "loss": 4.1722, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234629966790338e-05, + "loss": 4.1701, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233791372039286e-05, + "loss": 4.1794, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232952777288234e-05, + "loss": 4.1781, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232114182537182e-05, + "loss": 4.1809, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127558778613e-05, + "loss": 4.1641, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230436993035078e-05, + "loss": 4.1735, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296000361643986e-05, + "loss": 4.1697, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228761441413347e-05, + "loss": 4.1776, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227924484542668e-05, + "loss": 4.1653, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227085889791616e-05, + "loss": 4.1661, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226247295040564e-05, + "loss": 4.1635, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225408700289512e-05, + "loss": 4.1666, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224571743418833e-05, + "loss": 4.1676, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223733148667781e-05, + "loss": 4.1751, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222894553916729e-05, + "loss": 4.1748, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222055959165677e-05, + "loss": 4.1725, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221217364414625e-05, + "loss": 4.1667, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220380407543946e-05, + "loss": 4.1713, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219541812792894e-05, + "loss": 4.1749, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187032180418426e-05, + "loss": 4.157, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178646232907906e-05, + "loss": 4.1535, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170260285397386e-05, + "loss": 4.154, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161890716690595e-05, + "loss": 4.1618, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153504769180075e-05, + "loss": 4.1683, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145118821669555e-05, + "loss": 4.1635, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136732874159035e-05, + "loss": 4.1594, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212834692664851e-05, + "loss": 4.1645, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211996097913799e-05, + "loss": 4.1617, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211157503162747e-05, + "loss": 4.1655, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210320546292068e-05, + "loss": 4.159, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094819515410164e-05, + "loss": 4.1383, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2086433567899644e-05, + "loss": 4.1816, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078047620389124e-05, + "loss": 4.1648, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069661672878604e-05, + "loss": 4.174, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061275725368084e-05, + "loss": 4.1585, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052889777857564e-05, + "loss": 4.1609, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204452020915077e-05, + "loss": 4.1557, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203613426164025e-05, + "loss": 4.1574, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202774831412973e-05, + "loss": 4.1609, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201936236661921e-05, + "loss": 4.1534, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201097641910869e-05, + "loss": 4.1777, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200259047159817e-05, + "loss": 4.1534, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199422090289138e-05, + "loss": 4.1431, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198583495538086e-05, + "loss": 4.1693, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197744900787035e-05, + "loss": 4.1401, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196906306035983e-05, + "loss": 4.142, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196067711284931e-05, + "loss": 4.1672, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195230754414252e-05, + "loss": 4.1631, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943921596632e-05, + "loss": 4.1469, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193553564912148e-05, + "loss": 4.1579, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192714970161096e-05, + "loss": 4.1331, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191876375410044e-05, + "loss": 4.1518, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191037780658992e-05, + "loss": 4.1553, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902024616686856e-05, + "loss": 4.152, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893638669176336e-05, + "loss": 4.1569, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885252721665816e-05, + "loss": 4.1602, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768667741553e-05, + "loss": 4.169, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186848082664478e-05, + "loss": 4.1486, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186009487913426e-05, + "loss": 4.1509, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185172531042747e-05, + "loss": 4.162, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184333936291695e-05, + "loss": 4.1437, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183495341540643e-05, + "loss": 4.1585, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182656746789591e-05, + "loss": 4.1521, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181818152038539e-05, + "loss": 4.1471, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180979557287487e-05, + "loss": 4.167, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801409625364344e-05, + "loss": 4.1391, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793023677853824e-05, + "loss": 4.1433, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784637730343304e-05, + "loss": 4.1539, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776251782832784e-05, + "loss": 4.1565, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767865835322264e-05, + "loss": 4.1476, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175949626661548e-05, + "loss": 4.1552, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175111031910496e-05, + "loss": 4.1362, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174272437159444e-05, + "loss": 4.1453, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.1432, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.1509, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171758290786661e-05, + "loss": 4.1618, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170919696035609e-05, + "loss": 4.1488, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170081101284557e-05, + "loss": 4.1536, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169244144413878e-05, + "loss": 4.1436, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168405549662826e-05, + "loss": 4.1421, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167566954911774e-05, + "loss": 4.1454, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166728360160722e-05, + "loss": 4.1586, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658897654096704e-05, + "loss": 4.1508, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650511706586184e-05, + "loss": 4.1529, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642125759075664e-05, + "loss": 4.1399, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633739811565144e-05, + "loss": 4.1527, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1388, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1481, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160861472664104e-05, + "loss": 4.1339, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160022877913052e-05, + "loss": 4.1504, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159184283162e-05, + "loss": 4.1373, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158345688410948e-05, + "loss": 4.1451, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157507093659896e-05, + "loss": 4.1356, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156668498908844e-05, + "loss": 4.1458, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155829904157792e-05, + "loss": 4.1407, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15499130940674e-05, + "loss": 4.1369, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154154352536062e-05, + "loss": 4.1557, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.15331575778501e-05, + "loss": 4.1557, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152478800914331e-05, + "loss": 4.1507, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151640206163279e-05, + "loss": 4.1453, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150801611412227e-05, + "loss": 4.135, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149963016661175e-05, + "loss": 4.1399, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149124421910123e-05, + "loss": 4.1459, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14828582715907e-05, + "loss": 4.1475, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147447232408018e-05, + "loss": 4.1301, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466102755373396e-05, + "loss": 4.1463, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457716807862876e-05, + "loss": 4.1434, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449330860352356e-05, + "loss": 4.142, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1440944912841836e-05, + "loss": 4.139, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432558965331316e-05, + "loss": 4.1439, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424173017820796e-05, + "loss": 4.1343, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415787070310276e-05, + "loss": 4.1519, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1482, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399031554092965e-05, + "loss": 4.1479, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390645606582445e-05, + "loss": 4.1306, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382276037875654e-05, + "loss": 4.1472, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373890090365134e-05, + "loss": 4.1461, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365504142854614e-05, + "loss": 4.1374, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357118195344094e-05, + "loss": 4.145, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134873224783358e-05, + "loss": 4.1437, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134034630032306e-05, + "loss": 4.1427, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133196035281254e-05, + "loss": 4.1555, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132357440530202e-05, + "loss": 4.135, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131520483659523e-05, + "loss": 4.1451, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130681888908471e-05, + "loss": 4.1441, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1411, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12900633728674e-05, + "loss": 4.1328, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128167742535688e-05, + "loss": 4.1311, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1361, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126490553033584e-05, + "loss": 4.1326, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125651958282532e-05, + "loss": 4.143, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.140775680541992, + "eval_runtime": 316.591, + "eval_samples_per_second": 1205.312, + "eval_steps_per_second": 37.667, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248150014118534e-05, + "loss": 4.1417, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1239764066608014e-05, + "loss": 4.1287, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231378119097494e-05, + "loss": 4.1423, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230085503907e-05, + "loss": 4.1393, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121462260288018e-05, + "loss": 4.1463, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120623665536966e-05, + "loss": 4.1365, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119785070785914e-05, + "loss": 4.143, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118946476034862e-05, + "loss": 4.1267, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11810788128381e-05, + "loss": 4.1276, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117269286532758e-05, + "loss": 4.1427, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116432329662079e-05, + "loss": 4.1376, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115593734911027e-05, + "loss": 4.1321, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.1406, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1296, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1287, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.122, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.1308, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.1352, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1277, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.1447, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1411, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10720942528088e-05, + "loss": 4.142, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106370830529828e-05, + "loss": 4.1307, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105532235778776e-05, + "loss": 4.133, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104693641027724e-05, + "loss": 4.1378, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103855046276672e-05, + "loss": 4.1356, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.10301645152562e-05, + "loss": 4.1276, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102177856774568e-05, + "loss": 4.1306, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013408999038896e-05, + "loss": 4.1221, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005023051528376e-05, + "loss": 4.1307, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996637104017856e-05, + "loss": 4.1316, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.136, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979881587800545e-05, + "loss": 4.1381, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971495640290025e-05, + "loss": 4.1356, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963109692779505e-05, + "loss": 4.1327, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954740124072714e-05, + "loss": 4.1321, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946354176562194e-05, + "loss": 4.1379, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937968229051674e-05, + "loss": 4.1217, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929582281541154e-05, + "loss": 4.119, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921196334030634e-05, + "loss": 4.1162, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091281038652012e-05, + "loss": 4.1247, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.09044244390096e-05, + "loss": 4.1261, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089605487030281e-05, + "loss": 4.129, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088768530159602e-05, + "loss": 4.1246, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08792993540855e-05, + "loss": 4.1246, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087091340657498e-05, + "loss": 4.1281, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086252745906446e-05, + "loss": 4.1333, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085414151155394e-05, + "loss": 4.1204, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.1021, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08373696165329e-05, + "loss": 4.1401, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082898366902237e-05, + "loss": 4.1307, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082059772151186e-05, + "loss": 4.1378, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081221177400134e-05, + "loss": 4.124, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080382582649082e-05, + "loss": 4.1241, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.07954398789803e-05, + "loss": 4.1214, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078705393146978e-05, + "loss": 4.12, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077868436276299e-05, + "loss": 4.1286, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077029841525247e-05, + "loss": 4.1117, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076191246774195e-05, + "loss": 4.1438, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075352652023143e-05, + "loss": 4.1244, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745156951524636e-05, + "loss": 4.1029, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736771004014116e-05, + "loss": 4.1332, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728385056503596e-05, + "loss": 4.1073, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0719999108993076e-05, + "loss": 4.1069, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071162954028629e-05, + "loss": 4.1324, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070324359277577e-05, + "loss": 4.1248, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069489040287272e-05, + "loss": 4.1125, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1215, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067811850785167e-05, + "loss": 4.1015, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066973256034115e-05, + "loss": 4.114, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066134661283063e-05, + "loss": 4.1206, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065296066532011e-05, + "loss": 4.1155, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064457471780959e-05, + "loss": 4.1235, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063618877029907e-05, + "loss": 4.1219, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062780282278855e-05, + "loss": 4.1324, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619433254081766e-05, + "loss": 4.1142, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611047306571246e-05, + "loss": 4.1181, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602661359060726e-05, + "loss": 4.1258, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594275411550206e-05, + "loss": 4.111, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585889464039686e-05, + "loss": 4.1241, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577503516529166e-05, + "loss": 4.1195, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569117569018645e-05, + "loss": 4.1111, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560748000311855e-05, + "loss": 4.1322, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552362052801335e-05, + "loss": 4.1051, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543976105290814e-05, + "loss": 4.1079, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535590157780294e-05, + "loss": 4.1231, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527204210269774e-05, + "loss": 4.1199, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518818262759254e-05, + "loss": 4.1132, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510448694052463e-05, + "loss": 4.124, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502062746541943e-05, + "loss": 4.1017, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049367679903143e-05, + "loss": 4.108, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048529085152091e-05, + "loss": 4.1117, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047692128281412e-05, + "loss": 4.1137, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.04685353353036e-05, + "loss": 4.1303, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.1158, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045177981908629e-05, + "loss": 4.1205, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044339387157577e-05, + "loss": 4.1094, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043500792406525e-05, + "loss": 4.1086, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.1131, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1211, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1181, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.04014805128269e-05, + "loss": 4.1204, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393094565316384e-05, + "loss": 4.1099, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038470861780586e-05, + "loss": 4.1142, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037632267029534e-05, + "loss": 4.1105, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036793672278482e-05, + "loss": 4.11, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035956715407803e-05, + "loss": 4.1002, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351181206567506e-05, + "loss": 4.1195, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342795259056986e-05, + "loss": 4.1032, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334409311546466e-05, + "loss": 4.1105, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032603974283968e-05, + "loss": 4.103, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317653795329155e-05, + "loss": 4.1112, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309267847818635e-05, + "loss": 4.108, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030088190030812e-05, + "loss": 4.1047, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02924959527976e-05, + "loss": 4.118, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028411000528708e-05, + "loss": 4.1236, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027572405777656e-05, + "loss": 4.1225, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026733811026604e-05, + "loss": 4.1101, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025896854155925e-05, + "loss": 4.1033, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025058259404873e-05, + "loss": 4.1072, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024221302534194e-05, + "loss": 4.1141, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023382707783142e-05, + "loss": 4.1156, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02254411303209e-05, + "loss": 4.0974, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021705518281038e-05, + "loss": 4.1154, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020866923529986e-05, + "loss": 4.1131, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200299666593075e-05, + "loss": 4.1072, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191913719082555e-05, + "loss": 4.1076, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183527771572035e-05, + "loss": 4.1138, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175141824061515e-05, + "loss": 4.1026, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166755876550995e-05, + "loss": 4.1176, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158369929040475e-05, + "loss": 4.1124, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0149983981529955e-05, + "loss": 4.1178, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141598034019435e-05, + "loss": 4.0979, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013324484411637e-05, + "loss": 4.1156, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012485889660585e-05, + "loss": 4.1152, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011647294909533e-05, + "loss": 4.1071, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010808700158481e-05, + "loss": 4.1118, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009970105407429e-05, + "loss": 4.1095, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009131510656377e-05, + "loss": 4.1128, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008292915905325e-05, + "loss": 4.1261, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007454321154274e-05, + "loss": 4.1004, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006615726403222e-05, + "loss": 4.1157, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005777131652169e-05, + "loss": 4.1115, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004938536901117e-05, + "loss": 4.1086, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004101580030439e-05, + "loss": 4.1027, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003262985279387e-05, + "loss": 4.0967, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002424390528334e-05, + "loss": 4.1068, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001585795777282e-05, + "loss": 4.098, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00074720102623e-05, + "loss": 4.1105, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.117621898651123, + "eval_runtime": 335.8472, + "eval_samples_per_second": 1136.204, + "eval_steps_per_second": 35.507, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999908606275178e-05, + "loss": 4.1061, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999070011524126e-05, + "loss": 4.1014, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998231416773074e-05, + "loss": 4.11, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997392822022022e-05, + "loss": 4.1081, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996554227270971e-05, + "loss": 4.1149, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995715632519919e-05, + "loss": 4.1058, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994877037768867e-05, + "loss": 4.1135, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994038443017815e-05, + "loss": 4.096, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993199848266763e-05, + "loss": 4.0979, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992361253515711e-05, + "loss": 4.1126, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991522658764658e-05, + "loss": 4.1064, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990684064013606e-05, + "loss": 4.1018, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989847107142928e-05, + "loss": 4.1096, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989008512391876e-05, + "loss": 4.0973, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988169917640823e-05, + "loss": 4.1002, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987331322889771e-05, + "loss": 4.0865, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986492728138719e-05, + "loss": 4.1016, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985654133387668e-05, + "loss": 4.1093, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984815538636616e-05, + "loss": 4.0949, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983976943885564e-05, + "loss": 4.1127, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983138349134512e-05, + "loss": 4.1116, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9822997543834597e-05, + "loss": 4.1101, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814611596324077e-05, + "loss": 4.1032, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806225648813557e-05, + "loss": 4.1052, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797856080106766e-05, + "loss": 4.1051, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789486511399975e-05, + "loss": 4.1058, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781100563889455e-05, + "loss": 4.0955, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772714616378935e-05, + "loss": 4.103, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764328668868415e-05, + "loss": 4.0932, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755942721357895e-05, + "loss": 4.0982, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747556773847374e-05, + "loss": 4.1029, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973917082633686e-05, + "loss": 4.1029, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973078487882634e-05, + "loss": 4.1093, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972239893131582e-05, + "loss": 4.1106, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971402936260903e-05, + "loss": 4.0959, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970565979390224e-05, + "loss": 4.1033, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.1077, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.0892, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.0907, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967211600386016e-05, + "loss": 4.0904, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966373005634964e-05, + "loss": 4.0893, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965534410883912e-05, + "loss": 4.0999, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.96469581613286e-05, + "loss": 4.1001, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963858859262181e-05, + "loss": 4.0935, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630202645111295e-05, + "loss": 4.0947, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962181669760077e-05, + "loss": 4.096, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961343075009025e-05, + "loss": 4.1055, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960504480257973e-05, + "loss": 4.0878, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596675233872944e-05, + "loss": 4.0767, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958828928636242e-05, + "loss": 4.1071, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957991971765563e-05, + "loss": 4.0998, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957153377014511e-05, + "loss": 4.1076, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956314782263459e-05, + "loss": 4.0938, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554761875124066e-05, + "loss": 4.0928, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546375927613546e-05, + "loss": 4.0929, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953798998010303e-05, + "loss": 4.0918, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952960403259251e-05, + "loss": 4.0991, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952121808508199e-05, + "loss": 4.0824, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951286489517894e-05, + "loss": 4.1175, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950447894766842e-05, + "loss": 4.0911, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949609300015789e-05, + "loss": 4.0737, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948770705264737e-05, + "loss": 4.104, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947932110513685e-05, + "loss": 4.0833, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947093515762633e-05, + "loss": 4.0754, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946254921011581e-05, + "loss": 4.0997, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945416326260529e-05, + "loss": 4.097, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94457936938985e-05, + "loss": 4.087, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437424125191715e-05, + "loss": 4.0887, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429038177681195e-05, + "loss": 4.0709, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420652230170675e-05, + "loss": 4.0832, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412266282660155e-05, + "loss": 4.0934, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403880335149635e-05, + "loss": 4.0874, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395494387639115e-05, + "loss": 4.0917, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387124818932324e-05, + "loss": 4.089, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378738871421804e-05, + "loss": 4.1035, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937036930271501e-05, + "loss": 4.0868, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936198335520449e-05, + "loss": 4.0887, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935359740769397e-05, + "loss": 4.0942, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934521146018345e-05, + "loss": 4.0854, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933682551267294e-05, + "loss": 4.095, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932843956516242e-05, + "loss": 4.0893, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.93200536176519e-05, + "loss": 4.0856, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931166767014138e-05, + "loss": 4.1013, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930329810143459e-05, + "loss": 4.0769, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929491215392407e-05, + "loss": 4.0814, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928652620641355e-05, + "loss": 4.0914, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927814025890303e-05, + "loss": 4.0908, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926975431139251e-05, + "loss": 4.0797, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926136836388199e-05, + "loss": 4.0948, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92529987951752e-05, + "loss": 4.0797, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924461284766468e-05, + "loss": 4.079, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923622690015416e-05, + "loss": 4.079, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922784095264364e-05, + "loss": 4.0862, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219455005133124e-05, + "loss": 4.1004, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211085436426334e-05, + "loss": 4.0873, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202699488915813e-05, + "loss": 4.0903, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194313541405293e-05, + "loss": 4.082, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918592759389477e-05, + "loss": 4.0797, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917755802518798e-05, + "loss": 4.0829, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916917207767746e-05, + "loss": 4.0935, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916078613016694e-05, + "loss": 4.0897, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915240018265642e-05, + "loss": 4.088, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144014235145896e-05, + "loss": 4.0884, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135628287635375e-05, + "loss": 4.0845, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912724234012486e-05, + "loss": 4.0821, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911885639261434e-05, + "loss": 4.0824, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911048682390755e-05, + "loss": 4.0736, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102133634004496e-05, + "loss": 4.0884, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9093747686493976e-05, + "loss": 4.0765, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085361738983456e-05, + "loss": 4.0809, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9076975791472936e-05, + "loss": 4.0776, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068589843962416e-05, + "loss": 4.0797, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060203896451896e-05, + "loss": 4.0819, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905181794894137e-05, + "loss": 4.0774, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904343200143085e-05, + "loss": 4.0959, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903504605392033e-05, + "loss": 4.0924, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026660106409816e-05, + "loss": 4.0918, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018274158899296e-05, + "loss": 4.0825, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009888211388776e-05, + "loss": 4.08, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001518642681985e-05, + "loss": 4.078, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993132695171465e-05, + "loss": 4.0868, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984746747660945e-05, + "loss": 4.0901, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976360800150425e-05, + "loss": 4.0717, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967991231443634e-05, + "loss": 4.0837, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959605283933114e-05, + "loss": 4.0834, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951219336422594e-05, + "loss": 4.082, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942833388912074e-05, + "loss": 4.0769, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934447441401554e-05, + "loss": 4.0844, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926061493891034e-05, + "loss": 4.0742, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917675546380514e-05, + "loss": 4.0911, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909289598869994e-05, + "loss": 4.0843, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890090365135948e-05, + "loss": 4.0945, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889255046145642e-05, + "loss": 4.0729, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88841645139459e-05, + "loss": 4.0841, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887579494523911e-05, + "loss": 4.0897, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886740899772859e-05, + "loss": 4.0811, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885902305021807e-05, + "loss": 4.0816, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885063710270755e-05, + "loss": 4.084, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884225115519703e-05, + "loss": 4.082, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883386520768651e-05, + "loss": 4.0988, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882547926017599e-05, + "loss": 4.0771, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881709331266547e-05, + "loss": 4.0878, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880870736515495e-05, + "loss": 4.0858, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800321417644434e-05, + "loss": 4.0809, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8791935470133914e-05, + "loss": 4.074, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878354952262339e-05, + "loss": 4.0708, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.87751799539166e-05, + "loss": 4.0765, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876679400640608e-05, + "loss": 4.0785, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875842443769929e-05, + "loss": 4.081, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.097553253173828, + "eval_runtime": 300.4264, + "eval_samples_per_second": 1270.165, + "eval_steps_per_second": 39.694, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875003849018877e-05, + "loss": 4.0787, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874165254267825e-05, + "loss": 4.0747, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873326659516773e-05, + "loss": 4.0784, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724880647657205e-05, + "loss": 4.0859, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716494700146685e-05, + "loss": 4.0915, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870810875263617e-05, + "loss": 4.0796, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869972280512565e-05, + "loss": 4.0827, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869135323641886e-05, + "loss": 4.0713, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868296728890834e-05, + "loss": 4.0719, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867458134139782e-05, + "loss": 4.082, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.86661953938873e-05, + "loss": 4.0818, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865780944637678e-05, + "loss": 4.0751, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649456256473726e-05, + "loss": 4.0847, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641070308963206e-05, + "loss": 4.0724, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632700740256415e-05, + "loss": 4.0727, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624314792745895e-05, + "loss": 4.0577, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615928845235375e-05, + "loss": 4.0801, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607542897724855e-05, + "loss": 4.0811, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599156950214334e-05, + "loss": 4.0672, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590771002703814e-05, + "loss": 4.0833, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582385055193294e-05, + "loss": 4.0839, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573999107682774e-05, + "loss": 4.0853, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565613160172254e-05, + "loss": 4.0784, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557227212661734e-05, + "loss": 4.0792, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8548841265151214e-05, + "loss": 4.0756, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8540455317640694e-05, + "loss": 4.0836, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532069370130174e-05, + "loss": 4.0637, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852369980142338e-05, + "loss": 4.0768, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851531385391286e-05, + "loss": 4.0655, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850692790640234e-05, + "loss": 4.0735, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849854195889182e-05, + "loss": 4.0771, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849015601138131e-05, + "loss": 4.0798, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848178644267452e-05, + "loss": 4.076, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8473400495164e-05, + "loss": 4.0884, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846501454765348e-05, + "loss": 4.072, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845664497894669e-05, + "loss": 4.0782, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84482754102399e-05, + "loss": 4.0828, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843988946272938e-05, + "loss": 4.06, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843150351521886e-05, + "loss": 4.0668, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842311756770834e-05, + "loss": 4.0664, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841473162019782e-05, + "loss": 4.0614, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84063456726873e-05, + "loss": 4.0724, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839795972517678e-05, + "loss": 4.0785, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838957377766626e-05, + "loss": 4.0638, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381187830155743e-05, + "loss": 4.0714, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837281826144895e-05, + "loss": 4.0692, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836443231393843e-05, + "loss": 4.0758, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835604636642791e-05, + "loss": 4.0617, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834766041891739e-05, + "loss": 4.0522, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339274471406866e-05, + "loss": 4.0818, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8330888523896346e-05, + "loss": 4.0753, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832251895518956e-05, + "loss": 4.0874, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831414938648277e-05, + "loss": 4.0662, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830576343897225e-05, + "loss": 4.0665, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829737749146173e-05, + "loss": 4.0695, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828899154395121e-05, + "loss": 4.0638, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.82806055964407e-05, + "loss": 4.0777, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827221964893017e-05, + "loss": 4.0533, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263850080223386e-05, + "loss": 4.0944, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255464132712866e-05, + "loss": 4.0684, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824707818520234e-05, + "loss": 4.0471, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823869223769182e-05, + "loss": 4.0744, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.82303062901813e-05, + "loss": 4.062, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822192034267078e-05, + "loss": 4.0501, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821353439516026e-05, + "loss": 4.0732, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820514844764974e-05, + "loss": 4.0765, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819676250013922e-05, + "loss": 4.0584, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.81883765526287e-05, + "loss": 4.0679, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.817999060511818e-05, + "loss": 4.0448, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171621036411395e-05, + "loss": 4.0592, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163235088900875e-05, + "loss": 4.0661, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154849141390355e-05, + "loss": 4.06, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146463193879835e-05, + "loss": 4.0727, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138077246369315e-05, + "loss": 4.0607, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129707677662524e-05, + "loss": 4.0818, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8121321730152004e-05, + "loss": 4.0628, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8112935782641484e-05, + "loss": 4.066, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8104549835130964e-05, + "loss": 4.0676, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096163887620444e-05, + "loss": 4.06, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8087777940109924e-05, + "loss": 4.0699, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807940837140313e-05, + "loss": 4.0613, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807102242389262e-05, + "loss": 4.0671, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80626364763821e-05, + "loss": 4.072, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805425052887158e-05, + "loss": 4.0614, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804586458136105e-05, + "loss": 4.0503, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803749501265427e-05, + "loss": 4.0638, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802910906514375e-05, + "loss": 4.0704, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802072311763323e-05, + "loss": 4.057, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.80123371701227e-05, + "loss": 4.068, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800396760141592e-05, + "loss": 4.0555, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.79955816539054e-05, + "loss": 4.0565, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798719570639488e-05, + "loss": 4.0561, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797880975888436e-05, + "loss": 4.0621, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797042381137384e-05, + "loss": 4.0735, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796203786386332e-05, + "loss": 4.0648, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79536519163528e-05, + "loss": 4.0671, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794526596884228e-05, + "loss": 4.058, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7936896400135486e-05, + "loss": 4.057, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928510452624966e-05, + "loss": 4.059, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920124505114446e-05, + "loss": 4.0671, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7911738557603926e-05, + "loss": 4.0682, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7903368988897135e-05, + "loss": 4.066, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7894983041386615e-05, + "loss": 4.0633, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886597093876095e-05, + "loss": 4.058, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878211146365575e-05, + "loss": 4.0627, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786984157765879e-05, + "loss": 4.0564, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786145563014827e-05, + "loss": 4.0536, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785306968263775e-05, + "loss": 4.0609, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784468373512723e-05, + "loss": 4.0531, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783629778761671e-05, + "loss": 4.0564, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782791184010619e-05, + "loss": 4.0515, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.78195422713994e-05, + "loss": 4.0549, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781115632388888e-05, + "loss": 4.0609, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780277037637836e-05, + "loss": 4.0527, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779438442886784e-05, + "loss": 4.0683, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778599848135732e-05, + "loss": 4.0671, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777762891265053e-05, + "loss": 4.0713, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776924296514001e-05, + "loss": 4.0599, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776085701762949e-05, + "loss": 4.0577, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7752471070118975e-05, + "loss": 4.0531, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744101501412184e-05, + "loss": 4.0666, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7735715553901664e-05, + "loss": 4.0626, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727329606391144e-05, + "loss": 4.0479, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7718943658880624e-05, + "loss": 4.0603, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7710557711370104e-05, + "loss": 4.0603, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702171763859584e-05, + "loss": 4.0604, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769380219515279e-05, + "loss": 4.0548, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768541624764227e-05, + "loss": 4.0587, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767703030013175e-05, + "loss": 4.0518, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766864435262123e-05, + "loss": 4.0698, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766025840511071e-05, + "loss": 4.0603, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765187245760019e-05, + "loss": 4.0688, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764350288889341e-05, + "loss": 4.0515, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763511694138289e-05, + "loss": 4.0631, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762673099387236e-05, + "loss": 4.0665, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761834504636184e-05, + "loss": 4.0538, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760997547765506e-05, + "loss": 4.0587, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760158953014454e-05, + "loss": 4.0594, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759320358263401e-05, + "loss": 4.0639, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758481763512349e-05, + "loss": 4.0701, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757643168761297e-05, + "loss": 4.0577, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756804574010245e-05, + "loss": 4.0613, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755965979259193e-05, + "loss": 4.0639, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755127384508141e-05, + "loss": 4.0584, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.75428878975709e-05, + "loss": 4.0538, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534518328864107e-05, + "loss": 4.0508, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526132381353586e-05, + "loss": 4.0527, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517746433843066e-05, + "loss": 4.0553, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509360486332546e-05, + "loss": 4.0578, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.081639766693115, + "eval_runtime": 296.2092, + "eval_samples_per_second": 1288.248, + "eval_steps_per_second": 40.259, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7500974538822026e-05, + "loss": 4.0558, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492588591311506e-05, + "loss": 4.0494, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484202643800986e-05, + "loss": 4.0555, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.0613, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0675, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0553, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0606, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744227290624838e-05, + "loss": 4.0503, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433886958737866e-05, + "loss": 4.0488, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425501011227346e-05, + "loss": 4.0558, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417115063716826e-05, + "loss": 4.0626, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408729116206306e-05, + "loss": 4.053, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400359547499515e-05, + "loss": 4.061, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7391973599988995e-05, + "loss": 4.0481, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383587652478475e-05, + "loss": 4.0535, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375201704967955e-05, + "loss": 4.0327, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7366815757457435e-05, + "loss": 4.0589, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358429809946915e-05, + "loss": 4.0574, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350043862436395e-05, + "loss": 4.045, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341657914925875e-05, + "loss": 4.0616, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0632, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324886019904835e-05, + "loss": 4.0623, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316500072394315e-05, + "loss": 4.0547, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308114124883794e-05, + "loss": 4.0572, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729974455617701e-05, + "loss": 4.0558, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729135860866649e-05, + "loss": 4.0592, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282972661155963e-05, + "loss": 4.0417, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274586713645443e-05, + "loss": 4.0542, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726621714493866e-05, + "loss": 4.0466, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725784757623187e-05, + "loss": 4.0477, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724946162872135e-05, + "loss": 4.0554, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724109206001456e-05, + "loss": 4.0573, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723270611250404e-05, + "loss": 4.0552, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722432016499352e-05, + "loss": 4.0638, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7215934217483e-05, + "loss": 4.051, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7207548269972484e-05, + "loss": 4.0582, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199162322461964e-05, + "loss": 4.0618, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719077637495144e-05, + "loss": 4.0385, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718239042744092e-05, + "loss": 4.0407, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717402085873413e-05, + "loss": 4.0462, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716563491122361e-05, + "loss": 4.0363, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7157248963713086e-05, + "loss": 4.0498, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7148863016202566e-05, + "loss": 4.0571, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7140477068692046e-05, + "loss": 4.0423, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132091121181526e-05, + "loss": 4.0494, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7123705173671006e-05, + "loss": 4.051, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115319226160486e-05, + "loss": 4.0523, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71069496574537e-05, + "loss": 4.0402, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709856370994318e-05, + "loss": 4.0317, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709019414123639e-05, + "loss": 4.0571, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708180819372587e-05, + "loss": 4.0557, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707342224621535e-05, + "loss": 4.0661, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706503629870483e-05, + "loss": 4.0459, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705665035119431e-05, + "loss": 4.0432, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704826440368379e-05, + "loss": 4.0474, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703987845617327e-05, + "loss": 4.0401, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703149250866275e-05, + "loss": 4.0571, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702312293995596e-05, + "loss": 4.0263, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701473699244544e-05, + "loss": 4.0738, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006367423738655e-05, + "loss": 4.0486, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997981476228135e-05, + "loss": 4.0254, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989595528717615e-05, + "loss": 4.0506, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981209581207095e-05, + "loss": 4.0394, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972823633696575e-05, + "loss": 4.0286, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964454064989784e-05, + "loss": 4.0525, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956068117479264e-05, + "loss": 4.0519, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947682169968744e-05, + "loss": 4.0357, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939296222458224e-05, + "loss": 4.052, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6930910274947704e-05, + "loss": 4.0237, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6922524327437184e-05, + "loss": 4.0377, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691415475873039e-05, + "loss": 4.0404, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690576881121987e-05, + "loss": 4.043, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689738286370936e-05, + "loss": 4.0461, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688899691619884e-05, + "loss": 4.0399, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688061096868832e-05, + "loss": 4.061, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68722250211778e-05, + "loss": 4.0426, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686383907366727e-05, + "loss": 4.0469, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685545312615675e-05, + "loss": 4.0428, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684708355744997e-05, + "loss": 4.0379, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683869760993945e-05, + "loss": 4.0496, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683031166242892e-05, + "loss": 4.0399, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68219257149184e-05, + "loss": 4.044, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681355614621162e-05, + "loss": 4.0545, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.68051701987011e-05, + "loss": 4.0415, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679678425119058e-05, + "loss": 4.0269, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678839830368006e-05, + "loss": 4.0407, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678001235616954e-05, + "loss": 4.0507, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677164278746275e-05, + "loss": 4.0309, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676325683995223e-05, + "loss": 4.0502, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675487089244171e-05, + "loss": 4.0367, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746484944931187e-05, + "loss": 4.0319, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738115376224396e-05, + "loss": 4.0356, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729729428713876e-05, + "loss": 4.0404, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721343481203356e-05, + "loss": 4.0569, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712973912496565e-05, + "loss": 4.0415, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704587964986045e-05, + "loss": 4.0459, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669620201747553e-05, + "loss": 4.0382, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668781606996501e-05, + "loss": 4.0343, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667943012245449e-05, + "loss": 4.0372, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667104417494397e-05, + "loss": 4.0479, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666267460623718e-05, + "loss": 4.049, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665428865872666e-05, + "loss": 4.0441, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664590271121614e-05, + "loss": 4.0434, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663751676370562e-05, + "loss": 4.0346, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66291308161951e-05, + "loss": 4.043, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662074486868458e-05, + "loss": 4.0368, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661237529997779e-05, + "loss": 4.0339, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660398935246727e-05, + "loss": 4.0382, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659560340495675e-05, + "loss": 4.0354, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658721745744623e-05, + "loss": 4.0372, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578831509935716e-05, + "loss": 4.0301, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570445562425196e-05, + "loss": 4.0315, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562059614914676e-05, + "loss": 4.0382, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553673667404156e-05, + "loss": 4.04, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545304098697365e-05, + "loss": 4.0443, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6536918151186845e-05, + "loss": 4.0459, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6528548582480054e-05, + "loss": 4.053, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6520162634969534e-05, + "loss": 4.0383, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6511776687459014e-05, + "loss": 4.0377, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6503390739948494e-05, + "loss": 4.0327, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495004792437974e-05, + "loss": 4.0444, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6486618844927454e-05, + "loss": 4.0408, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647824927622067e-05, + "loss": 4.0316, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646986332871015e-05, + "loss": 4.0316, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646147738119963e-05, + "loss": 4.0432, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645309143368911e-05, + "loss": 4.0404, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644470548617858e-05, + "loss": 4.0309, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64363359174718e-05, + "loss": 4.0359, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642794996996128e-05, + "loss": 4.036, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641956402245075e-05, + "loss": 4.0442, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641117807494023e-05, + "loss": 4.0436, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640279212742971e-05, + "loss": 4.0468, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639442255872293e-05, + "loss": 4.033, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638603661121241e-05, + "loss": 4.0433, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637765066370189e-05, + "loss": 4.0467, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636926471619137e-05, + "loss": 4.0328, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636087876868085e-05, + "loss": 4.0388, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635249282117033e-05, + "loss": 4.0412, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634410687365981e-05, + "loss": 4.0457, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6335737304953016e-05, + "loss": 4.0483, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327367736246225e-05, + "loss": 4.038, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6318981788735705e-05, + "loss": 4.0416, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310595841225185e-05, + "loss": 4.0449, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6302209893714665e-05, + "loss": 4.0369, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0327, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.0325, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627706842998684e-05, + "loss": 4.0285, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626868248247632e-05, + "loss": 4.0375, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.62602965349658e-05, + "loss": 4.0362, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.068371295928955, + "eval_runtime": 296.9817, + "eval_samples_per_second": 1284.897, + "eval_steps_per_second": 40.154, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625192696625901e-05, + "loss": 4.0342, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624354101874849e-05, + "loss": 4.0336, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623515507123797e-05, + "loss": 4.0368, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622676912372745e-05, + "loss": 4.0398, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621838317621693e-05, + "loss": 4.0467, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.620999722870641e-05, + "loss": 4.0387, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620162765999962e-05, + "loss": 4.0399, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.61932417124891e-05, + "loss": 4.0319, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0257, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0339, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.0463, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6159697922447025e-05, + "loss": 4.0278, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0468, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0253, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.0319, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 4.0176, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0395, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.0372, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101012668677114e-05, + "loss": 4.031, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609262672116659e-05, + "loss": 4.0339, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608424077365607e-05, + "loss": 4.0493, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607587120494928e-05, + "loss": 4.0373, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606750163624249e-05, + "loss": 4.0363, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605911568873198e-05, + "loss": 4.0337, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605072974122146e-05, + "loss": 4.04, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604234379371094e-05, + "loss": 4.0361, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.0278, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602557189868989e-05, + "loss": 4.0323, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601720232998311e-05, + "loss": 4.028, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600881638247259e-05, + "loss": 4.0256, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600043043496206e-05, + "loss": 4.0392, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599204448745154e-05, + "loss": 4.0326, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598367491874476e-05, + "loss": 4.0397, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597528897123424e-05, + "loss": 4.0426, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596690302372372e-05, + "loss": 4.03, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595853345501693e-05, + "loss": 4.0388, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595014750750641e-05, + "loss": 4.0397, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594176155999589e-05, + "loss": 4.0227, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933375612485366e-05, + "loss": 4.0256, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5924989664974846e-05, + "loss": 4.0207, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916603717464326e-05, + "loss": 4.0208, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908217769953806e-05, + "loss": 4.0326, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899831822443286e-05, + "loss": 4.0401, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891445874932766e-05, + "loss": 4.0235, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883059927422245e-05, + "loss": 4.0253, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874673979911725e-05, + "loss": 4.032, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866304411204935e-05, + "loss": 4.0304, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0241, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58495325161839e-05, + "loss": 4.0125, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584114656867338e-05, + "loss": 4.0352, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583276062116286e-05, + "loss": 4.0412, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582437467365234e-05, + "loss": 4.0423, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581598872614182e-05, + "loss": 4.0266, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.58076027786313e-05, + "loss": 4.0234, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579923320992451e-05, + "loss": 4.0275, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579084726241399e-05, + "loss": 4.0196, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57824776937072e-05, + "loss": 4.0409, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577409174619668e-05, + "loss": 4.0121, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576570579868616e-05, + "loss": 4.0494, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575731985117564e-05, + "loss": 4.0312, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5748950282468855e-05, + "loss": 4.0125, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5740564334958335e-05, + "loss": 4.0294, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5732178387447815e-05, + "loss": 4.0219, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5723792439937295e-05, + "loss": 4.0113, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5715406492426775e-05, + "loss": 4.0296, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570702054491625e-05, + "loss": 4.0356, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569863459740573e-05, + "loss": 4.0186, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569024864989521e-05, + "loss": 4.0324, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568186270238469e-05, + "loss": 4.0056, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.56734931336779e-05, + "loss": 4.0205, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566510718616738e-05, + "loss": 4.0217, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565672123865686e-05, + "loss": 4.0261, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564833529114634e-05, + "loss": 4.0237, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563998210124329e-05, + "loss": 4.0227, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563159615373277e-05, + "loss": 4.0412, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562321020622225e-05, + "loss": 4.0274, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561482425871172e-05, + "loss": 4.0274, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.56064383112012e-05, + "loss": 4.0249, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559805236369068e-05, + "loss": 4.022, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558966641618016e-05, + "loss": 4.0305, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558128046866964e-05, + "loss": 4.0214, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557289452115912e-05, + "loss": 4.0226, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556452495245233e-05, + "loss": 4.0357, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555613900494181e-05, + "loss": 4.0264, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554775305743129e-05, + "loss": 4.006, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553936710992077e-05, + "loss": 4.0249, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553098116241026e-05, + "loss": 4.0287, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522611593703466e-05, + "loss": 4.0175, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514225646192946e-05, + "loss": 4.0284, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505839698682426e-05, + "loss": 4.0247, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5497453751171906e-05, + "loss": 4.0115, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5489067803661386e-05, + "loss": 4.0206, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5480681856150866e-05, + "loss": 4.0185, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472295908640346e-05, + "loss": 4.0349, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463909961129826e-05, + "loss": 4.0261, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455540392423035e-05, + "loss": 4.0303, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447170823716244e-05, + "loss": 4.0173, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438784876205724e-05, + "loss": 4.0145, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543039892869521e-05, + "loss": 4.0225, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542201298118469e-05, + "loss": 4.0304, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541362703367417e-05, + "loss": 4.0301, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540524108616365e-05, + "loss": 4.0245, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539685513865313e-05, + "loss": 4.0232, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538846919114261e-05, + "loss": 4.0156, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538009962243582e-05, + "loss": 4.0272, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.53717136749253e-05, + "loss": 4.017, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536334410621851e-05, + "loss": 4.0214, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535495815870799e-05, + "loss": 4.0177, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534657221119747e-05, + "loss": 4.0166, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533818626368695e-05, + "loss": 4.02, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532980031617643e-05, + "loss": 4.01, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5321430747469644e-05, + "loss": 4.0131, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313044799959124e-05, + "loss": 4.024, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5304658852448604e-05, + "loss": 4.0189, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5296272904938084e-05, + "loss": 4.0234, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528788695742756e-05, + "loss": 4.0265, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527951738872077e-05, + "loss": 4.0363, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527113144121025e-05, + "loss": 4.0189, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526274549369973e-05, + "loss": 4.0148, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254359546189206e-05, + "loss": 4.0192, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5245973598678686e-05, + "loss": 4.0249, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.52376040299719e-05, + "loss": 4.0229, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522923446126512e-05, + "loss": 4.0163, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52208485137546e-05, + "loss": 4.0165, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521246256624408e-05, + "loss": 4.0265, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520407661873356e-05, + "loss": 4.0161, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519569067122303e-05, + "loss": 4.0167, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518730472371251e-05, + "loss": 4.0216, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517893515500573e-05, + "loss": 4.018, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517054920749521e-05, + "loss": 4.02, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516216325998468e-05, + "loss": 4.0269, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515377731247416e-05, + "loss": 4.0266, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514539136496364e-05, + "loss": 4.0158, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513700541745312e-05, + "loss": 4.025, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51286194699426e-05, + "loss": 4.0277, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512023352243209e-05, + "loss": 4.0165, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111863953725296e-05, + "loss": 4.0176, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103478006214776e-05, + "loss": 4.0217, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095092058704256e-05, + "loss": 4.0305, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086706111193736e-05, + "loss": 4.0297, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078320163683216e-05, + "loss": 4.022, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069934216172696e-05, + "loss": 4.0199, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061548268662175e-05, + "loss": 4.0277, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053162321151655e-05, + "loss": 4.0215, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044776373641135e-05, + "loss": 4.0127, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036406804934344e-05, + "loss": 4.0181, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028037236227554e-05, + "loss": 4.0078, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501965128871704e-05, + "loss": 4.02, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501126534120652e-05, + "loss": 4.0191, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.056874752044678, + "eval_runtime": 294.558, + "eval_samples_per_second": 1295.47, + "eval_steps_per_second": 40.484, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002879393696e-05, + "loss": 4.0268, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499449344618548e-05, + "loss": 4.0112, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498610749867496e-05, + "loss": 4.0165, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497772155116444e-05, + "loss": 4.0268, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496933560365392e-05, + "loss": 4.0225, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496094965614339e-05, + "loss": 4.0251, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495256370863287e-05, + "loss": 4.0222, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494417776112235e-05, + "loss": 4.0157, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493579181361183e-05, + "loss": 4.0069, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492740586610131e-05, + "loss": 4.0218, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491901991859079e-05, + "loss": 4.0194, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491063397108027e-05, + "loss": 4.0155, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490226440237349e-05, + "loss": 4.0284, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489387845486297e-05, + "loss": 4.0075, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488549250735245e-05, + "loss": 4.0167, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487710655984193e-05, + "loss": 3.9964, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486872061233141e-05, + "loss": 4.0236, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486033466482089e-05, + "loss": 4.0161, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485194871731037e-05, + "loss": 4.0142, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484356276979985e-05, + "loss": 4.0174, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483519320109306e-05, + "loss": 4.0304, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482680725358254e-05, + "loss": 4.0225, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481842130607202e-05, + "loss": 4.0174, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48100353585615e-05, + "loss": 4.0169, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480164941105098e-05, + "loss": 4.0269, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479326346354046e-05, + "loss": 4.0173, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478489389483367e-05, + "loss": 4.0086, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477650794732315e-05, + "loss": 4.0179, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476812199981263e-05, + "loss": 4.0058, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759736052302106e-05, + "loss": 4.0137, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751350104791586e-05, + "loss": 4.0213, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47429805360848e-05, + "loss": 4.0146, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473459458857428e-05, + "loss": 4.0183, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726208641063755e-05, + "loss": 4.0265, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717822693553235e-05, + "loss": 4.0135, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709436746042715e-05, + "loss": 4.0216, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701050798532195e-05, + "loss": 4.0228, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469268122982541e-05, + "loss": 4.0052, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468429528231489e-05, + "loss": 4.0108, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467590933480437e-05, + "loss": 4.0007, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466752338729385e-05, + "loss": 4.0051, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465913743978333e-05, + "loss": 4.0133, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465075149227281e-05, + "loss": 4.0203, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464236554476229e-05, + "loss": 4.0058, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463397959725177e-05, + "loss": 4.0121, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462559364974125e-05, + "loss": 4.0132, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461722408103446e-05, + "loss": 4.0141, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460885451232767e-05, + "loss": 4.0079, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460046856481715e-05, + "loss": 3.9932, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459208261730663e-05, + "loss": 4.0126, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458369666979611e-05, + "loss": 4.0268, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575310722285595e-05, + "loss": 4.0246, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566924774775075e-05, + "loss": 4.0059, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558538827264555e-05, + "loss": 4.0079, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550152879754035e-05, + "loss": 4.0134, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541799689850974e-05, + "loss": 3.9976, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453343012114418e-05, + "loss": 4.0285, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452504417363366e-05, + "loss": 3.9917, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451665822612314e-05, + "loss": 4.0321, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450827227861262e-05, + "loss": 4.013, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44998863311021e-05, + "loss": 3.9963, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449150038359158e-05, + "loss": 4.0101, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448311443608106e-05, + "loss": 4.0078, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447472848857054e-05, + "loss": 3.9928, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446634254106003e-05, + "loss": 4.0112, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445797297235324e-05, + "loss": 4.0168, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444958702484272e-05, + "loss": 4.004, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.44412010773322e-05, + "loss": 4.0122, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443281512982168e-05, + "loss": 3.9891, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442442918231116e-05, + "loss": 4.0023, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441604323480064e-05, + "loss": 4.0032, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440765728729012e-05, + "loss": 4.0116, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439927133977959e-05, + "loss": 4.0056, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439090177107281e-05, + "loss": 4.0085, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438251582356229e-05, + "loss": 4.0219, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437412987605177e-05, + "loss": 4.0095, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436576030734498e-05, + "loss": 4.0096, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435737435983446e-05, + "loss": 4.0089, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434898841232394e-05, + "loss": 4.0045, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340602464813416e-05, + "loss": 4.0138, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433223289610663e-05, + "loss": 4.004, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432384694859611e-05, + "loss": 4.0124, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431546100108559e-05, + "loss": 4.0134, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307075053575065e-05, + "loss": 4.0114, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298689106064545e-05, + "loss": 3.9871, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429031953735776e-05, + "loss": 4.0112, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281933589847234e-05, + "loss": 4.0089, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427354764233672e-05, + "loss": 3.9999, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42651616948262e-05, + "loss": 4.0101, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425677574731568e-05, + "loss": 4.0045, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424840617860889e-05, + "loss": 3.9973, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424002023109837e-05, + "loss": 4.002, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423163428358785e-05, + "loss": 4.0055, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422324833607733e-05, + "loss": 4.0129, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 4.008, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420649281986002e-05, + "loss": 4.0128, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.41981068723495e-05, + "loss": 4.0038, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418972092483898e-05, + "loss": 3.9989, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418133497732846e-05, + "loss": 4.0047, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417294902981794e-05, + "loss": 4.0121, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416456308230742e-05, + "loss": 4.0115, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156177134796905e-05, + "loss": 4.009, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147791187286385e-05, + "loss": 4.0069, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139421618579594e-05, + "loss": 4.0, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131035671069074e-05, + "loss": 4.0112, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122649723558554e-05, + "loss": 4.0013, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114263776048034e-05, + "loss": 4.0043, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4105877828537514e-05, + "loss": 3.9984, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409750825983072e-05, + "loss": 4.0001, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408913869112393e-05, + "loss": 4.0019, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408075274361341e-05, + "loss": 3.9978, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407236679610289e-05, + "loss": 3.9925, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406398084859237e-05, + "loss": 4.0059, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405559490108186e-05, + "loss": 4.0101, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404720895357134e-05, + "loss": 4.0014, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403882300606082e-05, + "loss": 4.0106, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403045343735403e-05, + "loss": 4.0182, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402206748984351e-05, + "loss": 4.0036, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401368154233299e-05, + "loss": 4.0002, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400529559482247e-05, + "loss": 4.0046, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399690964731195e-05, + "loss": 4.0067, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398852369980142e-05, + "loss": 4.0031, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39801377522909e-05, + "loss": 4.0015, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3971768183584117e-05, + "loss": 4.0008, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963382236073596e-05, + "loss": 4.0074, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3954996288563076e-05, + "loss": 3.9971, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946610341052556e-05, + "loss": 4.0067, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 4.0032, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392985482483525e-05, + "loss": 4.0032, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921468877324725e-05, + "loss": 3.9986, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913082929814205e-05, + "loss": 4.0173, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904696982303685e-05, + "loss": 4.0089, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 4.0032, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887925087282645e-05, + "loss": 4.0039, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879539139772125e-05, + "loss": 4.0129, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871153192261605e-05, + "loss": 3.9962, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862783623554814e-05, + "loss": 4.0063, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385441405484803e-05, + "loss": 4.0073, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384602810733751e-05, + "loss": 4.0133, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383764215982699e-05, + "loss": 4.0102, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382925621231647e-05, + "loss": 4.0098, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382087026480595e-05, + "loss": 4.002, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381248431729543e-05, + "loss": 4.0157, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380409836978491e-05, + "loss": 4.0042, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379571242227439e-05, + "loss": 3.9949, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378735923237133e-05, + "loss": 4.0011, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377897328486081e-05, + "loss": 3.9907, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377058733735029e-05, + "loss": 4.0049, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376220138983977e-05, + "loss": 4.0014, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.046821594238281, + "eval_runtime": 292.298, + "eval_samples_per_second": 1305.486, + "eval_steps_per_second": 40.797, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375381544232925e-05, + "loss": 4.0034, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374542949481873e-05, + "loss": 3.9966, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3737043547308215e-05, + "loss": 4.002, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728657599797694e-05, + "loss": 4.0139, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720288031090904e-05, + "loss": 4.0042, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3711902083580384e-05, + "loss": 4.0125, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370353251487359e-05, + "loss": 4.0029, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369514656736307e-05, + "loss": 4.0002, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368676061985255e-05, + "loss": 3.9885, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367837467234203e-05, + "loss": 4.0085, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366998872483151e-05, + "loss": 4.0028, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366160277732099e-05, + "loss": 4.0019, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.36532332086142e-05, + "loss": 4.0133, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364484726110368e-05, + "loss": 3.9863, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363646131359317e-05, + "loss": 3.9987, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362807536608265e-05, + "loss": 3.9878, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361968941857213e-05, + "loss": 4.0033, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361130347106161e-05, + "loss": 4.0019, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360291752355109e-05, + "loss": 3.9948, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359453157604056e-05, + "loss": 4.0065, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358614562853004e-05, + "loss": 4.0119, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357777605982326e-05, + "loss": 4.007, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356939011231273e-05, + "loss": 4.0031, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356100416480221e-05, + "loss": 4.0004, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355261821729169e-05, + "loss": 4.0117, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354423226978117e-05, + "loss": 3.9999, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353584632227065e-05, + "loss": 3.995, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352746037476014e-05, + "loss": 4.0002, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351907442724962e-05, + "loss": 3.9899, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3510704858542826e-05, + "loss": 3.9983, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502335289836035e-05, + "loss": 4.0023, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493949342325515e-05, + "loss": 3.9994, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485563394814995e-05, + "loss": 4.0061, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477177447304475e-05, + "loss": 4.0088, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468791499793955e-05, + "loss": 3.9982, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3460421931087164e-05, + "loss": 4.0076, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452035983576644e-05, + "loss": 4.0091, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443650036066124e-05, + "loss": 3.9899, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435264088555604e-05, + "loss": 3.9955, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342687814104509e-05, + "loss": 3.9834, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341849219353457e-05, + "loss": 3.9929, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 3.9969, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340173667731726e-05, + "loss": 4.0103, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339335072980674e-05, + "loss": 3.9886, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338496478229622e-05, + "loss": 3.9951, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.33765788347857e-05, + "loss": 3.9977, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336819288727518e-05, + "loss": 3.9986, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335982331856839e-05, + "loss": 3.9948, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335143737105787e-05, + "loss": 3.9799, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334305142354735e-05, + "loss": 4.0016, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333466547603683e-05, + "loss": 4.0084, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332627952852631e-05, + "loss": 4.0036, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331789358101579e-05, + "loss": 3.997, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3309524012309004e-05, + "loss": 3.9899, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3301138064798484e-05, + "loss": 4.0011, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3292752117287964e-05, + "loss": 3.982, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3284366169777444e-05, + "loss": 4.012, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327598022226692e-05, + "loss": 3.9799, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.32675942747564e-05, + "loss": 4.0153, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325920832724588e-05, + "loss": 4.0016, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325082237973536e-05, + "loss": 3.9798, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242452811028566e-05, + "loss": 3.9936, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234066863518046e-05, + "loss": 3.9953, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225680916007526e-05, + "loss": 3.9795, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217294968497006e-05, + "loss": 3.9886, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320890902098649e-05, + "loss": 4.0079, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320052307347597e-05, + "loss": 3.9915, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319215350476918e-05, + "loss": 3.9931, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318376755725866e-05, + "loss": 3.977, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317538160974814e-05, + "loss": 3.9901, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316701204104135e-05, + "loss": 3.9874, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315862609353083e-05, + "loss": 3.9974, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315024014602031e-05, + "loss": 3.9898, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314185419850979e-05, + "loss": 3.995, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313346825099927e-05, + "loss": 4.0028, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312508230348875e-05, + "loss": 3.995, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311669635597823e-05, + "loss": 3.9939, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310831040846771e-05, + "loss": 3.9964, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3099940839760926e-05, + "loss": 3.9939, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091554892250406e-05, + "loss": 3.9976, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3083185323543615e-05, + "loss": 3.9885, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074799376033095e-05, + "loss": 3.9953, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066413428522575e-05, + "loss": 4.003, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058043859815784e-05, + "loss": 3.9966, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049657912305264e-05, + "loss": 3.9758, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041271964794744e-05, + "loss": 3.9946, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032886017284224e-05, + "loss": 3.9908, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3024500069773704e-05, + "loss": 3.9915, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016114122263184e-05, + "loss": 3.9917, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3007728174752664e-05, + "loss": 3.9962, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999342227242144e-05, + "loss": 3.9796, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299095627973163e-05, + "loss": 3.9887, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298257033222111e-05, + "loss": 3.9894, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974184384710584e-05, + "loss": 4.001, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2965798437200064e-05, + "loss": 3.993, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2957412489689544e-05, + "loss": 4.0044, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294904292098275e-05, + "loss": 3.984, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294067335227597e-05, + "loss": 3.9866, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293228740476545e-05, + "loss": 3.989, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292390145725493e-05, + "loss": 3.9978, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.29155155097444e-05, + "loss": 3.9967, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290712956223388e-05, + "loss": 3.995, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289874361472337e-05, + "loss": 3.993, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289035766721285e-05, + "loss": 3.9855, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288197171970233e-05, + "loss": 4.001, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287358577219181e-05, + "loss": 3.9846, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286521620348502e-05, + "loss": 3.9901, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.28568302559745e-05, + "loss": 3.9877, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284844430846398e-05, + "loss": 3.9857, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284005836095346e-05, + "loss": 3.9882, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283167241344294e-05, + "loss": 3.9896, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282328646593242e-05, + "loss": 3.9781, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2814916897225626e-05, + "loss": 3.9903, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806530949715106e-05, + "loss": 3.9954, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2798145002204586e-05, + "loss": 3.9868, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2789759054694066e-05, + "loss": 3.9983, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278138948598728e-05, + "loss": 4.0045, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277300353847676e-05, + "loss": 3.9904, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276461759096624e-05, + "loss": 3.9876, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275623164345572e-05, + "loss": 3.9882, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274786207474893e-05, + "loss": 3.9926, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273947612723841e-05, + "loss": 3.9895, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273109017972789e-05, + "loss": 3.988, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272270423221737e-05, + "loss": 3.9862, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271431828470685e-05, + "loss": 3.9965, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270593233719633e-05, + "loss": 3.9882, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269756276848954e-05, + "loss": 3.989, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268917682097902e-05, + "loss": 3.9883, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2680807252272236e-05, + "loss": 3.9891, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672421304761716e-05, + "loss": 3.9843, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664035357251196e-05, + "loss": 4.0018, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2655649409740676e-05, + "loss": 3.9979, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2647263462230156e-05, + "loss": 3.9917, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2638877514719636e-05, + "loss": 3.9898, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630491567209115e-05, + "loss": 3.9972, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262210561969859e-05, + "loss": 3.9891, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261371967218807e-05, + "loss": 3.9918, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2605350103481284e-05, + "loss": 3.992, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596980534774494e-05, + "loss": 4.006, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588594587263974e-05, + "loss": 3.9914, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580208639753453e-05, + "loss": 3.9977, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257182269224294e-05, + "loss": 3.9881, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563436744732413e-05, + "loss": 4.0019, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255505079722189e-05, + "loss": 3.9898, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254666484971137e-05, + "loss": 3.982, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253827890220085e-05, + "loss": 3.9901, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252989295469033e-05, + "loss": 3.9772, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252152338598354e-05, + "loss": 3.9922, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251313743847302e-05, + "loss": 3.9866, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.039783954620361, + "eval_runtime": 287.1795, + "eval_samples_per_second": 1328.754, + "eval_steps_per_second": 41.525, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.25047514909625e-05, + "loss": 3.9889, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249636554345198e-05, + "loss": 3.9859, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248797959594146e-05, + "loss": 3.9865, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247959364843094e-05, + "loss": 4.0012, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247120770092042e-05, + "loss": 3.9916, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246282175340991e-05, + "loss": 4.0022, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245443580589939e-05, + "loss": 3.9879, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244604985838887e-05, + "loss": 3.9842, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243766391087835e-05, + "loss": 3.9807, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242927796336783e-05, + "loss": 3.9921, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.24208920158573e-05, + "loss": 3.9888, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241250606834678e-05, + "loss": 3.9884, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240413649964e-05, + "loss": 4.0038, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239575055212948e-05, + "loss": 3.9764, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238736460461895e-05, + "loss": 3.9816, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237897865710843e-05, + "loss": 3.9768, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237059270959791e-05, + "loss": 3.9857, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236220676208739e-05, + "loss": 3.9917, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235382081457688e-05, + "loss": 3.9834, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234543486706636e-05, + "loss": 3.9902, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233704891955584e-05, + "loss": 4.0, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232866297204532e-05, + "loss": 3.9889, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.23202770245348e-05, + "loss": 3.9924, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231189107702428e-05, + "loss": 3.9848, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303521508317486e-05, + "loss": 4.0006, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295151939610695e-05, + "loss": 3.9861, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286765992100175e-05, + "loss": 3.9835, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278380044589655e-05, + "loss": 3.9853, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2269994097079135e-05, + "loss": 3.9796, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261608149568615e-05, + "loss": 3.9867, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253238580861824e-05, + "loss": 3.9885, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224485263335131e-05, + "loss": 3.9871, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223646668584079e-05, + "loss": 3.9935, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222808073833027e-05, + "loss": 3.9962, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221969479081975e-05, + "loss": 3.986, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221132522211296e-05, + "loss": 3.9938, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220293927460244e-05, + "loss": 3.9924, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219455332709192e-05, + "loss": 3.9794, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21861673795814e-05, + "loss": 3.9833, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217778143207088e-05, + "loss": 3.9694, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216939548456036e-05, + "loss": 3.984, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216100953704984e-05, + "loss": 3.9832, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215262358953931e-05, + "loss": 3.9955, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214423764202879e-05, + "loss": 3.9744, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135884452125745e-05, + "loss": 3.9825, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127498504615225e-05, + "loss": 3.988, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119112557104705e-05, + "loss": 3.9835, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110726609594184e-05, + "loss": 3.9856, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102340662083664e-05, + "loss": 3.9643, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209395471457314e-05, + "loss": 3.9851, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208556876706262e-05, + "loss": 3.9985, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.20771828195521e-05, + "loss": 3.9929, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206879687204158e-05, + "loss": 3.9829, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060427303334787e-05, + "loss": 3.9771, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052041355824267e-05, + "loss": 3.9877, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043655408313746e-05, + "loss": 3.9725, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203526946080323e-05, + "loss": 3.9967, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202689989209644e-05, + "loss": 3.9649, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201853032338966e-05, + "loss": 4.0043, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201014437587914e-05, + "loss": 3.9886, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200175842836861e-05, + "loss": 3.9663, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199337248085809e-05, + "loss": 3.9777, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198498653334757e-05, + "loss": 3.99, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197660058583705e-05, + "loss": 3.9655, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196821463832653e-05, + "loss": 3.9728, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195984506961974e-05, + "loss": 3.9959, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195145912210922e-05, + "loss": 3.9833, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.19430731745987e-05, + "loss": 3.9793, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193468722708819e-05, + "loss": 3.9612, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1926317658381396e-05, + "loss": 3.9765, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917931710870876e-05, + "loss": 3.9727, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909545763360356e-05, + "loss": 3.9886, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1901159815849836e-05, + "loss": 3.9726, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1892773868339316e-05, + "loss": 3.9832, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884404299632525e-05, + "loss": 3.9899, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1876018352122005e-05, + "loss": 3.9858, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867632404611485e-05, + "loss": 3.9763, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859246457100965e-05, + "loss": 3.9805, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850860509590445e-05, + "loss": 3.9854, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842474562079925e-05, + "loss": 3.9856, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834088614569405e-05, + "loss": 3.9755, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182571904586262e-05, + "loss": 3.9794, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181734947715583e-05, + "loss": 3.9863, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180897990844904e-05, + "loss": 3.9856, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180059396093852e-05, + "loss": 3.9644, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792208013428e-05, + "loss": 3.9812, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178382206591748e-05, + "loss": 3.9774, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177543611840696e-05, + "loss": 3.978, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176705017089644e-05, + "loss": 3.9812, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175866422338592e-05, + "loss": 3.9821, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.17502782758754e-05, + "loss": 3.9728, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174189232836488e-05, + "loss": 3.9724, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173350638085436e-05, + "loss": 3.9761, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172512043334384e-05, + "loss": 3.9882, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171673448583332e-05, + "loss": 3.9794, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170838129593026e-05, + "loss": 3.988, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169999534841974e-05, + "loss": 3.9771, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169160940090922e-05, + "loss": 3.9758, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.16832234533987e-05, + "loss": 3.9733, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167483750588818e-05, + "loss": 3.9896, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166645155837766e-05, + "loss": 3.9823, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165808198967087e-05, + "loss": 3.9855, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164969604216035e-05, + "loss": 3.9791, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164131009464983e-05, + "loss": 3.9722, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163292414713931e-05, + "loss": 3.9903, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162453819962879e-05, + "loss": 3.9674, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161616863092201e-05, + "loss": 3.9745, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160778268341149e-05, + "loss": 3.9785, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.159939673590097e-05, + "loss": 3.9701, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159101078839045e-05, + "loss": 3.975, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158262484087992e-05, + "loss": 3.9761, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.15742388933694e-05, + "loss": 3.9658, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156585294585888e-05, + "loss": 3.9819, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155746699834836e-05, + "loss": 3.9773, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154908105083784e-05, + "loss": 3.9789, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154071148213105e-05, + "loss": 3.9879, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153232553462053e-05, + "loss": 3.9898, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152393958711001e-05, + "loss": 3.9806, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1515553639599496e-05, + "loss": 3.9744, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1507184070892705e-05, + "loss": 3.9742, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1498798123382185e-05, + "loss": 3.9791, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1490412175871665e-05, + "loss": 3.975, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1482026228361145e-05, + "loss": 3.9786, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1473656659654354e-05, + "loss": 3.9707, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1465287090947564e-05, + "loss": 3.9856, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456901143437043e-05, + "loss": 3.9732, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448515195926523e-05, + "loss": 3.9781, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1440129248416003e-05, + "loss": 3.9771, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143174330090548e-05, + "loss": 3.9748, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142335735339496e-05, + "loss": 3.9705, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141497140588445e-05, + "loss": 3.9881, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140658545837393e-05, + "loss": 3.985, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139821588966714e-05, + "loss": 3.9837, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.138984632096035e-05, + "loss": 3.9717, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138146037344983e-05, + "loss": 3.9816, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137307442593931e-05, + "loss": 3.9791, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136468847842879e-05, + "loss": 3.9792, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135630253091827e-05, + "loss": 3.9824, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134791658340775e-05, + "loss": 3.9896, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133953063589723e-05, + "loss": 3.9788, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133114468838671e-05, + "loss": 3.9872, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132277511967992e-05, + "loss": 3.9764, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1314389172169404e-05, + "loss": 3.9853, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1306003224658884e-05, + "loss": 3.9748, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1297617277148364e-05, + "loss": 3.9733, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1289231329637844e-05, + "loss": 3.9793, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128086176093105e-05, + "loss": 3.9644, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127247581342053e-05, + "loss": 3.9773, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126408986591001e-05, + "loss": 3.9777, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.032771110534668, + "eval_runtime": 286.4161, + "eval_samples_per_second": 1332.296, + "eval_steps_per_second": 41.635, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125570391839949e-05, + "loss": 3.9743, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.12473343496927e-05, + "loss": 3.9761, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123894840218218e-05, + "loss": 3.9723, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123056245467166e-05, + "loss": 3.9871, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122217650716114e-05, + "loss": 3.9802, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121379055965062e-05, + "loss": 3.9899, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.12054046121401e-05, + "loss": 3.9723, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119703504343332e-05, + "loss": 3.9748, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11886490959228e-05, + "loss": 3.9652, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118026314841228e-05, + "loss": 3.984, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117187720090176e-05, + "loss": 3.9755, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1163507632194966e-05, + "loss": 3.977, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1155138063488175e-05, + "loss": 3.9845, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146768494781384e-05, + "loss": 3.9681, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138382547270864e-05, + "loss": 3.9738, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129996599760344e-05, + "loss": 3.9673, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121610652249824e-05, + "loss": 3.9671, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111322470473931e-05, + "loss": 3.9787, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110483875722879e-05, + "loss": 3.9728, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109645280971827e-05, + "loss": 3.9768, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108806686220775e-05, + "loss": 3.9887, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079680914697224e-05, + "loss": 3.9785, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1071294967186704e-05, + "loss": 3.9802, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1062909019676184e-05, + "loss": 3.976, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10545394509694e-05, + "loss": 3.988, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104615350345887e-05, + "loss": 3.9697, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103776755594835e-05, + "loss": 3.9751, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102938160843783e-05, + "loss": 3.9688, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102099566092731e-05, + "loss": 3.9708, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1012642471024265e-05, + "loss": 3.9755, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1004256523513745e-05, + "loss": 3.9718, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0995870576003225e-05, + "loss": 3.9787, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.09874846284927e-05, + "loss": 3.9817, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097909868098218e-05, + "loss": 3.9797, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970729112275394e-05, + "loss": 3.9755, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09623595435686e-05, + "loss": 3.9806, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095397359605808e-05, + "loss": 3.98, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094558764854756e-05, + "loss": 3.9639, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093720170103704e-05, + "loss": 3.9736, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092881575352652e-05, + "loss": 3.9573, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920429806016e-05, + "loss": 3.9718, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091204385850548e-05, + "loss": 3.9672, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090365791099496e-05, + "loss": 3.9836, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089527196348444e-05, + "loss": 3.9664, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088688601597392e-05, + "loss": 3.9669, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.08785000684634e-05, + "loss": 3.9736, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087011412095288e-05, + "loss": 3.9748, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086174455224609e-05, + "loss": 3.9728, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085335860473557e-05, + "loss": 3.9532, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084498903602878e-05, + "loss": 3.9708, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083660308851826e-05, + "loss": 3.9853, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082821714100774e-05, + "loss": 3.9809, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.081983119349722e-05, + "loss": 3.974, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.08114452459867e-05, + "loss": 3.9662, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080305929847618e-05, + "loss": 3.9796, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079467335096567e-05, + "loss": 3.9592, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078628740345515e-05, + "loss": 3.9833, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077790145594463e-05, + "loss": 3.954, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076951550843411e-05, + "loss": 3.9875, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076112956092359e-05, + "loss": 3.9798, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075274361341306e-05, + "loss": 3.9559, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0744374044706276e-05, + "loss": 3.9672, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0735988097195756e-05, + "loss": 3.978, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0727602149685236e-05, + "loss": 3.9506, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.071921620217471e-05, + "loss": 3.9636, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710846633467925e-05, + "loss": 3.9831, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702460685957405e-05, + "loss": 3.9715, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0694074738446885e-05, + "loss": 3.967, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685688790936365e-05, + "loss": 3.9545, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677302843425845e-05, + "loss": 3.9658, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066893327471906e-05, + "loss": 3.9576, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660547327208534e-05, + "loss": 3.9767, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652161379698014e-05, + "loss": 3.9606, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0643775432187494e-05, + "loss": 3.9731, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063542224228444e-05, + "loss": 3.9774, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062703629477392e-05, + "loss": 3.9734, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.06186503472634e-05, + "loss": 3.9667, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061026439975288e-05, + "loss": 3.9676, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060187845224236e-05, + "loss": 3.9757, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059349250473184e-05, + "loss": 3.9721, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058510655722132e-05, + "loss": 3.966, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.05767206097108e-05, + "loss": 3.9663, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056833466220028e-05, + "loss": 3.9741, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.055996509349349e-05, + "loss": 3.9739, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.05515955247867e-05, + "loss": 3.953, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054320957727618e-05, + "loss": 3.9678, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534823629765656e-05, + "loss": 3.9659, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526437682255136e-05, + "loss": 3.9675, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0518051734744616e-05, + "loss": 3.9701, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.05096657872341e-05, + "loss": 3.9696, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050127983972358e-05, + "loss": 3.9622, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049291027101679e-05, + "loss": 3.9574, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048452432350627e-05, + "loss": 3.9638, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047613837599575e-05, + "loss": 3.9754, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046775242848523e-05, + "loss": 3.9692, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459366480974712e-05, + "loss": 3.9781, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450980533464192e-05, + "loss": 3.9661, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442594585953672e-05, + "loss": 3.9628, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043420863844315e-05, + "loss": 3.962, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042582269093263e-05, + "loss": 3.9784, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041745312222584e-05, + "loss": 3.9686, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.040906717471532e-05, + "loss": 3.9739, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400681227204804e-05, + "loss": 3.9638, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392295279694284e-05, + "loss": 3.9589, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383925710987493e-05, + "loss": 3.9792, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375539763476973e-05, + "loss": 3.9604, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0367153815966453e-05, + "loss": 3.9619, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358767868455933e-05, + "loss": 3.967, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350398299749145e-05, + "loss": 3.9657, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0342012352238625e-05, + "loss": 3.9598, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333626404728105e-05, + "loss": 3.9639, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325240457217585e-05, + "loss": 3.9576, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316854509707065e-05, + "loss": 3.9668, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308468562196545e-05, + "loss": 3.9657, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0300082614686022e-05, + "loss": 3.969, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291696667175502e-05, + "loss": 3.9725, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283327098468718e-05, + "loss": 3.9808, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027494115095819e-05, + "loss": 3.9692, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266571582251407e-05, + "loss": 3.9645, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258185634740887e-05, + "loss": 3.9609, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249799687230367e-05, + "loss": 3.9645, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241413739719843e-05, + "loss": 3.9649, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0233027792209323e-05, + "loss": 3.9674, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022465822350254e-05, + "loss": 3.9602, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216288654795748e-05, + "loss": 3.9734, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207902707285228e-05, + "loss": 3.9639, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019951675977471e-05, + "loss": 3.9698, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019113081226419e-05, + "loss": 3.9622, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0182744864753664e-05, + "loss": 3.9651, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174358917243144e-05, + "loss": 3.959, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0165972969732624e-05, + "loss": 3.9736, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157587022222104e-05, + "loss": 3.9785, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149201074711588e-05, + "loss": 3.9737, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140815127201068e-05, + "loss": 3.9595, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132429179690548e-05, + "loss": 3.9667, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0124043232180028e-05, + "loss": 3.9691, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115673663473237e-05, + "loss": 3.9676, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010732047357018e-05, + "loss": 3.9699, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098934526059665e-05, + "loss": 3.9768, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090548578549138e-05, + "loss": 3.9662, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082162631038618e-05, + "loss": 3.9783, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073776683528098e-05, + "loss": 3.9627, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065390736017578e-05, + "loss": 3.974, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0057004788507058e-05, + "loss": 3.9664, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004861884099654e-05, + "loss": 3.9583, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004023289348602e-05, + "loss": 3.9699, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003186332477923e-05, + "loss": 3.9546, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002347737726871e-05, + "loss": 3.9622, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001509142975819e-05, + "loss": 3.9697, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000670548224767e-05, + "loss": 3.9631, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.026515483856201, + "eval_runtime": 283.6433, + "eval_samples_per_second": 1345.32, + "eval_steps_per_second": 42.042, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999831953473715e-05, + "loss": 3.9621, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.998993358722663e-05, + "loss": 3.963, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981547639716114e-05, + "loss": 3.9734, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973161692205593e-05, + "loss": 3.9679, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964775744695073e-05, + "loss": 3.9804, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956389797184553e-05, + "loss": 3.9627, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9948003849674027e-05, + "loss": 3.9603, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939617902163507e-05, + "loss": 3.9582, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993123195465299e-05, + "loss": 3.968, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992284600714247e-05, + "loss": 3.9643, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991446005963195e-05, + "loss": 3.9663, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990607411212143e-05, + "loss": 3.9703, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989770454341464e-05, + "loss": 3.9569, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.988931859590412e-05, + "loss": 3.9657, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.98809326483936e-05, + "loss": 3.9548, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872546700883082e-05, + "loss": 3.9543, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864160753372562e-05, + "loss": 3.9678, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855774805862042e-05, + "loss": 3.9615, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847388858351522e-05, + "loss": 3.9646, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9839002910841002e-05, + "loss": 3.9801, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830616963330482e-05, + "loss": 3.9652, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822231015819962e-05, + "loss": 3.9689, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813845068309442e-05, + "loss": 3.9644, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805475499602654e-05, + "loss": 3.974, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9797089552092134e-05, + "loss": 3.9608, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788703604581614e-05, + "loss": 3.9646, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780317657071094e-05, + "loss": 3.9572, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771931709560567e-05, + "loss": 3.9616, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976354576205005e-05, + "loss": 3.9593, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975515981453953e-05, + "loss": 3.964, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974677386702901e-05, + "loss": 3.9686, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973840429832222e-05, + "loss": 3.9681, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.97300183508117e-05, + "loss": 3.9678, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972163240330118e-05, + "loss": 3.9668, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713262834594392e-05, + "loss": 3.9637, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704876887083872e-05, + "loss": 3.9718, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696490939573352e-05, + "loss": 3.9559, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688104992062832e-05, + "loss": 3.9612, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679719044552312e-05, + "loss": 3.9484, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671333097041792e-05, + "loss": 3.9583, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662947149531272e-05, + "loss": 3.956, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654577580824484e-05, + "loss": 3.9696, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646191633313964e-05, + "loss": 3.9574, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9637805685803444e-05, + "loss": 3.9569, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629419738292924e-05, + "loss": 3.9653, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9621033790782404e-05, + "loss": 3.9627, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612647843271884e-05, + "loss": 3.9575, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604261895761364e-05, + "loss": 3.9487, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595875948250844e-05, + "loss": 3.9524, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587506379544056e-05, + "loss": 3.9756, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579136810837266e-05, + "loss": 3.9714, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570750863326746e-05, + "loss": 3.9581, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562364915816225e-05, + "loss": 3.9565, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553978968305705e-05, + "loss": 3.9673, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545593020795185e-05, + "loss": 3.9493, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953720707328467e-05, + "loss": 3.9676, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.952882112577415e-05, + "loss": 3.9464, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952043517826363e-05, + "loss": 3.9777, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512049230753102e-05, + "loss": 3.9646, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503679662046318e-05, + "loss": 3.9516, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495293714535798e-05, + "loss": 3.9506, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486907767025278e-05, + "loss": 3.9685, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478521819514754e-05, + "loss": 3.9379, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470135872004234e-05, + "loss": 3.9506, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461749924493714e-05, + "loss": 3.9692, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453363976983194e-05, + "loss": 3.9606, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9444994408276407e-05, + "loss": 3.9557, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436608460765886e-05, + "loss": 3.944, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428222513255366e-05, + "loss": 3.9504, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419836565744846e-05, + "loss": 3.9474, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411450618234326e-05, + "loss": 3.9683, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403064670723806e-05, + "loss": 3.9499, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394695102017015e-05, + "loss": 3.9616, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.93863091545065e-05, + "loss": 3.9623, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937792320699598e-05, + "loss": 3.9678, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936953725948546e-05, + "loss": 3.9523, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361167690778668e-05, + "loss": 3.9602, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352781743268148e-05, + "loss": 3.9627, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344395795757628e-05, + "loss": 3.9618, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9336009848247108e-05, + "loss": 3.9531, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932762390073659e-05, + "loss": 3.9554, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.931923795322607e-05, + "loss": 3.9628, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931086838451928e-05, + "loss": 3.9611, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930248243700876e-05, + "loss": 3.9472, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929409648949824e-05, + "loss": 3.953, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928571054198772e-05, + "loss": 3.956, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92773245944772e-05, + "loss": 3.961, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.926897140457414e-05, + "loss": 3.9555, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926058545706362e-05, + "loss": 3.9589, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.92521995095531e-05, + "loss": 3.9499, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924381356204258e-05, + "loss": 3.9454, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923542761453206e-05, + "loss": 3.9521, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9227041667021545e-05, + "loss": 3.9609, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218655719511025e-05, + "loss": 3.9575, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210269772000505e-05, + "loss": 3.967, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201883824489984e-05, + "loss": 3.9628, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193514255783194e-05, + "loss": 3.9477, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185128308272674e-05, + "loss": 3.9518, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176742360762153e-05, + "loss": 3.961, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168356413251637e-05, + "loss": 3.9629, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159970465741117e-05, + "loss": 3.9617, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151600897034326e-05, + "loss": 3.9544, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143214949523806e-05, + "loss": 3.9508, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134829002013286e-05, + "loss": 3.9677, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126443054502762e-05, + "loss": 3.9469, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9118057106992242e-05, + "loss": 3.9539, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109671159481722e-05, + "loss": 3.9544, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101285211971202e-05, + "loss": 3.9555, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909291564326441e-05, + "loss": 3.9452, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908452969575389e-05, + "loss": 3.9534, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076143748243375e-05, + "loss": 3.947, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067757800732855e-05, + "loss": 3.9578, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059371853222335e-05, + "loss": 3.9522, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9051002284515544e-05, + "loss": 3.9531, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042616337005024e-05, + "loss": 3.9659, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034230389494504e-05, + "loss": 3.971, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025844441983984e-05, + "loss": 3.961, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017458494473463e-05, + "loss": 3.9506, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9009072546962947e-05, + "loss": 3.9507, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000686599452427e-05, + "loss": 3.9527, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992300651941907e-05, + "loss": 3.9602, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983914704431387e-05, + "loss": 3.957, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975561514528325e-05, + "loss": 3.9476, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967175567017808e-05, + "loss": 3.9573, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958789619507288e-05, + "loss": 3.9539, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950403671996768e-05, + "loss": 3.9562, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8942017724486248e-05, + "loss": 3.9517, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933631776975728e-05, + "loss": 3.9555, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925262208268937e-05, + "loss": 3.949, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916876260758417e-05, + "loss": 3.9642, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.89084903132479e-05, + "loss": 3.965, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890010436573738e-05, + "loss": 3.9658, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889171841822686e-05, + "loss": 3.9468, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888334884952007e-05, + "loss": 3.9594, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887496290200955e-05, + "loss": 3.9572, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886657695449903e-05, + "loss": 3.958, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885819100698851e-05, + "loss": 3.9549, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849805059477993e-05, + "loss": 3.9676, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841419111967473e-05, + "loss": 3.9544, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8833033164456953e-05, + "loss": 3.9713, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824647216946426e-05, + "loss": 3.9506, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816261269435906e-05, + "loss": 3.9656, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880789170072912e-05, + "loss": 3.9549, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799522132022334e-05, + "loss": 3.9522, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791136184511814e-05, + "loss": 3.9568, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782750237001294e-05, + "loss": 3.947, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774364289490774e-05, + "loss": 3.9525, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765978341980247e-05, + "loss": 3.9569, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875759239446973e-05, + "loss": 3.9475, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.02132511138916, + "eval_runtime": 293.7865, + "eval_samples_per_second": 1298.872, + "eval_steps_per_second": 40.591, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.874920644695921e-05, + "loss": 3.9539, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740836878252426e-05, + "loss": 3.9521, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.87324509307419e-05, + "loss": 3.9646, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872406498323138e-05, + "loss": 3.9573, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871567903572086e-05, + "loss": 3.9697, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870729308821034e-05, + "loss": 3.9506, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698907140699823e-05, + "loss": 3.9523, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690521193189303e-05, + "loss": 3.9463, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682135245678783e-05, + "loss": 3.9593, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673765676971992e-05, + "loss": 3.9543, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866537972946147e-05, + "loss": 3.9542, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865699378195095e-05, + "loss": 3.9626, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648624213244164e-05, + "loss": 3.9443, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640238265733644e-05, + "loss": 3.9573, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631852318223124e-05, + "loss": 3.9432, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623466370712604e-05, + "loss": 3.9485, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615080423202084e-05, + "loss": 3.953, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8606694475691564e-05, + "loss": 3.949, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8598308528181044e-05, + "loss": 3.9539, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8589938959474256e-05, + "loss": 3.9753, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581553011963736e-05, + "loss": 3.9514, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573167064453216e-05, + "loss": 3.9552, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564781116942696e-05, + "loss": 3.9568, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556395169432176e-05, + "loss": 3.9609, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8548009221921656e-05, + "loss": 3.9552, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539623274411136e-05, + "loss": 3.956, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531237326900613e-05, + "loss": 3.9437, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852286775819383e-05, + "loss": 3.9521, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851448181068331e-05, + "loss": 3.9441, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850609586317278e-05, + "loss": 3.9563, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849770991566226e-05, + "loss": 3.9546, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.848932396815174e-05, + "loss": 3.9554, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480938020641225e-05, + "loss": 3.9623, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472568451934434e-05, + "loss": 3.9525, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846419888322765e-05, + "loss": 3.9605, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845581293571713e-05, + "loss": 3.9581, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844742698820661e-05, + "loss": 3.9493, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8439041040696086e-05, + "loss": 3.9484, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430655093185566e-05, + "loss": 3.939, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422269145675046e-05, + "loss": 3.9485, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413883198164526e-05, + "loss": 3.9499, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405497250654006e-05, + "loss": 3.9588, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397111303143486e-05, + "loss": 3.946, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388725355632966e-05, + "loss": 3.9481, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380339408122446e-05, + "loss": 3.9555, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371953460611926e-05, + "loss": 3.9482, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836358389190514e-05, + "loss": 3.9529, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835519794439462e-05, + "loss": 3.9388, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346828375687828e-05, + "loss": 3.94, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338442428177307e-05, + "loss": 3.9662, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8330056480666787e-05, + "loss": 3.9619, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832167053315627e-05, + "loss": 3.9454, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831328458564575e-05, + "loss": 3.9508, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830489863813523e-05, + "loss": 3.9557, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829651269062471e-05, + "loss": 3.9397, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828812674311419e-05, + "loss": 3.9583, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827974079560367e-05, + "loss": 3.9348, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271354848093147e-05, + "loss": 3.9637, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262968900582627e-05, + "loss": 3.9584, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254599331875843e-05, + "loss": 3.943, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246213384365323e-05, + "loss": 3.9408, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237827436854796e-05, + "loss": 3.9578, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229441489344276e-05, + "loss": 3.9283, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221055541833756e-05, + "loss": 3.9437, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821266959432324e-05, + "loss": 3.9583, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820428364681272e-05, + "loss": 3.9532, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819591407810593e-05, + "loss": 3.9447, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818752813059541e-05, + "loss": 3.9316, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179142183084888e-05, + "loss": 3.9403, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170756235574368e-05, + "loss": 3.9426, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162370288063848e-05, + "loss": 3.9536, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815398434055333e-05, + "loss": 3.9431, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814559839304281e-05, + "loss": 3.9514, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813721244553229e-05, + "loss": 3.9532, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.81288428768255e-05, + "loss": 3.9562, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812045692931498e-05, + "loss": 3.9417, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811207098180446e-05, + "loss": 3.9488, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810368503429394e-05, + "loss": 3.9524, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809529908678342e-05, + "loss": 3.9491, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086913139272904e-05, + "loss": 3.9474, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078527191762384e-05, + "loss": 3.9447, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070141244251857e-05, + "loss": 3.9542, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061771675545073e-05, + "loss": 3.9504, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053385728034553e-05, + "loss": 3.9347, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044999780524033e-05, + "loss": 3.9431, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803661383301351e-05, + "loss": 3.9453, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802822788550299e-05, + "loss": 3.9518, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801984193799247e-05, + "loss": 3.9485, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011472369285685e-05, + "loss": 3.9461, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003102800578894e-05, + "loss": 3.9425, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994716853068374e-05, + "loss": 3.9365, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986330905557857e-05, + "loss": 3.9406, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797794495804733e-05, + "loss": 3.9526, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796955901053681e-05, + "loss": 3.9494, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796117306302629e-05, + "loss": 3.9559, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795278711551577e-05, + "loss": 3.951, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944417546808983e-05, + "loss": 3.9431, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7936031599298463e-05, + "loss": 3.9419, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927645651787943e-05, + "loss": 3.9463, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919259704277423e-05, + "loss": 3.957, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910873756766903e-05, + "loss": 3.9522, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902487809256383e-05, + "loss": 3.9457, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894118240549595e-05, + "loss": 3.9399, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885732293039075e-05, + "loss": 3.9577, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877346345528555e-05, + "loss": 3.9371, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868960398018035e-05, + "loss": 3.9455, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860574450507515e-05, + "loss": 3.9443, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852188502996995e-05, + "loss": 3.9458, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843802555486475e-05, + "loss": 3.9342, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835416607975955e-05, + "loss": 3.9468, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827047039269167e-05, + "loss": 3.9363, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818661091758647e-05, + "loss": 3.9453, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810275144248127e-05, + "loss": 3.9432, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801889196737607e-05, + "loss": 3.9404, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793519628030816e-05, + "loss": 3.9595, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785133680520296e-05, + "loss": 3.9573, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777676411181351e-05, + "loss": 3.9505, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776837816430299e-05, + "loss": 3.9413, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.775999221679247e-05, + "loss": 3.9411, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775160626928195e-05, + "loss": 3.9454, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743236700575158e-05, + "loss": 3.9436, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773485075306464e-05, + "loss": 3.9549, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772646480555412e-05, + "loss": 3.9359, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.77180788580436e-05, + "loss": 3.9466, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.770969291053308e-05, + "loss": 3.9464, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770130696302256e-05, + "loss": 3.9492, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769292101551204e-05, + "loss": 3.9377, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768455144680525e-05, + "loss": 3.9442, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676165499294733e-05, + "loss": 3.9452, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667779551784213e-05, + "loss": 3.9482, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659393604273693e-05, + "loss": 3.9551, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651007656763166e-05, + "loss": 3.9577, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642621709252646e-05, + "loss": 3.9384, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634235761742126e-05, + "loss": 3.9488, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762584981423161e-05, + "loss": 3.9503, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761746386672109e-05, + "loss": 3.9475, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.76090942980143e-05, + "loss": 3.947, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760070835050378e-05, + "loss": 3.9539, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759232240299326e-05, + "loss": 3.9489, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758395283428647e-05, + "loss": 3.961, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757556688677595e-05, + "loss": 3.9422, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756718093926543e-05, + "loss": 3.955, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.755879499175491e-05, + "loss": 3.948, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755040904424439e-05, + "loss": 3.9406, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754202309673387e-05, + "loss": 3.9453, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753365352802708e-05, + "loss": 3.9412, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525267580516563e-05, + "loss": 3.9412, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516881633006043e-05, + "loss": 3.9455, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508495685495523e-05, + "loss": 3.9387, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.016661643981934, + "eval_runtime": 294.0566, + "eval_samples_per_second": 1297.679, + "eval_steps_per_second": 40.553, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500109737985003e-05, + "loss": 3.944, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491723790474483e-05, + "loss": 3.9397, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483337842963963e-05, + "loss": 3.9568, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7474951895453443e-05, + "loss": 3.9449, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466565947942923e-05, + "loss": 3.9638, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458180000432403e-05, + "loss": 3.9401, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.744979405292188e-05, + "loss": 3.9447, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744140810541136e-05, + "loss": 3.9329, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743302215790084e-05, + "loss": 3.9493, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742463621039032e-05, + "loss": 3.9461, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.74162502628798e-05, + "loss": 3.9427, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740786431536928e-05, + "loss": 3.9588, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399494746662492e-05, + "loss": 3.9322, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391108799151972e-05, + "loss": 3.9501, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738272285164145e-05, + "loss": 3.9337, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737433690413093e-05, + "loss": 3.9388, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736595095662041e-05, + "loss": 3.9357, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735756500910989e-05, + "loss": 3.9454, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349195440403104e-05, + "loss": 3.9441, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340809492892584e-05, + "loss": 3.9637, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332423545382064e-05, + "loss": 3.9452, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7324037597871544e-05, + "loss": 3.9448, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315651650361024e-05, + "loss": 3.9469, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307265702850504e-05, + "loss": 3.9526, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298879755339984e-05, + "loss": 3.9427, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290493807829464e-05, + "loss": 3.9476, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282107860318944e-05, + "loss": 3.9371, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727372191280842e-05, + "loss": 3.9414, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.72653359652979e-05, + "loss": 3.9323, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7256966396591116e-05, + "loss": 3.9475, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248580449080596e-05, + "loss": 3.9479, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240210880373805e-05, + "loss": 3.9449, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723182493286329e-05, + "loss": 3.9553, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722343898535277e-05, + "loss": 3.9431, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215069416645978e-05, + "loss": 3.9446, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206683469135457e-05, + "loss": 3.9507, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198297521624937e-05, + "loss": 3.9425, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7189911574114417e-05, + "loss": 3.9378, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181525626603894e-05, + "loss": 3.928, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173139679093374e-05, + "loss": 3.9378, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164753731582854e-05, + "loss": 3.9397, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156367784072334e-05, + "loss": 3.948, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7147981836561814e-05, + "loss": 3.9406, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7139595889051294e-05, + "loss": 3.9349, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7131209941540774e-05, + "loss": 3.9484, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7122823994030254e-05, + "loss": 3.9395, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7114454425323466e-05, + "loss": 3.9384, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106068477812946e-05, + "loss": 3.9336, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097682530302426e-05, + "loss": 3.9288, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089296582791906e-05, + "loss": 3.9566, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080910635281386e-05, + "loss": 3.9509, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072524687770866e-05, + "loss": 3.9377, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064138740260346e-05, + "loss": 3.9387, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705575279274983e-05, + "loss": 3.9482, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047399602846767e-05, + "loss": 3.9274, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7039013655336247e-05, + "loss": 3.9483, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030627707825727e-05, + "loss": 3.9269, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022241760315207e-05, + "loss": 3.9492, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701385581280469e-05, + "loss": 3.9524, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.70054862440979e-05, + "loss": 3.9344, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699710029658738e-05, + "loss": 3.9266, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.698871434907686e-05, + "loss": 3.9483, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698032840156634e-05, + "loss": 3.9204, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697194245405582e-05, + "loss": 3.9375, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.69635565065453e-05, + "loss": 3.9445, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6955170559034783e-05, + "loss": 3.9452, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6946784611524256e-05, + "loss": 3.9364, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938415042817472e-05, + "loss": 3.926, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6930029095306952e-05, + "loss": 3.9275, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692165952660016e-05, + "loss": 3.9294, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913273579089644e-05, + "loss": 3.9453, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904887631579124e-05, + "loss": 3.9342, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896501684068604e-05, + "loss": 3.9428, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888115736558077e-05, + "loss": 3.9464, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879746167851293e-05, + "loss": 3.9474, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871360220340773e-05, + "loss": 3.9301, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862974272830253e-05, + "loss": 3.939, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685458832531973e-05, + "loss": 3.948, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684620237780921e-05, + "loss": 3.9372, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683781643029869e-05, + "loss": 3.9383, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.682943048278817e-05, + "loss": 3.9369, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682104453527765e-05, + "loss": 3.9393, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812674966570862e-05, + "loss": 3.9444, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804289019060342e-05, + "loss": 3.9239, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795903071549822e-05, + "loss": 3.9393, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787517124039302e-05, + "loss": 3.9316, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.677914755533251e-05, + "loss": 3.9444, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677076160782199e-05, + "loss": 3.9369, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762392039115203e-05, + "loss": 3.9356, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6754006091604683e-05, + "loss": 3.9319, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745620144094163e-05, + "loss": 3.9285, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737234196583643e-05, + "loss": 3.9295, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6728848249073123e-05, + "loss": 3.9386, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6720462301562603e-05, + "loss": 3.9517, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6712092732855816e-05, + "loss": 3.9418, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6703706785345296e-05, + "loss": 3.9398, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6695337216638505e-05, + "loss": 3.9312, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6686951269127985e-05, + "loss": 3.9357, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6678565321617465e-05, + "loss": 3.9354, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670179374106945e-05, + "loss": 3.948, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661793426596428e-05, + "loss": 3.9415, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653407479085908e-05, + "loss": 3.9349, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645021531575388e-05, + "loss": 3.9301, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636635584064868e-05, + "loss": 3.9487, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628249636554348e-05, + "loss": 3.9276, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619863689043828e-05, + "loss": 3.9387, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611477741533308e-05, + "loss": 3.9295, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603091794022788e-05, + "loss": 3.9378, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594722225316e-05, + "loss": 3.9262, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658633627780548e-05, + "loss": 3.939, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657795033029496e-05, + "loss": 3.9304, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.656958076158817e-05, + "loss": 3.9315, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656121119288138e-05, + "loss": 3.9389, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655282524537086e-05, + "loss": 3.9274, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654443929786034e-05, + "loss": 3.9498, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653605335034982e-05, + "loss": 3.9485, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.65276674028393e-05, + "loss": 3.9414, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.651928145532878e-05, + "loss": 3.9334, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651089550781826e-05, + "loss": 3.9335, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650252593911147e-05, + "loss": 3.9348, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494139991600954e-05, + "loss": 3.9362, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485754044090434e-05, + "loss": 3.9453, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477368096579914e-05, + "loss": 3.9276, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6468982149069387e-05, + "loss": 3.9386, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460596201558867e-05, + "loss": 3.939, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452210254048347e-05, + "loss": 3.9401, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644382430653783e-05, + "loss": 3.9316, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643545473783104e-05, + "loss": 3.9345, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642706879032052e-05, + "loss": 3.9365, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.641868284281e-05, + "loss": 3.9394, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641029689529948e-05, + "loss": 3.942, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640191094778896e-05, + "loss": 3.9492, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639352500027844e-05, + "loss": 3.9275, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638515543157165e-05, + "loss": 3.9413, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637676948406113e-05, + "loss": 3.9418, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.636838353655061e-05, + "loss": 3.9356, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.635999758904009e-05, + "loss": 3.937, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635161164152957e-05, + "loss": 3.9481, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343242072822784e-05, + "loss": 3.9384, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334856125312264e-05, + "loss": 3.9511, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326470177801744e-05, + "loss": 3.9327, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318084230291224e-05, + "loss": 3.9402, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6309698282780704e-05, + "loss": 3.9393, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6301312335270184e-05, + "loss": 3.9344, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6292926387759664e-05, + "loss": 3.9336, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6284540440249144e-05, + "loss": 3.933, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6276170871542356e-05, + "loss": 3.929, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6267784924031836e-05, + "loss": 3.938, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259415355325045e-05, + "loss": 3.9312, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.012139797210693, + "eval_runtime": 293.7508, + "eval_samples_per_second": 1299.03, + "eval_steps_per_second": 40.596, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6251029407814525e-05, + "loss": 3.9367, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6242643460304005e-05, + "loss": 3.9298, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6234257512793485e-05, + "loss": 3.9467, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6225871565282968e-05, + "loss": 3.9344, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6217485617772448e-05, + "loss": 3.9567, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.620909967026192e-05, + "loss": 3.9328, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.62007137227514e-05, + "loss": 3.9365, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192344154044617e-05, + "loss": 3.9237, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618397458533783e-05, + "loss": 3.9381, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617558863782731e-05, + "loss": 3.9388, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616720269031679e-05, + "loss": 3.9315, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.615881674280627e-05, + "loss": 3.9417, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615044717409948e-05, + "loss": 3.9279, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614206122658896e-05, + "loss": 3.942, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613367527907844e-05, + "loss": 3.9268, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125289331567922e-05, + "loss": 3.9287, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6116903384057395e-05, + "loss": 3.9299, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108517436546875e-05, + "loss": 3.9334, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100131489036355e-05, + "loss": 3.936, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091745541525835e-05, + "loss": 3.9522, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083359594015315e-05, + "loss": 3.9361, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6074973646504798e-05, + "loss": 3.9419, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066587698994278e-05, + "loss": 3.9361, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058201751483758e-05, + "loss": 3.9408, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6049848561580696e-05, + "loss": 3.9328, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041462614070176e-05, + "loss": 3.9393, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603307666655966e-05, + "loss": 3.929, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602469071904914e-05, + "loss": 3.9282, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601632115034235e-05, + "loss": 3.9287, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600793520283183e-05, + "loss": 3.9354, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.599954925532131e-05, + "loss": 3.9405, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599116330781079e-05, + "loss": 3.9354, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598277736030027e-05, + "loss": 3.9477, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974391412789752e-05, + "loss": 3.9343, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596602184408296e-05, + "loss": 3.9336, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595763589657244e-05, + "loss": 3.9406, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.594924994906192e-05, + "loss": 3.9404, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.59408640015514e-05, + "loss": 3.9251, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593247805404088e-05, + "loss": 3.9182, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592409210653036e-05, + "loss": 3.9273, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591570615901984e-05, + "loss": 3.9364, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907320211509324e-05, + "loss": 3.9369, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898934263998804e-05, + "loss": 3.9329, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890548316488284e-05, + "loss": 3.9243, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5882162368977757e-05, + "loss": 3.939, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5873776421467237e-05, + "loss": 3.9307, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865390473956717e-05, + "loss": 3.9323, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5857020905249933e-05, + "loss": 3.9233, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584863495773941e-05, + "loss": 3.9146, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5840265389032625e-05, + "loss": 3.953, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5831879441522105e-05, + "loss": 3.9408, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582349349401158e-05, + "loss": 3.933, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815107546501062e-05, + "loss": 3.9331, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806721598990542e-05, + "loss": 3.9334, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798335651480022e-05, + "loss": 3.9223, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5789949703969502e-05, + "loss": 3.9362, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781563756458982e-05, + "loss": 3.9224, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577319418775219e-05, + "loss": 3.937, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576480824024167e-05, + "loss": 3.948, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756422292731154e-05, + "loss": 3.9259, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748036345220634e-05, + "loss": 3.9147, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739666776513843e-05, + "loss": 3.9419, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731280829003323e-05, + "loss": 3.9128, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5722894881492803e-05, + "loss": 3.9235, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714508933982283e-05, + "loss": 3.94, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706122986471763e-05, + "loss": 3.9347, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697753417764976e-05, + "loss": 3.9279, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689367470254455e-05, + "loss": 3.922, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5680981522743935e-05, + "loss": 3.9128, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672595575233415e-05, + "loss": 3.9215, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664226006526624e-05, + "loss": 3.9379, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5655840059016108e-05, + "loss": 3.9226, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647454111505588e-05, + "loss": 3.9365, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639068163995068e-05, + "loss": 3.9352, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630698595288277e-05, + "loss": 3.9424, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622312647777757e-05, + "loss": 3.9242, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613926700267237e-05, + "loss": 3.9283, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605540752756717e-05, + "loss": 3.9406, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.55971548052462e-05, + "loss": 3.926, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.558876885773568e-05, + "loss": 3.9359, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558038291022516e-05, + "loss": 3.9273, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557201334151837e-05, + "loss": 3.9299, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556362739400785e-05, + "loss": 3.934, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555524144649733e-05, + "loss": 3.919, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554685549898681e-05, + "loss": 3.9278, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538469551476292e-05, + "loss": 3.927, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.55300999827695e-05, + "loss": 3.9348, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552171403525898e-05, + "loss": 3.9293, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551332808774846e-05, + "loss": 3.9311, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550494214023794e-05, + "loss": 3.9245, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496572571531154e-05, + "loss": 3.9185, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488186624020634e-05, + "loss": 3.9232, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479800676510114e-05, + "loss": 3.9292, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471414728999594e-05, + "loss": 3.9427, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5463045160292803e-05, + "loss": 3.9377, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454659212782283e-05, + "loss": 3.9327, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446273265271763e-05, + "loss": 3.9212, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437887317761243e-05, + "loss": 3.925, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5429517749054455e-05, + "loss": 3.9289, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5421131801543935e-05, + "loss": 3.9381, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5412745854033415e-05, + "loss": 3.9336, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540435990652289e-05, + "loss": 3.9299, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539597395901237e-05, + "loss": 3.9219, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538758801150185e-05, + "loss": 3.9433, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.537920206399133e-05, + "loss": 3.9152, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537081611648081e-05, + "loss": 3.9318, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536244654777402e-05, + "loss": 3.9212, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.53540606002635e-05, + "loss": 3.9296, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345674652752984e-05, + "loss": 3.9191, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337288705242464e-05, + "loss": 3.9293, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328902757731944e-05, + "loss": 3.9235, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320533189025153e-05, + "loss": 3.9238, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312163620318362e-05, + "loss": 3.9268, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303777672807845e-05, + "loss": 3.9215, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295391725297325e-05, + "loss": 3.9404, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5287005777786805e-05, + "loss": 3.9413, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278619830276285e-05, + "loss": 3.935, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5270233882765765e-05, + "loss": 3.9246, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5261847935255245e-05, + "loss": 3.9258, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5253461987744725e-05, + "loss": 3.9242, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245092419037934e-05, + "loss": 3.9264, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236706471527417e-05, + "loss": 3.9379, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228320524016897e-05, + "loss": 3.9163, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5219934576506377e-05, + "loss": 3.931, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211548628995857e-05, + "loss": 3.9264, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203179060289066e-05, + "loss": 3.935, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194793112778546e-05, + "loss": 3.9222, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186439922875488e-05, + "loss": 3.9288, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5178053975364968e-05, + "loss": 3.9237, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169668027854448e-05, + "loss": 3.9373, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161282080343928e-05, + "loss": 3.9313, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152896132833408e-05, + "loss": 3.941, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144510185322888e-05, + "loss": 3.9176, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513612423781237e-05, + "loss": 3.9361, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512775466910558e-05, + "loss": 3.9358, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.511936872159506e-05, + "loss": 3.9243, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511098277408454e-05, + "loss": 3.9308, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510259682657402e-05, + "loss": 3.9392, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.50942108790635e-05, + "loss": 3.9341, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508582493155298e-05, + "loss": 3.9448, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077438984042463e-05, + "loss": 3.9229, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5069053036531943e-05, + "loss": 3.9359, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060667089021423e-05, + "loss": 3.9264, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052281141510903e-05, + "loss": 3.928, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043895194000376e-05, + "loss": 3.9286, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035509246489856e-05, + "loss": 3.9241, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027139677783072e-05, + "loss": 3.9212, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.501875373027255e-05, + "loss": 3.9272, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501036778276203e-05, + "loss": 3.9247, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.0086669921875, + "eval_runtime": 292.7915, + "eval_samples_per_second": 1303.286, + "eval_steps_per_second": 40.729, + "step": 1526400 + }, + { + "epoch": 2.0, + "learning_rate": 2.5001998214055244e-05, + "loss": 3.9313, + "step": 1526784 + }, + { + "epoch": 2.0, + "learning_rate": 2.499361226654472e-05, + "loss": 3.9233, + "step": 1527296 + }, + { + "epoch": 2.0, + "learning_rate": 2.49852263190342e-05, + "loss": 3.9391, + "step": 1527808 + }, + { + "epoch": 2.0, + "learning_rate": 2.497684037152368e-05, + "loss": 3.9263, + "step": 1528320 + }, + { + "epoch": 2.0, + "learning_rate": 2.4968454424013164e-05, + "loss": 3.9448, + "step": 1528832 + }, + { + "epoch": 2.0, + "learning_rate": 2.496006847650264e-05, + "loss": 3.9283, + "step": 1529344 + }, + { + "epoch": 2.0, + "learning_rate": 2.495168252899212e-05, + "loss": 3.9265, + "step": 1529856 + }, + { + "epoch": 2.0, + "learning_rate": 2.49432965814816e-05, + "loss": 3.9177, + "step": 1530368 + }, + { + "epoch": 2.0, + "learning_rate": 2.493491063397108e-05, + "loss": 3.929, + "step": 1530880 + }, + { + "epoch": 2.0, + "learning_rate": 2.4926541065264293e-05, + "loss": 3.9306, + "step": 1531392 + }, + { + "epoch": 2.0, + "learning_rate": 2.4918155117753773e-05, + "loss": 3.9275, + "step": 1531904 + }, + { + "epoch": 2.0, + "learning_rate": 2.4909769170243253e-05, + "loss": 3.9324, + "step": 1532416 + }, + { + "epoch": 2.0, + "learning_rate": 2.4901399601536466e-05, + "loss": 3.9197, + "step": 1532928 + }, + { + "epoch": 2.0, + "learning_rate": 2.4893013654025942e-05, + "loss": 3.9344, + "step": 1533440 + }, + { + "epoch": 2.0, + "learning_rate": 2.4884627706515422e-05, + "loss": 3.9181, + "step": 1533952 + }, + { + "epoch": 2.0, + "learning_rate": 2.4876241759004902e-05, + "loss": 3.9176, + "step": 1534464 + }, + { + "epoch": 2.0, + "learning_rate": 2.4867855811494385e-05, + "loss": 3.9218, + "step": 1534976 + }, + { + "epoch": 2.0, + "learning_rate": 2.4859469863983865e-05, + "loss": 3.9281, + "step": 1535488 + }, + { + "epoch": 2.0, + "learning_rate": 2.4851083916473345e-05, + "loss": 3.9257, + "step": 1536000 + }, + { + "epoch": 2.0, + "learning_rate": 2.4842697968962822e-05, + "loss": 3.9424, + "step": 1536512 + }, + { + "epoch": 2.0, + "learning_rate": 2.4834312021452302e-05, + "loss": 3.9303, + "step": 1537024 + }, + { + "epoch": 2.0, + "learning_rate": 2.4825942452745514e-05, + "loss": 3.9364, + "step": 1537536 + }, + { + "epoch": 2.0, + "learning_rate": 2.4817572884038727e-05, + "loss": 3.9262, + "step": 1538048 + }, + { + "epoch": 2.0, + "learning_rate": 2.4809186936528207e-05, + "loss": 3.9301, + "step": 1538560 + }, + { + "epoch": 2.0, + "learning_rate": 2.4800817367821416e-05, + "loss": 3.9258, + "step": 1539072 + }, + { + "epoch": 2.0, + "learning_rate": 2.4792431420310896e-05, + "loss": 3.9341, + "step": 1539584 + }, + { + "epoch": 2.0, + "learning_rate": 2.4784045472800376e-05, + "loss": 3.922, + "step": 1540096 + }, + { + "epoch": 2.0, + "learning_rate": 2.4775659525289856e-05, + "loss": 3.9214, + "step": 1540608 + }, + { + "epoch": 2.0, + "learning_rate": 2.476727357777934e-05, + "loss": 3.9194, + "step": 1541120 + }, + { + "epoch": 2.0, + "learning_rate": 2.475888763026882e-05, + "loss": 3.9238, + "step": 1541632 + }, + { + "epoch": 2.01, + "learning_rate": 2.4750501682758296e-05, + "loss": 3.9328, + "step": 1542144 + }, + { + "epoch": 2.01, + "learning_rate": 2.4742115735247776e-05, + "loss": 3.9278, + "step": 1542656 + }, + { + "epoch": 2.01, + "learning_rate": 2.4733729787737256e-05, + "loss": 3.9381, + "step": 1543168 + }, + { + "epoch": 2.01, + "learning_rate": 2.4725343840226736e-05, + "loss": 3.923, + "step": 1543680 + }, + { + "epoch": 2.01, + "learning_rate": 2.4716957892716215e-05, + "loss": 3.9264, + "step": 1544192 + }, + { + "epoch": 2.01, + "learning_rate": 2.4708588324009428e-05, + "loss": 3.9353, + "step": 1544704 + }, + { + "epoch": 2.01, + "learning_rate": 2.470021875530264e-05, + "loss": 3.9331, + "step": 1545216 + }, + { + "epoch": 2.01, + "learning_rate": 2.469183280779212e-05, + "loss": 3.9124, + "step": 1545728 + }, + { + "epoch": 2.01, + "learning_rate": 2.4683446860281597e-05, + "loss": 3.9176, + "step": 1546240 + }, + { + "epoch": 2.01, + "learning_rate": 2.4675060912771077e-05, + "loss": 3.9178, + "step": 1546752 + }, + { + "epoch": 2.01, + "learning_rate": 2.4666674965260557e-05, + "loss": 3.9224, + "step": 1547264 + }, + { + "epoch": 2.01, + "learning_rate": 2.465828901775004e-05, + "loss": 3.9329, + "step": 1547776 + }, + { + "epoch": 2.01, + "learning_rate": 2.464990307023952e-05, + "loss": 3.9232, + "step": 1548288 + }, + { + "epoch": 2.01, + "learning_rate": 2.464153350153273e-05, + "loss": 3.9197, + "step": 1548800 + }, + { + "epoch": 2.01, + "learning_rate": 2.463314755402221e-05, + "loss": 3.9288, + "step": 1549312 + }, + { + "epoch": 2.01, + "learning_rate": 2.462476160651169e-05, + "loss": 3.9221, + "step": 1549824 + }, + { + "epoch": 2.01, + "learning_rate": 2.461637565900117e-05, + "loss": 3.9266, + "step": 1550336 + }, + { + "epoch": 2.01, + "learning_rate": 2.460798971149065e-05, + "loss": 3.919, + "step": 1550848 + }, + { + "epoch": 2.01, + "learning_rate": 2.459960376398013e-05, + "loss": 3.9009, + "step": 1551360 + }, + { + "epoch": 2.01, + "learning_rate": 2.459121781646961e-05, + "loss": 3.9469, + "step": 1551872 + }, + { + "epoch": 2.01, + "learning_rate": 2.458283186895909e-05, + "loss": 3.9316, + "step": 1552384 + }, + { + "epoch": 2.01, + "learning_rate": 2.457444592144857e-05, + "loss": 3.9297, + "step": 1552896 + }, + { + "epoch": 2.01, + "learning_rate": 2.456605997393805e-05, + "loss": 3.925, + "step": 1553408 + }, + { + "epoch": 2.01, + "learning_rate": 2.455767402642753e-05, + "loss": 3.9252, + "step": 1553920 + }, + { + "epoch": 2.01, + "learning_rate": 2.454928807891701e-05, + "loss": 3.9165, + "step": 1554432 + }, + { + "epoch": 2.01, + "learning_rate": 2.454091851021022e-05, + "loss": 3.9256, + "step": 1554944 + }, + { + "epoch": 2.01, + "learning_rate": 2.45325325626997e-05, + "loss": 3.92, + "step": 1555456 + }, + { + "epoch": 2.01, + "learning_rate": 2.452416299399291e-05, + "loss": 3.9253, + "step": 1555968 + }, + { + "epoch": 2.01, + "learning_rate": 2.451577704648239e-05, + "loss": 3.9393, + "step": 1556480 + }, + { + "epoch": 2.01, + "learning_rate": 2.450739109897187e-05, + "loss": 3.9184, + "step": 1556992 + }, + { + "epoch": 2.01, + "learning_rate": 2.449900515146135e-05, + "loss": 3.9108, + "step": 1557504 + }, + { + "epoch": 2.01, + "learning_rate": 2.4490619203950834e-05, + "loss": 3.9343, + "step": 1558016 + }, + { + "epoch": 2.01, + "learning_rate": 2.448223325644031e-05, + "loss": 3.9037, + "step": 1558528 + }, + { + "epoch": 2.01, + "learning_rate": 2.4473863687733523e-05, + "loss": 3.9185, + "step": 1559040 + }, + { + "epoch": 2.01, + "learning_rate": 2.4465477740223003e-05, + "loss": 3.928, + "step": 1559552 + }, + { + "epoch": 2.01, + "learning_rate": 2.445709179271248e-05, + "loss": 3.9286, + "step": 1560064 + }, + { + "epoch": 2.01, + "learning_rate": 2.444870584520196e-05, + "loss": 3.9211, + "step": 1560576 + }, + { + "epoch": 2.01, + "learning_rate": 2.4440319897691442e-05, + "loss": 3.9166, + "step": 1561088 + }, + { + "epoch": 2.01, + "learning_rate": 2.4431950328984655e-05, + "loss": 3.9025, + "step": 1561600 + }, + { + "epoch": 2.01, + "learning_rate": 2.442356438147413e-05, + "loss": 3.9139, + "step": 1562112 + }, + { + "epoch": 2.01, + "learning_rate": 2.4415194812767344e-05, + "loss": 3.9272, + "step": 1562624 + }, + { + "epoch": 2.01, + "learning_rate": 2.4406808865256824e-05, + "loss": 3.9172, + "step": 1563136 + }, + { + "epoch": 2.01, + "learning_rate": 2.4398422917746304e-05, + "loss": 3.9236, + "step": 1563648 + }, + { + "epoch": 2.01, + "learning_rate": 2.4390036970235784e-05, + "loss": 3.9281, + "step": 1564160 + }, + { + "epoch": 2.01, + "learning_rate": 2.4381651022725264e-05, + "loss": 3.9366, + "step": 1564672 + }, + { + "epoch": 2.01, + "learning_rate": 2.4373265075214744e-05, + "loss": 3.9178, + "step": 1565184 + }, + { + "epoch": 2.01, + "learning_rate": 2.4364879127704224e-05, + "loss": 3.9164, + "step": 1565696 + }, + { + "epoch": 2.01, + "learning_rate": 2.4356493180193704e-05, + "loss": 3.9317, + "step": 1566208 + }, + { + "epoch": 2.01, + "learning_rate": 2.4348107232683184e-05, + "loss": 3.9137, + "step": 1566720 + }, + { + "epoch": 2.01, + "learning_rate": 2.4339721285172664e-05, + "loss": 3.9322, + "step": 1567232 + }, + { + "epoch": 2.01, + "learning_rate": 2.4331335337662143e-05, + "loss": 3.9191, + "step": 1567744 + }, + { + "epoch": 2.01, + "learning_rate": 2.4322965768955356e-05, + "loss": 3.9212, + "step": 1568256 + }, + { + "epoch": 2.01, + "learning_rate": 2.4314579821444836e-05, + "loss": 3.93, + "step": 1568768 + }, + { + "epoch": 2.01, + "learning_rate": 2.4306193873934313e-05, + "loss": 3.9085, + "step": 1569280 + }, + { + "epoch": 2.01, + "learning_rate": 2.4297807926423792e-05, + "loss": 3.9177, + "step": 1569792 + }, + { + "epoch": 2.01, + "learning_rate": 2.4289421978913272e-05, + "loss": 3.919, + "step": 1570304 + }, + { + "epoch": 2.01, + "learning_rate": 2.4281036031402756e-05, + "loss": 3.9284, + "step": 1570816 + }, + { + "epoch": 2.01, + "learning_rate": 2.4272666462695965e-05, + "loss": 3.918, + "step": 1571328 + }, + { + "epoch": 2.01, + "learning_rate": 2.4264280515185445e-05, + "loss": 3.9233, + "step": 1571840 + }, + { + "epoch": 2.02, + "learning_rate": 2.4255894567674925e-05, + "loss": 3.9172, + "step": 1572352 + }, + { + "epoch": 2.02, + "learning_rate": 2.4247508620164405e-05, + "loss": 3.9144, + "step": 1572864 + }, + { + "epoch": 2.02, + "learning_rate": 2.4239139051457617e-05, + "loss": 3.9125, + "step": 1573376 + }, + { + "epoch": 2.02, + "learning_rate": 2.4230753103947097e-05, + "loss": 3.9238, + "step": 1573888 + }, + { + "epoch": 2.02, + "learning_rate": 2.422238353524031e-05, + "loss": 3.9334, + "step": 1574400 + }, + { + "epoch": 2.02, + "learning_rate": 2.4213997587729786e-05, + "loss": 3.9264, + "step": 1574912 + }, + { + "epoch": 2.02, + "learning_rate": 2.4205611640219266e-05, + "loss": 3.93, + "step": 1575424 + }, + { + "epoch": 2.02, + "learning_rate": 2.4197225692708746e-05, + "loss": 3.9137, + "step": 1575936 + }, + { + "epoch": 2.02, + "learning_rate": 2.4188839745198226e-05, + "loss": 3.9173, + "step": 1576448 + }, + { + "epoch": 2.02, + "learning_rate": 2.4180453797687706e-05, + "loss": 3.9206, + "step": 1576960 + }, + { + "epoch": 2.02, + "learning_rate": 2.417206785017719e-05, + "loss": 3.9296, + "step": 1577472 + }, + { + "epoch": 2.02, + "learning_rate": 2.416368190266667e-05, + "loss": 3.9266, + "step": 1577984 + }, + { + "epoch": 2.02, + "learning_rate": 2.4155295955156146e-05, + "loss": 3.9208, + "step": 1578496 + }, + { + "epoch": 2.02, + "learning_rate": 2.414692638644936e-05, + "loss": 3.9176, + "step": 1579008 + }, + { + "epoch": 2.02, + "learning_rate": 2.413854043893884e-05, + "loss": 3.9339, + "step": 1579520 + }, + { + "epoch": 2.02, + "learning_rate": 2.4130154491428318e-05, + "loss": 3.9074, + "step": 1580032 + }, + { + "epoch": 2.02, + "learning_rate": 2.4121768543917798e-05, + "loss": 3.9236, + "step": 1580544 + }, + { + "epoch": 2.02, + "learning_rate": 2.4113382596407278e-05, + "loss": 3.9146, + "step": 1581056 + }, + { + "epoch": 2.02, + "learning_rate": 2.4104996648896758e-05, + "loss": 3.9226, + "step": 1581568 + }, + { + "epoch": 2.02, + "learning_rate": 2.4096610701386238e-05, + "loss": 3.9099, + "step": 1582080 + }, + { + "epoch": 2.02, + "learning_rate": 2.4088241132679447e-05, + "loss": 3.9223, + "step": 1582592 + }, + { + "epoch": 2.02, + "learning_rate": 2.4079855185168927e-05, + "loss": 3.9136, + "step": 1583104 + }, + { + "epoch": 2.02, + "learning_rate": 2.407146923765841e-05, + "loss": 3.9188, + "step": 1583616 + }, + { + "epoch": 2.02, + "learning_rate": 2.406308329014789e-05, + "loss": 3.9188, + "step": 1584128 + }, + { + "epoch": 2.02, + "learning_rate": 2.405469734263737e-05, + "loss": 3.9167, + "step": 1584640 + }, + { + "epoch": 2.02, + "learning_rate": 2.404632777393058e-05, + "loss": 3.931, + "step": 1585152 + }, + { + "epoch": 2.02, + "learning_rate": 2.403794182642006e-05, + "loss": 3.9327, + "step": 1585664 + }, + { + "epoch": 2.02, + "learning_rate": 2.402955587890954e-05, + "loss": 3.9235, + "step": 1586176 + }, + { + "epoch": 2.02, + "learning_rate": 2.402116993139902e-05, + "loss": 3.9223, + "step": 1586688 + }, + { + "epoch": 2.02, + "learning_rate": 2.40127839838885e-05, + "loss": 3.9139, + "step": 1587200 + }, + { + "epoch": 2.02, + "learning_rate": 2.400439803637798e-05, + "loss": 3.9197, + "step": 1587712 + }, + { + "epoch": 2.02, + "learning_rate": 2.399601208886746e-05, + "loss": 3.9187, + "step": 1588224 + }, + { + "epoch": 2.02, + "learning_rate": 2.3987642520160672e-05, + "loss": 3.9336, + "step": 1588736 + }, + { + "epoch": 2.02, + "learning_rate": 2.397925657265015e-05, + "loss": 3.9057, + "step": 1589248 + }, + { + "epoch": 2.02, + "learning_rate": 2.3970870625139628e-05, + "loss": 3.9238, + "step": 1589760 + }, + { + "epoch": 2.02, + "learning_rate": 2.396248467762911e-05, + "loss": 3.9181, + "step": 1590272 + }, + { + "epoch": 2.02, + "learning_rate": 2.395411510892232e-05, + "loss": 3.9255, + "step": 1590784 + }, + { + "epoch": 2.02, + "learning_rate": 2.39457291614118e-05, + "loss": 3.9173, + "step": 1591296 + }, + { + "epoch": 2.02, + "learning_rate": 2.393734321390128e-05, + "loss": 3.9209, + "step": 1591808 + }, + { + "epoch": 2.02, + "learning_rate": 2.3928973645194493e-05, + "loss": 3.9143, + "step": 1592320 + }, + { + "epoch": 2.02, + "learning_rate": 2.3920587697683973e-05, + "loss": 3.9281, + "step": 1592832 + }, + { + "epoch": 2.02, + "learning_rate": 2.3912201750173453e-05, + "loss": 3.928, + "step": 1593344 + }, + { + "epoch": 2.02, + "learning_rate": 2.3903815802662933e-05, + "loss": 3.9304, + "step": 1593856 + }, + { + "epoch": 2.02, + "learning_rate": 2.3895429855152413e-05, + "loss": 3.9137, + "step": 1594368 + }, + { + "epoch": 2.02, + "learning_rate": 2.3887043907641893e-05, + "loss": 3.9278, + "step": 1594880 + }, + { + "epoch": 2.02, + "learning_rate": 2.3878657960131373e-05, + "loss": 3.927, + "step": 1595392 + }, + { + "epoch": 2.02, + "learning_rate": 2.3870272012620853e-05, + "loss": 3.9179, + "step": 1595904 + }, + { + "epoch": 2.02, + "learning_rate": 2.386188606511033e-05, + "loss": 3.9225, + "step": 1596416 + }, + { + "epoch": 2.02, + "learning_rate": 2.3853500117599813e-05, + "loss": 3.9296, + "step": 1596928 + }, + { + "epoch": 2.02, + "learning_rate": 2.3845114170089293e-05, + "loss": 3.9236, + "step": 1597440 + }, + { + "epoch": 2.02, + "learning_rate": 2.3836728222578773e-05, + "loss": 3.9388, + "step": 1597952 + }, + { + "epoch": 2.02, + "learning_rate": 2.3828342275068253e-05, + "loss": 3.9153, + "step": 1598464 + }, + { + "epoch": 2.02, + "learning_rate": 2.381997270636146e-05, + "loss": 3.9264, + "step": 1598976 + }, + { + "epoch": 2.02, + "learning_rate": 2.381158675885094e-05, + "loss": 3.9196, + "step": 1599488 + }, + { + "epoch": 2.02, + "learning_rate": 2.380320081134042e-05, + "loss": 3.9209, + "step": 1600000 + }, + { + "epoch": 2.02, + "learning_rate": 2.3794814863829905e-05, + "loss": 3.9249, + "step": 1600512 + }, + { + "epoch": 2.02, + "learning_rate": 2.3786445295123114e-05, + "loss": 3.9162, + "step": 1601024 + }, + { + "epoch": 2.02, + "learning_rate": 2.3778059347612594e-05, + "loss": 3.9162, + "step": 1601536 + }, + { + "epoch": 2.02, + "learning_rate": 2.3769673400102074e-05, + "loss": 3.9124, + "step": 1602048 + }, + { + "epoch": 2.02, + "learning_rate": 2.3761287452591554e-05, + "loss": 3.9214, + "step": 1602560 + }, + { + "epoch": 2.03, + "eval_loss": 4.004925727844238, + "eval_runtime": 293.8521, + "eval_samples_per_second": 1298.582, + "eval_steps_per_second": 40.582, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3752917883884766e-05, + "loss": 3.9227, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744531936374246e-05, + "loss": 3.9129, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736145988863726e-05, + "loss": 3.9282, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727760041353206e-05, + "loss": 3.9244, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719374093842683e-05, + "loss": 3.9322, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3710988146332163e-05, + "loss": 3.9198, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702602198821643e-05, + "loss": 3.9202, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3694216251311123e-05, + "loss": 3.9104, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685830303800606e-05, + "loss": 3.9207, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677444356290086e-05, + "loss": 3.9218, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669058408779566e-05, + "loss": 3.9234, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660672461269042e-05, + "loss": 3.9212, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652302892562255e-05, + "loss": 3.9184, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3643916945051735e-05, + "loss": 3.9197, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635530997541215e-05, + "loss": 3.9131, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627145050030695e-05, + "loss": 3.9081, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618759102520175e-05, + "loss": 3.916, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610373155009655e-05, + "loss": 3.9196, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3601987207499135e-05, + "loss": 3.9182, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593601259988615e-05, + "loss": 3.9356, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585215312478095e-05, + "loss": 3.9234, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3576829364967575e-05, + "loss": 3.929, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568443417457055e-05, + "loss": 3.9175, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560057469946534e-05, + "loss": 3.922, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551687901239747e-05, + "loss": 3.9179, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543318332532956e-05, + "loss": 3.9293, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534932385022436e-05, + "loss": 3.9158, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526546437511916e-05, + "loss": 3.9141, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.351817686880513e-05, + "loss": 3.9113, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.350979092129461e-05, + "loss": 3.9205, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350140497378409e-05, + "loss": 3.9222, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349301902627357e-05, + "loss": 3.9246, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484633078763045e-05, + "loss": 3.9289, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476247131252528e-05, + "loss": 3.9215, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3467861183742008e-05, + "loss": 3.9189, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.345949161503522e-05, + "loss": 3.9286, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451105667524697e-05, + "loss": 3.9245, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442719720014177e-05, + "loss": 3.9091, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434333772503657e-05, + "loss": 3.9097, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342596420379687e-05, + "loss": 3.9095, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.341757825628635e-05, + "loss": 3.9124, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.340919230877583e-05, + "loss": 3.9279, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340080636126531e-05, + "loss": 3.9161, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339242041375479e-05, + "loss": 3.9131, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338403446624427e-05, + "loss": 3.9206, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337564851873375e-05, + "loss": 3.9135, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336726257122323e-05, + "loss": 3.9201, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.335887662371271e-05, + "loss": 3.9105, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335049067620219e-05, + "loss": 3.8938, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334210472869167e-05, + "loss": 3.9405, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3333735159984878e-05, + "loss": 3.9207, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325349212474358e-05, + "loss": 3.9252, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316963264963838e-05, + "loss": 3.9112, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.330859369625705e-05, + "loss": 3.9198, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330020774874653e-05, + "loss": 3.9094, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329182180123601e-05, + "loss": 3.9147, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328343585372549e-05, + "loss": 3.9156, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327504990621497e-05, + "loss": 3.9177, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326666395870445e-05, + "loss": 3.9359, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.325827801119393e-05, + "loss": 3.9088, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249924821290875e-05, + "loss": 3.9012, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3241538873780352e-05, + "loss": 3.9272, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233152926269832e-05, + "loss": 3.8968, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224766978759312e-05, + "loss": 3.9069, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3216397410052524e-05, + "loss": 3.923, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3208011462542004e-05, + "loss": 3.9237, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199625515031484e-05, + "loss": 3.9088, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191239567520964e-05, + "loss": 3.9143, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3182853620010444e-05, + "loss": 3.8932, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3174467672499924e-05, + "loss": 3.9104, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3166081724989404e-05, + "loss": 3.9196, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157695777478884e-05, + "loss": 3.9077, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149309829968364e-05, + "loss": 3.9186, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140923882457844e-05, + "loss": 3.9185, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132554313751056e-05, + "loss": 3.9308, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124168366240533e-05, + "loss": 3.9067, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115782418730013e-05, + "loss": 3.9147, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107396471219493e-05, + "loss": 3.9255, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099010523708976e-05, + "loss": 3.9064, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090624576198456e-05, + "loss": 3.9207, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082238628687936e-05, + "loss": 3.9152, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073852681177413e-05, + "loss": 3.9133, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065483112470625e-05, + "loss": 3.9242, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057097164960105e-05, + "loss": 3.9054, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048727596253318e-05, + "loss": 3.9073, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040341648742798e-05, + "loss": 3.9139, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031955701232278e-05, + "loss": 3.9187, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023569753721758e-05, + "loss": 3.9116, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015200185014967e-05, + "loss": 3.9158, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006814237504447e-05, + "loss": 3.9046, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299842828999393e-05, + "loss": 3.9118, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299004234248341e-05, + "loss": 3.9068, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2981656394972887e-05, + "loss": 3.9144, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973270447462366e-05, + "loss": 3.9311, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2964884499951846e-05, + "loss": 3.9172, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956498552441326e-05, + "loss": 3.9204, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.294812898373454e-05, + "loss": 3.9082, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.293975941502775e-05, + "loss": 3.91, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293137346751723e-05, + "loss": 3.9129, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292298752000671e-05, + "loss": 3.9239, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914601572496188e-05, + "loss": 3.9152, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906215624985668e-05, + "loss": 3.9209, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897846056278884e-05, + "loss": 3.9107, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.288946010876836e-05, + "loss": 3.9239, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288107416125784e-05, + "loss": 3.9024, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287268821374732e-05, + "loss": 3.9165, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.28643022662368e-05, + "loss": 3.9056, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285591631872628e-05, + "loss": 3.9189, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284753037121576e-05, + "loss": 3.9058, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.283914442370524e-05, + "loss": 3.9145, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830774854998452e-05, + "loss": 3.9096, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822388907487932e-05, + "loss": 3.9112, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814002959977412e-05, + "loss": 3.9116, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280561701246689e-05, + "loss": 3.9108, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.27972474437601e-05, + "loss": 3.9218, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788861496249585e-05, + "loss": 3.927, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780475548739065e-05, + "loss": 3.9194, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772105980032274e-05, + "loss": 3.9163, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2763720032521754e-05, + "loss": 3.9043, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755334085011234e-05, + "loss": 3.9111, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2746948137500714e-05, + "loss": 3.9146, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738562189990194e-05, + "loss": 3.9248, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730192621283406e-05, + "loss": 3.899, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721806673772886e-05, + "loss": 3.9163, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713420726262363e-05, + "loss": 3.9143, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705034778751843e-05, + "loss": 3.9146, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696648831241323e-05, + "loss": 3.9108, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268827926253454e-05, + "loss": 3.916, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679893315024015e-05, + "loss": 3.9091, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671507367513495e-05, + "loss": 3.9211, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663121420002975e-05, + "loss": 3.9189, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654735472492455e-05, + "loss": 3.9232, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.26463822825894e-05, + "loss": 3.9062, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263799633507888e-05, + "loss": 3.9201, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262961038756836e-05, + "loss": 3.9226, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2621224440057836e-05, + "loss": 3.9119, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612838492547316e-05, + "loss": 3.9171, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604452545036796e-05, + "loss": 3.9211, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2596066597526276e-05, + "loss": 3.9189, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2587680650015756e-05, + "loss": 3.9276, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257929470250524e-05, + "loss": 3.9119, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257090875499472e-05, + "loss": 3.917, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2562522807484196e-05, + "loss": 3.9149, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554136859973676e-05, + "loss": 3.9164, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254576729126689e-05, + "loss": 3.9105, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253738134375637e-05, + "loss": 3.9087, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252899539624585e-05, + "loss": 3.9136, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252060944873533e-05, + "loss": 3.9034, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512223501224808e-05, + "loss": 3.9176, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 4.002507209777832, + "eval_runtime": 290.3161, + "eval_samples_per_second": 1314.398, + "eval_steps_per_second": 41.076, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2503837553714288e-05, + "loss": 3.9204, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495451606203768e-05, + "loss": 3.9083, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487065658693248e-05, + "loss": 3.9218, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478679711182725e-05, + "loss": 3.9153, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470293763672208e-05, + "loss": 3.9263, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2461907816161688e-05, + "loss": 3.9128, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2453521868651168e-05, + "loss": 3.9144, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2445135921140648e-05, + "loss": 3.9028, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2436749973630128e-05, + "loss": 3.9139, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428364026119608e-05, + "loss": 3.9154, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2419978078609084e-05, + "loss": 3.9128, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411592131098564e-05, + "loss": 3.9138, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240322256239178e-05, + "loss": 3.9113, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239483661488126e-05, + "loss": 3.9134, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2386450667370737e-05, + "loss": 3.91, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2378064719860217e-05, + "loss": 3.8992, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369678772349697e-05, + "loss": 3.9097, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361292824839177e-05, + "loss": 3.9132, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2352906877328657e-05, + "loss": 3.9117, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234452092981814e-05, + "loss": 3.9266, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233615136111135e-05, + "loss": 3.9212, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.232776541360083e-05, + "loss": 3.9241, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.231937946609031e-05, + "loss": 3.9081, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231099351857979e-05, + "loss": 3.915, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.230260757106927e-05, + "loss": 3.9124, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229422162355875e-05, + "loss": 3.9194, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228583567604823e-05, + "loss": 3.9079, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227744972853771e-05, + "loss": 3.91, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2269080159830918e-05, + "loss": 3.9094, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260694212320398e-05, + "loss": 3.9095, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252308264809878e-05, + "loss": 3.9127, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224392231729936e-05, + "loss": 3.9205, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223555274859257e-05, + "loss": 3.9193, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222716680108205e-05, + "loss": 3.9169, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.221878085357153e-05, + "loss": 3.9123, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221041128486474e-05, + "loss": 3.9172, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2202041716157955e-05, + "loss": 3.9189, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2193655768647435e-05, + "loss": 3.9042, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218526982113691e-05, + "loss": 3.9003, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217688387362639e-05, + "loss": 3.9014, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.216849792611587e-05, + "loss": 3.9079, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216011197860535e-05, + "loss": 3.9147, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215172603109483e-05, + "loss": 3.913, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214334008358431e-05, + "loss": 3.9076, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2134954136073795e-05, + "loss": 3.9122, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212656818856327e-05, + "loss": 3.9095, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.211818224105275e-05, + "loss": 3.9128, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.210979629354223e-05, + "loss": 3.903, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2101426724835444e-05, + "loss": 3.8878, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2093040777324924e-05, + "loss": 3.9308, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084654829814404e-05, + "loss": 3.9128, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076268882303884e-05, + "loss": 3.9209, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2067882934793363e-05, + "loss": 3.9092, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2059513366086573e-05, + "loss": 3.911, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2051127418576053e-05, + "loss": 3.9046, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2042741471065532e-05, + "loss": 3.9057, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2034355523555016e-05, + "loss": 3.9116, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2025969576044496e-05, + "loss": 3.9069, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017600007337705e-05, + "loss": 3.9282, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009230438630917e-05, + "loss": 3.9072, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2000844491120394e-05, + "loss": 3.8963, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1992458543609877e-05, + "loss": 3.9217, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1984072596099357e-05, + "loss": 3.8918, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1975686648588837e-05, + "loss": 3.8965, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1967317079882046e-05, + "loss": 3.9231, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1958931132371526e-05, + "loss": 3.9162, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950545184861006e-05, + "loss": 3.9011, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1942159237350486e-05, + "loss": 3.9103, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193377328983997e-05, + "loss": 3.8891, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192540372113318e-05, + "loss": 3.9037, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191701777362266e-05, + "loss": 3.91, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.190863182611214e-05, + "loss": 3.9051, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190024587860162e-05, + "loss": 3.9118, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.18918599310911e-05, + "loss": 3.9133, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.188347398358058e-05, + "loss": 3.9208, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187508803607006e-05, + "loss": 3.9019, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1866702088559538e-05, + "loss": 3.9062, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1858332519852747e-05, + "loss": 3.9158, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1849946572342227e-05, + "loss": 3.9032, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841560624831707e-05, + "loss": 3.9134, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833174677321187e-05, + "loss": 3.9088, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.18248051086144e-05, + "loss": 3.9032, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1816435539907612e-05, + "loss": 3.922, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1808049592397092e-05, + "loss": 3.8953, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.17996800236903e-05, + "loss": 3.8978, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791294076179785e-05, + "loss": 3.9096, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1782908128669265e-05, + "loss": 3.9133, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774522181158745e-05, + "loss": 3.9054, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.176613623364822e-05, + "loss": 3.911, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.17577502861377e-05, + "loss": 3.895, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.174936433862718e-05, + "loss": 3.9042, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174097839111666e-05, + "loss": 3.9007, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173259244360614e-05, + "loss": 3.9078, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1724206496095624e-05, + "loss": 3.9227, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1715820548585104e-05, + "loss": 3.9085, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170743460107458e-05, + "loss": 3.915, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1699065032367793e-05, + "loss": 3.9026, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1690695463661002e-05, + "loss": 3.9026, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1682309516150486e-05, + "loss": 3.904, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1673923568639966e-05, + "loss": 3.9186, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665537621129446e-05, + "loss": 3.9112, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657151673618926e-05, + "loss": 3.9135, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648765726108402e-05, + "loss": 3.9017, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1640379778597882e-05, + "loss": 3.9136, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1631993831087362e-05, + "loss": 3.8989, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1623607883576842e-05, + "loss": 3.9099, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1615238314870054e-05, + "loss": 3.8954, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1606868746163267e-05, + "loss": 3.9131, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598482798652747e-05, + "loss": 3.8983, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590096851142223e-05, + "loss": 3.908, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581710903631703e-05, + "loss": 3.8968, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573324956121187e-05, + "loss": 3.9106, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1564939008610667e-05, + "loss": 3.899, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1556553061100147e-05, + "loss": 3.9024, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1548167113589627e-05, + "loss": 3.9188, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539797544882836e-05, + "loss": 3.9188, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531411597372316e-05, + "loss": 3.9138, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1523025649861796e-05, + "loss": 3.9059, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151463970235128e-05, + "loss": 3.8998, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1506270133644488e-05, + "loss": 3.9038, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1497884186133968e-05, + "loss": 3.9089, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489498238623448e-05, + "loss": 3.9113, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481112291112928e-05, + "loss": 3.8937, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472726343602405e-05, + "loss": 3.9092, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146435677489562e-05, + "loss": 3.9082, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.14559708273851e-05, + "loss": 3.9069, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144758487987458e-05, + "loss": 3.9064, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.143921531116779e-05, + "loss": 3.9059, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143082936365727e-05, + "loss": 3.9013, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142244341614675e-05, + "loss": 3.9176, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1414057468636233e-05, + "loss": 3.9155, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140567152112571e-05, + "loss": 3.912, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1397301952418922e-05, + "loss": 3.8985, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.13889160049084e-05, + "loss": 3.9163, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1380530057397878e-05, + "loss": 3.9123, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1372144109887358e-05, + "loss": 3.9038, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136375816237684e-05, + "loss": 3.911, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.135537221486632e-05, + "loss": 3.9107, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.13469862673558e-05, + "loss": 3.9117, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.133860031984528e-05, + "loss": 3.9222, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133021437233476e-05, + "loss": 3.9033, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1321828424824238e-05, + "loss": 3.9107, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313442477313718e-05, + "loss": 3.9121, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.13050565298032e-05, + "loss": 3.9084, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296686961096414e-05, + "loss": 3.9013, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.128830101358589e-05, + "loss": 3.8989, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.127991506607537e-05, + "loss": 3.9036, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1271545497368583e-05, + "loss": 3.8989, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1263159549858063e-05, + "loss": 3.909, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.9990947246551514, + "eval_runtime": 279.0209, + "eval_samples_per_second": 1367.607, + "eval_steps_per_second": 42.739, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1254773602347543e-05, + "loss": 3.9094, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246387654837023e-05, + "loss": 3.9017, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1238001707326503e-05, + "loss": 3.9112, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1229615759815983e-05, + "loss": 3.9116, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1221229812305462e-05, + "loss": 3.9195, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121286024359867e-05, + "loss": 3.9055, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120447429608815e-05, + "loss": 3.913, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1196104727381364e-05, + "loss": 3.8982, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187718779870844e-05, + "loss": 3.899, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1179332832360324e-05, + "loss": 3.9144, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1170946884849804e-05, + "loss": 3.9066, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1162560937339284e-05, + "loss": 3.9041, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1154191368632496e-05, + "loss": 3.914, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1145805421121976e-05, + "loss": 3.9001, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1137419473611456e-05, + "loss": 3.8984, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1129033526100936e-05, + "loss": 3.8964, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120663957394145e-05, + "loss": 3.9015, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112278009883625e-05, + "loss": 3.9067, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1103892062373105e-05, + "loss": 3.9005, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109550611486259e-05, + "loss": 3.9209, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1087120167352065e-05, + "loss": 3.914, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078734219841545e-05, + "loss": 3.916, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070348272331025e-05, + "loss": 3.9045, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1061962324820505e-05, + "loss": 3.9041, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1053592756113717e-05, + "loss": 3.9119, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1045206808603197e-05, + "loss": 3.9091, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1036820861092677e-05, + "loss": 3.9019, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.102845129238589e-05, + "loss": 3.9043, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1020065344875366e-05, + "loss": 3.8988, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1011679397364846e-05, + "loss": 3.9037, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003293449854326e-05, + "loss": 3.9062, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.099490750234381e-05, + "loss": 3.9119, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.098652155483329e-05, + "loss": 3.912, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.097813560732277e-05, + "loss": 3.9111, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0969749659812246e-05, + "loss": 3.9073, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.096138009110546e-05, + "loss": 3.9087, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.095299414359494e-05, + "loss": 3.9124, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.094460819608442e-05, + "loss": 3.8979, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.09362222485739e-05, + "loss": 3.8953, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.092783630106338e-05, + "loss": 3.8953, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.091945035355286e-05, + "loss": 3.9005, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.091106440604234e-05, + "loss": 3.9019, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090267845853182e-05, + "loss": 3.9073, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894292511021298e-05, + "loss": 3.9036, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0885906563510778e-05, + "loss": 3.9033, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0877520616000258e-05, + "loss": 3.9045, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.086915104729347e-05, + "loss": 3.9101, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086078147858668e-05, + "loss": 3.8953, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085239553107616e-05, + "loss": 3.8819, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084400958356564e-05, + "loss": 3.9174, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083562363605512e-05, + "loss": 3.9091, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827237688544603e-05, + "loss": 3.916, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.081885174103408e-05, + "loss": 3.9016, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081046579352356e-05, + "loss": 3.9025, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080207984601304e-05, + "loss": 3.8995, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0793710277306252e-05, + "loss": 3.8976, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078532432979573e-05, + "loss": 3.9092, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0776938382285212e-05, + "loss": 3.8923, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0768552434774692e-05, + "loss": 3.9256, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0760166487264172e-05, + "loss": 3.906, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0751780539753652e-05, + "loss": 3.8846, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074341097104686e-05, + "loss": 3.9148, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073502502353634e-05, + "loss": 3.8893, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072663907602582e-05, + "loss": 3.8883, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718253128515304e-05, + "loss": 3.9153, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0709867181004784e-05, + "loss": 3.9072, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.070148123349426e-05, + "loss": 3.897, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0693111664787473e-05, + "loss": 3.9013, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0684725717276953e-05, + "loss": 3.8849, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0676339769766433e-05, + "loss": 3.8948, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0667953822255913e-05, + "loss": 3.9029, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0659584253549125e-05, + "loss": 3.8984, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0651198306038605e-05, + "loss": 3.9048, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0642812358528082e-05, + "loss": 3.9022, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0634426411017562e-05, + "loss": 3.914, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0626040463507042e-05, + "loss": 3.8967, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0617654515996522e-05, + "loss": 3.9032, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0609284947289734e-05, + "loss": 3.9079, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0600898999779214e-05, + "loss": 3.8953, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592513052268694e-05, + "loss": 3.9085, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584127104758174e-05, + "loss": 3.9026, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0575757536051383e-05, + "loss": 3.8956, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0567371588540867e-05, + "loss": 3.9157, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0558985641030347e-05, + "loss": 3.8877, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550599693519827e-05, + "loss": 3.8904, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542213746009306e-05, + "loss": 3.906, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0533827798498786e-05, + "loss": 3.903, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525441850988263e-05, + "loss": 3.8982, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0517072282281475e-05, + "loss": 3.9077, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.050868633477096e-05, + "loss": 3.889, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050030038726044e-05, + "loss": 3.8941, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0491914439749915e-05, + "loss": 3.8975, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483528492239395e-05, + "loss": 3.8984, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475142544728875e-05, + "loss": 3.9166, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466756597218355e-05, + "loss": 3.9016, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458370649707835e-05, + "loss": 3.9083, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0449984702197315e-05, + "loss": 3.8961, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044163151229426e-05, + "loss": 3.897, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433245564783737e-05, + "loss": 3.8985, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0424859617273217e-05, + "loss": 3.9075, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416473669762697e-05, + "loss": 3.9042, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0408104101055912e-05, + "loss": 3.9078, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.039971815354539e-05, + "loss": 3.8983, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039133220603487e-05, + "loss": 3.9036, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038294625852435e-05, + "loss": 3.897, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037456031101383e-05, + "loss": 3.8998, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036617436350331e-05, + "loss": 3.8902, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.035778841599279e-05, + "loss": 3.9088, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0349418847286e-05, + "loss": 3.8901, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034103289977548e-05, + "loss": 3.8998, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033264695226496e-05, + "loss": 3.8917, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032426100475444e-05, + "loss": 3.9038, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0315875057243918e-05, + "loss": 3.8964, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.030750548853713e-05, + "loss": 3.8944, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299119541026614e-05, + "loss": 3.9073, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290733593516094e-05, + "loss": 3.9143, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028234764600557e-05, + "loss": 3.9103, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027396169849505e-05, + "loss": 3.9011, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026557575098453e-05, + "loss": 3.8943, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0257206182277743e-05, + "loss": 3.8961, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0248820234767222e-05, + "loss": 3.9039, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0240434287256702e-05, + "loss": 3.9047, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0232048339746182e-05, + "loss": 3.8893, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022367877103939e-05, + "loss": 3.9047, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021529282352887e-05, + "loss": 3.9045, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020690687601835e-05, + "loss": 3.8979, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0198520928507835e-05, + "loss": 3.8978, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190151359801044e-05, + "loss": 3.9045, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0181781791094256e-05, + "loss": 3.8958, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173395843583736e-05, + "loss": 3.9085, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0165026274876945e-05, + "loss": 3.9046, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015664032736643e-05, + "loss": 3.9093, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.014825437985591e-05, + "loss": 3.8943, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.013986843234539e-05, + "loss": 3.908, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0131482484834865e-05, + "loss": 3.9064, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0123096537324345e-05, + "loss": 3.9004, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114710589813825e-05, + "loss": 3.9034, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0106324642303305e-05, + "loss": 3.9029, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0097955073596518e-05, + "loss": 3.9064, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0089569126085997e-05, + "loss": 3.92, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081183178575477e-05, + "loss": 3.8944, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072797231064957e-05, + "loss": 3.9074, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064411283554437e-05, + "loss": 3.9052, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0056025336043917e-05, + "loss": 3.9033, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047639388533397e-05, + "loss": 3.8971, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0039253441022877e-05, + "loss": 3.8914, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0030867493512357e-05, + "loss": 3.9019, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0022481546001837e-05, + "loss": 3.8932, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0014095598491317e-05, + "loss": 3.9035, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.996737480163574, + "eval_runtime": 278.2889, + "eval_samples_per_second": 1371.204, + "eval_steps_per_second": 42.851, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005709650980797e-05, + "loss": 3.9, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997323703470277e-05, + "loss": 3.8991, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9988937755959754e-05, + "loss": 3.9043, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980551808449237e-05, + "loss": 3.9038, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972165860938717e-05, + "loss": 3.9104, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9963779913428197e-05, + "loss": 3.9013, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955393965917677e-05, + "loss": 3.909, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9947008018407157e-05, + "loss": 3.8931, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938622070896633e-05, + "loss": 3.8963, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930236123386113e-05, + "loss": 3.9101, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9921850175875593e-05, + "loss": 3.9007, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9913464228365077e-05, + "loss": 3.8966, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905094659658286e-05, + "loss": 3.9103, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896708712147766e-05, + "loss": 3.8936, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888322764637246e-05, + "loss": 3.8939, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9879936817126726e-05, + "loss": 3.885, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871550869616205e-05, + "loss": 3.8993, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863164922105685e-05, + "loss": 3.9046, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985477897459517e-05, + "loss": 3.8933, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9846409405888378e-05, + "loss": 3.9126, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838023458377858e-05, + "loss": 3.9084, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829637510867338e-05, + "loss": 3.9082, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821251563356814e-05, + "loss": 3.9034, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9812865615846298e-05, + "loss": 3.9014, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9804479668335778e-05, + "loss": 3.9031, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9796093720825258e-05, + "loss": 3.9028, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9787707773314738e-05, + "loss": 3.8944, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779321825804218e-05, + "loss": 3.9004, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9770935878293697e-05, + "loss": 3.8924, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762549930783174e-05, + "loss": 3.8974, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754163983272654e-05, + "loss": 3.901, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974579441456587e-05, + "loss": 3.9008, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973740846705535e-05, + "loss": 3.908, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729022519544826e-05, + "loss": 3.9103, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972065295083804e-05, + "loss": 3.8951, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971228338213125e-05, + "loss": 3.9052, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970389743462073e-05, + "loss": 3.91, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969551148711021e-05, + "loss": 3.8897, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968712553959969e-05, + "loss": 3.8925, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.967873959208917e-05, + "loss": 3.8906, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9670353644578648e-05, + "loss": 3.891, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9661967697068128e-05, + "loss": 3.8981, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9653581749557608e-05, + "loss": 3.9048, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964519580204709e-05, + "loss": 3.8967, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.963680985453657e-05, + "loss": 3.8965, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.962842390702605e-05, + "loss": 3.8956, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962003795951553e-05, + "loss": 3.9065, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961166839080874e-05, + "loss": 3.8874, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960328244329822e-05, + "loss": 3.8789, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.95948964957877e-05, + "loss": 3.9097, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958651054827718e-05, + "loss": 3.9027, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.957812460076666e-05, + "loss": 3.9104, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9569755032059872e-05, + "loss": 3.8954, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956138546335308e-05, + "loss": 3.8944, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955299951584256e-05, + "loss": 3.8969, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9544613568332045e-05, + "loss": 3.8952, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9536227620821525e-05, + "loss": 3.9045, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9527841673311005e-05, + "loss": 3.8866, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.951945572580048e-05, + "loss": 3.9229, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951106977828996e-05, + "loss": 3.8945, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950268383077944e-05, + "loss": 3.8765, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9494314262072654e-05, + "loss": 3.9086, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9485928314562133e-05, + "loss": 3.8883, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9477542367051613e-05, + "loss": 3.8798, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469156419541093e-05, + "loss": 3.9062, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9460803229638035e-05, + "loss": 3.9026, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9452417282127515e-05, + "loss": 3.8949, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9444031334617e-05, + "loss": 3.8945, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9435645387106478e-05, + "loss": 3.8778, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9427259439595955e-05, + "loss": 3.8888, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9418873492085435e-05, + "loss": 3.9006, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410487544574915e-05, + "loss": 3.8927, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402101597064395e-05, + "loss": 3.898, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393732028357607e-05, + "loss": 3.8955, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385346080847087e-05, + "loss": 3.9096, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.93769765121403e-05, + "loss": 3.8942, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368590564629776e-05, + "loss": 3.8966, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936022099592299e-05, + "loss": 3.8994, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935183504841247e-05, + "loss": 3.8932, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934344910090195e-05, + "loss": 3.9028, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933506315339143e-05, + "loss": 3.8951, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932667720588091e-05, + "loss": 3.8934, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.931829125837039e-05, + "loss": 3.9087, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.930990531085987e-05, + "loss": 3.8841, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930151936334935e-05, + "loss": 3.8873, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929313341583883e-05, + "loss": 3.8988, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284747468328308e-05, + "loss": 3.9004, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276361520817788e-05, + "loss": 3.8888, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9267975573307268e-05, + "loss": 3.9045, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.925960600460048e-05, + "loss": 3.8891, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925123643589369e-05, + "loss": 3.8895, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924285048838317e-05, + "loss": 3.8881, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234464540872653e-05, + "loss": 3.8942, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922607859336213e-05, + "loss": 3.909, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921769264585161e-05, + "loss": 3.8966, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.920930669834109e-05, + "loss": 3.9019, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920092075083057e-05, + "loss": 3.8927, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919255118212378e-05, + "loss": 3.8915, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184165234613262e-05, + "loss": 3.8929, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9175779287102742e-05, + "loss": 3.9026, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167393339592222e-05, + "loss": 3.9009, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9159007392081702e-05, + "loss": 3.8982, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9150621444571182e-05, + "loss": 3.8988, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9142235497060662e-05, + "loss": 3.8976, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913386592835387e-05, + "loss": 3.8939, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9125479980843354e-05, + "loss": 3.8932, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117094033332834e-05, + "loss": 3.8873, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910870808582231e-05, + "loss": 3.9007, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910032213831179e-05, + "loss": 3.8875, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909193619080127e-05, + "loss": 3.8923, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9083583000898216e-05, + "loss": 3.8893, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9075197053387696e-05, + "loss": 3.892, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9066811105877176e-05, + "loss": 3.8926, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9058425158366655e-05, + "loss": 3.8894, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9050039210856135e-05, + "loss": 3.9064, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9041653263345612e-05, + "loss": 3.9055, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9033267315835092e-05, + "loss": 3.9025, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9024881368324572e-05, + "loss": 3.8954, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9016495420814055e-05, + "loss": 3.893, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9008109473303535e-05, + "loss": 3.8908, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999723525793015e-05, + "loss": 3.9002, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991337578282492e-05, + "loss": 3.9027, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8982968009575704e-05, + "loss": 3.8854, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974582062065184e-05, + "loss": 3.8977, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8966196114554664e-05, + "loss": 3.897, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8957810167044144e-05, + "loss": 3.895, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949424219533624e-05, + "loss": 3.889, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941071029630566e-05, + "loss": 3.8974, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932685082120046e-05, + "loss": 3.8896, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8924299134609526e-05, + "loss": 3.9049, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891591318709901e-05, + "loss": 3.8971, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890752723958849e-05, + "loss": 3.9072, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899141292077965e-05, + "loss": 3.8895, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890755344567445e-05, + "loss": 3.9012, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882385775860658e-05, + "loss": 3.9056, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8873999828350138e-05, + "loss": 3.8947, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865613880839618e-05, + "loss": 3.8974, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857227933329098e-05, + "loss": 3.8985, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.884885836462231e-05, + "loss": 3.9004, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884047241711179e-05, + "loss": 3.9134, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832086469601267e-05, + "loss": 3.8932, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823700522090747e-05, + "loss": 3.9008, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881531457458023e-05, + "loss": 3.9024, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880692862706971e-05, + "loss": 3.8975, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.879854267955919e-05, + "loss": 3.8919, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.87901731108524e-05, + "loss": 3.8856, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878178716334188e-05, + "loss": 3.8936, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877340121583136e-05, + "loss": 3.8942, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876501526832084e-05, + "loss": 3.8969, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9953973293304443, + "eval_runtime": 302.634, + "eval_samples_per_second": 1260.899, + "eval_steps_per_second": 39.404, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875662932081032e-05, + "loss": 3.8958, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.87482433732998e-05, + "loss": 3.8927, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.873985742578928e-05, + "loss": 3.8953, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873147147827876e-05, + "loss": 3.9033, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8723101909571968e-05, + "loss": 3.909, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8714715962061448e-05, + "loss": 3.8966, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870633001455093e-05, + "loss": 3.8979, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.869794406704041e-05, + "loss": 3.8891, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.868955811952989e-05, + "loss": 3.891, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8681204929626833e-05, + "loss": 3.9006, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8672818982116313e-05, + "loss": 3.8971, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8664449413409525e-05, + "loss": 3.8956, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8656079844702734e-05, + "loss": 3.9037, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8647693897192214e-05, + "loss": 3.889, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8639307949681694e-05, + "loss": 3.8885, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8630922002171174e-05, + "loss": 3.8778, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8622536054660654e-05, + "loss": 3.8983, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8614150107150134e-05, + "loss": 3.8988, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8605764159639617e-05, + "loss": 3.8863, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8597378212129094e-05, + "loss": 3.9058, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8588992264618574e-05, + "loss": 3.9038, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8580606317108054e-05, + "loss": 3.9035, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8572220369597534e-05, + "loss": 3.8962, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8563834422087014e-05, + "loss": 3.8985, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8555448474576494e-05, + "loss": 3.896, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8547062527065974e-05, + "loss": 3.9035, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8538676579555454e-05, + "loss": 3.8849, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8530290632044934e-05, + "loss": 3.8987, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8521921063338146e-05, + "loss": 3.8862, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8513535115827623e-05, + "loss": 3.8941, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8505149168317103e-05, + "loss": 3.8974, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8496763220806586e-05, + "loss": 3.9002, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8488377273296066e-05, + "loss": 3.896, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8480007704589275e-05, + "loss": 3.9077, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8471621757078755e-05, + "loss": 3.8925, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463252188371967e-05, + "loss": 3.9005, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8454866240861447e-05, + "loss": 3.9045, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8446480293350927e-05, + "loss": 3.8814, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8438094345840407e-05, + "loss": 3.8859, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8429708398329887e-05, + "loss": 3.8886, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8421322450819367e-05, + "loss": 3.8857, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8412936503308847e-05, + "loss": 3.8923, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404550555798327e-05, + "loss": 3.9006, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839618098709154e-05, + "loss": 3.8891, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.838779503958102e-05, + "loss": 3.8936, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.83794090920705e-05, + "loss": 3.8922, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837102314455998e-05, + "loss": 3.8972, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836266995465692e-05, + "loss": 3.8842, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.83542840071464e-05, + "loss": 3.8776, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834589805963588e-05, + "loss": 3.9042, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.833751211212536e-05, + "loss": 3.8984, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8329158922222303e-05, + "loss": 3.909, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8320772974711783e-05, + "loss": 3.8894, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8312387027201262e-05, + "loss": 3.8904, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8304001079690742e-05, + "loss": 3.8911, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8295615132180222e-05, + "loss": 3.8873, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287229184669702e-05, + "loss": 3.9032, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8278843237159182e-05, + "loss": 3.8766, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8270457289648662e-05, + "loss": 3.9184, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8262071342138142e-05, + "loss": 3.8936, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8253701773431355e-05, + "loss": 3.8719, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8245315825920835e-05, + "loss": 3.8981, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8236929878410315e-05, + "loss": 3.8873, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8228543930899795e-05, + "loss": 3.8731, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8220157983389275e-05, + "loss": 3.8989, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821177203587875e-05, + "loss": 3.9018, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.820338608836823e-05, + "loss": 3.8864, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819500014085771e-05, + "loss": 3.8922, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8186630572150927e-05, + "loss": 3.8702, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8178244624640403e-05, + "loss": 3.8841, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8169858677129883e-05, + "loss": 3.8944, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8161472729619363e-05, + "loss": 3.8871, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8153103160912572e-05, + "loss": 3.8984, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8144717213402056e-05, + "loss": 3.8865, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8136331265891536e-05, + "loss": 3.9077, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8127945318381016e-05, + "loss": 3.8884, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8119575749674225e-05, + "loss": 3.8936, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8111206180967437e-05, + "loss": 3.8935, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8102820233456917e-05, + "loss": 3.8877, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8094434285946397e-05, + "loss": 3.8968, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8086048338435877e-05, + "loss": 3.8877, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8077662390925357e-05, + "loss": 3.8941, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.806929282221857e-05, + "loss": 3.8974, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8060906874708046e-05, + "loss": 3.8884, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052520927197526e-05, + "loss": 3.8756, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804413497968701e-05, + "loss": 3.8902, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803574903217649e-05, + "loss": 3.8975, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.80273794634697e-05, + "loss": 3.885, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.801899351595918e-05, + "loss": 3.8958, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801060756844866e-05, + "loss": 3.8852, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800222162093814e-05, + "loss": 3.8834, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.799383567342762e-05, + "loss": 3.8853, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.79854497259171e-05, + "loss": 3.8882, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.797708015721031e-05, + "loss": 3.9019, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.796871058850352e-05, + "loss": 3.8935, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7960324640993e-05, + "loss": 3.8986, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795193869348248e-05, + "loss": 3.8878, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943552745971963e-05, + "loss": 3.8871, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7935183177265172e-05, + "loss": 3.8879, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7926797229754652e-05, + "loss": 3.8962, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7918411282244132e-05, + "loss": 3.8965, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7910025334733612e-05, + "loss": 3.8958, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7901639387223092e-05, + "loss": 3.893, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7893253439712572e-05, + "loss": 3.8872, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7884867492202055e-05, + "loss": 3.8936, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876481544691532e-05, + "loss": 3.8878, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7868095597181012e-05, + "loss": 3.8849, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7859726028474224e-05, + "loss": 3.893, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.78513400809637e-05, + "loss": 3.8848, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.784295413345318e-05, + "loss": 3.8862, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7834568185942664e-05, + "loss": 3.8837, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7826182238432144e-05, + "loss": 3.8858, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7817796290921624e-05, + "loss": 3.8919, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7809410343411104e-05, + "loss": 3.8849, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7801040774704313e-05, + "loss": 3.901, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7792654827193793e-05, + "loss": 3.8981, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7784285258487006e-05, + "loss": 3.9013, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7775899310976486e-05, + "loss": 3.8893, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7767513363465966e-05, + "loss": 3.8888, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7759127415955446e-05, + "loss": 3.8828, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7750741468444925e-05, + "loss": 3.8985, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7742355520934405e-05, + "loss": 3.8936, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7733969573423882e-05, + "loss": 3.8795, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7725616383520827e-05, + "loss": 3.891, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7717230436010307e-05, + "loss": 3.8925, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7708844488499787e-05, + "loss": 3.8929, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7700458540989267e-05, + "loss": 3.8863, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7692072593478747e-05, + "loss": 3.891, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768370302477196e-05, + "loss": 3.8856, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767531707726144e-05, + "loss": 3.9021, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766693112975092e-05, + "loss": 3.893, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.76585451822404e-05, + "loss": 3.9008, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765015923472988e-05, + "loss": 3.8854, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7641773287219356e-05, + "loss": 3.8961, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7633387339708836e-05, + "loss": 3.8993, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762500139219832e-05, + "loss": 3.8889, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.76166154446878e-05, + "loss": 3.8937, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.760822949717728e-05, + "loss": 3.8907, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7599859928470488e-05, + "loss": 3.8993, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7591473980959968e-05, + "loss": 3.9036, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7583088033449448e-05, + "loss": 3.8933, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7574702085938928e-05, + "loss": 3.8932, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.756633251723214e-05, + "loss": 3.8994, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.755794656972162e-05, + "loss": 3.8935, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.75495606222111e-05, + "loss": 3.8869, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754117467470058e-05, + "loss": 3.8827, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753278872719006e-05, + "loss": 3.8869, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752440277967954e-05, + "loss": 3.8882, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.751601683216902e-05, + "loss": 3.8922, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.99375581741333, + "eval_runtime": 302.0511, + "eval_samples_per_second": 1263.333, + "eval_steps_per_second": 39.48, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.75076308846585e-05, + "loss": 3.8924, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.749924493714798e-05, + "loss": 3.8866, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749085898963746e-05, + "loss": 3.8908, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.748247304212694e-05, + "loss": 3.898, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.747408709461642e-05, + "loss": 3.9033, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465701147105896e-05, + "loss": 3.8906, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.745731519959538e-05, + "loss": 3.8968, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.744892925208486e-05, + "loss": 3.8848, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744054330457434e-05, + "loss": 3.8843, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.743217373586755e-05, + "loss": 3.8916, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742378778835703e-05, + "loss": 3.8967, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741540184084651e-05, + "loss": 3.8903, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740703227213972e-05, + "loss": 3.896, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.73986463246292e-05, + "loss": 3.8817, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739026037711868e-05, + "loss": 3.8865, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738187442960816e-05, + "loss": 3.8696, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737348848209764e-05, + "loss": 3.8938, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736510253458712e-05, + "loss": 3.8942, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.73567165870766e-05, + "loss": 3.8824, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.734833063956608e-05, + "loss": 3.8992, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.733994469205556e-05, + "loss": 3.902, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733155874454504e-05, + "loss": 3.8987, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732317279703452e-05, + "loss": 3.8907, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7314786849524e-05, + "loss": 3.8912, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730640090201348e-05, + "loss": 3.8949, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7298014954502957e-05, + "loss": 3.8963, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289629006992437e-05, + "loss": 3.8814, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728124305948192e-05, + "loss": 3.8899, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7272873490775133e-05, + "loss": 3.8864, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726448754326461e-05, + "loss": 3.8842, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725610159575409e-05, + "loss": 3.8932, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.724771564824357e-05, + "loss": 3.8933, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.723932970073305e-05, + "loss": 3.8917, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723094375322253e-05, + "loss": 3.902, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222574184515742e-05, + "loss": 3.8881, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7214204615808954e-05, + "loss": 3.8965, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720581866829843e-05, + "loss": 3.9008, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719743272078791e-05, + "loss": 3.8772, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.718904677327739e-05, + "loss": 3.8802, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7180660825766874e-05, + "loss": 3.8855, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172274878256354e-05, + "loss": 3.8753, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163888930745834e-05, + "loss": 3.8893, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155502983235314e-05, + "loss": 3.8984, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.714711703572479e-05, + "loss": 3.8832, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7138747467018003e-05, + "loss": 3.8886, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7130361519507483e-05, + "loss": 3.8904, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7121975571996966e-05, + "loss": 3.8905, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113606003290175e-05, + "loss": 3.8797, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105220055779655e-05, + "loss": 3.8698, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7096834108269135e-05, + "loss": 3.8967, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7088448160758612e-05, + "loss": 3.8971, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7080078592051828e-05, + "loss": 3.9061, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071692644541308e-05, + "loss": 3.8833, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063306697030788e-05, + "loss": 3.8829, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7054920749520264e-05, + "loss": 3.8886, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7046534802009744e-05, + "loss": 3.8806, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7038148854499224e-05, + "loss": 3.8983, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7029762906988704e-05, + "loss": 3.8694, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7021376959478184e-05, + "loss": 3.9133, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7012991011967667e-05, + "loss": 3.889, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004621443260877e-05, + "loss": 3.8671, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996235495750357e-05, + "loss": 3.8926, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987849548239836e-05, + "loss": 3.8827, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979463600729316e-05, + "loss": 3.87, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6971077653218796e-05, + "loss": 3.8937, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6962691705708276e-05, + "loss": 3.8953, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695432213700149e-05, + "loss": 3.8804, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694593618949097e-05, + "loss": 3.8923, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937550241980445e-05, + "loss": 3.866, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929180673273658e-05, + "loss": 3.8792, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920794725763138e-05, + "loss": 3.8825, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912408778252618e-05, + "loss": 3.8855, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6904022830742098e-05, + "loss": 3.8885, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895636883231578e-05, + "loss": 3.8827, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887250935721058e-05, + "loss": 3.9023, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878864988210538e-05, + "loss": 3.8862, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870479040700018e-05, + "loss": 3.8904, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6862093093189497e-05, + "loss": 3.885, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6853707145678977e-05, + "loss": 3.8812, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684533757697219e-05, + "loss": 3.8907, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683695162946167e-05, + "loss": 3.8816, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.682856568195115e-05, + "loss": 3.8875, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820179734440626e-05, + "loss": 3.898, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811793786930106e-05, + "loss": 3.882, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.680340783941959e-05, + "loss": 3.8711, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679502189190907e-05, + "loss": 3.885, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.678663594439855e-05, + "loss": 3.8938, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.677826637569176e-05, + "loss": 3.877, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.676988042818124e-05, + "loss": 3.8919, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.676151085947445e-05, + "loss": 3.8839, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753141290767664e-05, + "loss": 3.8748, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744755343257144e-05, + "loss": 3.8798, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6736369395746624e-05, + "loss": 3.8842, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.67279834482361e-05, + "loss": 3.9012, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6719613879529313e-05, + "loss": 3.8866, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6711227932018793e-05, + "loss": 3.8927, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6702841984508273e-05, + "loss": 3.8845, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694456036997752e-05, + "loss": 3.8807, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6686070089487232e-05, + "loss": 3.8824, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6677684141976712e-05, + "loss": 3.8916, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6669298194466192e-05, + "loss": 3.8937, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6660928625759405e-05, + "loss": 3.8894, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6652542678248885e-05, + "loss": 3.888, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644156730738365e-05, + "loss": 3.879, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635770783227845e-05, + "loss": 3.891, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627384835717325e-05, + "loss": 3.8822, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6618998888206805e-05, + "loss": 3.881, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661061294069628e-05, + "loss": 3.8838, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660222699318576e-05, + "loss": 3.881, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6593841045675244e-05, + "loss": 3.8821, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585455098164724e-05, + "loss": 3.8789, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577069150654204e-05, + "loss": 3.8805, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568683203143684e-05, + "loss": 3.8852, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6560313634436893e-05, + "loss": 3.8854, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6551944065730106e-05, + "loss": 3.8887, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6543558118219586e-05, + "loss": 3.8917, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6535172170709066e-05, + "loss": 3.8983, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526786223198546e-05, + "loss": 3.8842, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518400275688026e-05, + "loss": 3.8835, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6510014328177506e-05, + "loss": 3.8795, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6501628380666986e-05, + "loss": 3.8921, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6493242433156462e-05, + "loss": 3.8891, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6484856485645946e-05, + "loss": 3.8796, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476486916939158e-05, + "loss": 3.8796, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468117348232367e-05, + "loss": 3.8901, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459731400721847e-05, + "loss": 3.8874, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451345453211327e-05, + "loss": 3.8784, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6442959505700807e-05, + "loss": 3.8851, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434573558190287e-05, + "loss": 3.883, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426187610679767e-05, + "loss": 3.8915, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417801663169247e-05, + "loss": 3.8896, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6409415715658727e-05, + "loss": 3.8948, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640106252575567e-05, + "loss": 3.8805, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639269295704888e-05, + "loss": 3.8927, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638430700953836e-05, + "loss": 3.894, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637592106202784e-05, + "loss": 3.8809, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.636753511451732e-05, + "loss": 3.888, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.63591491670068e-05, + "loss": 3.8908, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635076321949628e-05, + "loss": 3.8971, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342393650789493e-05, + "loss": 3.8981, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6334007703278973e-05, + "loss": 3.8848, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6325621755768453e-05, + "loss": 3.8867, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631723580825793e-05, + "loss": 3.8934, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.630884986074741e-05, + "loss": 3.8853, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630046391323689e-05, + "loss": 3.8837, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629207796572637e-05, + "loss": 3.8826, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283692018215853e-05, + "loss": 3.8788, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275306070705333e-05, + "loss": 3.8868, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6266920123194813e-05, + "loss": 3.884, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.9920575618743896, + "eval_runtime": 295.1831, + "eval_samples_per_second": 1292.727, + "eval_steps_per_second": 40.399, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.625853417568429e-05, + "loss": 3.8838, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625014822817377e-05, + "loss": 3.8844, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6241778659466982e-05, + "loss": 3.8865, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6233392711956462e-05, + "loss": 3.8905, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6225006764445942e-05, + "loss": 3.8977, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6216637195739154e-05, + "loss": 3.8884, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6208251248228634e-05, + "loss": 3.892, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.619986530071811e-05, + "loss": 3.8827, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619147935320759e-05, + "loss": 3.8773, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618309340569707e-05, + "loss": 3.8853, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6174707458186554e-05, + "loss": 3.8971, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6166321510676034e-05, + "loss": 3.8807, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6157951941969243e-05, + "loss": 3.8959, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6149565994458723e-05, + "loss": 3.8746, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6141180046948203e-05, + "loss": 3.88, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6132794099437683e-05, + "loss": 3.8685, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6124424530730895e-05, + "loss": 3.8908, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6116038583220375e-05, + "loss": 3.8866, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6107669014513584e-05, + "loss": 3.8812, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6099283067003064e-05, + "loss": 3.8855, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6090897119492544e-05, + "loss": 3.9015, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6082511171982024e-05, + "loss": 3.889, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6074125224471508e-05, + "loss": 3.8877, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6065739276960988e-05, + "loss": 3.8859, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6057353329450468e-05, + "loss": 3.8931, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6048967381939944e-05, + "loss": 3.8882, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6040597813233157e-05, + "loss": 3.8799, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6032211865722637e-05, + "loss": 3.8841, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6023825918212117e-05, + "loss": 3.8802, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6015439970701596e-05, + "loss": 3.8772, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6007054023191076e-05, + "loss": 3.891, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.599868445448429e-05, + "loss": 3.8842, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5990298506973765e-05, + "loss": 3.8914, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5981912559463245e-05, + "loss": 3.8944, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.597352661195273e-05, + "loss": 3.8823, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596515704324594e-05, + "loss": 3.8937, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5956771095735418e-05, + "loss": 3.8929, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5948385148224898e-05, + "loss": 3.8735, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5939999200714378e-05, + "loss": 3.8786, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5931613253203858e-05, + "loss": 3.8742, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5923227305693338e-05, + "loss": 3.8751, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5914841358182818e-05, + "loss": 3.8842, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.59064554106723e-05, + "loss": 3.8941, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.589808584196551e-05, + "loss": 3.8786, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.588969989445499e-05, + "loss": 3.8804, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588131394694447e-05, + "loss": 3.8859, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5872927999433947e-05, + "loss": 3.8826, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5864558430727162e-05, + "loss": 3.8767, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5856172483216642e-05, + "loss": 3.866, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5847786535706122e-05, + "loss": 3.8905, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.58394005881956e-05, + "loss": 3.8934, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.583101464068508e-05, + "loss": 3.8961, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.582264507197829e-05, + "loss": 3.879, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.581425912446777e-05, + "loss": 3.8776, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.580587317695725e-05, + "loss": 3.8796, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.579748722944673e-05, + "loss": 3.8747, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5789117660739944e-05, + "loss": 3.8953, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.578073171322942e-05, + "loss": 3.8658, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.57723457657189e-05, + "loss": 3.9062, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5763959818208384e-05, + "loss": 3.8847, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5755573870697864e-05, + "loss": 3.8671, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5747187923187343e-05, + "loss": 3.8846, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5738818354480553e-05, + "loss": 3.8769, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5730432406970033e-05, + "loss": 3.8657, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5722046459459512e-05, + "loss": 3.8864, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5713660511948992e-05, + "loss": 3.8915, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5705274564438476e-05, + "loss": 3.8761, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5696888616927952e-05, + "loss": 3.8874, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5688502669417432e-05, + "loss": 3.8616, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5680133100710645e-05, + "loss": 3.8761, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5671747153200125e-05, + "loss": 3.8784, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.56633612056896e-05, + "loss": 3.8825, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5654975258179085e-05, + "loss": 3.8785, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5646589310668565e-05, + "loss": 3.8791, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5638203363158045e-05, + "loss": 3.8968, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5629817415647525e-05, + "loss": 3.8826, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5621431468137004e-05, + "loss": 3.8825, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5613061899430214e-05, + "loss": 3.8807, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5604675951919694e-05, + "loss": 3.8801, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5596290004409177e-05, + "loss": 3.8896, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5587904056898657e-05, + "loss": 3.8776, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5579534488191866e-05, + "loss": 3.8803, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5571148540681346e-05, + "loss": 3.8909, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5562762593170826e-05, + "loss": 3.8819, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555439302446404e-05, + "loss": 3.862, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5546007076953518e-05, + "loss": 3.8805, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5537621129442998e-05, + "loss": 3.8869, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5529235181932478e-05, + "loss": 3.8748, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5520849234421958e-05, + "loss": 3.8841, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5512463286911435e-05, + "loss": 3.8821, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5504093718204647e-05, + "loss": 3.8683, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549570777069413e-05, + "loss": 3.8788, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5487321823183607e-05, + "loss": 3.8764, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5478935875673087e-05, + "loss": 3.8937, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5470549928162567e-05, + "loss": 3.8846, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5462163980652047e-05, + "loss": 3.8899, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5453778033141527e-05, + "loss": 3.8749, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.544540846443474e-05, + "loss": 3.8779, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.543702251692422e-05, + "loss": 3.8815, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.54286365694137e-05, + "loss": 3.8864, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.542025062190318e-05, + "loss": 3.888, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541186467439266e-05, + "loss": 3.8846, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.540347872688214e-05, + "loss": 3.8829, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5395109158175348e-05, + "loss": 3.8748, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.538672321066483e-05, + "loss": 3.8873, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.537833726315431e-05, + "loss": 3.8771, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5369951315643788e-05, + "loss": 3.8816, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5361565368133268e-05, + "loss": 3.8771, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5353179420622748e-05, + "loss": 3.8752, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.534480985191596e-05, + "loss": 3.88, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533642390440544e-05, + "loss": 3.8694, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.532803795689492e-05, + "loss": 3.8732, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.53196520093844e-05, + "loss": 3.8842, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.531126606187388e-05, + "loss": 3.8812, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.530288011436336e-05, + "loss": 3.8825, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529449416685284e-05, + "loss": 3.8867, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.528610821934232e-05, + "loss": 3.8974, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5277738650635533e-05, + "loss": 3.8773, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5269352703125013e-05, + "loss": 3.8778, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5260966755614493e-05, + "loss": 3.8781, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5252597186907702e-05, + "loss": 3.886, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5244211239397183e-05, + "loss": 3.8823, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5235825291886663e-05, + "loss": 3.8769, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5227439344376143e-05, + "loss": 3.8768, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5219053396865622e-05, + "loss": 3.8859, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5210667449355102e-05, + "loss": 3.8764, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5202281501844581e-05, + "loss": 3.8781, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5193895554334061e-05, + "loss": 3.8835, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5185525985627272e-05, + "loss": 3.8792, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5177140038116752e-05, + "loss": 3.8798, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5168754090606232e-05, + "loss": 3.8865, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5160368143095712e-05, + "loss": 3.8879, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5151982195585194e-05, + "loss": 3.8774, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5143596248074674e-05, + "loss": 3.8859, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.513521030056415e-05, + "loss": 3.8882, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5126840731857364e-05, + "loss": 3.8779, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5118471163150574e-05, + "loss": 3.8788, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5110101594443788e-05, + "loss": 3.8851, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5101715646933264e-05, + "loss": 3.8941, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5093329699422746e-05, + "loss": 3.8936, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5084943751912226e-05, + "loss": 3.8841, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5076557804401706e-05, + "loss": 3.8809, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5068171856891186e-05, + "loss": 3.8882, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5059785909380666e-05, + "loss": 3.8864, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5051399961870147e-05, + "loss": 3.8761, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5043014014359624e-05, + "loss": 3.8805, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5034644445652838e-05, + "loss": 3.8697, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5026258498142318e-05, + "loss": 3.8819, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5017872550631798e-05, + "loss": 3.8804, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.9902238845825195, + "eval_runtime": 297.5367, + "eval_samples_per_second": 1282.501, + "eval_steps_per_second": 40.079, + "step": 2136960 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 8.66254058415639e+17, + "trial_name": null, + "trial_params": null +}