diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.99228835105896, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/lstm/3/checkpoints/checkpoint-2900160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2900160, + "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": 10.8201, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5492, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0526, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9871, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9407, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8843, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7378, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6415, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5324, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4537, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3806, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3206, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.252, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1814, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1257, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0627, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0237, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9827, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9414, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9069, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.879, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8403, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8174, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7748, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7628, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7318, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.712, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6865, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6532, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6376, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 5.6133, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6036, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5765, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5648, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5546, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5318, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5215, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4777, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4722, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4533, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.439, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.434, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4257, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.3975, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3965, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 5.3909, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.379, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3733, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3563, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3349, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3376, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3174, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3197, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2887, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3009, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2731, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2915, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2634, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2499, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2446, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2396, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2252, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2266, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.198, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.94634467685603e-05, + "loss": 5.195, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2061, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1981, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1816, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1626, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1623, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1629, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1562, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1519, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1479, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1494, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.1399, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 5.1137, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 5.1105, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 5.107, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.095, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.1048, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0855, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.1028, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0783, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0619, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.0673, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0676, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0641, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0502, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0465, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.0385, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 5.0372, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.025, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0226, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.021, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0256, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.0058, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.9998, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.9933, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9894, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.9939, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9811, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9736, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9654, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9688, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9409, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.956, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9429, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9493, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9367, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9451, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9312, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906108507609265e-05, + "loss": 4.9244, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9322, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9104, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9269, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9158, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.9131, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.9006, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.9007, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.9025, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8934, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.8928, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.8821, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.8854, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.8653, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.8692, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8529, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8585, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918573104825e-05, + "loss": 4.8461, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891018715731448e-05, + "loss": 4.8661, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890180120980396e-05, + "loss": 4.8716, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889341526229344e-05, + "loss": 4.8553, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8336, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8458, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.8442, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859887851055094e-05, + "loss": 4.838, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851501903544574e-05, + "loss": 4.8328, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8336, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8306, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8187, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8199, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.819, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8069, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.8075, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.8154, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8038, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.8018, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.8134, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.7907, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.779759407043457, + "eval_runtime": 295.6929, + "eval_samples_per_second": 1290.498, + "eval_steps_per_second": 40.329, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.7784, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.784, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.7984, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7851, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7911, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.765, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7833, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683848468549096e-05, + "loss": 4.7554, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.7691, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7587, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7718, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.7685, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7562, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7493, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.736, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.7379, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.748, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.7439, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.7368, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.7517, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.7459, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.7374, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.7243, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7455, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7214, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.731, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.7272, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.7206, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.85078090860431e-05, + "loss": 4.7096, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849942313853258e-05, + "loss": 4.7089, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849103719102206e-05, + "loss": 4.7119, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848265124351154e-05, + "loss": 4.7087, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847426529600102e-05, + "loss": 4.7094, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.84658793484905e-05, + "loss": 4.7141, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.7046, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449123832273194e-05, + "loss": 4.7035, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440737884762674e-05, + "loss": 4.6828, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432351937252154e-05, + "loss": 4.6883, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423965989741634e-05, + "loss": 4.6799, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.677, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840719409472059e-05, + "loss": 4.6866, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.83988245260138e-05, + "loss": 4.6895, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839043857850328e-05, + "loss": 4.6722, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838205263099276e-05, + "loss": 4.679, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.6768, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.6786, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835691116726493e-05, + "loss": 4.6803, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6717, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.6604, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6692, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832338375602659e-05, + "loss": 4.6563, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831499780851606e-05, + "loss": 4.6655, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830661186100554e-05, + "loss": 4.6524, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.663, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6406, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6642, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6484, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6416, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.6506, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6417, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6337, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6483, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6179, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6246, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6365, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6366, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.6268, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.6177, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.6172, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6221, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.6273, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.6222, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.623, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.628, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6244, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.6059, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6068, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.6139, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.5986, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6103, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807188722472964e-05, + "loss": 4.5963, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806350127721912e-05, + "loss": 4.6213, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.80551153297086e-05, + "loss": 4.6016, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804674576100181e-05, + "loss": 4.5852, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803835981349129e-05, + "loss": 4.5957, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.5981, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802158791847025e-05, + "loss": 4.6022, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.5909, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.5929, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996446454742424e-05, + "loss": 4.5963, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.79880605072319e-05, + "loss": 4.5843, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797967455972138e-05, + "loss": 4.5836, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797128861221086e-05, + "loss": 4.582, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.59, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.5858, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946147148483026e-05, + "loss": 4.5826, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937761200972506e-05, + "loss": 4.5722, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929375253461986e-05, + "loss": 4.5716, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5769, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791260335844095e-05, + "loss": 4.5757, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790421741093043e-05, + "loss": 4.5711, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789584784222364e-05, + "loss": 4.5677, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788747827351685e-05, + "loss": 4.5597, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787909232600633e-05, + "loss": 4.5716, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787070637849581e-05, + "loss": 4.5405, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5647, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785393448347477e-05, + "loss": 4.5553, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5642, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.551, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782879301974694e-05, + "loss": 4.5646, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782040707223642e-05, + "loss": 4.5518, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812021124725906e-05, + "loss": 4.5493, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803635177215386e-05, + "loss": 4.5595, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795249229704866e-05, + "loss": 4.5427, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786863282194346e-05, + "loss": 4.5573, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778477334683826e-05, + "loss": 4.5556, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770107765977035e-05, + "loss": 4.5497, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761721818466515e-05, + "loss": 4.5415, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.5465, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744966302249204e-05, + "loss": 4.5487, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736580354738684e-05, + "loss": 4.5352, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.551, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719808459717644e-05, + "loss": 4.5335, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771143889101086e-05, + "loss": 4.5419, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770305294350034e-05, + "loss": 4.5344, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769466699598982e-05, + "loss": 4.532, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.76862810484793e-05, + "loss": 4.5148, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5305, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5166, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5387, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5492, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5322, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.515, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5288, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5234, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5265, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760243795217783e-05, + "loss": 4.5231, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759405200466731e-05, + "loss": 4.5219, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758566605715679e-05, + "loss": 4.5186, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757731286725373e-05, + "loss": 4.5164, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568926919743206e-05, + "loss": 4.5163, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560540972232686e-05, + "loss": 4.521, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552155024722166e-05, + "loss": 4.5128, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5066, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.5203, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527013560994335e-05, + "loss": 4.5137, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518627613483815e-05, + "loss": 4.5045, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.5231, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5038, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.4971795082092285, + "eval_runtime": 294.126, + "eval_samples_per_second": 1297.373, + "eval_steps_per_second": 40.544, + "step": 152640 + }, + { + "epoch": 2.0, + "learning_rate": 4.749346977095226e-05, + "loss": 4.4931, + "step": 153088 + }, + { + "epoch": 2.0, + "learning_rate": 4.748508382344174e-05, + "loss": 4.4975, + "step": 153600 + }, + { + "epoch": 2.0, + "learning_rate": 4.747671425473495e-05, + "loss": 4.5146, + "step": 154112 + }, + { + "epoch": 2.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.505, + "step": 154624 + }, + { + "epoch": 2.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5102, + "step": 155136 + }, + { + "epoch": 2.0, + "learning_rate": 4.745158916981085e-05, + "loss": 4.4876, + "step": 155648 + }, + { + "epoch": 2.0, + "learning_rate": 4.744320322230033e-05, + "loss": 4.5064, + "step": 156160 + }, + { + "epoch": 2.0, + "learning_rate": 4.743481727478981e-05, + "loss": 4.4791, + "step": 156672 + }, + { + "epoch": 2.0, + "learning_rate": 4.742643132727929e-05, + "loss": 4.5046, + "step": 157184 + }, + { + "epoch": 2.0, + "learning_rate": 4.741804537976877e-05, + "loss": 4.4865, + "step": 157696 + }, + { + "epoch": 2.0, + "learning_rate": 4.740965943225825e-05, + "loss": 4.5028, + "step": 158208 + }, + { + "epoch": 2.0, + "learning_rate": 4.7401273484747736e-05, + "loss": 4.5012, + "step": 158720 + }, + { + "epoch": 2.0, + "learning_rate": 4.7392903916040945e-05, + "loss": 4.4898, + "step": 159232 + }, + { + "epoch": 2.0, + "learning_rate": 4.7384517968530425e-05, + "loss": 4.4859, + "step": 159744 + }, + { + "epoch": 2.0, + "learning_rate": 4.7376132021019905e-05, + "loss": 4.4796, + "step": 160256 + }, + { + "epoch": 2.0, + "learning_rate": 4.7367746073509385e-05, + "loss": 4.4778, + "step": 160768 + }, + { + "epoch": 2.0, + "learning_rate": 4.7359360125998865e-05, + "loss": 4.4841, + "step": 161280 + }, + { + "epoch": 2.0, + "learning_rate": 4.7350974178488345e-05, + "loss": 4.4842, + "step": 161792 + }, + { + "epoch": 2.0, + "learning_rate": 4.7342604609781554e-05, + "loss": 4.484, + "step": 162304 + }, + { + "epoch": 2.0, + "learning_rate": 4.7334218662271034e-05, + "loss": 4.4952, + "step": 162816 + }, + { + "epoch": 2.0, + "learning_rate": 4.7325832714760514e-05, + "loss": 4.4936, + "step": 163328 + }, + { + "epoch": 2.0, + "learning_rate": 4.7317446767249994e-05, + "loss": 4.4881, + "step": 163840 + }, + { + "epoch": 2.0, + "learning_rate": 4.7309060819739474e-05, + "loss": 4.4777, + "step": 164352 + }, + { + "epoch": 2.0, + "learning_rate": 4.7300674872228953e-05, + "loss": 4.4904, + "step": 164864 + }, + { + "epoch": 2.0, + "learning_rate": 4.7292288924718433e-05, + "loss": 4.476, + "step": 165376 + }, + { + "epoch": 2.0, + "learning_rate": 4.728390297720791e-05, + "loss": 4.4827, + "step": 165888 + }, + { + "epoch": 2.0, + "learning_rate": 4.727551702969739e-05, + "loss": 4.4823, + "step": 166400 + }, + { + "epoch": 2.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4769, + "step": 166912 + }, + { + "epoch": 2.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4666, + "step": 167424 + }, + { + "epoch": 2.01, + "learning_rate": 4.725037556596957e-05, + "loss": 4.4681, + "step": 167936 + }, + { + "epoch": 2.01, + "learning_rate": 4.724198961845904e-05, + "loss": 4.4715, + "step": 168448 + }, + { + "epoch": 2.01, + "learning_rate": 4.723360367094852e-05, + "loss": 4.4733, + "step": 168960 + }, + { + "epoch": 2.01, + "learning_rate": 4.7225217723438e-05, + "loss": 4.4762, + "step": 169472 + }, + { + "epoch": 2.01, + "learning_rate": 4.721683177592748e-05, + "loss": 4.4726, + "step": 169984 + }, + { + "epoch": 2.01, + "learning_rate": 4.720846220722069e-05, + "loss": 4.4689, + "step": 170496 + }, + { + "epoch": 2.01, + "learning_rate": 4.720007625971017e-05, + "loss": 4.4692, + "step": 171008 + }, + { + "epoch": 2.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4526, + "step": 171520 + }, + { + "epoch": 2.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4615, + "step": 172032 + }, + { + "epoch": 2.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.4528, + "step": 172544 + }, + { + "epoch": 2.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4521, + "step": 173056 + }, + { + "epoch": 2.01, + "learning_rate": 4.715816290096131e-05, + "loss": 4.4575, + "step": 173568 + }, + { + "epoch": 2.01, + "learning_rate": 4.714977695345079e-05, + "loss": 4.4652, + "step": 174080 + }, + { + "epoch": 2.01, + "learning_rate": 4.714139100594027e-05, + "loss": 4.4516, + "step": 174592 + }, + { + "epoch": 2.01, + "learning_rate": 4.713300505842975e-05, + "loss": 4.4523, + "step": 175104 + }, + { + "epoch": 2.01, + "learning_rate": 4.7124635489722956e-05, + "loss": 4.4615, + "step": 175616 + }, + { + "epoch": 2.01, + "learning_rate": 4.7116249542212436e-05, + "loss": 4.4527, + "step": 176128 + }, + { + "epoch": 2.01, + "learning_rate": 4.7107863594701916e-05, + "loss": 4.4667, + "step": 176640 + }, + { + "epoch": 2.01, + "learning_rate": 4.7099477647191396e-05, + "loss": 4.4512, + "step": 177152 + }, + { + "epoch": 2.01, + "learning_rate": 4.7091108078484605e-05, + "loss": 4.4405, + "step": 177664 + }, + { + "epoch": 2.01, + "learning_rate": 4.708272213097409e-05, + "loss": 4.4557, + "step": 178176 + }, + { + "epoch": 2.01, + "learning_rate": 4.707433618346357e-05, + "loss": 4.4432, + "step": 178688 + }, + { + "epoch": 2.01, + "learning_rate": 4.706595023595305e-05, + "loss": 4.4522, + "step": 179200 + }, + { + "epoch": 2.01, + "learning_rate": 4.705756428844253e-05, + "loss": 4.4412, + "step": 179712 + }, + { + "epoch": 2.01, + "learning_rate": 4.704917834093201e-05, + "loss": 4.4469, + "step": 180224 + }, + { + "epoch": 2.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4371, + "step": 180736 + }, + { + "epoch": 2.01, + "learning_rate": 4.70324228247147e-05, + "loss": 4.4486, + "step": 181248 + }, + { + "epoch": 2.01, + "learning_rate": 4.702403687720418e-05, + "loss": 4.4392, + "step": 181760 + }, + { + "epoch": 2.01, + "learning_rate": 4.701565092969366e-05, + "loss": 4.4362, + "step": 182272 + }, + { + "epoch": 2.01, + "learning_rate": 4.700726498218314e-05, + "loss": 4.4442, + "step": 182784 + }, + { + "epoch": 2.01, + "learning_rate": 4.699889541347635e-05, + "loss": 4.4328, + "step": 183296 + }, + { + "epoch": 2.01, + "learning_rate": 4.699050946596583e-05, + "loss": 4.4279, + "step": 183808 + }, + { + "epoch": 2.01, + "learning_rate": 4.698212351845531e-05, + "loss": 4.4509, + "step": 184320 + }, + { + "epoch": 2.01, + "learning_rate": 4.697373757094479e-05, + "loss": 4.4166, + "step": 184832 + }, + { + "epoch": 2.01, + "learning_rate": 4.6965351623434276e-05, + "loss": 4.4239, + "step": 185344 + }, + { + "epoch": 2.01, + "learning_rate": 4.6956965675923756e-05, + "loss": 4.4303, + "step": 185856 + }, + { + "epoch": 2.01, + "learning_rate": 4.694857972841323e-05, + "loss": 4.4423, + "step": 186368 + }, + { + "epoch": 2.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4291, + "step": 186880 + }, + { + "epoch": 2.01, + "learning_rate": 4.6931824212195925e-05, + "loss": 4.4205, + "step": 187392 + }, + { + "epoch": 2.01, + "learning_rate": 4.69234382646854e-05, + "loss": 4.4233, + "step": 187904 + }, + { + "epoch": 2.01, + "learning_rate": 4.691505231717488e-05, + "loss": 4.4245, + "step": 188416 + }, + { + "epoch": 2.01, + "learning_rate": 4.690666636966436e-05, + "loss": 4.4341, + "step": 188928 + }, + { + "epoch": 2.01, + "learning_rate": 4.6898296800957574e-05, + "loss": 4.4288, + "step": 189440 + }, + { + "epoch": 2.01, + "learning_rate": 4.688991085344705e-05, + "loss": 4.4278, + "step": 189952 + }, + { + "epoch": 2.01, + "learning_rate": 4.688154128474026e-05, + "loss": 4.433, + "step": 190464 + }, + { + "epoch": 2.01, + "learning_rate": 4.687315533722974e-05, + "loss": 4.436, + "step": 190976 + }, + { + "epoch": 2.01, + "learning_rate": 4.686476938971923e-05, + "loss": 4.4169, + "step": 191488 + }, + { + "epoch": 2.01, + "learning_rate": 4.68563834422087e-05, + "loss": 4.4169, + "step": 192000 + }, + { + "epoch": 2.01, + "learning_rate": 4.684799749469818e-05, + "loss": 4.4259, + "step": 192512 + }, + { + "epoch": 2.01, + "learning_rate": 4.68396279259914e-05, + "loss": 4.4087, + "step": 193024 + }, + { + "epoch": 2.01, + "learning_rate": 4.683124197848087e-05, + "loss": 4.4251, + "step": 193536 + }, + { + "epoch": 2.01, + "learning_rate": 4.682285603097035e-05, + "loss": 4.4103, + "step": 194048 + }, + { + "epoch": 2.01, + "learning_rate": 4.681447008345983e-05, + "loss": 4.4326, + "step": 194560 + }, + { + "epoch": 2.01, + "learning_rate": 4.680608413594931e-05, + "loss": 4.4184, + "step": 195072 + }, + { + "epoch": 2.01, + "learning_rate": 4.679771456724252e-05, + "loss": 4.4049, + "step": 195584 + }, + { + "epoch": 2.01, + "learning_rate": 4.6789328619732e-05, + "loss": 4.4091, + "step": 196096 + }, + { + "epoch": 2.01, + "learning_rate": 4.678094267222148e-05, + "loss": 4.4171, + "step": 196608 + }, + { + "epoch": 2.01, + "learning_rate": 4.677255672471097e-05, + "loss": 4.4258, + "step": 197120 + }, + { + "epoch": 2.01, + "learning_rate": 4.676417077720045e-05, + "loss": 4.4099, + "step": 197632 + }, + { + "epoch": 2.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4148, + "step": 198144 + }, + { + "epoch": 2.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4055, + "step": 198656 + }, + { + "epoch": 2.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4166, + "step": 199168 + }, + { + "epoch": 2.02, + "learning_rate": 4.6730643365962096e-05, + "loss": 4.4055, + "step": 199680 + }, + { + "epoch": 2.02, + "learning_rate": 4.6722257418451576e-05, + "loss": 4.4021, + "step": 200192 + }, + { + "epoch": 2.02, + "learning_rate": 4.6713871470941056e-05, + "loss": 4.4138, + "step": 200704 + }, + { + "epoch": 2.02, + "learning_rate": 4.6705485523430536e-05, + "loss": 4.4107, + "step": 201216 + }, + { + "epoch": 2.02, + "learning_rate": 4.6697099575920016e-05, + "loss": 4.4113, + "step": 201728 + }, + { + "epoch": 2.02, + "learning_rate": 4.6688730007213225e-05, + "loss": 4.3995, + "step": 202240 + }, + { + "epoch": 2.02, + "learning_rate": 4.6680344059702705e-05, + "loss": 4.3994, + "step": 202752 + }, + { + "epoch": 2.02, + "learning_rate": 4.6671958112192185e-05, + "loss": 4.4021, + "step": 203264 + }, + { + "epoch": 2.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.404, + "step": 203776 + }, + { + "epoch": 2.02, + "learning_rate": 4.665520259597488e-05, + "loss": 4.4035, + "step": 204288 + }, + { + "epoch": 2.02, + "learning_rate": 4.664681664846436e-05, + "loss": 4.394, + "step": 204800 + }, + { + "epoch": 2.02, + "learning_rate": 4.663843070095384e-05, + "loss": 4.3916, + "step": 205312 + }, + { + "epoch": 2.02, + "learning_rate": 4.663004475344332e-05, + "loss": 4.4033, + "step": 205824 + }, + { + "epoch": 2.02, + "learning_rate": 4.662167518473653e-05, + "loss": 4.3754, + "step": 206336 + }, + { + "epoch": 2.02, + "learning_rate": 4.661328923722601e-05, + "loss": 4.3937, + "step": 206848 + }, + { + "epoch": 2.02, + "learning_rate": 4.660491966851922e-05, + "loss": 4.3852, + "step": 207360 + }, + { + "epoch": 2.02, + "learning_rate": 4.659655009981243e-05, + "loss": 4.3997, + "step": 207872 + }, + { + "epoch": 2.02, + "learning_rate": 4.658816415230191e-05, + "loss": 4.3893, + "step": 208384 + }, + { + "epoch": 2.02, + "learning_rate": 4.657977820479139e-05, + "loss": 4.3975, + "step": 208896 + }, + { + "epoch": 2.02, + "learning_rate": 4.657139225728087e-05, + "loss": 4.3876, + "step": 209408 + }, + { + "epoch": 2.02, + "learning_rate": 4.6563006309770355e-05, + "loss": 4.386, + "step": 209920 + }, + { + "epoch": 2.02, + "learning_rate": 4.6554620362259835e-05, + "loss": 4.397, + "step": 210432 + }, + { + "epoch": 2.02, + "learning_rate": 4.6546234414749315e-05, + "loss": 4.3852, + "step": 210944 + }, + { + "epoch": 2.02, + "learning_rate": 4.6537848467238795e-05, + "loss": 4.3961, + "step": 211456 + }, + { + "epoch": 2.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.3927, + "step": 211968 + }, + { + "epoch": 2.02, + "learning_rate": 4.6521092951021484e-05, + "loss": 4.3928, + "step": 212480 + }, + { + "epoch": 2.02, + "learning_rate": 4.6512707003510964e-05, + "loss": 4.3836, + "step": 212992 + }, + { + "epoch": 2.02, + "learning_rate": 4.6504321056000444e-05, + "loss": 4.3802, + "step": 213504 + }, + { + "epoch": 2.02, + "learning_rate": 4.6495935108489924e-05, + "loss": 4.3954, + "step": 214016 + }, + { + "epoch": 2.02, + "learning_rate": 4.648756553978313e-05, + "loss": 4.3765, + "step": 214528 + }, + { + "epoch": 2.02, + "learning_rate": 4.647917959227261e-05, + "loss": 4.3928, + "step": 215040 + }, + { + "epoch": 2.02, + "learning_rate": 4.647079364476209e-05, + "loss": 4.3781, + "step": 215552 + }, + { + "epoch": 2.02, + "learning_rate": 4.646240769725157e-05, + "loss": 4.3835, + "step": 216064 + }, + { + "epoch": 2.02, + "learning_rate": 4.645402174974105e-05, + "loss": 4.3806, + "step": 216576 + }, + { + "epoch": 2.02, + "learning_rate": 4.644563580223053e-05, + "loss": 4.3797, + "step": 217088 + }, + { + "epoch": 2.02, + "learning_rate": 4.643726623352375e-05, + "loss": 4.3599, + "step": 217600 + }, + { + "epoch": 2.02, + "learning_rate": 4.642889666481696e-05, + "loss": 4.3796, + "step": 218112 + }, + { + "epoch": 2.02, + "learning_rate": 4.642051071730644e-05, + "loss": 4.3646, + "step": 218624 + }, + { + "epoch": 2.02, + "learning_rate": 4.641212476979592e-05, + "loss": 4.3811, + "step": 219136 + }, + { + "epoch": 2.02, + "learning_rate": 4.64037388222854e-05, + "loss": 4.3947, + "step": 219648 + }, + { + "epoch": 2.02, + "learning_rate": 4.639535287477488e-05, + "loss": 4.3884, + "step": 220160 + }, + { + "epoch": 2.02, + "learning_rate": 4.638696692726436e-05, + "loss": 4.3585, + "step": 220672 + }, + { + "epoch": 2.02, + "learning_rate": 4.637858097975383e-05, + "loss": 4.383, + "step": 221184 + }, + { + "epoch": 2.02, + "learning_rate": 4.637019503224331e-05, + "loss": 4.3781, + "step": 221696 + }, + { + "epoch": 2.02, + "learning_rate": 4.636180908473279e-05, + "loss": 4.3758, + "step": 222208 + }, + { + "epoch": 2.02, + "learning_rate": 4.6353439516026006e-05, + "loss": 4.3673, + "step": 222720 + }, + { + "epoch": 2.02, + "learning_rate": 4.6345053568515486e-05, + "loss": 4.3771, + "step": 223232 + }, + { + "epoch": 2.02, + "learning_rate": 4.6336667621004966e-05, + "loss": 4.3712, + "step": 223744 + }, + { + "epoch": 2.02, + "learning_rate": 4.6328281673494446e-05, + "loss": 4.3686, + "step": 224256 + }, + { + "epoch": 2.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.3699, + "step": 224768 + }, + { + "epoch": 2.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3739, + "step": 225280 + }, + { + "epoch": 2.02, + "learning_rate": 4.6303140209766615e-05, + "loss": 4.3683, + "step": 225792 + }, + { + "epoch": 2.02, + "learning_rate": 4.6294754262256095e-05, + "loss": 4.3655, + "step": 226304 + }, + { + "epoch": 2.02, + "learning_rate": 4.6286368314745575e-05, + "loss": 4.3719, + "step": 226816 + }, + { + "epoch": 2.02, + "learning_rate": 4.6277982367235055e-05, + "loss": 4.3701, + "step": 227328 + }, + { + "epoch": 2.02, + "learning_rate": 4.6269596419724535e-05, + "loss": 4.3623, + "step": 227840 + }, + { + "epoch": 2.02, + "learning_rate": 4.6261210472214015e-05, + "loss": 4.378, + "step": 228352 + }, + { + "epoch": 2.02, + "learning_rate": 4.6252824524703495e-05, + "loss": 4.363, + "step": 228864 + }, + { + "epoch": 2.03, + "eval_loss": 4.3638200759887695, + "eval_runtime": 293.4397, + "eval_samples_per_second": 1300.407, + "eval_steps_per_second": 40.639, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6244438577192975e-05, + "loss": 4.3519, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623605262968246e-05, + "loss": 4.3561, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622766668217194e-05, + "loss": 4.3736, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621928073466142e-05, + "loss": 4.3614, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.6210894787150895e-05, + "loss": 4.3746, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.6202508839640374e-05, + "loss": 4.3481, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.6194122892129854e-05, + "loss": 4.3681, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.6185736944619334e-05, + "loss": 4.3374, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.37, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.3507, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3643, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.6152193154577254e-05, + "loss": 4.3637, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614382358587046e-05, + "loss": 4.3506, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613543763835994e-05, + "loss": 4.3544, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612705169084942e-05, + "loss": 4.347, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611866574333891e-05, + "loss": 4.3402, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611027979582839e-05, + "loss": 4.3536, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610189384831787e-05, + "loss": 4.3501, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609350790080735e-05, + "loss": 4.3526, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608512195329683e-05, + "loss": 4.3601, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607673600578631e-05, + "loss": 4.3661, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606835005827578e-05, + "loss": 4.3537, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6059980489569e-05, + "loss": 4.3455, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605159454205848e-05, + "loss": 4.3597, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604320859454796e-05, + "loss": 4.343, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603482264703743e-05, + "loss": 4.3574, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602643669952691e-05, + "loss": 4.3517, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601805075201639e-05, + "loss": 4.3427, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600966480450588e-05, + "loss": 4.339, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600129523579909e-05, + "loss": 4.3438, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599290928828857e-05, + "loss": 4.3411, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598452334077805e-05, + "loss": 4.3479, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597613739326753e-05, + "loss": 4.3493, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596775144575701e-05, + "loss": 4.3457, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595936549824649e-05, + "loss": 4.3466, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595097955073597e-05, + "loss": 4.3438, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594259360322545e-05, + "loss": 4.328, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934224034518656e-05, + "loss": 4.3347, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5925838087008136e-05, + "loss": 4.3273, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917452139497616e-05, + "loss": 4.3334, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909066191987096e-05, + "loss": 4.3347, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590071300208404e-05, + "loss": 4.3399, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589232705457352e-05, + "loss": 4.3338, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.3271, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587555515955248e-05, + "loss": 4.3409, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586716921204196e-05, + "loss": 4.3348, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.3402, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.3326, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3182, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583364180080361e-05, + "loss": 4.3354, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582525585329309e-05, + "loss": 4.3239, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.58168862845863e-05, + "loss": 4.3323, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.5808500337075786e-05, + "loss": 4.3226, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.3224, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.5791728442054746e-05, + "loss": 4.3219, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.3285, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.5774972925837435e-05, + "loss": 4.3237, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766586978326915e-05, + "loss": 4.324, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3247, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3159, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741445514599084e-05, + "loss": 4.3134, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733059567088564e-05, + "loss": 4.3365, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724673619578044e-05, + "loss": 4.3028, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.307, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5707901724557004e-05, + "loss": 4.3121, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699515777046484e-05, + "loss": 4.3291, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691129829535963e-05, + "loss": 4.3143, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.3093, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674357934514923e-05, + "loss": 4.3052, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.3115, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565760241829762e-05, + "loss": 4.3235, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564921647078709e-05, + "loss": 4.315, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564083052327657e-05, + "loss": 4.3144, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563244457576605e-05, + "loss": 4.3265, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562407500705927e-05, + "loss": 4.3234, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561568905954874e-05, + "loss": 4.3063, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560730311203822e-05, + "loss": 4.3082, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559891716452771e-05, + "loss": 4.3193, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559053121701719e-05, + "loss": 4.2947, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558214526950667e-05, + "loss": 4.3154, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557377570079988e-05, + "loss": 4.2996, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556538975328936e-05, + "loss": 4.3249, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555700380577884e-05, + "loss": 4.3089, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548634237072046e-05, + "loss": 4.299, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540248289561526e-05, + "loss": 4.298, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.5531862342051006e-05, + "loss": 4.3115, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523476394540486e-05, + "loss": 4.3189, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515090447029966e-05, + "loss": 4.3057, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.3038, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.2977, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.3091, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.2989, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.2974, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546479114077058e-05, + "loss": 4.3083, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545640519326006e-05, + "loss": 4.308, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544801924574954e-05, + "loss": 4.304, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543964967704275e-05, + "loss": 4.2917, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543126372953223e-05, + "loss": 4.2993, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542287778202171e-05, + "loss": 4.2965, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541449183451119e-05, + "loss": 4.2998, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.54061222658044e-05, + "loss": 4.2998, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539773631829388e-05, + "loss": 4.2901, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538935037078336e-05, + "loss": 4.291, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538096442327284e-05, + "loss": 4.2988, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372578475762326e-05, + "loss": 4.2754, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364192528251806e-05, + "loss": 4.2947, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5355822959545015e-05, + "loss": 4.2803, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347437012034495e-05, + "loss": 4.2987, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339051064523975e-05, + "loss": 4.2887, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330665117013455e-05, + "loss": 4.2948, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532227916950293e-05, + "loss": 4.2858, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531389322199241e-05, + "loss": 4.2887, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530550727448189e-05, + "loss": 4.298, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529712132697137e-05, + "loss": 4.2817, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528875175826458e-05, + "loss": 4.2956, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280365810754064e-05, + "loss": 4.2937, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527199624204728e-05, + "loss": 4.2911, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526361029453675e-05, + "loss": 4.2923, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525522434702623e-05, + "loss": 4.278, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524685477831945e-05, + "loss": 4.2968, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523846883080893e-05, + "loss": 4.2835, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.52300828832984e-05, + "loss": 4.2923, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.2811, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521331098827736e-05, + "loss": 4.2862, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.2841, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519653909325632e-05, + "loss": 4.28, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.51881531457458e-05, + "loss": 4.2678, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.517976719823528e-05, + "loss": 4.2788, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.51713976295285e-05, + "loss": 4.2732, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516301168201798e-05, + "loss": 4.2853, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515462573450746e-05, + "loss": 4.2971, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514623978699694e-05, + "loss": 4.2927, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513785383948642e-05, + "loss": 4.2632, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51294678919759e-05, + "loss": 4.2918, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.5121098323269106e-05, + "loss": 4.283, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.2815, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104326428248066e-05, + "loss": 4.2751, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5095940480737546e-05, + "loss": 4.2838, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087554533227026e-05, + "loss": 4.274, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.5079168585716506e-05, + "loss": 4.2822, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.5070782638205986e-05, + "loss": 4.2744, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.5062396690695466e-05, + "loss": 4.2791, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505402712198868e-05, + "loss": 4.2786, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504564117447816e-05, + "loss": 4.273, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503727160577137e-05, + "loss": 4.2772, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502888565826085e-05, + "loss": 4.2831, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502049971075033e-05, + "loss": 4.267, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501211376323981e-05, + "loss": 4.283, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500372781572929e-05, + "loss": 4.2777, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 4.280254364013672, + "eval_runtime": 297.5027, + "eval_samples_per_second": 1282.647, + "eval_steps_per_second": 40.084, + "step": 305280 + }, + { + "epoch": 1.0, + "learning_rate": 4.4995341868218764e-05, + "loss": 4.2672, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.4986955920708244e-05, + "loss": 4.2652, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.4978569973197724e-05, + "loss": 4.2788, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.497020040449093e-05, + "loss": 4.2729, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.496181445698042e-05, + "loss": 4.2857, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.49534285094699e-05, + "loss": 4.2576, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.494504256195938e-05, + "loss": 4.2749, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.493667299325259e-05, + "loss": 4.2559, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.492828704574207e-05, + "loss": 4.2758, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.491990109823155e-05, + "loss": 4.2644, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.491151515072103e-05, + "loss": 4.2719, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.490312920321051e-05, + "loss": 4.2776, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.489475963450372e-05, + "loss": 4.2592, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.48863736869932e-05, + "loss": 4.2692, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.487798773948268e-05, + "loss": 4.2595, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.486960179197216e-05, + "loss": 4.2516, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.486121584446164e-05, + "loss": 4.2633, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.4852846275754853e-05, + "loss": 4.2644, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.484446032824433e-05, + "loss": 4.2645, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.483607438073381e-05, + "loss": 4.2751, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.482768843322329e-05, + "loss": 4.2809, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.481930248571277e-05, + "loss": 4.2682, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.481093291700598e-05, + "loss": 4.2624, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.480254696949546e-05, + "loss": 4.274, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.479416102198494e-05, + "loss": 4.2549, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.478577507447442e-05, + "loss": 4.2693, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.47773891269639e-05, + "loss": 4.2674, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.476900317945338e-05, + "loss": 4.2542, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.476061723194286e-05, + "loss": 4.2567, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.475223128443234e-05, + "loss": 4.257, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.474386171572556e-05, + "loss": 4.2581, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473547576821504e-05, + "loss": 4.263, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472708982070452e-05, + "loss": 4.2663, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.471872025199773e-05, + "loss": 4.2612, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.471033430448721e-05, + "loss": 4.2636, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.470194835697669e-05, + "loss": 4.2612, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.469356240946617e-05, + "loss": 4.2439, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.468517646195565e-05, + "loss": 4.2542, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.467679051444512e-05, + "loss": 4.2446, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.46684045669346e-05, + "loss": 4.2495, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.466001861942408e-05, + "loss": 4.25, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.4651649050717296e-05, + "loss": 4.2626, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.4643263103206776e-05, + "loss": 4.251, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.4634877155696256e-05, + "loss": 4.2442, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.4626491208185736e-05, + "loss": 4.2608, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.461812163947895e-05, + "loss": 4.251, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.460975207077216e-05, + "loss": 4.2565, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.460136612326164e-05, + "loss": 4.2548, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.459298017575112e-05, + "loss": 4.2373, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.4584594228240594e-05, + "loss": 4.2558, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.4576208280730074e-05, + "loss": 4.2419, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.4567822333219554e-05, + "loss": 4.2545, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.4559436385709033e-05, + "loss": 4.2431, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.4551050438198513e-05, + "loss": 4.2426, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.454266449068799e-05, + "loss": 4.2447, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.4534311300784945e-05, + "loss": 4.2479, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.4525925353274425e-05, + "loss": 4.244, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.45175394057639e-05, + "loss": 4.2443, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.450915345825338e-05, + "loss": 4.2488, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.450076751074286e-05, + "loss": 4.2369, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.449238156323234e-05, + "loss": 4.2332, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.448399561572182e-05, + "loss": 4.2633, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.447562604701503e-05, + "loss": 4.2228, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.446724009950451e-05, + "loss": 4.2295, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.445885415199399e-05, + "loss": 4.2359, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.445046820448347e-05, + "loss": 4.2531, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.444208225697295e-05, + "loss": 4.2312, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.443371268826616e-05, + "loss": 4.2362, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.442532674075564e-05, + "loss": 4.2256, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.441694079324512e-05, + "loss": 4.2352, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.44085548457346e-05, + "loss": 4.2438, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.440016889822408e-05, + "loss": 4.2421, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.439178295071356e-05, + "loss": 4.2389, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.438341338200677e-05, + "loss": 4.2468, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.437502743449625e-05, + "loss": 4.2458, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.436664148698573e-05, + "loss": 4.2326, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435825553947521e-05, + "loss": 4.2317, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.434988597076842e-05, + "loss": 4.2451, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.43415000232579e-05, + "loss": 4.2188, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.433311407574738e-05, + "loss": 4.2389, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.432472812823687e-05, + "loss": 4.2256, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431634218072635e-05, + "loss": 4.2496, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.430795623321583e-05, + "loss": 4.2343, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429957028570531e-05, + "loss": 4.2271, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.429118433819479e-05, + "loss": 4.2183, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.4282814769487996e-05, + "loss": 4.2394, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.4274428821977476e-05, + "loss": 4.2409, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4266042874466956e-05, + "loss": 4.2362, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.425765692695643e-05, + "loss": 4.2287, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.4249287358249645e-05, + "loss": 4.2273, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.4240901410739125e-05, + "loss": 4.2333, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.4232531842032334e-05, + "loss": 4.2241, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.422414589452182e-05, + "loss": 4.2246, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.42157599470113e-05, + "loss": 4.2372, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.420737399950078e-05, + "loss": 4.2329, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.419898805199026e-05, + "loss": 4.2314, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.4190602104479734e-05, + "loss": 4.2222, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.4182216156969214e-05, + "loss": 4.2275, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.4173830209458694e-05, + "loss": 4.221, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.41654606407519e-05, + "loss": 4.2291, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.415707469324138e-05, + "loss": 4.2265, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.414868874573086e-05, + "loss": 4.2235, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.414030279822034e-05, + "loss": 4.2216, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.413193322951356e-05, + "loss": 4.2208, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.412354728200304e-05, + "loss": 4.2159, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.411516133449252e-05, + "loss": 4.2182, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.4106775386982e-05, + "loss": 4.2105, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.409838943947148e-05, + "loss": 4.2279, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.409000349196096e-05, + "loss": 4.2207, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.408163392325417e-05, + "loss": 4.2201, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2145, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.406486202823313e-05, + "loss": 4.224, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.405647608072261e-05, + "loss": 4.2251, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.404809013321209e-05, + "loss": 4.2128, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.403970418570157e-05, + "loss": 4.2264, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.403131823819105e-05, + "loss": 4.2263, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.4022948669484257e-05, + "loss": 4.2218, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.401456272197374e-05, + "loss": 4.2254, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.400617677446322e-05, + "loss": 4.2096, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.39977908269527e-05, + "loss": 4.224, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.398942125824591e-05, + "loss": 4.2194, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.398103531073539e-05, + "loss": 4.2258, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.397264936322487e-05, + "loss": 4.2056, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.396426341571435e-05, + "loss": 4.2226, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.395589384700756e-05, + "loss": 4.2175, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.394750789949704e-05, + "loss": 4.2107, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.393912195198652e-05, + "loss": 4.2028, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.3930736004476e-05, + "loss": 4.2105, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.392236643576921e-05, + "loss": 4.2062, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.39139804882587e-05, + "loss": 4.2198, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.390559454074818e-05, + "loss": 4.2256, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.389720859323766e-05, + "loss": 4.2282, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.388882264572714e-05, + "loss": 4.199, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.388043669821662e-05, + "loss": 4.2242, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.3872067129509826e-05, + "loss": 4.2185, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.2101, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2071, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2206, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.383852333946774e-05, + "loss": 4.2097, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.3830153770760955e-05, + "loss": 4.2138, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.3821767823250435e-05, + "loss": 4.2055, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.3813381875739915e-05, + "loss": 4.212, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.3804995928229395e-05, + "loss": 4.213, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.3796609980718875e-05, + "loss": 4.2095, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.378824041201209e-05, + "loss": 4.2125, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.3779854464501564e-05, + "loss": 4.2178, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.3771468516991044e-05, + "loss": 4.2039, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.3763082569480524e-05, + "loss": 4.2148, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.375471300077374e-05, + "loss": 4.2145, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 4.223569393157959, + "eval_runtime": 297.3907, + "eval_samples_per_second": 1283.13, + "eval_steps_per_second": 40.099, + "step": 381600 + }, + { + "epoch": 2.0, + "learning_rate": 4.374632705326321e-05, + "loss": 4.2015, + "step": 381952 + }, + { + "epoch": 2.0, + "learning_rate": 4.373794110575269e-05, + "loss": 4.1987, + "step": 382464 + }, + { + "epoch": 2.0, + "learning_rate": 4.372955515824217e-05, + "loss": 4.2152, + "step": 382976 + }, + { + "epoch": 2.0, + "learning_rate": 4.372118558953539e-05, + "loss": 4.209, + "step": 383488 + }, + { + "epoch": 2.0, + "learning_rate": 4.371279964202487e-05, + "loss": 4.2164, + "step": 384000 + }, + { + "epoch": 2.0, + "learning_rate": 4.370441369451435e-05, + "loss": 4.2009, + "step": 384512 + }, + { + "epoch": 2.0, + "learning_rate": 4.369602774700383e-05, + "loss": 4.2084, + "step": 385024 + }, + { + "epoch": 2.0, + "learning_rate": 4.368764179949331e-05, + "loss": 4.1936, + "step": 385536 + }, + { + "epoch": 2.0, + "learning_rate": 4.367925585198279e-05, + "loss": 4.2075, + "step": 386048 + }, + { + "epoch": 2.0, + "learning_rate": 4.367086990447227e-05, + "loss": 4.205, + "step": 386560 + }, + { + "epoch": 2.0, + "learning_rate": 4.366248395696175e-05, + "loss": 4.2085, + "step": 387072 + }, + { + "epoch": 2.0, + "learning_rate": 4.365411438825496e-05, + "loss": 4.211, + "step": 387584 + }, + { + "epoch": 2.0, + "learning_rate": 4.3645744819548166e-05, + "loss": 4.2004, + "step": 388096 + }, + { + "epoch": 2.0, + "learning_rate": 4.3637358872037646e-05, + "loss": 4.2017, + "step": 388608 + }, + { + "epoch": 2.0, + "learning_rate": 4.3628972924527126e-05, + "loss": 4.1981, + "step": 389120 + }, + { + "epoch": 2.0, + "learning_rate": 4.3620586977016606e-05, + "loss": 4.1891, + "step": 389632 + }, + { + "epoch": 2.0, + "learning_rate": 4.3612201029506086e-05, + "loss": 4.1968, + "step": 390144 + }, + { + "epoch": 2.0, + "learning_rate": 4.3603815081995566e-05, + "loss": 4.2024, + "step": 390656 + }, + { + "epoch": 2.0, + "learning_rate": 4.359544551328878e-05, + "loss": 4.2019, + "step": 391168 + }, + { + "epoch": 2.0, + "learning_rate": 4.358705956577826e-05, + "loss": 4.2133, + "step": 391680 + }, + { + "epoch": 2.0, + "learning_rate": 4.357867361826774e-05, + "loss": 4.2175, + "step": 392192 + }, + { + "epoch": 2.0, + "learning_rate": 4.357028767075722e-05, + "loss": 4.21, + "step": 392704 + }, + { + "epoch": 2.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.2, + "step": 393216 + }, + { + "epoch": 2.0, + "learning_rate": 4.355353215453991e-05, + "loss": 4.2104, + "step": 393728 + }, + { + "epoch": 2.0, + "learning_rate": 4.354514620702939e-05, + "loss": 4.1982, + "step": 394240 + }, + { + "epoch": 2.0, + "learning_rate": 4.353676025951887e-05, + "loss": 4.2066, + "step": 394752 + }, + { + "epoch": 2.0, + "learning_rate": 4.352837431200835e-05, + "loss": 4.2047, + "step": 395264 + }, + { + "epoch": 2.0, + "learning_rate": 4.351998836449783e-05, + "loss": 4.1902, + "step": 395776 + }, + { + "epoch": 2.0, + "learning_rate": 4.351160241698731e-05, + "loss": 4.194, + "step": 396288 + }, + { + "epoch": 2.0, + "learning_rate": 4.350321646947679e-05, + "loss": 4.2006, + "step": 396800 + }, + { + "epoch": 2.01, + "learning_rate": 4.3494846900770006e-05, + "loss": 4.1986, + "step": 397312 + }, + { + "epoch": 2.01, + "learning_rate": 4.3486460953259486e-05, + "loss": 4.2009, + "step": 397824 + }, + { + "epoch": 2.01, + "learning_rate": 4.3478075005748966e-05, + "loss": 4.2065, + "step": 398336 + }, + { + "epoch": 2.01, + "learning_rate": 4.3469689058238446e-05, + "loss": 4.1991, + "step": 398848 + }, + { + "epoch": 2.01, + "learning_rate": 4.3461319489531655e-05, + "loss": 4.2022, + "step": 399360 + }, + { + "epoch": 2.01, + "learning_rate": 4.3452933542021135e-05, + "loss": 4.2019, + "step": 399872 + }, + { + "epoch": 2.01, + "learning_rate": 4.3444547594510615e-05, + "loss": 4.187, + "step": 400384 + }, + { + "epoch": 2.01, + "learning_rate": 4.3436161647000095e-05, + "loss": 4.1877, + "step": 400896 + }, + { + "epoch": 2.01, + "learning_rate": 4.3427775699489575e-05, + "loss": 4.1847, + "step": 401408 + }, + { + "epoch": 2.01, + "learning_rate": 4.341938975197905e-05, + "loss": 4.1897, + "step": 401920 + }, + { + "epoch": 2.01, + "learning_rate": 4.341100380446853e-05, + "loss": 4.1905, + "step": 402432 + }, + { + "epoch": 2.01, + "learning_rate": 4.340261785695801e-05, + "loss": 4.2032, + "step": 402944 + }, + { + "epoch": 2.01, + "learning_rate": 4.339423190944749e-05, + "loss": 4.191, + "step": 403456 + }, + { + "epoch": 2.01, + "learning_rate": 4.3385862340740704e-05, + "loss": 4.1852, + "step": 403968 + }, + { + "epoch": 2.01, + "learning_rate": 4.3377476393230184e-05, + "loss": 4.205, + "step": 404480 + }, + { + "epoch": 2.01, + "learning_rate": 4.33691068245234e-05, + "loss": 4.1877, + "step": 404992 + }, + { + "epoch": 2.01, + "learning_rate": 4.336072087701287e-05, + "loss": 4.2018, + "step": 405504 + }, + { + "epoch": 2.01, + "learning_rate": 4.335233492950235e-05, + "loss": 4.1937, + "step": 406016 + }, + { + "epoch": 2.01, + "learning_rate": 4.334394898199183e-05, + "loss": 4.1809, + "step": 406528 + }, + { + "epoch": 2.01, + "learning_rate": 4.333556303448131e-05, + "loss": 4.1963, + "step": 407040 + }, + { + "epoch": 2.01, + "learning_rate": 4.332717708697079e-05, + "loss": 4.186, + "step": 407552 + }, + { + "epoch": 2.01, + "learning_rate": 4.331879113946027e-05, + "loss": 4.1991, + "step": 408064 + }, + { + "epoch": 2.01, + "learning_rate": 4.331040519194975e-05, + "loss": 4.1806, + "step": 408576 + }, + { + "epoch": 2.01, + "learning_rate": 4.330203562324296e-05, + "loss": 4.1848, + "step": 409088 + }, + { + "epoch": 2.01, + "learning_rate": 4.329364967573244e-05, + "loss": 4.1831, + "step": 409600 + }, + { + "epoch": 2.01, + "learning_rate": 4.328528010702566e-05, + "loss": 4.1888, + "step": 410112 + }, + { + "epoch": 2.01, + "learning_rate": 4.327689415951514e-05, + "loss": 4.1895, + "step": 410624 + }, + { + "epoch": 2.01, + "learning_rate": 4.326850821200462e-05, + "loss": 4.1813, + "step": 411136 + }, + { + "epoch": 2.01, + "learning_rate": 4.32601222644941e-05, + "loss": 4.1932, + "step": 411648 + }, + { + "epoch": 2.01, + "learning_rate": 4.325173631698358e-05, + "loss": 4.1831, + "step": 412160 + }, + { + "epoch": 2.01, + "learning_rate": 4.324335036947306e-05, + "loss": 4.1724, + "step": 412672 + }, + { + "epoch": 2.01, + "learning_rate": 4.323496442196254e-05, + "loss": 4.2074, + "step": 413184 + }, + { + "epoch": 2.01, + "learning_rate": 4.322657847445202e-05, + "loss": 4.1651, + "step": 413696 + }, + { + "epoch": 2.01, + "learning_rate": 4.3218225284548956e-05, + "loss": 4.1655, + "step": 414208 + }, + { + "epoch": 2.01, + "learning_rate": 4.3209839337038436e-05, + "loss": 4.1798, + "step": 414720 + }, + { + "epoch": 2.01, + "learning_rate": 4.3201453389527916e-05, + "loss": 4.1989, + "step": 415232 + }, + { + "epoch": 2.01, + "learning_rate": 4.3193067442017396e-05, + "loss": 4.1718, + "step": 415744 + }, + { + "epoch": 2.01, + "learning_rate": 4.318469787331061e-05, + "loss": 4.1841, + "step": 416256 + }, + { + "epoch": 2.01, + "learning_rate": 4.317631192580009e-05, + "loss": 4.1687, + "step": 416768 + }, + { + "epoch": 2.01, + "learning_rate": 4.316792597828957e-05, + "loss": 4.178, + "step": 417280 + }, + { + "epoch": 2.01, + "learning_rate": 4.315954003077905e-05, + "loss": 4.1901, + "step": 417792 + }, + { + "epoch": 2.01, + "learning_rate": 4.315115408326853e-05, + "loss": 4.1869, + "step": 418304 + }, + { + "epoch": 2.01, + "learning_rate": 4.314276813575801e-05, + "loss": 4.1833, + "step": 418816 + }, + { + "epoch": 2.01, + "learning_rate": 4.313438218824749e-05, + "loss": 4.1868, + "step": 419328 + }, + { + "epoch": 2.01, + "learning_rate": 4.312599624073697e-05, + "loss": 4.1941, + "step": 419840 + }, + { + "epoch": 2.01, + "learning_rate": 4.311761029322645e-05, + "loss": 4.1736, + "step": 420352 + }, + { + "epoch": 2.01, + "learning_rate": 4.310922434571593e-05, + "loss": 4.1805, + "step": 420864 + }, + { + "epoch": 2.01, + "learning_rate": 4.310085477700914e-05, + "loss": 4.1867, + "step": 421376 + }, + { + "epoch": 2.01, + "learning_rate": 4.309246882949862e-05, + "loss": 4.1664, + "step": 421888 + }, + { + "epoch": 2.01, + "learning_rate": 4.30840828819881e-05, + "loss": 4.1804, + "step": 422400 + }, + { + "epoch": 2.01, + "learning_rate": 4.307569693447758e-05, + "loss": 4.176, + "step": 422912 + }, + { + "epoch": 2.01, + "learning_rate": 4.306731098696706e-05, + "loss": 4.1898, + "step": 423424 + }, + { + "epoch": 2.01, + "learning_rate": 4.305892503945654e-05, + "loss": 4.1822, + "step": 423936 + }, + { + "epoch": 2.01, + "learning_rate": 4.305053909194602e-05, + "loss": 4.1713, + "step": 424448 + }, + { + "epoch": 2.01, + "learning_rate": 4.30421531444355e-05, + "loss": 4.1638, + "step": 424960 + }, + { + "epoch": 2.01, + "learning_rate": 4.303378357572871e-05, + "loss": 4.1832, + "step": 425472 + }, + { + "epoch": 2.01, + "learning_rate": 4.302539762821819e-05, + "loss": 4.1837, + "step": 425984 + }, + { + "epoch": 2.01, + "learning_rate": 4.301701168070767e-05, + "loss": 4.177, + "step": 426496 + }, + { + "epoch": 2.01, + "learning_rate": 4.3008642112000885e-05, + "loss": 4.1788, + "step": 427008 + }, + { + "epoch": 2.02, + "learning_rate": 4.300025616449036e-05, + "loss": 4.1742, + "step": 427520 + }, + { + "epoch": 2.02, + "learning_rate": 4.299187021697984e-05, + "loss": 4.1785, + "step": 428032 + }, + { + "epoch": 2.02, + "learning_rate": 4.298348426946932e-05, + "loss": 4.1701, + "step": 428544 + }, + { + "epoch": 2.02, + "learning_rate": 4.29750983219588e-05, + "loss": 4.1696, + "step": 429056 + }, + { + "epoch": 2.02, + "learning_rate": 4.2966728753252014e-05, + "loss": 4.1847, + "step": 429568 + }, + { + "epoch": 2.02, + "learning_rate": 4.2958342805741494e-05, + "loss": 4.1799, + "step": 430080 + }, + { + "epoch": 2.02, + "learning_rate": 4.2949956858230974e-05, + "loss": 4.1755, + "step": 430592 + }, + { + "epoch": 2.02, + "learning_rate": 4.2941570910720454e-05, + "loss": 4.167, + "step": 431104 + }, + { + "epoch": 2.02, + "learning_rate": 4.2933184963209934e-05, + "loss": 4.1764, + "step": 431616 + }, + { + "epoch": 2.02, + "learning_rate": 4.2924799015699413e-05, + "loss": 4.1647, + "step": 432128 + }, + { + "epoch": 2.02, + "learning_rate": 4.2916413068188893e-05, + "loss": 4.1775, + "step": 432640 + }, + { + "epoch": 2.02, + "learning_rate": 4.29080434994821e-05, + "loss": 4.1742, + "step": 433152 + }, + { + "epoch": 2.02, + "learning_rate": 4.289965755197158e-05, + "loss": 4.1712, + "step": 433664 + }, + { + "epoch": 2.02, + "learning_rate": 4.289128798326479e-05, + "loss": 4.1688, + "step": 434176 + }, + { + "epoch": 2.02, + "learning_rate": 4.288290203575427e-05, + "loss": 4.1608, + "step": 434688 + }, + { + "epoch": 2.02, + "learning_rate": 4.287451608824375e-05, + "loss": 4.1682, + "step": 435200 + }, + { + "epoch": 2.02, + "learning_rate": 4.286613014073324e-05, + "loss": 4.1616, + "step": 435712 + }, + { + "epoch": 2.02, + "learning_rate": 4.285774419322272e-05, + "loss": 4.1626, + "step": 436224 + }, + { + "epoch": 2.02, + "learning_rate": 4.28493582457122e-05, + "loss": 4.1718, + "step": 436736 + }, + { + "epoch": 2.02, + "learning_rate": 4.284097229820168e-05, + "loss": 4.1706, + "step": 437248 + }, + { + "epoch": 2.02, + "learning_rate": 4.283258635069116e-05, + "loss": 4.1674, + "step": 437760 + }, + { + "epoch": 2.02, + "learning_rate": 4.282420040318064e-05, + "loss": 4.1594, + "step": 438272 + }, + { + "epoch": 2.02, + "learning_rate": 4.281581445567012e-05, + "loss": 4.1694, + "step": 438784 + }, + { + "epoch": 2.02, + "learning_rate": 4.28074285081596e-05, + "loss": 4.1731, + "step": 439296 + }, + { + "epoch": 2.02, + "learning_rate": 4.279904256064907e-05, + "loss": 4.1632, + "step": 439808 + }, + { + "epoch": 2.02, + "learning_rate": 4.279067299194229e-05, + "loss": 4.1761, + "step": 440320 + }, + { + "epoch": 2.02, + "learning_rate": 4.278228704443177e-05, + "loss": 4.1718, + "step": 440832 + }, + { + "epoch": 2.02, + "learning_rate": 4.277390109692124e-05, + "loss": 4.1724, + "step": 441344 + }, + { + "epoch": 2.02, + "learning_rate": 4.276551514941072e-05, + "loss": 4.1701, + "step": 441856 + }, + { + "epoch": 2.02, + "learning_rate": 4.2757145580703936e-05, + "loss": 4.1592, + "step": 442368 + }, + { + "epoch": 2.02, + "learning_rate": 4.2748759633193416e-05, + "loss": 4.1673, + "step": 442880 + }, + { + "epoch": 2.02, + "learning_rate": 4.2740373685682896e-05, + "loss": 4.17, + "step": 443392 + }, + { + "epoch": 2.02, + "learning_rate": 4.2731987738172376e-05, + "loss": 4.1747, + "step": 443904 + }, + { + "epoch": 2.02, + "learning_rate": 4.2723601790661856e-05, + "loss": 4.1577, + "step": 444416 + }, + { + "epoch": 2.02, + "learning_rate": 4.2715215843151336e-05, + "loss": 4.168, + "step": 444928 + }, + { + "epoch": 2.02, + "learning_rate": 4.2706829895640816e-05, + "loss": 4.1688, + "step": 445440 + }, + { + "epoch": 2.02, + "learning_rate": 4.2698443948130296e-05, + "loss": 4.1607, + "step": 445952 + }, + { + "epoch": 2.02, + "learning_rate": 4.2690074379423505e-05, + "loss": 4.1487, + "step": 446464 + }, + { + "epoch": 2.02, + "learning_rate": 4.2681688431912985e-05, + "loss": 4.1635, + "step": 446976 + }, + { + "epoch": 2.02, + "learning_rate": 4.2673302484402465e-05, + "loss": 4.1532, + "step": 447488 + }, + { + "epoch": 2.02, + "learning_rate": 4.2664916536891945e-05, + "loss": 4.1688, + "step": 448000 + }, + { + "epoch": 2.02, + "learning_rate": 4.2656546968185154e-05, + "loss": 4.1741, + "step": 448512 + }, + { + "epoch": 2.02, + "learning_rate": 4.264816102067464e-05, + "loss": 4.1765, + "step": 449024 + }, + { + "epoch": 2.02, + "learning_rate": 4.263977507316412e-05, + "loss": 4.148, + "step": 449536 + }, + { + "epoch": 2.02, + "learning_rate": 4.263140550445733e-05, + "loss": 4.1728, + "step": 450048 + }, + { + "epoch": 2.02, + "learning_rate": 4.262301955694681e-05, + "loss": 4.1672, + "step": 450560 + }, + { + "epoch": 2.02, + "learning_rate": 4.261463360943629e-05, + "loss": 4.1596, + "step": 451072 + }, + { + "epoch": 2.02, + "learning_rate": 4.260624766192577e-05, + "loss": 4.1583, + "step": 451584 + }, + { + "epoch": 2.02, + "learning_rate": 4.259786171441525e-05, + "loss": 4.173, + "step": 452096 + }, + { + "epoch": 2.02, + "learning_rate": 4.258949214570846e-05, + "loss": 4.1554, + "step": 452608 + }, + { + "epoch": 2.02, + "learning_rate": 4.258110619819794e-05, + "loss": 4.167, + "step": 453120 + }, + { + "epoch": 2.02, + "learning_rate": 4.257273662949115e-05, + "loss": 4.1544, + "step": 453632 + }, + { + "epoch": 2.02, + "learning_rate": 4.256435068198063e-05, + "loss": 4.1651, + "step": 454144 + }, + { + "epoch": 2.02, + "learning_rate": 4.255596473447011e-05, + "loss": 4.1624, + "step": 454656 + }, + { + "epoch": 2.02, + "learning_rate": 4.2547578786959594e-05, + "loss": 4.1597, + "step": 455168 + }, + { + "epoch": 2.02, + "learning_rate": 4.2539192839449074e-05, + "loss": 4.1673, + "step": 455680 + }, + { + "epoch": 2.02, + "learning_rate": 4.2530806891938554e-05, + "loss": 4.1611, + "step": 456192 + }, + { + "epoch": 2.02, + "learning_rate": 4.2522420944428034e-05, + "loss": 4.1625, + "step": 456704 + }, + { + "epoch": 2.02, + "learning_rate": 4.2514034996917514e-05, + "loss": 4.1584, + "step": 457216 + }, + { + "epoch": 2.02, + "learning_rate": 4.2505649049406994e-05, + "loss": 4.1703, + "step": 457728 + }, + { + "epoch": 2.03, + "eval_loss": 4.182224750518799, + "eval_runtime": 296.6792, + "eval_samples_per_second": 1286.208, + "eval_steps_per_second": 40.195, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497263101896474e-05, + "loss": 4.1577, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488877154385954e-05, + "loss": 4.1487, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480491206875434e-05, + "loss": 4.1613, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247210525936491e-05, + "loss": 4.1642, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246371931185439e-05, + "loss": 4.1669, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245533336434387e-05, + "loss": 4.1527, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244694741683335e-05, + "loss": 4.1579, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243856146932283e-05, + "loss": 4.1455, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243017552181231e-05, + "loss": 4.161, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2421789574301793e-05, + "loss": 4.1541, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241340362679127e-05, + "loss": 4.1639, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240501767928075e-05, + "loss": 4.16, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239664811057396e-05, + "loss": 4.1539, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238826216306344e-05, + "loss": 4.1576, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237987621555292e-05, + "loss": 4.1451, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.23714902680424e-05, + "loss": 4.1408, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236310432053188e-05, + "loss": 4.1502, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235471837302136e-05, + "loss": 4.1585, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234634880431457e-05, + "loss": 4.1525, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233796285680405e-05, + "loss": 4.1701, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232957690929353e-05, + "loss": 4.1659, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232119096178301e-05, + "loss": 4.1642, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231282139307623e-05, + "loss": 4.1532, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230443544556571e-05, + "loss": 4.16, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229604949805519e-05, + "loss": 4.148, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228766355054467e-05, + "loss": 4.1636, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227927760303415e-05, + "loss": 4.1545, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270908034327356e-05, + "loss": 4.144, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262522086816836e-05, + "loss": 4.1519, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254136139306316e-05, + "loss": 4.1513, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224575019179579e-05, + "loss": 4.1513, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223736424428527e-05, + "loss": 4.1568, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228994675578485e-05, + "loss": 4.1562, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220608728067965e-05, + "loss": 4.16, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212222780557445e-05, + "loss": 4.1481, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203836833046925e-05, + "loss": 4.154, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195450885536405e-05, + "loss": 4.149, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187064938025885e-05, + "loss": 4.137, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178678990515365e-05, + "loss": 4.1392, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170293043004845e-05, + "loss": 4.1429, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161907095494325e-05, + "loss": 4.1443, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153521147983804e-05, + "loss": 4.158, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145135200473284e-05, + "loss": 4.1461, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136749252962764e-05, + "loss": 4.1412, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128379684255973e-05, + "loss": 4.1607, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212001011554918e-05, + "loss": 4.1415, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211162416803866e-05, + "loss": 4.1542, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210323822052815e-05, + "loss": 4.1476, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209485227301763e-05, + "loss": 4.1283, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208646632550711e-05, + "loss": 4.1575, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207808037799659e-05, + "loss": 4.1387, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206969443048607e-05, + "loss": 4.1529, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206130848297555e-05, + "loss": 4.1392, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205295529307249e-05, + "loss": 4.1409, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204456934556197e-05, + "loss": 4.1331, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036199776855176e-05, + "loss": 4.1416, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027813829344656e-05, + "loss": 4.1498, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019427881834136e-05, + "loss": 4.133, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011041934323616e-05, + "loss": 4.1496, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.20026559868131e-05, + "loss": 4.1409, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199427003930258e-05, + "loss": 4.1289, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198588409179206e-05, + "loss": 4.1569, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197749814428154e-05, + "loss": 4.1243, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196911219677102e-05, + "loss": 4.1224, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19607262492605e-05, + "loss": 4.1389, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195234030174998e-05, + "loss": 4.1505, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943954354239456e-05, + "loss": 4.1277, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193558478553267e-05, + "loss": 4.1432, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192719883802215e-05, + "loss": 4.122, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918812890511625e-05, + "loss": 4.1381, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910426943001105e-05, + "loss": 4.1428, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190205737429432e-05, + "loss": 4.1406, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.18936714267838e-05, + "loss": 4.1406, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188528547927328e-05, + "loss": 4.1394, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187689953176276e-05, + "loss": 4.151, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868529963055976e-05, + "loss": 4.1303, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860144015545456e-05, + "loss": 4.1384, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851774446838665e-05, + "loss": 4.1378, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843388499328145e-05, + "loss": 4.1251, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835002551817625e-05, + "loss": 4.1371, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826632983110834e-05, + "loss": 4.1334, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818247035600314e-05, + "loss": 4.1467, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809861088089794e-05, + "loss": 4.1443, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801475140579274e-05, + "loss": 4.1224, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793089193068754e-05, + "loss": 4.1235, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784703245558234e-05, + "loss": 4.1401, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776317298047714e-05, + "loss": 4.1445, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767931350537194e-05, + "loss": 4.1371, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.17595617818304e-05, + "loss": 4.1301, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175117583431988e-05, + "loss": 4.1343, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174278988680936e-05, + "loss": 4.1332, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173440393929884e-05, + "loss": 4.1312, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172601799178832e-05, + "loss": 4.1253, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.17176320442778e-05, + "loss": 4.139, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170926247557101e-05, + "loss": 4.1355, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170087652806049e-05, + "loss": 4.137, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169249058054998e-05, + "loss": 4.126, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168410463303946e-05, + "loss": 4.1313, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167571868552894e-05, + "loss": 4.1271, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166733273801842e-05, + "loss": 4.1348, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.16589467905079e-05, + "loss": 4.1317, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165056084299738e-05, + "loss": 4.1255, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164219127429059e-05, + "loss": 4.1327, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163380532678007e-05, + "loss": 4.1211, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162541937926955e-05, + "loss": 4.1249, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161703343175903e-05, + "loss": 4.1206, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160864748424851e-05, + "loss": 4.1241, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160026153673799e-05, + "loss": 4.1236, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159187558922746e-05, + "loss": 4.1341, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158348964171694e-05, + "loss": 4.1192, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575120073010156e-05, + "loss": 4.123, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156673412549964e-05, + "loss": 4.1247, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558348177989116e-05, + "loss": 4.1301, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1549962230478596e-05, + "loss": 4.1245, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154159266177181e-05, + "loss": 4.1369, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.1533206714261285e-05, + "loss": 4.1295, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1524820766750765e-05, + "loss": 4.1297, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151645119804398e-05, + "loss": 4.1294, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150806525053346e-05, + "loss": 4.1215, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499679303022934e-05, + "loss": 4.125, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491293355512414e-05, + "loss": 4.1305, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482907408001894e-05, + "loss": 4.1269, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147452146049138e-05, + "loss": 4.1201, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146613551298086e-05, + "loss": 4.1311, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145774956547034e-05, + "loss": 4.1258, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144936361795982e-05, + "loss": 4.1222, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.14409776704493e-05, + "loss": 4.1086, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143260810174251e-05, + "loss": 4.1206, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142422215423199e-05, + "loss": 4.1132, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141583620672147e-05, + "loss": 4.1288, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140745025921095e-05, + "loss": 4.1346, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139908069050416e-05, + "loss": 4.1341, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139069474299364e-05, + "loss": 4.1082, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138230879548312e-05, + "loss": 4.1327, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.13739228479726e-05, + "loss": 4.1264, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136553690046208e-05, + "loss": 4.1237, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357150952951565e-05, + "loss": 4.1172, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348765005441045e-05, + "loss": 4.132, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340379057930525e-05, + "loss": 4.1146, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332009489223734e-05, + "loss": 4.1311, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1323623541713214e-05, + "loss": 4.1123, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315237594202694e-05, + "loss": 4.1255, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1306851646692174e-05, + "loss": 4.1217, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129849845678911e-05, + "loss": 4.1193, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129011250927859e-05, + "loss": 4.1245, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128172656176807e-05, + "loss": 4.1224, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127334061425755e-05, + "loss": 4.1219, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649874243545e-05, + "loss": 4.1185, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125660147684398e-05, + "loss": 4.133, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.151233673095703, + "eval_runtime": 295.0048, + "eval_samples_per_second": 1293.508, + "eval_steps_per_second": 40.423, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124821552933346e-05, + "loss": 4.1152, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123982958182294e-05, + "loss": 4.1088, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123144363431242e-05, + "loss": 4.1262, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230576868019e-05, + "loss": 4.1241, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121467173929138e-05, + "loss": 4.1268, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120628579178086e-05, + "loss": 4.1162, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119789984427034e-05, + "loss": 4.1205, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118951389675982e-05, + "loss": 4.1066, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11811279492493e-05, + "loss": 4.1211, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117274200173877e-05, + "loss": 4.1183, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116435605422826e-05, + "loss": 4.121, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115597010671774e-05, + "loss": 4.1215, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114761691681468e-05, + "loss": 4.1185, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113923096930416e-05, + "loss": 4.1137, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113084502179364e-05, + "loss": 4.1077, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112245907428312e-05, + "loss": 4.1015, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114073126772595e-05, + "loss": 4.1133, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1105687179262075e-05, + "loss": 4.1179, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097301231751555e-05, + "loss": 4.113, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1088915284241035e-05, + "loss": 4.1247, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080529336730515e-05, + "loss": 4.1303, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072143389219995e-05, + "loss": 4.1285, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063757441709475e-05, + "loss": 4.1151, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055371494198955e-05, + "loss": 4.1189, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1046985546688435e-05, + "loss": 4.1169, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103861597798165e-05, + "loss": 4.1211, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103023003047113e-05, + "loss": 4.1146, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102184408296061e-05, + "loss": 4.1124, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101347451425382e-05, + "loss": 4.1154, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10050885667433e-05, + "loss": 4.1121, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099670261923278e-05, + "loss": 4.1096, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098831667172226e-05, + "loss": 4.1183, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097993072421174e-05, + "loss": 4.1216, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097154477670122e-05, + "loss": 4.1201, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096317520799443e-05, + "loss": 4.1097, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095478926048391e-05, + "loss": 4.1204, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094640331297339e-05, + "loss": 4.1151, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938033744266604e-05, + "loss": 4.0976, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929647796756084e-05, + "loss": 4.102, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921261849245564e-05, + "loss": 4.1059, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0912875901735044e-05, + "loss": 4.1114, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904489954224524e-05, + "loss": 4.1159, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896104006714004e-05, + "loss": 4.1096, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0887718059203484e-05, + "loss": 4.1017, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087933211169296e-05, + "loss": 4.1254, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087094616418244e-05, + "loss": 4.1052, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086256021667192e-05, + "loss": 4.1186, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085419064796513e-05, + "loss": 4.1138, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084580470045461e-05, + "loss": 4.086, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083741875294409e-05, + "loss": 4.125, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082903280543357e-05, + "loss": 4.0994, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082064685792305e-05, + "loss": 4.1152, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1055, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1013, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079548901539149e-05, + "loss": 4.1017, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.07871194466847e-05, + "loss": 4.1014, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077874987797791e-05, + "loss": 4.1191, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077036393046739e-05, + "loss": 4.0928, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076197798295687e-05, + "loss": 4.1125, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075360841425008e-05, + "loss": 4.1094, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745222466739566e-05, + "loss": 4.0909, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736836519229046e-05, + "loss": 4.1172, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728450571718526e-05, + "loss": 4.0943, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720064624208006e-05, + "loss": 4.0893, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0711678676697486e-05, + "loss": 4.1002, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703292729186966e-05, + "loss": 4.1109, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0694906781676446e-05, + "loss": 4.0943, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0686520834165926e-05, + "loss": 4.1089, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678134886655406e-05, + "loss": 4.0867, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0669748939144886e-05, + "loss": 4.0992, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661362991634366e-05, + "loss": 4.1085, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652993422927575e-05, + "loss": 4.1021, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0644607475417055e-05, + "loss": 4.1086, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636221527906535e-05, + "loss": 4.1022, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627835580396015e-05, + "loss": 4.1127, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619449632885495e-05, + "loss": 4.0984, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061108006417871e-05, + "loss": 4.1043, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060269411666819e-05, + "loss": 4.0969, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059430816915767e-05, + "loss": 4.0954, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058595497925461e-05, + "loss": 4.1005, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057756903174409e-05, + "loss": 4.1001, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056918308423357e-05, + "loss": 4.1083, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056079713672305e-05, + "loss": 4.1124, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055241118921253e-05, + "loss": 4.0848, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054402524170201e-05, + "loss": 4.0888, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053563929419149e-05, + "loss": 4.1023, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052725334668097e-05, + "loss": 4.109, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051886739917045e-05, + "loss": 4.1014, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510497830463664e-05, + "loss": 4.0961, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502111882953144e-05, + "loss": 4.1042, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049372593544262e-05, + "loss": 4.0952, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.04853399879321e-05, + "loss": 4.0982, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047695404042158e-05, + "loss": 4.0909, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046856809291106e-05, + "loss": 4.1029, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460198524204267e-05, + "loss": 4.1042, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0451812576693746e-05, + "loss": 4.1046, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443426629183226e-05, + "loss": 4.0925, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435040681672706e-05, + "loss": 4.0928, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0426654734162186e-05, + "loss": 4.0913, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418268786651666e-05, + "loss": 4.1014, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040988283914115e-05, + "loss": 4.0994, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040151327043436e-05, + "loss": 4.0901, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039312732292384e-05, + "loss": 4.0965, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038474137541332e-05, + "loss": 4.088, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.03763554279028e-05, + "loss": 4.089, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036798585919601e-05, + "loss": 4.0848, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035959991168549e-05, + "loss": 4.0927, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035121396417497e-05, + "loss": 4.0912, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034282801666445e-05, + "loss": 4.0967, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033445844795766e-05, + "loss": 4.0906, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032607250044714e-05, + "loss": 4.0838, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031768655293662e-05, + "loss": 4.0935, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030930060542611e-05, + "loss": 4.0944, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0300931036719316e-05, + "loss": 4.0927, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0292545089208796e-05, + "loss": 4.101, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284159141698276e-05, + "loss": 4.0937, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275773194187756e-05, + "loss": 4.1031, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267403625480965e-05, + "loss": 4.0936, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259017677970445e-05, + "loss": 4.0885, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250631730459925e-05, + "loss": 4.0898, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242245782949405e-05, + "loss": 4.1031, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233859835438885e-05, + "loss": 4.0915, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225473887928365e-05, + "loss": 4.0871, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217104319221574e-05, + "loss": 4.0966, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020871837171106e-05, + "loss": 4.0956, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020033242420054e-05, + "loss": 4.0858, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019194647669002e-05, + "loss": 4.0794, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018357690798323e-05, + "loss": 4.0876, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017519096047271e-05, + "loss": 4.0816, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016680501296219e-05, + "loss": 4.0954, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015841906545167e-05, + "loss": 4.1015, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015003311794115e-05, + "loss": 4.1029, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014164717043063e-05, + "loss": 4.0751, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.01332612229201e-05, + "loss": 4.1009, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012487527540958e-05, + "loss": 4.0927, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.01165057067028e-05, + "loss": 4.0909, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010811975919228e-05, + "loss": 4.0849, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009973381168176e-05, + "loss": 4.0974, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009134786417124e-05, + "loss": 4.0854, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008296191666072e-05, + "loss": 4.1009, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007459234795393e-05, + "loss": 4.0793, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006620640044341e-05, + "loss": 4.0917, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005782045293289e-05, + "loss": 4.091, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004943450542237e-05, + "loss": 4.0891, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004104855791185e-05, + "loss": 4.0911, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032678989205056e-05, + "loss": 4.0887, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024293041694536e-05, + "loss": 4.0922, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015907094184016e-05, + "loss": 4.0885, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000753752547723e-05, + "loss": 4.0977, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.12639856338501, + "eval_runtime": 294.6039, + "eval_samples_per_second": 1295.268, + "eval_steps_per_second": 40.478, + "step": 610560 + }, + { + "epoch": 2.0, + "learning_rate": 3.999915157796671e-05, + "loss": 4.0801, + "step": 610816 + }, + { + "epoch": 2.0, + "learning_rate": 3.999076563045619e-05, + "loss": 4.0796, + "step": 611328 + }, + { + "epoch": 2.0, + "learning_rate": 3.998237968294567e-05, + "loss": 4.0896, + "step": 611840 + }, + { + "epoch": 2.0, + "learning_rate": 3.997399373543515e-05, + "loss": 4.0926, + "step": 612352 + }, + { + "epoch": 2.0, + "learning_rate": 3.996560778792463e-05, + "loss": 4.0973, + "step": 612864 + }, + { + "epoch": 2.0, + "learning_rate": 3.995722184041411e-05, + "loss": 4.0832, + "step": 613376 + }, + { + "epoch": 2.0, + "learning_rate": 3.994883589290359e-05, + "loss": 4.0927, + "step": 613888 + }, + { + "epoch": 2.0, + "learning_rate": 3.99404663241968e-05, + "loss": 4.0774, + "step": 614400 + }, + { + "epoch": 2.0, + "learning_rate": 3.993208037668628e-05, + "loss": 4.0843, + "step": 614912 + }, + { + "epoch": 2.0, + "learning_rate": 3.992369442917576e-05, + "loss": 4.0876, + "step": 615424 + }, + { + "epoch": 2.0, + "learning_rate": 3.991530848166524e-05, + "loss": 4.0899, + "step": 615936 + }, + { + "epoch": 2.0, + "learning_rate": 3.990693891295845e-05, + "loss": 4.0886, + "step": 616448 + }, + { + "epoch": 2.0, + "learning_rate": 3.9898569344251665e-05, + "loss": 4.0906, + "step": 616960 + }, + { + "epoch": 2.0, + "learning_rate": 3.9890183396741145e-05, + "loss": 4.0788, + "step": 617472 + }, + { + "epoch": 2.0, + "learning_rate": 3.9881797449230625e-05, + "loss": 4.0784, + "step": 617984 + }, + { + "epoch": 2.0, + "learning_rate": 3.9873411501720105e-05, + "loss": 4.0706, + "step": 618496 + }, + { + "epoch": 2.0, + "learning_rate": 3.9865025554209585e-05, + "loss": 4.0823, + "step": 619008 + }, + { + "epoch": 2.0, + "learning_rate": 3.9856655985502794e-05, + "loss": 4.0914, + "step": 619520 + }, + { + "epoch": 2.0, + "learning_rate": 3.9848270037992274e-05, + "loss": 4.0783, + "step": 620032 + }, + { + "epoch": 2.0, + "learning_rate": 3.9839884090481754e-05, + "loss": 4.0934, + "step": 620544 + }, + { + "epoch": 2.0, + "learning_rate": 3.9831498142971234e-05, + "loss": 4.0977, + "step": 621056 + }, + { + "epoch": 2.0, + "learning_rate": 3.9823112195460714e-05, + "loss": 4.0954, + "step": 621568 + }, + { + "epoch": 2.0, + "learning_rate": 3.9814726247950194e-05, + "loss": 4.0904, + "step": 622080 + }, + { + "epoch": 2.0, + "learning_rate": 3.9806340300439674e-05, + "loss": 4.082, + "step": 622592 + }, + { + "epoch": 2.0, + "learning_rate": 3.9797954352929154e-05, + "loss": 4.0836, + "step": 623104 + }, + { + "epoch": 2.0, + "learning_rate": 3.97896011630261e-05, + "loss": 4.0896, + "step": 623616 + }, + { + "epoch": 2.0, + "learning_rate": 3.978121521551558e-05, + "loss": 4.0898, + "step": 624128 + }, + { + "epoch": 2.0, + "learning_rate": 3.977282926800506e-05, + "loss": 4.08, + "step": 624640 + }, + { + "epoch": 2.0, + "learning_rate": 3.976444332049454e-05, + "loss": 4.0851, + "step": 625152 + }, + { + "epoch": 2.0, + "learning_rate": 3.975605737298402e-05, + "loss": 4.0817, + "step": 625664 + }, + { + "epoch": 2.01, + "learning_rate": 3.97476714254735e-05, + "loss": 4.0773, + "step": 626176 + }, + { + "epoch": 2.01, + "learning_rate": 3.973928547796298e-05, + "loss": 4.0864, + "step": 626688 + }, + { + "epoch": 2.01, + "learning_rate": 3.973089953045246e-05, + "loss": 4.0876, + "step": 627200 + }, + { + "epoch": 2.01, + "learning_rate": 3.972252996174567e-05, + "loss": 4.0903, + "step": 627712 + }, + { + "epoch": 2.01, + "learning_rate": 3.971416039303888e-05, + "loss": 4.0801, + "step": 628224 + }, + { + "epoch": 2.01, + "learning_rate": 3.970579082433209e-05, + "loss": 4.088, + "step": 628736 + }, + { + "epoch": 2.01, + "learning_rate": 3.969740487682157e-05, + "loss": 4.0864, + "step": 629248 + }, + { + "epoch": 2.01, + "learning_rate": 3.968901892931105e-05, + "loss": 4.0638, + "step": 629760 + }, + { + "epoch": 2.01, + "learning_rate": 3.968063298180053e-05, + "loss": 4.0761, + "step": 630272 + }, + { + "epoch": 2.01, + "learning_rate": 3.967224703429001e-05, + "loss": 4.0704, + "step": 630784 + }, + { + "epoch": 2.01, + "learning_rate": 3.966386108677949e-05, + "loss": 4.0773, + "step": 631296 + }, + { + "epoch": 2.01, + "learning_rate": 3.965547513926897e-05, + "loss": 4.0906, + "step": 631808 + }, + { + "epoch": 2.01, + "learning_rate": 3.964708919175845e-05, + "loss": 4.0778, + "step": 632320 + }, + { + "epoch": 2.01, + "learning_rate": 3.963871962305166e-05, + "loss": 4.074, + "step": 632832 + }, + { + "epoch": 2.01, + "learning_rate": 3.963033367554114e-05, + "loss": 4.088, + "step": 633344 + }, + { + "epoch": 2.01, + "learning_rate": 3.962194772803062e-05, + "loss": 4.0767, + "step": 633856 + }, + { + "epoch": 2.01, + "learning_rate": 3.96135617805201e-05, + "loss": 4.0909, + "step": 634368 + }, + { + "epoch": 2.01, + "learning_rate": 3.960519221181331e-05, + "loss": 4.0831, + "step": 634880 + }, + { + "epoch": 2.01, + "learning_rate": 3.959680626430279e-05, + "loss": 4.057, + "step": 635392 + }, + { + "epoch": 2.01, + "learning_rate": 3.958842031679228e-05, + "loss": 4.0938, + "step": 635904 + }, + { + "epoch": 2.01, + "learning_rate": 3.958003436928176e-05, + "loss": 4.0709, + "step": 636416 + }, + { + "epoch": 2.01, + "learning_rate": 3.957164842177124e-05, + "loss": 4.0841, + "step": 636928 + }, + { + "epoch": 2.01, + "learning_rate": 3.956326247426071e-05, + "loss": 4.0752, + "step": 637440 + }, + { + "epoch": 2.01, + "learning_rate": 3.955487652675019e-05, + "loss": 4.0722, + "step": 637952 + }, + { + "epoch": 2.01, + "learning_rate": 3.9546506958043406e-05, + "loss": 4.0704, + "step": 638464 + }, + { + "epoch": 2.01, + "learning_rate": 3.953812101053288e-05, + "loss": 4.0727, + "step": 638976 + }, + { + "epoch": 2.01, + "learning_rate": 3.952973506302236e-05, + "loss": 4.0916, + "step": 639488 + }, + { + "epoch": 2.01, + "learning_rate": 3.952134911551184e-05, + "loss": 4.062, + "step": 640000 + }, + { + "epoch": 2.01, + "learning_rate": 3.951296316800132e-05, + "loss": 4.0881, + "step": 640512 + }, + { + "epoch": 2.01, + "learning_rate": 3.95045772204908e-05, + "loss": 4.0772, + "step": 641024 + }, + { + "epoch": 2.01, + "learning_rate": 3.949619127298028e-05, + "loss": 4.0582, + "step": 641536 + }, + { + "epoch": 2.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.0887, + "step": 642048 + }, + { + "epoch": 2.01, + "learning_rate": 3.9479435756762975e-05, + "loss": 4.0667, + "step": 642560 + }, + { + "epoch": 2.01, + "learning_rate": 3.9471049809252455e-05, + "loss": 4.0557, + "step": 643072 + }, + { + "epoch": 2.01, + "learning_rate": 3.9462663861741935e-05, + "loss": 4.0695, + "step": 643584 + }, + { + "epoch": 2.01, + "learning_rate": 3.9454294293035144e-05, + "loss": 4.08, + "step": 644096 + }, + { + "epoch": 2.01, + "learning_rate": 3.9445908345524624e-05, + "loss": 4.0673, + "step": 644608 + }, + { + "epoch": 2.01, + "learning_rate": 3.9437522398014104e-05, + "loss": 4.0776, + "step": 645120 + }, + { + "epoch": 2.01, + "learning_rate": 3.9429136450503584e-05, + "loss": 4.0612, + "step": 645632 + }, + { + "epoch": 2.01, + "learning_rate": 3.9420750502993064e-05, + "loss": 4.0664, + "step": 646144 + }, + { + "epoch": 2.01, + "learning_rate": 3.9412364555482544e-05, + "loss": 4.0786, + "step": 646656 + }, + { + "epoch": 2.01, + "learning_rate": 3.9403978607972024e-05, + "loss": 4.0759, + "step": 647168 + }, + { + "epoch": 2.01, + "learning_rate": 3.939560903926523e-05, + "loss": 4.0764, + "step": 647680 + }, + { + "epoch": 2.01, + "learning_rate": 3.938722309175471e-05, + "loss": 4.072, + "step": 648192 + }, + { + "epoch": 2.01, + "learning_rate": 3.93788371442442e-05, + "loss": 4.0875, + "step": 648704 + }, + { + "epoch": 2.01, + "learning_rate": 3.937045119673368e-05, + "loss": 4.0671, + "step": 649216 + }, + { + "epoch": 2.01, + "learning_rate": 3.936206524922316e-05, + "loss": 4.0771, + "step": 649728 + }, + { + "epoch": 2.01, + "learning_rate": 3.93537120593201e-05, + "loss": 4.0663, + "step": 650240 + }, + { + "epoch": 2.01, + "learning_rate": 3.934532611180958e-05, + "loss": 4.0659, + "step": 650752 + }, + { + "epoch": 2.01, + "learning_rate": 3.933694016429906e-05, + "loss": 4.0746, + "step": 651264 + }, + { + "epoch": 2.01, + "learning_rate": 3.932855421678854e-05, + "loss": 4.068, + "step": 651776 + }, + { + "epoch": 2.01, + "learning_rate": 3.932016826927802e-05, + "loss": 4.0776, + "step": 652288 + }, + { + "epoch": 2.01, + "learning_rate": 3.93117823217675e-05, + "loss": 4.0874, + "step": 652800 + }, + { + "epoch": 2.01, + "learning_rate": 3.930339637425698e-05, + "loss": 4.0556, + "step": 653312 + }, + { + "epoch": 2.01, + "learning_rate": 3.929501042674646e-05, + "loss": 4.0592, + "step": 653824 + }, + { + "epoch": 2.01, + "learning_rate": 3.928662447923594e-05, + "loss": 4.0751, + "step": 654336 + }, + { + "epoch": 2.01, + "learning_rate": 3.927823853172542e-05, + "loss": 4.0764, + "step": 654848 + }, + { + "epoch": 2.01, + "learning_rate": 3.92698525842149e-05, + "loss": 4.0744, + "step": 655360 + }, + { + "epoch": 2.01, + "learning_rate": 3.926148301550811e-05, + "loss": 4.0686, + "step": 655872 + }, + { + "epoch": 2.02, + "learning_rate": 3.925309706799759e-05, + "loss": 4.0733, + "step": 656384 + }, + { + "epoch": 2.02, + "learning_rate": 3.9244711120487066e-05, + "loss": 4.0685, + "step": 656896 + }, + { + "epoch": 2.02, + "learning_rate": 3.9236325172976546e-05, + "loss": 4.0655, + "step": 657408 + }, + { + "epoch": 2.02, + "learning_rate": 3.9227939225466026e-05, + "loss": 4.0661, + "step": 657920 + }, + { + "epoch": 2.02, + "learning_rate": 3.9219553277955506e-05, + "loss": 4.0756, + "step": 658432 + }, + { + "epoch": 2.02, + "learning_rate": 3.9211183709248715e-05, + "loss": 4.0771, + "step": 658944 + }, + { + "epoch": 2.02, + "learning_rate": 3.9202797761738195e-05, + "loss": 4.0749, + "step": 659456 + }, + { + "epoch": 2.02, + "learning_rate": 3.9194411814227675e-05, + "loss": 4.0616, + "step": 659968 + }, + { + "epoch": 2.02, + "learning_rate": 3.9186025866717155e-05, + "loss": 4.0666, + "step": 660480 + }, + { + "epoch": 2.02, + "learning_rate": 3.9177639919206635e-05, + "loss": 4.0633, + "step": 660992 + }, + { + "epoch": 2.02, + "learning_rate": 3.9169253971696115e-05, + "loss": 4.0712, + "step": 661504 + }, + { + "epoch": 2.02, + "learning_rate": 3.91608680241856e-05, + "loss": 4.0724, + "step": 662016 + }, + { + "epoch": 2.02, + "learning_rate": 3.915249845547881e-05, + "loss": 4.0596, + "step": 662528 + }, + { + "epoch": 2.02, + "learning_rate": 3.914411250796829e-05, + "loss": 4.0705, + "step": 663040 + }, + { + "epoch": 2.02, + "learning_rate": 3.913572656045777e-05, + "loss": 4.0547, + "step": 663552 + }, + { + "epoch": 2.02, + "learning_rate": 3.912734061294725e-05, + "loss": 4.062, + "step": 664064 + }, + { + "epoch": 2.02, + "learning_rate": 3.911897104424046e-05, + "loss": 4.0557, + "step": 664576 + }, + { + "epoch": 2.02, + "learning_rate": 3.911060147553367e-05, + "loss": 4.066, + "step": 665088 + }, + { + "epoch": 2.02, + "learning_rate": 3.910221552802315e-05, + "loss": 4.0643, + "step": 665600 + }, + { + "epoch": 2.02, + "learning_rate": 3.909382958051263e-05, + "loss": 4.0686, + "step": 666112 + }, + { + "epoch": 2.02, + "learning_rate": 3.908544363300211e-05, + "loss": 4.0593, + "step": 666624 + }, + { + "epoch": 2.02, + "learning_rate": 3.907705768549159e-05, + "loss": 4.0591, + "step": 667136 + }, + { + "epoch": 2.02, + "learning_rate": 3.906867173798107e-05, + "loss": 4.0607, + "step": 667648 + }, + { + "epoch": 2.02, + "learning_rate": 3.9060285790470555e-05, + "loss": 4.0701, + "step": 668160 + }, + { + "epoch": 2.02, + "learning_rate": 3.9051899842960035e-05, + "loss": 4.0636, + "step": 668672 + }, + { + "epoch": 2.02, + "learning_rate": 3.9043513895449515e-05, + "loss": 4.0681, + "step": 669184 + }, + { + "epoch": 2.02, + "learning_rate": 3.9035127947938995e-05, + "loss": 4.0659, + "step": 669696 + }, + { + "epoch": 2.02, + "learning_rate": 3.9026742000428475e-05, + "loss": 4.0765, + "step": 670208 + }, + { + "epoch": 2.02, + "learning_rate": 3.9018372431721684e-05, + "loss": 4.0665, + "step": 670720 + }, + { + "epoch": 2.02, + "learning_rate": 3.9009986484211164e-05, + "loss": 4.0597, + "step": 671232 + }, + { + "epoch": 2.02, + "learning_rate": 3.9001600536700644e-05, + "loss": 4.0657, + "step": 671744 + }, + { + "epoch": 2.02, + "learning_rate": 3.8993214589190124e-05, + "loss": 4.0724, + "step": 672256 + }, + { + "epoch": 2.02, + "learning_rate": 3.8984828641679604e-05, + "loss": 4.0638, + "step": 672768 + }, + { + "epoch": 2.02, + "learning_rate": 3.897644269416908e-05, + "loss": 4.0598, + "step": 673280 + }, + { + "epoch": 2.02, + "learning_rate": 3.896805674665856e-05, + "loss": 4.066, + "step": 673792 + }, + { + "epoch": 2.02, + "learning_rate": 3.895967079914804e-05, + "loss": 4.0687, + "step": 674304 + }, + { + "epoch": 2.02, + "learning_rate": 3.895130123044125e-05, + "loss": 4.0586, + "step": 674816 + }, + { + "epoch": 2.02, + "learning_rate": 3.894291528293073e-05, + "loss": 4.052, + "step": 675328 + }, + { + "epoch": 2.02, + "learning_rate": 3.893454571422395e-05, + "loss": 4.0596, + "step": 675840 + }, + { + "epoch": 2.02, + "learning_rate": 3.892615976671343e-05, + "loss": 4.0523, + "step": 676352 + }, + { + "epoch": 2.02, + "learning_rate": 3.89177738192029e-05, + "loss": 4.0695, + "step": 676864 + }, + { + "epoch": 2.02, + "learning_rate": 3.890938787169238e-05, + "loss": 4.0699, + "step": 677376 + }, + { + "epoch": 2.02, + "learning_rate": 3.890100192418186e-05, + "loss": 4.0732, + "step": 677888 + }, + { + "epoch": 2.02, + "learning_rate": 3.889261597667134e-05, + "loss": 4.0493, + "step": 678400 + }, + { + "epoch": 2.02, + "learning_rate": 3.888423002916082e-05, + "loss": 4.0732, + "step": 678912 + }, + { + "epoch": 2.02, + "learning_rate": 3.88758440816503e-05, + "loss": 4.065, + "step": 679424 + }, + { + "epoch": 2.02, + "learning_rate": 3.886747451294351e-05, + "loss": 4.0636, + "step": 679936 + }, + { + "epoch": 2.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0602, + "step": 680448 + }, + { + "epoch": 2.02, + "learning_rate": 3.885070261792248e-05, + "loss": 4.061, + "step": 680960 + }, + { + "epoch": 2.02, + "learning_rate": 3.884231667041196e-05, + "loss": 4.0603, + "step": 681472 + }, + { + "epoch": 2.02, + "learning_rate": 3.883393072290144e-05, + "loss": 4.0736, + "step": 681984 + }, + { + "epoch": 2.02, + "learning_rate": 3.882554477539092e-05, + "loss": 4.0511, + "step": 682496 + }, + { + "epoch": 2.02, + "learning_rate": 3.88171588278804e-05, + "loss": 4.0656, + "step": 683008 + }, + { + "epoch": 2.02, + "learning_rate": 3.880877288036988e-05, + "loss": 4.0657, + "step": 683520 + }, + { + "epoch": 2.02, + "learning_rate": 3.8800403311663086e-05, + "loss": 4.0639, + "step": 684032 + }, + { + "epoch": 2.02, + "learning_rate": 3.8792033742956296e-05, + "loss": 4.0589, + "step": 684544 + }, + { + "epoch": 2.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0627, + "step": 685056 + }, + { + "epoch": 2.02, + "learning_rate": 3.8775261847935255e-05, + "loss": 4.065, + "step": 685568 + }, + { + "epoch": 2.02, + "learning_rate": 3.8766875900424735e-05, + "loss": 4.0613, + "step": 686080 + }, + { + "epoch": 2.02, + "learning_rate": 3.8758489952914215e-05, + "loss": 4.0708, + "step": 686592 + }, + { + "epoch": 2.03, + "eval_loss": 4.106845378875732, + "eval_runtime": 292.4243, + "eval_samples_per_second": 1304.922, + "eval_steps_per_second": 40.78, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750104005403695e-05, + "loss": 4.0586, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8741718057893175e-05, + "loss": 4.0483, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8733332110382655e-05, + "loss": 4.0622, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872494616287214e-05, + "loss": 4.066, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8716560215361615e-05, + "loss": 4.0687, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708174267851095e-05, + "loss": 4.0573, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8699788320340575e-05, + "loss": 4.0649, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691402372830055e-05, + "loss": 4.0492, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683016425319535e-05, + "loss": 4.058, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8674630477809015e-05, + "loss": 4.0619, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666244530298495e-05, + "loss": 4.0642, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8657858582787975e-05, + "loss": 4.064, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8649489014081184e-05, + "loss": 4.0689, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641103066570664e-05, + "loss": 4.0496, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8632717119060144e-05, + "loss": 4.0512, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8624331171549624e-05, + "loss": 4.0392, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861594522403911e-05, + "loss": 4.0595, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860755927652859e-05, + "loss": 4.0654, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.85991897078218e-05, + "loss": 4.0503, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859080376031128e-05, + "loss": 4.0647, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858241781280076e-05, + "loss": 4.0754, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857403186529024e-05, + "loss": 4.0669, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856564591777972e-05, + "loss": 4.062, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.85572599702692e-05, + "loss": 4.0583, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854889040156241e-05, + "loss": 4.0616, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854050445405189e-05, + "loss": 4.0589, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853211850654137e-05, + "loss": 4.0632, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852373255903085e-05, + "loss": 4.0609, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851534661152033e-05, + "loss": 4.0543, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850696066400981e-05, + "loss": 4.0503, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849857471649929e-05, + "loss": 4.0516, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849018876898877e-05, + "loss": 4.0616, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848180282147825e-05, + "loss": 4.0635, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847341687396773e-05, + "loss": 4.0636, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846503092645721e-05, + "loss": 4.055, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845666135775042e-05, + "loss": 4.0575, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.84482754102399e-05, + "loss": 4.0607, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.843988946272938e-05, + "loss": 4.0397, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843150351521886e-05, + "loss": 4.048, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842311756770834e-05, + "loss": 4.0487, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841473162019782e-05, + "loss": 4.0488, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.84063456726873e-05, + "loss": 4.0641, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839797610398051e-05, + "loss": 4.0537, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.838959015646999e-05, + "loss": 4.0484, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838120420895947e-05, + "loss": 4.0634, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837281826144895e-05, + "loss": 4.048, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836443231393843e-05, + "loss": 4.06, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835604636642791e-05, + "loss": 4.0652, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834767679772112e-05, + "loss": 4.0308, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.83392908502106e-05, + "loss": 4.0628, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833090490270008e-05, + "loss": 4.0493, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832251895518956e-05, + "loss": 4.0564, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831413300767904e-05, + "loss": 4.0497, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830576343897225e-05, + "loss": 4.044, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829737749146173e-05, + "loss": 4.0476, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289007922754946e-05, + "loss": 4.0444, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8280621975244426e-05, + "loss": 4.0683, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8272236027733906e-05, + "loss": 4.0361, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8263850080223386e-05, + "loss": 4.0627, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8255496890320324e-05, + "loss": 4.0545, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8247110942809804e-05, + "loss": 4.0357, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8238724995299284e-05, + "loss": 4.0632, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.8230339047788764e-05, + "loss": 4.0407, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.8221953100278244e-05, + "loss": 4.0324, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.8213567152767724e-05, + "loss": 4.0412, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8205181205257204e-05, + "loss": 4.0586, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8196795257746684e-05, + "loss": 4.0384, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8188409310236164e-05, + "loss": 4.0554, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8180023362725644e-05, + "loss": 4.0363, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8171637415215124e-05, + "loss": 4.039, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816326784650834e-05, + "loss": 4.05, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815488189899781e-05, + "loss": 4.0521, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814649595148729e-05, + "loss": 4.0538, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813811000397677e-05, + "loss": 4.0495, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.812972405646625e-05, + "loss": 4.0571, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812133810895573e-05, + "loss": 4.0466, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811295216144521e-05, + "loss": 4.0507, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810458259273842e-05, + "loss": 4.037, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.80961966452279e-05, + "loss": 4.0434, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808781069771739e-05, + "loss": 4.0485, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.807942475020687e-05, + "loss": 4.0411, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807103880269635e-05, + "loss": 4.0541, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806265285518583e-05, + "loss": 4.0603, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805428328647904e-05, + "loss": 4.0396, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804589733896852e-05, + "loss": 4.0312, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8037511391458e-05, + "loss": 4.0482, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802912544394748e-05, + "loss": 4.0506, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802073949643696e-05, + "loss": 4.0502, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8012369927730166e-05, + "loss": 4.042, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8003983980219646e-05, + "loss": 4.0503, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7995598032709126e-05, + "loss": 4.0417, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7987212085198606e-05, + "loss": 4.0434, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7978826137688086e-05, + "loss": 4.0412, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.79704565689813e-05, + "loss": 4.0484, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796207062147078e-05, + "loss": 4.0502, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795368467396026e-05, + "loss": 4.0518, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794529872644974e-05, + "loss": 4.0352, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793691277893922e-05, + "loss": 4.045, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.79285268314287e-05, + "loss": 4.0367, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.7920140883918175e-05, + "loss": 4.0472, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7911754936407655e-05, + "loss": 4.0465, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7903368988897135e-05, + "loss": 4.0395, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789499942019035e-05, + "loss": 4.046, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7886613472679824e-05, + "loss": 4.0307, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787824390397304e-05, + "loss": 4.0373, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.786985795646253e-05, + "loss": 4.0317, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7861488387755736e-05, + "loss": 4.041, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853102440245216e-05, + "loss": 4.0414, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7844716492734696e-05, + "loss": 4.0413, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7836330545224176e-05, + "loss": 4.0342, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782794459771365e-05, + "loss": 4.0345, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781955865020313e-05, + "loss": 4.0376, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781117270269261e-05, + "loss": 4.0462, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780278675518209e-05, + "loss": 4.0413, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779440080767157e-05, + "loss": 4.0421, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778601486016105e-05, + "loss": 4.0426, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777762891265053e-05, + "loss": 4.0494, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776924296514001e-05, + "loss": 4.0415, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7760873396433224e-05, + "loss": 4.0363, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7752487448922704e-05, + "loss": 4.0415, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744117880215913e-05, + "loss": 4.0461, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7735731932705393e-05, + "loss": 4.0423, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772734598519487e-05, + "loss": 4.0371, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771896003768435e-05, + "loss": 4.0374, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771057409017383e-05, + "loss": 4.0464, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770218814266331e-05, + "loss": 4.0329, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769380219515279e-05, + "loss": 4.0278, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7685432626446e-05, + "loss": 4.0335, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767704667893548e-05, + "loss": 4.0252, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766866073142496e-05, + "loss": 4.0504, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766027478391444e-05, + "loss": 4.04, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765188883640393e-05, + "loss": 4.0534, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764351926769714e-05, + "loss": 4.028, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763513332018662e-05, + "loss": 4.0452, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762676375147983e-05, + "loss": 4.041, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761837780396931e-05, + "loss": 4.0413, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.760999185645879e-05, + "loss": 4.0388, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760160590894827e-05, + "loss": 4.0375, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759321996143775e-05, + "loss": 4.0327, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758483401392723e-05, + "loss": 4.0533, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757644806641671e-05, + "loss": 4.0266, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756806211890618e-05, + "loss": 4.0427, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.755967617139567e-05, + "loss": 4.0445, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755129022388515e-05, + "loss": 4.0379, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7542904276374627e-05, + "loss": 4.0347, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7534518328864107e-05, + "loss": 4.0392, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526148760157316e-05, + "loss": 4.0432, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7517762812646796e-05, + "loss": 4.0411, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7509376865136276e-05, + "loss": 4.0454, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.090456962585449, + "eval_runtime": 295.0121, + "eval_samples_per_second": 1293.476, + "eval_steps_per_second": 40.422, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.7500990917625755e-05, + "loss": 4.0269, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7492621348918965e-05, + "loss": 4.0271, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7484235401408445e-05, + "loss": 4.04, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7475849453897924e-05, + "loss": 4.0427, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7467463506387404e-05, + "loss": 4.0469, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459077558876884e-05, + "loss": 4.0337, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7450691611366364e-05, + "loss": 4.0407, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744232204265958e-05, + "loss": 4.0307, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743393609514906e-05, + "loss": 4.0349, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742555014763854e-05, + "loss": 4.0377, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741716420012802e-05, + "loss": 4.0368, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.74087782526175e-05, + "loss": 4.0433, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740040868391071e-05, + "loss": 4.0433, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739202273640019e-05, + "loss": 4.0274, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738363678888967e-05, + "loss": 4.0289, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737525084137915e-05, + "loss": 4.0166, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736686489386863e-05, + "loss": 4.0401, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735847894635811e-05, + "loss": 4.0371, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735009299884759e-05, + "loss": 4.027, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734170705133707e-05, + "loss": 4.0378, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733332110382655e-05, + "loss": 4.0559, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732493515631603e-05, + "loss": 4.044, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7316565587609245e-05, + "loss": 4.0399, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308179640098725e-05, + "loss": 4.0351, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.72997936925882e-05, + "loss": 4.041, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729140774507768e-05, + "loss": 4.0354, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283038176370894e-05, + "loss": 4.0356, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7274652228860374e-05, + "loss": 4.0385, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726626628134985e-05, + "loss": 4.034, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725788033383933e-05, + "loss": 4.0309, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.724949438632881e-05, + "loss": 4.031, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724112481762202e-05, + "loss": 4.0378, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.72327388701115e-05, + "loss": 4.0365, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722435292260098e-05, + "loss": 4.0419, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721596697509046e-05, + "loss": 4.0342, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720759740638367e-05, + "loss": 4.035, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719921145887315e-05, + "loss": 4.038, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719084189016637e-05, + "loss": 4.0209, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718245594265585e-05, + "loss": 4.0256, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717406999514532e-05, + "loss": 4.0266, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.71656840476348e-05, + "loss": 4.0252, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7157314478928016e-05, + "loss": 4.0386, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7148928531417496e-05, + "loss": 4.0324, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7140542583906976e-05, + "loss": 4.0322, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7132156636396456e-05, + "loss": 4.0336, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712378706768967e-05, + "loss": 4.0285, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7115401120179145e-05, + "loss": 4.0392, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107015172668625e-05, + "loss": 4.0425, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.7098629225158105e-05, + "loss": 4.0069, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7090243277647585e-05, + "loss": 4.0409, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7081857330137065e-05, + "loss": 4.0249, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7073471382626545e-05, + "loss": 4.0365, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065101813919754e-05, + "loss": 4.0294, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.7056715866409234e-05, + "loss": 4.0187, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.7048329918898714e-05, + "loss": 4.0289, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.7039943971388194e-05, + "loss": 4.019, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.7031558023877674e-05, + "loss": 4.0428, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702317207636716e-05, + "loss": 4.0181, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701478612885664e-05, + "loss": 4.037, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700640018134612e-05, + "loss": 4.032, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.69980142338356e-05, + "loss": 4.0175, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.698962828632508e-05, + "loss": 4.038, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698124233881456e-05, + "loss": 4.0166, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6972856391304034e-05, + "loss": 4.0131, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696448682259725e-05, + "loss": 4.0181, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695610087508673e-05, + "loss": 4.037, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.69477149275762e-05, + "loss": 4.0181, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.693932898006568e-05, + "loss": 4.0359, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693094303255516e-05, + "loss": 4.0105, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692257346384838e-05, + "loss": 4.0217, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691418751633786e-05, + "loss": 4.029, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690580156882734e-05, + "loss": 4.0298, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689741562131682e-05, + "loss": 4.0316, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889046052610034e-05, + "loss": 4.0302, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688067648390324e-05, + "loss": 4.0351, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687229053639272e-05, + "loss": 4.0226, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.68639045888822e-05, + "loss": 4.0292, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685553502017541e-05, + "loss": 4.0204, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684714907266489e-05, + "loss": 4.0221, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683876312515437e-05, + "loss": 4.0247, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683037717764385e-05, + "loss": 4.0169, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682199123013333e-05, + "loss": 4.0313, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681360528262281e-05, + "loss": 4.0384, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680521933511229e-05, + "loss": 4.0244, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679683338760177e-05, + "loss": 4.006, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678844744009125e-05, + "loss": 4.0278, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678007787138446e-05, + "loss": 4.0285, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677169192387394e-05, + "loss": 4.033, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676330597636342e-05, + "loss": 4.0154, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675493640765663e-05, + "loss": 4.0309, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674655046014611e-05, + "loss": 4.0222, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673816451263559e-05, + "loss": 4.02, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672977856512507e-05, + "loss": 4.0195, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672139261761455e-05, + "loss": 4.0296, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.6713006670104037e-05, + "loss": 4.0274, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6704620722593516e-05, + "loss": 4.0317, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696234775082996e-05, + "loss": 4.0161, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6687848827572476e-05, + "loss": 4.023, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6679479258865685e-05, + "loss": 4.0153, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.6671093311355165e-05, + "loss": 4.0243, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6662707363844645e-05, + "loss": 4.0239, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6654321416334125e-05, + "loss": 4.0205, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6645935468823605e-05, + "loss": 4.0226, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6637565900116814e-05, + "loss": 4.0087, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629179952606294e-05, + "loss": 4.0212, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6620810383899503e-05, + "loss": 4.0082, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6612424436388983e-05, + "loss": 4.0208, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660403848887847e-05, + "loss": 4.0161, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659565254136795e-05, + "loss": 4.0251, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658726659385743e-05, + "loss": 4.0133, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657888064634691e-05, + "loss": 4.015, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657049469883639e-05, + "loss": 4.0145, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656210875132587e-05, + "loss": 4.0275, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655372280381534e-05, + "loss": 4.0221, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654533685630482e-05, + "loss": 4.0221, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.65369509087943e-05, + "loss": 4.0234, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652858134008751e-05, + "loss": 4.0293, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652019539257699e-05, + "loss": 4.0207, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651180944506647e-05, + "loss": 4.0177, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650342349755595e-05, + "loss": 4.0191, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649503755004544e-05, + "loss": 4.0271, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648665160253492e-05, + "loss": 4.0203, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.64782656550244e-05, + "loss": 4.0201, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.646987970751388e-05, + "loss": 4.0182, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646149376000336e-05, + "loss": 4.0264, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645312419129657e-05, + "loss": 4.0113, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644473824378605e-05, + "loss": 4.0128, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643636867507926e-05, + "loss": 4.0078, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642798272756874e-05, + "loss": 4.0094, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6419596780058217e-05, + "loss": 4.0252, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6411210832547697e-05, + "loss": 4.0228, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6402824885037176e-05, + "loss": 4.034, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6394438937526656e-05, + "loss": 4.0069, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638606936881987e-05, + "loss": 4.0257, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637768342130935e-05, + "loss": 4.0189, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636929747379883e-05, + "loss": 4.0225, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636091152628831e-05, + "loss": 4.0161, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635252557877779e-05, + "loss": 4.0163, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634413963126727e-05, + "loss": 4.0161, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633577006256048e-05, + "loss": 4.0322, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632738411504996e-05, + "loss": 4.0053, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631899816753944e-05, + "loss": 4.0235, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631061222002892e-05, + "loss": 4.0245, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.63022262725184e-05, + "loss": 4.0163, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0153, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.0235, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627706842998684e-05, + "loss": 4.0194, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626869886128006e-05, + "loss": 4.0234, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6260329292573266e-05, + "loss": 4.0224, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.077542781829834, + "eval_runtime": 307.2271, + "eval_samples_per_second": 1242.049, + "eval_steps_per_second": 38.815, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6251943345062746e-05, + "loss": 3.9998, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6243557397552226e-05, + "loss": 4.0087, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62351714500417e-05, + "loss": 4.0181, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622678550253118e-05, + "loss": 4.0221, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621839955502066e-05, + "loss": 4.0275, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621001360751014e-05, + "loss": 4.0172, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620162765999962e-05, + "loss": 4.0228, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.61932417124891e-05, + "loss": 4.0146, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0116, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.013, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.0227, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6159697922447025e-05, + "loss": 4.0183, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0265, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0065, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.009, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 3.9969, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0198, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.0176, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101012668677114e-05, + "loss": 4.005, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609262672116659e-05, + "loss": 4.0211, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608424077365607e-05, + "loss": 4.0379, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607585482614555e-05, + "loss": 4.0224, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606748525743876e-05, + "loss": 4.0196, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605909930992824e-05, + "loss": 4.0166, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605071336241772e-05, + "loss": 4.021, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.60423274149072e-05, + "loss": 4.0183, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.0152, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602557189868989e-05, + "loss": 4.0172, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601718595117937e-05, + "loss": 4.0153, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600880000366885e-05, + "loss": 4.0114, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600041405615833e-05, + "loss": 4.0154, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599202810864781e-05, + "loss": 4.0135, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598365853994102e-05, + "loss": 4.0178, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.59752725924305e-05, + "loss": 4.0257, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596688664491998e-05, + "loss": 4.0146, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.59585170762132e-05, + "loss": 4.0131, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595013112870268e-05, + "loss": 4.0209, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594174518119216e-05, + "loss": 4.001, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5933359233681637e-05, + "loss": 4.0094, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5924973286171117e-05, + "loss": 4.0052, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5916587338660597e-05, + "loss": 4.0092, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908201391150076e-05, + "loss": 4.0122, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5899815443639556e-05, + "loss": 4.0132, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5891429496129036e-05, + "loss": 4.0154, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5883043548618516e-05, + "loss": 4.0141, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5874657601107996e-05, + "loss": 4.0151, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5866271653597476e-05, + "loss": 4.0151, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5857902084890685e-05, + "loss": 4.0243, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5849516137380165e-05, + "loss": 3.9911, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5841130189869645e-05, + "loss": 4.0235, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583274424235913e-05, + "loss": 4.007, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5824358294848605e-05, + "loss": 4.0153, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581598872614182e-05, + "loss": 4.0101, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.58076027786313e-05, + "loss": 4.0054, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5799216831120774e-05, + "loss": 4.0035, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579084726241399e-05, + "loss": 3.9998, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578246131490347e-05, + "loss": 4.0288, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577407536739295e-05, + "loss": 3.9982, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576568941988242e-05, + "loss": 4.0195, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.57573034723719e-05, + "loss": 4.0071, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574893390366512e-05, + "loss": 4.001, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.57405479561546e-05, + "loss": 4.0174, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573216200864408e-05, + "loss": 4.0027, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572377606113356e-05, + "loss": 3.9891, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571539011362304e-05, + "loss": 4.0012, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570700416611252e-05, + "loss": 4.0188, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5698618218602e-05, + "loss": 3.9993, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569023227109148e-05, + "loss": 4.0174, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568184632358096e-05, + "loss": 3.9903, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567346037607044e-05, + "loss": 4.0017, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566510718616738e-05, + "loss": 4.0098, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565672123865686e-05, + "loss": 4.0128, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564835166995007e-05, + "loss": 4.0112, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.563996572243955e-05, + "loss": 4.0126, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563157977492903e-05, + "loss": 4.0183, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562319382741851e-05, + "loss": 4.0046, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561480787990799e-05, + "loss": 4.0068, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560642193239747e-05, + "loss": 4.0018, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559803598488695e-05, + "loss": 4.0084, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.558965003737643e-05, + "loss": 4.0036, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558126408986591e-05, + "loss": 4.0015, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557289452115912e-05, + "loss": 4.0138, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.55645085736486e-05, + "loss": 4.0184, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555612262613808e-05, + "loss": 4.0064, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554773667862756e-05, + "loss": 3.9862, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553935073111704e-05, + "loss": 4.0089, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553098116241026e-05, + "loss": 4.0087, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552259521489974e-05, + "loss": 4.0172, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551420926738922e-05, + "loss": 3.9982, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.5505839698682426e-05, + "loss": 4.0105, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.5497453751171906e-05, + "loss": 4.0103, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5489067803661386e-05, + "loss": 3.9981, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5480681856150866e-05, + "loss": 4.0001, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5472295908640346e-05, + "loss": 4.0135, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5463909961129826e-05, + "loss": 4.0066, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5455524013619306e-05, + "loss": 4.0139, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447138066108786e-05, + "loss": 3.9999, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543875211859826e-05, + "loss": 4.0039, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5430382549891475e-05, + "loss": 3.9983, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5421996602380955e-05, + "loss": 4.0097, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541361065487044e-05, + "loss": 4.0098, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5405224707359915e-05, + "loss": 3.9999, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5396838759849395e-05, + "loss": 4.0048, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5388452812338875e-05, + "loss": 3.9935, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5380083243632084e-05, + "loss": 4.0015, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5371697296121564e-05, + "loss": 3.9876, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5363311348611044e-05, + "loss": 4.0036, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5354925401100524e-05, + "loss": 3.9979, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5346539453590004e-05, + "loss": 4.0061, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533816988488321e-05, + "loss": 3.9996, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.532978393737269e-05, + "loss": 4.0046, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532139798986218e-05, + "loss": 3.9924, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531301204235166e-05, + "loss": 4.0093, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530462609484114e-05, + "loss": 4.0025, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529624014733062e-05, + "loss": 4.0029, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.52878541998201e-05, + "loss": 4.0027, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.527946825230958e-05, + "loss": 4.0158, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527109868360279e-05, + "loss": 4.0004, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526271273609227e-05, + "loss": 3.9995, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525432678858175e-05, + "loss": 4.0033, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524594084107123e-05, + "loss": 4.0079, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523757127236444e-05, + "loss": 4.0002, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522918532485392e-05, + "loss": 4.0049, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.52207993773434e-05, + "loss": 3.999, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521241342983288e-05, + "loss": 4.005, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520404386112609e-05, + "loss": 3.991, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519565791361557e-05, + "loss": 3.9965, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518727196610505e-05, + "loss": 3.9898, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517888601859453e-05, + "loss": 3.9972, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517050007108401e-05, + "loss": 4.0053, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516211412357349e-05, + "loss": 4.0056, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515372817606297e-05, + "loss": 4.0133, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5145342228552446e-05, + "loss": 3.9938, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5136956281041926e-05, + "loss": 4.0041, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5128570333531406e-05, + "loss": 4.0057, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5120184386020886e-05, + "loss": 4.0043, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.51118148173141e-05, + "loss": 3.9999, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510342886980358e-05, + "loss": 3.9946, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509504292229306e-05, + "loss": 4.0011, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508665697478254e-05, + "loss": 4.0098, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507827102727202e-05, + "loss": 3.9945, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.506990145856523e-05, + "loss": 4.005, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506151551105471e-05, + "loss": 4.0058, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505312956354419e-05, + "loss": 4.0007, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.50447599948374e-05, + "loss": 3.9968, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503637404732688e-05, + "loss": 4.0041, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502798809981636e-05, + "loss": 3.9997, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501960215230584e-05, + "loss": 4.0033, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501121620479532e-05, + "loss": 4.01, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.06660795211792, + "eval_runtime": 319.6273, + "eval_samples_per_second": 1193.862, + "eval_steps_per_second": 37.309, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.5002846636088535e-05, + "loss": 3.9945, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.4994460688578015e-05, + "loss": 3.9874, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4986074741067495e-05, + "loss": 4.0005, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.4977705172360704e-05, + "loss": 4.0053, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.4969319224850184e-05, + "loss": 4.0057, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.4960933277339664e-05, + "loss": 4.0008, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4952547329829144e-05, + "loss": 4.0028, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4944161382318624e-05, + "loss": 3.9976, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4935775434808104e-05, + "loss": 3.9932, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4927389487297584e-05, + "loss": 3.9968, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4919003539787064e-05, + "loss": 4.0055, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4910617592276544e-05, + "loss": 3.9995, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490224802356975e-05, + "loss": 4.0107, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489386207605923e-05, + "loss": 3.9869, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488547612854872e-05, + "loss": 3.9933, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.48770901810382e-05, + "loss": 3.9804, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486870423352768e-05, + "loss": 4.0022, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486031828601716e-05, + "loss": 3.9996, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485193233850663e-05, + "loss": 3.9945, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484356276979985e-05, + "loss": 3.9973, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483517682228933e-05, + "loss": 4.0187, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482679087477881e-05, + "loss": 4.0057, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481840492726828e-05, + "loss": 4.002, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481001897975776e-05, + "loss": 3.9975, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480164941105098e-05, + "loss": 4.0096, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479326346354046e-05, + "loss": 3.9998, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478487751602994e-05, + "loss": 3.9941, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477649156851942e-05, + "loss": 4.0039, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.47681056210089e-05, + "loss": 3.9916, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.4759736052302106e-05, + "loss": 3.998, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.4751350104791586e-05, + "loss": 3.9989, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4742964157281066e-05, + "loss": 3.9946, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4734578209770546e-05, + "loss": 4.0007, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4726192262260026e-05, + "loss": 4.0106, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4717806314749506e-05, + "loss": 3.9954, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4709436746042715e-05, + "loss": 4.0002, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4701050798532195e-05, + "loss": 4.0045, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469268122982541e-05, + "loss": 3.984, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468429528231489e-05, + "loss": 3.9898, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467590933480437e-05, + "loss": 3.9916, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466752338729385e-05, + "loss": 3.9891, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.465913743978333e-05, + "loss": 3.9937, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465075149227281e-05, + "loss": 3.9975, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464236554476229e-05, + "loss": 3.9971, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.46339959760555e-05, + "loss": 3.997, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462561002854498e-05, + "loss": 3.9969, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461722408103446e-05, + "loss": 4.0001, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460883813352394e-05, + "loss": 4.0046, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460045218601342e-05, + "loss": 3.9803, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.45920662385029e-05, + "loss": 4.0026, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458368029099238e-05, + "loss": 3.9888, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457529434348186e-05, + "loss": 3.9963, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456690839597134e-05, + "loss": 3.9958, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.4558538827264555e-05, + "loss": 3.9885, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.4550152879754035e-05, + "loss": 3.9877, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.4541783311047244e-05, + "loss": 3.981, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4533397363536724e-05, + "loss": 4.0137, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4525011416026204e-05, + "loss": 3.9819, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4516625468515684e-05, + "loss": 3.9995, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4508239521005164e-05, + "loss": 3.991, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4499853573494644e-05, + "loss": 3.9855, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449146762598412e-05, + "loss": 3.9971, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.44830816784736e-05, + "loss": 3.9885, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447469573096308e-05, + "loss": 3.9773, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446630978345256e-05, + "loss": 3.9775, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445794021474577e-05, + "loss": 4.0081, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.444955426723525e-05, + "loss": 3.9853, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444116831972473e-05, + "loss": 3.9947, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443278237221421e-05, + "loss": 3.9778, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442441280350742e-05, + "loss": 3.9874, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.44160268559969e-05, + "loss": 3.9884, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440764090848638e-05, + "loss": 3.9998, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.439925496097586e-05, + "loss": 3.9946, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439086901346534e-05, + "loss": 3.9957, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438248306595482e-05, + "loss": 4.0006, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.43740971184443e-05, + "loss": 3.9878, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436571117093378e-05, + "loss": 3.9911, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435732522342326e-05, + "loss": 3.9839, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434897203352021e-05, + "loss": 3.9919, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434058608600969e-05, + "loss": 3.9897, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433220013849917e-05, + "loss": 3.9822, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432381419098865e-05, + "loss": 4.0002, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4315428243478127e-05, + "loss": 4.0019, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.4307042295967607e-05, + "loss": 3.9914, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4298656348457086e-05, + "loss": 3.9664, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4290270400946566e-05, + "loss": 3.991, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4281900832239776e-05, + "loss": 3.9963, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4273514884729256e-05, + "loss": 3.9987, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4265128937218735e-05, + "loss": 3.9885, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425675936851195e-05, + "loss": 3.9912, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424837342100143e-05, + "loss": 3.9925, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.423998747349091e-05, + "loss": 3.9833, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423160152598039e-05, + "loss": 3.9849, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422321557846987e-05, + "loss": 3.9959, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421482963095935e-05, + "loss": 3.9876, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420646006225256e-05, + "loss": 4.0001, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419807411474204e-05, + "loss": 3.9878, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.418968816723152e-05, + "loss": 3.9849, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418131859852473e-05, + "loss": 3.9839, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417293265101421e-05, + "loss": 3.9923, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416454670350369e-05, + "loss": 3.9947, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415616075599317e-05, + "loss": 3.9826, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414777480848265e-05, + "loss": 3.9882, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.413938886097213e-05, + "loss": 3.9772, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413100291346161e-05, + "loss": 3.9902, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412261696595109e-05, + "loss": 3.9679, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411423101844057e-05, + "loss": 3.9845, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410586144973378e-05, + "loss": 3.9869, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4097491881026994e-05, + "loss": 3.9903, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4089105933516474e-05, + "loss": 3.9774, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408071998600595e-05, + "loss": 3.99, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407233403849543e-05, + "loss": 3.9769, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406394809098491e-05, + "loss": 3.9926, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405556214347439e-05, + "loss": 3.9853, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.40471925747676e-05, + "loss": 3.9855, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403880662725708e-05, + "loss": 3.9855, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403042067974656e-05, + "loss": 4.0001, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402205111103978e-05, + "loss": 3.9854, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401366516352925e-05, + "loss": 3.9826, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400527921601873e-05, + "loss": 3.989, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399689326850821e-05, + "loss": 3.9872, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398850732099769e-05, + "loss": 3.9854, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398012137348717e-05, + "loss": 3.9883, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397173542597665e-05, + "loss": 3.9822, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396334947846613e-05, + "loss": 3.9902, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395496353095561e-05, + "loss": 3.975, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394657758344509e-05, + "loss": 3.9845, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393819163593457e-05, + "loss": 3.977, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.392980568842405e-05, + "loss": 3.9842, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392141974091354e-05, + "loss": 3.9836, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391303379340302e-05, + "loss": 3.9913, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390466422469623e-05, + "loss": 3.9976, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389627827718571e-05, + "loss": 3.9799, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388789232967519e-05, + "loss": 3.9875, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.387950638216467e-05, + "loss": 3.9869, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387112043465414e-05, + "loss": 3.9872, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3862750865947356e-05, + "loss": 3.9865, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3854364918436836e-05, + "loss": 3.9768, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384597897092631e-05, + "loss": 3.989, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383759302341579e-05, + "loss": 3.9941, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3829207075905276e-05, + "loss": 3.9767, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3820821128394756e-05, + "loss": 3.9876, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3812435180884236e-05, + "loss": 3.9925, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3804049233373716e-05, + "loss": 3.9801, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3795679664666925e-05, + "loss": 3.9822, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.3787293717156405e-05, + "loss": 3.9913, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3778907769645885e-05, + "loss": 3.983, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3770521822135365e-05, + "loss": 3.9849, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3762152253428574e-05, + "loss": 3.996, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 4.056432247161865, + "eval_runtime": 295.56, + "eval_samples_per_second": 1291.078, + "eval_steps_per_second": 40.347, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3753766305918054e-05, + "loss": 3.988, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3745380358407534e-05, + "loss": 3.9687, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3736994410897014e-05, + "loss": 3.9833, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3728608463386493e-05, + "loss": 3.9939, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3720222515875973e-05, + "loss": 3.9888, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371183656836546e-05, + "loss": 3.9871, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370345062085494e-05, + "loss": 3.9837, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369506467334442e-05, + "loss": 3.9841, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.36866787258339e-05, + "loss": 3.9772, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367829277832338e-05, + "loss": 3.9827, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.366990683081285e-05, + "loss": 3.9862, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366152088330233e-05, + "loss": 3.9849, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365315131459555e-05, + "loss": 3.9958, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364476536708503e-05, + "loss": 3.9712, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.36363794195745e-05, + "loss": 3.9768, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362799347206398e-05, + "loss": 3.9643, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361960752455346e-05, + "loss": 3.9871, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361122157704294e-05, + "loss": 3.9841, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360283562953243e-05, + "loss": 3.9801, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359444968202191e-05, + "loss": 3.981, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358606373451139e-05, + "loss": 4.0018, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357767778700087e-05, + "loss": 3.9906, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356930821829408e-05, + "loss": 3.9849, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356092227078356e-05, + "loss": 3.9815, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355253632327304e-05, + "loss": 3.9965, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354415037576252e-05, + "loss": 3.9807, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3535764428252e-05, + "loss": 3.9812, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352737848074148e-05, + "loss": 3.9886, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351899253323096e-05, + "loss": 3.9766, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351060658572044e-05, + "loss": 3.9813, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350222063820991e-05, + "loss": 3.9828, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3493851069503126e-05, + "loss": 3.9764, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.3485465121992606e-05, + "loss": 3.9867, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347707917448209e-05, + "loss": 3.9925, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3468693226971566e-05, + "loss": 3.9804, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346032365826478e-05, + "loss": 3.9844, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345193771075426e-05, + "loss": 3.9936, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344355176324374e-05, + "loss": 3.9623, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3435165815733215e-05, + "loss": 3.9778, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342679624702643e-05, + "loss": 3.9779, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341841029951591e-05, + "loss": 3.9691, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3410024352005384e-05, + "loss": 3.9802, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3401638404494864e-05, + "loss": 3.9833, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339326883578808e-05, + "loss": 3.9805, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338488288827756e-05, + "loss": 3.9814, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337649694076704e-05, + "loss": 3.9776, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3368127372060256e-05, + "loss": 3.9793, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3359741424549736e-05, + "loss": 3.9917, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3351371855842945e-05, + "loss": 3.9674, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3342985908332425e-05, + "loss": 3.9865, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3334599960821905e-05, + "loss": 3.9776, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3326214013311385e-05, + "loss": 3.9791, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331782806580086e-05, + "loss": 3.9807, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.330944211829034e-05, + "loss": 3.9667, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330105617077982e-05, + "loss": 3.9794, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3292686602073034e-05, + "loss": 3.9644, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3284300654562514e-05, + "loss": 3.9964, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3275914707051994e-05, + "loss": 3.9649, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3267528759541474e-05, + "loss": 3.9865, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3259142812030954e-05, + "loss": 3.9736, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3250756864520434e-05, + "loss": 3.9702, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242370917009914e-05, + "loss": 3.9784, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3233984969499393e-05, + "loss": 3.9755, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3225599021988873e-05, + "loss": 3.9654, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321721307447835e-05, + "loss": 3.9589, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320882712696783e-05, + "loss": 3.9891, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320045755826104e-05, + "loss": 3.9753, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319207161075052e-05, + "loss": 3.9775, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318368566324e-05, + "loss": 3.9627, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317529971572948e-05, + "loss": 3.9696, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.31669301470227e-05, + "loss": 3.9774, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315854419951218e-05, + "loss": 3.9842, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315015825200166e-05, + "loss": 3.9789, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314177230449114e-05, + "loss": 3.9828, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313338635698062e-05, + "loss": 3.9836, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312501678827383e-05, + "loss": 3.9728, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311663084076331e-05, + "loss": 3.9741, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310824489325279e-05, + "loss": 3.9721, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.309985894574227e-05, + "loss": 3.9753, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309147299823175e-05, + "loss": 3.9764, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3083103429524956e-05, + "loss": 3.9671, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3074717482014436e-05, + "loss": 3.9821, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3066331534503916e-05, + "loss": 3.9862, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.30579455869934e-05, + "loss": 3.9741, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3049559639482876e-05, + "loss": 3.9563, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3041173691972356e-05, + "loss": 3.9754, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3032787744461836e-05, + "loss": 3.9798, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3024401796951316e-05, + "loss": 3.9807, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3016032228244525e-05, + "loss": 3.973, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300766265953774e-05, + "loss": 3.9744, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.299927671202722e-05, + "loss": 3.9794, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2990890764516694e-05, + "loss": 3.9654, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2982504817006174e-05, + "loss": 3.9714, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2974118869495654e-05, + "loss": 3.9771, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296573292198514e-05, + "loss": 3.9734, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295736335327835e-05, + "loss": 3.9858, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2948993784571565e-05, + "loss": 3.9762, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2940607837061045e-05, + "loss": 3.9656, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293222188955052e-05, + "loss": 3.9676, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292383594204e-05, + "loss": 3.9768, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291544999452948e-05, + "loss": 3.9813, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290706404701896e-05, + "loss": 3.9685, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289867809950844e-05, + "loss": 3.9699, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289029215199792e-05, + "loss": 3.962, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.28819062044874e-05, + "loss": 3.9789, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287352025697688e-05, + "loss": 3.9534, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286513430946636e-05, + "loss": 3.9682, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285674836195584e-05, + "loss": 3.9729, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2848378793249054e-05, + "loss": 3.9766, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284000922454226e-05, + "loss": 3.9632, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283162327703174e-05, + "loss": 3.9731, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282323732952122e-05, + "loss": 3.9645, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.28148513820107e-05, + "loss": 3.9764, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280646543450018e-05, + "loss": 3.9739, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279807948698966e-05, + "loss": 3.9677, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.278969353947914e-05, + "loss": 3.973, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278130759196862e-05, + "loss": 3.9863, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277293802326183e-05, + "loss": 3.9706, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276455207575131e-05, + "loss": 3.9723, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275616612824079e-05, + "loss": 3.972, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274779655953401e-05, + "loss": 3.9721, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273941061202349e-05, + "loss": 3.9721, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273102466451297e-05, + "loss": 3.9737, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272263871700245e-05, + "loss": 3.9716, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271425276949193e-05, + "loss": 3.9748, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270586682198141e-05, + "loss": 3.9631, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269748087447088e-05, + "loss": 3.9658, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.268909492696036e-05, + "loss": 3.963, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2680725358253576e-05, + "loss": 3.9706, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672339410743056e-05, + "loss": 3.9618, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266395346323253e-05, + "loss": 3.9836, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2655567515722016e-05, + "loss": 3.9836, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264719794701523e-05, + "loss": 3.9622, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263881199950471e-05, + "loss": 3.975, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2630426051994185e-05, + "loss": 3.973, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.26220564832874e-05, + "loss": 3.9768, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261367053577688e-05, + "loss": 3.9657, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2605284588266354e-05, + "loss": 3.9664, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2596898640755834e-05, + "loss": 3.9764, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2588512693245314e-05, + "loss": 3.9793, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2580126745734794e-05, + "loss": 3.9627, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2571757177028e-05, + "loss": 3.9735, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256337122951748e-05, + "loss": 3.9817, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255498528200697e-05, + "loss": 3.9676, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254659933449645e-05, + "loss": 3.9663, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253821338698593e-05, + "loss": 3.9767, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.252982743947541e-05, + "loss": 3.9679, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252144149196489e-05, + "loss": 3.9744, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251305554445437e-05, + "loss": 3.9765, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.049461364746094, + "eval_runtime": 352.8796, + "eval_samples_per_second": 1081.363, + "eval_steps_per_second": 33.793, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250466959694385e-05, + "loss": 3.9697, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249628364943333e-05, + "loss": 3.955, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248791408072654e-05, + "loss": 3.9687, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247952813321602e-05, + "loss": 3.9828, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.24711421857055e-05, + "loss": 3.9755, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246275623819498e-05, + "loss": 3.9735, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245437029068446e-05, + "loss": 3.9686, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244600072197767e-05, + "loss": 3.972, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243761477446715e-05, + "loss": 3.9633, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2429228826956634e-05, + "loss": 3.9735, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2420842879446114e-05, + "loss": 3.9681, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2412456931935594e-05, + "loss": 3.9758, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2404087363228803e-05, + "loss": 3.9806, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239570141571828e-05, + "loss": 3.9587, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238731546820776e-05, + "loss": 3.9638, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237892952069724e-05, + "loss": 3.95, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237055995199045e-05, + "loss": 3.971, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236217400447993e-05, + "loss": 3.973, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235378805696941e-05, + "loss": 3.966, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234540210945889e-05, + "loss": 3.965, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233701616194837e-05, + "loss": 3.9923, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232863021443785e-05, + "loss": 3.9808, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232024426692733e-05, + "loss": 3.9707, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231185831941681e-05, + "loss": 3.9708, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230347237190629e-05, + "loss": 3.9855, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229511918200324e-05, + "loss": 3.9693, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228673323449272e-05, + "loss": 3.9648, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227834728698219e-05, + "loss": 3.9796, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.226996133947167e-05, + "loss": 3.9622, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226157539196115e-05, + "loss": 3.966, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225318944445063e-05, + "loss": 3.9666, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224480349694011e-05, + "loss": 3.9629, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2236433928233326e-05, + "loss": 3.9744, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2228047980722806e-05, + "loss": 3.9801, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2219662033212286e-05, + "loss": 3.9643, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2211292464505495e-05, + "loss": 3.9767, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2202906516994975e-05, + "loss": 3.9749, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2194520569484455e-05, + "loss": 3.9511, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2186134621973935e-05, + "loss": 3.9615, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2177765053267144e-05, + "loss": 3.9677, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2169379105756624e-05, + "loss": 3.9552, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2160993158246104e-05, + "loss": 3.9716, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2152607210735584e-05, + "loss": 3.9713, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2144221263225064e-05, + "loss": 3.9665, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2135835315714544e-05, + "loss": 3.969, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2127449368204024e-05, + "loss": 3.9693, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.211906342069351e-05, + "loss": 3.9631, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211067747318299e-05, + "loss": 3.9805, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210229152567247e-05, + "loss": 3.9529, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209390557816195e-05, + "loss": 3.9714, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208551963065143e-05, + "loss": 3.971, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.20771336831409e-05, + "loss": 3.9646, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.206876411443412e-05, + "loss": 3.968, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206039454572733e-05, + "loss": 3.9538, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205202497702054e-05, + "loss": 3.9667, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204363902951002e-05, + "loss": 3.9489, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.20352530819995e-05, + "loss": 3.9847, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202686713448898e-05, + "loss": 3.9554, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2018481186978464e-05, + "loss": 3.973, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2010095239467944e-05, + "loss": 3.9633, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2001709291957424e-05, + "loss": 3.9581, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1993323344446904e-05, + "loss": 3.9635, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198493739693638e-05, + "loss": 3.9661, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197655144942586e-05, + "loss": 3.9486, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196816550191534e-05, + "loss": 3.949, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.195977955440482e-05, + "loss": 3.9751, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1951409985698026e-05, + "loss": 3.965, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194304041699124e-05, + "loss": 3.9618, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193465446948072e-05, + "loss": 3.9483, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.19262685219702e-05, + "loss": 3.958, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191788257445968e-05, + "loss": 3.9638, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.190949662694916e-05, + "loss": 3.969, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190111067943864e-05, + "loss": 3.9685, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189274111073185e-05, + "loss": 3.9678, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188435516322133e-05, + "loss": 3.9687, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187596921571081e-05, + "loss": 3.9617, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186758326820029e-05, + "loss": 3.9601, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.185919732068977e-05, + "loss": 3.9591, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185081137317925e-05, + "loss": 3.9645, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184242542566873e-05, + "loss": 3.9627, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183403947815821e-05, + "loss": 3.9565, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182565353064769e-05, + "loss": 3.9643, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.18172839619409e-05, + "loss": 3.9703, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1808914393234115e-05, + "loss": 3.9627, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1800544824527324e-05, + "loss": 3.9503, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1792158877016804e-05, + "loss": 3.9572, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1783772929506284e-05, + "loss": 3.9649, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1775386981995764e-05, + "loss": 3.9733, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1767001034485244e-05, + "loss": 3.9611, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175863146577845e-05, + "loss": 3.9615, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175024551826793e-05, + "loss": 3.9654, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174185957075741e-05, + "loss": 3.9565, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173347362324689e-05, + "loss": 3.9577, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172508767573637e-05, + "loss": 3.9611, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171670172822585e-05, + "loss": 3.9656, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170831578071533e-05, + "loss": 3.9699, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.169992983320482e-05, + "loss": 3.9675, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.16915438856943e-05, + "loss": 3.951, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168315793818378e-05, + "loss": 3.957, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167478836947699e-05, + "loss": 3.9611, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.16664188007702e-05, + "loss": 3.9692, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165803285325968e-05, + "loss": 3.9564, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164964690574916e-05, + "loss": 3.9565, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164126095823864e-05, + "loss": 3.9505, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163287501072812e-05, + "loss": 3.9628, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.16244890632176e-05, + "loss": 3.9414, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161610311570708e-05, + "loss": 3.956, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160771716819656e-05, + "loss": 3.9611, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.159933122068604e-05, + "loss": 3.9595, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159094527317552e-05, + "loss": 3.9535, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1582559325665e-05, + "loss": 3.9602, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157417337815448e-05, + "loss": 3.9514, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1565803809447687e-05, + "loss": 3.9612, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.15574342407409e-05, + "loss": 3.9647, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.154904829323038e-05, + "loss": 3.952, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154066234571986e-05, + "loss": 3.9633, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1532276398209335e-05, + "loss": 3.9702, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1523890450698815e-05, + "loss": 3.9633, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1515504503188295e-05, + "loss": 3.9515, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1507118555677775e-05, + "loss": 3.9637, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1498732608167255e-05, + "loss": 3.9601, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149037941826421e-05, + "loss": 3.9552, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148199347075369e-05, + "loss": 3.9634, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147360752324316e-05, + "loss": 3.956, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146522157573264e-05, + "loss": 3.9624, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145683562822212e-05, + "loss": 3.9512, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.14484496807116e-05, + "loss": 3.9548, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144006373320108e-05, + "loss": 3.9491, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143167778569056e-05, + "loss": 3.9565, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142329183818004e-05, + "loss": 3.9451, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141492226947325e-05, + "loss": 3.9698, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140653632196273e-05, + "loss": 3.9704, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139815037445221e-05, + "loss": 3.9539, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1389764426941696e-05, + "loss": 3.9587, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1381378479431176e-05, + "loss": 3.9646, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1373008910724385e-05, + "loss": 3.961, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1364622963213865e-05, + "loss": 3.9545, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1356237015703345e-05, + "loss": 3.9541, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1347867446996554e-05, + "loss": 3.9636, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1339481499486034e-05, + "loss": 3.9639, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.1331095551975514e-05, + "loss": 3.9535, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1322709604464994e-05, + "loss": 3.9591, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.1314323656954474e-05, + "loss": 3.9679, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.1305937709443954e-05, + "loss": 3.9526, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129756814073716e-05, + "loss": 3.9547, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.128918219322665e-05, + "loss": 3.9655, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128079624571613e-05, + "loss": 3.9538, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127241029820561e-05, + "loss": 3.963, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126402435069509e-05, + "loss": 3.9628, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.042651176452637, + "eval_runtime": 356.4098, + "eval_samples_per_second": 1070.652, + "eval_steps_per_second": 33.459, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125563840318457e-05, + "loss": 3.9399, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124725245567405e-05, + "loss": 3.9477, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123886650816352e-05, + "loss": 3.9548, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1230480560653e-05, + "loss": 3.9667, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122209461314248e-05, + "loss": 3.9623, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121370866563196e-05, + "loss": 3.9672, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120532271812144e-05, + "loss": 3.952, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119693677061092e-05, + "loss": 3.9619, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118856720190413e-05, + "loss": 3.9468, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118018125439361e-05, + "loss": 3.9626, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.11717953068831e-05, + "loss": 3.953, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116340935937258e-05, + "loss": 3.9679, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115502341186206e-05, + "loss": 3.9692, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114663746435154e-05, + "loss": 3.9453, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113825151684102e-05, + "loss": 3.9499, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.11298655693305e-05, + "loss": 3.9415, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112147962181998e-05, + "loss": 3.9502, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111309367430946e-05, + "loss": 3.9588, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110470772679894e-05, + "loss": 3.9566, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109632177928841e-05, + "loss": 3.9515, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108793583177789e-05, + "loss": 3.9812, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.107954988426737e-05, + "loss": 3.9641, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107116393675685e-05, + "loss": 3.9616, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106277798924633e-05, + "loss": 3.9543, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1054408420539546e-05, + "loss": 3.9717, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1046022473029026e-05, + "loss": 3.9565, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1037636525518506e-05, + "loss": 3.954, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1029250578007986e-05, + "loss": 3.9641, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1020864630497466e-05, + "loss": 3.9456, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1012478682986946e-05, + "loss": 3.958, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1004109114280155e-05, + "loss": 3.9525, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0995723166769635e-05, + "loss": 3.9546, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0987337219259115e-05, + "loss": 3.9596, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0978951271748595e-05, + "loss": 3.9649, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0970565324238075e-05, + "loss": 3.954, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0962195755531284e-05, + "loss": 3.9667, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0953809808020764e-05, + "loss": 3.9612, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094542386051025e-05, + "loss": 3.9371, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093703791299973e-05, + "loss": 3.9522, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092865196548921e-05, + "loss": 3.9518, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092028239678242e-05, + "loss": 3.9387, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.09118964492719e-05, + "loss": 3.9591, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090351050176138e-05, + "loss": 3.9605, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089512455425086e-05, + "loss": 3.9565, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088673860674034e-05, + "loss": 3.9487, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087835265922982e-05, + "loss": 3.9633, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.08699667117193e-05, + "loss": 3.9504, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086158076420877e-05, + "loss": 3.9686, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085319481669825e-05, + "loss": 3.938, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084482524799147e-05, + "loss": 3.956, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083643930048095e-05, + "loss": 3.9597, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082805335297043e-05, + "loss": 3.9515, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.081966740545991e-05, + "loss": 3.9573, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0811314215556854e-05, + "loss": 3.9387, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0802928268046333e-05, + "loss": 3.9551, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0794542320535813e-05, + "loss": 3.937, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0786156373025293e-05, + "loss": 3.9665, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.07777868043185e-05, + "loss": 3.9462, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.076940085680798e-05, + "loss": 3.9567, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076101490929746e-05, + "loss": 3.955, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075262896178694e-05, + "loss": 3.9453, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074424301427642e-05, + "loss": 3.9501, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073587344556964e-05, + "loss": 3.9537, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072748749805912e-05, + "loss": 3.9361, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.07191015505486e-05, + "loss": 3.9374, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071071560303807e-05, + "loss": 3.9589, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070232965552755e-05, + "loss": 3.9526, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069394370801703e-05, + "loss": 3.9525, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068555776050651e-05, + "loss": 3.936, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067717181299599e-05, + "loss": 3.9433, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.06688022442892e-05, + "loss": 3.9497, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066041629677868e-05, + "loss": 3.9563, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065203034926816e-05, + "loss": 3.9578, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064364440175764e-05, + "loss": 3.9525, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063525845424712e-05, + "loss": 3.9593, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0626888885540336e-05, + "loss": 3.9489, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0618502938029816e-05, + "loss": 3.9452, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0610116990519296e-05, + "loss": 3.948, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0601747421812505e-05, + "loss": 3.9473, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0593361474301985e-05, + "loss": 3.9507, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0584975526791465e-05, + "loss": 3.9467, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0576589579280945e-05, + "loss": 3.9464, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0568203631770425e-05, + "loss": 3.9663, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0559834063063634e-05, + "loss": 3.9482, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0551448115553114e-05, + "loss": 3.9391, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0543062168042594e-05, + "loss": 3.9446, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0534676220532074e-05, + "loss": 3.9508, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052630665182529e-05, + "loss": 3.9572, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051792070431477e-05, + "loss": 3.9496, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.050953475680425e-05, + "loss": 3.9468, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050114880929373e-05, + "loss": 3.9542, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049276286178321e-05, + "loss": 3.9462, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048439329307642e-05, + "loss": 3.9447, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.04760073455659e-05, + "loss": 3.9491, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046762139805538e-05, + "loss": 3.9529, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.045923545054486e-05, + "loss": 3.9592, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0450849503034338e-05, + "loss": 3.9525, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044246355552382e-05, + "loss": 3.9426, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043409398681703e-05, + "loss": 3.9429, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042570803930651e-05, + "loss": 3.9477, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041732209179599e-05, + "loss": 3.9601, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.040893614428547e-05, + "loss": 3.9442, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040055019677495e-05, + "loss": 3.9438, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039216424926443e-05, + "loss": 3.9411, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0383778301753907e-05, + "loss": 3.9477, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0375408733047123e-05, + "loss": 3.9297, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0367022785536603e-05, + "loss": 3.9471, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0358636838026076e-05, + "loss": 3.9452, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035025089051556e-05, + "loss": 3.9492, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0341881321808775e-05, + "loss": 3.9417, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0333495374298255e-05, + "loss": 3.9513, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032510942678773e-05, + "loss": 3.9383, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031672347927721e-05, + "loss": 3.9488, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030833753176669e-05, + "loss": 3.9531, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.029995158425617e-05, + "loss": 3.9389, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029156563674565e-05, + "loss": 3.9536, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028319606803886e-05, + "loss": 3.9578, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0274826499332077e-05, + "loss": 3.9529, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.026644055182155e-05, + "loss": 3.9426, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025805460431103e-05, + "loss": 3.9445, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0249668656800513e-05, + "loss": 3.9512, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0241282709289993e-05, + "loss": 3.9429, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0232896761779473e-05, + "loss": 3.9527, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0224510814268953e-05, + "loss": 3.9441, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0216124866758433e-05, + "loss": 3.9536, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0207738919247913e-05, + "loss": 3.9382, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0199352971737393e-05, + "loss": 3.9434, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0190967024226873e-05, + "loss": 3.9367, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182597455520085e-05, + "loss": 3.9431, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0174211508009565e-05, + "loss": 3.9333, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0165825560499045e-05, + "loss": 3.9567, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0157455991792254e-05, + "loss": 3.9637, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0149070044281734e-05, + "loss": 3.9442, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0140684096771214e-05, + "loss": 3.9426, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0132298149260698e-05, + "loss": 3.9529, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0123912201750177e-05, + "loss": 3.954, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115526254239657e-05, + "loss": 3.9453, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0107140306729137e-05, + "loss": 3.9401, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0098754359218617e-05, + "loss": 3.9556, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009036841170809e-05, + "loss": 3.9497, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0081998843001306e-05, + "loss": 3.9457, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007361289549079e-05, + "loss": 3.945, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006522694798027e-05, + "loss": 3.9542, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0056841000469743e-05, + "loss": 3.9424, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004847143176296e-05, + "loss": 3.9435, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004008548425244e-05, + "loss": 3.9548, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0031699536741915e-05, + "loss": 3.9447, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0023313589231395e-05, + "loss": 3.9488, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0014927641720875e-05, + "loss": 3.9543, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0006541694210355e-05, + "loss": 3.946, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 4.036015033721924, + "eval_runtime": 286.3134, + "eval_samples_per_second": 1332.774, + "eval_steps_per_second": 41.65, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998155746699835e-05, + "loss": 3.9368, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989769799189315e-05, + "loss": 3.9398, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981383851678795e-05, + "loss": 3.9538, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9972997904168275e-05, + "loss": 3.9507, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964611956657755e-05, + "loss": 3.9538, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956226009147238e-05, + "loss": 3.9402, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947840061636718e-05, + "loss": 3.9531, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939454114126198e-05, + "loss": 3.9347, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931068166615678e-05, + "loss": 3.9536, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992268221910515e-05, + "loss": 3.9385, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991429627159463e-05, + "loss": 3.958, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905910324084115e-05, + "loss": 3.9542, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989754075537733e-05, + "loss": 3.9387, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889154807866804e-05, + "loss": 3.9384, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880768860356284e-05, + "loss": 3.9324, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872382912845764e-05, + "loss": 3.9359, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9863996965335244e-05, + "loss": 3.9495, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855611017824723e-05, + "loss": 3.944, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847225070314207e-05, + "loss": 3.9435, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838839122803687e-05, + "loss": 3.968, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830469554096896e-05, + "loss": 3.9506, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822083606586376e-05, + "loss": 3.9516, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813697659075856e-05, + "loss": 3.9416, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805311711565336e-05, + "loss": 3.9584, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796942142858548e-05, + "loss": 3.9413, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788556195348028e-05, + "loss": 3.9499, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780170247837508e-05, + "loss": 3.9496, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771784300326988e-05, + "loss": 3.9401, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763398352816468e-05, + "loss": 3.9422, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755028784109677e-05, + "loss": 3.9416, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974664283659916e-05, + "loss": 3.9448, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973825688908864e-05, + "loss": 3.9479, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.972987094157812e-05, + "loss": 3.954, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.97214849940676e-05, + "loss": 3.9483, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971311542536081e-05, + "loss": 3.9514, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970472947785029e-05, + "loss": 3.9497, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969634353033977e-05, + "loss": 3.9308, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9687957582829253e-05, + "loss": 3.9414, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679571635318733e-05, + "loss": 3.9386, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671185687808213e-05, + "loss": 3.9303, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662799740297693e-05, + "loss": 3.9475, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654413792787166e-05, + "loss": 3.952, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964604422408038e-05, + "loss": 3.9422, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963765827656986e-05, + "loss": 3.9407, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629272329059345e-05, + "loss": 3.9505, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620886381548818e-05, + "loss": 3.9446, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612533191645763e-05, + "loss": 3.9509, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604147244135243e-05, + "loss": 3.9351, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595761296624723e-05, + "loss": 3.9407, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587375349114206e-05, + "loss": 3.9504, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9578989401603686e-05, + "loss": 3.9422, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570619832896895e-05, + "loss": 3.9445, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562233885386375e-05, + "loss": 3.9343, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553847937875855e-05, + "loss": 3.945, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545461990365335e-05, + "loss": 3.927, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537076042854815e-05, + "loss": 3.9542, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528690095344292e-05, + "loss": 3.9386, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520304147833772e-05, + "loss": 3.9441, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511918200323252e-05, + "loss": 3.9411, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950354863161646e-05, + "loss": 3.9388, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495162684105944e-05, + "loss": 3.9364, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486776736595424e-05, + "loss": 3.9451, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478390789084904e-05, + "loss": 3.9285, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470004841574384e-05, + "loss": 3.9275, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461635272867593e-05, + "loss": 3.9464, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453249325357073e-05, + "loss": 3.947, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9444863377846553e-05, + "loss": 3.941, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436477430336033e-05, + "loss": 3.9264, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942812424043298e-05, + "loss": 3.9335, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.941973829292246e-05, + "loss": 3.94, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411352345411935e-05, + "loss": 3.9469, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9402966397901415e-05, + "loss": 3.9443, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394580450390894e-05, + "loss": 3.9439, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938621088168411e-05, + "loss": 3.9493, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377824934173587e-05, + "loss": 3.9464, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369438986663067e-05, + "loss": 3.9308, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361053039152547e-05, + "loss": 3.9372, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352667091642027e-05, + "loss": 3.9445, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344281144131507e-05, + "loss": 3.9373, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933591157542472e-05, + "loss": 3.9384, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.93275256279142e-05, + "loss": 3.9359, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.931913968040368e-05, + "loss": 3.9552, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310770111696888e-05, + "loss": 3.9367, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302384164186368e-05, + "loss": 3.9275, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9293998216675848e-05, + "loss": 3.9373, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928561226916533e-05, + "loss": 3.942, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927722632165481e-05, + "loss": 3.9483, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.926884037414429e-05, + "loss": 3.9361, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926045442663377e-05, + "loss": 3.9383, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925206847912325e-05, + "loss": 3.9415, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924369891041646e-05, + "loss": 3.9384, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923531296290594e-05, + "loss": 3.9317, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226927015395424e-05, + "loss": 3.9377, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218541067884904e-05, + "loss": 3.9452, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210155120374384e-05, + "loss": 3.9537, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201769172863864e-05, + "loss": 3.9358, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193383225353344e-05, + "loss": 3.9321, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185030035450285e-05, + "loss": 3.9386, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176644087939765e-05, + "loss": 3.9388, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168258140429245e-05, + "loss": 3.9473, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159872192918725e-05, + "loss": 3.9361, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151486245408205e-05, + "loss": 3.9348, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143100297897685e-05, + "loss": 3.9301, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134714350387165e-05, + "loss": 3.9433, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126328402876645e-05, + "loss": 3.9162, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911794245536612e-05, + "loss": 3.9369, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.91095565078556e-05, + "loss": 3.9341, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910117056034508e-05, + "loss": 3.9403, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092800991638297e-05, + "loss": 3.9317, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908441504412777e-05, + "loss": 3.942, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076045475420986e-05, + "loss": 3.9308, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.90676759067142e-05, + "loss": 3.9354, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.905928995920368e-05, + "loss": 3.9401, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905090401169316e-05, + "loss": 3.9318, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904251806418264e-05, + "loss": 3.9468, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903413211667212e-05, + "loss": 3.9496, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025746169161595e-05, + "loss": 3.9415, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017360221651075e-05, + "loss": 3.9345, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9008974274140555e-05, + "loss": 3.9343, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000588326630035e-05, + "loss": 3.9391, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992202379119515e-05, + "loss": 3.9345, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983816431608995e-05, + "loss": 3.9422, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975430484098475e-05, + "loss": 3.9375, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967044536587955e-05, + "loss": 3.9407, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958658589077438e-05, + "loss": 3.9299, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950272641566918e-05, + "loss": 3.9338, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941886694056398e-05, + "loss": 3.9258, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933533504153336e-05, + "loss": 3.9313, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925147556642816e-05, + "loss": 3.922, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.89167616091323e-05, + "loss": 3.9463, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890837566162178e-05, + "loss": 3.955, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.889998971411126e-05, + "loss": 3.9426, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889160376660074e-05, + "loss": 3.925, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888323419789395e-05, + "loss": 3.9454, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887484825038343e-05, + "loss": 3.9419, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886646230287291e-05, + "loss": 3.9358, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885807635536239e-05, + "loss": 3.9303, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849690407851872e-05, + "loss": 3.9441, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841304460341352e-05, + "loss": 3.9381, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883293489163456e-05, + "loss": 3.9346, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882454894412404e-05, + "loss": 3.9387, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881616299661352e-05, + "loss": 3.9432, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807777049103e-05, + "loss": 3.934, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.879939110159248e-05, + "loss": 3.932, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791005154081957e-05, + "loss": 3.948, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782635585375173e-05, + "loss": 3.9339, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774266016668382e-05, + "loss": 3.9375, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765880069157862e-05, + "loss": 3.9456, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757494121647342e-05, + "loss": 3.9308, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.031096458435059, + "eval_runtime": 299.0363, + "eval_samples_per_second": 1276.069, + "eval_steps_per_second": 39.878, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749108174136825e-05, + "loss": 3.9278, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740722226626305e-05, + "loss": 3.9343, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873233627911578e-05, + "loss": 3.9435, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872395033160526e-05, + "loss": 3.9393, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871556438409474e-05, + "loss": 3.9465, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870717843658422e-05, + "loss": 3.9302, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.869880886787743e-05, + "loss": 3.9394, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869042292036691e-05, + "loss": 3.9261, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868203697285639e-05, + "loss": 3.9439, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867365102534587e-05, + "loss": 3.9313, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866526507783535e-05, + "loss": 3.945, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865687913032483e-05, + "loss": 3.9419, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648509561618043e-05, + "loss": 3.9344, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640123614107523e-05, + "loss": 3.9284, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631737666597003e-05, + "loss": 3.9251, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623351719086483e-05, + "loss": 3.9261, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8614982150379692e-05, + "loss": 3.9375, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8606612581672905e-05, + "loss": 3.9364, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8598226634162385e-05, + "loss": 3.9322, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8589840686651865e-05, + "loss": 3.9568, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581454739141344e-05, + "loss": 3.9467, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573068791630824e-05, + "loss": 3.9405, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564682844120304e-05, + "loss": 3.9329, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556296896609784e-05, + "loss": 3.9514, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547910949099264e-05, + "loss": 3.929, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539525001588748e-05, + "loss": 3.9389, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531139054078228e-05, + "loss": 3.939, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522753106567708e-05, + "loss": 3.9351, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514367159057188e-05, + "loss": 3.9297, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8505997590350397e-05, + "loss": 3.9331, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849762802164361e-05, + "loss": 3.9352, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.848924207413309e-05, + "loss": 3.9372, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848085612662257e-05, + "loss": 3.9411, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847247017911205e-05, + "loss": 3.9413, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464100610405258e-05, + "loss": 3.9429, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455714662894738e-05, + "loss": 3.937, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447328715384218e-05, + "loss": 3.923, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.84389427678737e-05, + "loss": 3.9356, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843055682036318e-05, + "loss": 3.9281, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842217087285266e-05, + "loss": 3.9244, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841378492534214e-05, + "loss": 3.9384, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405398977831614e-05, + "loss": 3.9421, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397013030321094e-05, + "loss": 3.9308, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388627082810578e-05, + "loss": 3.9313, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380241135300058e-05, + "loss": 3.9377, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371855187789538e-05, + "loss": 3.9365, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363518376690212e-05, + "loss": 3.9402, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835513242917969e-05, + "loss": 3.9301, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834674648166917e-05, + "loss": 3.9311, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338360534158655e-05, + "loss": 3.938, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329974586648135e-05, + "loss": 3.9308, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321588639137615e-05, + "loss": 3.9327, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313202691627088e-05, + "loss": 3.9275, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304816744116568e-05, + "loss": 3.937, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296430796606048e-05, + "loss": 3.9153, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288061227899264e-05, + "loss": 3.9403, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827967528038874e-05, + "loss": 3.9295, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827128933287822e-05, + "loss": 3.9306, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.82629033853677e-05, + "loss": 3.9386, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825451743785718e-05, + "loss": 3.9277, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824613149034666e-05, + "loss": 3.9243, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823774554283614e-05, + "loss": 3.9405, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.822935959532562e-05, + "loss": 3.9145, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8220990026618833e-05, + "loss": 3.9196, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212604079108313e-05, + "loss": 3.9351, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204218131597793e-05, + "loss": 3.9372, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195848562891e-05, + "loss": 3.9309, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818746261538048e-05, + "loss": 3.9171, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179076667869965e-05, + "loss": 3.9222, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170690720359445e-05, + "loss": 3.9269, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162304772848925e-05, + "loss": 3.9392, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8153918825338405e-05, + "loss": 3.9325, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145532877827885e-05, + "loss": 3.9371, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8137146930317365e-05, + "loss": 3.9369, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128777361610574e-05, + "loss": 3.9399, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120391414100057e-05, + "loss": 3.9199, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8112005466589537e-05, + "loss": 3.9287, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8103619519079017e-05, + "loss": 3.9379, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8095249950372226e-05, + "loss": 3.9266, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086864002861706e-05, + "loss": 3.9333, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.807849443415492e-05, + "loss": 3.9221, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.80701084866444e-05, + "loss": 3.9466, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806172253913388e-05, + "loss": 3.9285, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805333659162336e-05, + "loss": 3.9186, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804495064411284e-05, + "loss": 3.9263, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803656469660232e-05, + "loss": 3.9325, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.80281787490918e-05, + "loss": 3.9383, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801980918038501e-05, + "loss": 3.9276, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801142323287449e-05, + "loss": 3.9288, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800303728536397e-05, + "loss": 3.9349, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799465133785345e-05, + "loss": 3.9269, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798628176914666e-05, + "loss": 3.9225, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797789582163614e-05, + "loss": 3.9267, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796950987412562e-05, + "loss": 3.9391, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961123926615103e-05, + "loss": 3.9371, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952737979104576e-05, + "loss": 3.9338, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944368410397792e-05, + "loss": 3.9207, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935982462887272e-05, + "loss": 3.9265, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792759651537675e-05, + "loss": 3.9308, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919226946669965e-05, + "loss": 3.9335, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910840999159444e-05, + "loss": 3.9298, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902455051648924e-05, + "loss": 3.9268, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894069104138398e-05, + "loss": 3.9196, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885683156627878e-05, + "loss": 3.9348, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877297209117358e-05, + "loss": 3.9041, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.786891126160684e-05, + "loss": 3.9312, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786052531409632e-05, + "loss": 3.9218, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.78521393665858e-05, + "loss": 3.9327, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784375341907528e-05, + "loss": 3.9198, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783536747156476e-05, + "loss": 3.9334, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782699790285797e-05, + "loss": 3.9207, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.781861195534745e-05, + "loss": 3.9248, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810226007836933e-05, + "loss": 3.9327, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801840060326413e-05, + "loss": 3.9237, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793454112815893e-05, + "loss": 3.9346, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785068165305373e-05, + "loss": 3.9397, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776698596598582e-05, + "loss": 3.931, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768312649088062e-05, + "loss": 3.9235, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7759926701577542e-05, + "loss": 3.9271, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751540754067022e-05, + "loss": 3.9313, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743154806556505e-05, + "loss": 3.9191, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734768859045985e-05, + "loss": 3.9371, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726382911535465e-05, + "loss": 3.9235, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771799696402494e-05, + "loss": 3.9325, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709627395318154e-05, + "loss": 3.9263, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701241447807634e-05, + "loss": 3.9223, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769285550029711e-05, + "loss": 3.9141, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768446955278659e-05, + "loss": 3.9241, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767608360527607e-05, + "loss": 3.9147, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667714036569287e-05, + "loss": 3.9374, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.765932808905876e-05, + "loss": 3.9481, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7650942141548243e-05, + "loss": 3.9318, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642556194037723e-05, + "loss": 3.9165, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634170246527203e-05, + "loss": 3.9338, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625784299016683e-05, + "loss": 3.9279, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617398351506163e-05, + "loss": 3.9288, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609012403995643e-05, + "loss": 3.9268, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600659214092584e-05, + "loss": 3.9309, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592273266582064e-05, + "loss": 3.9257, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583887319071544e-05, + "loss": 3.9285, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575501371561024e-05, + "loss": 3.9302, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567131802854233e-05, + "loss": 3.9353, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558745855343713e-05, + "loss": 3.9292, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755037628663693e-05, + "loss": 3.9198, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7541990339126406e-05, + "loss": 3.9383, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533604391615886e-05, + "loss": 3.9294, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525218444105366e-05, + "loss": 3.9238, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751684887539858e-05, + "loss": 3.9387, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508462927888058e-05, + "loss": 3.9241, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.026576519012451, + "eval_runtime": 298.136, + "eval_samples_per_second": 1279.922, + "eval_steps_per_second": 39.999, + "step": 1373760 + }, + { + "epoch": 2.0, + "learning_rate": 2.7500076980377538e-05, + "loss": 3.9206, + "step": 1374208 + }, + { + "epoch": 2.0, + "learning_rate": 2.7491691032867018e-05, + "loss": 3.9234, + "step": 1374720 + }, + { + "epoch": 2.0, + "learning_rate": 2.7483305085356498e-05, + "loss": 3.9356, + "step": 1375232 + }, + { + "epoch": 2.0, + "learning_rate": 2.7474919137845978e-05, + "loss": 3.9329, + "step": 1375744 + }, + { + "epoch": 2.0, + "learning_rate": 2.7466533190335458e-05, + "loss": 3.9365, + "step": 1376256 + }, + { + "epoch": 2.0, + "learning_rate": 2.7458147242824938e-05, + "loss": 3.9229, + "step": 1376768 + }, + { + "epoch": 2.0, + "learning_rate": 2.7449761295314418e-05, + "loss": 3.9313, + "step": 1377280 + }, + { + "epoch": 2.0, + "learning_rate": 2.7441375347803898e-05, + "loss": 3.9124, + "step": 1377792 + }, + { + "epoch": 2.0, + "learning_rate": 2.743298940029338e-05, + "loss": 3.9382, + "step": 1378304 + }, + { + "epoch": 2.0, + "learning_rate": 2.742460345278286e-05, + "loss": 3.9196, + "step": 1378816 + }, + { + "epoch": 2.0, + "learning_rate": 2.741623388407607e-05, + "loss": 3.9367, + "step": 1379328 + }, + { + "epoch": 2.0, + "learning_rate": 2.740784793656555e-05, + "loss": 3.9311, + "step": 1379840 + }, + { + "epoch": 2.0, + "learning_rate": 2.739947836785876e-05, + "loss": 3.927, + "step": 1380352 + }, + { + "epoch": 2.0, + "learning_rate": 2.7391092420348243e-05, + "loss": 3.9184, + "step": 1380864 + }, + { + "epoch": 2.0, + "learning_rate": 2.7382706472837723e-05, + "loss": 3.9192, + "step": 1381376 + }, + { + "epoch": 2.0, + "learning_rate": 2.7374320525327203e-05, + "loss": 3.9199, + "step": 1381888 + }, + { + "epoch": 2.0, + "learning_rate": 2.736595095662041e-05, + "loss": 3.9256, + "step": 1382400 + }, + { + "epoch": 2.0, + "learning_rate": 2.735756500910989e-05, + "loss": 3.9277, + "step": 1382912 + }, + { + "epoch": 2.0, + "learning_rate": 2.734917906159937e-05, + "loss": 3.9263, + "step": 1383424 + }, + { + "epoch": 2.0, + "learning_rate": 2.734079311408885e-05, + "loss": 3.9442, + "step": 1383936 + }, + { + "epoch": 2.0, + "learning_rate": 2.7332407166578335e-05, + "loss": 3.939, + "step": 1384448 + }, + { + "epoch": 2.0, + "learning_rate": 2.7324021219067815e-05, + "loss": 3.9334, + "step": 1384960 + }, + { + "epoch": 2.0, + "learning_rate": 2.7315635271557295e-05, + "loss": 3.9263, + "step": 1385472 + }, + { + "epoch": 2.0, + "learning_rate": 2.7307265702850504e-05, + "loss": 3.9343, + "step": 1385984 + }, + { + "epoch": 2.0, + "learning_rate": 2.7298879755339984e-05, + "loss": 3.924, + "step": 1386496 + }, + { + "epoch": 2.0, + "learning_rate": 2.7290493807829464e-05, + "loss": 3.9329, + "step": 1387008 + }, + { + "epoch": 2.0, + "learning_rate": 2.7282107860318944e-05, + "loss": 3.9298, + "step": 1387520 + }, + { + "epoch": 2.0, + "learning_rate": 2.727372191280842e-05, + "loss": 3.9281, + "step": 1388032 + }, + { + "epoch": 2.0, + "learning_rate": 2.72653359652979e-05, + "loss": 3.9208, + "step": 1388544 + }, + { + "epoch": 2.01, + "learning_rate": 2.725695001778738e-05, + "loss": 3.9232, + "step": 1389056 + }, + { + "epoch": 2.01, + "learning_rate": 2.724856407027686e-05, + "loss": 3.9262, + "step": 1389568 + }, + { + "epoch": 2.01, + "learning_rate": 2.7240194501570073e-05, + "loss": 3.9302, + "step": 1390080 + }, + { + "epoch": 2.01, + "learning_rate": 2.723182493286329e-05, + "loss": 3.9351, + "step": 1390592 + }, + { + "epoch": 2.01, + "learning_rate": 2.722343898535277e-05, + "loss": 3.9313, + "step": 1391104 + }, + { + "epoch": 2.01, + "learning_rate": 2.7215069416645978e-05, + "loss": 3.9309, + "step": 1391616 + }, + { + "epoch": 2.01, + "learning_rate": 2.7206683469135457e-05, + "loss": 3.9281, + "step": 1392128 + }, + { + "epoch": 2.01, + "learning_rate": 2.7198297521624937e-05, + "loss": 3.9146, + "step": 1392640 + }, + { + "epoch": 2.01, + "learning_rate": 2.7189911574114417e-05, + "loss": 3.9279, + "step": 1393152 + }, + { + "epoch": 2.01, + "learning_rate": 2.7181525626603894e-05, + "loss": 3.918, + "step": 1393664 + }, + { + "epoch": 2.01, + "learning_rate": 2.7173139679093374e-05, + "loss": 3.9192, + "step": 1394176 + }, + { + "epoch": 2.01, + "learning_rate": 2.7164753731582854e-05, + "loss": 3.9243, + "step": 1394688 + }, + { + "epoch": 2.01, + "learning_rate": 2.7156367784072334e-05, + "loss": 3.9356, + "step": 1395200 + }, + { + "epoch": 2.01, + "learning_rate": 2.7147981836561814e-05, + "loss": 3.9224, + "step": 1395712 + }, + { + "epoch": 2.01, + "learning_rate": 2.7139595889051294e-05, + "loss": 3.9205, + "step": 1396224 + }, + { + "epoch": 2.01, + "learning_rate": 2.7131209941540774e-05, + "loss": 3.9335, + "step": 1396736 + }, + { + "epoch": 2.01, + "learning_rate": 2.7122823994030254e-05, + "loss": 3.923, + "step": 1397248 + }, + { + "epoch": 2.01, + "learning_rate": 2.7114438046519737e-05, + "loss": 3.9355, + "step": 1397760 + }, + { + "epoch": 2.01, + "learning_rate": 2.7106068477812946e-05, + "loss": 3.9203, + "step": 1398272 + }, + { + "epoch": 2.01, + "learning_rate": 2.7097682530302426e-05, + "loss": 3.9162, + "step": 1398784 + }, + { + "epoch": 2.01, + "learning_rate": 2.7089296582791906e-05, + "loss": 3.9318, + "step": 1399296 + }, + { + "epoch": 2.01, + "learning_rate": 2.7080910635281386e-05, + "loss": 3.9237, + "step": 1399808 + }, + { + "epoch": 2.01, + "learning_rate": 2.7072524687770866e-05, + "loss": 3.9267, + "step": 1400320 + }, + { + "epoch": 2.01, + "learning_rate": 2.7064138740260346e-05, + "loss": 3.9212, + "step": 1400832 + }, + { + "epoch": 2.01, + "learning_rate": 2.705575279274983e-05, + "loss": 3.9238, + "step": 1401344 + }, + { + "epoch": 2.01, + "learning_rate": 2.704736684523931e-05, + "loss": 3.9123, + "step": 1401856 + }, + { + "epoch": 2.01, + "learning_rate": 2.7038997276532518e-05, + "loss": 3.928, + "step": 1402368 + }, + { + "epoch": 2.01, + "learning_rate": 2.7030611329021998e-05, + "loss": 3.921, + "step": 1402880 + }, + { + "epoch": 2.01, + "learning_rate": 2.7022225381511478e-05, + "loss": 3.9233, + "step": 1403392 + }, + { + "epoch": 2.01, + "learning_rate": 2.7013839434000955e-05, + "loss": 3.9307, + "step": 1403904 + }, + { + "epoch": 2.01, + "learning_rate": 2.7005453486490435e-05, + "loss": 3.9161, + "step": 1404416 + }, + { + "epoch": 2.01, + "learning_rate": 2.6997067538979915e-05, + "loss": 3.9133, + "step": 1404928 + }, + { + "epoch": 2.01, + "learning_rate": 2.6988681591469395e-05, + "loss": 3.9365, + "step": 1405440 + }, + { + "epoch": 2.01, + "learning_rate": 2.6980295643958875e-05, + "loss": 3.9058, + "step": 1405952 + }, + { + "epoch": 2.01, + "learning_rate": 2.6971926075252084e-05, + "loss": 3.9103, + "step": 1406464 + }, + { + "epoch": 2.01, + "learning_rate": 2.69635565065453e-05, + "loss": 3.9235, + "step": 1406976 + }, + { + "epoch": 2.01, + "learning_rate": 2.6955170559034783e-05, + "loss": 3.9322, + "step": 1407488 + }, + { + "epoch": 2.01, + "learning_rate": 2.6946784611524256e-05, + "loss": 3.9208, + "step": 1408000 + }, + { + "epoch": 2.01, + "learning_rate": 2.6938398664013736e-05, + "loss": 3.9136, + "step": 1408512 + }, + { + "epoch": 2.01, + "learning_rate": 2.6930012716503216e-05, + "loss": 3.9143, + "step": 1409024 + }, + { + "epoch": 2.01, + "learning_rate": 2.6921626768992696e-05, + "loss": 3.9141, + "step": 1409536 + }, + { + "epoch": 2.01, + "learning_rate": 2.6913240821482176e-05, + "loss": 3.9312, + "step": 1410048 + }, + { + "epoch": 2.01, + "learning_rate": 2.690487125277539e-05, + "loss": 3.9234, + "step": 1410560 + }, + { + "epoch": 2.01, + "learning_rate": 2.689648530526487e-05, + "loss": 3.9272, + "step": 1411072 + }, + { + "epoch": 2.01, + "learning_rate": 2.6888099357754348e-05, + "loss": 3.9284, + "step": 1411584 + }, + { + "epoch": 2.01, + "learning_rate": 2.6879713410243828e-05, + "loss": 3.9331, + "step": 1412096 + }, + { + "epoch": 2.01, + "learning_rate": 2.6871327462733308e-05, + "loss": 3.9139, + "step": 1412608 + }, + { + "epoch": 2.01, + "learning_rate": 2.686295789402652e-05, + "loss": 3.9181, + "step": 1413120 + }, + { + "epoch": 2.01, + "learning_rate": 2.6854571946516e-05, + "loss": 3.9295, + "step": 1413632 + }, + { + "epoch": 2.01, + "learning_rate": 2.684618599900548e-05, + "loss": 3.9141, + "step": 1414144 + }, + { + "epoch": 2.01, + "learning_rate": 2.683780005149496e-05, + "loss": 3.9262, + "step": 1414656 + }, + { + "epoch": 2.01, + "learning_rate": 2.682941410398444e-05, + "loss": 3.9146, + "step": 1415168 + }, + { + "epoch": 2.01, + "learning_rate": 2.682104453527765e-05, + "loss": 3.9347, + "step": 1415680 + }, + { + "epoch": 2.01, + "learning_rate": 2.681265858776713e-05, + "loss": 3.9235, + "step": 1416192 + }, + { + "epoch": 2.01, + "learning_rate": 2.6804272640256613e-05, + "loss": 3.9109, + "step": 1416704 + }, + { + "epoch": 2.01, + "learning_rate": 2.6795886692746093e-05, + "loss": 3.9159, + "step": 1417216 + }, + { + "epoch": 2.01, + "learning_rate": 2.6787500745235573e-05, + "loss": 3.9227, + "step": 1417728 + }, + { + "epoch": 2.01, + "learning_rate": 2.6779114797725053e-05, + "loss": 3.9325, + "step": 1418240 + }, + { + "epoch": 2.01, + "learning_rate": 2.6770728850214533e-05, + "loss": 3.9196, + "step": 1418752 + }, + { + "epoch": 2.01, + "learning_rate": 2.6762359281507742e-05, + "loss": 3.9218, + "step": 1419264 + }, + { + "epoch": 2.02, + "learning_rate": 2.6753973333997222e-05, + "loss": 3.918, + "step": 1419776 + }, + { + "epoch": 2.02, + "learning_rate": 2.6745587386486705e-05, + "loss": 3.9249, + "step": 1420288 + }, + { + "epoch": 2.02, + "learning_rate": 2.6737201438976185e-05, + "loss": 3.9158, + "step": 1420800 + }, + { + "epoch": 2.02, + "learning_rate": 2.6728815491465665e-05, + "loss": 3.9156, + "step": 1421312 + }, + { + "epoch": 2.02, + "learning_rate": 2.6720429543955145e-05, + "loss": 3.9304, + "step": 1421824 + }, + { + "epoch": 2.02, + "learning_rate": 2.6712059975248354e-05, + "loss": 3.9284, + "step": 1422336 + }, + { + "epoch": 2.02, + "learning_rate": 2.6703674027737834e-05, + "loss": 3.9284, + "step": 1422848 + }, + { + "epoch": 2.02, + "learning_rate": 2.6695288080227314e-05, + "loss": 3.9128, + "step": 1423360 + }, + { + "epoch": 2.02, + "learning_rate": 2.668690213271679e-05, + "loss": 3.9184, + "step": 1423872 + }, + { + "epoch": 2.02, + "learning_rate": 2.667851618520627e-05, + "loss": 3.9189, + "step": 1424384 + }, + { + "epoch": 2.02, + "learning_rate": 2.667013023769575e-05, + "loss": 3.9246, + "step": 1424896 + }, + { + "epoch": 2.02, + "learning_rate": 2.666174429018523e-05, + "loss": 3.9244, + "step": 1425408 + }, + { + "epoch": 2.02, + "learning_rate": 2.665335834267471e-05, + "loss": 3.9151, + "step": 1425920 + }, + { + "epoch": 2.02, + "learning_rate": 2.6644988773967923e-05, + "loss": 3.9135, + "step": 1426432 + }, + { + "epoch": 2.02, + "learning_rate": 2.6636602826457403e-05, + "loss": 3.9263, + "step": 1426944 + }, + { + "epoch": 2.02, + "learning_rate": 2.662823325775062e-05, + "loss": 3.9003, + "step": 1427456 + }, + { + "epoch": 2.02, + "learning_rate": 2.6619847310240092e-05, + "loss": 3.9173, + "step": 1427968 + }, + { + "epoch": 2.02, + "learning_rate": 2.6611461362729572e-05, + "loss": 3.9121, + "step": 1428480 + }, + { + "epoch": 2.02, + "learning_rate": 2.6603075415219052e-05, + "loss": 3.9249, + "step": 1428992 + }, + { + "epoch": 2.02, + "learning_rate": 2.6594689467708532e-05, + "loss": 3.9148, + "step": 1429504 + }, + { + "epoch": 2.02, + "learning_rate": 2.6586319899001744e-05, + "loss": 3.9224, + "step": 1430016 + }, + { + "epoch": 2.02, + "learning_rate": 2.6577933951491224e-05, + "loss": 3.9137, + "step": 1430528 + }, + { + "epoch": 2.02, + "learning_rate": 2.6569548003980704e-05, + "loss": 3.9183, + "step": 1431040 + }, + { + "epoch": 2.02, + "learning_rate": 2.6561162056470184e-05, + "loss": 3.9248, + "step": 1431552 + }, + { + "epoch": 2.02, + "learning_rate": 2.6552792487763397e-05, + "loss": 3.9174, + "step": 1432064 + }, + { + "epoch": 2.02, + "learning_rate": 2.6544406540252877e-05, + "loss": 3.9247, + "step": 1432576 + }, + { + "epoch": 2.02, + "learning_rate": 2.6536020592742356e-05, + "loss": 3.9283, + "step": 1433088 + }, + { + "epoch": 2.02, + "learning_rate": 2.6527634645231836e-05, + "loss": 3.9249, + "step": 1433600 + }, + { + "epoch": 2.02, + "learning_rate": 2.6519248697721316e-05, + "loss": 3.9159, + "step": 1434112 + }, + { + "epoch": 2.02, + "learning_rate": 2.6510862750210796e-05, + "loss": 3.9135, + "step": 1434624 + }, + { + "epoch": 2.02, + "learning_rate": 2.6502476802700276e-05, + "loss": 3.9269, + "step": 1435136 + }, + { + "epoch": 2.02, + "learning_rate": 2.6494090855189756e-05, + "loss": 3.9102, + "step": 1435648 + }, + { + "epoch": 2.02, + "learning_rate": 2.6485704907679236e-05, + "loss": 3.9286, + "step": 1436160 + }, + { + "epoch": 2.02, + "learning_rate": 2.6477318960168716e-05, + "loss": 3.916, + "step": 1436672 + }, + { + "epoch": 2.02, + "learning_rate": 2.646894939146193e-05, + "loss": 3.9221, + "step": 1437184 + }, + { + "epoch": 2.02, + "learning_rate": 2.646056344395141e-05, + "loss": 3.9189, + "step": 1437696 + }, + { + "epoch": 2.02, + "learning_rate": 2.645217749644089e-05, + "loss": 3.9161, + "step": 1438208 + }, + { + "epoch": 2.02, + "learning_rate": 2.644379154893037e-05, + "loss": 3.9034, + "step": 1438720 + }, + { + "epoch": 2.02, + "learning_rate": 2.643543835902731e-05, + "loss": 3.917, + "step": 1439232 + }, + { + "epoch": 2.02, + "learning_rate": 2.642705241151679e-05, + "loss": 3.9072, + "step": 1439744 + }, + { + "epoch": 2.02, + "learning_rate": 2.641866646400627e-05, + "loss": 3.9218, + "step": 1440256 + }, + { + "epoch": 2.02, + "learning_rate": 2.641028051649575e-05, + "loss": 3.9369, + "step": 1440768 + }, + { + "epoch": 2.02, + "learning_rate": 2.640189456898523e-05, + "loss": 3.9317, + "step": 1441280 + }, + { + "epoch": 2.02, + "learning_rate": 2.639350862147471e-05, + "loss": 3.9041, + "step": 1441792 + }, + { + "epoch": 2.02, + "learning_rate": 2.638512267396419e-05, + "loss": 3.9311, + "step": 1442304 + }, + { + "epoch": 2.02, + "learning_rate": 2.637673672645367e-05, + "loss": 3.9211, + "step": 1442816 + }, + { + "epoch": 2.02, + "learning_rate": 2.6368350778943153e-05, + "loss": 3.9194, + "step": 1443328 + }, + { + "epoch": 2.02, + "learning_rate": 2.6359964831432626e-05, + "loss": 3.9109, + "step": 1443840 + }, + { + "epoch": 2.02, + "learning_rate": 2.6351578883922106e-05, + "loss": 3.9253, + "step": 1444352 + }, + { + "epoch": 2.02, + "learning_rate": 2.6343192936411586e-05, + "loss": 3.9173, + "step": 1444864 + }, + { + "epoch": 2.02, + "learning_rate": 2.6334806988901066e-05, + "loss": 3.9199, + "step": 1445376 + }, + { + "epoch": 2.02, + "learning_rate": 2.6326453798998015e-05, + "loss": 3.9222, + "step": 1445888 + }, + { + "epoch": 2.02, + "learning_rate": 2.6318067851487495e-05, + "loss": 3.9269, + "step": 1446400 + }, + { + "epoch": 2.02, + "learning_rate": 2.6309681903976975e-05, + "loss": 3.9222, + "step": 1446912 + }, + { + "epoch": 2.02, + "learning_rate": 2.6301295956466448e-05, + "loss": 3.9143, + "step": 1447424 + }, + { + "epoch": 2.02, + "learning_rate": 2.6292910008955928e-05, + "loss": 3.9251, + "step": 1447936 + }, + { + "epoch": 2.02, + "learning_rate": 2.6284524061445408e-05, + "loss": 3.923, + "step": 1448448 + }, + { + "epoch": 2.02, + "learning_rate": 2.627613811393489e-05, + "loss": 3.9165, + "step": 1448960 + }, + { + "epoch": 2.02, + "learning_rate": 2.626775216642437e-05, + "loss": 3.93, + "step": 1449472 + }, + { + "epoch": 2.02, + "learning_rate": 2.6259398976521316e-05, + "loss": 3.9126, + "step": 1449984 + }, + { + "epoch": 2.03, + "eval_loss": 4.023057460784912, + "eval_runtime": 289.9723, + "eval_samples_per_second": 1315.957, + "eval_steps_per_second": 41.125, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6251013029010796e-05, + "loss": 3.9101, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6242627081500276e-05, + "loss": 3.9161, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6234241133989752e-05, + "loss": 3.9298, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6225855186479232e-05, + "loss": 3.9206, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217469238968712e-05, + "loss": 3.9336, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6209083291458192e-05, + "loss": 3.9097, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6200697343947672e-05, + "loss": 3.9236, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6192311396437152e-05, + "loss": 3.9002, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6183925448926632e-05, + "loss": 3.932, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6175539501416112e-05, + "loss": 3.9141, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6167153553905592e-05, + "loss": 3.9273, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6158767606395075e-05, + "loss": 3.9246, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6150398037688285e-05, + "loss": 3.9134, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6142012090177764e-05, + "loss": 3.916, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6133626142667244e-05, + "loss": 3.9117, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6125240195156724e-05, + "loss": 3.9078, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6116854247646204e-05, + "loss": 3.9213, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6108468300135684e-05, + "loss": 3.9156, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6100082352625164e-05, + "loss": 3.9189, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609169640511464e-05, + "loss": 3.9323, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608331045760412e-05, + "loss": 3.934, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.60749245100936e-05, + "loss": 3.9224, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606653856258308e-05, + "loss": 3.9202, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.605815261507256e-05, + "loss": 3.9258, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6049783046365773e-05, + "loss": 3.9137, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6041397098855253e-05, + "loss": 3.9277, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6033011151344733e-05, + "loss": 3.9208, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6024625203834213e-05, + "loss": 3.9157, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6016255635127422e-05, + "loss": 3.9123, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6007869687616902e-05, + "loss": 3.9174, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.5999500118910115e-05, + "loss": 3.9161, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5991114171399594e-05, + "loss": 3.9216, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5982728223889074e-05, + "loss": 3.9278, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5974342276378554e-05, + "loss": 3.9228, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5965972707671763e-05, + "loss": 3.9251, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5957586760161247e-05, + "loss": 3.9215, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5949200812650727e-05, + "loss": 3.9045, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5940814865140207e-05, + "loss": 3.9169, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5932428917629687e-05, + "loss": 3.9066, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5924042970119167e-05, + "loss": 3.9138, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915673401412376e-05, + "loss": 3.9166, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907287453901856e-05, + "loss": 3.9212, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.589890150639134e-05, + "loss": 3.9184, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589051555888082e-05, + "loss": 3.909, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.58821296113703e-05, + "loss": 3.9252, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587374366385978e-05, + "loss": 3.9207, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586535771634926e-05, + "loss": 3.9236, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.58570045264462e-05, + "loss": 3.9166, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.584861857893568e-05, + "loss": 3.9051, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584023263142516e-05, + "loss": 3.9244, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583184668391464e-05, + "loss": 3.9134, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582346073640412e-05, + "loss": 3.9187, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.58150747888936e-05, + "loss": 3.9127, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580668884138308e-05, + "loss": 3.9124, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5798319272676293e-05, + "loss": 3.9068, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5789949703969502e-05, + "loss": 3.9165, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781563756458982e-05, + "loss": 3.9169, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773177808948462e-05, + "loss": 3.9202, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576479186143794e-05, + "loss": 3.9189, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575640591392742e-05, + "loss": 3.9081, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.57480199664169e-05, + "loss": 3.9073, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5739634018906385e-05, + "loss": 3.9319, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731248071395865e-05, + "loss": 3.898, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5722862123885345e-05, + "loss": 3.8996, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714476176374825e-05, + "loss": 3.9113, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5706090228864298e-05, + "loss": 3.9237, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5697704281353778e-05, + "loss": 3.9125, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.568931833384326e-05, + "loss": 3.9061, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568093238633274e-05, + "loss": 3.9016, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567254643882222e-05, + "loss": 3.9071, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.56641604913117e-05, + "loss": 3.9254, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5655807301408646e-05, + "loss": 3.9141, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5647454111505588e-05, + "loss": 3.9143, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5639068163995068e-05, + "loss": 3.9252, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5630682216484548e-05, + "loss": 3.9234, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5622296268974028e-05, + "loss": 3.9067, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5613910321463508e-05, + "loss": 3.9122, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5605524373952988e-05, + "loss": 3.9219, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5597138426442468e-05, + "loss": 3.9022, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5588752478931944e-05, + "loss": 3.9171, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5580366531421424e-05, + "loss": 3.9049, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5571980583910904e-05, + "loss": 3.928, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5563594636400384e-05, + "loss": 3.9136, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5555208688889864e-05, + "loss": 3.9034, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5546822741379344e-05, + "loss": 3.9042, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5538436793868824e-05, + "loss": 3.9156, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5530067225162036e-05, + "loss": 3.9253, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5521681277651516e-05, + "loss": 3.9152, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5513295330140996e-05, + "loss": 3.9101, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5504925761434205e-05, + "loss": 3.9086, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5496539813923685e-05, + "loss": 3.9164, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.548815386641317e-05, + "loss": 3.9078, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.547976791890265e-05, + "loss": 3.9085, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547138197139213e-05, + "loss": 3.9217, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5463012402685338e-05, + "loss": 3.9227, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454626455174818e-05, + "loss": 3.9174, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446240507664298e-05, + "loss": 3.9023, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5437854560153777e-05, + "loss": 3.9142, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5429468612643257e-05, + "loss": 3.9098, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542108266513274e-05, + "loss": 3.9155, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541269671762222e-05, + "loss": 3.9156, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54043107701117e-05, + "loss": 3.9062, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539592482260118e-05, + "loss": 3.9085, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538753887509066e-05, + "loss": 3.9151, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5379152927580134e-05, + "loss": 3.8951, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5370766980069617e-05, + "loss": 3.9109, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5362397411362833e-05, + "loss": 3.9019, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5354027842656042e-05, + "loss": 3.918, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5345641895145522e-05, + "loss": 3.9082, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533727232643873e-05, + "loss": 3.9119, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.532888637892821e-05, + "loss": 3.9052, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5320500431417694e-05, + "loss": 3.9118, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312114483907174e-05, + "loss": 3.9168, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303728536396654e-05, + "loss": 3.9056, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295342588886134e-05, + "loss": 3.9155, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5286973020179343e-05, + "loss": 3.9212, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278587072668823e-05, + "loss": 3.9145, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5270201125158303e-05, + "loss": 3.9153, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526181517764778e-05, + "loss": 3.9013, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525342923013726e-05, + "loss": 3.9189, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524504328262674e-05, + "loss": 3.9072, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523665733511622e-05, + "loss": 3.916, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.52282713876057e-05, + "loss": 3.9055, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.521988544009518e-05, + "loss": 3.9157, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5211515871388392e-05, + "loss": 3.9114, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5203129923877872e-05, + "loss": 3.9047, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5194743976367352e-05, + "loss": 3.8977, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5186358028856832e-05, + "loss": 3.9051, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5177972081346312e-05, + "loss": 3.9062, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5169602512639524e-05, + "loss": 3.9121, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5161216565129004e-05, + "loss": 3.9262, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5152830617618484e-05, + "loss": 3.9232, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5144444670107964e-05, + "loss": 3.895, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5136058722597444e-05, + "loss": 3.9231, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5127672775086924e-05, + "loss": 3.911, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5119286827576404e-05, + "loss": 3.9125, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5110900880065884e-05, + "loss": 3.9056, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5102531311359097e-05, + "loss": 3.9159, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5094145363848577e-05, + "loss": 3.9071, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5085759416338057e-05, + "loss": 3.9158, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077373468827536e-05, + "loss": 3.9117, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5069003900120746e-05, + "loss": 3.9147, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5060634331413958e-05, + "loss": 3.9162, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5052248383903438e-05, + "loss": 3.9056, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5043862436392918e-05, + "loss": 3.9125, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5035492867686127e-05, + "loss": 3.9195, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5027106920175607e-05, + "loss": 3.9065, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5018720972665087e-05, + "loss": 3.9156, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501033502515457e-05, + "loss": 3.9133, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 4.019649982452393, + "eval_runtime": 286.8796, + "eval_samples_per_second": 1330.143, + "eval_steps_per_second": 41.568, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.500194907764405e-05, + "loss": 3.9054, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4993563130133527e-05, + "loss": 3.908, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4985177182623007e-05, + "loss": 3.9153, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4976791235112487e-05, + "loss": 3.9136, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4968405287601967e-05, + "loss": 3.9279, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496003571889518e-05, + "loss": 3.903, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4951666150188392e-05, + "loss": 3.9141, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494328020267787e-05, + "loss": 3.8982, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4934894255167348e-05, + "loss": 3.9171, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4926508307656828e-05, + "loss": 3.9084, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918122360146308e-05, + "loss": 3.9128, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909736412635788e-05, + "loss": 3.9187, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901366843929e-05, + "loss": 3.9038, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.489298089641848e-05, + "loss": 3.9105, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.488459494890796e-05, + "loss": 3.9042, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487620900139744e-05, + "loss": 3.9023, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.486782305388692e-05, + "loss": 3.9085, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.48594371063764e-05, + "loss": 3.9101, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.485105115886588e-05, + "loss": 3.9093, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.484266521135536e-05, + "loss": 3.924, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.483427926384484e-05, + "loss": 3.9274, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4825909695138053e-05, + "loss": 3.9146, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481752374762753e-05, + "loss": 3.913, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.480913780011701e-05, + "loss": 3.9213, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.480075185260649e-05, + "loss": 3.9012, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792382283899705e-05, + "loss": 3.9199, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.478399633638918e-05, + "loss": 3.914, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.477561038887866e-05, + "loss": 3.9055, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476722444136814e-05, + "loss": 3.9085, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.475883849385762e-05, + "loss": 3.9086, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.47504525463471e-05, + "loss": 3.9091, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474206659883658e-05, + "loss": 3.9127, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4733680651326065e-05, + "loss": 3.9197, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.472529470381554e-05, + "loss": 3.9144, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4716925135108754e-05, + "loss": 3.9174, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4708539187598234e-05, + "loss": 3.915, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470015324008771e-05, + "loss": 3.8962, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4691767292577194e-05, + "loss": 3.9107, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4683381345066674e-05, + "loss": 3.8983, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4675011776359886e-05, + "loss": 3.9045, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4666625828849363e-05, + "loss": 3.9068, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4658239881338843e-05, + "loss": 3.9186, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4649853933828323e-05, + "loss": 3.9099, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4641467986317803e-05, + "loss": 3.9006, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4633082038807282e-05, + "loss": 3.9202, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4624696091296766e-05, + "loss": 3.9089, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4616310143786242e-05, + "loss": 3.9131, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4607924196275722e-05, + "loss": 3.9102, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4599554627568935e-05, + "loss": 3.8984, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4591168680058415e-05, + "loss": 3.9195, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4582782732547895e-05, + "loss": 3.9048, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4574396785037375e-05, + "loss": 3.9119, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4566010837526855e-05, + "loss": 3.9053, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4557641268820067e-05, + "loss": 3.9013, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4549255321309544e-05, + "loss": 3.9019, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4540885752602756e-05, + "loss": 3.9093, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4532499805092236e-05, + "loss": 3.9073, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4524113857581716e-05, + "loss": 3.9095, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4515727910071196e-05, + "loss": 3.9142, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4507341962560676e-05, + "loss": 3.8994, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4498956015050156e-05, + "loss": 3.896, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4490570067539636e-05, + "loss": 3.9251, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4482184120029116e-05, + "loss": 3.8875, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.447381455132233e-05, + "loss": 3.8912, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446542860381181e-05, + "loss": 3.9048, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4457042656301288e-05, + "loss": 3.9192, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4448656708790768e-05, + "loss": 3.9014, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4440270761280248e-05, + "loss": 3.9047, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4431901192573457e-05, + "loss": 3.8926, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442351524506294e-05, + "loss": 3.9004, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441514567635615e-05, + "loss": 3.9124, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440675972884563e-05, + "loss": 3.9093, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.439837378133511e-05, + "loss": 3.9077, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.438998783382459e-05, + "loss": 3.9159, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381618265117802e-05, + "loss": 3.9157, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373232317607282e-05, + "loss": 3.9015, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4364846370096762e-05, + "loss": 3.9044, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4356460422586242e-05, + "loss": 3.9161, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4348074475075722e-05, + "loss": 3.8954, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.43396885275652e-05, + "loss": 3.9122, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.433130258005468e-05, + "loss": 3.8991, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.432291663254416e-05, + "loss": 3.9209, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431454706383737e-05, + "loss": 3.9073, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306177495130583e-05, + "loss": 3.8977, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4297791547620063e-05, + "loss": 3.8915, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4289405600109543e-05, + "loss": 3.9111, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428101965259902e-05, + "loss": 3.9126, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4272633705088503e-05, + "loss": 3.911, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4264264136381716e-05, + "loss": 3.9021, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4255878188871196e-05, + "loss": 3.9022, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4247492241360672e-05, + "loss": 3.9084, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4239106293850152e-05, + "loss": 3.899, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4230720346339632e-05, + "loss": 3.9006, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4222334398829112e-05, + "loss": 3.915, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4213964830122325e-05, + "loss": 3.9122, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4205578882611804e-05, + "loss": 3.9096, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4197192935101284e-05, + "loss": 3.8981, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4188806987590764e-05, + "loss": 3.9053, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4180437418883974e-05, + "loss": 3.8976, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4172051471373457e-05, + "loss": 3.9076, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4163665523862937e-05, + "loss": 3.906, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4155279576352417e-05, + "loss": 3.9035, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4146893628841897e-05, + "loss": 3.899, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4138507681331377e-05, + "loss": 3.9022, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4130138112624586e-05, + "loss": 3.8959, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4121752165114066e-05, + "loss": 3.8991, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411336621760355e-05, + "loss": 3.894, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4104980270093026e-05, + "loss": 3.9108, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4096594322582506e-05, + "loss": 3.9011, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088208375071986e-05, + "loss": 3.8994, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4079838806365198e-05, + "loss": 3.8963, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4071452858854675e-05, + "loss": 3.9088, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4063066911344158e-05, + "loss": 3.9095, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4054680963833638e-05, + "loss": 3.8967, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4046295016323118e-05, + "loss": 3.9088, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4037909068812598e-05, + "loss": 3.9141, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4029539500105807e-05, + "loss": 3.9077, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021153552595287e-05, + "loss": 3.9077, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.40127839838885e-05, + "loss": 3.8942, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.400439803637798e-05, + "loss": 3.9087, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399601208886746e-05, + "loss": 3.9041, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.398762614135694e-05, + "loss": 3.9115, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.397924019384642e-05, + "loss": 3.894, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.39708542463359e-05, + "loss": 3.911, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.396246829882538e-05, + "loss": 3.9043, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395408235131486e-05, + "loss": 3.8972, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394569640380434e-05, + "loss": 3.8927, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393732683509755e-05, + "loss": 3.8985, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3928940887587028e-05, + "loss": 3.8964, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3920554940076508e-05, + "loss": 3.9102, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3912168992565988e-05, + "loss": 3.9138, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903783045055468e-05, + "loss": 3.9186, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389539709754495e-05, + "loss": 3.8889, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.388701115003443e-05, + "loss": 3.9149, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.387862520252391e-05, + "loss": 3.907, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3870239255013388e-05, + "loss": 3.9008, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.38618696863066e-05, + "loss": 3.8987, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385348373879608e-05, + "loss": 3.9124, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384509779128556e-05, + "loss": 3.9007, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383671184377504e-05, + "loss": 3.9081, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3828342275068253e-05, + "loss": 3.899, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3819956327557733e-05, + "loss": 3.9055, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381158675885094e-05, + "loss": 3.908, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380320081134042e-05, + "loss": 3.9019, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3794814863829905e-05, + "loss": 3.9065, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786428916319385e-05, + "loss": 3.9127, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.377804296880886e-05, + "loss": 3.8991, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769673400102074e-05, + "loss": 3.9065, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761287452591554e-05, + "loss": 3.9074, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 4.017175197601318, + "eval_runtime": 287.1832, + "eval_samples_per_second": 1328.737, + "eval_steps_per_second": 41.524, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3752901505081034e-05, + "loss": 3.8978, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744515557570514e-05, + "loss": 3.8982, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736129610059994e-05, + "loss": 3.9099, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727743662549474e-05, + "loss": 3.9086, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719357715038954e-05, + "loss": 3.915, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3710971767528434e-05, + "loss": 3.9011, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702585820017914e-05, + "loss": 3.9073, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369419987250739e-05, + "loss": 3.8942, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685813924996873e-05, + "loss": 3.9072, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677427977486353e-05, + "loss": 3.9029, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669042029975833e-05, + "loss": 3.9078, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660656082465313e-05, + "loss": 3.9096, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652286513758522e-05, + "loss": 3.8987, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3643900566248002e-05, + "loss": 3.9008, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635514618737482e-05, + "loss": 3.8994, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627128671226966e-05, + "loss": 3.8923, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618742723716446e-05, + "loss": 3.8987, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610356776205926e-05, + "loss": 3.9033, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3601970828695402e-05, + "loss": 3.903, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593584881184882e-05, + "loss": 3.9181, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585198933674362e-05, + "loss": 3.9182, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3576829364967575e-05, + "loss": 3.9116, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568443417457055e-05, + "loss": 3.9045, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560057469946534e-05, + "loss": 3.9112, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551671522436014e-05, + "loss": 3.8991, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543285574925494e-05, + "loss": 3.9108, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534899627414974e-05, + "loss": 3.9076, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526513679904454e-05, + "loss": 3.8965, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.351812773239393e-05, + "loss": 3.9013, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509758163687147e-05, + "loss": 3.9062, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501388594980356e-05, + "loss": 3.9026, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3493002647469836e-05, + "loss": 3.9059, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484616699959316e-05, + "loss": 3.9129, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476230752448796e-05, + "loss": 3.9071, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346787756254574e-05, + "loss": 3.909, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.345949161503522e-05, + "loss": 3.909, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451105667524697e-05, + "loss": 3.8944, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442719720014177e-05, + "loss": 3.8962, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434333772503657e-05, + "loss": 3.892, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425947824993137e-05, + "loss": 3.8976, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.341756187748262e-05, + "loss": 3.8998, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.34091759299721e-05, + "loss": 3.913, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400789982461577e-05, + "loss": 3.904, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3392404034951057e-05, + "loss": 3.8915, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338403446624427e-05, + "loss": 3.914, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337564851873375e-05, + "loss": 3.8992, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336726257122323e-05, + "loss": 3.9105, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.335887662371271e-05, + "loss": 3.9, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335049067620219e-05, + "loss": 3.8914, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334210472869167e-05, + "loss": 3.9102, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333371878118115e-05, + "loss": 3.9008, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332533283367063e-05, + "loss": 3.9068, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331694688616011e-05, + "loss": 3.8936, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.330857731745332e-05, + "loss": 3.8969, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.33001913699428e-05, + "loss": 3.8927, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329182180123601e-05, + "loss": 3.9009, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328343585372549e-05, + "loss": 3.9037, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327504990621497e-05, + "loss": 3.8969, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326666395870445e-05, + "loss": 3.9091, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258294389997663e-05, + "loss": 3.8967, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249908442487143e-05, + "loss": 3.8913, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3241522494976623e-05, + "loss": 3.92, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233136547466103e-05, + "loss": 3.8822, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224750599955583e-05, + "loss": 3.8808, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3216381031248792e-05, + "loss": 3.8984, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3207995083738275e-05, + "loss": 3.9155, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199609136227755e-05, + "loss": 3.8897, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191223188717232e-05, + "loss": 3.9005, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3182837241206712e-05, + "loss": 3.8853, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317445129369619e-05, + "loss": 3.8929, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316606534618567e-05, + "loss": 3.9065, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157695777478884e-05, + "loss": 3.9044, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149309829968364e-05, + "loss": 3.9016, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140923882457844e-05, + "loss": 3.9045, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132537934947324e-05, + "loss": 3.9096, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124151987436804e-05, + "loss": 3.8917, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115782418730013e-05, + "loss": 3.9, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310741285002323e-05, + "loss": 3.9053, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099026902512705e-05, + "loss": 3.8898, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090640955002185e-05, + "loss": 3.9009, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082255007491665e-05, + "loss": 3.8959, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073869059981145e-05, + "loss": 3.9113, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065483112470625e-05, + "loss": 3.903, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057097164960105e-05, + "loss": 3.8933, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048727596253318e-05, + "loss": 3.886, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040341648742798e-05, + "loss": 3.9023, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031955701232278e-05, + "loss": 3.9053, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023569753721758e-05, + "loss": 3.8996, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015200185014967e-05, + "loss": 3.8997, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006814237504447e-05, + "loss": 3.8977, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299842828999393e-05, + "loss": 3.9005, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299004234248341e-05, + "loss": 3.8935, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2981656394972887e-05, + "loss": 3.8907, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973270447462366e-05, + "loss": 3.9089, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296490087875558e-05, + "loss": 3.9047, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295651493124506e-05, + "loss": 3.9005, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.294812898373454e-05, + "loss": 3.8896, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.293974303622402e-05, + "loss": 3.901, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.29313570887135e-05, + "loss": 3.8903, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292298752000671e-05, + "loss": 3.9037, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914601572496188e-05, + "loss": 3.898, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906215624985668e-05, + "loss": 3.8964, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897829677475148e-05, + "loss": 3.8937, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.288946010876836e-05, + "loss": 3.8901, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288107416125784e-05, + "loss": 3.8955, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287268821374732e-05, + "loss": 3.8881, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.28643022662368e-05, + "loss": 3.8904, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285591631872628e-05, + "loss": 3.8992, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284753037121576e-05, + "loss": 3.8989, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839160802508972e-05, + "loss": 3.8931, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830774854998452e-05, + "loss": 3.8878, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822388907487932e-05, + "loss": 3.8993, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814002959977412e-05, + "loss": 3.9033, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280561701246689e-05, + "loss": 3.8957, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279723106495637e-05, + "loss": 3.9036, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788845117445852e-05, + "loss": 3.9041, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780459169935332e-05, + "loss": 3.9028, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277208960122854e-05, + "loss": 3.8979, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276370365371802e-05, + "loss": 3.8895, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.27553177062075e-05, + "loss": 3.8976, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274693175869698e-05, + "loss": 3.8982, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.273854581118646e-05, + "loss": 3.9031, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730159863675944e-05, + "loss": 3.89, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721773916165424e-05, + "loss": 3.9006, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.27133879686549e-05, + "loss": 3.8967, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705018399948113e-05, + "loss": 3.8925, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696632452437593e-05, + "loss": 3.8825, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268824650492707e-05, + "loss": 3.8949, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679876936220286e-05, + "loss": 3.8891, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671490988709766e-05, + "loss": 3.9024, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663105041199246e-05, + "loss": 3.9074, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654719093688722e-05, + "loss": 3.9109, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646333146178202e-05, + "loss": 3.8837, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2637947198667682e-05, + "loss": 3.9073, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2629561251157162e-05, + "loss": 3.9012, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2621191682450375e-05, + "loss": 3.8954, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612805734939855e-05, + "loss": 3.8904, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604419787429335e-05, + "loss": 3.9077, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2596033839918815e-05, + "loss": 3.8904, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2587647892408294e-05, + "loss": 3.9053, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2579261944897774e-05, + "loss": 3.891, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2570875997387254e-05, + "loss": 3.9025, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2562490049876734e-05, + "loss": 3.8985, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554136859973676e-05, + "loss": 3.8962, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545750912463156e-05, + "loss": 3.9026, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537364964952636e-05, + "loss": 3.8984, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2528979017442116e-05, + "loss": 3.9006, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252060944873533e-05, + "loss": 3.8924, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512223501224808e-05, + "loss": 3.9082, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 4.014023303985596, + "eval_runtime": 364.7677, + "eval_samples_per_second": 1046.121, + "eval_steps_per_second": 32.692, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2503837553714288e-05, + "loss": 3.895, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2495451606203768e-05, + "loss": 3.8893, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2487065658693248e-05, + "loss": 3.8991, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478679711182725e-05, + "loss": 3.9057, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470293763672208e-05, + "loss": 3.9071, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2461907816161688e-05, + "loss": 3.8924, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2453521868651168e-05, + "loss": 3.8971, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445152299944377e-05, + "loss": 3.8864, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436766352433857e-05, + "loss": 3.9018, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.242839678372707e-05, + "loss": 3.8952, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2420010836216553e-05, + "loss": 3.9028, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241162488870603e-05, + "loss": 3.9016, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403255319999242e-05, + "loss": 3.8936, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2394869372488722e-05, + "loss": 3.8969, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.23864834249782e-05, + "loss": 3.887, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.237809747746768e-05, + "loss": 3.884, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369711529957162e-05, + "loss": 3.8929, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236132558244664e-05, + "loss": 3.9004, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235293963493612e-05, + "loss": 3.8938, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.23445536874256e-05, + "loss": 3.9146, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233616773991508e-05, + "loss": 3.9087, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327781792404558e-05, + "loss": 3.9066, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319395844894038e-05, + "loss": 3.8985, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2311026276187254e-05, + "loss": 3.9024, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230264032867673e-05, + "loss": 3.8888, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.229425438116621e-05, + "loss": 3.9081, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.228586843365569e-05, + "loss": 3.8969, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227748248614517e-05, + "loss": 3.8904, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.226909653863465e-05, + "loss": 3.8979, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226071059112413e-05, + "loss": 3.8968, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.225232464361361e-05, + "loss": 3.8959, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2243955074906823e-05, + "loss": 3.8994, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235585506200032e-05, + "loss": 3.9022, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227199558689512e-05, + "loss": 3.9058, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2218829989982724e-05, + "loss": 3.8945, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2210444042472204e-05, + "loss": 3.9019, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2202058094961684e-05, + "loss": 3.8933, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193672147451164e-05, + "loss": 3.8853, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185286199940644e-05, + "loss": 3.8861, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2176900252430124e-05, + "loss": 3.8907, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2168514304919604e-05, + "loss": 3.8945, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2160128357409084e-05, + "loss": 3.905, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2151742409898564e-05, + "loss": 3.8955, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2143356462388044e-05, + "loss": 3.8878, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2134970514877524e-05, + "loss": 3.9078, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126584567367004e-05, + "loss": 3.8921, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118214998660213e-05, + "loss": 3.9039, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2109829051149693e-05, + "loss": 3.8957, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2101443103639173e-05, + "loss": 3.879, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2093057156128656e-05, + "loss": 3.9097, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084687587421865e-05, + "loss": 3.8923, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076301639911345e-05, + "loss": 3.9015, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067915692400825e-05, + "loss": 3.8908, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2059529744890305e-05, + "loss": 3.8905, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205117655498725e-05, + "loss": 3.8828, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204279060747673e-05, + "loss": 3.8914, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203440465996621e-05, + "loss": 3.9016, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2026018712455687e-05, + "loss": 3.887, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2017632764945167e-05, + "loss": 3.9019, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2009246817434646e-05, + "loss": 3.8937, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2000860869924126e-05, + "loss": 3.8831, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199247492241361e-05, + "loss": 3.9089, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198410535370682e-05, + "loss": 3.8778, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.19757194061963e-05, + "loss": 3.8737, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196733345868578e-05, + "loss": 3.8955, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.195894751117526e-05, + "loss": 3.9012, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.195056156366474e-05, + "loss": 3.8827, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194217561615422e-05, + "loss": 3.8956, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.19337896686437e-05, + "loss": 3.8762, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192540372113318e-05, + "loss": 3.8906, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191703415242639e-05, + "loss": 3.8982, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908648204915868e-05, + "loss": 3.894, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900262257405348e-05, + "loss": 3.8971, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.189187630989483e-05, + "loss": 3.8966, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.188349036238431e-05, + "loss": 3.9052, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187512079367752e-05, + "loss": 3.8838, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1866734846167e-05, + "loss": 3.8957, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858365277460212e-05, + "loss": 3.8919, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1849979329949692e-05, + "loss": 3.885, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841593382439172e-05, + "loss": 3.8949, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833207434928652e-05, + "loss": 3.8911, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824821487418132e-05, + "loss": 3.9005, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816435539907612e-05, + "loss": 3.9009, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1808049592397092e-05, + "loss": 3.8799, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799663644886572e-05, + "loss": 3.8811, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791294076179785e-05, + "loss": 3.8955, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782908128669265e-05, + "loss": 3.9007, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774522181158745e-05, + "loss": 3.8955, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176613623364822e-05, + "loss": 3.8886, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.17577502861377e-05, + "loss": 3.8943, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.174936433862718e-05, + "loss": 3.8907, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174097839111666e-05, + "loss": 3.8903, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173259244360614e-05, + "loss": 3.8841, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724222874899353e-05, + "loss": 3.9009, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715836927388833e-05, + "loss": 3.897, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707450979878313e-05, + "loss": 3.8983, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1699081411171522e-05, + "loss": 3.8847, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690695463661002e-05, + "loss": 3.8902, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1682309516150486e-05, + "loss": 3.8877, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1673923568639966e-05, + "loss": 3.8963, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665537621129446e-05, + "loss": 3.8921, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657151673618926e-05, + "loss": 3.8875, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1648765726108402e-05, + "loss": 3.8903, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1640379778597882e-05, + "loss": 3.8831, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1631993831087362e-05, + "loss": 3.8881, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1623607883576842e-05, + "loss": 3.8816, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1615221936066325e-05, + "loss": 3.8869, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1606835988555805e-05, + "loss": 3.8868, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1598466419849014e-05, + "loss": 3.8987, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1590096851142223e-05, + "loss": 3.8819, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1581710903631703e-05, + "loss": 3.8864, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1573324956121187e-05, + "loss": 3.8884, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1564939008610667e-05, + "loss": 3.8964, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1556553061100147e-05, + "loss": 3.8892, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1548167113589627e-05, + "loss": 3.8993, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1539781166079107e-05, + "loss": 3.8978, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531411597372316e-05, + "loss": 3.8969, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1523042028665528e-05, + "loss": 3.8914, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1514656081155008e-05, + "loss": 3.8867, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1506270133644488e-05, + "loss": 3.8902, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1497884186133968e-05, + "loss": 3.8962, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489498238623448e-05, + "loss": 3.8909, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481112291112928e-05, + "loss": 3.8876, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472726343602405e-05, + "loss": 3.8967, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464340396091888e-05, + "loss": 3.8912, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1455954448581368e-05, + "loss": 3.8876, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144758487987458e-05, + "loss": 3.8755, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439198932364057e-05, + "loss": 3.8863, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430812984853537e-05, + "loss": 3.8813, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422427037343017e-05, + "loss": 3.896, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414041089832497e-05, + "loss": 3.9021, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140567152112571e-05, + "loss": 3.9015, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139728557361519e-05, + "loss": 3.8773, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.138889962610467e-05, + "loss": 3.9001, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138051367859415e-05, + "loss": 3.8929, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137212773108363e-05, + "loss": 3.8919, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136374178357311e-05, + "loss": 3.8849, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135535583606259e-05, + "loss": 3.8983, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.134696988855207e-05, + "loss": 3.8835, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.133860031984528e-05, + "loss": 3.8987, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133021437233476e-05, + "loss": 3.8824, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321828424824238e-05, + "loss": 3.8948, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131345885611745e-05, + "loss": 3.8915, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305072908606934e-05, + "loss": 3.8894, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296703339900143e-05, + "loss": 3.8938, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288317392389623e-05, + "loss": 3.8941, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1279931444879103e-05, + "loss": 3.8951, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1271545497368583e-05, + "loss": 3.8861, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1263159549858063e-05, + "loss": 3.9023, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 4.011499881744385, + "eval_runtime": 353.0713, + "eval_samples_per_second": 1080.776, + "eval_steps_per_second": 33.775, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1254773602347543e-05, + "loss": 3.8897, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1246387654837023e-05, + "loss": 3.8811, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1238001707326503e-05, + "loss": 3.8959, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1229615759815983e-05, + "loss": 3.8972, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1221229812305462e-05, + "loss": 3.8991, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1212843864794942e-05, + "loss": 3.887, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120445791728442e-05, + "loss": 3.8938, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196071969773902e-05, + "loss": 3.8804, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187686022263382e-05, + "loss": 3.8936, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179300074752862e-05, + "loss": 3.8922, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1170914127242342e-05, + "loss": 3.8936, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1162528179731822e-05, + "loss": 3.8961, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115415861102503e-05, + "loss": 3.8907, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114577266351451e-05, + "loss": 3.8876, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1137386716003995e-05, + "loss": 3.8829, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1129000768493474e-05, + "loss": 3.8792, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112061482098295e-05, + "loss": 3.8882, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111222887347243e-05, + "loss": 3.8932, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110384292596191e-05, + "loss": 3.8887, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1095473357255123e-05, + "loss": 3.9031, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087087409744603e-05, + "loss": 3.9036, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078701462234083e-05, + "loss": 3.9026, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070315514723563e-05, + "loss": 3.8907, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1061929567213043e-05, + "loss": 3.8927, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1053543619702523e-05, + "loss": 3.8896, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1045157672192003e-05, + "loss": 3.8991, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103677172468148e-05, + "loss": 3.8891, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.102838577717096e-05, + "loss": 3.8878, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1020016208464176e-05, + "loss": 3.8919, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1011630260953656e-05, + "loss": 3.888, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1003244313443132e-05, + "loss": 3.8869, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0994858365932612e-05, + "loss": 3.895, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986472418422092e-05, + "loss": 3.8965, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0978102849715305e-05, + "loss": 3.9001, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0969733281008517e-05, + "loss": 3.8846, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0961347333497997e-05, + "loss": 3.8999, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0952961385987477e-05, + "loss": 3.8906, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0944575438476953e-05, + "loss": 3.8754, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0936189490966433e-05, + "loss": 3.8787, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0927803543455913e-05, + "loss": 3.8821, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0919417595945397e-05, + "loss": 3.8903, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0911031648434877e-05, + "loss": 3.8951, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0902645700924357e-05, + "loss": 3.8904, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0894259753413837e-05, + "loss": 3.8809, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885873805903313e-05, + "loss": 3.9034, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877487858392793e-05, + "loss": 3.8865, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0869101910882273e-05, + "loss": 3.8979, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0860748720979218e-05, + "loss": 3.8908, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0852362773468698e-05, + "loss": 3.8666, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0843976825958178e-05, + "loss": 3.9066, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835590878447658e-05, + "loss": 3.8826, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827204930937135e-05, + "loss": 3.8941, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0818818983426618e-05, + "loss": 3.8852, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081044941471983e-05, + "loss": 3.8829, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080206346720931e-05, + "loss": 3.8807, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793677519698787e-05, + "loss": 3.8809, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785291572188267e-05, + "loss": 3.9011, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077692200348148e-05, + "loss": 3.8767, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.076853605597096e-05, + "loss": 3.894, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076015010846044e-05, + "loss": 3.8906, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075176416094992e-05, + "loss": 3.8743, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.07433782134394e-05, + "loss": 3.8991, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073499226592888e-05, + "loss": 3.8799, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072660631841836e-05, + "loss": 3.8715, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.071822037090784e-05, + "loss": 3.8846, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.070983442339732e-05, + "loss": 3.8944, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070146485469053e-05, + "loss": 3.8783, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069307890718001e-05, + "loss": 3.8913, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068469295966949e-05, + "loss": 3.8723, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676307012158968e-05, + "loss": 3.8798, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.066793744345218e-05, + "loss": 3.8926, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.065955149594166e-05, + "loss": 3.8865, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651165548431144e-05, + "loss": 3.8922, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064277960092062e-05, + "loss": 3.8866, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0634410032213833e-05, + "loss": 3.8979, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0626024084703313e-05, + "loss": 3.8841, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0617654515996522e-05, + "loss": 3.8908, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0609268568486005e-05, + "loss": 3.8814, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0600882620975485e-05, + "loss": 3.8826, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592496673464965e-05, + "loss": 3.8876, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058411072595444e-05, + "loss": 3.8869, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057572477844392e-05, + "loss": 3.8936, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.05673388309334e-05, + "loss": 3.8999, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0558969262226614e-05, + "loss": 3.8702, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550583314716094e-05, + "loss": 3.8756, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542197367205574e-05, + "loss": 3.8878, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533811419695054e-05, + "loss": 3.8938, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0525425472184534e-05, + "loss": 3.8902, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0517055903477743e-05, + "loss": 3.8812, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.050868633477096e-05, + "loss": 3.8917, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050030038726044e-05, + "loss": 3.8836, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0491930818553648e-05, + "loss": 3.8846, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483544871043128e-05, + "loss": 3.8794, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475158923532608e-05, + "loss": 3.8915, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0466772976022088e-05, + "loss": 3.8934, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0458387028511568e-05, + "loss": 3.8919, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0450001081001048e-05, + "loss": 3.8789, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0441615133490528e-05, + "loss": 3.8798, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0433229185980008e-05, + "loss": 3.881, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0424843238469488e-05, + "loss": 3.8897, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0416457290958967e-05, + "loss": 3.888, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408071343448444e-05, + "loss": 3.881, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0399685395937927e-05, + "loss": 3.884, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0391299448427407e-05, + "loss": 3.8785, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0382913500916887e-05, + "loss": 3.8812, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0374527553406367e-05, + "loss": 3.8749, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0366141605895847e-05, + "loss": 3.8825, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0357772037189056e-05, + "loss": 3.8821, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349386089678536e-05, + "loss": 3.8901, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034100014216802e-05, + "loss": 3.88, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.03326141946575e-05, + "loss": 3.874, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032424462595071e-05, + "loss": 3.8833, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031585867844019e-05, + "loss": 3.8879, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.030747273092967e-05, + "loss": 3.8852, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.029908678341915e-05, + "loss": 3.8906, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0290733593516094e-05, + "loss": 3.8885, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028234764600557e-05, + "loss": 3.8957, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027396169849505e-05, + "loss": 3.8848, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026557575098453e-05, + "loss": 3.8808, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025718980347401e-05, + "loss": 3.8802, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0248820234767222e-05, + "loss": 3.8945, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240434287256702e-05, + "loss": 3.8826, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0232048339746182e-05, + "loss": 3.8795, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223662392235662e-05, + "loss": 3.8903, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021529282352887e-05, + "loss": 3.8905, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020690687601835e-05, + "loss": 3.8783, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0198520928507835e-05, + "loss": 3.8727, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190134980997315e-05, + "loss": 3.8795, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181749033486795e-05, + "loss": 3.8774, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173363085976275e-05, + "loss": 3.8888, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016497713846575e-05, + "loss": 3.893, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015659119095523e-05, + "loss": 3.8971, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.014820524344471e-05, + "loss": 3.8703, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.013981929593419e-05, + "loss": 3.8972, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131433348423674e-05, + "loss": 3.8861, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0123047400913154e-05, + "loss": 3.8861, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0114677832206363e-05, + "loss": 3.8789, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0106308263499573e-05, + "loss": 3.8898, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0097922315989052e-05, + "loss": 3.8778, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0089536368478536e-05, + "loss": 3.8963, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081150420968016e-05, + "loss": 3.8785, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072764473457496e-05, + "loss": 3.8876, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064378525946976e-05, + "loss": 3.8867, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0055992578436456e-05, + "loss": 3.8866, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0047623009729665e-05, + "loss": 3.886, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0039237062219145e-05, + "loss": 3.8862, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0030851114708628e-05, + "loss": 3.8896, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0022465167198105e-05, + "loss": 3.8823, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014095598491317e-05, + "loss": 3.8936, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 4.009556293487549, + "eval_runtime": 293.1806, + "eval_samples_per_second": 1301.556, + "eval_steps_per_second": 40.675, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0005726029784526e-05, + "loss": 3.877, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9997340082274006e-05, + "loss": 3.8785, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.998895413476349e-05, + "loss": 3.8851, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.998056818725297e-05, + "loss": 3.8907, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997218223974245e-05, + "loss": 3.8961, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996379629223193e-05, + "loss": 3.8821, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9955410344721406e-05, + "loss": 3.8915, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9947024397210886e-05, + "loss": 3.8774, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99386548285041e-05, + "loss": 3.8838, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993026888099358e-05, + "loss": 3.8852, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9921882933483058e-05, + "loss": 3.8873, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991351336477627e-05, + "loss": 3.8892, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990514379606948e-05, + "loss": 3.8884, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989675784855896e-05, + "loss": 3.8767, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888371901048443e-05, + "loss": 3.8789, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9879985953537923e-05, + "loss": 3.8705, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.98716000060274e-05, + "loss": 3.8816, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986321405851688e-05, + "loss": 3.8902, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985482811100636e-05, + "loss": 3.8793, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984644216349584e-05, + "loss": 3.8957, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.983805621598532e-05, + "loss": 3.8974, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.98296702684748e-05, + "loss": 3.8937, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821300699768012e-05, + "loss": 3.8921, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9812914752257492e-05, + "loss": 3.8814, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9804528804746972e-05, + "loss": 3.8828, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9796142857236452e-05, + "loss": 3.8893, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9787756909725932e-05, + "loss": 3.8891, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.977937096221541e-05, + "loss": 3.8814, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977098501470489e-05, + "loss": 3.8865, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976259906719437e-05, + "loss": 3.8842, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975421311968385e-05, + "loss": 3.8777, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974582717217333e-05, + "loss": 3.8887, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.973744122466281e-05, + "loss": 3.8891, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9729055277152288e-05, + "loss": 3.8917, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.97206857084455e-05, + "loss": 3.8817, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712332518542446e-05, + "loss": 3.8909, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9703946571031926e-05, + "loss": 3.885, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695560623521405e-05, + "loss": 3.8692, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9687174676010882e-05, + "loss": 3.8785, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678788728500362e-05, + "loss": 3.8746, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670402780989845e-05, + "loss": 3.8808, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9662016833479325e-05, + "loss": 3.8931, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653630885968805e-05, + "loss": 3.8849, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645244938458285e-05, + "loss": 3.8769, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636858990947762e-05, + "loss": 3.893, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9628473043437242e-05, + "loss": 3.8788, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962008709592672e-05, + "loss": 3.894, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9611733906023667e-05, + "loss": 3.8866, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9603347958513147e-05, + "loss": 3.8597, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9594962011002627e-05, + "loss": 3.9002, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586576063492107e-05, + "loss": 3.8769, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9578206494785316e-05, + "loss": 3.8882, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.95698205472748e-05, + "loss": 3.8802, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956143459976428e-05, + "loss": 3.8783, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955304865225376e-05, + "loss": 3.8751, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9544679083546968e-05, + "loss": 3.8768, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9536293136036448e-05, + "loss": 3.8966, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9527907188525928e-05, + "loss": 3.8681, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9519521241015408e-05, + "loss": 3.8937, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951115167230862e-05, + "loss": 3.8828, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.95027657247981e-05, + "loss": 3.8668, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949437977728758e-05, + "loss": 3.8949, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948599382977706e-05, + "loss": 3.8738, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9477607882266537e-05, + "loss": 3.8621, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469221934756017e-05, + "loss": 3.8791, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.94608359872455e-05, + "loss": 3.888, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945245003973498e-05, + "loss": 3.8759, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944406409222446e-05, + "loss": 3.8835, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943569452351767e-05, + "loss": 3.8698, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942730857600715e-05, + "loss": 3.8736, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.941892262849663e-05, + "loss": 3.887, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941053668098611e-05, + "loss": 3.8831, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940216711227932e-05, + "loss": 3.8832, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.93937811647688e-05, + "loss": 3.8814, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938539521725828e-05, + "loss": 3.8961, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937700926974776e-05, + "loss": 3.875, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.936863970104097e-05, + "loss": 3.8846, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9360253753530454e-05, + "loss": 3.8744, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9351867806019934e-05, + "loss": 3.8762, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9343481858509414e-05, + "loss": 3.883, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933509591099889e-05, + "loss": 3.8768, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9326726342292103e-05, + "loss": 3.8877, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9318340394781583e-05, + "loss": 3.8951, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9309954447271063e-05, + "loss": 3.866, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9301568499760543e-05, + "loss": 3.8691, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293198931053755e-05, + "loss": 3.8826, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9284812983543235e-05, + "loss": 3.8856, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927642703603271e-05, + "loss": 3.8843, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.926804108852219e-05, + "loss": 3.8786, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259655141011675e-05, + "loss": 3.8849, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251269193501155e-05, + "loss": 3.8784, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242899624794364e-05, + "loss": 3.8748, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234513677283844e-05, + "loss": 3.8772, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226127729773324e-05, + "loss": 3.888, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9217758161066536e-05, + "loss": 3.8891, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9209372213556016e-05, + "loss": 3.8876, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9200986266045496e-05, + "loss": 3.8705, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192600318534976e-05, + "loss": 3.8767, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184214371024456e-05, + "loss": 3.8766, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175828423513936e-05, + "loss": 3.8816, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167442476003416e-05, + "loss": 3.8837, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9159056528492893e-05, + "loss": 3.8719, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9150670580982376e-05, + "loss": 3.8817, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9142284633471856e-05, + "loss": 3.8685, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9133898685961336e-05, + "loss": 3.8745, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125512738450816e-05, + "loss": 3.8682, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117143169744025e-05, + "loss": 3.8798, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108773601037237e-05, + "loss": 3.8782, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9100387653526717e-05, + "loss": 3.8821, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9092001706016197e-05, + "loss": 3.8724, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908363213730941e-05, + "loss": 3.8736, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.907524618979889e-05, + "loss": 3.8739, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9066860242288366e-05, + "loss": 3.8875, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058474294777846e-05, + "loss": 3.8786, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.905008834726733e-05, + "loss": 3.8814, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.904170239975681e-05, + "loss": 3.8822, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903331645224629e-05, + "loss": 3.8913, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902493050473577e-05, + "loss": 3.8789, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901654455722525e-05, + "loss": 3.8763, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9008158609714726e-05, + "loss": 3.8789, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.8999772662204206e-05, + "loss": 3.8863, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8991386714693686e-05, + "loss": 3.8767, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898300076718317e-05, + "loss": 3.8764, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897464757728011e-05, + "loss": 3.8813, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896626162976959e-05, + "loss": 3.8835, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895787568225907e-05, + "loss": 3.873, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8949489734748547e-05, + "loss": 3.8667, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8941120166041763e-05, + "loss": 3.872, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8932734218531243e-05, + "loss": 3.8695, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8924348271020723e-05, + "loss": 3.8868, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.89159623235102e-05, + "loss": 3.8857, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890757637599968e-05, + "loss": 3.891, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.889919042848916e-05, + "loss": 3.8659, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889080448097864e-05, + "loss": 3.8908, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882434912271852e-05, + "loss": 3.8814, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8874065343565065e-05, + "loss": 3.8806, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8865679396054545e-05, + "loss": 3.8761, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.885729344854402e-05, + "loss": 3.8761, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.88489075010335e-05, + "loss": 3.8772, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8840521553522984e-05, + "loss": 3.8908, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832135606012464e-05, + "loss": 3.8692, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8823749658501944e-05, + "loss": 3.8829, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8815363710991424e-05, + "loss": 3.8853, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8806977763480904e-05, + "loss": 3.8834, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.879859181597038e-05, + "loss": 3.8732, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879020586845986e-05, + "loss": 3.8813, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8781836299753077e-05, + "loss": 3.8844, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8773466731046286e-05, + "loss": 3.8774, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8765080783535766e-05, + "loss": 3.886, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 4.0070624351501465, + "eval_runtime": 295.1859, + "eval_samples_per_second": 1292.714, + "eval_steps_per_second": 40.398, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756694836025246e-05, + "loss": 3.8776, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748308888514726e-05, + "loss": 3.87, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8739922941004202e-05, + "loss": 3.8811, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731536993493686e-05, + "loss": 3.8864, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723151045983165e-05, + "loss": 3.8897, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714765098472645e-05, + "loss": 3.8796, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706379150962125e-05, + "loss": 3.8833, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8697993203451605e-05, + "loss": 3.8691, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689607255941085e-05, + "loss": 3.8777, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681221308430562e-05, + "loss": 3.8809, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672835360920042e-05, + "loss": 3.8816, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664449413409525e-05, + "loss": 3.8828, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656079844702734e-05, + "loss": 3.8866, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647693897192214e-05, + "loss": 3.8697, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639307949681694e-05, + "loss": 3.8721, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8630922002171174e-05, + "loss": 3.8616, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8622536054660654e-05, + "loss": 3.8809, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8614150107150134e-05, + "loss": 3.8855, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605780538443347e-05, + "loss": 3.8703, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597394590932826e-05, + "loss": 3.8871, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8589008643422306e-05, + "loss": 3.8949, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580622695911786e-05, + "loss": 3.889, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572236748401266e-05, + "loss": 3.8833, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563850800890746e-05, + "loss": 3.8784, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555464853380226e-05, + "loss": 3.8802, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8547078905869706e-05, + "loss": 3.881, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538709337162915e-05, + "loss": 3.8834, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530323389652395e-05, + "loss": 3.8834, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8521937442141875e-05, + "loss": 3.8778, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8513551494631355e-05, + "loss": 3.8741, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850516554712084e-05, + "loss": 3.8733, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849677959961032e-05, + "loss": 3.8855, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.84883936520998e-05, + "loss": 3.887, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8480007704589275e-05, + "loss": 3.8845, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471621757078755e-05, + "loss": 3.8774, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8463252188371967e-05, + "loss": 3.8815, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845488261966518e-05, + "loss": 3.8817, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844649667215466e-05, + "loss": 3.8645, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.843811072464414e-05, + "loss": 3.8715, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.842972477713362e-05, + "loss": 3.8702, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421338829623096e-05, + "loss": 3.8733, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8412952882112576e-05, + "loss": 3.8865, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8404566934602056e-05, + "loss": 3.8781, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839618098709154e-05, + "loss": 3.8731, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.838779503958102e-05, + "loss": 3.8868, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.837942547087423e-05, + "loss": 3.8727, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837103952336371e-05, + "loss": 3.8845, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836265357585319e-05, + "loss": 3.8889, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835426762834267e-05, + "loss": 3.8532, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834588168083215e-05, + "loss": 3.8897, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8337495733321632e-05, + "loss": 3.8766, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.832912616461484e-05, + "loss": 3.8816, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832074021710432e-05, + "loss": 3.8749, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.83123542695938e-05, + "loss": 3.8689, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8303968322083277e-05, + "loss": 3.8725, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295598753376493e-05, + "loss": 3.869, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8287212805865973e-05, + "loss": 3.8922, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8278826858355453e-05, + "loss": 3.8633, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827044091084493e-05, + "loss": 3.8892, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826205496333441e-05, + "loss": 3.8786, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825366901582389e-05, + "loss": 3.8614, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8245299447117102e-05, + "loss": 3.8886, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8236913499606582e-05, + "loss": 3.8661, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228527552096062e-05, + "loss": 3.8579, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220157983389275e-05, + "loss": 3.8702, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821177203587875e-05, + "loss": 3.8854, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820338608836823e-05, + "loss": 3.8669, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819500014085771e-05, + "loss": 3.8815, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8186614193347194e-05, + "loss": 3.8649, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178228245836674e-05, + "loss": 3.8649, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169842298326154e-05, + "loss": 3.8785, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161456350815634e-05, + "loss": 3.8783, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815307040330511e-05, + "loss": 3.8819, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8144700834598323e-05, + "loss": 3.8784, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136314887087803e-05, + "loss": 3.8855, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8127928939577283e-05, + "loss": 3.8748, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119542992066763e-05, + "loss": 3.8767, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111157044556243e-05, + "loss": 3.8646, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102803854653185e-05, + "loss": 3.8743, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094417907142665e-05, + "loss": 3.8769, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8086031959632148e-05, + "loss": 3.87, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077646012121628e-05, + "loss": 3.8829, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069260064611108e-05, + "loss": 3.8874, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060890495904317e-05, + "loss": 3.8674, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052504548393797e-05, + "loss": 3.8607, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044118600883277e-05, + "loss": 3.8785, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035732653372757e-05, + "loss": 3.8777, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027346705862237e-05, + "loss": 3.8811, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.801897713715545e-05, + "loss": 3.871, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801059118964493e-05, + "loss": 3.882, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002205242134406e-05, + "loss": 3.8709, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993819294623886e-05, + "loss": 3.871, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985433347113366e-05, + "loss": 3.8737, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797704739960285e-05, + "loss": 3.8784, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.796866145209233e-05, + "loss": 3.8801, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796027550458181e-05, + "loss": 3.8838, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795188955707129e-05, + "loss": 3.8651, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943503609560766e-05, + "loss": 3.8756, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935117662050246e-05, + "loss": 3.8664, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926748093343458e-05, + "loss": 3.878, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918362145832938e-05, + "loss": 3.8784, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7909976198322418e-05, + "loss": 3.8712, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7901590250811898e-05, + "loss": 3.876, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789322068210511e-05, + "loss": 3.8646, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7884834734594587e-05, + "loss": 3.8716, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787644878708407e-05, + "loss": 3.864, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786806283957355e-05, + "loss": 3.8731, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.785967689206303e-05, + "loss": 3.8737, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785129094455251e-05, + "loss": 3.875, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784290499704199e-05, + "loss": 3.8661, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783451904953147e-05, + "loss": 3.8671, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782614948082468e-05, + "loss": 3.8689, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781776353331416e-05, + "loss": 3.8823, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.780939396460737e-05, + "loss": 3.8743, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780100801709685e-05, + "loss": 3.8737, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779262206958633e-05, + "loss": 3.8786, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778423612207581e-05, + "loss": 3.8852, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777586655336902e-05, + "loss": 3.8742, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7767480605858504e-05, + "loss": 3.871, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7759094658347984e-05, + "loss": 3.8736, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750708710837464e-05, + "loss": 3.8802, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7742339142130673e-05, + "loss": 3.8752, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7733953194620153e-05, + "loss": 3.8703, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7725567247109633e-05, + "loss": 3.8724, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7717181299599113e-05, + "loss": 3.8814, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708795352088593e-05, + "loss": 3.867, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700409404578073e-05, + "loss": 3.8639, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7692039835871285e-05, + "loss": 3.8655, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683653888360765e-05, + "loss": 3.862, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767526794085024e-05, + "loss": 3.8848, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666881993339725e-05, + "loss": 3.874, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658496045829205e-05, + "loss": 3.8887, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650110098318685e-05, + "loss": 3.8644, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641724150808165e-05, + "loss": 3.8806, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633354582101374e-05, + "loss": 3.8748, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7624968634590854e-05, + "loss": 3.8764, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7616582687080334e-05, + "loss": 3.8731, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7608196739569814e-05, + "loss": 3.8707, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599827170863026e-05, + "loss": 3.8679, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591441223352506e-05, + "loss": 3.8888, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7583055275841986e-05, + "loss": 3.8652, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574669328331466e-05, + "loss": 3.8783, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566283380820946e-05, + "loss": 3.8811, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557897433310426e-05, + "loss": 3.8731, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.754952786460364e-05, + "loss": 3.8681, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754114191709312e-05, + "loss": 3.8759, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532755969582595e-05, + "loss": 3.8774, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524370022072075e-05, + "loss": 3.8756, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7515984074561555e-05, + "loss": 3.8806, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 4.0049662590026855, + "eval_runtime": 295.9435, + "eval_samples_per_second": 1289.405, + "eval_steps_per_second": 40.295, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7507598127051035e-05, + "loss": 3.8654, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.749921217954052e-05, + "loss": 3.8657, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7490842610833727e-05, + "loss": 3.8767, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7482456663323207e-05, + "loss": 3.8805, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7474070715812687e-05, + "loss": 3.8864, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7465684768302167e-05, + "loss": 3.8721, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.745731519959538e-05, + "loss": 3.8767, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.744892925208486e-05, + "loss": 3.8684, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744055968337807e-05, + "loss": 3.8725, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743217373586755e-05, + "loss": 3.8754, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.742378778835703e-05, + "loss": 3.8741, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741540184084651e-05, + "loss": 3.8808, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740703227213972e-05, + "loss": 3.8815, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7398662703432934e-05, + "loss": 3.8639, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7390276755922414e-05, + "loss": 3.8687, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7381890808411894e-05, + "loss": 3.8577, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737350486090137e-05, + "loss": 3.8779, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736511891339085e-05, + "loss": 3.8751, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7356732965880333e-05, + "loss": 3.8649, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7348347018369813e-05, + "loss": 3.8774, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7339961070859293e-05, + "loss": 3.8931, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7331575123348773e-05, + "loss": 3.8825, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732318917583825e-05, + "loss": 3.8806, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731480322832773e-05, + "loss": 3.8722, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730641728081721e-05, + "loss": 3.878, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.729803133330669e-05, + "loss": 3.8755, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7289661764599902e-05, + "loss": 3.8739, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7281275817089382e-05, + "loss": 3.8783, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7272889869578862e-05, + "loss": 3.8733, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7264503922068342e-05, + "loss": 3.8703, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7256117974557822e-05, + "loss": 3.8687, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7247748405851035e-05, + "loss": 3.8766, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7239362458340514e-05, + "loss": 3.8767, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7230992889633724e-05, + "loss": 3.8823, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7222606942123204e-05, + "loss": 3.8721, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7214237373416416e-05, + "loss": 3.8765, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7205851425905896e-05, + "loss": 3.8789, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7197465478395376e-05, + "loss": 3.8626, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7189079530884856e-05, + "loss": 3.8667, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7180693583374336e-05, + "loss": 3.866, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7172307635863816e-05, + "loss": 3.8663, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7163921688353296e-05, + "loss": 3.8779, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7155535740842776e-05, + "loss": 3.8742, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7147149793332256e-05, + "loss": 3.8732, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7138763845821736e-05, + "loss": 3.8753, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7130377898311216e-05, + "loss": 3.8701, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7121991950800696e-05, + "loss": 3.8812, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7113622382093905e-05, + "loss": 3.8816, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7105236434583385e-05, + "loss": 3.8482, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7096850487072865e-05, + "loss": 3.8843, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7088464539562344e-05, + "loss": 3.8662, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7080078592051828e-05, + "loss": 3.8804, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7071709023345037e-05, + "loss": 3.8733, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7063323075834517e-05, + "loss": 3.8615, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7054937128323997e-05, + "loss": 3.87, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7046567559617206e-05, + "loss": 3.8608, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.703818161210669e-05, + "loss": 3.8833, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.702979566459617e-05, + "loss": 3.8624, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702140971708565e-05, + "loss": 3.8798, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.701302376957513e-05, + "loss": 3.8745, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700463782206461e-05, + "loss": 3.8619, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6996251874554086e-05, + "loss": 3.8797, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6987865927043566e-05, + "loss": 3.8599, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6979479979533046e-05, + "loss": 3.857, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697111041082626e-05, + "loss": 3.8623, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6962724463315738e-05, + "loss": 3.8816, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6954338515805218e-05, + "loss": 3.8617, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6945952568294698e-05, + "loss": 3.8819, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6937566620784178e-05, + "loss": 3.8539, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6929180673273658e-05, + "loss": 3.8641, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692081110456687e-05, + "loss": 3.8717, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691242515705635e-05, + "loss": 3.8718, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690403920954583e-05, + "loss": 3.8763, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689565326203531e-05, + "loss": 3.8755, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.688726731452479e-05, + "loss": 3.8801, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6878881367014267e-05, + "loss": 3.8655, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6870511798307483e-05, + "loss": 3.8739, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6862125850796963e-05, + "loss": 3.8638, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6853739903286443e-05, + "loss": 3.8691, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684535395577592e-05, + "loss": 3.87, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.68369680082654e-05, + "loss": 3.8619, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.682858206075488e-05, + "loss": 3.8778, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682019611324436e-05, + "loss": 3.8841, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6811810165733842e-05, + "loss": 3.8703, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680344059702705e-05, + "loss": 3.8511, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679505464951653e-05, + "loss": 3.8737, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678666870200601e-05, + "loss": 3.8722, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.677829913329922e-05, + "loss": 3.8803, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6769913185788704e-05, + "loss": 3.8601, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6761527238278184e-05, + "loss": 3.8773, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6753141290767664e-05, + "loss": 3.8675, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6744755343257144e-05, + "loss": 3.8641, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6736369395746624e-05, + "loss": 3.8645, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.67279834482361e-05, + "loss": 3.874, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6719613879529313e-05, + "loss": 3.8749, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6711227932018793e-05, + "loss": 3.878, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6702841984508273e-05, + "loss": 3.861, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6694472415801485e-05, + "loss": 3.8697, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6686086468290965e-05, + "loss": 3.8632, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6677700520780445e-05, + "loss": 3.8723, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.666931457326992e-05, + "loss": 3.8729, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6660928625759405e-05, + "loss": 3.8678, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6652542678248885e-05, + "loss": 3.8698, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6644156730738365e-05, + "loss": 3.8573, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6635770783227845e-05, + "loss": 3.8709, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6627401214521054e-05, + "loss": 3.855, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6619015267010534e-05, + "loss": 3.8681, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6610629319500014e-05, + "loss": 3.865, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6602243371989497e-05, + "loss": 3.8725, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6593857424478977e-05, + "loss": 3.8603, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6585471476968454e-05, + "loss": 3.8634, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6577085529457934e-05, + "loss": 3.8622, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6568715960751146e-05, + "loss": 3.878, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6560330013240626e-05, + "loss": 3.8708, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6551944065730106e-05, + "loss": 3.8698, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6543558118219586e-05, + "loss": 3.8729, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.65351885495128e-05, + "loss": 3.8799, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652680260200228e-05, + "loss": 3.8681, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6518416654491755e-05, + "loss": 3.8681, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6510030706981235e-05, + "loss": 3.8658, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650166113827445e-05, + "loss": 3.8751, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6493275190763927e-05, + "loss": 3.8682, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6484889243253407e-05, + "loss": 3.8663, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6476503295742887e-05, + "loss": 3.867, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6468117348232367e-05, + "loss": 3.8757, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6459764158329312e-05, + "loss": 3.8605, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6451378210818792e-05, + "loss": 3.86, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6442992263308272e-05, + "loss": 3.8553, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6434606315797752e-05, + "loss": 3.862, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642622036828723e-05, + "loss": 3.8763, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.641783442077671e-05, + "loss": 3.8739, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.640946485206992e-05, + "loss": 3.8863, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.64010789045594e-05, + "loss": 3.8577, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639269295704888e-05, + "loss": 3.8764, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638430700953836e-05, + "loss": 3.8699, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637592106202784e-05, + "loss": 3.8739, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.636753511451732e-05, + "loss": 3.8657, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.635916554581053e-05, + "loss": 3.8642, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6350779598300013e-05, + "loss": 3.8673, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6342393650789493e-05, + "loss": 3.8834, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6334007703278973e-05, + "loss": 3.8572, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6325621755768453e-05, + "loss": 3.8749, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.631723580825793e-05, + "loss": 3.876, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.630884986074741e-05, + "loss": 3.8673, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630046391323689e-05, + "loss": 3.8665, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629207796572637e-05, + "loss": 3.8732, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6283708397019582e-05, + "loss": 3.8705, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6275322449509062e-05, + "loss": 3.8712, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6266952880802274e-05, + "loss": 3.8726, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 4.002951622009277, + "eval_runtime": 293.4599, + "eval_samples_per_second": 1300.318, + "eval_steps_per_second": 40.636, + "step": 2060640 + }, + { + "epoch": 2.0, + "learning_rate": 1.6258566933291754e-05, + "loss": 3.8604, + "step": 2060800 + }, + { + "epoch": 2.0, + "learning_rate": 1.625018098578123e-05, + "loss": 3.8631, + "step": 2061312 + }, + { + "epoch": 2.0, + "learning_rate": 1.6241795038270714e-05, + "loss": 3.8697, + "step": 2061824 + }, + { + "epoch": 2.0, + "learning_rate": 1.6233409090760194e-05, + "loss": 3.8735, + "step": 2062336 + }, + { + "epoch": 2.0, + "learning_rate": 1.6225023143249674e-05, + "loss": 3.883, + "step": 2062848 + }, + { + "epoch": 2.0, + "learning_rate": 1.6216637195739154e-05, + "loss": 3.8673, + "step": 2063360 + }, + { + "epoch": 2.0, + "learning_rate": 1.6208251248228634e-05, + "loss": 3.8728, + "step": 2063872 + }, + { + "epoch": 2.0, + "learning_rate": 1.619986530071811e-05, + "loss": 3.8674, + "step": 2064384 + }, + { + "epoch": 2.0, + "learning_rate": 1.6191495732011323e-05, + "loss": 3.8652, + "step": 2064896 + }, + { + "epoch": 2.0, + "learning_rate": 1.6183109784500807e-05, + "loss": 3.8654, + "step": 2065408 + }, + { + "epoch": 2.0, + "learning_rate": 1.6174723836990287e-05, + "loss": 3.8738, + "step": 2065920 + }, + { + "epoch": 2.0, + "learning_rate": 1.6166337889479763e-05, + "loss": 3.8723, + "step": 2066432 + }, + { + "epoch": 2.0, + "learning_rate": 1.6157984699576705e-05, + "loss": 3.8804, + "step": 2066944 + }, + { + "epoch": 2.0, + "learning_rate": 1.6149598752066185e-05, + "loss": 3.8591, + "step": 2067456 + }, + { + "epoch": 2.0, + "learning_rate": 1.6141212804555668e-05, + "loss": 3.8647, + "step": 2067968 + }, + { + "epoch": 2.0, + "learning_rate": 1.6132826857045148e-05, + "loss": 3.8506, + "step": 2068480 + }, + { + "epoch": 2.0, + "learning_rate": 1.6124440909534628e-05, + "loss": 3.8719, + "step": 2068992 + }, + { + "epoch": 2.0, + "learning_rate": 1.6116054962024108e-05, + "loss": 3.8698, + "step": 2069504 + }, + { + "epoch": 2.0, + "learning_rate": 1.6107669014513584e-05, + "loss": 3.8586, + "step": 2070016 + }, + { + "epoch": 2.0, + "learning_rate": 1.6099283067003064e-05, + "loss": 3.8747, + "step": 2070528 + }, + { + "epoch": 2.0, + "learning_rate": 1.6090897119492544e-05, + "loss": 3.8898, + "step": 2071040 + }, + { + "epoch": 2.0, + "learning_rate": 1.6082511171982024e-05, + "loss": 3.8747, + "step": 2071552 + }, + { + "epoch": 2.0, + "learning_rate": 1.6074125224471508e-05, + "loss": 3.8737, + "step": 2072064 + }, + { + "epoch": 2.0, + "learning_rate": 1.6065739276960988e-05, + "loss": 3.8694, + "step": 2072576 + }, + { + "epoch": 2.0, + "learning_rate": 1.6057369708254197e-05, + "loss": 3.8739, + "step": 2073088 + }, + { + "epoch": 2.0, + "learning_rate": 1.604900013954741e-05, + "loss": 3.8724, + "step": 2073600 + }, + { + "epoch": 2.0, + "learning_rate": 1.6040614192036886e-05, + "loss": 3.8697, + "step": 2074112 + }, + { + "epoch": 2.0, + "learning_rate": 1.603222824452637e-05, + "loss": 3.8705, + "step": 2074624 + }, + { + "epoch": 2.0, + "learning_rate": 1.602384229701585e-05, + "loss": 3.8694, + "step": 2075136 + }, + { + "epoch": 2.0, + "learning_rate": 1.601545634950533e-05, + "loss": 3.8648, + "step": 2075648 + }, + { + "epoch": 2.01, + "learning_rate": 1.600707040199481e-05, + "loss": 3.8682, + "step": 2076160 + }, + { + "epoch": 2.01, + "learning_rate": 1.5998700833288018e-05, + "loss": 3.8676, + "step": 2076672 + }, + { + "epoch": 2.01, + "learning_rate": 1.5990314885777498e-05, + "loss": 3.8712, + "step": 2077184 + }, + { + "epoch": 2.01, + "learning_rate": 1.5981928938266978e-05, + "loss": 3.8815, + "step": 2077696 + }, + { + "epoch": 2.01, + "learning_rate": 1.597354299075646e-05, + "loss": 3.8681, + "step": 2078208 + }, + { + "epoch": 2.01, + "learning_rate": 1.596517342204967e-05, + "loss": 3.87, + "step": 2078720 + }, + { + "epoch": 2.01, + "learning_rate": 1.595678747453915e-05, + "loss": 3.8748, + "step": 2079232 + }, + { + "epoch": 2.01, + "learning_rate": 1.594840152702863e-05, + "loss": 3.8564, + "step": 2079744 + }, + { + "epoch": 2.01, + "learning_rate": 1.594001557951811e-05, + "loss": 3.8627, + "step": 2080256 + }, + { + "epoch": 2.01, + "learning_rate": 1.593162963200759e-05, + "loss": 3.8597, + "step": 2080768 + }, + { + "epoch": 2.01, + "learning_rate": 1.592324368449707e-05, + "loss": 3.8644, + "step": 2081280 + }, + { + "epoch": 2.01, + "learning_rate": 1.591485773698655e-05, + "loss": 3.8677, + "step": 2081792 + }, + { + "epoch": 2.01, + "learning_rate": 1.590647178947603e-05, + "loss": 3.8706, + "step": 2082304 + }, + { + "epoch": 2.01, + "learning_rate": 1.589808584196551e-05, + "loss": 3.8708, + "step": 2082816 + }, + { + "epoch": 2.01, + "learning_rate": 1.588969989445499e-05, + "loss": 3.8696, + "step": 2083328 + }, + { + "epoch": 2.01, + "learning_rate": 1.588131394694447e-05, + "loss": 3.8702, + "step": 2083840 + }, + { + "epoch": 2.01, + "learning_rate": 1.5872927999433947e-05, + "loss": 3.8699, + "step": 2084352 + }, + { + "epoch": 2.01, + "learning_rate": 1.5864558430727162e-05, + "loss": 3.8783, + "step": 2084864 + }, + { + "epoch": 2.01, + "learning_rate": 1.585618886202037e-05, + "loss": 3.8469, + "step": 2085376 + }, + { + "epoch": 2.01, + "learning_rate": 1.584780291450985e-05, + "loss": 3.8796, + "step": 2085888 + }, + { + "epoch": 2.01, + "learning_rate": 1.583941696699933e-05, + "loss": 3.8622, + "step": 2086400 + }, + { + "epoch": 2.01, + "learning_rate": 1.583103101948881e-05, + "loss": 3.8726, + "step": 2086912 + }, + { + "epoch": 2.01, + "learning_rate": 1.5822661450782024e-05, + "loss": 3.8648, + "step": 2087424 + }, + { + "epoch": 2.01, + "learning_rate": 1.5814275503271504e-05, + "loss": 3.8622, + "step": 2087936 + }, + { + "epoch": 2.01, + "learning_rate": 1.5805889555760984e-05, + "loss": 3.8598, + "step": 2088448 + }, + { + "epoch": 2.01, + "learning_rate": 1.5797503608250464e-05, + "loss": 3.858, + "step": 2088960 + }, + { + "epoch": 2.01, + "learning_rate": 1.5789117660739944e-05, + "loss": 3.8834, + "step": 2089472 + }, + { + "epoch": 2.01, + "learning_rate": 1.5780748092033153e-05, + "loss": 3.8546, + "step": 2089984 + }, + { + "epoch": 2.01, + "learning_rate": 1.5772378523326365e-05, + "loss": 3.8766, + "step": 2090496 + }, + { + "epoch": 2.01, + "learning_rate": 1.5763992575815845e-05, + "loss": 3.8666, + "step": 2091008 + }, + { + "epoch": 2.01, + "learning_rate": 1.5755606628305325e-05, + "loss": 3.8571, + "step": 2091520 + }, + { + "epoch": 2.01, + "learning_rate": 1.5747220680794805e-05, + "loss": 3.8731, + "step": 2092032 + }, + { + "epoch": 2.01, + "learning_rate": 1.5738834733284285e-05, + "loss": 3.8594, + "step": 2092544 + }, + { + "epoch": 2.01, + "learning_rate": 1.5730448785773765e-05, + "loss": 3.8488, + "step": 2093056 + }, + { + "epoch": 2.01, + "learning_rate": 1.5722062838263245e-05, + "loss": 3.8578, + "step": 2093568 + }, + { + "epoch": 2.01, + "learning_rate": 1.5713676890752725e-05, + "loss": 3.8759, + "step": 2094080 + }, + { + "epoch": 2.01, + "learning_rate": 1.5705290943242205e-05, + "loss": 3.858, + "step": 2094592 + }, + { + "epoch": 2.01, + "learning_rate": 1.5696904995731685e-05, + "loss": 3.8752, + "step": 2095104 + }, + { + "epoch": 2.01, + "learning_rate": 1.5688519048221165e-05, + "loss": 3.8476, + "step": 2095616 + }, + { + "epoch": 2.01, + "learning_rate": 1.5680133100710645e-05, + "loss": 3.8607, + "step": 2096128 + }, + { + "epoch": 2.01, + "learning_rate": 1.5671763532003854e-05, + "loss": 3.8667, + "step": 2096640 + }, + { + "epoch": 2.01, + "learning_rate": 1.5663377584493337e-05, + "loss": 3.8712, + "step": 2097152 + }, + { + "epoch": 2.01, + "learning_rate": 1.5654991636982817e-05, + "loss": 3.8687, + "step": 2097664 + }, + { + "epoch": 2.01, + "learning_rate": 1.5646605689472297e-05, + "loss": 3.8697, + "step": 2098176 + }, + { + "epoch": 2.01, + "learning_rate": 1.5638219741961777e-05, + "loss": 3.8755, + "step": 2098688 + }, + { + "epoch": 2.01, + "learning_rate": 1.5629833794451254e-05, + "loss": 3.8633, + "step": 2099200 + }, + { + "epoch": 2.01, + "learning_rate": 1.5621447846940734e-05, + "loss": 3.8658, + "step": 2099712 + }, + { + "epoch": 2.01, + "learning_rate": 1.5613061899430214e-05, + "loss": 3.8595, + "step": 2100224 + }, + { + "epoch": 2.01, + "learning_rate": 1.5604675951919694e-05, + "loss": 3.8686, + "step": 2100736 + }, + { + "epoch": 2.01, + "learning_rate": 1.559632276201664e-05, + "loss": 3.8608, + "step": 2101248 + }, + { + "epoch": 2.01, + "learning_rate": 1.558793681450612e-05, + "loss": 3.8594, + "step": 2101760 + }, + { + "epoch": 2.01, + "learning_rate": 1.5579567245799328e-05, + "loss": 3.8725, + "step": 2102272 + }, + { + "epoch": 2.01, + "learning_rate": 1.5571181298288808e-05, + "loss": 3.877, + "step": 2102784 + }, + { + "epoch": 2.01, + "learning_rate": 1.556279535077829e-05, + "loss": 3.8665, + "step": 2103296 + }, + { + "epoch": 2.01, + "learning_rate": 1.555440940326777e-05, + "loss": 3.845, + "step": 2103808 + }, + { + "epoch": 2.01, + "learning_rate": 1.554602345575725e-05, + "loss": 3.8679, + "step": 2104320 + }, + { + "epoch": 2.01, + "learning_rate": 1.5537637508246727e-05, + "loss": 3.8686, + "step": 2104832 + }, + { + "epoch": 2.01, + "learning_rate": 1.5529251560736207e-05, + "loss": 3.8758, + "step": 2105344 + }, + { + "epoch": 2.01, + "learning_rate": 1.5520865613225687e-05, + "loss": 3.8577, + "step": 2105856 + }, + { + "epoch": 2.01, + "learning_rate": 1.55124960445189e-05, + "loss": 3.8692, + "step": 2106368 + }, + { + "epoch": 2.02, + "learning_rate": 1.550411009700838e-05, + "loss": 3.8693, + "step": 2106880 + }, + { + "epoch": 2.02, + "learning_rate": 1.549572414949786e-05, + "loss": 3.8573, + "step": 2107392 + }, + { + "epoch": 2.02, + "learning_rate": 1.548733820198734e-05, + "loss": 3.8591, + "step": 2107904 + }, + { + "epoch": 2.02, + "learning_rate": 1.547895225447682e-05, + "loss": 3.8725, + "step": 2108416 + }, + { + "epoch": 2.02, + "learning_rate": 1.54705663069663e-05, + "loss": 3.8693, + "step": 2108928 + }, + { + "epoch": 2.02, + "learning_rate": 1.546219673825951e-05, + "loss": 3.8749, + "step": 2109440 + }, + { + "epoch": 2.02, + "learning_rate": 1.5453810790748992e-05, + "loss": 3.8587, + "step": 2109952 + }, + { + "epoch": 2.02, + "learning_rate": 1.54454412220422e-05, + "loss": 3.8625, + "step": 2110464 + }, + { + "epoch": 2.02, + "learning_rate": 1.543705527453168e-05, + "loss": 3.8591, + "step": 2110976 + }, + { + "epoch": 2.02, + "learning_rate": 1.542866932702116e-05, + "loss": 3.8689, + "step": 2111488 + }, + { + "epoch": 2.02, + "learning_rate": 1.542028337951064e-05, + "loss": 3.8699, + "step": 2112000 + }, + { + "epoch": 2.02, + "learning_rate": 1.541189743200012e-05, + "loss": 3.8612, + "step": 2112512 + }, + { + "epoch": 2.02, + "learning_rate": 1.54035114844896e-05, + "loss": 3.8658, + "step": 2113024 + }, + { + "epoch": 2.02, + "learning_rate": 1.539512553697908e-05, + "loss": 3.8557, + "step": 2113536 + }, + { + "epoch": 2.02, + "learning_rate": 1.538673958946856e-05, + "loss": 3.8637, + "step": 2114048 + }, + { + "epoch": 2.02, + "learning_rate": 1.537835364195804e-05, + "loss": 3.8484, + "step": 2114560 + }, + { + "epoch": 2.02, + "learning_rate": 1.5369984073251253e-05, + "loss": 3.8653, + "step": 2115072 + }, + { + "epoch": 2.02, + "learning_rate": 1.536159812574073e-05, + "loss": 3.8594, + "step": 2115584 + }, + { + "epoch": 2.02, + "learning_rate": 1.535321217823021e-05, + "loss": 3.8675, + "step": 2116096 + }, + { + "epoch": 2.02, + "learning_rate": 1.5344826230719693e-05, + "loss": 3.8592, + "step": 2116608 + }, + { + "epoch": 2.02, + "learning_rate": 1.5336456662012906e-05, + "loss": 3.8661, + "step": 2117120 + }, + { + "epoch": 2.02, + "learning_rate": 1.5328070714502382e-05, + "loss": 3.8534, + "step": 2117632 + }, + { + "epoch": 2.02, + "learning_rate": 1.5319684766991862e-05, + "loss": 3.8737, + "step": 2118144 + }, + { + "epoch": 2.02, + "learning_rate": 1.5311298819481342e-05, + "loss": 3.8639, + "step": 2118656 + }, + { + "epoch": 2.02, + "learning_rate": 1.5302912871970822e-05, + "loss": 3.8621, + "step": 2119168 + }, + { + "epoch": 2.02, + "learning_rate": 1.5294543303264034e-05, + "loss": 3.8659, + "step": 2119680 + }, + { + "epoch": 2.02, + "learning_rate": 1.5286157355753514e-05, + "loss": 3.8809, + "step": 2120192 + }, + { + "epoch": 2.02, + "learning_rate": 1.5277771408242994e-05, + "loss": 3.8623, + "step": 2120704 + }, + { + "epoch": 2.02, + "learning_rate": 1.5269385460732474e-05, + "loss": 3.8614, + "step": 2121216 + }, + { + "epoch": 2.02, + "learning_rate": 1.5260999513221954e-05, + "loss": 3.8656, + "step": 2121728 + }, + { + "epoch": 2.02, + "learning_rate": 1.5252629944515165e-05, + "loss": 3.8699, + "step": 2122240 + }, + { + "epoch": 2.02, + "learning_rate": 1.5244243997004645e-05, + "loss": 3.863, + "step": 2122752 + }, + { + "epoch": 2.02, + "learning_rate": 1.5235858049494125e-05, + "loss": 3.866, + "step": 2123264 + }, + { + "epoch": 2.02, + "learning_rate": 1.5227472101983607e-05, + "loss": 3.8618, + "step": 2123776 + }, + { + "epoch": 2.02, + "learning_rate": 1.5219086154473087e-05, + "loss": 3.8691, + "step": 2124288 + }, + { + "epoch": 2.02, + "learning_rate": 1.5210716585766296e-05, + "loss": 3.853, + "step": 2124800 + }, + { + "epoch": 2.02, + "learning_rate": 1.5202330638255777e-05, + "loss": 3.8573, + "step": 2125312 + }, + { + "epoch": 2.02, + "learning_rate": 1.5193944690745257e-05, + "loss": 3.851, + "step": 2125824 + }, + { + "epoch": 2.02, + "learning_rate": 1.5185558743234734e-05, + "loss": 3.8612, + "step": 2126336 + }, + { + "epoch": 2.02, + "learning_rate": 1.5177172795724216e-05, + "loss": 3.8695, + "step": 2126848 + }, + { + "epoch": 2.02, + "learning_rate": 1.5168786848213695e-05, + "loss": 3.8682, + "step": 2127360 + }, + { + "epoch": 2.02, + "learning_rate": 1.5160417279506908e-05, + "loss": 3.8788, + "step": 2127872 + }, + { + "epoch": 2.02, + "learning_rate": 1.5152031331996386e-05, + "loss": 3.8565, + "step": 2128384 + }, + { + "epoch": 2.02, + "learning_rate": 1.5143645384485866e-05, + "loss": 3.8669, + "step": 2128896 + }, + { + "epoch": 2.02, + "learning_rate": 1.5135259436975346e-05, + "loss": 3.8705, + "step": 2129408 + }, + { + "epoch": 2.02, + "learning_rate": 1.5126873489464826e-05, + "loss": 3.8663, + "step": 2129920 + }, + { + "epoch": 2.02, + "learning_rate": 1.5118503920758037e-05, + "loss": 3.8625, + "step": 2130432 + }, + { + "epoch": 2.02, + "learning_rate": 1.5110117973247517e-05, + "loss": 3.8568, + "step": 2130944 + }, + { + "epoch": 2.02, + "learning_rate": 1.5101732025736997e-05, + "loss": 3.866, + "step": 2131456 + }, + { + "epoch": 2.02, + "learning_rate": 1.5093346078226478e-05, + "loss": 3.8718, + "step": 2131968 + }, + { + "epoch": 2.02, + "learning_rate": 1.5084960130715958e-05, + "loss": 3.8583, + "step": 2132480 + }, + { + "epoch": 2.02, + "learning_rate": 1.5076574183205438e-05, + "loss": 3.8695, + "step": 2132992 + }, + { + "epoch": 2.02, + "learning_rate": 1.5068204614498649e-05, + "loss": 3.8723, + "step": 2133504 + }, + { + "epoch": 2.02, + "learning_rate": 1.5059818666988129e-05, + "loss": 3.8658, + "step": 2134016 + }, + { + "epoch": 2.02, + "learning_rate": 1.5051432719477609e-05, + "loss": 3.8612, + "step": 2134528 + }, + { + "epoch": 2.02, + "learning_rate": 1.5043046771967089e-05, + "loss": 3.867, + "step": 2135040 + }, + { + "epoch": 2.02, + "learning_rate": 1.5034660824456567e-05, + "loss": 3.8645, + "step": 2135552 + }, + { + "epoch": 2.02, + "learning_rate": 1.502629125574978e-05, + "loss": 3.8638, + "step": 2136064 + }, + { + "epoch": 2.02, + "learning_rate": 1.501792168704299e-05, + "loss": 3.8738, + "step": 2136576 + }, + { + "epoch": 2.03, + "eval_loss": 4.001996994018555, + "eval_runtime": 292.8877, + "eval_samples_per_second": 1302.858, + "eval_steps_per_second": 40.715, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.500953573953247e-05, + "loss": 3.8638, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.500114979202195e-05, + "loss": 3.854, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4992763844511432e-05, + "loss": 3.8668, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4984377897000912e-05, + "loss": 3.8706, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4975991949490389e-05, + "loss": 3.8738, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.496760600197987e-05, + "loss": 3.8669, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.495922005446935e-05, + "loss": 3.8674, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.495083410695883e-05, + "loss": 3.8639, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.494244815944831e-05, + "loss": 3.8598, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4934062211937792e-05, + "loss": 3.8643, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925676264427272e-05, + "loss": 3.871, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4917290316916748e-05, + "loss": 3.8656, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4908920748209963e-05, + "loss": 3.8766, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900534800699442e-05, + "loss": 3.8522, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4892165231992653e-05, + "loss": 3.8603, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883779284482133e-05, + "loss": 3.8498, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875393336971613e-05, + "loss": 3.8678, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4867007389461093e-05, + "loss": 3.8645, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4858621441950571e-05, + "loss": 3.8612, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4850235494440051e-05, + "loss": 3.8649, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4841849546929531e-05, + "loss": 3.8855, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4833463599419011e-05, + "loss": 3.8732, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4825077651908493e-05, + "loss": 3.8683, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816708083201702e-05, + "loss": 3.8624, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808322135691182e-05, + "loss": 3.875, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4799936188180664e-05, + "loss": 3.8658, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4791550240670144e-05, + "loss": 3.8612, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4783164293159624e-05, + "loss": 3.8709, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4774778345649102e-05, + "loss": 3.8585, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4766392398138582e-05, + "loss": 3.863, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4758006450628062e-05, + "loss": 3.8655, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749636881921274e-05, + "loss": 3.8623, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4741267313214485e-05, + "loss": 3.8685, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4732881365703965e-05, + "loss": 3.8777, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4724495418193447e-05, + "loss": 3.8626, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4716125849486656e-05, + "loss": 3.8673, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4707739901976136e-05, + "loss": 3.8714, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4699353954465617e-05, + "loss": 3.8534, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690968006955097e-05, + "loss": 3.8562, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4682582059444574e-05, + "loss": 3.8585, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4674196111934055e-05, + "loss": 3.8571, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4665810164423535e-05, + "loss": 3.8611, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657424216913015e-05, + "loss": 3.8672, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4649038269402495e-05, + "loss": 3.8655, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640652321891977e-05, + "loss": 3.8662, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632266374381457e-05, + "loss": 3.8652, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4623880426870933e-05, + "loss": 3.867, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4615494479360413e-05, + "loss": 3.8724, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4607108531849895e-05, + "loss": 3.8488, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598738963143104e-05, + "loss": 3.8736, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590353015632586e-05, + "loss": 3.8585, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4581983446925798e-05, + "loss": 3.8674, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4573597499415278e-05, + "loss": 3.8658, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4565211551904757e-05, + "loss": 3.8569, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4556825604394236e-05, + "loss": 3.856, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4548439656883716e-05, + "loss": 3.8506, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4540053709373196e-05, + "loss": 3.8824, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4531667761862678e-05, + "loss": 3.8528, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4523281814352158e-05, + "loss": 3.8694, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4514895866841638e-05, + "loss": 3.8613, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4506509919331116e-05, + "loss": 3.8564, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4498123971820596e-05, + "loss": 3.8656, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4489754403113809e-05, + "loss": 3.8591, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.448138483440702e-05, + "loss": 3.8486, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.44729988868965e-05, + "loss": 3.8469, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446461293938598e-05, + "loss": 3.8766, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.445622699187546e-05, + "loss": 3.8557, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4447841044364938e-05, + "loss": 3.8661, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4439455096854418e-05, + "loss": 3.8477, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4431069149343897e-05, + "loss": 3.8583, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4422683201833379e-05, + "loss": 3.8573, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4414297254322859e-05, + "loss": 3.869, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4405911306812339e-05, + "loss": 3.8645, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.439754173810555e-05, + "loss": 3.867, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.438915579059503e-05, + "loss": 3.872, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.438076984308451e-05, + "loss": 3.8587, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.437238389557399e-05, + "loss": 3.8614, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4363997948063468e-05, + "loss": 3.8556, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355612000552948e-05, + "loss": 3.8619, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.434724243184616e-05, + "loss": 3.8621, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4338856484335642e-05, + "loss": 3.8521, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4330470536825119e-05, + "loss": 3.8699, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4322084589314599e-05, + "loss": 3.8728, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313715020607813e-05, + "loss": 3.8623, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4305329073097293e-05, + "loss": 3.839, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4296943125586771e-05, + "loss": 3.8623, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4288557178076251e-05, + "loss": 3.8654, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4280171230565731e-05, + "loss": 3.8718, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.427178528305521e-05, + "loss": 3.8603, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263415714348422e-05, + "loss": 3.8625, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4255029766837902e-05, + "loss": 3.8637, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246643819327382e-05, + "loss": 3.8536, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4238257871816863e-05, + "loss": 3.8577, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4229871924306343e-05, + "loss": 3.868, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4221502355599552e-05, + "loss": 3.8612, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4213132786892766e-05, + "loss": 3.8732, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204746839382243e-05, + "loss": 3.8599, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4196360891871725e-05, + "loss": 3.854, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4187974944361205e-05, + "loss": 3.8557, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4179605375654414e-05, + "loss": 3.8656, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4171219428143895e-05, + "loss": 3.8655, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4162833480633375e-05, + "loss": 3.8566, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4154447533122855e-05, + "loss": 3.8584, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4146061585612335e-05, + "loss": 3.8506, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4137675638101817e-05, + "loss": 3.8646, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129289690591297e-05, + "loss": 3.8413, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4120903743080773e-05, + "loss": 3.8582, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4112534174373988e-05, + "loss": 3.8633, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4104148226863468e-05, + "loss": 3.863, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095762279352947e-05, + "loss": 3.8504, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087392710646158e-05, + "loss": 3.8628, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4079006763135638e-05, + "loss": 3.8508, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4070620815625118e-05, + "loss": 3.868, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4062234868114596e-05, + "loss": 3.8607, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4053848920604076e-05, + "loss": 3.861, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045462973093556e-05, + "loss": 3.8598, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4037077025583036e-05, + "loss": 3.8755, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4028691078072518e-05, + "loss": 3.8576, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020321509365727e-05, + "loss": 3.8575, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4011935561855207e-05, + "loss": 3.8642, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4003549614344689e-05, + "loss": 3.861, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3995163666834169e-05, + "loss": 3.8588, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3986777719323649e-05, + "loss": 3.8626, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3978391771813127e-05, + "loss": 3.8582, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3970005824302607e-05, + "loss": 3.8667, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.396163625559582e-05, + "loss": 3.8478, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.39532503080853e-05, + "loss": 3.8579, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3944864360574777e-05, + "loss": 3.8491, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.393649479186799e-05, + "loss": 3.8588, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3928108844357472e-05, + "loss": 3.856, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3919722896846952e-05, + "loss": 3.8663, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3911336949336428e-05, + "loss": 3.8738, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.390295100182591e-05, + "loss": 3.8543, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.389456505431539e-05, + "loss": 3.8636, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.388617910680487e-05, + "loss": 3.863, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.387779315929435e-05, + "loss": 3.8635, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.386940721178383e-05, + "loss": 3.8601, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3861021264273308e-05, + "loss": 3.8523, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.385265169556652e-05, + "loss": 3.8658, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3844265748056002e-05, + "loss": 3.8695, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3835879800545482e-05, + "loss": 3.8548, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3827493853034959e-05, + "loss": 3.8643, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.381910790552444e-05, + "loss": 3.8698, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.381072195801392e-05, + "loss": 3.8576, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.38023360105034e-05, + "loss": 3.8584, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.379395006299288e-05, + "loss": 3.8659, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.378558049428609e-05, + "loss": 3.8582, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.377719454677557e-05, + "loss": 3.8601, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.376880859926505e-05, + "loss": 3.8718, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 4.000596523284912, + "eval_runtime": 296.2429, + "eval_samples_per_second": 1288.102, + "eval_steps_per_second": 40.254, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.376042265175453e-05, + "loss": 3.8544, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3752053083047741e-05, + "loss": 3.848, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3743683514340954e-05, + "loss": 3.8617, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3735297566830432e-05, + "loss": 3.8694, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3726911619319912e-05, + "loss": 3.8654, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3718525671809392e-05, + "loss": 3.8649, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3710139724298874e-05, + "loss": 3.8619, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3701770155592083e-05, + "loss": 3.8608, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3693384208081565e-05, + "loss": 3.8555, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3684998260571045e-05, + "loss": 3.8601, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3676612313060524e-05, + "loss": 3.8635, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3668226365550004e-05, + "loss": 3.8621, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3659856796843215e-05, + "loss": 3.872, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3651470849332695e-05, + "loss": 3.8483, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3643084901822175e-05, + "loss": 3.8536, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3634698954311657e-05, + "loss": 3.8426, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3626313006801137e-05, + "loss": 3.8649, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3617943438094346e-05, + "loss": 3.8621, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3609557490583827e-05, + "loss": 3.8574, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3601171543073307e-05, + "loss": 3.8616, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3592785595562787e-05, + "loss": 3.8801, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3584399648052266e-05, + "loss": 3.8669, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3576030079345478e-05, + "loss": 3.8629, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3567644131834958e-05, + "loss": 3.8603, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3559258184324436e-05, + "loss": 3.876, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3550872236813916e-05, + "loss": 3.8581, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3542486289303396e-05, + "loss": 3.8599, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3534100341792876e-05, + "loss": 3.8678, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3525714394282358e-05, + "loss": 3.8557, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3517328446771838e-05, + "loss": 3.8594, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3508975256868781e-05, + "loss": 3.8618, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3500589309358261e-05, + "loss": 3.8552, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3492203361847738e-05, + "loss": 3.8652, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.348381741433722e-05, + "loss": 3.8722, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.34754314668267e-05, + "loss": 3.8594, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.346706189811991e-05, + "loss": 3.8628, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.345867595060939e-05, + "loss": 3.8729, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3450306381902602e-05, + "loss": 3.8422, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3441920434392082e-05, + "loss": 3.856, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.343353448688156e-05, + "loss": 3.8559, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.342514853937104e-05, + "loss": 3.8488, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.341676259186052e-05, + "loss": 3.8601, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.340837664435e-05, + "loss": 3.866, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3400007075643211e-05, + "loss": 3.8604, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3391621128132691e-05, + "loss": 3.861, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3383235180622173e-05, + "loss": 3.8593, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3374849233111653e-05, + "loss": 3.859, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3366463285601133e-05, + "loss": 3.8689, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3358077338090613e-05, + "loss": 3.8463, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3349707769383824e-05, + "loss": 3.8669, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3341321821873304e-05, + "loss": 3.8593, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3332935874362784e-05, + "loss": 3.8619, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3324549926852265e-05, + "loss": 3.8611, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3316163979341742e-05, + "loss": 3.8483, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3307778031831222e-05, + "loss": 3.8571, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3299392084320703e-05, + "loss": 3.8446, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3291006136810183e-05, + "loss": 3.8787, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282636568103392e-05, + "loss": 3.8475, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274250620592874e-05, + "loss": 3.8702, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3265864673082354e-05, + "loss": 3.8522, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257478725571834e-05, + "loss": 3.8512, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3249109156865045e-05, + "loss": 3.8586, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240723209354525e-05, + "loss": 3.8577, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3232337261844005e-05, + "loss": 3.8488, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3223951314333485e-05, + "loss": 3.84, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3215565366822966e-05, + "loss": 3.8693, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3207179419312446e-05, + "loss": 3.8573, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3198793471801923e-05, + "loss": 3.8596, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3190407524291404e-05, + "loss": 3.8446, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3182037955584617e-05, + "loss": 3.849, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3173652008074095e-05, + "loss": 3.8568, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3165266060563575e-05, + "loss": 3.8637, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3156896491856788e-05, + "loss": 3.8596, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3148510544346268e-05, + "loss": 3.8627, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3140124596835746e-05, + "loss": 3.8648, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3131738649325226e-05, + "loss": 3.8541, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3123352701814706e-05, + "loss": 3.8574, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.311498313310792e-05, + "loss": 3.8529, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3106613564401129e-05, + "loss": 3.8601, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3098227616890609e-05, + "loss": 3.8594, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.308984166938009e-05, + "loss": 3.8494, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3081455721869567e-05, + "loss": 3.8645, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3073086153162781e-05, + "loss": 3.868, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3064700205652261e-05, + "loss": 3.8552, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3056314258141741e-05, + "loss": 3.8415, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.304792831063122e-05, + "loss": 3.8587, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.30395423631207e-05, + "loss": 3.8611, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.303115641561018e-05, + "loss": 3.8642, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.302277046809966e-05, + "loss": 3.8539, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.301438452058914e-05, + "loss": 3.8585, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3005998573078621e-05, + "loss": 3.8628, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997612625568101e-05, + "loss": 3.848, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2989226678057578e-05, + "loss": 3.8545, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.298084073054706e-05, + "loss": 3.8595, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.297245478303654e-05, + "loss": 3.8586, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.296408521432975e-05, + "loss": 3.8695, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.295569926681923e-05, + "loss": 3.8598, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.294731331930871e-05, + "loss": 3.8494, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.293892737179819e-05, + "loss": 3.852, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.293054142428767e-05, + "loss": 3.8593, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2922155476777151e-05, + "loss": 3.862, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2913769529266631e-05, + "loss": 3.8529, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2905383581756108e-05, + "loss": 3.8526, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2897014013049322e-05, + "loss": 3.8447, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2888628065538802e-05, + "loss": 3.8627, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2880242118028282e-05, + "loss": 3.8371, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.287185617051776e-05, + "loss": 3.8542, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2863486601810973e-05, + "loss": 3.8564, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2855100654300453e-05, + "loss": 3.8601, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2846714706789931e-05, + "loss": 3.8474, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2838361516886874e-05, + "loss": 3.8595, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2829975569376354e-05, + "loss": 3.8486, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2821589621865834e-05, + "loss": 3.8603, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2813203674355314e-05, + "loss": 3.857, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2804817726844794e-05, + "loss": 3.8533, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2796431779334276e-05, + "loss": 3.8578, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2788045831823752e-05, + "loss": 3.8707, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2779676263116967e-05, + "loss": 3.8548, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2771290315606447e-05, + "loss": 3.8546, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2762904368095926e-05, + "loss": 3.8557, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2754518420585405e-05, + "loss": 3.8566, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2746132473074885e-05, + "loss": 3.857, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2737762904368097e-05, + "loss": 3.8567, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2729376956857577e-05, + "loss": 3.8544, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2720991009347055e-05, + "loss": 3.8605, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2712605061836535e-05, + "loss": 3.8468, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2704235493129748e-05, + "loss": 3.8513, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2695849545619226e-05, + "loss": 3.8465, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2687463598108706e-05, + "loss": 3.8558, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2679077650598186e-05, + "loss": 3.847, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2670691703087668e-05, + "loss": 3.8687, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2662305755577148e-05, + "loss": 3.8694, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2653919808066628e-05, + "loss": 3.8482, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2645533860556108e-05, + "loss": 3.8603, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2637147913045586e-05, + "loss": 3.8602, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2628778344338798e-05, + "loss": 3.8609, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2620392396828278e-05, + "loss": 3.8496, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.261200644931776e-05, + "loss": 3.8508, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2603620501807236e-05, + "loss": 3.8631, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2595234554296716e-05, + "loss": 3.863, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2586848606786198e-05, + "loss": 3.8485, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2578462659275678e-05, + "loss": 3.8602, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2570076711765158e-05, + "loss": 3.8671, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2561707143058369e-05, + "loss": 3.855, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2553353953155312e-05, + "loss": 3.8511, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2544968005644792e-05, + "loss": 3.8604, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2536582058134272e-05, + "loss": 3.8523, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2528196110623752e-05, + "loss": 3.8584, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2519810163113232e-05, + "loss": 3.8638, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.999021530151367, + "eval_runtime": 292.6657, + "eval_samples_per_second": 1303.846, + "eval_steps_per_second": 40.746, + "step": 2289600 + }, + { + "epoch": 2.0, + "learning_rate": 1.251142421560271e-05, + "loss": 3.8553, + "step": 2289664 + }, + { + "epoch": 2.0, + "learning_rate": 1.250303826809219e-05, + "loss": 3.8435, + "step": 2290176 + }, + { + "epoch": 2.0, + "learning_rate": 1.249465232058167e-05, + "loss": 3.8567, + "step": 2290688 + }, + { + "epoch": 2.0, + "learning_rate": 1.2486266373071152e-05, + "loss": 3.8687, + "step": 2291200 + }, + { + "epoch": 2.0, + "learning_rate": 1.2477880425560632e-05, + "loss": 3.8616, + "step": 2291712 + }, + { + "epoch": 2.0, + "learning_rate": 1.246949447805011e-05, + "loss": 3.8618, + "step": 2292224 + }, + { + "epoch": 2.0, + "learning_rate": 1.246110853053959e-05, + "loss": 3.8564, + "step": 2292736 + }, + { + "epoch": 2.0, + "learning_rate": 1.2452738961832802e-05, + "loss": 3.8588, + "step": 2293248 + }, + { + "epoch": 2.0, + "learning_rate": 1.244435301432228e-05, + "loss": 3.8503, + "step": 2293760 + }, + { + "epoch": 2.0, + "learning_rate": 1.2435967066811762e-05, + "loss": 3.8608, + "step": 2294272 + }, + { + "epoch": 2.0, + "learning_rate": 1.2427581119301242e-05, + "loss": 3.8534, + "step": 2294784 + }, + { + "epoch": 2.0, + "learning_rate": 1.2419211550594453e-05, + "loss": 3.8628, + "step": 2295296 + }, + { + "epoch": 2.0, + "learning_rate": 1.2410841981887664e-05, + "loss": 3.868, + "step": 2295808 + }, + { + "epoch": 2.0, + "learning_rate": 1.2402456034377144e-05, + "loss": 3.8454, + "step": 2296320 + }, + { + "epoch": 2.0, + "learning_rate": 1.2394070086866624e-05, + "loss": 3.8506, + "step": 2296832 + }, + { + "epoch": 2.0, + "learning_rate": 1.2385684139356105e-05, + "loss": 3.8398, + "step": 2297344 + }, + { + "epoch": 2.0, + "learning_rate": 1.2377298191845584e-05, + "loss": 3.859, + "step": 2297856 + }, + { + "epoch": 2.0, + "learning_rate": 1.2368912244335064e-05, + "loss": 3.8585, + "step": 2298368 + }, + { + "epoch": 2.0, + "learning_rate": 1.2360526296824544e-05, + "loss": 3.8542, + "step": 2298880 + }, + { + "epoch": 2.0, + "learning_rate": 1.2352140349314023e-05, + "loss": 3.8524, + "step": 2299392 + }, + { + "epoch": 2.0, + "learning_rate": 1.2343754401803503e-05, + "loss": 3.8803, + "step": 2299904 + }, + { + "epoch": 2.0, + "learning_rate": 1.2335368454292983e-05, + "loss": 3.8657, + "step": 2300416 + }, + { + "epoch": 2.0, + "learning_rate": 1.2326982506782463e-05, + "loss": 3.8575, + "step": 2300928 + }, + { + "epoch": 2.0, + "learning_rate": 1.2318596559271943e-05, + "loss": 3.8572, + "step": 2301440 + }, + { + "epoch": 2.0, + "learning_rate": 1.2310243369368887e-05, + "loss": 3.8702, + "step": 2301952 + }, + { + "epoch": 2.0, + "learning_rate": 1.2301857421858367e-05, + "loss": 3.8533, + "step": 2302464 + }, + { + "epoch": 2.0, + "learning_rate": 1.2293471474347845e-05, + "loss": 3.8531, + "step": 2302976 + }, + { + "epoch": 2.0, + "learning_rate": 1.2285085526837325e-05, + "loss": 3.8656, + "step": 2303488 + }, + { + "epoch": 2.0, + "learning_rate": 1.2276699579326806e-05, + "loss": 3.8507, + "step": 2304000 + }, + { + "epoch": 2.0, + "learning_rate": 1.2268313631816286e-05, + "loss": 3.853, + "step": 2304512 + }, + { + "epoch": 2.01, + "learning_rate": 1.2259927684305765e-05, + "loss": 3.857, + "step": 2305024 + }, + { + "epoch": 2.01, + "learning_rate": 1.2251558115598977e-05, + "loss": 3.8529, + "step": 2305536 + }, + { + "epoch": 2.01, + "learning_rate": 1.2243188546892188e-05, + "loss": 3.8631, + "step": 2306048 + }, + { + "epoch": 2.01, + "learning_rate": 1.2234802599381668e-05, + "loss": 3.8659, + "step": 2306560 + }, + { + "epoch": 2.01, + "learning_rate": 1.2226416651871148e-05, + "loss": 3.8534, + "step": 2307072 + }, + { + "epoch": 2.01, + "learning_rate": 1.2218047083164359e-05, + "loss": 3.8655, + "step": 2307584 + }, + { + "epoch": 2.01, + "learning_rate": 1.220966113565384e-05, + "loss": 3.8631, + "step": 2308096 + }, + { + "epoch": 2.01, + "learning_rate": 1.2201275188143319e-05, + "loss": 3.8391, + "step": 2308608 + }, + { + "epoch": 2.01, + "learning_rate": 1.2192889240632799e-05, + "loss": 3.851, + "step": 2309120 + }, + { + "epoch": 2.01, + "learning_rate": 1.2184503293122278e-05, + "loss": 3.855, + "step": 2309632 + }, + { + "epoch": 2.01, + "learning_rate": 1.2176117345611758e-05, + "loss": 3.843, + "step": 2310144 + }, + { + "epoch": 2.01, + "learning_rate": 1.2167731398101238e-05, + "loss": 3.86, + "step": 2310656 + }, + { + "epoch": 2.01, + "learning_rate": 1.2159345450590718e-05, + "loss": 3.8598, + "step": 2311168 + }, + { + "epoch": 2.01, + "learning_rate": 1.2150959503080198e-05, + "loss": 3.8549, + "step": 2311680 + }, + { + "epoch": 2.01, + "learning_rate": 1.2142573555569678e-05, + "loss": 3.8564, + "step": 2312192 + }, + { + "epoch": 2.01, + "learning_rate": 1.2134187608059158e-05, + "loss": 3.8595, + "step": 2312704 + }, + { + "epoch": 2.01, + "learning_rate": 1.2125801660548638e-05, + "loss": 3.8516, + "step": 2313216 + }, + { + "epoch": 2.01, + "learning_rate": 1.2117415713038118e-05, + "loss": 3.8685, + "step": 2313728 + }, + { + "epoch": 2.01, + "learning_rate": 1.2109029765527598e-05, + "loss": 3.8424, + "step": 2314240 + }, + { + "epoch": 2.01, + "learning_rate": 1.2100660196820809e-05, + "loss": 3.8619, + "step": 2314752 + }, + { + "epoch": 2.01, + "learning_rate": 1.209227424931029e-05, + "loss": 3.8586, + "step": 2315264 + }, + { + "epoch": 2.01, + "learning_rate": 1.2083888301799769e-05, + "loss": 3.8556, + "step": 2315776 + }, + { + "epoch": 2.01, + "learning_rate": 1.207551873309298e-05, + "loss": 3.8582, + "step": 2316288 + }, + { + "epoch": 2.01, + "learning_rate": 1.2067132785582461e-05, + "loss": 3.8422, + "step": 2316800 + }, + { + "epoch": 2.01, + "learning_rate": 1.205874683807194e-05, + "loss": 3.8563, + "step": 2317312 + }, + { + "epoch": 2.01, + "learning_rate": 1.205036089056142e-05, + "loss": 3.8391, + "step": 2317824 + }, + { + "epoch": 2.01, + "learning_rate": 1.20419749430509e-05, + "loss": 3.8735, + "step": 2318336 + }, + { + "epoch": 2.01, + "learning_rate": 1.2033588995540381e-05, + "loss": 3.8449, + "step": 2318848 + }, + { + "epoch": 2.01, + "learning_rate": 1.202521942683359e-05, + "loss": 3.8617, + "step": 2319360 + }, + { + "epoch": 2.01, + "learning_rate": 1.2016833479323072e-05, + "loss": 3.8543, + "step": 2319872 + }, + { + "epoch": 2.01, + "learning_rate": 1.2008447531812552e-05, + "loss": 3.8493, + "step": 2320384 + }, + { + "epoch": 2.01, + "learning_rate": 1.200006158430203e-05, + "loss": 3.8512, + "step": 2320896 + }, + { + "epoch": 2.01, + "learning_rate": 1.199167563679151e-05, + "loss": 3.8559, + "step": 2321408 + }, + { + "epoch": 2.01, + "learning_rate": 1.1983289689280992e-05, + "loss": 3.8387, + "step": 2321920 + }, + { + "epoch": 2.01, + "learning_rate": 1.1974903741770472e-05, + "loss": 3.8386, + "step": 2322432 + }, + { + "epoch": 2.01, + "learning_rate": 1.196651779425995e-05, + "loss": 3.866, + "step": 2322944 + }, + { + "epoch": 2.01, + "learning_rate": 1.195813184674943e-05, + "loss": 3.8558, + "step": 2323456 + }, + { + "epoch": 2.01, + "learning_rate": 1.1949778656846373e-05, + "loss": 3.8524, + "step": 2323968 + }, + { + "epoch": 2.01, + "learning_rate": 1.1941392709335853e-05, + "loss": 3.8408, + "step": 2324480 + }, + { + "epoch": 2.01, + "learning_rate": 1.1933006761825333e-05, + "loss": 3.8493, + "step": 2324992 + }, + { + "epoch": 2.01, + "learning_rate": 1.1924620814314813e-05, + "loss": 3.8532, + "step": 2325504 + }, + { + "epoch": 2.01, + "learning_rate": 1.1916234866804293e-05, + "loss": 3.86, + "step": 2326016 + }, + { + "epoch": 2.01, + "learning_rate": 1.1907848919293773e-05, + "loss": 3.861, + "step": 2326528 + }, + { + "epoch": 2.01, + "learning_rate": 1.1899462971783253e-05, + "loss": 3.8593, + "step": 2327040 + }, + { + "epoch": 2.01, + "learning_rate": 1.1891093403076464e-05, + "loss": 3.8603, + "step": 2327552 + }, + { + "epoch": 2.01, + "learning_rate": 1.1882707455565945e-05, + "loss": 3.8518, + "step": 2328064 + }, + { + "epoch": 2.01, + "learning_rate": 1.1874321508055424e-05, + "loss": 3.8512, + "step": 2328576 + }, + { + "epoch": 2.01, + "learning_rate": 1.1865935560544903e-05, + "loss": 3.8492, + "step": 2329088 + }, + { + "epoch": 2.01, + "learning_rate": 1.1857549613034383e-05, + "loss": 3.8562, + "step": 2329600 + }, + { + "epoch": 2.01, + "learning_rate": 1.1849163665523863e-05, + "loss": 3.854, + "step": 2330112 + }, + { + "epoch": 2.01, + "learning_rate": 1.1840777718013343e-05, + "loss": 3.8465, + "step": 2330624 + }, + { + "epoch": 2.01, + "learning_rate": 1.1832391770502823e-05, + "loss": 3.857, + "step": 2331136 + }, + { + "epoch": 2.01, + "learning_rate": 1.1824005822992303e-05, + "loss": 3.8614, + "step": 2331648 + }, + { + "epoch": 2.01, + "learning_rate": 1.1815636254285514e-05, + "loss": 3.8529, + "step": 2332160 + }, + { + "epoch": 2.01, + "learning_rate": 1.1807250306774994e-05, + "loss": 3.8432, + "step": 2332672 + }, + { + "epoch": 2.01, + "learning_rate": 1.1798864359264476e-05, + "loss": 3.8488, + "step": 2333184 + }, + { + "epoch": 2.01, + "learning_rate": 1.1790494790557685e-05, + "loss": 3.8551, + "step": 2333696 + }, + { + "epoch": 2.01, + "learning_rate": 1.1782108843047165e-05, + "loss": 3.8632, + "step": 2334208 + }, + { + "epoch": 2.01, + "learning_rate": 1.1773722895536646e-05, + "loss": 3.852, + "step": 2334720 + }, + { + "epoch": 2.01, + "learning_rate": 1.1765336948026126e-05, + "loss": 3.8543, + "step": 2335232 + }, + { + "epoch": 2.02, + "learning_rate": 1.1756951000515605e-05, + "loss": 3.8568, + "step": 2335744 + }, + { + "epoch": 2.02, + "learning_rate": 1.1748565053005085e-05, + "loss": 3.8456, + "step": 2336256 + }, + { + "epoch": 2.02, + "learning_rate": 1.1740179105494566e-05, + "loss": 3.848, + "step": 2336768 + }, + { + "epoch": 2.02, + "learning_rate": 1.1731793157984044e-05, + "loss": 3.8533, + "step": 2337280 + }, + { + "epoch": 2.02, + "learning_rate": 1.1723423589277257e-05, + "loss": 3.8573, + "step": 2337792 + }, + { + "epoch": 2.02, + "learning_rate": 1.1715037641766737e-05, + "loss": 3.8616, + "step": 2338304 + }, + { + "epoch": 2.02, + "learning_rate": 1.1706651694256217e-05, + "loss": 3.8585, + "step": 2338816 + }, + { + "epoch": 2.02, + "learning_rate": 1.1698265746745695e-05, + "loss": 3.8434, + "step": 2339328 + }, + { + "epoch": 2.02, + "learning_rate": 1.1689879799235177e-05, + "loss": 3.8521, + "step": 2339840 + }, + { + "epoch": 2.02, + "learning_rate": 1.1681493851724657e-05, + "loss": 3.8538, + "step": 2340352 + }, + { + "epoch": 2.02, + "learning_rate": 1.1673124283017866e-05, + "loss": 3.8599, + "step": 2340864 + }, + { + "epoch": 2.02, + "learning_rate": 1.1664738335507347e-05, + "loss": 3.8492, + "step": 2341376 + }, + { + "epoch": 2.02, + "learning_rate": 1.1656352387996827e-05, + "loss": 3.8494, + "step": 2341888 + }, + { + "epoch": 2.02, + "learning_rate": 1.1647966440486307e-05, + "loss": 3.8431, + "step": 2342400 + }, + { + "epoch": 2.02, + "learning_rate": 1.1639580492975787e-05, + "loss": 3.8549, + "step": 2342912 + }, + { + "epoch": 2.02, + "learning_rate": 1.1631210924268998e-05, + "loss": 3.8344, + "step": 2343424 + }, + { + "epoch": 2.02, + "learning_rate": 1.1622824976758478e-05, + "loss": 3.8496, + "step": 2343936 + }, + { + "epoch": 2.02, + "learning_rate": 1.1614439029247958e-05, + "loss": 3.8551, + "step": 2344448 + }, + { + "epoch": 2.02, + "learning_rate": 1.1606053081737438e-05, + "loss": 3.8519, + "step": 2344960 + }, + { + "epoch": 2.02, + "learning_rate": 1.1597683513030649e-05, + "loss": 3.8443, + "step": 2345472 + }, + { + "epoch": 2.02, + "learning_rate": 1.158929756552013e-05, + "loss": 3.8526, + "step": 2345984 + }, + { + "epoch": 2.02, + "learning_rate": 1.1580911618009609e-05, + "loss": 3.8438, + "step": 2346496 + }, + { + "epoch": 2.02, + "learning_rate": 1.1572525670499089e-05, + "loss": 3.8556, + "step": 2347008 + }, + { + "epoch": 2.02, + "learning_rate": 1.1564139722988569e-05, + "loss": 3.8576, + "step": 2347520 + }, + { + "epoch": 2.02, + "learning_rate": 1.1555753775478049e-05, + "loss": 3.8469, + "step": 2348032 + }, + { + "epoch": 2.02, + "learning_rate": 1.1547367827967529e-05, + "loss": 3.8575, + "step": 2348544 + }, + { + "epoch": 2.02, + "learning_rate": 1.1538981880457008e-05, + "loss": 3.8633, + "step": 2349056 + }, + { + "epoch": 2.02, + "learning_rate": 1.1530612311750221e-05, + "loss": 3.8581, + "step": 2349568 + }, + { + "epoch": 2.02, + "learning_rate": 1.152224274304343e-05, + "loss": 3.8455, + "step": 2350080 + }, + { + "epoch": 2.02, + "learning_rate": 1.1513856795532912e-05, + "loss": 3.8575, + "step": 2350592 + }, + { + "epoch": 2.02, + "learning_rate": 1.1505470848022392e-05, + "loss": 3.8536, + "step": 2351104 + }, + { + "epoch": 2.02, + "learning_rate": 1.149708490051187e-05, + "loss": 3.8485, + "step": 2351616 + }, + { + "epoch": 2.02, + "learning_rate": 1.148869895300135e-05, + "loss": 3.8553, + "step": 2352128 + }, + { + "epoch": 2.02, + "learning_rate": 1.1480313005490832e-05, + "loss": 3.8483, + "step": 2352640 + }, + { + "epoch": 2.02, + "learning_rate": 1.1471927057980311e-05, + "loss": 3.8566, + "step": 2353152 + }, + { + "epoch": 2.02, + "learning_rate": 1.146354111046979e-05, + "loss": 3.844, + "step": 2353664 + }, + { + "epoch": 2.02, + "learning_rate": 1.145515516295927e-05, + "loss": 3.8475, + "step": 2354176 + }, + { + "epoch": 2.02, + "learning_rate": 1.1446785594252482e-05, + "loss": 3.84, + "step": 2354688 + }, + { + "epoch": 2.02, + "learning_rate": 1.143839964674196e-05, + "loss": 3.8502, + "step": 2355200 + }, + { + "epoch": 2.02, + "learning_rate": 1.1430013699231442e-05, + "loss": 3.8393, + "step": 2355712 + }, + { + "epoch": 2.02, + "learning_rate": 1.1421627751720922e-05, + "loss": 3.8639, + "step": 2356224 + }, + { + "epoch": 2.02, + "learning_rate": 1.1413241804210402e-05, + "loss": 3.8655, + "step": 2356736 + }, + { + "epoch": 2.02, + "learning_rate": 1.1404872235503613e-05, + "loss": 3.8468, + "step": 2357248 + }, + { + "epoch": 2.02, + "learning_rate": 1.1396486287993093e-05, + "loss": 3.8522, + "step": 2357760 + }, + { + "epoch": 2.02, + "learning_rate": 1.1388100340482573e-05, + "loss": 3.8584, + "step": 2358272 + }, + { + "epoch": 2.02, + "learning_rate": 1.1379714392972051e-05, + "loss": 3.8572, + "step": 2358784 + }, + { + "epoch": 2.02, + "learning_rate": 1.1371328445461533e-05, + "loss": 3.8482, + "step": 2359296 + }, + { + "epoch": 2.02, + "learning_rate": 1.1362942497951013e-05, + "loss": 3.8467, + "step": 2359808 + }, + { + "epoch": 2.02, + "learning_rate": 1.1354556550440493e-05, + "loss": 3.8591, + "step": 2360320 + }, + { + "epoch": 2.02, + "learning_rate": 1.1346203360537434e-05, + "loss": 3.8586, + "step": 2360832 + }, + { + "epoch": 2.02, + "learning_rate": 1.1337817413026914e-05, + "loss": 3.8481, + "step": 2361344 + }, + { + "epoch": 2.02, + "learning_rate": 1.1329431465516396e-05, + "loss": 3.8544, + "step": 2361856 + }, + { + "epoch": 2.02, + "learning_rate": 1.1321045518005876e-05, + "loss": 3.8626, + "step": 2362368 + }, + { + "epoch": 2.02, + "learning_rate": 1.1312659570495354e-05, + "loss": 3.8497, + "step": 2362880 + }, + { + "epoch": 2.02, + "learning_rate": 1.1304273622984834e-05, + "loss": 3.8508, + "step": 2363392 + }, + { + "epoch": 2.02, + "learning_rate": 1.1295887675474316e-05, + "loss": 3.8571, + "step": 2363904 + }, + { + "epoch": 2.02, + "learning_rate": 1.1287501727963794e-05, + "loss": 3.848, + "step": 2364416 + }, + { + "epoch": 2.02, + "learning_rate": 1.1279115780453274e-05, + "loss": 3.857, + "step": 2364928 + }, + { + "epoch": 2.02, + "learning_rate": 1.1270746211746486e-05, + "loss": 3.8573, + "step": 2365440 + }, + { + "epoch": 2.03, + "eval_loss": 3.997340440750122, + "eval_runtime": 291.679, + "eval_samples_per_second": 1308.257, + "eval_steps_per_second": 40.884, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1262360264235966e-05, + "loss": 3.8326, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1253974316725444e-05, + "loss": 3.8432, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1245588369214924e-05, + "loss": 3.8506, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1237202421704406e-05, + "loss": 3.8621, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1228816474193884e-05, + "loss": 3.8558, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1220430526683364e-05, + "loss": 3.8627, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1212044579172844e-05, + "loss": 3.8483, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1203658631662324e-05, + "loss": 3.8584, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1195272684151804e-05, + "loss": 3.8432, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1186886736641284e-05, + "loss": 3.8571, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1178517167934497e-05, + "loss": 3.8475, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1170131220423975e-05, + "loss": 3.8609, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1161745272913455e-05, + "loss": 3.865, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1153359325402936e-05, + "loss": 3.8418, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1144973377892415e-05, + "loss": 3.8452, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1136587430381895e-05, + "loss": 3.8387, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1128201482871375e-05, + "loss": 3.848, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1119815535360856e-05, + "loss": 3.8536, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1111429587850335e-05, + "loss": 3.8525, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1103043640339815e-05, + "loss": 3.8488, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1094674071633027e-05, + "loss": 3.8767, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1086288124122505e-05, + "loss": 3.8598, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1077902176611985e-05, + "loss": 3.8588, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1069516229101467e-05, + "loss": 3.8513, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1061146660394678e-05, + "loss": 3.866, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1052760712884156e-05, + "loss": 3.8514, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1044374765373638e-05, + "loss": 3.852, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1035988817863118e-05, + "loss": 3.86, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1027602870352596e-05, + "loss": 3.8424, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1019216922842077e-05, + "loss": 3.8547, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1010830975331557e-05, + "loss": 3.8489, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1002445027821036e-05, + "loss": 3.8502, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0994075459114248e-05, + "loss": 3.8559, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0985705890407459e-05, + "loss": 3.863, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0977319942896939e-05, + "loss": 3.8512, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0968950374190151e-05, + "loss": 3.8637, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.096056442667963e-05, + "loss": 3.8579, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095217847916911e-05, + "loss": 3.8349, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0943792531658591e-05, + "loss": 3.8507, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.093540658414807e-05, + "loss": 3.8488, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.092702063663755e-05, + "loss": 3.8358, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.091863468912703e-05, + "loss": 3.8554, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.091024874161651e-05, + "loss": 3.8581, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.090187917290972e-05, + "loss": 3.854, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0893493225399202e-05, + "loss": 3.845, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0885107277888682e-05, + "loss": 3.8604, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.087672133037816e-05, + "loss": 3.8479, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.086833538286764e-05, + "loss": 3.8664, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0859965814160852e-05, + "loss": 3.8363, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0851579866650332e-05, + "loss": 3.8539, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0843193919139812e-05, + "loss": 3.8587, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0834807971629292e-05, + "loss": 3.8502, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0826422024118772e-05, + "loss": 3.8553, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.081803607660825e-05, + "loss": 3.8354, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0809650129097732e-05, + "loss": 3.8555, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0801264181587212e-05, + "loss": 3.836, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.079287823407669e-05, + "loss": 3.8645, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0784508665369903e-05, + "loss": 3.8443, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0776122717859383e-05, + "loss": 3.8542, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0767736770348863e-05, + "loss": 3.8534, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0759350822838341e-05, + "loss": 3.8451, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0750964875327823e-05, + "loss": 3.8486, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0742578927817303e-05, + "loss": 3.8522, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0734192980306781e-05, + "loss": 3.8361, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0725823411599993e-05, + "loss": 3.8363, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0717437464089473e-05, + "loss": 3.8574, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0709051516578953e-05, + "loss": 3.8525, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0700665569068433e-05, + "loss": 3.8517, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0692279621557913e-05, + "loss": 3.8359, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0683893674047393e-05, + "loss": 3.8427, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0675507726536871e-05, + "loss": 3.8498, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0667138157830084e-05, + "loss": 3.8544, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0658768589123295e-05, + "loss": 3.8574, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0650382641612776e-05, + "loss": 3.8518, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0641996694102255e-05, + "loss": 3.8586, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0633610746591735e-05, + "loss": 3.8489, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0625224799081215e-05, + "loss": 3.8445, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0616855230374427e-05, + "loss": 3.8498, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0608469282863905e-05, + "loss": 3.8485, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0600083335353387e-05, + "loss": 3.853, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0591697387842867e-05, + "loss": 3.8449, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0583311440332345e-05, + "loss": 3.8475, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0574925492821825e-05, + "loss": 3.8653, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0566539545311307e-05, + "loss": 3.8475, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0558153597800787e-05, + "loss": 3.8389, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0549784029093998e-05, + "loss": 3.8453, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0541398081583477e-05, + "loss": 3.8525, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0533012134072957e-05, + "loss": 3.857, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0524626186562436e-05, + "loss": 3.8497, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0516240239051917e-05, + "loss": 3.8457, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0507854291541397e-05, + "loss": 3.8547, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0499468344030877e-05, + "loss": 3.8447, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0491115154127819e-05, + "loss": 3.8439, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0482729206617299e-05, + "loss": 3.8489, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0474343259106779e-05, + "loss": 3.8526, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.046595731159626e-05, + "loss": 3.8587, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0457571364085739e-05, + "loss": 3.8547, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0449185416575219e-05, + "loss": 3.8431, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0440799469064699e-05, + "loss": 3.8446, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0432413521554179e-05, + "loss": 3.8495, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.042404395284739e-05, + "loss": 3.8578, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0415658005336871e-05, + "loss": 3.8442, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.040727205782635e-05, + "loss": 3.8445, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.039888611031583e-05, + "loss": 3.8427, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.039050016280531e-05, + "loss": 3.8496, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0382130594098522e-05, + "loss": 3.8327, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0373744646588e-05, + "loss": 3.8464, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.036535869907748e-05, + "loss": 3.8463, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0356972751566962e-05, + "loss": 3.8495, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.034858680405644e-05, + "loss": 3.8421, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340217235349652e-05, + "loss": 3.8491, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0331831287839132e-05, + "loss": 3.8375, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0323445340328612e-05, + "loss": 3.8515, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0315075771621823e-05, + "loss": 3.8552, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306689824111303e-05, + "loss": 3.8398, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0298303876600783e-05, + "loss": 3.855, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0289917929090263e-05, + "loss": 3.861, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0281531981579743e-05, + "loss": 3.8549, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0273146034069223e-05, + "loss": 3.8431, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0264760086558703e-05, + "loss": 3.8477, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0256374139048181e-05, + "loss": 3.8525, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0247988191537663e-05, + "loss": 3.8448, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0239602244027143e-05, + "loss": 3.8552, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0231232675320353e-05, + "loss": 3.8448, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0222846727809833e-05, + "loss": 3.8543, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0214460780299313e-05, + "loss": 3.8413, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0206074832788793e-05, + "loss": 3.845, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0197688885278273e-05, + "loss": 3.8375, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0189319316571484e-05, + "loss": 3.8466, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0180933369060964e-05, + "loss": 3.836, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0172547421550446e-05, + "loss": 3.8591, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0164161474039924e-05, + "loss": 3.8679, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0155775526529404e-05, + "loss": 3.8479, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0147389579018884e-05, + "loss": 3.8442, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0139020010312095e-05, + "loss": 3.8552, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0130634062801575e-05, + "loss": 3.8562, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0122248115291054e-05, + "loss": 3.8483, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113862167780536e-05, + "loss": 3.8415, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0105492599073745e-05, + "loss": 3.8587, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0097106651563227e-05, + "loss": 3.8511, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0088737082856438e-05, + "loss": 3.8483, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0080351135345918e-05, + "loss": 3.8492, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0071965187835398e-05, + "loss": 3.8573, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0063579240324878e-05, + "loss": 3.847, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0055209671618088e-05, + "loss": 3.8465, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0046823724107568e-05, + "loss": 3.8554, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0038437776597048e-05, + "loss": 3.8458, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0030051829086528e-05, + "loss": 3.8506, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0021665881576008e-05, + "loss": 3.8563, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0013279934065488e-05, + "loss": 3.8484, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.9963762760162354, + "eval_runtime": 314.5137, + "eval_samples_per_second": 1213.273, + "eval_steps_per_second": 37.916, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0004893986554968e-05, + "loss": 3.842, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.996508039044448e-06, + "loss": 3.8463, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.988122091533928e-06, + "loss": 3.8588, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.979736144023408e-06, + "loss": 3.8547, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.971366575316619e-06, + "loss": 3.8593, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.9629806278061e-06, + "loss": 3.8443, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.954594680295579e-06, + "loss": 3.8544, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.946208732785059e-06, + "loss": 3.8387, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.937839164078271e-06, + "loss": 3.8583, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.92945321656775e-06, + "loss": 3.8411, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92106726905723e-06, + "loss": 3.8612, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.912681321546711e-06, + "loss": 3.8592, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.904311752839922e-06, + "loss": 3.8415, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.8959258053294e-06, + "loss": 3.8421, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.887539857818882e-06, + "loss": 3.839, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.879153910308362e-06, + "loss": 3.841, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87076796279784e-06, + "loss": 3.8511, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86238201528732e-06, + "loss": 3.846, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.853996067776801e-06, + "loss": 3.8482, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.84561012026628e-06, + "loss": 3.8731, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.837240551559492e-06, + "loss": 3.8555, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.828854604048972e-06, + "loss": 3.8565, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.820468656538452e-06, + "loss": 3.8473, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81208270902793e-06, + "loss": 3.8606, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.803696761517412e-06, + "loss": 3.8431, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.795327192810623e-06, + "loss": 3.8542, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.786941245300103e-06, + "loss": 3.8543, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.778555297789583e-06, + "loss": 3.844, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.770169350279063e-06, + "loss": 3.8465, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.761783402768543e-06, + "loss": 3.8453, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.753413834061753e-06, + "loss": 3.8495, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.745027886551233e-06, + "loss": 3.8528, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.736641939040713e-06, + "loss": 3.8594, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.728272370333926e-06, + "loss": 3.8507, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.719902801627135e-06, + "loss": 3.8591, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.711516854116617e-06, + "loss": 3.8526, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.703130906606097e-06, + "loss": 3.8351, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.694744959095576e-06, + "loss": 3.8475, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.686359011585055e-06, + "loss": 3.841, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.677973064074536e-06, + "loss": 3.836, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.669587116564016e-06, + "loss": 3.8518, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.661201169053495e-06, + "loss": 3.8565, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.652815221542975e-06, + "loss": 3.8463, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.644429274032456e-06, + "loss": 3.8462, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.636043326521934e-06, + "loss": 3.8563, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.627657379011414e-06, + "loss": 3.8518, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.619287810304627e-06, + "loss": 3.8546, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.610901862794107e-06, + "loss": 3.8389, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.602515915283585e-06, + "loss": 3.8461, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.594146346576798e-06, + "loss": 3.8551, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.585760399066278e-06, + "loss": 3.8498, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.577374451555758e-06, + "loss": 3.8482, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.568988504045237e-06, + "loss": 3.8382, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.560602556534717e-06, + "loss": 3.8516, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.552216609024197e-06, + "loss": 3.8326, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.543830661513677e-06, + "loss": 3.8591, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.535461092806888e-06, + "loss": 3.8442, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.527075145296368e-06, + "loss": 3.8501, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.518689197785848e-06, + "loss": 3.8475, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.510303250275328e-06, + "loss": 3.8456, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.501917302764808e-06, + "loss": 3.8399, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.493531355254288e-06, + "loss": 3.8503, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.485145407743768e-06, + "loss": 3.8363, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.476759460233248e-06, + "loss": 3.8329, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.468373512722728e-06, + "loss": 3.8524, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46000394401594e-06, + "loss": 3.8535, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.451617996505419e-06, + "loss": 3.8479, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.443232048994898e-06, + "loss": 3.8308, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.434846101484378e-06, + "loss": 3.8392, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.426460153973858e-06, + "loss": 3.8477, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.418074206463338e-06, + "loss": 3.8534, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.409688258952818e-06, + "loss": 3.8506, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.40131869024603e-06, + "loss": 3.8486, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.392932742735509e-06, + "loss": 3.8565, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.384546795224989e-06, + "loss": 3.8534, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.37616084771447e-06, + "loss": 3.8357, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.367774900203949e-06, + "loss": 3.8433, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.359388952693429e-06, + "loss": 3.8499, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.351019383986641e-06, + "loss": 3.8462, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.342633436476121e-06, + "loss": 3.8461, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.3342474889656e-06, + "loss": 3.8434, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.325861541455081e-06, + "loss": 3.865, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.317475593944561e-06, + "loss": 3.8431, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.30910602523777e-06, + "loss": 3.8357, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.300720077727252e-06, + "loss": 3.8462, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.292334130216732e-06, + "loss": 3.8495, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.28394818270621e-06, + "loss": 3.8542, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.27556223519569e-06, + "loss": 3.8434, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.267192666488903e-06, + "loss": 3.8473, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.258806718978383e-06, + "loss": 3.8485, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.250420771467863e-06, + "loss": 3.8447, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.242034823957342e-06, + "loss": 3.8372, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.233648876446822e-06, + "loss": 3.8442, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.2252629289363e-06, + "loss": 3.8544, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.216893360229513e-06, + "loss": 3.86, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.208507412718993e-06, + "loss": 3.8438, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.200121465208473e-06, + "loss": 3.8367, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.191735517697953e-06, + "loss": 3.8452, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.183349570187433e-06, + "loss": 3.8443, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.174963622676913e-06, + "loss": 3.8542, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.166577675166391e-06, + "loss": 3.8434, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.158191727655873e-06, + "loss": 3.8433, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.149822158949084e-06, + "loss": 3.8367, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.141452590242296e-06, + "loss": 3.8517, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.133083021535507e-06, + "loss": 3.826, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.124697074024987e-06, + "loss": 3.8471, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.116311126514467e-06, + "loss": 3.8405, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.107925179003947e-06, + "loss": 3.849, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.099539231493425e-06, + "loss": 3.8391, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.091153283982907e-06, + "loss": 3.8487, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.082767336472387e-06, + "loss": 3.8386, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.074381388961865e-06, + "loss": 3.8447, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.065995441451345e-06, + "loss": 3.8495, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.057609493940827e-06, + "loss": 3.8383, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.049223546430306e-06, + "loss": 3.8549, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.040837598919785e-06, + "loss": 3.859, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.032468030212997e-06, + "loss": 3.8501, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.024098461506208e-06, + "loss": 3.8412, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.01571251399569e-06, + "loss": 3.8425, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.007326566485168e-06, + "loss": 3.8465, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 8.998940618974648e-06, + "loss": 3.8437, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.990554671464128e-06, + "loss": 3.8502, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.982185102757339e-06, + "loss": 3.8468, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.973799155246819e-06, + "loss": 3.8493, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.965413207736299e-06, + "loss": 3.8393, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.95702726022578e-06, + "loss": 3.8421, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.948641312715258e-06, + "loss": 3.8329, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.940271744008471e-06, + "loss": 3.8403, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.931885796497951e-06, + "loss": 3.8306, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.923499848987429e-06, + "loss": 3.8552, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.915113901476909e-06, + "loss": 3.8629, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.90672795396639e-06, + "loss": 3.8503, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.89834200645587e-06, + "loss": 3.8339, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.88997243774908e-06, + "loss": 3.8536, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.881586490238561e-06, + "loss": 3.8509, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.873200542728041e-06, + "loss": 3.8446, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.86481459521752e-06, + "loss": 3.8402, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.856445026510732e-06, + "loss": 3.8556, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.848075457803943e-06, + "loss": 3.8478, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.839689510293425e-06, + "loss": 3.8445, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.831303562782903e-06, + "loss": 3.8482, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.822917615272383e-06, + "loss": 3.8508, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.814531667761863e-06, + "loss": 3.8418, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.806145720251344e-06, + "loss": 3.8423, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.797759772740823e-06, + "loss": 3.8553, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.789373825230303e-06, + "loss": 3.8457, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.781004256523515e-06, + "loss": 3.8475, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.772618309012993e-06, + "loss": 3.8561, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.764232361502473e-06, + "loss": 3.8425, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.995408535003662, + "eval_runtime": 315.1855, + "eval_samples_per_second": 1210.687, + "eval_steps_per_second": 37.835, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.755846413991953e-06, + "loss": 3.8373, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.747460466481435e-06, + "loss": 3.8449, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.739074518970913e-06, + "loss": 3.8557, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.730688571460393e-06, + "loss": 3.8517, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.722302623949873e-06, + "loss": 3.8562, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.713916676439353e-06, + "loss": 3.8402, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.705530728928833e-06, + "loss": 3.8512, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.697144781418313e-06, + "loss": 3.8357, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.688775212711525e-06, + "loss": 3.8552, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.680389265201004e-06, + "loss": 3.8416, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.672003317690484e-06, + "loss": 3.857, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.663617370179965e-06, + "loss": 3.8509, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.655231422669444e-06, + "loss": 3.8472, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.646845475158924e-06, + "loss": 3.8383, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.638459527648404e-06, + "loss": 3.8364, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.630073580137883e-06, + "loss": 3.837, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.621687632627363e-06, + "loss": 3.8462, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.613301685116843e-06, + "loss": 3.8462, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.604915737606323e-06, + "loss": 3.8425, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.596529790095803e-06, + "loss": 3.8672, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.588143842585283e-06, + "loss": 3.8586, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.579757895074763e-06, + "loss": 3.8502, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.571371947564243e-06, + "loss": 3.845, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.562986000053723e-06, + "loss": 3.8596, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.554616431346934e-06, + "loss": 3.8384, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.546230483836414e-06, + "loss": 3.8508, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.537860915129625e-06, + "loss": 3.8498, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.529474967619106e-06, + "loss": 3.8466, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.521105398912317e-06, + "loss": 3.8404, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.512719451401795e-06, + "loss": 3.8425, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.504333503891277e-06, + "loss": 3.8475, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.495947556380757e-06, + "loss": 3.8489, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.487561608870237e-06, + "loss": 3.8525, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.479175661359715e-06, + "loss": 3.8536, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.470806092652928e-06, + "loss": 3.8547, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.462420145142408e-06, + "loss": 3.8479, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.454034197631888e-06, + "loss": 3.8337, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.445648250121368e-06, + "loss": 3.8469, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.437262302610847e-06, + "loss": 3.8384, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.428876355100327e-06, + "loss": 3.8359, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.420490407589807e-06, + "loss": 3.8503, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.412120838883018e-06, + "loss": 3.8535, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.403734891372498e-06, + "loss": 3.8426, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.395348943861978e-06, + "loss": 3.8445, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.386962996351458e-06, + "loss": 3.848, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.378577048840938e-06, + "loss": 3.8481, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.370191101330418e-06, + "loss": 3.8516, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.361805153819898e-06, + "loss": 3.84, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.353419206309378e-06, + "loss": 3.845, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.345049637602589e-06, + "loss": 3.8496, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.336663690092069e-06, + "loss": 3.8444, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.32829412138528e-06, + "loss": 3.8453, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.319908173874761e-06, + "loss": 3.8383, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.311522226364241e-06, + "loss": 3.849, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.30313627885372e-06, + "loss": 3.829, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.2947503313432e-06, + "loss": 3.8518, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.286364383832681e-06, + "loss": 3.8437, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.277978436322159e-06, + "loss": 3.8437, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.269592488811639e-06, + "loss": 3.8502, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.261222920104852e-06, + "loss": 3.8419, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.252836972594332e-06, + "loss": 3.8377, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.24445102508381e-06, + "loss": 3.8534, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.236065077573291e-06, + "loss": 3.8279, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.227679130062771e-06, + "loss": 3.8321, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.21929318255225e-06, + "loss": 3.8481, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.21090723504173e-06, + "loss": 3.85, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.202521287531211e-06, + "loss": 3.8459, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.194135340020691e-06, + "loss": 3.8313, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.18574939251017e-06, + "loss": 3.8347, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.17736344499965e-06, + "loss": 3.8394, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.168993876292862e-06, + "loss": 3.8515, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.16060792878234e-06, + "loss": 3.8451, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.152238360075553e-06, + "loss": 3.8489, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.143852412565033e-06, + "loss": 3.8513, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.135466465054513e-06, + "loss": 3.8525, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.127080517543993e-06, + "loss": 3.8339, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.118694570033472e-06, + "loss": 3.8409, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.110308622522952e-06, + "loss": 3.8537, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.10192267501243e-06, + "loss": 3.8405, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.093536727501912e-06, + "loss": 3.8463, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.085167158795123e-06, + "loss": 3.8372, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.076797590088336e-06, + "loss": 3.8595, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.068411642577814e-06, + "loss": 3.8419, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.060025695067294e-06, + "loss": 3.8318, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.051639747556774e-06, + "loss": 3.8418, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.043253800046254e-06, + "loss": 3.8467, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.034867852535734e-06, + "loss": 3.8527, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.026498283828946e-06, + "loss": 3.8426, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.018112336318426e-06, + "loss": 3.8419, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.009726388807904e-06, + "loss": 3.8488, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.001340441297384e-06, + "loss": 3.8383, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.992954493786866e-06, + "loss": 3.8369, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.984568546276344e-06, + "loss": 3.8408, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.976182598765824e-06, + "loss": 3.8529, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.967813030059037e-06, + "loss": 3.851, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.959427082548517e-06, + "loss": 3.8489, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.951041135037995e-06, + "loss": 3.8329, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.942655187527475e-06, + "loss": 3.8412, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.934285618820687e-06, + "loss": 3.8434, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.925899671310167e-06, + "loss": 3.847, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.917513723799647e-06, + "loss": 3.8437, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.909127776289127e-06, + "loss": 3.8403, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.900741828778607e-06, + "loss": 3.8339, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.892355881268085e-06, + "loss": 3.8498, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.883969933757567e-06, + "loss": 3.8204, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.875583986247047e-06, + "loss": 3.8449, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.867198038736525e-06, + "loss": 3.8383, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.858828470029738e-06, + "loss": 3.8474, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.850442522519218e-06, + "loss": 3.8351, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.842056575008698e-06, + "loss": 3.8467, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.833670627498178e-06, + "loss": 3.8361, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.825284679987658e-06, + "loss": 3.8432, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.816898732477138e-06, + "loss": 3.8483, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.808529163770348e-06, + "loss": 3.8377, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.800143216259828e-06, + "loss": 3.85, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.791773647553039e-06, + "loss": 3.8558, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78338770004252e-06, + "loss": 3.8456, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.775018131335732e-06, + "loss": 3.8381, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.76663218382521e-06, + "loss": 3.844, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.758246236314691e-06, + "loss": 3.8454, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.749860288804171e-06, + "loss": 3.8343, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.74147434129365e-06, + "loss": 3.8519, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.733088393783131e-06, + "loss": 3.8384, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.724702446272611e-06, + "loss": 3.8473, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.71631649876209e-06, + "loss": 3.8421, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.70793055125157e-06, + "loss": 3.837, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.699544603741051e-06, + "loss": 3.8282, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.691158656230531e-06, + "loss": 3.8369, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.68277270872001e-06, + "loss": 3.8306, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.67438676120949e-06, + "loss": 3.8531, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.666000813698971e-06, + "loss": 3.8621, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.65763124499218e-06, + "loss": 3.8478, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.64924529748166e-06, + "loss": 3.8312, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.640859349971142e-06, + "loss": 3.8507, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.632473402460622e-06, + "loss": 3.8445, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.624087454950101e-06, + "loss": 3.8431, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.615701507439581e-06, + "loss": 3.8415, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.607315559929061e-06, + "loss": 3.8477, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.5989459912222715e-06, + "loss": 3.8422, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.590560043711751e-06, + "loss": 3.8456, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.582174096201232e-06, + "loss": 3.8461, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.573788148690712e-06, + "loss": 3.8521, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.565418579983922e-06, + "loss": 3.8453, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.557032632473403e-06, + "loss": 3.8352, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.548646684962883e-06, + "loss": 3.8509, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.540260737452362e-06, + "loss": 3.8447, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.531891168745574e-06, + "loss": 3.8397, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.5235052212350544e-06, + "loss": 3.8544, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.515119273724534e-06, + "loss": 3.8384, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.9945976734161377, + "eval_runtime": 292.3174, + "eval_samples_per_second": 1305.4, + "eval_steps_per_second": 40.795, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.5067333262140135e-06, + "loss": 3.835, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.4983473787034935e-06, + "loss": 3.839, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.489961431192974e-06, + "loss": 3.8522, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.4815754836824525e-06, + "loss": 3.8471, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.473205914975664e-06, + "loss": 3.8539, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.464819967465145e-06, + "loss": 3.8379, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.456434019954625e-06, + "loss": 3.8475, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.448048072444104e-06, + "loss": 3.8293, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.439662124933584e-06, + "loss": 3.8565, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.431276177423065e-06, + "loss": 3.8363, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.422890229912544e-06, + "loss": 3.8537, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.4145206612057555e-06, + "loss": 3.8474, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.406151092498967e-06, + "loss": 3.8439, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.397765144988447e-06, + "loss": 3.8337, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.389379197477926e-06, + "loss": 3.8378, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.380993249967406e-06, + "loss": 3.8368, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.372607302456887e-06, + "loss": 3.8407, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.364221354946365e-06, + "loss": 3.843, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.355851786239578e-06, + "loss": 3.842, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.347465838729058e-06, + "loss": 3.862, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.339079891218538e-06, + "loss": 3.8539, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.330693943708017e-06, + "loss": 3.8493, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.3223079961974976e-06, + "loss": 3.8443, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.3139220486869775e-06, + "loss": 3.8517, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.305536101176457e-06, + "loss": 3.8397, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.2971501536659366e-06, + "loss": 3.8491, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.288764206155417e-06, + "loss": 3.8466, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.280378258644897e-06, + "loss": 3.8454, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.272008689938107e-06, + "loss": 3.8365, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.263622742427588e-06, + "loss": 3.841, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.255236794917068e-06, + "loss": 3.8431, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.246850847406547e-06, + "loss": 3.8461, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.238464899896027e-06, + "loss": 3.8521, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.230078952385508e-06, + "loss": 3.8488, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.221725762482451e-06, + "loss": 3.8472, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.2133398149719295e-06, + "loss": 3.8457, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.20495386746141e-06, + "loss": 3.8316, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.19656791995089e-06, + "loss": 3.8458, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.188181972440371e-06, + "loss": 3.8338, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.179796024929849e-06, + "loss": 3.8361, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.17141007741933e-06, + "loss": 3.8416, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.16302412990881e-06, + "loss": 3.852, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.154638182398289e-06, + "loss": 3.8392, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.146268613691501e-06, + "loss": 3.8377, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.137882666180981e-06, + "loss": 3.8527, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.1294967186704616e-06, + "loss": 3.8415, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.121110771159941e-06, + "loss": 3.8519, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.112741202453152e-06, + "loss": 3.8382, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.104355254942632e-06, + "loss": 3.8357, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.095969307432111e-06, + "loss": 3.8507, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.087583359921591e-06, + "loss": 3.8422, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.079197412411072e-06, + "loss": 3.8433, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.070811464900552e-06, + "loss": 3.8371, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.062425517390031e-06, + "loss": 3.8415, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.054039569879511e-06, + "loss": 3.8312, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.045670001172723e-06, + "loss": 3.8458, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.037284053662202e-06, + "loss": 3.8393, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.0289144849554135e-06, + "loss": 3.8425, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.020528537444894e-06, + "loss": 3.8493, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.012142589934374e-06, + "loss": 3.8368, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.003756642423853e-06, + "loss": 3.8334, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.995370694913333e-06, + "loss": 3.856, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.986984747402814e-06, + "loss": 3.8248, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.978615178696026e-06, + "loss": 3.8283, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.970229231185504e-06, + "loss": 3.8409, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.961843283674985e-06, + "loss": 3.8508, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.953457336164465e-06, + "loss": 3.8415, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.945071388653944e-06, + "loss": 3.8291, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.936685441143424e-06, + "loss": 3.8324, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.928299493632905e-06, + "loss": 3.8324, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.919913546122384e-06, + "loss": 3.85, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.911527598611864e-06, + "loss": 3.8429, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.9031416511013446e-06, + "loss": 3.8452, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.894755703590823e-06, + "loss": 3.8472, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.8863861348840345e-06, + "loss": 3.8502, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.878000187373515e-06, + "loss": 3.8319, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.869614239862995e-06, + "loss": 3.838, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.861228292352474e-06, + "loss": 3.8495, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.852842344841954e-06, + "loss": 3.8336, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.844456397331435e-06, + "loss": 3.8454, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.836070449820914e-06, + "loss": 3.8355, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.827684502310394e-06, + "loss": 3.8533, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.819314933603606e-06, + "loss": 3.841, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.810945364896817e-06, + "loss": 3.8301, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.802575796190029e-06, + "loss": 3.8362, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.794189848679508e-06, + "loss": 3.8424, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.785803901168988e-06, + "loss": 3.8519, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.777417953658469e-06, + "loss": 3.84, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.769032006147947e-06, + "loss": 3.8377, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.760646058637428e-06, + "loss": 3.8375, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.752260111126908e-06, + "loss": 3.8433, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.743874163616387e-06, + "loss": 3.8365, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.735488216105868e-06, + "loss": 3.8331, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.727102268595348e-06, + "loss": 3.8492, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.7187326998885594e-06, + "loss": 3.8465, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.7103467523780386e-06, + "loss": 3.8462, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.7019608048675185e-06, + "loss": 3.8316, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.693574857356999e-06, + "loss": 3.8379, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.685205288650211e-06, + "loss": 3.8393, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.676819341139689e-06, + "loss": 3.8432, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.66843339362917e-06, + "loss": 3.8442, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.66004744611865e-06, + "loss": 3.8352, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.651661498608129e-06, + "loss": 3.831, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.643275551097609e-06, + "loss": 3.8466, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.63488960358709e-06, + "loss": 3.8209, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.626503656076569e-06, + "loss": 3.839, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.618117708566049e-06, + "loss": 3.8322, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.6097481398592605e-06, + "loss": 3.8452, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.601362192348741e-06, + "loss": 3.8349, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.59297624483822e-06, + "loss": 3.8408, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.5845902973277e-06, + "loss": 3.8347, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.576220728620912e-06, + "loss": 3.8383, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.567834781110392e-06, + "loss": 3.8467, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.559448833599871e-06, + "loss": 3.8382, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.551062886089351e-06, + "loss": 3.8464, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.542676938578832e-06, + "loss": 3.8508, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.534290991068311e-06, + "loss": 3.846, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.525905043557791e-06, + "loss": 3.8379, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.517519096047271e-06, + "loss": 3.8337, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.50913314853675e-06, + "loss": 3.8466, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.500779958633693e-06, + "loss": 3.8327, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.492394011123173e-06, + "loss": 3.8487, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.484008063612654e-06, + "loss": 3.8368, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.475622116102132e-06, + "loss": 3.8438, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.467236168591613e-06, + "loss": 3.8394, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.458866599884825e-06, + "loss": 3.8366, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.450480652374305e-06, + "loss": 3.8244, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.442094704863784e-06, + "loss": 3.8368, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.433708757353265e-06, + "loss": 3.8304, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.425339188646476e-06, + "loss": 3.844, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.416953241135956e-06, + "loss": 3.8567, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.408567293625435e-06, + "loss": 3.8512, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.400181346114915e-06, + "loss": 3.8233, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.391811777408127e-06, + "loss": 3.8518, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.383425829897606e-06, + "loss": 3.8413, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.375039882387086e-06, + "loss": 3.841, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.366653934876567e-06, + "loss": 3.8326, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.358267987366047e-06, + "loss": 3.8464, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.3498984186592575e-06, + "loss": 3.8383, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.3415124711487375e-06, + "loss": 3.8422, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.3331265236382175e-06, + "loss": 3.843, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.3247405761276966e-06, + "loss": 3.8476, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.316354628617177e-06, + "loss": 3.8428, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.307968681106657e-06, + "loss": 3.8362, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.2995827335961364e-06, + "loss": 3.8459, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.291196786085616e-06, + "loss": 3.8455, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.282827217378828e-06, + "loss": 3.8389, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.27445764867204e-06, + "loss": 3.8505, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.266071701161519e-06, + "loss": 3.8355, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.994095802307129, + "eval_runtime": 293.7473, + "eval_samples_per_second": 1299.045, + "eval_steps_per_second": 40.596, + "step": 2671200 + }, + { + "epoch": 2.0, + "learning_rate": 6.257685753651e-06, + "loss": 3.8334, + "step": 2671616 + }, + { + "epoch": 2.0, + "learning_rate": 6.2492998061404795e-06, + "loss": 3.8393, + "step": 2672128 + }, + { + "epoch": 2.0, + "learning_rate": 6.2409138586299595e-06, + "loss": 3.8504, + "step": 2672640 + }, + { + "epoch": 2.0, + "learning_rate": 6.2325279111194394e-06, + "loss": 3.8424, + "step": 2673152 + }, + { + "epoch": 2.0, + "learning_rate": 6.22415834241265e-06, + "loss": 3.8561, + "step": 2673664 + }, + { + "epoch": 2.0, + "learning_rate": 6.215772394902131e-06, + "loss": 3.8332, + "step": 2674176 + }, + { + "epoch": 2.0, + "learning_rate": 6.20738644739161e-06, + "loss": 3.8463, + "step": 2674688 + }, + { + "epoch": 2.0, + "learning_rate": 6.19900049988109e-06, + "loss": 3.8235, + "step": 2675200 + }, + { + "epoch": 2.0, + "learning_rate": 6.190630931174302e-06, + "loss": 3.8558, + "step": 2675712 + }, + { + "epoch": 2.0, + "learning_rate": 6.182244983663781e-06, + "loss": 3.8363, + "step": 2676224 + }, + { + "epoch": 2.0, + "learning_rate": 6.173859036153262e-06, + "loss": 3.8486, + "step": 2676736 + }, + { + "epoch": 2.0, + "learning_rate": 6.165473088642741e-06, + "loss": 3.8461, + "step": 2677248 + }, + { + "epoch": 2.0, + "learning_rate": 6.1570871411322216e-06, + "loss": 3.8358, + "step": 2677760 + }, + { + "epoch": 2.0, + "learning_rate": 6.148701193621701e-06, + "loss": 3.8367, + "step": 2678272 + }, + { + "epoch": 2.0, + "learning_rate": 6.140315246111181e-06, + "loss": 3.8353, + "step": 2678784 + }, + { + "epoch": 2.0, + "learning_rate": 6.1319292986006614e-06, + "loss": 3.8315, + "step": 2679296 + }, + { + "epoch": 2.0, + "learning_rate": 6.1235433510901405e-06, + "loss": 3.8408, + "step": 2679808 + }, + { + "epoch": 2.0, + "learning_rate": 6.115157403579621e-06, + "loss": 3.8385, + "step": 2680320 + }, + { + "epoch": 2.0, + "learning_rate": 6.106787834872832e-06, + "loss": 3.8394, + "step": 2680832 + }, + { + "epoch": 2.0, + "learning_rate": 6.098401887362312e-06, + "loss": 3.8566, + "step": 2681344 + }, + { + "epoch": 2.0, + "learning_rate": 6.090015939851792e-06, + "loss": 3.8544, + "step": 2681856 + }, + { + "epoch": 2.0, + "learning_rate": 6.081629992341271e-06, + "loss": 3.8434, + "step": 2682368 + }, + { + "epoch": 2.0, + "learning_rate": 6.073244044830752e-06, + "loss": 3.8428, + "step": 2682880 + }, + { + "epoch": 2.0, + "learning_rate": 6.064858097320231e-06, + "loss": 3.8489, + "step": 2683392 + }, + { + "epoch": 2.0, + "learning_rate": 6.056472149809711e-06, + "loss": 3.8365, + "step": 2683904 + }, + { + "epoch": 2.0, + "learning_rate": 6.048102581102923e-06, + "loss": 3.8501, + "step": 2684416 + }, + { + "epoch": 2.0, + "learning_rate": 6.039716633592403e-06, + "loss": 3.8429, + "step": 2684928 + }, + { + "epoch": 2.0, + "learning_rate": 6.0313306860818826e-06, + "loss": 3.8376, + "step": 2685440 + }, + { + "epoch": 2.0, + "learning_rate": 6.0229447385713625e-06, + "loss": 3.8359, + "step": 2685952 + }, + { + "epoch": 2.01, + "learning_rate": 6.0145587910608425e-06, + "loss": 3.8396, + "step": 2686464 + }, + { + "epoch": 2.01, + "learning_rate": 6.006189222354053e-06, + "loss": 3.8388, + "step": 2686976 + }, + { + "epoch": 2.01, + "learning_rate": 5.997803274843534e-06, + "loss": 3.8458, + "step": 2687488 + }, + { + "epoch": 2.01, + "learning_rate": 5.989417327333013e-06, + "loss": 3.8503, + "step": 2688000 + }, + { + "epoch": 2.01, + "learning_rate": 5.981031379822493e-06, + "loss": 3.8456, + "step": 2688512 + }, + { + "epoch": 2.01, + "learning_rate": 5.972661811115705e-06, + "loss": 3.8476, + "step": 2689024 + }, + { + "epoch": 2.01, + "learning_rate": 5.964275863605185e-06, + "loss": 3.843, + "step": 2689536 + }, + { + "epoch": 2.01, + "learning_rate": 5.955889916094665e-06, + "loss": 3.8297, + "step": 2690048 + }, + { + "epoch": 2.01, + "learning_rate": 5.947503968584145e-06, + "loss": 3.839, + "step": 2690560 + }, + { + "epoch": 2.01, + "learning_rate": 5.939134399877356e-06, + "loss": 3.8293, + "step": 2691072 + }, + { + "epoch": 2.01, + "learning_rate": 5.930748452366835e-06, + "loss": 3.8377, + "step": 2691584 + }, + { + "epoch": 2.01, + "learning_rate": 5.922362504856316e-06, + "loss": 3.8409, + "step": 2692096 + }, + { + "epoch": 2.01, + "learning_rate": 5.913976557345795e-06, + "loss": 3.8446, + "step": 2692608 + }, + { + "epoch": 2.01, + "learning_rate": 5.905590609835275e-06, + "loss": 3.8414, + "step": 2693120 + }, + { + "epoch": 2.01, + "learning_rate": 5.897204662324755e-06, + "loss": 3.8323, + "step": 2693632 + }, + { + "epoch": 2.01, + "learning_rate": 5.888818714814235e-06, + "loss": 3.8477, + "step": 2694144 + }, + { + "epoch": 2.01, + "learning_rate": 5.880449146107447e-06, + "loss": 3.8444, + "step": 2694656 + }, + { + "epoch": 2.01, + "learning_rate": 5.872063198596926e-06, + "loss": 3.8469, + "step": 2695168 + }, + { + "epoch": 2.01, + "learning_rate": 5.863677251086407e-06, + "loss": 3.839, + "step": 2695680 + }, + { + "epoch": 2.01, + "learning_rate": 5.855291303575886e-06, + "loss": 3.8288, + "step": 2696192 + }, + { + "epoch": 2.01, + "learning_rate": 5.846905356065366e-06, + "loss": 3.8499, + "step": 2696704 + }, + { + "epoch": 2.01, + "learning_rate": 5.838519408554846e-06, + "loss": 3.8384, + "step": 2697216 + }, + { + "epoch": 2.01, + "learning_rate": 5.830133461044326e-06, + "loss": 3.8421, + "step": 2697728 + }, + { + "epoch": 2.01, + "learning_rate": 5.8217475135338065e-06, + "loss": 3.8361, + "step": 2698240 + }, + { + "epoch": 2.01, + "learning_rate": 5.813394323630748e-06, + "loss": 3.8333, + "step": 2698752 + }, + { + "epoch": 2.01, + "learning_rate": 5.805008376120229e-06, + "loss": 3.8323, + "step": 2699264 + }, + { + "epoch": 2.01, + "learning_rate": 5.796655186217171e-06, + "loss": 3.8401, + "step": 2699776 + }, + { + "epoch": 2.01, + "learning_rate": 5.788269238706651e-06, + "loss": 3.8399, + "step": 2700288 + }, + { + "epoch": 2.01, + "learning_rate": 5.779883291196131e-06, + "loss": 3.8421, + "step": 2700800 + }, + { + "epoch": 2.01, + "learning_rate": 5.771497343685611e-06, + "loss": 3.8421, + "step": 2701312 + }, + { + "epoch": 2.01, + "learning_rate": 5.763111396175091e-06, + "loss": 3.8349, + "step": 2701824 + }, + { + "epoch": 2.01, + "learning_rate": 5.754725448664571e-06, + "loss": 3.8299, + "step": 2702336 + }, + { + "epoch": 2.01, + "learning_rate": 5.746339501154051e-06, + "loss": 3.8549, + "step": 2702848 + }, + { + "epoch": 2.01, + "learning_rate": 5.73795355364353e-06, + "loss": 3.8241, + "step": 2703360 + }, + { + "epoch": 2.01, + "learning_rate": 5.729567606133011e-06, + "loss": 3.8239, + "step": 2703872 + }, + { + "epoch": 2.01, + "learning_rate": 5.72118165862249e-06, + "loss": 3.8367, + "step": 2704384 + }, + { + "epoch": 2.01, + "learning_rate": 5.712795711111971e-06, + "loss": 3.8485, + "step": 2704896 + }, + { + "epoch": 2.01, + "learning_rate": 5.70440976360145e-06, + "loss": 3.8384, + "step": 2705408 + }, + { + "epoch": 2.01, + "learning_rate": 5.69602381609093e-06, + "loss": 3.8312, + "step": 2705920 + }, + { + "epoch": 2.01, + "learning_rate": 5.68763786858041e-06, + "loss": 3.8262, + "step": 2706432 + }, + { + "epoch": 2.01, + "learning_rate": 5.679268299873621e-06, + "loss": 3.8303, + "step": 2706944 + }, + { + "epoch": 2.01, + "learning_rate": 5.6708823523631016e-06, + "loss": 3.8494, + "step": 2707456 + }, + { + "epoch": 2.01, + "learning_rate": 5.6624964048525815e-06, + "loss": 3.8396, + "step": 2707968 + }, + { + "epoch": 2.01, + "learning_rate": 5.6541104573420615e-06, + "loss": 3.8399, + "step": 2708480 + }, + { + "epoch": 2.01, + "learning_rate": 5.6457245098315414e-06, + "loss": 3.8502, + "step": 2708992 + }, + { + "epoch": 2.01, + "learning_rate": 5.6373385623210205e-06, + "loss": 3.8482, + "step": 2709504 + }, + { + "epoch": 2.01, + "learning_rate": 5.628968993614232e-06, + "loss": 3.8296, + "step": 2710016 + }, + { + "epoch": 2.01, + "learning_rate": 5.620583046103712e-06, + "loss": 3.8367, + "step": 2710528 + }, + { + "epoch": 2.01, + "learning_rate": 5.612197098593192e-06, + "loss": 3.8467, + "step": 2711040 + }, + { + "epoch": 2.01, + "learning_rate": 5.603811151082672e-06, + "loss": 3.8276, + "step": 2711552 + }, + { + "epoch": 2.01, + "learning_rate": 5.595425203572152e-06, + "loss": 3.8424, + "step": 2712064 + }, + { + "epoch": 2.01, + "learning_rate": 5.587039256061632e-06, + "loss": 3.83, + "step": 2712576 + }, + { + "epoch": 2.01, + "learning_rate": 5.578653308551111e-06, + "loss": 3.8523, + "step": 2713088 + }, + { + "epoch": 2.01, + "learning_rate": 5.570283739844323e-06, + "loss": 3.8383, + "step": 2713600 + }, + { + "epoch": 2.01, + "learning_rate": 5.561897792333803e-06, + "loss": 3.8296, + "step": 2714112 + }, + { + "epoch": 2.01, + "learning_rate": 5.553511844823283e-06, + "loss": 3.83, + "step": 2714624 + }, + { + "epoch": 2.01, + "learning_rate": 5.545142276116494e-06, + "loss": 3.8417, + "step": 2715136 + }, + { + "epoch": 2.01, + "learning_rate": 5.536756328605974e-06, + "loss": 3.8486, + "step": 2715648 + }, + { + "epoch": 2.01, + "learning_rate": 5.528370381095454e-06, + "loss": 3.8406, + "step": 2716160 + }, + { + "epoch": 2.01, + "learning_rate": 5.519984433584934e-06, + "loss": 3.8347, + "step": 2716672 + }, + { + "epoch": 2.02, + "learning_rate": 5.511598486074414e-06, + "loss": 3.8329, + "step": 2717184 + }, + { + "epoch": 2.02, + "learning_rate": 5.503212538563893e-06, + "loss": 3.8425, + "step": 2717696 + }, + { + "epoch": 2.02, + "learning_rate": 5.494826591053374e-06, + "loss": 3.834, + "step": 2718208 + }, + { + "epoch": 2.02, + "learning_rate": 5.486440643542853e-06, + "loss": 3.8355, + "step": 2718720 + }, + { + "epoch": 2.02, + "learning_rate": 5.478054696032334e-06, + "loss": 3.8467, + "step": 2719232 + }, + { + "epoch": 2.02, + "learning_rate": 5.469685127325545e-06, + "loss": 3.8459, + "step": 2719744 + }, + { + "epoch": 2.02, + "learning_rate": 5.461299179815025e-06, + "loss": 3.843, + "step": 2720256 + }, + { + "epoch": 2.02, + "learning_rate": 5.452913232304505e-06, + "loss": 3.8264, + "step": 2720768 + }, + { + "epoch": 2.02, + "learning_rate": 5.444543663597715e-06, + "loss": 3.84, + "step": 2721280 + }, + { + "epoch": 2.02, + "learning_rate": 5.436157716087196e-06, + "loss": 3.834, + "step": 2721792 + }, + { + "epoch": 2.02, + "learning_rate": 5.427771768576675e-06, + "loss": 3.8411, + "step": 2722304 + }, + { + "epoch": 2.02, + "learning_rate": 5.419385821066156e-06, + "loss": 3.8411, + "step": 2722816 + }, + { + "epoch": 2.02, + "learning_rate": 5.410999873555635e-06, + "loss": 3.8311, + "step": 2723328 + }, + { + "epoch": 2.02, + "learning_rate": 5.402613926045115e-06, + "loss": 3.833, + "step": 2723840 + }, + { + "epoch": 2.02, + "learning_rate": 5.394227978534595e-06, + "loss": 3.8406, + "step": 2724352 + }, + { + "epoch": 2.02, + "learning_rate": 5.385858409827806e-06, + "loss": 3.8203, + "step": 2724864 + }, + { + "epoch": 2.02, + "learning_rate": 5.377472462317287e-06, + "loss": 3.8365, + "step": 2725376 + }, + { + "epoch": 2.02, + "learning_rate": 5.369086514806766e-06, + "loss": 3.8278, + "step": 2725888 + }, + { + "epoch": 2.02, + "learning_rate": 5.360700567296247e-06, + "loss": 3.8419, + "step": 2726400 + }, + { + "epoch": 2.02, + "learning_rate": 5.352314619785726e-06, + "loss": 3.8331, + "step": 2726912 + }, + { + "epoch": 2.02, + "learning_rate": 5.343945051078938e-06, + "loss": 3.8363, + "step": 2727424 + }, + { + "epoch": 2.02, + "learning_rate": 5.335559103568417e-06, + "loss": 3.8303, + "step": 2727936 + }, + { + "epoch": 2.02, + "learning_rate": 5.327173156057897e-06, + "loss": 3.8402, + "step": 2728448 + }, + { + "epoch": 2.02, + "learning_rate": 5.318787208547377e-06, + "loss": 3.8441, + "step": 2728960 + }, + { + "epoch": 2.02, + "learning_rate": 5.310401261036857e-06, + "loss": 3.8334, + "step": 2729472 + }, + { + "epoch": 2.02, + "learning_rate": 5.302015313526337e-06, + "loss": 3.8425, + "step": 2729984 + }, + { + "epoch": 2.02, + "learning_rate": 5.293629366015817e-06, + "loss": 3.8476, + "step": 2730496 + }, + { + "epoch": 2.02, + "learning_rate": 5.285243418505296e-06, + "loss": 3.8395, + "step": 2731008 + }, + { + "epoch": 2.02, + "learning_rate": 5.276873849798508e-06, + "loss": 3.843, + "step": 2731520 + }, + { + "epoch": 2.02, + "learning_rate": 5.268487902287988e-06, + "loss": 3.828, + "step": 2732032 + }, + { + "epoch": 2.02, + "learning_rate": 5.260101954777468e-06, + "loss": 3.8454, + "step": 2732544 + }, + { + "epoch": 2.02, + "learning_rate": 5.251716007266948e-06, + "loss": 3.833, + "step": 2733056 + }, + { + "epoch": 2.02, + "learning_rate": 5.243330059756428e-06, + "loss": 3.8427, + "step": 2733568 + }, + { + "epoch": 2.02, + "learning_rate": 5.234960491049639e-06, + "loss": 3.8335, + "step": 2734080 + }, + { + "epoch": 2.02, + "learning_rate": 5.226574543539119e-06, + "loss": 3.8416, + "step": 2734592 + }, + { + "epoch": 2.02, + "learning_rate": 5.21820497483233e-06, + "loss": 3.8376, + "step": 2735104 + }, + { + "epoch": 2.02, + "learning_rate": 5.209819027321811e-06, + "loss": 3.831, + "step": 2735616 + }, + { + "epoch": 2.02, + "learning_rate": 5.20143307981129e-06, + "loss": 3.8239, + "step": 2736128 + }, + { + "epoch": 2.02, + "learning_rate": 5.19304713230077e-06, + "loss": 3.8323, + "step": 2736640 + }, + { + "epoch": 2.02, + "learning_rate": 5.18466118479025e-06, + "loss": 3.8322, + "step": 2737152 + }, + { + "epoch": 2.02, + "learning_rate": 5.17627523727973e-06, + "loss": 3.8399, + "step": 2737664 + }, + { + "epoch": 2.02, + "learning_rate": 5.16788928976921e-06, + "loss": 3.8539, + "step": 2738176 + }, + { + "epoch": 2.02, + "learning_rate": 5.15950334225869e-06, + "loss": 3.8494, + "step": 2738688 + }, + { + "epoch": 2.02, + "learning_rate": 5.15111739474817e-06, + "loss": 3.8235, + "step": 2739200 + }, + { + "epoch": 2.02, + "learning_rate": 5.14273144723765e-06, + "loss": 3.85, + "step": 2739712 + }, + { + "epoch": 2.02, + "learning_rate": 5.13434549972713e-06, + "loss": 3.8387, + "step": 2740224 + }, + { + "epoch": 2.02, + "learning_rate": 5.125975931020341e-06, + "loss": 3.8391, + "step": 2740736 + }, + { + "epoch": 2.02, + "learning_rate": 5.11758998350982e-06, + "loss": 3.832, + "step": 2741248 + }, + { + "epoch": 2.02, + "learning_rate": 5.109204035999301e-06, + "loss": 3.8415, + "step": 2741760 + }, + { + "epoch": 2.02, + "learning_rate": 5.100834467292512e-06, + "loss": 3.833, + "step": 2742272 + }, + { + "epoch": 2.02, + "learning_rate": 5.092448519781992e-06, + "loss": 3.845, + "step": 2742784 + }, + { + "epoch": 2.02, + "learning_rate": 5.084062572271472e-06, + "loss": 3.8386, + "step": 2743296 + }, + { + "epoch": 2.02, + "learning_rate": 5.075676624760951e-06, + "loss": 3.8405, + "step": 2743808 + }, + { + "epoch": 2.02, + "learning_rate": 5.067290677250432e-06, + "loss": 3.8433, + "step": 2744320 + }, + { + "epoch": 2.02, + "learning_rate": 5.058904729739911e-06, + "loss": 3.8319, + "step": 2744832 + }, + { + "epoch": 2.02, + "learning_rate": 5.050518782229392e-06, + "loss": 3.8406, + "step": 2745344 + }, + { + "epoch": 2.02, + "learning_rate": 5.042132834718871e-06, + "loss": 3.8467, + "step": 2745856 + }, + { + "epoch": 2.02, + "learning_rate": 5.033746887208351e-06, + "loss": 3.8343, + "step": 2746368 + }, + { + "epoch": 2.02, + "learning_rate": 5.025377318501562e-06, + "loss": 3.8437, + "step": 2746880 + }, + { + "epoch": 2.02, + "learning_rate": 5.016991370991042e-06, + "loss": 3.8391, + "step": 2747392 + }, + { + "epoch": 2.03, + "eval_loss": 3.99332594871521, + "eval_runtime": 292.0783, + "eval_samples_per_second": 1306.468, + "eval_steps_per_second": 40.828, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.008605423480522e-06, + "loss": 3.8306, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.000219475970002e-06, + "loss": 3.8351, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.991833528459482e-06, + "loss": 3.8428, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.983447580948962e-06, + "loss": 3.8427, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.975061633438441e-06, + "loss": 3.8564, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.966675685927922e-06, + "loss": 3.8278, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.958289738417401e-06, + "loss": 3.8409, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.949903790906882e-06, + "loss": 3.8277, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.941517843396361e-06, + "loss": 3.8464, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.933131895885841e-06, + "loss": 3.8376, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.924745948375321e-06, + "loss": 3.8433, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.916360000864801e-06, + "loss": 3.8462, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.907990432158013e-06, + "loss": 3.8325, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.8996044846474926e-06, + "loss": 3.838, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.891218537136972e-06, + "loss": 3.8337, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.8828325896264525e-06, + "loss": 3.8288, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.8744466421159316e-06, + "loss": 3.8351, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.866060694605412e-06, + "loss": 3.838, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.8576747470948915e-06, + "loss": 3.8364, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.8492887995843714e-06, + "loss": 3.8535, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.840902852073851e-06, + "loss": 3.8548, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.832516904563331e-06, + "loss": 3.8436, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.824130957052811e-06, + "loss": 3.8423, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.815745009542291e-06, + "loss": 3.8471, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.807375440835503e-06, + "loss": 3.8312, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.798989493324983e-06, + "loss": 3.8478, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.7906199246181945e-06, + "loss": 3.8424, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.782233977107674e-06, + "loss": 3.8349, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.7738480295971536e-06, + "loss": 3.8345, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.7654620820866335e-06, + "loss": 3.8366, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.757092513379844e-06, + "loss": 3.8381, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.748706565869325e-06, + "loss": 3.8404, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.740336997162536e-06, + "loss": 3.8476, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.731951049652016e-06, + "loss": 3.8425, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.7235814809452275e-06, + "loss": 3.8458, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.7151955334347074e-06, + "loss": 3.8429, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.706809585924187e-06, + "loss": 3.823, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.698423638413667e-06, + "loss": 3.8398, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.690037690903147e-06, + "loss": 3.8265, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.681651743392626e-06, + "loss": 3.8331, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.673265795882107e-06, + "loss": 3.835, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.664879848371586e-06, + "loss": 3.847, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.656493900861067e-06, + "loss": 3.8383, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.648107953350546e-06, + "loss": 3.8288, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.639722005840026e-06, + "loss": 3.8488, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.631336058329506e-06, + "loss": 3.8395, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.622966489622718e-06, + "loss": 3.8423, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.614580542112198e-06, + "loss": 3.8394, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.606194594601678e-06, + "loss": 3.8268, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.597808647091158e-06, + "loss": 3.8495, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.589422699580638e-06, + "loss": 3.8345, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.581036752070117e-06, + "loss": 3.8403, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.5726508045595975e-06, + "loss": 3.8337, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.564264857049077e-06, + "loss": 3.8313, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.5558789095385574e-06, + "loss": 3.8316, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.5475257196355e-06, + "loss": 3.8377, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.53913977212498e-06, + "loss": 3.8378, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.53075382461446e-06, + "loss": 3.8397, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.52236787710394e-06, + "loss": 3.8439, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.51398192959342e-06, + "loss": 3.8308, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.505595982082899e-06, + "loss": 3.8265, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.49721003457238e-06, + "loss": 3.854, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.488824087061859e-06, + "loss": 3.8188, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4804381395513396e-06, + "loss": 3.8214, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.472052192040819e-06, + "loss": 3.8327, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.463666244530299e-06, + "loss": 3.8491, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.45529667582351e-06, + "loss": 3.8316, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.446910728312989e-06, + "loss": 3.8335, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.43852478080247e-06, + "loss": 3.823, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.430155212095681e-06, + "loss": 3.8302, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.421769264585161e-06, + "loss": 3.8418, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.413383317074641e-06, + "loss": 3.8387, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.404997369564122e-06, + "loss": 3.837, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.396611422053601e-06, + "loss": 3.8444, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.388225474543081e-06, + "loss": 3.8454, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.379855905836292e-06, + "loss": 3.8317, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3714699583257715e-06, + "loss": 3.834, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.363084010815252e-06, + "loss": 3.8455, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.354698063304731e-06, + "loss": 3.825, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.346312115794212e-06, + "loss": 3.8409, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.337926168283691e-06, + "loss": 3.8295, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.329540220773171e-06, + "loss": 3.8526, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.321154273262651e-06, + "loss": 3.8371, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.312768325752131e-06, + "loss": 3.8284, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.304398757045343e-06, + "loss": 3.8218, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.296012809534823e-06, + "loss": 3.8427, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.287626862024302e-06, + "loss": 3.8447, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.279240914513783e-06, + "loss": 3.8432, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.270854967003262e-06, + "loss": 3.8317, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.262469019492743e-06, + "loss": 3.8341, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.254099450785953e-06, + "loss": 3.8404, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.245713503275433e-06, + "loss": 3.8312, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.237327555764913e-06, + "loss": 3.8296, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.228941608254393e-06, + "loss": 3.8437, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.220572039547605e-06, + "loss": 3.8434, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.212186092037084e-06, + "loss": 3.8417, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.203816523330296e-06, + "loss": 3.828, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.195430575819776e-06, + "loss": 3.8367, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.1870446283092555e-06, + "loss": 3.8308, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.1786586807987355e-06, + "loss": 3.8406, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.1702727332882154e-06, + "loss": 3.8361, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.161886785777695e-06, + "loss": 3.8346, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.1535008382671745e-06, + "loss": 3.8286, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.145114890756655e-06, + "loss": 3.8337, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.136728943246134e-06, + "loss": 3.8282, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.128342995735615e-06, + "loss": 3.8305, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.119957048225094e-06, + "loss": 3.8258, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.111571100714574e-06, + "loss": 3.8419, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.103201532007786e-06, + "loss": 3.8334, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.094815584497266e-06, + "loss": 3.8313, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.086429636986746e-06, + "loss": 3.8266, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.078060068279957e-06, + "loss": 3.8403, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.0696741207694374e-06, + "loss": 3.8405, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.0612881732589165e-06, + "loss": 3.8298, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.052902225748397e-06, + "loss": 3.8419, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.044532657041608e-06, + "loss": 3.8462, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.036146709531088e-06, + "loss": 3.8391, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.027760762020568e-06, + "loss": 3.8403, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.019374814510048e-06, + "loss": 3.8267, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.010988866999528e-06, + "loss": 3.8398, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.002602919489008e-06, + "loss": 3.8375, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.994216971978488e-06, + "loss": 3.8433, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.985831024467968e-06, + "loss": 3.8247, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.9774614557611795e-06, + "loss": 3.8418, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.9690755082506586e-06, + "loss": 3.8361, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.96070593954387e-06, + "loss": 3.829, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.95231999203335e-06, + "loss": 3.8235, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.943934044522829e-06, + "loss": 3.8287, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.93554809701231e-06, + "loss": 3.8268, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.927178528305521e-06, + "loss": 3.8416, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.918792580795002e-06, + "loss": 3.8455, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.910406633284481e-06, + "loss": 3.8487, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.902020685773962e-06, + "loss": 3.8197, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.893634738263441e-06, + "loss": 3.8478, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.885248790752921e-06, + "loss": 3.8392, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.876879222046132e-06, + "loss": 3.834, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.868509653339344e-06, + "loss": 3.8292, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.860123705828823e-06, + "loss": 3.8456, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.851737758318303e-06, + "loss": 3.8336, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.843351810807783e-06, + "loss": 3.8407, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.834965863297263e-06, + "loss": 3.8314, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.826579915786743e-06, + "loss": 3.8389, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.818193968276223e-06, + "loss": 3.8408, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.8098080207657023e-06, + "loss": 3.8335, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.8014220732551827e-06, + "loss": 3.8374, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.793052504548394e-06, + "loss": 3.8448, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.784666557037874e-06, + "loss": 3.8324, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.776296988331085e-06, + "loss": 3.8375, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.7679110408205655e-06, + "loss": 3.8404, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.992769718170166, + "eval_runtime": 295.5746, + "eval_samples_per_second": 1291.014, + "eval_steps_per_second": 40.345, + "step": 2823840 + }, + { + "epoch": 1.0, + "learning_rate": 3.759525093310045e-06, + "loss": 3.8302, + "step": 2824192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7511391457995254e-06, + "loss": 3.8303, + "step": 2824704 + }, + { + "epoch": 1.0, + "learning_rate": 3.742753198289005e-06, + "loss": 3.8418, + "step": 2825216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7343672507784845e-06, + "loss": 3.8436, + "step": 2825728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725981303267965e-06, + "loss": 3.8487, + "step": 2826240 + }, + { + "epoch": 1.0, + "learning_rate": 3.7175953557574444e-06, + "loss": 3.8316, + "step": 2826752 + }, + { + "epoch": 1.0, + "learning_rate": 3.709225787050656e-06, + "loss": 3.8388, + "step": 2827264 + }, + { + "epoch": 1.0, + "learning_rate": 3.7008398395401355e-06, + "loss": 3.828, + "step": 2827776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6924538920296155e-06, + "loss": 3.8399, + "step": 2828288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6840679445190954e-06, + "loss": 3.8364, + "step": 2828800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6756819970085754e-06, + "loss": 3.8398, + "step": 2829312 + }, + { + "epoch": 1.0, + "learning_rate": 3.667312428301787e-06, + "loss": 3.8425, + "step": 2829824 + }, + { + "epoch": 1.0, + "learning_rate": 3.658942859594998e-06, + "loss": 3.8328, + "step": 2830336 + }, + { + "epoch": 1.0, + "learning_rate": 3.650556912084478e-06, + "loss": 3.832, + "step": 2830848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6421709645739577e-06, + "loss": 3.8319, + "step": 2831360 + }, + { + "epoch": 1.0, + "learning_rate": 3.633785017063438e-06, + "loss": 3.8252, + "step": 2831872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6253990695529177e-06, + "loss": 3.8312, + "step": 2832384 + }, + { + "epoch": 1.0, + "learning_rate": 3.617013122042397e-06, + "loss": 3.8351, + "step": 2832896 + }, + { + "epoch": 1.0, + "learning_rate": 3.608643553335609e-06, + "loss": 3.8361, + "step": 2833408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6002576058250888e-06, + "loss": 3.8524, + "step": 2833920 + }, + { + "epoch": 1.0, + "learning_rate": 3.591871658314569e-06, + "loss": 3.8514, + "step": 2834432 + }, + { + "epoch": 1.0, + "learning_rate": 3.5834857108040487e-06, + "loss": 3.8431, + "step": 2834944 + }, + { + "epoch": 1.0, + "learning_rate": 3.575099763293529e-06, + "loss": 3.8392, + "step": 2835456 + }, + { + "epoch": 1.0, + "learning_rate": 3.5667138157830086e-06, + "loss": 3.844, + "step": 2835968 + }, + { + "epoch": 1.0, + "learning_rate": 3.558327868272488e-06, + "loss": 3.8326, + "step": 2836480 + }, + { + "epoch": 1.0, + "learning_rate": 3.5499582995656998e-06, + "loss": 3.844, + "step": 2836992 + }, + { + "epoch": 1.0, + "learning_rate": 3.5415723520551793e-06, + "loss": 3.8385, + "step": 2837504 + }, + { + "epoch": 1.0, + "learning_rate": 3.5331864045446597e-06, + "loss": 3.8292, + "step": 2838016 + }, + { + "epoch": 1.0, + "learning_rate": 3.5248004570341392e-06, + "loss": 3.8328, + "step": 2838528 + }, + { + "epoch": 1.0, + "learning_rate": 3.5164145095236196e-06, + "loss": 3.8372, + "step": 2839040 + }, + { + "epoch": 1.01, + "learning_rate": 3.508028562013099e-06, + "loss": 3.8353, + "step": 2839552 + }, + { + "epoch": 1.01, + "learning_rate": 3.499642614502579e-06, + "loss": 3.8391, + "step": 2840064 + }, + { + "epoch": 1.01, + "learning_rate": 3.491256666992059e-06, + "loss": 3.8481, + "step": 2840576 + }, + { + "epoch": 1.01, + "learning_rate": 3.4828870982852703e-06, + "loss": 3.8401, + "step": 2841088 + }, + { + "epoch": 1.01, + "learning_rate": 3.474533908382213e-06, + "loss": 3.8417, + "step": 2841600 + }, + { + "epoch": 1.01, + "learning_rate": 3.4661479608716935e-06, + "loss": 3.8432, + "step": 2842112 + }, + { + "epoch": 1.01, + "learning_rate": 3.457762013361173e-06, + "loss": 3.8272, + "step": 2842624 + }, + { + "epoch": 1.01, + "learning_rate": 3.4493760658506526e-06, + "loss": 3.8301, + "step": 2843136 + }, + { + "epoch": 1.01, + "learning_rate": 3.440990118340133e-06, + "loss": 3.8263, + "step": 2843648 + }, + { + "epoch": 1.01, + "learning_rate": 3.4326041708296125e-06, + "loss": 3.8315, + "step": 2844160 + }, + { + "epoch": 1.01, + "learning_rate": 3.424218223319093e-06, + "loss": 3.8331, + "step": 2844672 + }, + { + "epoch": 1.01, + "learning_rate": 3.4158322758085724e-06, + "loss": 3.8459, + "step": 2845184 + }, + { + "epoch": 1.01, + "learning_rate": 3.4074463282980524e-06, + "loss": 3.8379, + "step": 2845696 + }, + { + "epoch": 1.01, + "learning_rate": 3.3990603807875323e-06, + "loss": 3.8274, + "step": 2846208 + }, + { + "epoch": 1.01, + "learning_rate": 3.3906744332770123e-06, + "loss": 3.8491, + "step": 2846720 + }, + { + "epoch": 1.01, + "learning_rate": 3.3822884857664922e-06, + "loss": 3.832, + "step": 2847232 + }, + { + "epoch": 1.01, + "learning_rate": 3.373902538255972e-06, + "loss": 3.845, + "step": 2847744 + }, + { + "epoch": 1.01, + "learning_rate": 3.3655165907454517e-06, + "loss": 3.8356, + "step": 2848256 + }, + { + "epoch": 1.01, + "learning_rate": 3.3571470220386634e-06, + "loss": 3.8251, + "step": 2848768 + }, + { + "epoch": 1.01, + "learning_rate": 3.348761074528143e-06, + "loss": 3.8445, + "step": 2849280 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403915058213545e-06, + "loss": 3.8342, + "step": 2849792 + }, + { + "epoch": 1.01, + "learning_rate": 3.332005558310834e-06, + "loss": 3.8411, + "step": 2850304 + }, + { + "epoch": 1.01, + "learning_rate": 3.3236196108003144e-06, + "loss": 3.8268, + "step": 2850816 + }, + { + "epoch": 1.01, + "learning_rate": 3.315233663289794e-06, + "loss": 3.8314, + "step": 2851328 + }, + { + "epoch": 1.01, + "learning_rate": 3.3068477157792744e-06, + "loss": 3.8284, + "step": 2851840 + }, + { + "epoch": 1.01, + "learning_rate": 3.298461768268754e-06, + "loss": 3.8349, + "step": 2852352 + }, + { + "epoch": 1.01, + "learning_rate": 3.290092199561966e-06, + "loss": 3.8395, + "step": 2852864 + }, + { + "epoch": 1.01, + "learning_rate": 3.2817062520514455e-06, + "loss": 3.8316, + "step": 2853376 + }, + { + "epoch": 1.01, + "learning_rate": 3.273320304540925e-06, + "loss": 3.843, + "step": 2853888 + }, + { + "epoch": 1.01, + "learning_rate": 3.2649343570304054e-06, + "loss": 3.832, + "step": 2854400 + }, + { + "epoch": 1.01, + "learning_rate": 3.256548409519885e-06, + "loss": 3.8236, + "step": 2854912 + }, + { + "epoch": 1.01, + "learning_rate": 3.2481624620093653e-06, + "loss": 3.8528, + "step": 2855424 + }, + { + "epoch": 1.01, + "learning_rate": 3.239776514498845e-06, + "loss": 3.8165, + "step": 2855936 + }, + { + "epoch": 1.01, + "learning_rate": 3.2313905669883244e-06, + "loss": 3.816, + "step": 2856448 + }, + { + "epoch": 1.01, + "learning_rate": 3.2230046194778047e-06, + "loss": 3.8341, + "step": 2856960 + }, + { + "epoch": 1.01, + "learning_rate": 3.2146186719672843e-06, + "loss": 3.8481, + "step": 2857472 + }, + { + "epoch": 1.01, + "learning_rate": 3.2062327244567647e-06, + "loss": 3.8253, + "step": 2857984 + }, + { + "epoch": 1.01, + "learning_rate": 3.197846776946244e-06, + "loss": 3.8339, + "step": 2858496 + }, + { + "epoch": 1.01, + "learning_rate": 3.1894935870431875e-06, + "loss": 3.8196, + "step": 2859008 + }, + { + "epoch": 1.01, + "learning_rate": 3.181107639532667e-06, + "loss": 3.8282, + "step": 2859520 + }, + { + "epoch": 1.01, + "learning_rate": 3.1727216920221474e-06, + "loss": 3.8411, + "step": 2860032 + }, + { + "epoch": 1.01, + "learning_rate": 3.164352123315358e-06, + "loss": 3.8373, + "step": 2860544 + }, + { + "epoch": 1.01, + "learning_rate": 3.1559661758048386e-06, + "loss": 3.8352, + "step": 2861056 + }, + { + "epoch": 1.01, + "learning_rate": 3.147580228294318e-06, + "loss": 3.8394, + "step": 2861568 + }, + { + "epoch": 1.01, + "learning_rate": 3.1391942807837977e-06, + "loss": 3.8471, + "step": 2862080 + }, + { + "epoch": 1.01, + "learning_rate": 3.130808333273278e-06, + "loss": 3.8257, + "step": 2862592 + }, + { + "epoch": 1.01, + "learning_rate": 3.1224223857627576e-06, + "loss": 3.8347, + "step": 2863104 + }, + { + "epoch": 1.01, + "learning_rate": 3.1140364382522375e-06, + "loss": 3.8403, + "step": 2863616 + }, + { + "epoch": 1.01, + "learning_rate": 3.1056504907417175e-06, + "loss": 3.8248, + "step": 2864128 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972645432311974e-06, + "loss": 3.8354, + "step": 2864640 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888785957206774e-06, + "loss": 3.833, + "step": 2865152 + }, + { + "epoch": 1.01, + "learning_rate": 3.080509027013889e-06, + "loss": 3.8442, + "step": 2865664 + }, + { + "epoch": 1.01, + "learning_rate": 3.0721230795033686e-06, + "loss": 3.8382, + "step": 2866176 + }, + { + "epoch": 1.01, + "learning_rate": 3.0637371319928485e-06, + "loss": 3.8284, + "step": 2866688 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553511844823285e-06, + "loss": 3.8217, + "step": 2867200 + }, + { + "epoch": 1.01, + "learning_rate": 3.0469652369718084e-06, + "loss": 3.8382, + "step": 2867712 + }, + { + "epoch": 1.01, + "learning_rate": 3.0385792894612884e-06, + "loss": 3.8397, + "step": 2868224 + }, + { + "epoch": 1.01, + "learning_rate": 3.030193341950768e-06, + "loss": 3.8364, + "step": 2868736 + }, + { + "epoch": 1.01, + "learning_rate": 3.021840152047711e-06, + "loss": 3.8343, + "step": 2869248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134542045371908e-06, + "loss": 3.8318, + "step": 2869760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050682570266707e-06, + "loss": 3.8366, + "step": 2870272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9966823095161507e-06, + "loss": 3.8287, + "step": 2870784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9883127408093623e-06, + "loss": 3.8266, + "step": 2871296 + }, + { + "epoch": 1.02, + "learning_rate": 2.979926793298842e-06, + "loss": 3.8457, + "step": 2871808 + }, + { + "epoch": 1.02, + "learning_rate": 2.971540845788322e-06, + "loss": 3.8398, + "step": 2872320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9631548982778018e-06, + "loss": 3.8374, + "step": 2872832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9547689507672817e-06, + "loss": 3.826, + "step": 2873344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9463830032567612e-06, + "loss": 3.8367, + "step": 2873856 + }, + { + "epoch": 1.02, + "learning_rate": 2.937997055746241e-06, + "loss": 3.8262, + "step": 2874368 + }, + { + "epoch": 1.02, + "learning_rate": 2.929611108235721e-06, + "loss": 3.8382, + "step": 2874880 + }, + { + "epoch": 1.02, + "learning_rate": 2.921225160725201e-06, + "loss": 3.8354, + "step": 2875392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128555920184123e-06, + "loss": 3.8332, + "step": 2875904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044696445078923e-06, + "loss": 3.8279, + "step": 2876416 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960836969973727e-06, + "loss": 3.8252, + "step": 2876928 + }, + { + "epoch": 1.02, + "learning_rate": 2.887697749486852e-06, + "loss": 3.8317, + "step": 2877440 + }, + { + "epoch": 1.02, + "learning_rate": 2.879311801976332e-06, + "loss": 3.8251, + "step": 2877952 + }, + { + "epoch": 1.02, + "learning_rate": 2.8709422332695434e-06, + "loss": 3.825, + "step": 2878464 + }, + { + "epoch": 1.02, + "learning_rate": 2.8625562857590233e-06, + "loss": 3.8359, + "step": 2878976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8541867170522345e-06, + "loss": 3.8342, + "step": 2879488 + }, + { + "epoch": 1.02, + "learning_rate": 2.845817148345446e-06, + "loss": 3.8282, + "step": 2880000 + }, + { + "epoch": 1.02, + "learning_rate": 2.8374312008349257e-06, + "loss": 3.8242, + "step": 2880512 + }, + { + "epoch": 1.02, + "learning_rate": 2.8290452533244057e-06, + "loss": 3.8354, + "step": 2881024 + }, + { + "epoch": 1.02, + "learning_rate": 2.8206593058138856e-06, + "loss": 3.8397, + "step": 2881536 + }, + { + "epoch": 1.02, + "learning_rate": 2.812273358303366e-06, + "loss": 3.8303, + "step": 2882048 + }, + { + "epoch": 1.02, + "learning_rate": 2.803887410792846e-06, + "loss": 3.8402, + "step": 2882560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7955014632823255e-06, + "loss": 3.8397, + "step": 2883072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7871155157718054e-06, + "loss": 3.8381, + "step": 2883584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787295682612854e-06, + "loss": 3.8347, + "step": 2884096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703599995544966e-06, + "loss": 3.8273, + "step": 2884608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619740520439766e-06, + "loss": 3.8338, + "step": 2885120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535881045334565e-06, + "loss": 3.8356, + "step": 2885632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7452021570229365e-06, + "loss": 3.8398, + "step": 2886144 + }, + { + "epoch": 1.02, + "learning_rate": 2.736816209512416e-06, + "loss": 3.8255, + "step": 2886656 + }, + { + "epoch": 1.02, + "learning_rate": 2.728430262001896e-06, + "loss": 3.8388, + "step": 2887168 + }, + { + "epoch": 1.02, + "learning_rate": 2.720044314491376e-06, + "loss": 3.8354, + "step": 2887680 + }, + { + "epoch": 1.02, + "learning_rate": 2.711658366980856e-06, + "loss": 3.8276, + "step": 2888192 + }, + { + "epoch": 1.02, + "learning_rate": 2.703272419470336e-06, + "loss": 3.8194, + "step": 2888704 + }, + { + "epoch": 1.02, + "learning_rate": 2.6949028507635475e-06, + "loss": 3.83, + "step": 2889216 + }, + { + "epoch": 1.02, + "learning_rate": 2.6865169032530274e-06, + "loss": 3.8245, + "step": 2889728 + }, + { + "epoch": 1.02, + "learning_rate": 2.678130955742507e-06, + "loss": 3.8391, + "step": 2890240 + }, + { + "epoch": 1.02, + "learning_rate": 2.669745008231987e-06, + "loss": 3.8421, + "step": 2890752 + }, + { + "epoch": 1.02, + "learning_rate": 2.661359060721467e-06, + "loss": 3.8496, + "step": 2891264 + }, + { + "epoch": 1.02, + "learning_rate": 2.652989492014678e-06, + "loss": 3.8187, + "step": 2891776 + }, + { + "epoch": 1.02, + "learning_rate": 2.644603544504158e-06, + "loss": 3.8447, + "step": 2892288 + }, + { + "epoch": 1.02, + "learning_rate": 2.636217596993638e-06, + "loss": 3.8379, + "step": 2892800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278316494831175e-06, + "loss": 3.8316, + "step": 2893312 + }, + { + "epoch": 1.02, + "learning_rate": 2.619462080776329e-06, + "loss": 3.828, + "step": 2893824 + }, + { + "epoch": 1.02, + "learning_rate": 2.611076133265809e-06, + "loss": 3.8437, + "step": 2894336 + }, + { + "epoch": 1.02, + "learning_rate": 2.602690185755289e-06, + "loss": 3.8281, + "step": 2894848 + }, + { + "epoch": 1.02, + "learning_rate": 2.594304238244769e-06, + "loss": 3.8417, + "step": 2895360 + }, + { + "epoch": 1.02, + "learning_rate": 2.585918290734249e-06, + "loss": 3.829, + "step": 2895872 + }, + { + "epoch": 1.02, + "learning_rate": 2.57754872202746e-06, + "loss": 3.8395, + "step": 2896384 + }, + { + "epoch": 1.02, + "learning_rate": 2.56916277451694e-06, + "loss": 3.8359, + "step": 2896896 + }, + { + "epoch": 1.02, + "learning_rate": 2.56077682700642e-06, + "loss": 3.8312, + "step": 2897408 + }, + { + "epoch": 1.02, + "learning_rate": 2.5523908794958996e-06, + "loss": 3.8392, + "step": 2897920 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440049319853796e-06, + "loss": 3.8358, + "step": 2898432 + }, + { + "epoch": 1.02, + "learning_rate": 2.535635363278591e-06, + "loss": 3.8382, + "step": 2898944 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272494157680708e-06, + "loss": 3.8285, + "step": 2899456 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188634682575507e-06, + "loss": 3.8431, + "step": 2899968 + }, + { + "epoch": 1.03, + "eval_loss": 3.99228835105896, + "eval_runtime": 294.8725, + "eval_samples_per_second": 1294.088, + "eval_steps_per_second": 40.441, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1612628733695414e+18, + "trial_name": null, + "trial_params": null +}