diff --git "a/checkpoint-2671200/trainer_state.json" "b/checkpoint-2671200/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2671200/trainer_state.json" @@ -0,0 +1,31607 @@ +{ + "best_metric": 3.974538803100586, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/4/checkpoints/checkpoint-2671200", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2671200, + "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": 10.8187, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5522, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0634, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9974, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9525, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9269, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7716, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6558, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5453, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4658, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4051, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3491, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.287, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2231, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1728, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.1052, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0722, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 6.0118, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9669, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9341, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.897, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8582, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8299, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7953, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7755, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7404, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7204, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6887, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6644, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6469, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6267, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6106, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5907, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.572, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5566, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5407, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5248, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.497, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4919, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4535, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4539, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4425, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4403, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4025, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4035, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3934, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3848, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3823, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3474, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3424, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3471, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3361, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3166, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2969, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3018, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2818, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.3038, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2514, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2628, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2509, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2479, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2452, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2212, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.2047, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.94634467685603e-05, + "loss": 5.2098, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945506082104978e-05, + "loss": 5.2197, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.9446674873539255e-05, + "loss": 5.1907, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1897, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1669, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1658, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1788, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1755, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1491, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1609, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1598, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1485, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1175, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1253, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.114, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1078, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.106, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932093479729265e-05, + "loss": 5.1015, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.1019, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0886, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 5.0734, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 5.0737, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 5.0752, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 5.0642, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 5.0612, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 5.0453, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 5.0464, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 5.0349, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.043, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0319, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.0293, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0271, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.0143, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0097, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 5.001, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9966, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.9992, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9826, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9867, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9828, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9696, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9656, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9613, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9596, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9504, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9535, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9453, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.933, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9456, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9278, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.933, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9274, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.92, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.9164, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.9125, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.927, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.9138, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.8973, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8924, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8899, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8846, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8783, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8825, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8674, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8677, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8618, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8809, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8753, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.8555, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.855, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8488, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8583, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8501, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8486, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8435, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8399, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.834, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8246, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8321, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8209, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.8104, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8215, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8174, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.8166, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.8069, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.8017, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.766572952270508, + "eval_runtime": 290.7547, + "eval_samples_per_second": 1312.416, + "eval_steps_per_second": 41.014, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.7981, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.7938, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.8075, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.7924, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.7962, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.7784, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.7933, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7744, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675478899842306e-05, + "loss": 4.7754, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667092952331785e-05, + "loss": 4.774, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865870700482127e-05, + "loss": 4.7815, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865032105731075e-05, + "loss": 4.7755, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7574, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7606, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.753, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.7526, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.7569, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.7486, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.7505, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.7613, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7469, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.7456, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.7377, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7527, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.7219, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.7349, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.7221, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.7251, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.7194, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.7133, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.7194, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.7257, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.7145, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.7196, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.7052, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.7121, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.6979, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.7058, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.6834, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.6953, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.6899, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.7026, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6743, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6926, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6876, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.6801, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.6908, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6658, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.667, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.6839, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6708, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.6663, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.6616, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6652, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.6544, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.6748, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6422, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6537, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6511, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6514, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6579, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6462, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6267, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.6337, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6572, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6321, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.6319, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180888163562664e-05, + "loss": 4.6257, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.6259, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6413, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.6395, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.6262, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.81389748048138e-05, + "loss": 4.6379, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813058885730328e-05, + "loss": 4.6422, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812220290979276e-05, + "loss": 4.6377, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.6099, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6261, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.616, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.6182, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.6139, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.6156, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806351765602285e-05, + "loss": 4.6241, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805513170851233e-05, + "loss": 4.6137, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804674576100181e-05, + "loss": 4.5996, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803835981349129e-05, + "loss": 4.6036, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.6055, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.6093, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013218349763464e-05, + "loss": 4.6084, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.5935, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996446454742424e-05, + "loss": 4.6019, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.79880605072319e-05, + "loss": 4.5858, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797969093852511e-05, + "loss": 4.6014, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797130499101459e-05, + "loss": 4.5969, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.5927, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.5976, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946147148483026e-05, + "loss": 4.5891, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793777757977624e-05, + "loss": 4.5853, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792939163226572e-05, + "loss": 4.5853, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.79210056847552e-05, + "loss": 4.5867, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.583, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.5745, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789586422102737e-05, + "loss": 4.5793, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788747827351685e-05, + "loss": 4.5812, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787909232600633e-05, + "loss": 4.5771, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787070637849581e-05, + "loss": 4.5631, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786233680978902e-05, + "loss": 4.5741, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.78539508622785e-05, + "loss": 4.5729, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784556491476798e-05, + "loss": 4.5663, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783717896725746e-05, + "loss": 4.5658, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5661, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.5523, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812037503529635e-05, + "loss": 4.5744, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803651556019115e-05, + "loss": 4.5602, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795265608508595e-05, + "loss": 4.5631, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786879660998075e-05, + "loss": 4.5594, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778493713487555e-05, + "loss": 4.5651, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770107765977035e-05, + "loss": 4.5554, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761721818466515e-05, + "loss": 4.5586, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.5672, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744949923445475e-05, + "loss": 4.5608, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736563975934955e-05, + "loss": 4.5495, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772821078603189e-05, + "loss": 4.5482, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771982483852137e-05, + "loss": 4.5431, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771143889101086e-05, + "loss": 4.541, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770305294350034e-05, + "loss": 4.5454, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5413, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.5344, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5362, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5348, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5506, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5528, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5382, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.5289, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762761217351312e-05, + "loss": 4.5352, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.76192262260026e-05, + "loss": 4.5403, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761084027849208e-05, + "loss": 4.5391, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760245433098156e-05, + "loss": 4.5334, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759406838347104e-05, + "loss": 4.5376, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5279, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757731286725373e-05, + "loss": 4.5293, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568926919743206e-05, + "loss": 4.5246, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560540972232686e-05, + "loss": 4.5308, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552155024722166e-05, + "loss": 4.5216, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543769077211646e-05, + "loss": 4.5172, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535383129701126e-05, + "loss": 4.5251, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527013560994335e-05, + "loss": 4.5257, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518627613483815e-05, + "loss": 4.5258, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.5154, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5163, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.484960556030273, + "eval_runtime": 290.9399, + "eval_samples_per_second": 1311.58, + "eval_steps_per_second": 40.988, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749346977095226e-05, + "loss": 4.5109, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748508382344174e-05, + "loss": 4.51, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747669787593122e-05, + "loss": 4.5243, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.5131, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5191, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.502, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.5161, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743476813837862e-05, + "loss": 4.5015, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426382190868095e-05, + "loss": 4.5092, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417996243357575e-05, + "loss": 4.5047, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409610295847055e-05, + "loss": 4.5153, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401224348336535e-05, + "loss": 4.5089, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739285477962975e-05, + "loss": 4.4924, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738446883211923e-05, + "loss": 4.5011, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737608288460871e-05, + "loss": 4.4921, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736769693709819e-05, + "loss": 4.4968, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735931098958767e-05, + "loss": 4.4966, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735092504207715e-05, + "loss": 4.4901, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734253909456663e-05, + "loss": 4.4944, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733415314705611e-05, + "loss": 4.5114, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.4977, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.4933, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.4932, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730062573581776e-05, + "loss": 4.5016, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4757, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.4869, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.4847, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.481, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258712377068895e-05, + "loss": 4.4758, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4731, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4847, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4896, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225184965830544e-05, + "loss": 4.4804, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4823, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4737, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720004350210271e-05, + "loss": 4.4767, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4642, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4819, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717488565957115e-05, + "loss": 4.4553, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716649971206063e-05, + "loss": 4.4693, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715813014335385e-05, + "loss": 4.4633, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714974419584333e-05, + "loss": 4.4785, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714135824833281e-05, + "loss": 4.4542, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713297230082228e-05, + "loss": 4.4661, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712458635331176e-05, + "loss": 4.4685, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711620040580124e-05, + "loss": 4.4606, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710783083709446e-05, + "loss": 4.4703, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4506, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4492, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4691, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4547, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4537, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.4497, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049145583324546e-05, + "loss": 4.4572, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040759635814026e-05, + "loss": 4.4427, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032390067107235e-05, + "loss": 4.462, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.434, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4481, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4507, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998846277065155e-05, + "loss": 4.4435, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990460329554635e-05, + "loss": 4.4509, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982074382044115e-05, + "loss": 4.448, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973688434533595e-05, + "loss": 4.4235, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965318865826804e-05, + "loss": 4.4366, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695693291831629e-05, + "loss": 4.4476, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694854697080577e-05, + "loss": 4.4376, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694016102329525e-05, + "loss": 4.4388, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693177507578473e-05, + "loss": 4.4235, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692338912827421e-05, + "loss": 4.4292, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691501955956742e-05, + "loss": 4.4477, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.69066336120569e-05, + "loss": 4.4444, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689824766454638e-05, + "loss": 4.4295, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4457, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688149214832907e-05, + "loss": 4.4494, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687310620081855e-05, + "loss": 4.4501, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686472025330803e-05, + "loss": 4.4163, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685633430579751e-05, + "loss": 4.4365, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684794835828699e-05, + "loss": 4.4286, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683956241077647e-05, + "loss": 4.4259, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683117646326595e-05, + "loss": 4.4307, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682279051575543e-05, + "loss": 4.4296, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681440456824491e-05, + "loss": 4.4341, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680603499953812e-05, + "loss": 4.434, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.67976490520276e-05, + "loss": 4.4117, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678926310451708e-05, + "loss": 4.4232, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678087715700656e-05, + "loss": 4.4213, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677249120949604e-05, + "loss": 4.4267, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676410526198552e-05, + "loss": 4.4291, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755735693278726e-05, + "loss": 4.4128, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747349745768206e-05, + "loss": 4.4204, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673896379825769e-05, + "loss": 4.4095, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673057785074717e-05, + "loss": 4.4224, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672219190323665e-05, + "loss": 4.4174, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671380595572613e-05, + "loss": 4.4142, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670543638701934e-05, + "loss": 4.4216, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669705043950882e-05, + "loss": 4.4182, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.66886644919983e-05, + "loss": 4.4091, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668027854448778e-05, + "loss": 4.4145, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667190897578099e-05, + "loss": 4.4154, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666352302827047e-05, + "loss": 4.4137, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665513708075995e-05, + "loss": 4.3994, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664675113324943e-05, + "loss": 4.4087, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663838156454265e-05, + "loss": 4.4129, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.662999561703213e-05, + "loss": 4.4094, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662160966952161e-05, + "loss": 4.3894, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661322372201109e-05, + "loss": 4.4042, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604837774500567e-05, + "loss": 4.4077, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596451826990047e-05, + "loss": 4.4002, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588065879479526e-05, + "loss": 4.3987, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579679931969006e-05, + "loss": 4.401, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571310363262216e-05, + "loss": 4.3906, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562940794555425e-05, + "loss": 4.4093, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554554847044905e-05, + "loss": 4.3929, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546168899534385e-05, + "loss": 4.4016, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537782952023865e-05, + "loss": 4.4004, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529397004513344e-05, + "loss": 4.4027, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652102743580656e-05, + "loss": 4.3917, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651264148829604e-05, + "loss": 4.4023, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650425554078552e-05, + "loss": 4.4056, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6495869593275e-05, + "loss": 4.4004, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648748364576447e-05, + "loss": 4.3871, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647909769825395e-05, + "loss": 4.3908, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647071175074343e-05, + "loss": 4.3848, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646234218203665e-05, + "loss": 4.3899, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645395623452612e-05, + "loss": 4.3862, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.64455702870156e-05, + "loss": 4.3902, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643718433950508e-05, + "loss": 4.3766, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.64288147707983e-05, + "loss": 4.3825, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642042882328778e-05, + "loss": 4.3778, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641204287577726e-05, + "loss": 4.3966, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640365692826674e-05, + "loss": 4.3982, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639528735955995e-05, + "loss": 4.3886, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638690141204943e-05, + "loss": 4.3749, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.383, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637014589583212e-05, + "loss": 4.391, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361759948321596e-05, + "loss": 4.3869, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353374000811076e-05, + "loss": 4.3835, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6344988053300556e-05, + "loss": 4.3862, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336602105790036e-05, + "loss": 4.3808, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632821615827952e-05, + "loss": 4.3862, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319830210769e-05, + "loss": 4.3703, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631144426325848e-05, + "loss": 4.3854, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630305831574796e-05, + "loss": 4.3749, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629467236823744e-05, + "loss": 4.3687, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628630279953065e-05, + "loss": 4.3784, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627791685202013e-05, + "loss": 4.3834, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626953090450961e-05, + "loss": 4.3761, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626116133580282e-05, + "loss": 4.3713, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.62527753882923e-05, + "loss": 4.3691, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.348117828369141, + "eval_runtime": 295.2315, + "eval_samples_per_second": 1292.515, + "eval_steps_per_second": 40.392, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624440581958551e-05, + "loss": 4.3776, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623601987207499e-05, + "loss": 4.3637, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227633924564476e-05, + "loss": 4.3821, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219247977053956e-05, + "loss": 4.3665, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210862029543436e-05, + "loss": 4.3816, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202476082032916e-05, + "loss": 4.359, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194106513326125e-05, + "loss": 4.3762, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185720565815605e-05, + "loss": 4.3596, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177334618305085e-05, + "loss": 4.3721, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168948670794565e-05, + "loss": 4.3673, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160562723284045e-05, + "loss": 4.3689, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152176775773525e-05, + "loss": 4.3748, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143807207066734e-05, + "loss": 4.3537, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135421259556214e-05, + "loss": 4.3644, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127035312045694e-05, + "loss": 4.3567, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118649364535174e-05, + "loss": 4.362, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110263417024654e-05, + "loss": 4.3593, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610189384831787e-05, + "loss": 4.3563, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609350790080735e-05, + "loss": 4.3597, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608512195329683e-05, + "loss": 4.376, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607673600578631e-05, + "loss": 4.3604, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606835005827578e-05, + "loss": 4.3609, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605996411076526e-05, + "loss": 4.362, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605157816325474e-05, + "loss": 4.3668, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604319221574422e-05, + "loss": 4.3459, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603482264703743e-05, + "loss": 4.3618, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602643669952691e-05, + "loss": 4.3484, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601805075201639e-05, + "loss": 4.348, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600966480450588e-05, + "loss": 4.3446, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600127885699536e-05, + "loss": 4.3491, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599290928828857e-05, + "loss": 4.3499, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598452334077805e-05, + "loss": 4.3615, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597613739326753e-05, + "loss": 4.3528, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596775144575701e-05, + "loss": 4.3539, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595939825585395e-05, + "loss": 4.3428, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595101230834343e-05, + "loss": 4.3536, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942626360832906e-05, + "loss": 4.3351, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934240413322386e-05, + "loss": 4.3566, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925854465811865e-05, + "loss": 4.3281, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917468518301345e-05, + "loss": 4.3407, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590908257079083e-05, + "loss": 4.3398, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590069662328031e-05, + "loss": 4.3538, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589231067576979e-05, + "loss": 4.3339, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.3403, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587555515955248e-05, + "loss": 4.3426, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586716921204196e-05, + "loss": 4.34, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585878326453144e-05, + "loss": 4.3484, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585039731702092e-05, + "loss": 4.331, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58420113695104e-05, + "loss": 4.3238, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583362542199988e-05, + "loss": 4.3457, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582525585329309e-05, + "loss": 4.3349, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581686990578257e-05, + "loss": 4.3316, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808500337075786e-05, + "loss": 4.3314, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.3344, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791728442054746e-05, + "loss": 4.3197, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783342494544226e-05, + "loss": 4.3426, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774956547033706e-05, + "loss": 4.3151, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766570599523186e-05, + "loss": 4.3294, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758184652012666e-05, + "loss": 4.3281, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749798704502146e-05, + "loss": 4.3328, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574141275699162e-05, + "loss": 4.328, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.57330268094811e-05, + "loss": 4.3325, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572464086197058e-05, + "loss": 4.306, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571625491446006e-05, + "loss": 4.3256, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707901724557004e-05, + "loss": 4.3296, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569953215585022e-05, + "loss": 4.3252, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56911462083397e-05, + "loss": 4.3159, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568276026082918e-05, + "loss": 4.3166, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.3126, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.3273, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565760241829762e-05, + "loss": 4.3336, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564921647078709e-05, + "loss": 4.3173, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564083052327657e-05, + "loss": 4.332, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563244457576605e-05, + "loss": 4.3351, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562405862825553e-05, + "loss": 4.3405, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561567268074501e-05, + "loss": 4.3024, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560728673323449e-05, + "loss": 4.3212, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559891716452771e-05, + "loss": 4.3222, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559054759582092e-05, + "loss": 4.3118, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.55821616483104e-05, + "loss": 4.321, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557377570079988e-05, + "loss": 4.3211, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556538975328936e-05, + "loss": 4.327, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555700380577884e-05, + "loss": 4.3172, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554861785826832e-05, + "loss": 4.308, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540248289561526e-05, + "loss": 4.3122, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5531862342051006e-05, + "loss": 4.3102, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523476394540486e-05, + "loss": 4.318, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515090447029966e-05, + "loss": 4.3209, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.3039, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.3112, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.3012, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.3127, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.3124, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546480751957431e-05, + "loss": 4.3062, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545642157206379e-05, + "loss": 4.3168, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544803562455327e-05, + "loss": 4.3122, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543964967704275e-05, + "loss": 4.3047, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543126372953223e-05, + "loss": 4.3069, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542287778202171e-05, + "loss": 4.3106, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541449183451119e-05, + "loss": 4.3121, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540610588700067e-05, + "loss": 4.2941, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539775269709761e-05, + "loss": 4.3031, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389366749587095e-05, + "loss": 4.3085, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380980802076575e-05, + "loss": 4.3094, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372594854566055e-05, + "loss": 4.2897, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364225285859264e-05, + "loss": 4.295, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355839338348744e-05, + "loss": 4.3068, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347453390838224e-05, + "loss": 4.2999, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339067443327704e-05, + "loss": 4.2955, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330681495817184e-05, + "loss": 4.2958, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322295548306664e-05, + "loss": 4.2965, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5313909600796144e-05, + "loss": 4.3009, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305523653285624e-05, + "loss": 4.2952, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529715408457883e-05, + "loss": 4.2943, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528878451587205e-05, + "loss": 4.3011, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528039856836153e-05, + "loss": 4.3041, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527201262085101e-05, + "loss": 4.3021, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526362667334049e-05, + "loss": 4.2942, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525524072582997e-05, + "loss": 4.3072, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524685477831945e-05, + "loss": 4.3016, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523846883080893e-05, + "loss": 4.2871, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52300828832984e-05, + "loss": 4.2933, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.288, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.52133273670811e-05, + "loss": 4.2943, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520495779837431e-05, + "loss": 4.2862, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519657185086379e-05, + "loss": 4.2966, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518818590335327e-05, + "loss": 4.2801, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517979995584275e-05, + "loss": 4.2873, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517141400833223e-05, + "loss": 4.2826, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516302806082171e-05, + "loss": 4.3021, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154642113311187e-05, + "loss": 4.2976, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146256165800667e-05, + "loss": 4.2943, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137870218290147e-05, + "loss": 4.2789, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129500649583356e-05, + "loss": 4.2916, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121114702072836e-05, + "loss": 4.2987, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112728754562316e-05, + "loss": 4.2897, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104342807051795e-05, + "loss": 4.2862, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095956859541275e-05, + "loss": 4.2941, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087570912030755e-05, + "loss": 4.2865, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.2936, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070799017009715e-05, + "loss": 4.2741, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506242944830293e-05, + "loss": 4.2933, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505405987959614e-05, + "loss": 4.2813, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504567393208562e-05, + "loss": 4.2814, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.50372879845751e-05, + "loss": 4.2844, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502890203706458e-05, + "loss": 4.2923, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502051608955406e-05, + "loss": 4.2826, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501213014204354e-05, + "loss": 4.2779, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500374419453302e-05, + "loss": 4.2822, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.26480770111084, + "eval_runtime": 300.5019, + "eval_samples_per_second": 1269.846, + "eval_steps_per_second": 39.684, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49953582470225e-05, + "loss": 4.2819, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498697229951198e-05, + "loss": 4.2744, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497858635200146e-05, + "loss": 4.2868, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497020040449093e-05, + "loss": 4.276, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496181445698042e-05, + "loss": 4.2899, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.49534285094699e-05, + "loss": 4.2745, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494504256195938e-05, + "loss": 4.2812, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493665661444886e-05, + "loss": 4.2709, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492827066693834e-05, + "loss": 4.2797, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491988471942782e-05, + "loss": 4.2835, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.49114987719173e-05, + "loss": 4.2788, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490311282440678e-05, + "loss": 4.2804, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489474325569999e-05, + "loss": 4.2674, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488635730818947e-05, + "loss": 4.2744, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487797136067895e-05, + "loss": 4.2725, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2706, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2721, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.2706, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2711, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.2838, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.2777, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2723, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481091653820225e-05, + "loss": 4.2779, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480253059069173e-05, + "loss": 4.2804, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479414464318121e-05, + "loss": 4.2583, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478575869567069e-05, + "loss": 4.2754, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477737274816017e-05, + "loss": 4.2625, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476898680064965e-05, + "loss": 4.2609, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760600853139126e-05, + "loss": 4.2596, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475223128443234e-05, + "loss": 4.2659, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474384533692182e-05, + "loss": 4.2651, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47354593894113e-05, + "loss": 4.2765, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472707344190078e-05, + "loss": 4.2699, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471868749439026e-05, + "loss": 4.2664, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471031792568348e-05, + "loss": 4.2608, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470193197817295e-05, + "loss": 4.268, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469354603066243e-05, + "loss": 4.2598, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468516008315191e-05, + "loss": 4.2687, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467677413564139e-05, + "loss": 4.2463, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466838818813087e-05, + "loss": 4.2553, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2572, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2719, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2568, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2564, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2624, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461807250306775e-05, + "loss": 4.2575, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.2649, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601316986850446e-05, + "loss": 4.2517, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592931039339926e-05, + "loss": 4.2429, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2639, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576175523122615e-05, + "loss": 4.2531, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567789575612095e-05, + "loss": 4.2536, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559403628101575e-05, + "loss": 4.2471, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551017680591055e-05, + "loss": 4.2556, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542631733080535e-05, + "loss": 4.2432, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2559, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525876216863224e-05, + "loss": 4.24, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517490269352704e-05, + "loss": 4.2482, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450910432184219e-05, + "loss": 4.2522, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45007347531354e-05, + "loss": 4.2514, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449236518442861e-05, + "loss": 4.2472, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448397923691809e-05, + "loss": 4.2584, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447559328940757e-05, + "loss": 4.2295, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446720734189705e-05, + "loss": 4.2405, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445882139438653e-05, + "loss": 4.2532, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.2447, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.2449, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2365, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2344, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441689165683393e-05, + "loss": 4.2476, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440850570932341e-05, + "loss": 4.2571, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440011976181289e-05, + "loss": 4.2456, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2517, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.257, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2657, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436659235057454e-05, + "loss": 4.2308, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.2426, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2524, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2308, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2479, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324678991825666e-05, + "loss": 4.2447, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431630942311888e-05, + "loss": 4.2494, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430792347560836e-05, + "loss": 4.2458, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2313, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429115158058732e-05, + "loss": 4.2385, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428279839068426e-05, + "loss": 4.2356, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427441244317374e-05, + "loss": 4.2425, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426602649566322e-05, + "loss": 4.2481, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42576405481527e-05, + "loss": 4.2303, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.2375, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424086865313166e-05, + "loss": 4.2289, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.2364, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2392, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4215727189403836e-05, + "loss": 4.2379, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207341241893316e-05, + "loss": 4.2458, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198955294382796e-05, + "loss": 4.2345, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190569346872276e-05, + "loss": 4.2344, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182183399361756e-05, + "loss": 4.2346, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173830209458694e-05, + "loss": 4.2346, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165444261948174e-05, + "loss": 4.2412, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157058314437654e-05, + "loss": 4.2231, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148672366927134e-05, + "loss": 4.2318, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414030279822034e-05, + "loss": 4.2355, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413191685070982e-05, + "loss": 4.2366, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41235309031993e-05, + "loss": 4.22, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411514495568879e-05, + "loss": 4.2249, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410675900817827e-05, + "loss": 4.2362, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409837306066775e-05, + "loss": 4.2296, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408998711315723e-05, + "loss": 4.2231, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408160116564671e-05, + "loss": 4.2307, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407321521813619e-05, + "loss": 4.2212, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.40648456494294e-05, + "loss": 4.2346, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405647608072261e-05, + "loss": 4.2255, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404809013321209e-05, + "loss": 4.2206, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403970418570157e-05, + "loss": 4.2351, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403131823819105e-05, + "loss": 4.239, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4022948669484257e-05, + "loss": 4.2305, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401456272197374e-05, + "loss": 4.2263, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400617677446322e-05, + "loss": 4.2335, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977908269527e-05, + "loss": 4.2311, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398940487944218e-05, + "loss": 4.2209, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398101893193166e-05, + "loss": 4.2298, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397264936322487e-05, + "loss": 4.2179, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396426341571435e-05, + "loss": 4.2242, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395587746820383e-05, + "loss": 4.2189, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394749152069331e-05, + "loss": 4.2249, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393910557318279e-05, + "loss": 4.2133, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393075238327973e-05, + "loss": 4.2158, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392236643576921e-05, + "loss": 4.2181, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.39139804882587e-05, + "loss": 4.2301, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390559454074818e-05, + "loss": 4.2312, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389720859323766e-05, + "loss": 4.2264, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388882264572714e-05, + "loss": 4.2105, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388043669821662e-05, + "loss": 4.2279, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387205075070609e-05, + "loss": 4.2288, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386366480319557e-05, + "loss": 4.2251, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2177, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2327, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383852333946774e-05, + "loss": 4.2179, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383013739195722e-05, + "loss": 4.2302, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.38217514444467e-05, + "loss": 4.2045, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381336549693618e-05, + "loss": 4.2314, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804995928229395e-05, + "loss": 4.2121, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796609980718875e-05, + "loss": 4.2135, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788224033208355e-05, + "loss": 4.2219, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779838085697835e-05, + "loss": 4.2194, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771452138187314e-05, + "loss": 4.2206, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763066190676794e-05, + "loss": 4.2075, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754680243166274e-05, + "loss": 4.2214, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.206742763519287, + "eval_runtime": 304.405, + "eval_samples_per_second": 1253.563, + "eval_steps_per_second": 39.175, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746310674459483e-05, + "loss": 4.2179, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737924726948963e-05, + "loss": 4.2095, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729538779438443e-05, + "loss": 4.223, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372115283192792e-05, + "loss": 4.2125, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.37127668844174e-05, + "loss": 4.2233, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370438093690688e-05, + "loss": 4.2107, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369599498939636e-05, + "loss": 4.2108, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368760904188584e-05, + "loss": 4.2121, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367923947317906e-05, + "loss": 4.2131, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367085352566854e-05, + "loss": 4.2188, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366248395696175e-05, + "loss": 4.2142, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365409800945123e-05, + "loss": 4.2191, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364572844074444e-05, + "loss": 4.2049, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363734249323392e-05, + "loss": 4.2087, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36289565457234e-05, + "loss": 4.2126, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362057059821288e-05, + "loss": 4.2033, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361218465070236e-05, + "loss": 4.211, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360379870319184e-05, + "loss": 4.2043, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359541275568132e-05, + "loss": 4.2055, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35870268081708e-05, + "loss": 4.2247, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578640860660284e-05, + "loss": 4.2142, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357025491314976e-05, + "loss": 4.2167, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356186896563924e-05, + "loss": 4.2099, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355349939693245e-05, + "loss": 4.216, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545113449421926e-05, + "loss": 4.1966, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536727501911406e-05, + "loss": 4.2149, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528341554400886e-05, + "loss": 4.2032, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519955606890366e-05, + "loss": 4.1945, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511586038183575e-05, + "loss": 4.1984, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503200090673055e-05, + "loss": 4.2023, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349483052196627e-05, + "loss": 4.2048, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348644457445575e-05, + "loss": 4.2123, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347805862694523e-05, + "loss": 4.2103, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346967267943471e-05, + "loss": 4.2048, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346128673192419e-05, + "loss": 4.203, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345290078441367e-05, + "loss": 4.2042, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344453121570688e-05, + "loss": 4.1995, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343614526819636e-05, + "loss": 4.205, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342775932068584e-05, + "loss": 4.191, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341937337317532e-05, + "loss": 4.1914, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.34109874256648e-05, + "loss": 4.1982, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340260147815428e-05, + "loss": 4.2094, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339421553064376e-05, + "loss": 4.1991, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338582958313324e-05, + "loss": 4.1943, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337744363562272e-05, + "loss": 4.2015, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.33690576881122e-05, + "loss": 4.1947, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360688119405415e-05, + "loss": 4.2053, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352302171894895e-05, + "loss": 4.1906, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343916224384375e-05, + "loss": 4.1825, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335530276873855e-05, + "loss": 4.2021, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327160708167064e-05, + "loss": 4.1973, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318774760656544e-05, + "loss": 4.1922, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310388813146024e-05, + "loss": 4.1946, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302002865635504e-05, + "loss": 4.1921, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293616918124984e-05, + "loss": 4.1874, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328524734941819e-05, + "loss": 4.193, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327686140190767e-05, + "loss": 4.1854, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326847545439715e-05, + "loss": 4.1876, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326008950688664e-05, + "loss": 4.1981, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325171993817985e-05, + "loss": 4.1878, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324333399066933e-05, + "loss": 4.1903, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323494804315881e-05, + "loss": 4.1993, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322656209564829e-05, + "loss": 4.1767, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321817614813776e-05, + "loss": 4.182, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320979020062724e-05, + "loss": 4.1906, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320140425311672e-05, + "loss": 4.1922, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319303468440994e-05, + "loss": 4.1828, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318464873689941e-05, + "loss": 4.1822, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317626278938889e-05, + "loss": 4.1757, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316787684187838e-05, + "loss": 4.1923, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315949089436786e-05, + "loss": 4.1964, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315110494685734e-05, + "loss": 4.1896, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3142735378150546e-05, + "loss": 4.1954, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134349430640026e-05, + "loss": 4.1935, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3125963483129506e-05, + "loss": 4.2151, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117577535618986e-05, + "loss": 4.1742, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109207966912195e-05, + "loss": 4.1834, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100822019401675e-05, + "loss": 4.1983, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092452450694884e-05, + "loss": 4.1738, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084066503184364e-05, + "loss": 4.1895, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075680555673844e-05, + "loss": 4.1892, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306729460816333e-05, + "loss": 4.1922, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305890866065281e-05, + "loss": 4.1887, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305052271314229e-05, + "loss": 4.1733, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304213676563177e-05, + "loss": 4.1893, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303375081812125e-05, + "loss": 4.1741, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302538124941446e-05, + "loss": 4.1885, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301699530190394e-05, + "loss": 4.1922, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300860935439342e-05, + "loss": 4.1725, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.30002234068829e-05, + "loss": 4.1839, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299183745937238e-05, + "loss": 4.1756, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298346789066559e-05, + "loss": 4.1787, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297508194315507e-05, + "loss": 4.1791, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296669599564455e-05, + "loss": 4.1894, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295831004813403e-05, + "loss": 4.1925, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949924100623515e-05, + "loss": 4.1767, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941554531916724e-05, + "loss": 4.1784, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933168584406204e-05, + "loss": 4.1843, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924782636895684e-05, + "loss": 4.1771, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916396689385164e-05, + "loss": 4.1899, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908010741874644e-05, + "loss": 4.1716, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289964117316785e-05, + "loss": 4.176, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289125522565733e-05, + "loss": 4.1827, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288286927814681e-05, + "loss": 4.1845, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287448333063629e-05, + "loss": 4.1637, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866097383125766e-05, + "loss": 4.1719, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285772781441898e-05, + "loss": 4.1804, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284934186690847e-05, + "loss": 4.1782, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284095591939795e-05, + "loss": 4.1669, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283256997188742e-05, + "loss": 4.1841, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.28241840243769e-05, + "loss": 4.1649, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281579807686638e-05, + "loss": 4.1765, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.28074285081596e-05, + "loss": 4.1742, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279904256064907e-05, + "loss": 4.1685, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279067299194229e-05, + "loss": 4.1799, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278228704443177e-05, + "loss": 4.1897, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277390109692124e-05, + "loss": 4.1781, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276551514941072e-05, + "loss": 4.1747, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275712920190021e-05, + "loss": 4.1802, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274874325438969e-05, + "loss": 4.1785, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274035730687917e-05, + "loss": 4.1684, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273197135936865e-05, + "loss": 4.1732, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2723585411858127e-05, + "loss": 4.1669, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715199464347607e-05, + "loss": 4.1707, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2706813516837087e-05, + "loss": 4.1711, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698427569326566e-05, + "loss": 4.1694, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690058000619776e-05, + "loss": 4.1658, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681672053109256e-05, + "loss": 4.1622, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673302484402465e-05, + "loss": 4.1709, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664932915695674e-05, + "loss": 4.1764, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656546968185154e-05, + "loss": 4.1775, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264816102067464e-05, + "loss": 4.1757, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263977507316412e-05, + "loss": 4.1575, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.26313891256536e-05, + "loss": 4.1802, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262300317814308e-05, + "loss": 4.1783, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261461723063256e-05, + "loss": 4.1711, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260623128312204e-05, + "loss": 4.1693, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259784533561152e-05, + "loss": 4.1756, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589459388101e-05, + "loss": 4.1676, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258107344059048e-05, + "loss": 4.1828, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257270387188369e-05, + "loss": 4.154, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256431792437317e-05, + "loss": 4.1782, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255594835566638e-05, + "loss": 4.1611, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254756240815586e-05, + "loss": 4.1664, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253917646064534e-05, + "loss": 4.1709, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530790513134825e-05, + "loss": 4.167, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522404565624305e-05, + "loss": 4.178, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514018618113785e-05, + "loss": 4.1526, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250563267060326e-05, + "loss": 4.1738, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.164763927459717, + "eval_runtime": 303.1387, + "eval_samples_per_second": 1258.8, + "eval_steps_per_second": 39.338, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249724672309274e-05, + "loss": 4.172, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248886077558222e-05, + "loss": 4.1589, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.24804748280717e-05, + "loss": 4.1734, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247208888056118e-05, + "loss": 4.1647, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246370293305066e-05, + "loss": 4.1707, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245531698554014e-05, + "loss": 4.1634, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244693103802962e-05, + "loss": 4.1604, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24385450905191e-05, + "loss": 4.1651, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243015914300858e-05, + "loss": 4.1634, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2421789574301793e-05, + "loss": 4.1693, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241340362679127e-05, + "loss": 4.1695, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240501767928075e-05, + "loss": 4.1665, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239663173177023e-05, + "loss": 4.1607, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238824578425971e-05, + "loss": 4.1598, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237985983674919e-05, + "loss": 4.1641, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237147388923867e-05, + "loss": 4.1529, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363087941728146e-05, + "loss": 4.162, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2354701994217626e-05, + "loss": 4.157, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346316046707106e-05, + "loss": 4.1594, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337930099196586e-05, + "loss": 4.1744, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329544151686066e-05, + "loss": 4.1684, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321174582979275e-05, + "loss": 4.1686, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231278863546876e-05, + "loss": 4.1621, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230440268795824e-05, + "loss": 4.1695, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229601674044772e-05, + "loss": 4.1491, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.22876307929372e-05, + "loss": 4.1693, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227926122423041e-05, + "loss": 4.1557, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227087527671989e-05, + "loss": 4.1476, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226248932920937e-05, + "loss": 4.1543, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225411976050258e-05, + "loss": 4.1561, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224573381299206e-05, + "loss": 4.1574, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223736424428527e-05, + "loss": 4.1669, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222897829677475e-05, + "loss": 4.1619, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222059234926423e-05, + "loss": 4.1603, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221220640175371e-05, + "loss": 4.1509, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203820454243196e-05, + "loss": 4.1609, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195434506732676e-05, + "loss": 4.1581, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187048559222156e-05, + "loss": 4.1518, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178662611711635e-05, + "loss": 4.1501, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170276664201115e-05, + "loss": 4.1427, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161890716690595e-05, + "loss": 4.1522, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153504769180075e-05, + "loss": 4.1618, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145118821669555e-05, + "loss": 4.1533, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136732874159035e-05, + "loss": 4.1492, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128363305452244e-05, + "loss": 4.1579, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119993736745453e-05, + "loss": 4.1484, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211160778923493e-05, + "loss": 4.1619, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210322184172441e-05, + "loss": 4.148, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209483589421389e-05, + "loss": 4.1333, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208644994670338e-05, + "loss": 4.1572, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207808037799659e-05, + "loss": 4.1522, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206969443048607e-05, + "loss": 4.1507, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206130848297555e-05, + "loss": 4.1455, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205293891426876e-05, + "loss": 4.1446, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204455296675824e-05, + "loss": 4.1452, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203616701924772e-05, + "loss": 4.1442, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20277810717372e-05, + "loss": 4.1412, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201939512422668e-05, + "loss": 4.146, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201100917671615e-05, + "loss": 4.1511, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200262322920563e-05, + "loss": 4.1436, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199423728169512e-05, + "loss": 4.1435, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858513341846e-05, + "loss": 4.1612, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197746538667408e-05, + "loss": 4.13, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196909581796729e-05, + "loss": 4.1361, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196070987045677e-05, + "loss": 4.1482, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195232392294625e-05, + "loss": 4.1511, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194393797543573e-05, + "loss": 4.1391, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193555202792521e-05, + "loss": 4.1384, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927166080414687e-05, + "loss": 4.1329, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918780132904167e-05, + "loss": 4.1453, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910394185393647e-05, + "loss": 4.1556, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902024616686856e-05, + "loss": 4.1467, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189365504798007e-05, + "loss": 4.1473, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188526910046955e-05, + "loss": 4.1536, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187688315295903e-05, + "loss": 4.1698, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186849720544851e-05, + "loss": 4.1345, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186011125793799e-05, + "loss": 4.1416, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185172531042747e-05, + "loss": 4.1534, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184335574172068e-05, + "loss": 4.1318, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183496979421016e-05, + "loss": 4.1472, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182658384669964e-05, + "loss": 4.1477, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181819789918912e-05, + "loss": 4.1495, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.18098119516786e-05, + "loss": 4.1487, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180142600416808e-05, + "loss": 4.1317, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179305643546129e-05, + "loss": 4.1447, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178467048795077e-05, + "loss": 4.1374, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177628454044025e-05, + "loss": 4.1423, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767898592929736e-05, + "loss": 4.1483, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759512645419216e-05, + "loss": 4.1322, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751126697908696e-05, + "loss": 4.1419, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1742757129201905e-05, + "loss": 4.1351, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734371181691385e-05, + "loss": 4.1328, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726001612984594e-05, + "loss": 4.1417, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1717615665474074e-05, + "loss": 4.1458, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709229717963554e-05, + "loss": 4.1508, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1700843770453034e-05, + "loss": 4.1372, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1692457822942514e-05, + "loss": 4.1367, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168407187543199e-05, + "loss": 4.1406, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1675685927921474e-05, + "loss": 4.1396, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667299980410954e-05, + "loss": 4.1463, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658914032900434e-05, + "loss": 4.133, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650528085389914e-05, + "loss": 4.1343, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1399, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1474, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1191, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161700067415156e-05, + "loss": 4.1343, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160863110544477e-05, + "loss": 4.1349, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160024515793425e-05, + "loss": 4.1398, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159185921042373e-05, + "loss": 4.1236, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158347326291321e-05, + "loss": 4.138, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157508731540269e-05, + "loss": 4.1322, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156670136789217e-05, + "loss": 4.1317, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155833179918539e-05, + "loss": 4.1374, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154994585167487e-05, + "loss": 4.1277, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154155990416435e-05, + "loss": 4.1353, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153317395665383e-05, + "loss": 4.1495, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152478800914331e-05, + "loss": 4.1374, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151640206163279e-05, + "loss": 4.1309, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150801611412227e-05, + "loss": 4.1416, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499646545415476e-05, + "loss": 4.1396, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491260597904956e-05, + "loss": 4.1243, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482874650394436e-05, + "loss": 4.138, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474488702883916e-05, + "loss": 4.1267, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466119134177125e-05, + "loss": 4.1274, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145773318666661e-05, + "loss": 4.1315, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144934723915609e-05, + "loss": 4.1306, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144096129164557e-05, + "loss": 4.1282, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143257534413505e-05, + "loss": 4.1265, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142420577542826e-05, + "loss": 4.1279, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141581982791774e-05, + "loss": 4.1398, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140743388040722e-05, + "loss": 4.1339, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13990479328967e-05, + "loss": 4.1345, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139067836418991e-05, + "loss": 4.1193, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138229241667939e-05, + "loss": 4.1433, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137390646916887e-05, + "loss": 4.1349, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136552052165835e-05, + "loss": 4.1345, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357150952951565e-05, + "loss": 4.1319, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348765005441045e-05, + "loss": 4.1364, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340379057930525e-05, + "loss": 4.1261, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1331993110420005e-05, + "loss": 4.1471, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132360716290948e-05, + "loss": 4.1155, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315237594202694e-05, + "loss": 4.1353, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1306851646692174e-05, + "loss": 4.1262, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129846569918165e-05, + "loss": 4.1268, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129007975167113e-05, + "loss": 4.1297, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128169380416061e-05, + "loss": 4.124, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127332423545382e-05, + "loss": 4.1403, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649382879433e-05, + "loss": 4.1191, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125655234043278e-05, + "loss": 4.1346, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.133495807647705, + "eval_runtime": 295.0853, + "eval_samples_per_second": 1293.155, + "eval_steps_per_second": 40.412, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124816639292226e-05, + "loss": 4.1303, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123978044541174e-05, + "loss": 4.1194, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123139449790122e-05, + "loss": 4.1341, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230085503907e-05, + "loss": 4.1263, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121462260288018e-05, + "loss": 4.1294, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120623665536966e-05, + "loss": 4.1239, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119785070785914e-05, + "loss": 4.1263, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118948113915235e-05, + "loss": 4.1224, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118111157044556e-05, + "loss": 4.1286, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117272562293504e-05, + "loss": 4.1324, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116433967542452e-05, + "loss": 4.1303, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155953727914e-05, + "loss": 4.1255, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114758415920722e-05, + "loss": 4.1222, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.11391982116967e-05, + "loss": 4.1228, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113081226418618e-05, + "loss": 4.1275, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112242631667566e-05, + "loss": 4.1158, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111404036916514e-05, + "loss": 4.1235, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1105654421654617e-05, + "loss": 4.1199, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097268474144097e-05, + "loss": 4.1222, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1088882526633577e-05, + "loss": 4.1316, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080496579123056e-05, + "loss": 4.1337, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072127010416266e-05, + "loss": 4.1314, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063741062905746e-05, + "loss": 4.1245, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055355115395225e-05, + "loss": 4.1294, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1046969167884705e-05, + "loss": 4.1137, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038583220374185e-05, + "loss": 4.1312, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.1178, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021811325353145e-05, + "loss": 4.1132, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013425377842625e-05, + "loss": 4.1162, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1187, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996669861625314e-05, + "loss": 4.1186, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988283914114794e-05, + "loss": 4.1288, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979897966604274e-05, + "loss": 4.1282, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971512019093754e-05, + "loss": 4.1184, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.09631588291907e-05, + "loss": 4.117, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095477288168018e-05, + "loss": 4.1247, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094638693416966e-05, + "loss": 4.1225, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093800098665914e-05, + "loss": 4.1137, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092961503914862e-05, + "loss": 4.1152, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921245470441835e-05, + "loss": 4.1073, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091285952293131e-05, + "loss": 4.1127, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090447357542079e-05, + "loss": 4.126, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089608762791027e-05, + "loss": 4.1167, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088770168039975e-05, + "loss": 4.1103, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087931573288923e-05, + "loss": 4.1205, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087094616418244e-05, + "loss": 4.1116, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086256021667192e-05, + "loss": 4.1246, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08541742691614e-05, + "loss": 4.1152, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084578832165088e-05, + "loss": 4.0947, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083740237414036e-05, + "loss": 4.1215, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829016426629844e-05, + "loss": 4.1157, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820630479119323e-05, + "loss": 4.1181, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1091, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1073, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079548901539149e-05, + "loss": 4.1091, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078710306788097e-05, + "loss": 4.1068, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077871712037045e-05, + "loss": 4.1081, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077034755166366e-05, + "loss": 4.1069, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076196160415314e-05, + "loss": 4.1212, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075357565664262e-05, + "loss": 4.1023, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07451897091321e-05, + "loss": 4.1092, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073680376162158e-05, + "loss": 4.1241, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072841781411106e-05, + "loss": 4.0943, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072003186660054e-05, + "loss": 4.0974, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071164591909002e-05, + "loss": 4.1156, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07032599715795e-05, + "loss": 4.1135, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069489040287272e-05, + "loss": 4.1011, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1057, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067811850785167e-05, + "loss": 4.0943, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066973256034115e-05, + "loss": 4.1153, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661362991634366e-05, + "loss": 4.1163, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652977044123846e-05, + "loss": 4.1121, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1107, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06362051491028e-05, + "loss": 4.1206, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627835580396015e-05, + "loss": 4.133, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619449632885495e-05, + "loss": 4.101, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611063685374975e-05, + "loss": 4.1057, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602677737864455e-05, + "loss": 4.1189, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594291790353935e-05, + "loss": 4.0985, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585905842843415e-05, + "loss": 4.1089, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577519895332895e-05, + "loss": 4.1127, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569133947822375e-05, + "loss": 4.1147, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560748000311855e-05, + "loss": 4.1183, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055239481040879e-05, + "loss": 4.0966, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054400886289827e-05, + "loss": 4.1059, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053562291538775e-05, + "loss": 4.1027, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052723696787723e-05, + "loss": 4.1085, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051885102036671e-05, + "loss": 4.1108, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051048145165993e-05, + "loss": 4.0997, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050209550414941e-05, + "loss": 4.1057, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049370955663889e-05, + "loss": 4.1013, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048532360912837e-05, + "loss": 4.0977, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047693766161785e-05, + "loss": 4.106, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046855171410733e-05, + "loss": 4.1099, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.1137, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045179619789002e-05, + "loss": 4.108, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.04434102503795e-05, + "loss": 4.0986, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043502430286898e-05, + "loss": 4.108, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.1052, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1058, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1022, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.04014805128269e-05, + "loss": 4.0997, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039311094412011e-05, + "loss": 4.103, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038472499660959e-05, + "loss": 4.1136, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037633904909907e-05, + "loss": 4.0883, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.0999, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035958353288176e-05, + "loss": 4.0972, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035119758537124e-05, + "loss": 4.1049, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034281163786072e-05, + "loss": 4.0953, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.03344256903502e-05, + "loss": 4.1071, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032603974283968e-05, + "loss": 4.0931, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317653795329155e-05, + "loss": 4.1016, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309267847818635e-05, + "loss": 4.1048, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030088190030812e-05, + "loss": 4.0926, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029252871040507e-05, + "loss": 4.1012, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284142762894547e-05, + "loss": 4.1168, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275756815384027e-05, + "loss": 4.104, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267370867873506e-05, + "loss": 4.0974, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025898492036298e-05, + "loss": 4.1055, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250615351656196e-05, + "loss": 4.1108, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242229404145675e-05, + "loss": 4.0958, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233843456635155e-05, + "loss": 4.1036, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022545750912463e-05, + "loss": 4.0876, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021707156161411e-05, + "loss": 4.0957, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020868561410359e-05, + "loss": 4.0948, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200299666593075e-05, + "loss": 4.0978, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191930097886284e-05, + "loss": 4.0949, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.01835605291795e-05, + "loss": 4.0953, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017517458166898e-05, + "loss": 4.0916, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016678863415845e-05, + "loss": 4.1073, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015840268664793e-05, + "loss": 4.1044, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015003311794115e-05, + "loss": 4.1024, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014166354923436e-05, + "loss": 4.0851, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013327760172384e-05, + "loss": 4.1135, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012489165421332e-05, + "loss": 4.0976, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.01165057067028e-05, + "loss": 4.1025, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010811975919228e-05, + "loss": 4.1025, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009973381168176e-05, + "loss": 4.0993, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009134786417124e-05, + "loss": 4.0945, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008296191666072e-05, + "loss": 4.1134, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.00745759691502e-05, + "loss": 4.0852, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006619002163968e-05, + "loss": 4.1035, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005780407412916e-05, + "loss": 4.0927, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004941812661864e-05, + "loss": 4.0967, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004104855791185e-05, + "loss": 4.0945, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003266261040133e-05, + "loss": 4.0922, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002427666289081e-05, + "loss": 4.1055, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001589071538029e-05, + "loss": 4.0914, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000750476786977e-05, + "loss": 4.0994, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.108636856079102, + "eval_runtime": 293.8051, + "eval_samples_per_second": 1298.79, + "eval_steps_per_second": 40.588, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999913519916298e-05, + "loss": 4.0986, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999074925165246e-05, + "loss": 4.0904, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998236330414194e-05, + "loss": 4.097, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997397735663142e-05, + "loss": 4.0922, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.99655914091209e-05, + "loss": 4.1011, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995720546161038e-05, + "loss": 4.0905, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994881951409986e-05, + "loss": 4.0965, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994043356658934e-05, + "loss": 4.0934, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932047619078815e-05, + "loss": 4.0929, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9923661671568295e-05, + "loss": 4.1034, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915275724057775e-05, + "loss": 4.097, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906889776547255e-05, + "loss": 4.0923, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898503829036735e-05, + "loss": 4.1004, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890117881526215e-05, + "loss": 4.0842, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881731934015695e-05, + "loss": 4.0933, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873345986505175e-05, + "loss": 4.0859, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986496003899466e-05, + "loss": 4.0944, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985657409148414e-05, + "loss": 4.0891, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984818814397362e-05, + "loss": 4.0858, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98398021964631e-05, + "loss": 4.1006, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983143262775631e-05, + "loss": 4.1059, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982304668024579e-05, + "loss": 4.102, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981466073273527e-05, + "loss": 4.0906, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980629116402848e-05, + "loss": 4.0942, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979790521651796e-05, + "loss": 4.0867, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978951926900744e-05, + "loss": 4.0967, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978113332149692e-05, + "loss": 4.0904, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977276375279013e-05, + "loss": 4.0871, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764377805279616e-05, + "loss": 4.0833, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755991857769096e-05, + "loss": 4.0868, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747605910258575e-05, + "loss": 4.0849, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739219962748055e-05, + "loss": 4.0985, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973083401523753e-05, + "loss": 4.0956, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972244806772701e-05, + "loss": 4.0894, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714078499020224e-05, + "loss": 4.0857, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705692551509704e-05, + "loss": 4.0914, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969730660399918e-05, + "loss": 4.0914, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968892065648866e-05, + "loss": 4.0858, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968053470897814e-05, + "loss": 4.0864, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967214876146762e-05, + "loss": 4.0752, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.96637628139571e-05, + "loss": 4.0792, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655376866446584e-05, + "loss": 4.0978, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964700729773979e-05, + "loss": 4.0913, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638637729033e-05, + "loss": 4.0788, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963026816032622e-05, + "loss": 4.0907, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.96218822128157e-05, + "loss": 4.0804, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961349626530518e-05, + "loss": 4.0931, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960511031779465e-05, + "loss": 4.0852, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959672437028413e-05, + "loss": 4.0612, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958833842277361e-05, + "loss": 4.0936, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957995247526309e-05, + "loss": 4.085, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957156652775257e-05, + "loss": 4.0889, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956318058024205e-05, + "loss": 4.0808, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955479463273154e-05, + "loss": 4.0783, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954640868522102e-05, + "loss": 4.0776, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.95380227377105e-05, + "loss": 4.0779, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952965316900371e-05, + "loss": 4.0785, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952126722149319e-05, + "loss": 4.0749, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951288127398267e-05, + "loss": 4.0925, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950449532647215e-05, + "loss": 4.0748, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496142136569085e-05, + "loss": 4.0788, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9487756189058565e-05, + "loss": 4.094, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479370241548045e-05, + "loss": 4.0655, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9470984294037525e-05, + "loss": 4.0679, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462598346527005e-05, + "loss": 4.0856, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454212399016485e-05, + "loss": 4.0839, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94458428303097e-05, + "loss": 4.0739, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943745688279918e-05, + "loss": 4.0764, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942907093528866e-05, + "loss": 4.0688, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942068498777814e-05, + "loss": 4.0804, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941229904026762e-05, + "loss": 4.0867, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940392947156083e-05, + "loss": 4.0813, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939554352405031e-05, + "loss": 4.0848, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938715757653979e-05, + "loss": 4.09, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937877162902927e-05, + "loss": 4.1029, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937038568151875e-05, + "loss": 4.07, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936199973400823e-05, + "loss": 4.0801, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935363016530144e-05, + "loss": 4.0865, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345244217790925e-05, + "loss": 4.0735, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336858270280405e-05, + "loss": 4.0738, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328472322769885e-05, + "loss": 4.0899, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320086375259365e-05, + "loss": 4.0855, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9311716806552574e-05, + "loss": 4.0885, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303330859042054e-05, + "loss": 4.0682, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294944911531534e-05, + "loss": 4.0738, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928655896402101e-05, + "loss": 4.0747, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927817301651049e-05, + "loss": 4.0804, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926978706899997e-05, + "loss": 4.0825, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926141750029318e-05, + "loss": 4.0765, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925303155278266e-05, + "loss": 4.071, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924464560527214e-05, + "loss": 4.0773, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923625965776162e-05, + "loss": 4.0701, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92278737102511e-05, + "loss": 4.0762, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921950414154431e-05, + "loss": 4.0863, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921111819403379e-05, + "loss": 4.0841, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920273224652327e-05, + "loss": 4.0769, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919434629901275e-05, + "loss": 4.0724, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918597673030596e-05, + "loss": 4.0785, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917759078279544e-05, + "loss": 4.0761, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916920483528492e-05, + "loss": 4.0812, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608188877744e-05, + "loss": 4.0763, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915243294026388e-05, + "loss": 4.0678, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914404699275336e-05, + "loss": 4.0839, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913566104524285e-05, + "loss": 4.081, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912727509773233e-05, + "loss": 4.0597, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118905529025536e-05, + "loss": 4.0721, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110519581515016e-05, + "loss": 4.0663, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102133634004496e-05, + "loss": 4.0824, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9093747686493976e-05, + "loss": 4.0624, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085361738983456e-05, + "loss": 4.0812, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077008549080394e-05, + "loss": 4.0663, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068622601569874e-05, + "loss": 4.0741, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060236654059354e-05, + "loss": 4.0743, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051850706548834e-05, + "loss": 4.067, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043464759038314e-05, + "loss": 4.0708, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.90350788115278e-05, + "loss": 4.0881, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902670924282101e-05, + "loss": 4.074, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901832329531049e-05, + "loss": 4.0756, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900993734779997e-05, + "loss": 4.0764, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900155140028945e-05, + "loss": 4.0798, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899316545277893e-05, + "loss": 4.0751, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898477950526841e-05, + "loss": 4.0739, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897639355775789e-05, + "loss": 4.0585, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896800761024737e-05, + "loss": 4.0711, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895962166273684e-05, + "loss": 4.0674, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895125209403006e-05, + "loss": 4.0691, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894286614651954e-05, + "loss": 4.0655, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893448019900902e-05, + "loss": 4.0712, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.89260942514985e-05, + "loss": 4.0639, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891770830398798e-05, + "loss": 4.0835, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909338735281195e-05, + "loss": 4.0716, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8900952787770674e-05, + "loss": 4.0789, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889256684026015e-05, + "loss": 4.055, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888418089274963e-05, + "loss": 4.0864, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887579494523911e-05, + "loss": 4.0699, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886742537653232e-05, + "loss": 4.0775, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859039429021797e-05, + "loss": 4.0741, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8850653481511277e-05, + "loss": 4.0717, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842267534000757e-05, + "loss": 4.0702, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833881586490236e-05, + "loss": 4.0854, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825495638979716e-05, + "loss": 4.0546, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.88171096914692e-05, + "loss": 4.0797, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880872374395868e-05, + "loss": 4.07, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880035417525189e-05, + "loss": 4.064, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879196822774137e-05, + "loss": 4.0684, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878358228023085e-05, + "loss": 4.0653, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877519633272033e-05, + "loss": 4.0801, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876681038520981e-05, + "loss": 4.066, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875842443769929e-05, + "loss": 4.0717, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.08804988861084, + "eval_runtime": 295.8931, + "eval_samples_per_second": 1289.625, + "eval_steps_per_second": 40.302, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.87500548689925e-05, + "loss": 4.0659, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874168530028571e-05, + "loss": 4.0657, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733315731578926e-05, + "loss": 4.0675, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724929784068406e-05, + "loss": 4.0692, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716543836557886e-05, + "loss": 4.0766, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708157889047366e-05, + "loss": 4.0622, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8699771941536846e-05, + "loss": 4.0691, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8691385994026326e-05, + "loss": 4.0657, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683000046515806e-05, + "loss": 4.0688, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674614099005286e-05, + "loss": 4.0766, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666228151494766e-05, + "loss": 4.0669, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8657842203984246e-05, + "loss": 4.0682, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649472635277455e-05, + "loss": 4.0757, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641086687766935e-05, + "loss": 4.0548, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632700740256415e-05, + "loss": 4.0648, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624314792745895e-05, + "loss": 4.0571, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615928845235375e-05, + "loss": 4.0678, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860755927652859e-05, + "loss": 4.062, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.85991897078218e-05, + "loss": 4.0628, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859080376031128e-05, + "loss": 4.0737, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858241781280076e-05, + "loss": 4.077, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857403186529024e-05, + "loss": 4.0784, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856564591777972e-05, + "loss": 4.0678, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.85572599702692e-05, + "loss": 4.063, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854887402275868e-05, + "loss": 4.0592, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854048807524815e-05, + "loss": 4.0694, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853210212773763e-05, + "loss": 4.0645, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852371618022711e-05, + "loss": 4.0625, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851533023271659e-05, + "loss": 4.057, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850694428520608e-05, + "loss": 4.0604, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849857471649929e-05, + "loss": 4.057, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490205147792504e-05, + "loss": 4.0736, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848181920028198e-05, + "loss": 4.0715, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847343325277146e-05, + "loss": 4.0628, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846504730526094e-05, + "loss": 4.0615, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845666135775042e-05, + "loss": 4.0629, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84482754102399e-05, + "loss": 4.069, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843988946272938e-05, + "loss": 4.0603, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843150351521886e-05, + "loss": 4.0606, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423133946512066e-05, + "loss": 4.0489, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414747999001546e-05, + "loss": 4.0566, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840636205149103e-05, + "loss": 4.0654, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839799248278424e-05, + "loss": 4.0652, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838960653527372e-05, + "loss": 4.0584, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.83812205877632e-05, + "loss": 4.0604, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837283464025268e-05, + "loss": 4.0595, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836444869274216e-05, + "loss": 4.0648, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835606274523164e-05, + "loss": 4.0611, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834767679772112e-05, + "loss": 4.0332, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833930722901433e-05, + "loss": 4.0688, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833092128150381e-05, + "loss": 4.0603, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832253533399329e-05, + "loss": 4.0665, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831414938648277e-05, + "loss": 4.0564, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830576343897225e-05, + "loss": 4.0511, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297393870265466e-05, + "loss": 4.0528, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289024301558675e-05, + "loss": 4.0496, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8280638354048155e-05, + "loss": 4.0578, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272252406537635e-05, + "loss": 4.044, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263866459027115e-05, + "loss": 4.0651, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255480511516595e-05, + "loss": 4.0539, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247094564006075e-05, + "loss": 4.0496, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8238708616495555e-05, + "loss": 4.0726, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230322668985035e-05, + "loss": 4.0422, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221936721474515e-05, + "loss": 4.0413, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821355077396399e-05, + "loss": 4.0618, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820516482645347e-05, + "loss": 4.0595, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196795257746684e-05, + "loss": 4.0492, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188409310236164e-05, + "loss": 4.0542, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180023362725644e-05, + "loss": 4.0376, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171637415215124e-05, + "loss": 4.057, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163251467704604e-05, + "loss": 4.0612, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154865520194084e-05, + "loss": 4.0618, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146479572683564e-05, + "loss": 4.0572, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138093625173044e-05, + "loss": 4.0625, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129707677662524e-05, + "loss": 4.077, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812133810895573e-05, + "loss": 4.0488, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811296854024894e-05, + "loss": 4.0587, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810458259273842e-05, + "loss": 4.0548, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80961966452279e-05, + "loss": 4.0522, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808781069771739e-05, + "loss": 4.0476, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807942475020687e-05, + "loss": 4.0665, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807103880269635e-05, + "loss": 4.059, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806266923398956e-05, + "loss": 4.0635, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805428328647904e-05, + "loss": 4.0429, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804589733896852e-05, + "loss": 4.0502, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8037511391458e-05, + "loss": 4.0522, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029141822751207e-05, + "loss": 4.0549, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020755875240687e-05, + "loss": 4.0579, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8012369927730166e-05, + "loss": 4.053, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8003983980219646e-05, + "loss": 4.042, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995598032709126e-05, + "loss": 4.0565, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987212085198606e-05, + "loss": 4.0466, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978826137688086e-05, + "loss": 4.0495, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797044019017757e-05, + "loss": 4.0602, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796207062147078e-05, + "loss": 4.0599, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795368467396026e-05, + "loss": 4.0523, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794529872644974e-05, + "loss": 4.0496, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793692915774295e-05, + "loss": 4.0502, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792854321023243e-05, + "loss": 4.0523, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792015726272191e-05, + "loss": 4.0598, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791177131521139e-05, + "loss": 4.0516, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.79034017465046e-05, + "loss": 4.0457, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789501579899408e-05, + "loss": 4.0559, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788662985148356e-05, + "loss": 4.0569, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787824390397304e-05, + "loss": 4.0373, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786985795646253e-05, + "loss": 4.0508, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861472008952e-05, + "loss": 4.0405, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785308606144148e-05, + "loss": 4.0568, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784470011393096e-05, + "loss": 4.0421, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783631416642044e-05, + "loss": 4.0552, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782794459771365e-05, + "loss": 4.0405, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819575029006865e-05, + "loss": 4.055, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811189081496345e-05, + "loss": 4.0487, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7802803133985825e-05, + "loss": 4.0417, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.77944171864753e-05, + "loss": 4.051, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778603123896478e-05, + "loss": 4.0659, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777645291454264e-05, + "loss": 4.0513, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769259343943744e-05, + "loss": 4.0534, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7760873396433224e-05, + "loss": 4.0468, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775252020653017e-05, + "loss": 4.0531, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774413425901965e-05, + "loss": 4.0557, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773574831150912e-05, + "loss": 4.046, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.77273623639986e-05, + "loss": 4.0373, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771897641648808e-05, + "loss": 4.0476, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.77106068477813e-05, + "loss": 4.0469, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770222090027077e-05, + "loss": 4.0449, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769383495276025e-05, + "loss": 4.045, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768544900524973e-05, + "loss": 4.0466, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767706305773921e-05, + "loss": 4.0387, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.76686771102287e-05, + "loss": 4.0577, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766029116271818e-05, + "loss": 4.0478, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765190521520766e-05, + "loss": 4.0555, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764353564650087e-05, + "loss": 4.0327, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763514969899035e-05, + "loss": 4.0607, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762676375147983e-05, + "loss": 4.0511, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7618394182773036e-05, + "loss": 4.0517, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610008235262516e-05, + "loss": 4.0476, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7601622287751996e-05, + "loss": 4.0482, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593236340241476e-05, + "loss": 4.0499, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584850392730956e-05, + "loss": 4.0616, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576464445220436e-05, + "loss": 4.0339, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568078497709916e-05, + "loss": 4.0548, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7559692550199396e-05, + "loss": 4.0455, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755130660268888e-05, + "loss": 4.0441, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754293703398209e-05, + "loss": 4.0476, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753455108647157e-05, + "loss": 4.0426, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752616513896105e-05, + "loss": 4.0518, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751779557025426e-05, + "loss": 4.0497, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750940962274374e-05, + "loss": 4.0442, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.072386264801025, + "eval_runtime": 300.4077, + "eval_samples_per_second": 1270.244, + "eval_steps_per_second": 39.696, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750102367523322e-05, + "loss": 4.0468, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74926377277227e-05, + "loss": 4.0437, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748425178021218e-05, + "loss": 4.0439, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475865832701654e-05, + "loss": 4.0489, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467479885191134e-05, + "loss": 4.0528, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745909393768062e-05, + "loss": 4.0416, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74507079901701e-05, + "loss": 4.0457, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744232204265958e-05, + "loss": 4.0459, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743393609514906e-05, + "loss": 4.0448, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742555014763854e-05, + "loss": 4.0501, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741716420012802e-05, + "loss": 4.0451, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74087782526175e-05, + "loss": 4.0477, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740039230510698e-05, + "loss": 4.0527, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739200635759646e-05, + "loss": 4.0342, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738362041008594e-05, + "loss": 4.0424, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737523446257542e-05, + "loss": 4.0328, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736686489386863e-05, + "loss": 4.0465, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735847894635811e-05, + "loss": 4.0417, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735009299884759e-05, + "loss": 4.0381, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734170705133707e-05, + "loss": 4.05, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733332110382655e-05, + "loss": 4.0515, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732493515631603e-05, + "loss": 4.053, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731654920880551e-05, + "loss": 4.0486, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308179640098725e-05, + "loss": 4.0428, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.72997936925882e-05, + "loss": 4.0428, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729140774507768e-05, + "loss": 4.0427, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728302179756716e-05, + "loss": 4.0425, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727463585005664e-05, + "loss": 4.0426, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726626628134985e-05, + "loss": 4.0352, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725788033383933e-05, + "loss": 4.0371, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724949438632881e-05, + "loss": 4.0379, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724112481762202e-05, + "loss": 4.0438, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72327388701115e-05, + "loss": 4.0521, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722435292260098e-05, + "loss": 4.0409, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721596697509046e-05, + "loss": 4.0411, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720758102757994e-05, + "loss": 4.0371, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719919508006942e-05, + "loss": 4.0499, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.71908091325589e-05, + "loss": 4.0387, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718242318504838e-05, + "loss": 4.0399, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717403723753786e-05, + "loss": 4.0275, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716565129002734e-05, + "loss": 4.0379, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715726534251682e-05, + "loss": 4.0393, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.71488793950063e-05, + "loss": 4.0437, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714050982629951e-05, + "loss": 4.0383, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713212387878899e-05, + "loss": 4.0393, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712375431008221e-05, + "loss": 4.0383, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711536836257169e-05, + "loss": 4.0434, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710698241506117e-05, + "loss": 4.04, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709859646755065e-05, + "loss": 4.0123, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090226898843856e-05, + "loss": 4.0446, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081840951333336e-05, + "loss": 4.038, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073471382626545e-05, + "loss": 4.0464, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065085435116025e-05, + "loss": 4.0339, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056699487605505e-05, + "loss": 4.0316, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048313540094985e-05, + "loss": 4.031, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039927592584465e-05, + "loss": 4.0295, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031541645073945e-05, + "loss": 4.0412, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023155697563425e-05, + "loss": 4.0174, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014769750052905e-05, + "loss": 4.0456, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006383802542385e-05, + "loss": 4.0306, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997997855031865e-05, + "loss": 4.026, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989611907521345e-05, + "loss": 4.052, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981225960010824e-05, + "loss": 4.027, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972856391304034e-05, + "loss": 4.0199, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964470443793514e-05, + "loss": 4.0386, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956084496282993e-05, + "loss": 4.0385, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69477149275762e-05, + "loss": 4.027, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693932898006568e-05, + "loss": 4.0344, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693094303255516e-05, + "loss": 4.018, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692255708504464e-05, + "loss": 4.0326, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691417113753413e-05, + "loss": 4.0411, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690578519002361e-05, + "loss": 4.0394, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689739924251309e-05, + "loss": 4.0358, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.68890296738063e-05, + "loss": 4.0406, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688064372629578e-05, + "loss": 4.0565, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687225777878526e-05, + "loss": 4.0326, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686387183127474e-05, + "loss": 4.0354, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685548588376422e-05, + "loss": 4.0339, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684711631505743e-05, + "loss": 4.0342, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683873036754691e-05, + "loss": 4.0264, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683034442003639e-05, + "loss": 4.0459, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682195847252587e-05, + "loss": 4.0386, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681357252501535e-05, + "loss": 4.047, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680520295630856e-05, + "loss": 4.0205, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679681700879804e-05, + "loss": 4.0315, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678843106128752e-05, + "loss": 4.0312, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780045113777e-05, + "loss": 4.0339, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677165916626648e-05, + "loss": 4.0346, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676328959755969e-05, + "loss": 4.0364, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675490365004917e-05, + "loss": 4.0199, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674651770253865e-05, + "loss": 4.0342, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673813175502813e-05, + "loss": 4.0305, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672974580751761e-05, + "loss": 4.0263, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672135986000709e-05, + "loss": 4.0401, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712973912496565e-05, + "loss": 4.043, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704587964986045e-05, + "loss": 4.0296, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669621839627926e-05, + "loss": 4.0299, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668783244876875e-05, + "loss": 4.032, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6679462880061956e-05, + "loss": 4.0276, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671076932551436e-05, + "loss": 4.0391, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6662690985040916e-05, + "loss": 4.0312, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6654305037530396e-05, + "loss": 4.0307, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664591909001987e-05, + "loss": 4.0333, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663753314250935e-05, + "loss": 4.0288, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629163573802565e-05, + "loss": 4.028, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620794005095774e-05, + "loss": 4.0258, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612408057585254e-05, + "loss": 4.0189, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604022110074734e-05, + "loss": 4.0357, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595636162564214e-05, + "loss": 4.0288, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587250215053694e-05, + "loss": 4.0301, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657888064634691e-05, + "loss": 4.0164, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657049469883639e-05, + "loss": 4.0337, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656210875132587e-05, + "loss": 4.0338, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655372280381534e-05, + "loss": 4.0227, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654535323510856e-05, + "loss": 4.0314, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653696728759804e-05, + "loss": 4.0447, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652858134008751e-05, + "loss": 4.0275, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652019539257699e-05, + "loss": 4.0367, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651180944506647e-05, + "loss": 4.0283, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650342349755595e-05, + "loss": 4.036, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649503755004544e-05, + "loss": 4.035, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648665160253492e-05, + "loss": 4.0252, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64782656550244e-05, + "loss": 4.0209, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646987970751388e-05, + "loss": 4.0291, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646149376000336e-05, + "loss": 4.0296, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645310781249284e-05, + "loss": 4.0278, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644475462258978e-05, + "loss": 4.0186, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643636867507926e-05, + "loss": 4.029, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642798272756874e-05, + "loss": 4.0169, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6419596780058217e-05, + "loss": 4.0385, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411210832547697e-05, + "loss": 4.026, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402824885037176e-05, + "loss": 4.0358, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394438937526656e-05, + "loss": 4.0172, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386052990016136e-05, + "loss": 4.0374, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637768342130935e-05, + "loss": 4.0325, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636931385260256e-05, + "loss": 4.0309, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636092790509204e-05, + "loss": 4.0325, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635254195758152e-05, + "loss": 4.0268, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344156010071e-05, + "loss": 4.029, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633577006256048e-05, + "loss": 4.043, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632738411504996e-05, + "loss": 4.0158, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631899816753944e-05, + "loss": 4.0333, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631061222002892e-05, + "loss": 4.0228, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630224265132213e-05, + "loss": 4.0257, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629385670381161e-05, + "loss": 4.0285, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628547075630109e-05, + "loss": 4.0217, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627708480879058e-05, + "loss": 4.0322, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268731618887515e-05, + "loss": 4.0324, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260345671376995e-05, + "loss": 4.0257, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.059869766235352, + "eval_runtime": 295.5689, + "eval_samples_per_second": 1291.039, + "eval_steps_per_second": 40.346, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251959723866475e-05, + "loss": 4.0207, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243573776355955e-05, + "loss": 4.0227, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6235187828845435e-05, + "loss": 4.026, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6226801881334915e-05, + "loss": 4.0291, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6218415933824395e-05, + "loss": 4.0326, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210029986313875e-05, + "loss": 4.0231, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620164403880335e-05, + "loss": 4.0283, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6193274470096564e-05, + "loss": 4.0263, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6184888522586044e-05, + "loss": 4.0233, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617651895387926e-05, + "loss": 4.0262, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616813300636874e-05, + "loss": 4.0326, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615974705885822e-05, + "loss": 4.026, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.61513611113477e-05, + "loss": 4.0318, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614297516383717e-05, + "loss": 4.0146, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613458921632665e-05, + "loss": 4.024, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612620326881613e-05, + "loss": 4.01, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611781732130561e-05, + "loss": 4.0333, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610944775259882e-05, + "loss": 4.0217, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61010618050883e-05, + "loss": 4.0166, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609269223638152e-05, + "loss": 4.0318, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6084306288871e-05, + "loss": 4.0321, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607592034136048e-05, + "loss": 4.0313, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606753439384996e-05, + "loss": 4.0311, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605914844633944e-05, + "loss": 4.0239, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605076249882892e-05, + "loss": 4.0254, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.60423765513184e-05, + "loss": 4.0283, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603399060380788e-05, + "loss": 4.0155, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602560465629736e-05, + "loss": 4.0247, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017235087590566e-05, + "loss": 4.0207, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008849140080046e-05, + "loss": 4.0175, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6000463192569526e-05, + "loss": 4.0198, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992093623862735e-05, + "loss": 4.0267, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5983707676352215e-05, + "loss": 4.0289, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.59753217288417e-05, + "loss": 4.0302, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596693578133118e-05, + "loss": 4.0198, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595856621262439e-05, + "loss": 4.018, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595018026511387e-05, + "loss": 4.0301, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594179431760335e-05, + "loss": 4.0155, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593340837009283e-05, + "loss": 4.0237, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592502242258231e-05, + "loss": 4.011, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591663647507179e-05, + "loss": 4.0127, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590825052756127e-05, + "loss": 4.022, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589986458005075e-05, + "loss": 4.0265, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589149501134396e-05, + "loss": 4.0192, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588312544263717e-05, + "loss": 4.0187, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874739495126656e-05, + "loss": 4.0205, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866353547616136e-05, + "loss": 4.022, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857967600105615e-05, + "loss": 4.0234, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849581652595095e-05, + "loss": 3.9963, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841195705084575e-05, + "loss": 4.0231, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5832809757574055e-05, + "loss": 4.017, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824440188867264e-05, + "loss": 4.0297, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816054241356744e-05, + "loss": 4.0147, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807668293846224e-05, + "loss": 4.0109, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799282346335704e-05, + "loss": 4.0125, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790896398825184e-05, + "loss": 4.0083, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578251045131466e-05, + "loss": 4.0226, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577412450380414e-05, + "loss": 3.9978, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5765738556293624e-05, + "loss": 4.0288, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575736898758683e-05, + "loss": 4.0146, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574898304007631e-05, + "loss": 4.0064, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574059709256579e-05, + "loss": 4.0321, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573221114505527e-05, + "loss": 4.0087, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572384157634848e-05, + "loss": 4.0035, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571545562883796e-05, + "loss": 4.0192, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570706968132744e-05, + "loss": 4.0205, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569868373381692e-05, + "loss": 4.0046, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.56902977863064e-05, + "loss": 4.0188, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568192821759961e-05, + "loss": 3.9985, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567354227008909e-05, + "loss": 4.0133, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566515632257858e-05, + "loss": 4.0236, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565677037506806e-05, + "loss": 4.0201, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564840080636127e-05, + "loss": 4.0194, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564003123765448e-05, + "loss": 4.021, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631645290143956e-05, + "loss": 4.0385, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5623259342633436e-05, + "loss": 4.0147, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5614873395122916e-05, + "loss": 4.0199, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5606487447612396e-05, + "loss": 4.0114, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598101500101876e-05, + "loss": 4.0146, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589715552591356e-05, + "loss": 4.0102, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581329605080836e-05, + "loss": 4.0252, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5572943657570316e-05, + "loss": 4.0206, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5564557710059796e-05, + "loss": 4.0265, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556171762549275e-05, + "loss": 4.0068, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547785815038755e-05, + "loss": 4.0122, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553939986752824e-05, + "loss": 4.0125, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553103029882145e-05, + "loss": 4.0126, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552266073011466e-05, + "loss": 4.0163, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551427478260414e-05, + "loss": 4.0186, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550588883509362e-05, + "loss": 4.0062, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549751926638683e-05, + "loss": 4.0139, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548913331887631e-05, + "loss": 4.0124, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548074737136579e-05, + "loss": 4.0054, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547236142385527e-05, + "loss": 4.0228, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546397547634475e-05, + "loss": 4.0246, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545558952883423e-05, + "loss": 4.0149, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544720358132371e-05, + "loss": 4.0071, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438817633813196e-05, + "loss": 4.0164, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543043168630267e-05, + "loss": 4.0086, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422062117595885e-05, + "loss": 4.0177, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5413676170085365e-05, + "loss": 4.0183, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405290222574845e-05, + "loss": 4.0081, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539690427506432e-05, + "loss": 4.0165, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53885183275538e-05, + "loss": 4.0105, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5380148758847014e-05, + "loss": 4.0106, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371762811336494e-05, + "loss": 4.0054, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536337686382597e-05, + "loss": 4.0044, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535499091631545e-05, + "loss": 4.0143, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534662134760866e-05, + "loss": 4.0136, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533823540009814e-05, + "loss": 4.0111, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532986583139136e-05, + "loss": 3.9991, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532147988388084e-05, + "loss": 4.0108, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531309393637032e-05, + "loss": 4.0173, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530470798885979e-05, + "loss": 4.0041, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529633842015301e-05, + "loss": 4.0156, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528795247264249e-05, + "loss": 4.0239, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527956652513197e-05, + "loss": 4.0137, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527118057762144e-05, + "loss": 4.0143, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526279463011092e-05, + "loss": 4.0143, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52544086826004e-05, + "loss": 4.0163, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524602273508989e-05, + "loss": 4.0166, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523763678757937e-05, + "loss": 4.0047, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5229267218872576e-05, + "loss": 4.005, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5220881271362056e-05, + "loss": 4.0109, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5212495323851536e-05, + "loss": 4.011, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204109376341016e-05, + "loss": 4.0069, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5195739807634225e-05, + "loss": 4.0073, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5187353860123705e-05, + "loss": 4.0049, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5178967912613185e-05, + "loss": 4.0013, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170581965102665e-05, + "loss": 4.021, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162196017592145e-05, + "loss": 4.0085, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153810070081625e-05, + "loss": 4.0203, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145424122571105e-05, + "loss": 3.9974, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513705455386432e-05, + "loss": 4.0209, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51286686063538e-05, + "loss": 4.016, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512028265884328e-05, + "loss": 4.0126, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511189671133276e-05, + "loss": 4.0102, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510351076382224e-05, + "loss": 4.013, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509512481631172e-05, + "loss": 4.013, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.50867388688012e-05, + "loss": 4.0188, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507835292129068e-05, + "loss": 4.0037, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.506998335258389e-05, + "loss": 4.0106, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.50616137838771e-05, + "loss": 4.0098, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505322783636658e-05, + "loss": 4.0081, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044858267659795e-05, + "loss": 4.0071, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036472320149275e-05, + "loss": 4.009, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028086372638755e-05, + "loss": 4.0132, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5019700425128234e-05, + "loss": 4.0135, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5011314477617714e-05, + "loss": 4.0076, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.048203468322754, + "eval_runtime": 298.4768, + "eval_samples_per_second": 1278.461, + "eval_steps_per_second": 39.953, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002928530107194e-05, + "loss": 4.0159, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4994542582596674e-05, + "loss": 4.0036, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986156635086154e-05, + "loss": 4.0095, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497777068757563e-05, + "loss": 4.0124, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496938474006511e-05, + "loss": 4.0095, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496099879255459e-05, + "loss": 4.0108, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495261284504407e-05, + "loss": 4.0127, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494422689753355e-05, + "loss": 4.0082, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493584095002303e-05, + "loss": 4.0034, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492745500251251e-05, + "loss": 4.0105, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491906905500199e-05, + "loss": 4.0142, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910683107491474e-05, + "loss": 4.0051, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902297159980954e-05, + "loss": 4.021, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893911212470434e-05, + "loss": 3.9922, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885525264959914e-05, + "loss": 4.0044, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877139317449394e-05, + "loss": 3.9954, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.48687697487426e-05, + "loss": 4.0161, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486038380123208e-05, + "loss": 4.0027, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485201423252529e-05, + "loss": 4.0005, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484362828501477e-05, + "loss": 4.009, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483524233750425e-05, + "loss": 4.0175, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482685638999373e-05, + "loss": 4.0135, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481847044248321e-05, + "loss": 4.0113, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481008449497269e-05, + "loss": 4.0068, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480169854746217e-05, + "loss": 4.011, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479331259995165e-05, + "loss": 4.0059, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478492665244113e-05, + "loss": 3.9971, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477654070493061e-05, + "loss": 4.0055, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476815475742009e-05, + "loss": 4.0038, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475976880990957e-05, + "loss": 3.9977, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475139924120278e-05, + "loss": 4.0046, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474301329369226e-05, + "loss": 4.0061, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473462734618174e-05, + "loss": 4.0122, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472624139867122e-05, + "loss": 4.0141, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47178554511607e-05, + "loss": 4.002, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709502261257645e-05, + "loss": 4.0008, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701116313747125e-05, + "loss": 4.0126, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469274674504034e-05, + "loss": 3.9972, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4684360797529814e-05, + "loss": 4.0039, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4675974850019294e-05, + "loss": 3.9976, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4667588902508774e-05, + "loss": 3.9948, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4659202954998254e-05, + "loss": 4.0038, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4650817007487734e-05, + "loss": 4.0087, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4642431059977214e-05, + "loss": 4.0, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634045112466694e-05, + "loss": 4.0014, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4625659164956174e-05, + "loss": 4.0038, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617273217445654e-05, + "loss": 4.0036, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608887269935134e-05, + "loss": 4.0091, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600501322424614e-05, + "loss": 3.9813, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459213175371783e-05, + "loss": 4.0065, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458374580620731e-05, + "loss": 3.9994, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457535985869679e-05, + "loss": 4.0131, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456697391118627e-05, + "loss": 3.9952, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455862072128321e-05, + "loss": 3.9968, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455023477377269e-05, + "loss": 3.9933, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454184882626217e-05, + "loss": 3.9928, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453346287875165e-05, + "loss": 4.0049, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452507693124113e-05, + "loss": 3.979, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451669098373061e-05, + "loss": 4.0127, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450830503622009e-05, + "loss": 3.9974, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449991908870957e-05, + "loss": 3.9868, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449156589880651e-05, + "loss": 4.0169, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448317995129599e-05, + "loss": 3.9873, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447479400378547e-05, + "loss": 3.9863, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446640805627495e-05, + "loss": 3.9996, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445802210876443e-05, + "loss": 4.0055, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444963616125391e-05, + "loss": 3.991, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444125021374339e-05, + "loss": 3.9998, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.44328806450366e-05, + "loss": 3.9807, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442449469752608e-05, + "loss": 3.9964, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441610875001556e-05, + "loss": 4.0051, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440772280250504e-05, + "loss": 4.0061, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439933685499452e-05, + "loss": 3.9987, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4390950907484e-05, + "loss": 4.0042, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438256495997348e-05, + "loss": 4.0203, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43741953912667e-05, + "loss": 3.9971, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436580944375618e-05, + "loss": 4.0057, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435742349624565e-05, + "loss": 3.9915, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434903754873513e-05, + "loss": 3.9989, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434065160122461e-05, + "loss": 3.9908, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433228203251782e-05, + "loss": 4.0086, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43238960850073e-05, + "loss": 4.0029, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431551013749678e-05, + "loss": 4.0121, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430712418998626e-05, + "loss": 3.9922, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298754621279475e-05, + "loss": 3.9919, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290368673768955e-05, + "loss": 3.9933, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281982726258435e-05, + "loss": 4.0024, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4273596778747915e-05, + "loss": 3.9955, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265210831237395e-05, + "loss": 4.0021, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4256824883726875e-05, + "loss": 3.991, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4248438936216355e-05, + "loss": 3.9954, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4240052988705835e-05, + "loss": 3.9947, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4231683419999044e-05, + "loss": 3.9904, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4223297472488524e-05, + "loss": 4.0021, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4214911524978004e-05, + "loss": 4.0096, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4206525577467484e-05, + "loss": 4.0002, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4198139629956964e-05, + "loss": 3.9914, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4189753682446443e-05, + "loss": 3.9946, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181367734935923e-05, + "loss": 3.9949, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.41729817874254e-05, + "loss": 4.002, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416461221871862e-05, + "loss": 3.9985, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.41562262712081e-05, + "loss": 3.9895, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414785670250131e-05, + "loss": 4.002, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413948713379452e-05, + "loss": 3.996, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131101186284e-05, + "loss": 3.994, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412271523877348e-05, + "loss": 3.9903, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411432929126296e-05, + "loss": 3.9902, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410594334375244e-05, + "loss": 3.9933, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409755739624192e-05, + "loss": 3.9977, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.40891714487314e-05, + "loss": 3.9918, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408078550122088e-05, + "loss": 3.9828, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407239955371036e-05, + "loss": 3.9934, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406402998500357e-05, + "loss": 4.001, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405564403749305e-05, + "loss": 3.9923, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404727446878626e-05, + "loss": 3.9962, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403888852127574e-05, + "loss": 4.0039, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403050257376522e-05, + "loss": 3.9985, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.40221166262547e-05, + "loss": 3.9977, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401373067874418e-05, + "loss": 3.999, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005344731233655e-05, + "loss": 3.9996, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3996958783723135e-05, + "loss": 4.0057, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398858921501635e-05, + "loss": 3.9848, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398020326750583e-05, + "loss": 3.9922, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397181731999531e-05, + "loss": 3.9894, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963447751288527e-05, + "loss": 3.9961, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955061803778007e-05, + "loss": 3.9919, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394667585626748e-05, + "loss": 3.9896, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393828990875696e-05, + "loss": 3.986, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392990396124644e-05, + "loss": 3.9876, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392151801373592e-05, + "loss": 4.0043, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.39131320662254e-05, + "loss": 3.9961, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390474611871488e-05, + "loss": 3.9981, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389636017120436e-05, + "loss": 3.9865, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388797422369384e-05, + "loss": 4.0022, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387958827618332e-05, + "loss": 4.0012, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871235086280264e-05, + "loss": 3.9972, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862849138769744e-05, + "loss": 3.9902, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854463191259224e-05, + "loss": 3.9973, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846077243748704e-05, + "loss": 3.9992, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3837691296238184e-05, + "loss": 4.0022, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3829305348727664e-05, + "loss": 3.9888, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3820919401217144e-05, + "loss": 3.9931, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812533453706624e-05, + "loss": 3.9925, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380416388499983e-05, + "loss": 3.9946, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379577793748931e-05, + "loss": 3.9887, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378739198997879e-05, + "loss": 3.9959, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377900604246827e-05, + "loss": 3.9911, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377062009495775e-05, + "loss": 4.0014, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376225052625097e-05, + "loss": 3.9916, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.038919448852539, + "eval_runtime": 278.9967, + "eval_samples_per_second": 1367.726, + "eval_steps_per_second": 42.742, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375386457874045e-05, + "loss": 4.0042, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374547863122993e-05, + "loss": 3.988, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373709268371941e-05, + "loss": 3.9924, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372870673620889e-05, + "loss": 3.9998, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372032078869837e-05, + "loss": 3.9939, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371193484118784e-05, + "loss": 3.9952, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370354889367732e-05, + "loss": 3.9921, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.36951629461668e-05, + "loss": 3.9934, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368677699865628e-05, + "loss": 3.9879, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367839105114576e-05, + "loss": 3.9999, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367000510363524e-05, + "loss": 3.993, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366161915612472e-05, + "loss": 3.9963, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.36532332086142e-05, + "loss": 4.005, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364484726110368e-05, + "loss": 3.9786, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363646131359317e-05, + "loss": 3.9893, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362807536608265e-05, + "loss": 3.9795, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361968941857213e-05, + "loss": 4.0021, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361130347106161e-05, + "loss": 3.9847, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360293390235482e-05, + "loss": 3.988, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.35945479548443e-05, + "loss": 3.9918, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358616200733378e-05, + "loss": 4.0042, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357777605982326e-05, + "loss": 3.9952, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356939011231273e-05, + "loss": 3.9983, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356100416480221e-05, + "loss": 3.9906, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355261821729169e-05, + "loss": 3.9982, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354423226978117e-05, + "loss": 3.9882, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3535862701074386e-05, + "loss": 3.9856, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.35274931323676e-05, + "loss": 3.9888, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351910718485708e-05, + "loss": 3.9868, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351072123734656e-05, + "loss": 3.9831, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3502335289836035e-05, + "loss": 3.9873, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3493949342325515e-05, + "loss": 3.9919, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.3485563394814995e-05, + "loss": 3.998, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3477177447304475e-05, + "loss": 3.9963, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3468807878597684e-05, + "loss": 3.988, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.34604383098909e-05, + "loss": 3.9863, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345205236238038e-05, + "loss": 4.0029, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344366641486986e-05, + "loss": 3.9756, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343528046735934e-05, + "loss": 3.994, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342689451984882e-05, + "loss": 3.9838, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.34185085723383e-05, + "loss": 3.9747, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341012262482778e-05, + "loss": 3.9903, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340173667731726e-05, + "loss": 3.9953, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339335072980674e-05, + "loss": 3.9869, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338496478229622e-05, + "loss": 3.9881, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337659521358943e-05, + "loss": 3.9869, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336820926607891e-05, + "loss": 3.9875, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.335982331856839e-05, + "loss": 3.9947, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335143737105787e-05, + "loss": 3.9666, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334305142354735e-05, + "loss": 3.9865, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333466547603683e-05, + "loss": 3.9878, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3326295907330044e-05, + "loss": 4.0009, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3317909959819524e-05, + "loss": 3.979, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3309524012309004e-05, + "loss": 3.9853, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3301138064798484e-05, + "loss": 3.9703, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3292752117287964e-05, + "loss": 3.9805, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3284366169777444e-05, + "loss": 3.9928, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327598022226692e-05, + "loss": 3.9639, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.32675942747564e-05, + "loss": 3.9944, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.325920832724588e-05, + "loss": 3.9863, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325082237973536e-05, + "loss": 3.9754, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242452811028566e-05, + "loss": 3.9997, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3234066863518046e-05, + "loss": 3.9722, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322569729481126e-05, + "loss": 3.9719, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321731134730074e-05, + "loss": 3.9822, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320892539979022e-05, + "loss": 3.9949, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.32005394522797e-05, + "loss": 3.9764, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319215350476918e-05, + "loss": 3.984, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318376755725866e-05, + "loss": 3.9661, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317539798855187e-05, + "loss": 3.9811, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316701204104135e-05, + "loss": 3.9906, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315862609353083e-05, + "loss": 3.9953, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315024014602031e-05, + "loss": 3.9829, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314185419850979e-05, + "loss": 3.9925, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313346825099927e-05, + "loss": 4.0006, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312509868229248e-05, + "loss": 3.986, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311671273478196e-05, + "loss": 3.9864, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3108326787271446e-05, + "loss": 3.9813, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.3099940839760926e-05, + "loss": 3.9865, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3091554892250406e-05, + "loss": 3.9785, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3083168944739886e-05, + "loss": 3.9892, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3074782997229366e-05, + "loss": 3.9878, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3066413428522575e-05, + "loss": 3.9996, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3058043859815784e-05, + "loss": 3.985, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3049657912305264e-05, + "loss": 3.9754, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3041271964794744e-05, + "loss": 3.9769, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3032886017284224e-05, + "loss": 3.988, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3024500069773704e-05, + "loss": 3.9757, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3016114122263184e-05, + "loss": 3.9897, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3007728174752664e-05, + "loss": 3.979, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.2999342227242144e-05, + "loss": 3.9801, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299097265853536e-05, + "loss": 3.9815, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298258671102484e-05, + "loss": 3.9795, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297420076351432e-05, + "loss": 3.9871, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.29658148160038e-05, + "loss": 3.9914, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295744524729701e-05, + "loss": 3.9893, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294907567859022e-05, + "loss": 3.9749, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.29406897310797e-05, + "loss": 3.9839, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293230378356918e-05, + "loss": 3.9792, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292391783605866e-05, + "loss": 3.9869, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291553188854814e-05, + "loss": 3.989, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290714594103762e-05, + "loss": 3.9723, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.28987599935271e-05, + "loss": 3.9872, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2890374046016584e-05, + "loss": 3.9802, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288198809850606e-05, + "loss": 3.979, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2873618529799273e-05, + "loss": 3.9783, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286523258228875e-05, + "loss": 3.9751, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.2856846634778227e-05, + "loss": 3.98, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2848460687267707e-05, + "loss": 3.9855, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2840074739757186e-05, + "loss": 3.9776, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.28317051710504e-05, + "loss": 3.9691, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2823319223539876e-05, + "loss": 3.9776, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2814933276029355e-05, + "loss": 3.99, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2806547328518835e-05, + "loss": 3.9766, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279817775981205e-05, + "loss": 3.983, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.278979181230153e-05, + "loss": 3.9864, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278140586479101e-05, + "loss": 3.9905, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277301991728049e-05, + "loss": 3.9849, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276463396976997e-05, + "loss": 3.9824, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275624802225945e-05, + "loss": 3.9886, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274786207474893e-05, + "loss": 3.989, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273947612723841e-05, + "loss": 3.973, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273110655853162e-05, + "loss": 3.979, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.27227206110211e-05, + "loss": 3.9707, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271435104231431e-05, + "loss": 3.9847, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270596509480379e-05, + "loss": 3.9792, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269757914729327e-05, + "loss": 3.9731, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2689193199782756e-05, + "loss": 3.971, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2680823631075965e-05, + "loss": 3.9773, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672437683565445e-05, + "loss": 3.9889, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2664051736054925e-05, + "loss": 3.983, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2655665788544405e-05, + "loss": 3.9812, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2647279841033885e-05, + "loss": 3.9726, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2638893893523365e-05, + "loss": 3.988, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2630507946012845e-05, + "loss": 3.9873, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262215475610978e-05, + "loss": 3.9854, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261376880859926e-05, + "loss": 3.9779, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260538286108874e-05, + "loss": 3.9829, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259699691357822e-05, + "loss": 3.9861, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258861096606771e-05, + "loss": 3.9899, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258022501855719e-05, + "loss": 3.9765, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.25718554498504e-05, + "loss": 3.9746, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256346950233988e-05, + "loss": 3.9841, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255508355482936e-05, + "loss": 3.9805, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254669760731884e-05, + "loss": 3.9719, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253831165980832e-05, + "loss": 3.9851, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.25299257122978e-05, + "loss": 3.9756, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252153976478728e-05, + "loss": 3.9918, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251315381727676e-05, + "loss": 3.9715, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.030765056610107, + "eval_runtime": 293.0561, + "eval_samples_per_second": 1302.109, + "eval_steps_per_second": 40.692, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250476786976624e-05, + "loss": 3.9817, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249639830105945e-05, + "loss": 3.9751, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248801235354893e-05, + "loss": 3.9786, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247962640603841e-05, + "loss": 3.9867, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247124045852789e-05, + "loss": 3.9802, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246285451101737e-05, + "loss": 3.9822, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245446856350685e-05, + "loss": 3.9799, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244608261599633e-05, + "loss": 3.9791, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243769666848581e-05, + "loss": 3.9767, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2429327099779016e-05, + "loss": 3.9846, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2420941152268496e-05, + "loss": 3.983, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2412555204757976e-05, + "loss": 3.9827, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2404185636051185e-05, + "loss": 3.9891, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.2395799688540665e-05, + "loss": 3.9672, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2387413741030145e-05, + "loss": 3.9746, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237902779351963e-05, + "loss": 3.9662, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237065822481284e-05, + "loss": 3.9874, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236227227730232e-05, + "loss": 3.9723, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.23538863297918e-05, + "loss": 3.9729, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234550038228128e-05, + "loss": 3.9817, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233711443477076e-05, + "loss": 3.9879, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232874486606397e-05, + "loss": 3.9836, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232035891855345e-05, + "loss": 3.9818, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231197297104293e-05, + "loss": 3.9813, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230358702353241e-05, + "loss": 3.9841, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229520107602189e-05, + "loss": 3.9719, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228681512851137e-05, + "loss": 3.9751, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227842918100085e-05, + "loss": 3.9785, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2270059612294065e-05, + "loss": 3.972, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2261673664783545e-05, + "loss": 3.9658, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2253287717273025e-05, + "loss": 3.9754, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2244901769762505e-05, + "loss": 3.9738, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2236515822251985e-05, + "loss": 3.9873, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2228129874741465e-05, + "loss": 3.9838, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2219760306034674e-05, + "loss": 3.9715, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221139073732788e-05, + "loss": 3.9782, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220300478981736e-05, + "loss": 3.9871, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219461884230684e-05, + "loss": 3.9621, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218623289479632e-05, + "loss": 3.984, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.21778469472858e-05, + "loss": 3.9662, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.216946099977528e-05, + "loss": 3.9644, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216107505226476e-05, + "loss": 3.9766, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215268910475425e-05, + "loss": 3.9882, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214430315724372e-05, + "loss": 3.9664, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.21359172097332e-05, + "loss": 3.975, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212753126222268e-05, + "loss": 3.9743, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.211914531471216e-05, + "loss": 3.9736, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211075936720164e-05, + "loss": 3.9787, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210238979849485e-05, + "loss": 3.9588, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209400385098433e-05, + "loss": 3.975, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208561790347381e-05, + "loss": 3.9772, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207724833476702e-05, + "loss": 3.9828, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.20688623872565e-05, + "loss": 3.9637, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206047643974599e-05, + "loss": 3.9658, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205209049223547e-05, + "loss": 3.9689, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2043720923528677e-05, + "loss": 3.9621, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2035334976018157e-05, + "loss": 3.9822, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2026949028507636e-05, + "loss": 3.9505, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2018579459800846e-05, + "loss": 3.9779, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2010193512290326e-05, + "loss": 3.9729, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2001807564779806e-05, + "loss": 3.9659, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1993421617269285e-05, + "loss": 3.984, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1985035669758765e-05, + "loss": 3.9616, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1976649722248245e-05, + "loss": 3.9592, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1968263774737725e-05, + "loss": 3.9639, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1959877827227205e-05, + "loss": 3.9857, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195150825852042e-05, + "loss": 3.9645, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.19431223110099e-05, + "loss": 3.9647, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193473636349938e-05, + "loss": 3.958, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192635041598886e-05, + "loss": 3.9643, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191796446847834e-05, + "loss": 3.9796, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.190957852096782e-05, + "loss": 3.9826, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190120895226103e-05, + "loss": 3.9672, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189282300475051e-05, + "loss": 3.9816, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188443705723999e-05, + "loss": 3.9861, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187605110972947e-05, + "loss": 3.9734, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186766516221895e-05, + "loss": 3.9724, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.185927921470843e-05, + "loss": 3.9688, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185089326719791e-05, + "loss": 3.9756, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184250731968739e-05, + "loss": 3.9669, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.1834154129784335e-05, + "loss": 3.9749, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.1825768182273815e-05, + "loss": 3.9769, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.1817382234763295e-05, + "loss": 3.9853, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1808996287252775e-05, + "loss": 3.9732, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1800610339742255e-05, + "loss": 3.9586, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1792240771035464e-05, + "loss": 3.9634, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1783854823524944e-05, + "loss": 3.9772, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1775468876014424e-05, + "loss": 3.9636, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1767082928503904e-05, + "loss": 3.9755, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175869698099338e-05, + "loss": 3.9686, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1750311033482863e-05, + "loss": 3.9658, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174194146477608e-05, + "loss": 3.964, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173355551726556e-05, + "loss": 3.9693, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172516956975503e-05, + "loss": 3.9752, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171678362224451e-05, + "loss": 3.9793, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170839767473399e-05, + "loss": 3.9734, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170001172722347e-05, + "loss": 3.9626, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169164215851668e-05, + "loss": 3.9713, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168325621100616e-05, + "loss": 3.9703, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167487026349564e-05, + "loss": 3.9723, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166648431598512e-05, + "loss": 3.9761, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165811474727833e-05, + "loss": 3.958, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164972879976782e-05, + "loss": 3.9745, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.16413428522573e-05, + "loss": 3.9686, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163295690474678e-05, + "loss": 3.9654, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1624587336039986e-05, + "loss": 3.9634, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1616201388529466e-05, + "loss": 3.9653, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1607815441018946e-05, + "loss": 3.9674, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1599429493508426e-05, + "loss": 3.973, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1591043545997906e-05, + "loss": 3.9649, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1582657598487386e-05, + "loss": 3.956, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1574271650976866e-05, + "loss": 3.9608, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1565885703466346e-05, + "loss": 3.9784, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1557516134759555e-05, + "loss": 3.9637, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1549130187249035e-05, + "loss": 3.9679, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1540744239738515e-05, + "loss": 3.9743, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153237467103173e-05, + "loss": 3.9779, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152398872352121e-05, + "loss": 3.9698, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151560277601069e-05, + "loss": 3.9709, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150721682850017e-05, + "loss": 3.9753, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.149883088098965e-05, + "loss": 3.9734, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149044493347913e-05, + "loss": 3.9604, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148205898596861e-05, + "loss": 3.9642, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147368941726182e-05, + "loss": 3.9627, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.14653034697513e-05, + "loss": 3.9664, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145691752224078e-05, + "loss": 3.964, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144853157473026e-05, + "loss": 3.9593, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144016200602347e-05, + "loss": 3.9634, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1431792437316684e-05, + "loss": 3.9663, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1423406489806164e-05, + "loss": 3.9655, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1415020542295644e-05, + "loss": 3.9758, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1406634594785124e-05, + "loss": 3.972, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1398248647274604e-05, + "loss": 3.9601, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1389862699764084e-05, + "loss": 3.9728, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1381476752253564e-05, + "loss": 3.9716, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137309080474304e-05, + "loss": 3.9741, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136470485723252e-05, + "loss": 3.965, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1356318909722e-05, + "loss": 3.9711, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134794934101521e-05, + "loss": 3.9728, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1339563393504686e-05, + "loss": 3.9726, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133117744599417e-05, + "loss": 3.9653, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132280787728739e-05, + "loss": 3.9645, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131442192977687e-05, + "loss": 3.9706, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130603598226634e-05, + "loss": 3.966, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129765003475582e-05, + "loss": 3.9592, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.12892640872453e-05, + "loss": 3.9722, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128087813973478e-05, + "loss": 3.9639, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127249219222426e-05, + "loss": 3.9794, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126410624471374e-05, + "loss": 3.96, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.0235676765441895, + "eval_runtime": 288.3026, + "eval_samples_per_second": 1323.578, + "eval_steps_per_second": 41.363, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125572029720322e-05, + "loss": 3.9599, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.12473343496927e-05, + "loss": 3.9645, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123894840218218e-05, + "loss": 3.9639, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123056245467166e-05, + "loss": 3.975, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122217650716114e-05, + "loss": 3.9649, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121379055965062e-05, + "loss": 3.9717, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.12054046121401e-05, + "loss": 3.9636, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119701866462958e-05, + "loss": 3.9648, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118863271711906e-05, + "loss": 3.965, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118024676960854e-05, + "loss": 3.9713, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117186082209802e-05, + "loss": 3.9661, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.11634748745875e-05, + "loss": 3.9753, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115508892707698e-05, + "loss": 3.9776, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114670297956646e-05, + "loss": 3.9554, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113831703205594e-05, + "loss": 3.9589, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.112993108454542e-05, + "loss": 3.9565, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.11215451370349e-05, + "loss": 3.9717, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111315918952438e-05, + "loss": 3.9661, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110477324201386e-05, + "loss": 3.9574, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109638729450334e-05, + "loss": 3.9649, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108800134699282e-05, + "loss": 3.9749, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.107963177828604e-05, + "loss": 3.9725, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107124583077552e-05, + "loss": 3.968, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1062859883264997e-05, + "loss": 3.9667, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1054490314558206e-05, + "loss": 3.9787, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1046104367047686e-05, + "loss": 3.9588, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1037718419537166e-05, + "loss": 3.9639, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.102933247202664e-05, + "loss": 3.9676, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102094652451612e-05, + "loss": 3.9554, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1012576955809335e-05, + "loss": 3.9599, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1004191008298815e-05, + "loss": 3.9612, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099580506078829e-05, + "loss": 3.9655, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0987419113277774e-05, + "loss": 3.9756, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0979033165767254e-05, + "loss": 3.9675, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0970647218256734e-05, + "loss": 3.9658, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0962277649549943e-05, + "loss": 3.9628, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095390808084316e-05, + "loss": 3.9716, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094552213333264e-05, + "loss": 3.9541, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093713618582211e-05, + "loss": 3.9697, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092875023831159e-05, + "loss": 3.9548, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092036429080107e-05, + "loss": 3.9537, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091197834329055e-05, + "loss": 3.9617, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090359239578003e-05, + "loss": 3.9792, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089520644826951e-05, + "loss": 3.951, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088682050075899e-05, + "loss": 3.9663, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087843455324847e-05, + "loss": 3.963, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087004860573796e-05, + "loss": 3.9617, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086167903703117e-05, + "loss": 3.9676, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085329308952065e-05, + "loss": 3.9432, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084490714201013e-05, + "loss": 3.9615, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083652119449961e-05, + "loss": 3.9688, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082815162579282e-05, + "loss": 3.9681, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.08197656782823e-05, + "loss": 3.9552, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0811396109575506e-05, + "loss": 3.9527, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0803010162064986e-05, + "loss": 3.9563, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0794624214554466e-05, + "loss": 3.9483, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0786238267043946e-05, + "loss": 3.973, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0777852319533426e-05, + "loss": 3.9389, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.076946637202291e-05, + "loss": 3.965, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076108042451239e-05, + "loss": 3.9612, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075269447700187e-05, + "loss": 3.9548, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074430852949135e-05, + "loss": 3.9681, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073593896078456e-05, + "loss": 3.9534, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072755301327404e-05, + "loss": 3.9468, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.071916706576352e-05, + "loss": 3.9494, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071079749705673e-05, + "loss": 3.9774, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070241154954621e-05, + "loss": 3.9518, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069404198083942e-05, + "loss": 3.9527, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.06856560333289e-05, + "loss": 3.9458, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067727008581838e-05, + "loss": 3.9526, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0668884138307866e-05, + "loss": 3.9679, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0660498190797346e-05, + "loss": 3.9693, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0652112243286826e-05, + "loss": 3.953, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0643726295776306e-05, + "loss": 3.9682, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063534034826578e-05, + "loss": 3.9749, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062695440075526e-05, + "loss": 3.9649, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.061856845324474e-05, + "loss": 3.9552, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061019888453795e-05, + "loss": 3.961, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060181293702743e-05, + "loss": 3.961, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059342698951691e-05, + "loss": 3.9585, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058504104200639e-05, + "loss": 3.9587, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057665509449587e-05, + "loss": 3.9698, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056826914698535e-05, + "loss": 3.9717, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.055988319947483e-05, + "loss": 3.9655, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0551513630768044e-05, + "loss": 3.9445, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0543127683257524e-05, + "loss": 3.9507, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0534741735747004e-05, + "loss": 3.9645, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0526355788236484e-05, + "loss": 3.9524, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051798621952969e-05, + "loss": 3.9647, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0509600272019173e-05, + "loss": 3.9557, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0501214324508653e-05, + "loss": 3.9551, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0492828376998133e-05, + "loss": 3.9517, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0484442429487613e-05, + "loss": 3.96, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0476072860780825e-05, + "loss": 3.9608, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0467686913270305e-05, + "loss": 3.9645, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0459300965759785e-05, + "loss": 3.9653, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0450931397052994e-05, + "loss": 3.9484, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0442545449542474e-05, + "loss": 3.9614, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0434159502031957e-05, + "loss": 3.9567, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0425773554521437e-05, + "loss": 3.9609, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0417387607010917e-05, + "loss": 3.9657, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0409001659500397e-05, + "loss": 3.9487, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0400615711989877e-05, + "loss": 3.958, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0392246143283086e-05, + "loss": 3.9597, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0383860195772566e-05, + "loss": 3.9579, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037547424826205e-05, + "loss": 3.9503, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036708830075153e-05, + "loss": 3.9532, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.035870235324101e-05, + "loss": 3.9564, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035031640573049e-05, + "loss": 3.9629, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0341930458219963e-05, + "loss": 3.9505, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0333544510709443e-05, + "loss": 3.948, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032517494200266e-05, + "loss": 3.9474, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0316788994492135e-05, + "loss": 3.9657, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0308403046981615e-05, + "loss": 3.9528, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0300017099471095e-05, + "loss": 3.9552, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029164753076431e-05, + "loss": 3.9657, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0283261583253787e-05, + "loss": 3.9665, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0274875635743267e-05, + "loss": 3.9578, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0266489688232747e-05, + "loss": 3.9585, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0258120119525963e-05, + "loss": 3.9655, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0249734172015436e-05, + "loss": 3.9613, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0241348224504916e-05, + "loss": 3.9504, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0232962276994396e-05, + "loss": 3.9549, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0224576329483876e-05, + "loss": 3.9484, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.021620676077709e-05, + "loss": 3.9568, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.020782081326657e-05, + "loss": 3.9502, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.019943486575605e-05, + "loss": 3.9546, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019104891824553e-05, + "loss": 3.9513, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182679349538738e-05, + "loss": 3.9534, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017429340202822e-05, + "loss": 3.9546, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.01659074545177e-05, + "loss": 3.9642, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015752150700718e-05, + "loss": 3.9633, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.014915193830039e-05, + "loss": 3.9518, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014076599078987e-05, + "loss": 3.9551, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.013238004327935e-05, + "loss": 3.9596, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012399409576883e-05, + "loss": 3.9609, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115608148258313e-05, + "loss": 3.9585, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010725495835526e-05, + "loss": 3.9589, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.009886901084473e-05, + "loss": 3.9614, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009048306333421e-05, + "loss": 3.9587, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008209711582369e-05, + "loss": 3.9546, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0073711168313175e-05, + "loss": 3.9531, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0065325220802655e-05, + "loss": 3.9569, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0056955652095864e-05, + "loss": 3.954, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0048569704585344e-05, + "loss": 3.9473, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0040183757074824e-05, + "loss": 3.9638, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0031797809564304e-05, + "loss": 3.9538, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0023411862053784e-05, + "loss": 3.9642, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0015025914543267e-05, + "loss": 3.9504, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0006639967032747e-05, + "loss": 3.9543, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 4.017756462097168, + "eval_runtime": 294.8347, + "eval_samples_per_second": 1294.254, + "eval_steps_per_second": 40.446, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9998254019522227e-05, + "loss": 3.9566, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9989868072011707e-05, + "loss": 3.948, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9981482124501187e-05, + "loss": 3.9656, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9973096176990667e-05, + "loss": 3.9564, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9964710229480147e-05, + "loss": 3.9609, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.995634066077336e-05, + "loss": 3.9518, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9947971092066568e-05, + "loss": 3.9548, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9939585144556048e-05, + "loss": 3.9495, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9931199197045528e-05, + "loss": 3.9606, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9922813249535008e-05, + "loss": 3.9549, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9914427302024488e-05, + "loss": 3.9664, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9906041354513968e-05, + "loss": 3.9628, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989767178580718e-05, + "loss": 3.9487, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.988928583829666e-05, + "loss": 3.9496, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988089989078614e-05, + "loss": 3.9425, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987251394327562e-05, + "loss": 3.9594, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986414437456883e-05, + "loss": 3.9532, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9855758427058313e-05, + "loss": 3.9512, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9847372479547793e-05, + "loss": 3.9493, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9838986532037266e-05, + "loss": 3.9688, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9830600584526746e-05, + "loss": 3.9575, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9822214637016226e-05, + "loss": 3.9607, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9813828689505706e-05, + "loss": 3.9572, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980544274199519e-05, + "loss": 3.9631, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979705679448467e-05, + "loss": 3.9469, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9788687225777878e-05, + "loss": 3.9547, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9780301278267358e-05, + "loss": 3.9514, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9771915330756838e-05, + "loss": 3.9471, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9763529383246318e-05, + "loss": 3.9477, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975515981453953e-05, + "loss": 3.9486, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.974677386702901e-05, + "loss": 3.9531, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.973838791951849e-05, + "loss": 3.9656, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.973000197200797e-05, + "loss": 3.9557, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.972163240330118e-05, + "loss": 3.9523, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9713279213398128e-05, + "loss": 3.9542, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9704893265887608e-05, + "loss": 3.9579, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9696507318377088e-05, + "loss": 3.9445, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9688121370866568e-05, + "loss": 3.9597, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.967973542335604e-05, + "loss": 3.9416, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967134947584552e-05, + "loss": 3.9467, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9662963528335004e-05, + "loss": 3.9512, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9654577580824484e-05, + "loss": 3.9628, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9646208012117693e-05, + "loss": 3.9427, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9637822064607173e-05, + "loss": 3.9532, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9629436117096653e-05, + "loss": 3.9509, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9621050169586133e-05, + "loss": 3.9494, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9612664222075613e-05, + "loss": 3.9608, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9604294653368826e-05, + "loss": 3.9308, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9595908705858306e-05, + "loss": 3.9491, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9587522758347786e-05, + "loss": 3.9574, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9579136810837266e-05, + "loss": 3.9596, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9570767242130475e-05, + "loss": 3.9469, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9562381294619958e-05, + "loss": 3.9375, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9553995347109438e-05, + "loss": 3.9483, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9545609399598918e-05, + "loss": 3.9354, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9537223452088398e-05, + "loss": 3.9624, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9528837504577878e-05, + "loss": 3.9299, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9520451557067358e-05, + "loss": 3.9534, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9512065609556838e-05, + "loss": 3.9495, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9503696040850047e-05, + "loss": 3.9454, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949532647214326e-05, + "loss": 3.9548, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948694052463274e-05, + "loss": 3.9449, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.947855457712222e-05, + "loss": 3.9342, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.94701686296117e-05, + "loss": 3.9403, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9461799060904908e-05, + "loss": 3.9611, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945341311339439e-05, + "loss": 3.9447, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.94450435446876e-05, + "loss": 3.9437, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943665759717708e-05, + "loss": 3.9328, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942827164966656e-05, + "loss": 3.9407, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.941988570215604e-05, + "loss": 3.9549, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941149975464552e-05, + "loss": 3.9608, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9403113807135e-05, + "loss": 3.9416, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9394727859624484e-05, + "loss": 3.9572, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9386341912113964e-05, + "loss": 3.9652, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9377955964603444e-05, + "loss": 3.9548, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9369570017092924e-05, + "loss": 3.9397, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9361184069582404e-05, + "loss": 3.9515, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9352798122071877e-05, + "loss": 3.952, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.934441217456136e-05, + "loss": 3.9479, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9336042605854576e-05, + "loss": 3.947, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932765665834405e-05, + "loss": 3.9525, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.931927071083353e-05, + "loss": 3.96, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931088476332301e-05, + "loss": 3.9552, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930249881581249e-05, + "loss": 3.9344, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.92941292471057e-05, + "loss": 3.945, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928574329959518e-05, + "loss": 3.949, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.927735735208466e-05, + "loss": 3.9476, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.926897140457414e-05, + "loss": 3.9499, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.926060183586735e-05, + "loss": 3.9467, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.925221588835683e-05, + "loss": 3.9455, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9243829940846314e-05, + "loss": 3.9386, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9235443993335794e-05, + "loss": 3.9474, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9227074424629003e-05, + "loss": 3.9484, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9218688477118483e-05, + "loss": 3.9516, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.92103189084117e-05, + "loss": 3.954, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9201932960901175e-05, + "loss": 3.9412, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9193547013390655e-05, + "loss": 3.948, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9185161065880135e-05, + "loss": 3.9481, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9176775118369615e-05, + "loss": 3.9467, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9168389170859095e-05, + "loss": 3.9556, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9160003223348575e-05, + "loss": 3.9387, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9151617275838055e-05, + "loss": 3.9466, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9143247707131268e-05, + "loss": 3.9479, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9134861759620747e-05, + "loss": 3.9464, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9126475812110227e-05, + "loss": 3.938, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9118089864599707e-05, + "loss": 3.9431, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9109703917089187e-05, + "loss": 3.9502, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9101334348382396e-05, + "loss": 3.9454, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9092948400871876e-05, + "loss": 3.9442, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908456245336136e-05, + "loss": 3.9394, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907617650585084e-05, + "loss": 3.9367, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9067823315947778e-05, + "loss": 3.9579, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9059437368437258e-05, + "loss": 3.9392, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9051051420926738e-05, + "loss": 3.9469, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.904266547341622e-05, + "loss": 3.9499, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.90342795259057e-05, + "loss": 3.9569, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902589357839518e-05, + "loss": 3.9438, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901750763088466e-05, + "loss": 3.9461, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.900912168337414e-05, + "loss": 3.9591, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.900075211466735e-05, + "loss": 3.9504, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899236616715683e-05, + "loss": 3.9394, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8983980219646313e-05, + "loss": 3.9441, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8975610650939523e-05, + "loss": 3.9399, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896724108223273e-05, + "loss": 3.943, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.895885513472221e-05, + "loss": 3.9408, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.895046918721169e-05, + "loss": 3.945, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8942083239701175e-05, + "loss": 3.9385, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8933697292190655e-05, + "loss": 3.9411, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8925311344680135e-05, + "loss": 3.9396, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8916925397169615e-05, + "loss": 3.9588, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8908539449659095e-05, + "loss": 3.9555, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8900153502148575e-05, + "loss": 3.9413, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8891767554638055e-05, + "loss": 3.9431, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8883381607127535e-05, + "loss": 3.9457, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887499565961701e-05, + "loss": 3.9529, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8866642469713956e-05, + "loss": 3.9502, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8858256522203436e-05, + "loss": 3.9465, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8849870574692916e-05, + "loss": 3.9517, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8841484627182396e-05, + "loss": 3.9465, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8833098679671876e-05, + "loss": 3.9459, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.882472911096509e-05, + "loss": 3.9415, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881634316345457e-05, + "loss": 3.9508, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8807973594747777e-05, + "loss": 3.9432, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8799587647237257e-05, + "loss": 3.9339, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8791201699726737e-05, + "loss": 3.9517, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8782815752216217e-05, + "loss": 3.9462, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.87744298047057e-05, + "loss": 3.9536, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876604385719518e-05, + "loss": 3.9384, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8757657909684654e-05, + "loss": 3.942, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 4.012300491333008, + "eval_runtime": 294.9991, + "eval_samples_per_second": 1293.533, + "eval_steps_per_second": 40.424, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8749271962174134e-05, + "loss": 3.9424, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8740886014663614e-05, + "loss": 3.9413, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8732500067153094e-05, + "loss": 3.9534, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8724114119642577e-05, + "loss": 3.9411, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8715728172132057e-05, + "loss": 3.9543, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8707342224621537e-05, + "loss": 3.9392, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8698956277111017e-05, + "loss": 3.9458, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8690570329600497e-05, + "loss": 3.9385, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8682184382089977e-05, + "loss": 3.9484, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8673798434579457e-05, + "loss": 3.9469, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8665412487068937e-05, + "loss": 3.9543, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8657026539558417e-05, + "loss": 3.9506, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.864865697085163e-05, + "loss": 3.9368, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864027102334111e-05, + "loss": 3.9406, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863188507583059e-05, + "loss": 3.9396, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862349912832007e-05, + "loss": 3.9389, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8615113180809546e-05, + "loss": 3.9436, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8606727233299026e-05, + "loss": 3.939, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8598341285788506e-05, + "loss": 3.9429, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8589955338277985e-05, + "loss": 3.9603, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8581569390767465e-05, + "loss": 3.9449, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8573183443256945e-05, + "loss": 3.9496, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8564797495746425e-05, + "loss": 3.9443, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8556411548235905e-05, + "loss": 3.9568, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8548025600725385e-05, + "loss": 3.9291, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8539656032018598e-05, + "loss": 3.948, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8531286463311807e-05, + "loss": 3.9369, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8522900515801287e-05, + "loss": 3.9403, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8514514568290767e-05, + "loss": 3.9381, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8506128620780247e-05, + "loss": 3.9357, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849774267326973e-05, + "loss": 3.945, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.848935672575921e-05, + "loss": 3.9554, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848098715705242e-05, + "loss": 3.9427, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.84726012095419e-05, + "loss": 3.9465, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8464231640835108e-05, + "loss": 3.9406, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845584569332459e-05, + "loss": 3.9444, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.844745974581407e-05, + "loss": 3.9394, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.843907379830355e-05, + "loss": 3.9499, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843068785079303e-05, + "loss": 3.9322, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842230190328251e-05, + "loss": 3.937, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841391595577199e-05, + "loss": 3.9394, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840553000826147e-05, + "loss": 3.9525, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839714406075095e-05, + "loss": 3.9315, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8388774492044164e-05, + "loss": 3.9443, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8380388544533644e-05, + "loss": 3.9443, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8372002597023124e-05, + "loss": 3.9377, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8363616649512604e-05, + "loss": 3.95, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8355230702002083e-05, + "loss": 3.924, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8346844754491557e-05, + "loss": 3.9348, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.833845880698104e-05, + "loss": 3.9497, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833007285947052e-05, + "loss": 3.9426, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832170329076373e-05, + "loss": 3.9366, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831331734325321e-05, + "loss": 3.9344, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830493139574269e-05, + "loss": 3.9361, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829654544823217e-05, + "loss": 3.9273, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828817587952538e-05, + "loss": 3.9469, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.827978993201486e-05, + "loss": 3.9208, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827140398450434e-05, + "loss": 3.9396, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826301803699382e-05, + "loss": 3.9396, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825464846828703e-05, + "loss": 3.935, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824626252077651e-05, + "loss": 3.9444, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8237876573265994e-05, + "loss": 3.9373, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8229490625755474e-05, + "loss": 3.924, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8221104678244954e-05, + "loss": 3.9265, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8212718730734434e-05, + "loss": 3.9529, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8204332783223913e-05, + "loss": 3.9357, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8195946835713393e-05, + "loss": 3.9328, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8187577267006603e-05, + "loss": 3.9263, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8179191319496086e-05, + "loss": 3.9307, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8170805371985566e-05, + "loss": 3.9424, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8162452182082504e-05, + "loss": 3.9476, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8154066234571984e-05, + "loss": 3.9367, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8145680287061464e-05, + "loss": 3.9478, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8137294339550947e-05, + "loss": 3.9505, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8128908392040427e-05, + "loss": 3.949, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8120522444529907e-05, + "loss": 3.9284, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8112136497019387e-05, + "loss": 3.9425, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8103750549508867e-05, + "loss": 3.9379, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8095364601998347e-05, + "loss": 3.9403, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8086995033291556e-05, + "loss": 3.9371, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.807860908578104e-05, + "loss": 3.942, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807022313827052e-05, + "loss": 3.9521, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806183719076e-05, + "loss": 3.9446, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.805345124324948e-05, + "loss": 3.9247, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804508167454269e-05, + "loss": 3.9321, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803669572703217e-05, + "loss": 3.9382, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802830977952165e-05, + "loss": 3.9402, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8019923832011132e-05, + "loss": 3.9421, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8011537884500612e-05, + "loss": 3.9335, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800315193699009e-05, + "loss": 3.9387, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7994765989479565e-05, + "loss": 3.9237, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798639642077278e-05, + "loss": 3.9359, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.797801047326226e-05, + "loss": 3.939, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.796962452575174e-05, + "loss": 3.9368, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7961238578241217e-05, + "loss": 3.947, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7952852630730697e-05, + "loss": 3.9359, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7944466683220177e-05, + "loss": 3.9358, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7936080735709657e-05, + "loss": 3.9406, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7927694788199137e-05, + "loss": 3.9422, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7919308840688617e-05, + "loss": 3.9388, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791093927198183e-05, + "loss": 3.9333, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790256970327504e-05, + "loss": 3.9352, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789418375576452e-05, + "loss": 3.9386, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7885797808254e-05, + "loss": 3.9406, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787741186074348e-05, + "loss": 3.9237, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.786902591323296e-05, + "loss": 3.936, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7860639965722442e-05, + "loss": 3.9393, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7852254018211922e-05, + "loss": 3.9363, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.78438680707014e-05, + "loss": 3.9325, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783549850199461e-05, + "loss": 3.929, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782711255448409e-05, + "loss": 3.9258, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.781872660697357e-05, + "loss": 3.9473, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7810357038266783e-05, + "loss": 3.931, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7801971090756263e-05, + "loss": 3.9391, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7793585143245743e-05, + "loss": 3.9373, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7785199195735223e-05, + "loss": 3.9492, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7776813248224703e-05, + "loss": 3.9327, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7768427300714183e-05, + "loss": 3.9378, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7760057732007395e-05, + "loss": 3.9449, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7751671784496875e-05, + "loss": 3.9387, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7743285836986355e-05, + "loss": 3.9332, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7734899889475835e-05, + "loss": 3.9359, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7726513941965315e-05, + "loss": 3.9273, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7718127994454795e-05, + "loss": 3.9328, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7709758425748004e-05, + "loss": 3.935, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7701372478237488e-05, + "loss": 3.9322, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7692986530726968e-05, + "loss": 3.9292, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7684600583216448e-05, + "loss": 3.9324, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7676231014509657e-05, + "loss": 3.9312, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7667845066999137e-05, + "loss": 3.9467, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7659459119488617e-05, + "loss": 3.9481, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7651073171978097e-05, + "loss": 3.9358, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764268722446758e-05, + "loss": 3.9272, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7634301276957053e-05, + "loss": 3.9403, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762593170825027e-05, + "loss": 3.9424, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761754576073975e-05, + "loss": 3.942, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7609159813229225e-05, + "loss": 3.9352, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7600773865718705e-05, + "loss": 3.9432, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759240429701192e-05, + "loss": 3.9362, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.75840183495014e-05, + "loss": 3.9382, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757564878079461e-05, + "loss": 3.935, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756726283328409e-05, + "loss": 3.9388, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.755887688577357e-05, + "loss": 3.9349, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755049093826305e-05, + "loss": 3.9284, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7542104990752527e-05, + "loss": 3.9414, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7533719043242007e-05, + "loss": 3.9379, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7525333095731487e-05, + "loss": 3.9434, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7516947148220967e-05, + "loss": 3.9297, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7508561200710447e-05, + "loss": 3.9331, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 4.007538795471191, + "eval_runtime": 291.096, + "eval_samples_per_second": 1310.877, + "eval_steps_per_second": 40.966, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.750019163200366e-05, + "loss": 3.9372, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.749180568449314e-05, + "loss": 3.9339, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748341973698262e-05, + "loss": 3.9432, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.74750337894721e-05, + "loss": 3.9318, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746664784196158e-05, + "loss": 3.9446, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.745826189445106e-05, + "loss": 3.9283, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.744987594694054e-05, + "loss": 3.9368, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744148999943002e-05, + "loss": 3.9288, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743313680952696e-05, + "loss": 3.9412, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742475086201644e-05, + "loss": 3.9354, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741636491450592e-05, + "loss": 3.9458, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.74079789669954e-05, + "loss": 3.9392, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.739959301948488e-05, + "loss": 3.9274, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7391223450778093e-05, + "loss": 3.9344, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7382837503267573e-05, + "loss": 3.9305, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7374451555757053e-05, + "loss": 3.9328, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7366065608246533e-05, + "loss": 3.9323, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7357679660736012e-05, + "loss": 3.928, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7349293713225492e-05, + "loss": 3.9309, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7340907765714972e-05, + "loss": 3.9525, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7332521818204452e-05, + "loss": 3.9387, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7324135870693936e-05, + "loss": 3.9386, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7315766301987145e-05, + "loss": 3.9387, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7307380354476625e-05, + "loss": 3.9452, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7298994406966105e-05, + "loss": 3.9208, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7290608459455585e-05, + "loss": 3.9366, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7282238890748797e-05, + "loss": 3.9323, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7273852943238277e-05, + "loss": 3.9298, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7265466995727757e-05, + "loss": 3.9253, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7257097427020966e-05, + "loss": 3.9259, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7248711479510446e-05, + "loss": 3.9358, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7240325531999926e-05, + "loss": 3.9463, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7231939584489406e-05, + "loss": 3.9328, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7223553636978883e-05, + "loss": 3.9369, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.72151840682721e-05, + "loss": 3.9327, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720679812076158e-05, + "loss": 3.9307, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.719841217325106e-05, + "loss": 3.9274, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7190026225740535e-05, + "loss": 3.9432, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7181640278230015e-05, + "loss": 3.9216, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717327070952323e-05, + "loss": 3.9306, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716488476201271e-05, + "loss": 3.928, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7156498814502184e-05, + "loss": 3.943, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7148112866991664e-05, + "loss": 3.926, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7139726919481144e-05, + "loss": 3.9314, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7131340971970627e-05, + "loss": 3.9361, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7122955024460107e-05, + "loss": 3.9319, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7114569076949587e-05, + "loss": 3.9396, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7106199508242796e-05, + "loss": 3.9186, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7097829939536005e-05, + "loss": 3.9251, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.708944399202549e-05, + "loss": 3.9403, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708105804451497e-05, + "loss": 3.932, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707267209700445e-05, + "loss": 3.9277, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.706428614949393e-05, + "loss": 3.9255, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705590020198341e-05, + "loss": 3.9312, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7047530633276618e-05, + "loss": 3.92, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7039144685766097e-05, + "loss": 3.9337, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703075873825558e-05, + "loss": 3.9145, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702237279074506e-05, + "loss": 3.9313, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701400322203827e-05, + "loss": 3.9344, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700561727452775e-05, + "loss": 3.9252, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699723132701723e-05, + "loss": 3.9324, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.698884537950671e-05, + "loss": 3.9328, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698045943199619e-05, + "loss": 3.9124, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6972073484485673e-05, + "loss": 3.9223, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6963687536975153e-05, + "loss": 3.9355, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6955301589464633e-05, + "loss": 3.9304, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6946932020757842e-05, + "loss": 3.9272, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6938546073247322e-05, + "loss": 3.9137, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6930176504540534e-05, + "loss": 3.9216, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6921790557030014e-05, + "loss": 3.9366, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6913404609519494e-05, + "loss": 3.9409, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6905018662008974e-05, + "loss": 3.9239, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6896649093302183e-05, + "loss": 3.9407, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6888263145791663e-05, + "loss": 3.9405, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6879877198281143e-05, + "loss": 3.9448, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6871491250770627e-05, + "loss": 3.9132, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6863105303260107e-05, + "loss": 3.9371, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6854719355749587e-05, + "loss": 3.929, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6846333408239067e-05, + "loss": 3.9282, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.683794746072854e-05, + "loss": 3.9314, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.682956151321802e-05, + "loss": 3.9323, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6821191944511236e-05, + "loss": 3.9377, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6812822375804448e-05, + "loss": 3.9392, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6804436428293928e-05, + "loss": 3.9143, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6796050480783408e-05, + "loss": 3.9273, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6787664533272888e-05, + "loss": 3.9266, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6779294964566097e-05, + "loss": 3.932, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677090901705558e-05, + "loss": 3.9357, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.676253944834879e-05, + "loss": 3.9226, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675415350083827e-05, + "loss": 3.9325, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.674576755332775e-05, + "loss": 3.9172, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673738160581723e-05, + "loss": 3.9286, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.672899565830671e-05, + "loss": 3.9284, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672060971079619e-05, + "loss": 3.9281, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6712223763285666e-05, + "loss": 3.9363, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6703837815775146e-05, + "loss": 3.9331, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6695451868264626e-05, + "loss": 3.9244, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6687065920754106e-05, + "loss": 3.9324, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6678679973243586e-05, + "loss": 3.9349, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6670294025733066e-05, + "loss": 3.9321, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6661924457026278e-05, + "loss": 3.9207, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6653554888319487e-05, + "loss": 3.9284, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6645168940808967e-05, + "loss": 3.9301, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6636782993298447e-05, + "loss": 3.9328, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6628397045787927e-05, + "loss": 3.9128, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6620011098277407e-05, + "loss": 3.9259, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661162515076689e-05, + "loss": 3.9352, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.66032555820601e-05, + "loss": 3.9251, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659486963454958e-05, + "loss": 3.9214, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658648368703906e-05, + "loss": 3.9233, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.657809773952854e-05, + "loss": 3.9182, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.656971179201802e-05, + "loss": 3.9366, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6561342223311232e-05, + "loss": 3.9189, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6552956275800712e-05, + "loss": 3.9313, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654457032829019e-05, + "loss": 3.9322, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653618438077967e-05, + "loss": 3.9387, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652779843326915e-05, + "loss": 3.9245, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.651941248575863e-05, + "loss": 3.9336, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651102653824811e-05, + "loss": 3.9362, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6502656969541324e-05, + "loss": 3.9307, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6494287400834533e-05, + "loss": 3.9217, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6485901453324013e-05, + "loss": 3.9265, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6477515505813493e-05, + "loss": 3.9205, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6469129558302973e-05, + "loss": 3.9289, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6460743610792453e-05, + "loss": 3.9227, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6452357663281936e-05, + "loss": 3.9273, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6443971715771416e-05, + "loss": 3.9181, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6435585768260896e-05, + "loss": 3.9226, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6427199820750376e-05, + "loss": 3.921, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.641881387323985e-05, + "loss": 3.9379, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410444304533065e-05, + "loss": 3.9404, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6402058357022545e-05, + "loss": 3.9297, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639367240951203e-05, + "loss": 3.9177, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.63852864620015e-05, + "loss": 3.9296, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637690051449098e-05, + "loss": 3.9366, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.636851456698046e-05, + "loss": 3.9298, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636012861946994e-05, + "loss": 3.9275, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635174267195942e-05, + "loss": 3.9328, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6343356724448905e-05, + "loss": 3.9296, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633500353454585e-05, + "loss": 3.9338, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6326617587035323e-05, + "loss": 3.9206, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6318231639524803e-05, + "loss": 3.9327, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6309845692014283e-05, + "loss": 3.925, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6301459744503766e-05, + "loss": 3.9176, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6293073796993246e-05, + "loss": 3.9305, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6284704228286455e-05, + "loss": 3.9323, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6276318280775935e-05, + "loss": 3.9311, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6267932333265415e-05, + "loss": 3.9239, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6259562764558628e-05, + "loss": 3.9207, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 4.003603458404541, + "eval_runtime": 289.2282, + "eval_samples_per_second": 1319.342, + "eval_steps_per_second": 41.23, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6251176817048108e-05, + "loss": 3.9293, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6242790869537588e-05, + "loss": 3.9236, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6234404922027068e-05, + "loss": 3.9342, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6226018974516548e-05, + "loss": 3.9213, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217633027006027e-05, + "loss": 3.9418, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6209247079495507e-05, + "loss": 3.9169, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6200861131984987e-05, + "loss": 3.9321, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6192475184474467e-05, + "loss": 3.9191, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618408923696395e-05, + "loss": 3.9334, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617570328945343e-05, + "loss": 3.928, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616731734194291e-05, + "loss": 3.9302, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.615893139443239e-05, + "loss": 3.9357, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6150545446921864e-05, + "loss": 3.9168, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6142159499411344e-05, + "loss": 3.9248, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6133773551900824e-05, + "loss": 3.9237, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6125387604390307e-05, + "loss": 3.9259, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6117018035683516e-05, + "loss": 3.9234, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6108632088172996e-05, + "loss": 3.9212, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6100246140662476e-05, + "loss": 3.9246, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6091860193151956e-05, + "loss": 3.9441, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6083474245641436e-05, + "loss": 3.9279, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6075088298130916e-05, + "loss": 3.9302, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.60667023506204e-05, + "loss": 3.9325, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.605831640310988e-05, + "loss": 3.9328, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6049946834403088e-05, + "loss": 3.9137, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6041560886892568e-05, + "loss": 3.9352, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6033191318185777e-05, + "loss": 3.9196, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602480537067526e-05, + "loss": 3.9233, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601641942316474e-05, + "loss": 3.9159, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600803347565422e-05, + "loss": 3.9213, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.59996475281437e-05, + "loss": 3.9234, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599127795943691e-05, + "loss": 3.9392, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598289201192639e-05, + "loss": 3.9299, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597450606441587e-05, + "loss": 3.9294, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5966136495709082e-05, + "loss": 3.9195, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5957750548198562e-05, + "loss": 3.9282, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5949364600688042e-05, + "loss": 3.9153, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5940978653177522e-05, + "loss": 3.9352, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5932592705667002e-05, + "loss": 3.9128, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5924206758156482e-05, + "loss": 3.9186, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915820810645962e-05, + "loss": 3.9218, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907434863135445e-05, + "loss": 3.9351, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5899048915624925e-05, + "loss": 3.9187, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5890662968114398e-05, + "loss": 3.9216, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5882277020603878e-05, + "loss": 3.926, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5873891073093358e-05, + "loss": 3.9241, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5865521504386574e-05, + "loss": 3.9319, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585713555687605e-05, + "loss": 3.915, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.584874960936553e-05, + "loss": 3.9125, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584036366185501e-05, + "loss": 3.9302, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583197771434449e-05, + "loss": 3.9225, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.58236081456377e-05, + "loss": 3.9198, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5815222198127183e-05, + "loss": 3.9198, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5806836250616663e-05, + "loss": 3.922, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5798450303106143e-05, + "loss": 3.9096, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5790064355595623e-05, + "loss": 3.9264, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781678408085103e-05, + "loss": 3.9061, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773292460574583e-05, + "loss": 3.9243, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5764906513064063e-05, + "loss": 3.9212, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5756520565553543e-05, + "loss": 3.9238, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5748150996846755e-05, + "loss": 3.9199, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5739765049336235e-05, + "loss": 3.9258, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731379101825715e-05, + "loss": 3.903, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5722993154315195e-05, + "loss": 3.9179, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714623585608404e-05, + "loss": 3.9257, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5706237638097884e-05, + "loss": 3.9256, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5697851690587367e-05, + "loss": 3.9123, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5689465743076847e-05, + "loss": 3.9122, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5681096174370056e-05, + "loss": 3.9128, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5672710226859536e-05, + "loss": 3.9232, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5664324279349016e-05, + "loss": 3.9305, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5655938331838496e-05, + "loss": 3.9172, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564756876313171e-05, + "loss": 3.9319, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.563918281562119e-05, + "loss": 3.9335, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563079686811067e-05, + "loss": 3.9402, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562241092060015e-05, + "loss": 3.9032, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561402497308963e-05, + "loss": 3.9252, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560563902557911e-05, + "loss": 3.9274, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5597253078068585e-05, + "loss": 3.916, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5588867130558065e-05, + "loss": 3.9244, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558049756185128e-05, + "loss": 3.9275, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557211161434076e-05, + "loss": 3.9328, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556374204563397e-05, + "loss": 3.9245, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555535609812345e-05, + "loss": 3.913, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554697015061293e-05, + "loss": 3.9172, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.553858420310241e-05, + "loss": 3.9169, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5530214634395622e-05, + "loss": 3.9257, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5521828686885102e-05, + "loss": 3.9279, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551345911817831e-05, + "loss": 3.9145, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550507317066779e-05, + "loss": 3.9223, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549668722315727e-05, + "loss": 3.9104, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5488301275646755e-05, + "loss": 3.9163, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5479915328136235e-05, + "loss": 3.9208, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5471529380625708e-05, + "loss": 3.9184, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5463143433115188e-05, + "loss": 3.9298, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454757485604668e-05, + "loss": 3.9238, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446371538094148e-05, + "loss": 3.9159, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543798559058363e-05, + "loss": 3.9239, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.542959964307311e-05, + "loss": 3.926, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542121369556259e-05, + "loss": 3.9268, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.54128441268558e-05, + "loss": 3.9113, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540445817934528e-05, + "loss": 3.9194, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539607223183476e-05, + "loss": 3.9233, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538768628432424e-05, + "loss": 3.9271, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5379316715617452e-05, + "loss": 3.9071, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537094714691066e-05, + "loss": 3.9134, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536256119940014e-05, + "loss": 3.9274, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535417525188962e-05, + "loss": 3.9199, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.53457893043791e-05, + "loss": 3.9134, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5337403356868585e-05, + "loss": 3.9135, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5329017409358065e-05, + "loss": 3.9175, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5320631461847545e-05, + "loss": 3.9234, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312245514337024e-05, + "loss": 3.9157, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303875945630234e-05, + "loss": 3.9184, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295489998119714e-05, + "loss": 3.9246, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5287104050609193e-05, + "loss": 3.931, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278718103098677e-05, + "loss": 3.9248, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5270332155588157e-05, + "loss": 3.9171, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5261946208077637e-05, + "loss": 3.9316, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5253560260567117e-05, + "loss": 3.9223, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5245190691860326e-05, + "loss": 3.9121, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5236804744349806e-05, + "loss": 3.9192, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5228418796839286e-05, + "loss": 3.9127, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522003284932877e-05, + "loss": 3.9215, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521164690181825e-05, + "loss": 3.9124, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5203260954307722e-05, + "loss": 3.9222, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5194875006797202e-05, + "loss": 3.91, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5186505438090418e-05, + "loss": 3.9158, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.517813586938363e-05, + "loss": 3.9117, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.516974992187311e-05, + "loss": 3.9322, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516136397436259e-05, + "loss": 3.926, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515297802685207e-05, + "loss": 3.925, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514460845814528e-05, + "loss": 3.909, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513622251063476e-05, + "loss": 3.9244, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512783656312424e-05, + "loss": 3.9293, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5119466994417452e-05, + "loss": 3.9199, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5111081046906932e-05, + "loss": 3.9178, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5102695099396412e-05, + "loss": 3.9251, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5094309151885892e-05, + "loss": 3.9205, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5085923204375368e-05, + "loss": 3.9284, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077537256864848e-05, + "loss": 3.9109, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5069151309354328e-05, + "loss": 3.9266, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5060765361843808e-05, + "loss": 3.9151, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5052379414333288e-05, + "loss": 3.9155, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5043993466822768e-05, + "loss": 3.9217, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5035607519312248e-05, + "loss": 3.9271, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502725432940919e-05, + "loss": 3.9206, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.501886838189867e-05, + "loss": 3.9134, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501048243438815e-05, + "loss": 3.9177, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 4.0000386238098145, + "eval_runtime": 317.2141, + "eval_samples_per_second": 1202.945, + "eval_steps_per_second": 37.593, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.500209648687763e-05, + "loss": 3.9236, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499371053936711e-05, + "loss": 3.9169, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498532459185659e-05, + "loss": 3.9223, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497693864434607e-05, + "loss": 3.915, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4968569075639282e-05, + "loss": 3.9306, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4960183128128762e-05, + "loss": 3.9168, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4951797180618242e-05, + "loss": 3.919, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4943411233107722e-05, + "loss": 3.9105, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.49350252855972e-05, + "loss": 3.9231, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492663933808668e-05, + "loss": 3.9253, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918269769379894e-05, + "loss": 3.9216, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909883821869374e-05, + "loss": 3.9231, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901497874358854e-05, + "loss": 3.9112, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4893111926848334e-05, + "loss": 3.9171, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4884725979337814e-05, + "loss": 3.9172, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487634003182729e-05, + "loss": 3.9159, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.486795408431677e-05, + "loss": 3.9179, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4859568136806254e-05, + "loss": 3.9141, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4851182189295734e-05, + "loss": 3.9171, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4842796241785214e-05, + "loss": 3.9319, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4834410294274694e-05, + "loss": 3.924, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.482602434676417e-05, + "loss": 3.9215, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4817654778057383e-05, + "loss": 3.9241, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4809268830546863e-05, + "loss": 3.9265, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4800882883036343e-05, + "loss": 3.9055, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792496935525823e-05, + "loss": 3.9254, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4784127366819035e-05, + "loss": 3.9127, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4775741419308515e-05, + "loss": 3.9122, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4767371850601724e-05, + "loss": 3.9084, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4758985903091207e-05, + "loss": 3.9167, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4750599955580687e-05, + "loss": 3.9136, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4742214008070167e-05, + "loss": 3.9315, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4733828060559644e-05, + "loss": 3.9217, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4725442113049124e-05, + "loss": 3.9201, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4717072544342336e-05, + "loss": 3.914, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4708686596831816e-05, + "loss": 3.9189, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4700300649321296e-05, + "loss": 3.9141, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4691914701810776e-05, + "loss": 3.9244, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4683528754300256e-05, + "loss": 3.903, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4675142806789736e-05, + "loss": 3.9114, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4666756859279216e-05, + "loss": 3.9128, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4658387290572425e-05, + "loss": 3.9279, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465000134306191e-05, + "loss": 3.9156, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464161539555139e-05, + "loss": 3.9156, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463322944804087e-05, + "loss": 3.917, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4624859879334078e-05, + "loss": 3.9151, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4616473931823558e-05, + "loss": 3.924, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4608087984313037e-05, + "loss": 3.9088, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4599702036802517e-05, + "loss": 3.9032, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459133246809573e-05, + "loss": 3.9239, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458294652058521e-05, + "loss": 3.9131, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457456057307469e-05, + "loss": 3.9148, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456617462556417e-05, + "loss": 3.9104, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.455780505685738e-05, + "loss": 3.9153, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4549419109346862e-05, + "loss": 3.9031, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4541033161836342e-05, + "loss": 3.915, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4532647214325822e-05, + "loss": 3.902, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.45242612668153e-05, + "loss": 3.9122, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.451587531930478e-05, + "loss": 3.9177, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.450748937179426e-05, + "loss": 3.915, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.449910342428374e-05, + "loss": 3.9114, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.449073385557695e-05, + "loss": 3.9227, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448234790806643e-05, + "loss": 3.8955, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4473978339359644e-05, + "loss": 3.9038, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446559239184912e-05, + "loss": 3.92, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.44572064443386e-05, + "loss": 3.915, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4448836875631816e-05, + "loss": 3.9095, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4440450928121296e-05, + "loss": 3.9013, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4432064980610772e-05, + "loss": 3.9025, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4423679033100252e-05, + "loss": 3.9129, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4415293085589732e-05, + "loss": 3.9241, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4406907138079212e-05, + "loss": 3.914, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4398521190568692e-05, + "loss": 3.9205, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4390135243058172e-05, + "loss": 3.9238, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381749295547656e-05, + "loss": 3.9358, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373363348037132e-05, + "loss": 3.8995, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4364977400526612e-05, + "loss": 3.9136, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4356591453016092e-05, + "loss": 3.9221, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4348205505505572e-05, + "loss": 3.9024, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4339852315602517e-05, + "loss": 3.9194, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4331466368091997e-05, + "loss": 3.918, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4323080420581477e-05, + "loss": 3.9248, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4314694473070953e-05, + "loss": 3.919, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306324904364166e-05, + "loss": 3.9021, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4297938956853646e-05, + "loss": 3.9102, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4289553009343126e-05, + "loss": 3.9088, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4281167061832606e-05, + "loss": 3.9153, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4272781114322086e-05, + "loss": 3.9209, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4264411545615298e-05, + "loss": 3.9059, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4256025598104775e-05, + "loss": 3.9155, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4247656029397987e-05, + "loss": 3.9022, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.423927008188747e-05, + "loss": 3.9098, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423088413437695e-05, + "loss": 3.9131, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4222498186866427e-05, + "loss": 3.9148, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4214112239355907e-05, + "loss": 3.9254, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4205726291845387e-05, + "loss": 3.9124, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4197340344334867e-05, + "loss": 3.9104, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4188954396824347e-05, + "loss": 3.9144, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4180568449313827e-05, + "loss": 3.9142, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417218250180331e-05, + "loss": 3.9198, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4163796554292787e-05, + "loss": 3.9045, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4155426985586e-05, + "loss": 3.9131, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414704103807548e-05, + "loss": 3.914, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4138655090564956e-05, + "loss": 3.9194, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4130269143054436e-05, + "loss": 3.8984, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412188319554392e-05, + "loss": 3.9071, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.41134972480334e-05, + "loss": 3.9174, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410511130052288e-05, + "loss": 3.9129, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409672535301236e-05, + "loss": 3.903, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088355784305568e-05, + "loss": 3.9114, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4079969836795048e-05, + "loss": 3.9041, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4071583889284528e-05, + "loss": 3.9201, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406319794177401e-05, + "loss": 3.9081, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405481199426349e-05, + "loss": 3.9055, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.40464424255567e-05, + "loss": 3.9182, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.403805647804618e-05, + "loss": 3.9264, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.402968690933939e-05, + "loss": 3.9158, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021300961828873e-05, + "loss": 3.9113, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4012915014318353e-05, + "loss": 3.9176, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4004529066807833e-05, + "loss": 3.9144, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3996143119297313e-05, + "loss": 3.9057, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.398775717178679e-05, + "loss": 3.9168, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.397937122427627e-05, + "loss": 3.9054, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397098527676575e-05, + "loss": 3.9103, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3962615708058965e-05, + "loss": 3.9053, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395422976054844e-05, + "loss": 3.914, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394584381303792e-05, + "loss": 3.9027, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.39374578655274e-05, + "loss": 3.9039, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.392907191801688e-05, + "loss": 3.9088, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392068597050636e-05, + "loss": 3.9195, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391230002299584e-05, + "loss": 3.9198, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903930454289054e-05, + "loss": 3.9175, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3895544506778534e-05, + "loss": 3.9019, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3887158559268014e-05, + "loss": 3.919, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3878772611757494e-05, + "loss": 3.9195, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387038666424697e-05, + "loss": 3.9141, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3862017095540183e-05, + "loss": 3.9081, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3853631148029666e-05, + "loss": 3.9225, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3845245200519143e-05, + "loss": 3.9123, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3836859253008623e-05, + "loss": 3.9218, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3828473305498103e-05, + "loss": 3.8978, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3820087357987583e-05, + "loss": 3.9221, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3811701410477063e-05, + "loss": 3.9045, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3803315462966543e-05, + "loss": 3.9085, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3794929515456026e-05, + "loss": 3.9149, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786559946749235e-05, + "loss": 3.914, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3778173999238715e-05, + "loss": 3.9162, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769788051728195e-05, + "loss": 3.9014, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761402104217675e-05, + "loss": 3.9148, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9963581562042236, + "eval_runtime": 318.1647, + "eval_samples_per_second": 1199.351, + "eval_steps_per_second": 37.481, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3753032535510887e-05, + "loss": 3.9134, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744646588000367e-05, + "loss": 3.9108, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736260640489847e-05, + "loss": 3.9167, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727874692979324e-05, + "loss": 3.9087, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719488745468804e-05, + "loss": 3.9215, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3711102797958284e-05, + "loss": 3.9088, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702716850447764e-05, + "loss": 3.9075, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3694330902937244e-05, + "loss": 3.9101, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685944955426727e-05, + "loss": 3.914, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677559007916207e-05, + "loss": 3.9172, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669173060405683e-05, + "loss": 3.912, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660787112895163e-05, + "loss": 3.9192, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652417544188376e-05, + "loss": 3.9045, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3644031596677856e-05, + "loss": 3.9085, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635645649167336e-05, + "loss": 3.9131, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627259701656816e-05, + "loss": 3.9049, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618873754146296e-05, + "loss": 3.9109, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610487806635776e-05, + "loss": 3.9048, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3602101859125256e-05, + "loss": 3.9058, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593715911614736e-05, + "loss": 3.9268, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585329964104212e-05, + "loss": 3.9153, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3576944016593696e-05, + "loss": 3.9205, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568558069083175e-05, + "loss": 3.9119, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560172121572655e-05, + "loss": 3.9164, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551802552865865e-05, + "loss": 3.8992, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543416605355344e-05, + "loss": 3.9181, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3535030657844824e-05, + "loss": 3.9053, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526661089138037e-05, + "loss": 3.9012, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518275141627517e-05, + "loss": 3.9016, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509889194116997e-05, + "loss": 3.9064, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501503246606477e-05, + "loss": 3.9101, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3493117299095957e-05, + "loss": 3.9205, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484731351585437e-05, + "loss": 3.9191, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476345404074917e-05, + "loss": 3.9099, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346799221417186e-05, + "loss": 3.9089, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3459606266661338e-05, + "loss": 3.9106, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451220319150818e-05, + "loss": 3.9066, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442834371640298e-05, + "loss": 3.9131, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434448424129778e-05, + "loss": 3.9018, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3426062476619258e-05, + "loss": 3.9007, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417676529108738e-05, + "loss": 3.9063, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3409290581598218e-05, + "loss": 3.9194, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400904634087698e-05, + "loss": 3.9085, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3392518686577178e-05, + "loss": 3.9071, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338414911787039e-05, + "loss": 3.9129, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375763170359867e-05, + "loss": 3.9071, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336737722284935e-05, + "loss": 3.9148, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.335899127533883e-05, + "loss": 3.9031, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335060532782831e-05, + "loss": 3.8949, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334221938031779e-05, + "loss": 3.915, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333383343280727e-05, + "loss": 3.908, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332546386410048e-05, + "loss": 3.9042, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331707791658996e-05, + "loss": 3.9077, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308691969079442e-05, + "loss": 3.9044, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3300306021568922e-05, + "loss": 3.8983, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.32919200740584e-05, + "loss": 3.9024, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328353412654788e-05, + "loss": 3.8974, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327514817903736e-05, + "loss": 3.9028, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326677861033057e-05, + "loss": 3.9142, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.325839266282005e-05, + "loss": 3.9025, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325000671530953e-05, + "loss": 3.9071, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324162076779901e-05, + "loss": 3.9142, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233251199092224e-05, + "loss": 3.8911, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.32248652515817e-05, + "loss": 3.8953, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321647930407118e-05, + "loss": 3.9086, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320809335656066e-05, + "loss": 3.9104, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199707409050144e-05, + "loss": 3.8991, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191337840343353e-05, + "loss": 3.8985, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3182951892832833e-05, + "loss": 3.8946, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3174565945322313e-05, + "loss": 3.9072, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3166179997811793e-05, + "loss": 3.914, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157794050301272e-05, + "loss": 3.9076, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149408102790752e-05, + "loss": 3.9162, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3141022155280232e-05, + "loss": 3.9106, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132636207769712e-05, + "loss": 3.935, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124283017866654e-05, + "loss": 3.8914, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115897070356134e-05, + "loss": 3.9058, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107511122845614e-05, + "loss": 3.918, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099125175335097e-05, + "loss": 3.8938, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090755606628306e-05, + "loss": 3.9131, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082369659117786e-05, + "loss": 3.9109, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073983711607266e-05, + "loss": 3.9138, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065597764096746e-05, + "loss": 3.9117, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057211816586226e-05, + "loss": 3.8958, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048825869075706e-05, + "loss": 3.909, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040439921565186e-05, + "loss": 3.8969, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3032053974054666e-05, + "loss": 3.9118, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302368440534788e-05, + "loss": 3.9158, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015314836641088e-05, + "loss": 3.8962, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.30069452679343e-05, + "loss": 3.9106, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299855932042378e-05, + "loss": 3.8981, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299017337291326e-05, + "loss": 3.9011, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298178742540274e-05, + "loss": 3.9025, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297340147789222e-05, + "loss": 3.9152, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.29650155303817e-05, + "loss": 3.9171, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956645961674912e-05, + "loss": 3.9023, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2948260014164392e-05, + "loss": 3.9022, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2939874066653872e-05, + "loss": 3.9091, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2931488119143352e-05, + "loss": 3.9047, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292310217163283e-05, + "loss": 3.9162, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291471622412231e-05, + "loss": 3.899, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290633027661179e-05, + "loss": 3.9036, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.289794432910127e-05, + "loss": 3.9078, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2889558381590752e-05, + "loss": 3.9115, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2881172434080232e-05, + "loss": 3.8923, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287278648656971e-05, + "loss": 3.9013, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286441691786292e-05, + "loss": 3.9077, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285604734915613e-05, + "loss": 3.9084, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2847661401645613e-05, + "loss": 3.8929, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839275454135093e-05, + "loss": 3.9128, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830889506624573e-05, + "loss": 3.8952, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822503559114053e-05, + "loss": 3.9085, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814117611603533e-05, + "loss": 3.9031, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280573166409301e-05, + "loss": 3.8991, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279734571658249e-05, + "loss": 3.9092, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788976147875706e-05, + "loss": 3.9213, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780590200365182e-05, + "loss": 3.9072, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772204252854662e-05, + "loss": 3.9061, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2763818305344142e-05, + "loss": 3.9115, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755448736637355e-05, + "loss": 3.9086, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274706278912683e-05, + "loss": 3.9005, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738676841616315e-05, + "loss": 3.9072, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730290894105795e-05, + "loss": 3.8999, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721921325399004e-05, + "loss": 3.904, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713551756692216e-05, + "loss": 3.903, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705165809181696e-05, + "loss": 3.9012, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696779861671176e-05, + "loss": 3.9014, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2688393914160656e-05, + "loss": 3.8968, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2680007966650136e-05, + "loss": 3.9043, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267163839794335e-05, + "loss": 3.9115, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266325245043283e-05, + "loss": 3.91, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654866502922305e-05, + "loss": 3.9109, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646480555411785e-05, + "loss": 3.8921, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2638094607901268e-05, + "loss": 3.9169, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262974141799821e-05, + "loss": 3.9134, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262135547048769e-05, + "loss": 3.9058, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261296952297717e-05, + "loss": 3.9053, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260458357546665e-05, + "loss": 3.9102, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259619762795613e-05, + "loss": 3.9043, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.258781168044561e-05, + "loss": 3.9184, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257942573293509e-05, + "loss": 3.891, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257103978542457e-05, + "loss": 3.9136, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256265383791405e-05, + "loss": 3.8969, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255428426920726e-05, + "loss": 3.9041, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254589832169674e-05, + "loss": 3.907, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537512374186222e-05, + "loss": 3.9037, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2529126426675702e-05, + "loss": 3.9183, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2520740479165182e-05, + "loss": 3.8906, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251235453165466e-05, + "loss": 3.9113, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.993824005126953, + "eval_runtime": 337.3948, + "eval_samples_per_second": 1130.992, + "eval_steps_per_second": 35.344, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250396858414414e-05, + "loss": 3.9091, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249559901543735e-05, + "loss": 3.9035, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248721306792683e-05, + "loss": 3.9112, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.247882712041631e-05, + "loss": 3.9038, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247044117290579e-05, + "loss": 3.9116, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246205522539527e-05, + "loss": 3.9028, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245366927788475e-05, + "loss": 3.899, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244528333037423e-05, + "loss": 3.9046, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243689738286371e-05, + "loss": 3.906, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428527814156923e-05, + "loss": 3.9082, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2420141866646403e-05, + "loss": 3.9093, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411772297939612e-05, + "loss": 3.909, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403386350429092e-05, + "loss": 3.9021, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2395000402918572e-05, + "loss": 3.9022, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2386614455408052e-05, + "loss": 3.907, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378228507897532e-05, + "loss": 3.8964, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369842560387015e-05, + "loss": 3.9047, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361456612876492e-05, + "loss": 3.8977, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2353070665365972e-05, + "loss": 3.902, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2344701096659184e-05, + "loss": 3.9178, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336315149148664e-05, + "loss": 3.9114, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327929201638144e-05, + "loss": 3.9123, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319543254127624e-05, + "loss": 3.9069, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2311173685420837e-05, + "loss": 3.91, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302787737910313e-05, + "loss": 3.8937, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294401790399793e-05, + "loss": 3.9151, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2286015842889273e-05, + "loss": 3.8988, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2277629895378753e-05, + "loss": 3.8954, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2269243947868236e-05, + "loss": 3.8996, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2260858000357716e-05, + "loss": 3.9018, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252472052847196e-05, + "loss": 3.9048, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2244118862944138e-05, + "loss": 3.9147, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235732915433614e-05, + "loss": 3.91, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227346967923098e-05, + "loss": 3.9055, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.221897739921631e-05, + "loss": 3.899, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2210591451705787e-05, + "loss": 3.9073, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2202205504195267e-05, + "loss": 3.9046, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193819556684747e-05, + "loss": 3.9014, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185433609174227e-05, + "loss": 3.8982, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2177047661663707e-05, + "loss": 3.8929, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2168661714153187e-05, + "loss": 3.901, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216027576664267e-05, + "loss": 3.9111, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2151889819132147e-05, + "loss": 3.9043, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214352025042536e-05, + "loss": 3.8992, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213513430291484e-05, + "loss": 3.9063, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126764734208048e-05, + "loss": 3.8986, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.211837878669753e-05, + "loss": 3.9117, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.210999283918701e-05, + "loss": 3.8965, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210160689167649e-05, + "loss": 3.8859, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2093220944165968e-05, + "loss": 3.9086, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084834996655448e-05, + "loss": 3.9039, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076449049144928e-05, + "loss": 3.9034, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2068063101634408e-05, + "loss": 3.899, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.205967715412389e-05, + "loss": 3.8955, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205129120661337e-05, + "loss": 3.8954, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204292163790658e-05, + "loss": 3.8935, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203453569039606e-05, + "loss": 3.8913, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202614974288554e-05, + "loss": 3.9005, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.201776379537502e-05, + "loss": 3.9048, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.20093778478645e-05, + "loss": 3.8975, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200099190035398e-05, + "loss": 3.8981, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1992622331647192e-05, + "loss": 3.9143, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1984236384136672e-05, + "loss": 3.8835, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197585043662615e-05, + "loss": 3.8878, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196746448911563e-05, + "loss": 3.904, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.195907854160511e-05, + "loss": 3.9071, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950708972898325e-05, + "loss": 3.8935, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.19423230253878e-05, + "loss": 3.8917, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193393707787728e-05, + "loss": 3.8894, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192555113036676e-05, + "loss": 3.9, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191716518285624e-05, + "loss": 3.9112, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.190877923534572e-05, + "loss": 3.9028, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.19003932878352e-05, + "loss": 3.9025, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1892023719128414e-05, + "loss": 3.9091, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883637771617893e-05, + "loss": 3.923, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875284581714835e-05, + "loss": 3.8914, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1866898634204315e-05, + "loss": 3.9008, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858512686693795e-05, + "loss": 3.9074, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1850126739183275e-05, + "loss": 3.8884, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841740791672755e-05, + "loss": 3.9044, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833354844162235e-05, + "loss": 3.9058, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824968896651715e-05, + "loss": 3.9073, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816582949141195e-05, + "loss": 3.9092, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1808197001630675e-05, + "loss": 3.8888, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799811054120155e-05, + "loss": 3.9015, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791425106609635e-05, + "loss": 3.8946, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1783055537902847e-05, + "loss": 3.9012, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774669590392327e-05, + "loss": 3.9081, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766300021685536e-05, + "loss": 3.8901, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757914074175016e-05, + "loss": 3.9044, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.17495281266645e-05, + "loss": 3.8936, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174114217915398e-05, + "loss": 3.891, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1732756231643456e-05, + "loss": 3.8988, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724370284132936e-05, + "loss": 3.9054, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715984336622416e-05, + "loss": 3.9111, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707598389111896e-05, + "loss": 3.8998, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1699212441601376e-05, + "loss": 3.8967, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690826494090856e-05, + "loss": 3.9029, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1682440546580336e-05, + "loss": 3.899, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1674054599069816e-05, + "loss": 3.9065, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665685030363028e-05, + "loss": 3.8966, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657299082852508e-05, + "loss": 3.8954, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1648913135341985e-05, + "loss": 3.9015, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1640527187831465e-05, + "loss": 3.91, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163215761912468e-05, + "loss": 3.8812, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162377167161416e-05, + "loss": 3.8971, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1615385724103637e-05, + "loss": 3.8987, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1606999776593117e-05, + "loss": 3.904, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1598613829082597e-05, + "loss": 3.8886, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159024426037581e-05, + "loss": 3.9027, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158185831286529e-05, + "loss": 3.8958, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1573488744158502e-05, + "loss": 3.8964, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1565102796647982e-05, + "loss": 3.9006, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155671684913746e-05, + "loss": 3.8953, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.154833090162694e-05, + "loss": 3.8986, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.153994495411642e-05, + "loss": 3.9181, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531559006605902e-05, + "loss": 3.9028, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152317305909538e-05, + "loss": 3.8962, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151478711158486e-05, + "loss": 3.9064, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150641754287807e-05, + "loss": 3.9035, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.149803159536755e-05, + "loss": 3.89, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489662026660763e-05, + "loss": 3.905, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481276079150243e-05, + "loss": 3.8919, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472890131639723e-05, + "loss": 3.8968, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464504184129203e-05, + "loss": 3.8987, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1456118236618683e-05, + "loss": 3.8954, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1447748667911892e-05, + "loss": 3.8955, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439362720401372e-05, + "loss": 3.894, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430976772890855e-05, + "loss": 3.8945, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422590825380335e-05, + "loss": 3.9083, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414204877869812e-05, + "loss": 3.901, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1405835309163024e-05, + "loss": 3.9052, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1397449361652504e-05, + "loss": 3.8862, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1389063414141984e-05, + "loss": 3.9125, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380677466631464e-05, + "loss": 3.9035, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372307897924677e-05, + "loss": 3.9031, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363921950414157e-05, + "loss": 3.8999, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355536002903637e-05, + "loss": 3.9038, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1347150055393113e-05, + "loss": 3.8969, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1338764107882593e-05, + "loss": 3.917, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330378160372077e-05, + "loss": 3.8852, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321992212861556e-05, + "loss": 3.9052, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313606265351036e-05, + "loss": 3.8953, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305236696644246e-05, + "loss": 3.8987, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296850749133725e-05, + "loss": 3.8988, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288464801623205e-05, + "loss": 3.895, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1280078854112685e-05, + "loss": 3.9118, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1271709285405898e-05, + "loss": 3.887, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1263323337895378e-05, + "loss": 3.9051, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9916927814483643, + "eval_runtime": 340.329, + "eval_samples_per_second": 1121.241, + "eval_steps_per_second": 35.04, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1254953769188587e-05, + "loss": 3.9057, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1246567821678067e-05, + "loss": 3.8955, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1238181874167547e-05, + "loss": 3.9026, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1229795926657027e-05, + "loss": 3.8984, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122140997914651e-05, + "loss": 3.9034, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121302403163599e-05, + "loss": 3.8968, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1204638084125467e-05, + "loss": 3.8989, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196252136614947e-05, + "loss": 3.8941, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187866189104427e-05, + "loss": 3.9039, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179480241593907e-05, + "loss": 3.9048, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1171094294083386e-05, + "loss": 3.9021, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116270834657287e-05, + "loss": 3.901, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115433877786608e-05, + "loss": 3.8957, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114595283035556e-05, + "loss": 3.8964, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.113756688284504e-05, + "loss": 3.9022, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.112918093533452e-05, + "loss": 3.889, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120794987824e-05, + "loss": 3.8981, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111242541911721e-05, + "loss": 3.8932, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110403947160669e-05, + "loss": 3.8964, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109565352409617e-05, + "loss": 3.9077, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087267576585648e-05, + "loss": 3.9074, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078881629075128e-05, + "loss": 3.9077, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070495681564608e-05, + "loss": 3.9012, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1062109734054088e-05, + "loss": 3.9018, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105372378654357e-05, + "loss": 3.8886, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104533783903305e-05, + "loss": 3.9081, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103695189152253e-05, + "loss": 3.8918, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1028565944012007e-05, + "loss": 3.8902, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1020179996501487e-05, + "loss": 3.8913, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.10118104277947e-05, + "loss": 3.8968, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100342448028418e-05, + "loss": 3.8978, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0995054911577392e-05, + "loss": 3.9077, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986668964066872e-05, + "loss": 3.9051, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0978283016556352e-05, + "loss": 3.8949, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.096991344784956e-05, + "loss": 3.8953, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096152750033904e-05, + "loss": 3.9028, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0953141552828525e-05, + "loss": 3.8995, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0944755605318005e-05, + "loss": 3.8931, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093636965780748e-05, + "loss": 3.8949, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.092798371029696e-05, + "loss": 3.8877, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.091959776278644e-05, + "loss": 3.8929, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091121181527592e-05, + "loss": 3.908, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.09028258677654e-05, + "loss": 3.9007, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089443992025488e-05, + "loss": 3.8924, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088605397274436e-05, + "loss": 3.9, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877684404037573e-05, + "loss": 3.8912, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0869314835330782e-05, + "loss": 3.9075, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0860928887820262e-05, + "loss": 3.8946, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0852542940309742e-05, + "loss": 3.875, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0844156992799226e-05, + "loss": 3.9019, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835787424092435e-05, + "loss": 3.8964, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827401476581915e-05, + "loss": 3.9005, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0819015529071395e-05, + "loss": 3.8919, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0810629581560875e-05, + "loss": 3.8893, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0802260012854087e-05, + "loss": 3.8881, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793874065343567e-05, + "loss": 3.887, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785488117833047e-05, + "loss": 3.8889, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0777102170322527e-05, + "loss": 3.8916, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768716222812007e-05, + "loss": 3.9038, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760330275301484e-05, + "loss": 3.8864, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0751944327790963e-05, + "loss": 3.8927, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0743558380280443e-05, + "loss": 3.9068, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0735172432769927e-05, + "loss": 3.8782, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0726786485259407e-05, + "loss": 3.8804, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718400537748887e-05, + "loss": 3.9003, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0710014590238367e-05, + "loss": 3.8991, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0701628642727843e-05, + "loss": 3.8876, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0693242695217323e-05, + "loss": 3.8903, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0684856747706803e-05, + "loss": 3.8808, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676487179000016e-05, + "loss": 3.8961, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0668101231489496e-05, + "loss": 3.9006, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0659731662782708e-05, + "loss": 3.8973, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651345715272188e-05, + "loss": 3.8948, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0642959767761665e-05, + "loss": 3.9042, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0634573820251148e-05, + "loss": 3.9159, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0626187872740628e-05, + "loss": 3.8871, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0617801925230108e-05, + "loss": 3.8938, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0609415977719588e-05, + "loss": 3.9042, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0601030030209068e-05, + "loss": 3.8851, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592644082698548e-05, + "loss": 3.8965, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0584258135188024e-05, + "loss": 3.8996, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0575872187677504e-05, + "loss": 3.9032, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.056750261897072e-05, + "loss": 3.9053, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.055913305026393e-05, + "loss": 3.8854, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055074710275341e-05, + "loss": 3.8919, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054236115524289e-05, + "loss": 3.8896, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053397520773237e-05, + "loss": 3.8962, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.052558926022185e-05, + "loss": 3.8996, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051720331271133e-05, + "loss": 3.8898, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.050883374400454e-05, + "loss": 3.8948, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050044779649402e-05, + "loss": 3.8911, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0492061848983498e-05, + "loss": 3.8867, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483675901472978e-05, + "loss": 3.8913, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475289953962458e-05, + "loss": 3.8995, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046692038525567e-05, + "loss": 3.9056, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.045853443774515e-05, + "loss": 3.898, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045014849023463e-05, + "loss": 3.8871, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044176254272411e-05, + "loss": 3.8981, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043337659521359e-05, + "loss": 3.8948, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042499064770307e-05, + "loss": 3.8982, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041660470019255e-05, + "loss": 3.8935, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408235131485763e-05, + "loss": 3.8907, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0399849183975243e-05, + "loss": 3.8933, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0391463236464722e-05, + "loss": 3.9056, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.03830772889542e-05, + "loss": 3.879, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037469134144368e-05, + "loss": 3.8916, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0366321772736895e-05, + "loss": 3.8893, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0357935825226375e-05, + "loss": 3.8956, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.034954987771585e-05, + "loss": 3.8867, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034116393020533e-05, + "loss": 3.8985, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0332794361498544e-05, + "loss": 3.8843, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0324408413988024e-05, + "loss": 3.8966, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0316022466477504e-05, + "loss": 3.8975, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0307636518966984e-05, + "loss": 3.8861, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0299250571456464e-05, + "loss": 3.8936, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0290897381553405e-05, + "loss": 3.9088, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0282511434042885e-05, + "loss": 3.897, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0274125486532365e-05, + "loss": 3.8913, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026573953902185e-05, + "loss": 3.8979, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0257353591511325e-05, + "loss": 3.9022, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0248967644000805e-05, + "loss": 3.8876, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240581696490285e-05, + "loss": 3.8997, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0232195748979765e-05, + "loss": 3.8823, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223826180272974e-05, + "loss": 3.8928, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215440232762457e-05, + "loss": 3.8896, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020707066405567e-05, + "loss": 3.891, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0198684716545146e-05, + "loss": 3.8907, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190298769034626e-05, + "loss": 3.8899, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181912821524106e-05, + "loss": 3.8869, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173526874013586e-05, + "loss": 3.9032, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0165140926503066e-05, + "loss": 3.9006, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015675497899255e-05, + "loss": 3.898, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.014836903148203e-05, + "loss": 3.8797, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0139983083971506e-05, + "loss": 3.9069, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013161351526472e-05, + "loss": 3.8932, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.01232275677542e-05, + "loss": 3.897, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011485799904741e-05, + "loss": 3.8981, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.010647205153689e-05, + "loss": 3.8939, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.009808610402637e-05, + "loss": 3.8926, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.008970015651585e-05, + "loss": 3.9095, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081314209005328e-05, + "loss": 3.8831, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072928261494807e-05, + "loss": 3.9009, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064542313984287e-05, + "loss": 3.8897, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0056172745277503e-05, + "loss": 3.8952, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.004778679776698e-05, + "loss": 3.8921, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.003940085025646e-05, + "loss": 3.8914, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003101490274594e-05, + "loss": 3.9047, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002262895523542e-05, + "loss": 3.8874, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.00142430077249e-05, + "loss": 3.8958, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.9896106719970703, + "eval_runtime": 341.7466, + "eval_samples_per_second": 1116.59, + "eval_steps_per_second": 34.894, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.000585706021438e-05, + "loss": 3.8927, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.999747111270386e-05, + "loss": 3.8932, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.998908516519334e-05, + "loss": 3.8939, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9980715596486552e-05, + "loss": 3.8915, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9972329648976032e-05, + "loss": 3.9011, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996394370146551e-05, + "loss": 3.8902, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995555775395499e-05, + "loss": 3.8963, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994717180644447e-05, + "loss": 3.8918, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9938802237737684e-05, + "loss": 3.8939, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993041629022716e-05, + "loss": 3.9041, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992203034271664e-05, + "loss": 3.8939, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9913660774009853e-05, + "loss": 3.8942, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9905274826499333e-05, + "loss": 3.898, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9896888878988813e-05, + "loss": 3.884, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888502931478293e-05, + "loss": 3.893, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9880116983967773e-05, + "loss": 3.8873, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9871731036457253e-05, + "loss": 3.8924, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9863345088946733e-05, + "loss": 3.8877, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9854959141436213e-05, + "loss": 3.886, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984657319392569e-05, + "loss": 3.902, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9838187246415173e-05, + "loss": 3.9049, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9829801298904653e-05, + "loss": 3.9056, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821415351394133e-05, + "loss": 3.8911, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9813045782687342e-05, + "loss": 3.8941, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9804676213980554e-05, + "loss": 3.8884, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9796290266470034e-05, + "loss": 3.8993, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9787904318959514e-05, + "loss": 3.8923, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9779518371448994e-05, + "loss": 3.8903, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9771132423938474e-05, + "loss": 3.8849, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9762746476427954e-05, + "loss": 3.8887, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9754360528917434e-05, + "loss": 3.8887, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9745990960210643e-05, + "loss": 3.9035, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9737605012700127e-05, + "loss": 3.8989, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9729219065189607e-05, + "loss": 3.8908, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9720833117679087e-05, + "loss": 3.8898, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712463548972296e-05, + "loss": 3.8957, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9704077601461776e-05, + "loss": 3.8938, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695691653951256e-05, + "loss": 3.8898, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9687305706440735e-05, + "loss": 3.8917, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678919758930215e-05, + "loss": 3.8808, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670533811419695e-05, + "loss": 3.8838, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9662147863909175e-05, + "loss": 3.901, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653761916398655e-05, + "loss": 3.8968, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645375968888135e-05, + "loss": 3.884, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636990021377615e-05, + "loss": 3.8945, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9628604073867095e-05, + "loss": 3.8862, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9620234505160308e-05, + "loss": 3.8982, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9611848557649788e-05, + "loss": 3.8897, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9603462610139268e-05, + "loss": 3.8664, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9595076662628748e-05, + "loss": 3.9004, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586690715118227e-05, + "loss": 3.8906, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9578304767607704e-05, + "loss": 3.8965, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9569918820097184e-05, + "loss": 3.8865, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9561532872586667e-05, + "loss": 3.8841, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9553163303879876e-05, + "loss": 3.882, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9544777356369356e-05, + "loss": 3.8832, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9536391408858836e-05, + "loss": 3.8845, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.952802184015205e-05, + "loss": 3.8839, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.951963589264153e-05, + "loss": 3.9017, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951124994513101e-05, + "loss": 3.881, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950286399762049e-05, + "loss": 3.8862, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949447805010997e-05, + "loss": 3.8999, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948609210259945e-05, + "loss": 3.8746, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.947770615508893e-05, + "loss": 3.8741, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469336586382138e-05, + "loss": 3.8942, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946095063887162e-05, + "loss": 3.8925, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.94525646913611e-05, + "loss": 3.8828, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944419512265431e-05, + "loss": 3.8833, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943580917514379e-05, + "loss": 3.88, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942742322763327e-05, + "loss": 3.8876, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.941903728012275e-05, + "loss": 3.8936, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941065133261223e-05, + "loss": 3.8893, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940226538510171e-05, + "loss": 3.8917, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.939387943759119e-05, + "loss": 3.8989, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938549349008067e-05, + "loss": 3.911, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937710754257015e-05, + "loss": 3.8786, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.936873797386336e-05, + "loss": 3.8926, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936035202635284e-05, + "loss": 3.8957, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9351966078842322e-05, + "loss": 3.8826, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9343580131331802e-05, + "loss": 3.8857, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9335194183821282e-05, + "loss": 3.9016, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9326808236310762e-05, + "loss": 3.8979, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.931842228880024e-05, + "loss": 3.9009, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931005272009345e-05, + "loss": 3.8778, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930166677258293e-05, + "loss": 3.8835, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293280825072414e-05, + "loss": 3.8852, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928489487756189e-05, + "loss": 3.8946, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927650893005137e-05, + "loss": 3.8926, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9268139361344583e-05, + "loss": 3.8881, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259753413834063e-05, + "loss": 3.8827, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251367466323543e-05, + "loss": 3.8895, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242981518813023e-05, + "loss": 3.8811, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234595571302503e-05, + "loss": 3.8865, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226209623791983e-05, + "loss": 3.8976, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9217840055085192e-05, + "loss": 3.8992, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9209454107574672e-05, + "loss": 3.8896, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9201068160064152e-05, + "loss": 3.8821, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192682212553632e-05, + "loss": 3.8916, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184296265043115e-05, + "loss": 3.8859, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175910317532595e-05, + "loss": 3.894, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167524370022072e-05, + "loss": 3.8905, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9159138422511552e-05, + "loss": 3.881, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9150768853804764e-05, + "loss": 3.8959, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9142382906294244e-05, + "loss": 3.8945, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9133996958783724e-05, + "loss": 3.8731, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125627390076937e-05, + "loss": 3.8866, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117241442566417e-05, + "loss": 3.8798, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108855495055893e-05, + "loss": 3.8955, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9100469547545373e-05, + "loss": 3.8774, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9092099978838586e-05, + "loss": 3.8945, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908371403132807e-05, + "loss": 3.8801, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9075328083817546e-05, + "loss": 3.8877, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9066942136307026e-05, + "loss": 3.8901, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058556188796506e-05, + "loss": 3.8842, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9050170241285986e-05, + "loss": 3.886, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9041784293775465e-05, + "loss": 3.9053, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9033414725068678e-05, + "loss": 3.8901, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9025028777558158e-05, + "loss": 3.8892, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9016642830047638e-05, + "loss": 3.8921, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9008256882537118e-05, + "loss": 3.894, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.8999870935026598e-05, + "loss": 3.8887, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8991501366319807e-05, + "loss": 3.8908, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898311541880929e-05, + "loss": 3.8761, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897472947129877e-05, + "loss": 3.8878, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896634352378825e-05, + "loss": 3.8814, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8957957576277727e-05, + "loss": 3.887, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.894958800757094e-05, + "loss": 3.884, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894120206006042e-05, + "loss": 3.8875, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.89328161125499e-05, + "loss": 3.881, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892443016503938e-05, + "loss": 3.8998, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891604421752886e-05, + "loss": 3.888, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890767464882207e-05, + "loss": 3.8969, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8899288701311548e-05, + "loss": 3.8732, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8890902753801028e-05, + "loss": 3.9038, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882516806290508e-05, + "loss": 3.8879, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887413085877999e-05, + "loss": 3.8936, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886574491126947e-05, + "loss": 3.8927, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.885735896375895e-05, + "loss": 3.8889, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.884897301624843e-05, + "loss": 3.8906, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884061982634537e-05, + "loss": 3.903, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832233878834853e-05, + "loss": 3.8736, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8823847931324333e-05, + "loss": 3.8978, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8815461983813813e-05, + "loss": 3.8879, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8807076036303293e-05, + "loss": 3.8825, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8798690088792773e-05, + "loss": 3.886, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8790304141282253e-05, + "loss": 3.8847, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878191819377173e-05, + "loss": 3.9003, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8773548625064945e-05, + "loss": 3.8849, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8765179056358154e-05, + "loss": 3.888, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.987260341644287, + "eval_runtime": 333.3617, + "eval_samples_per_second": 1144.676, + "eval_steps_per_second": 35.772, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756793108847634e-05, + "loss": 3.8898, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748407161337114e-05, + "loss": 3.8871, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8740021213826594e-05, + "loss": 3.8864, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731635266316074e-05, + "loss": 3.8891, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723249318805554e-05, + "loss": 3.8994, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714863371295034e-05, + "loss": 3.8826, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706477423784514e-05, + "loss": 3.8902, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8698091476273994e-05, + "loss": 3.8854, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689705528763474e-05, + "loss": 3.8911, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681319581252954e-05, + "loss": 3.8963, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672933633742434e-05, + "loss": 3.8858, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.866454768623191e-05, + "loss": 3.8911, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656161738721394e-05, + "loss": 3.8953, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647775791210873e-05, + "loss": 3.8764, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639389843700353e-05, + "loss": 3.8876, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8631003896189833e-05, + "loss": 3.8804, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8622634327483042e-05, + "loss": 3.8892, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8614248379972522e-05, + "loss": 3.8825, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605862432462002e-05, + "loss": 3.884, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597476484951486e-05, + "loss": 3.8957, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8589090537440966e-05, + "loss": 3.8958, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580720968734175e-05, + "loss": 3.8997, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572335021223655e-05, + "loss": 3.8896, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563949073713135e-05, + "loss": 3.8861, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555563126202615e-05, + "loss": 3.8819, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8547177178692095e-05, + "loss": 3.8928, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538791231181575e-05, + "loss": 3.8868, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530405283671055e-05, + "loss": 3.885, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8522019336160534e-05, + "loss": 3.8799, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8513649767453744e-05, + "loss": 3.8851, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8505263819943224e-05, + "loss": 3.8808, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849689425123644e-05, + "loss": 3.8967, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8488508303725916e-05, + "loss": 3.8955, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8480122356215396e-05, + "loss": 3.8871, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471736408704876e-05, + "loss": 3.8858, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846336683999809e-05, + "loss": 3.8838, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845498089248757e-05, + "loss": 3.8904, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8446594944977048e-05, + "loss": 3.8867, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8438208997466528e-05, + "loss": 3.8847, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8429823049956008e-05, + "loss": 3.8754, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421437102445488e-05, + "loss": 3.8833, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8413051154934968e-05, + "loss": 3.8883, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8404665207424445e-05, + "loss": 3.8917, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8396279259913925e-05, + "loss": 3.8867, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8387893312403408e-05, + "loss": 3.8853, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8379507364892888e-05, + "loss": 3.8862, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8371137796186097e-05, + "loss": 3.8905, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8362751848675577e-05, + "loss": 3.8859, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8354365901165057e-05, + "loss": 3.8575, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8345979953654537e-05, + "loss": 3.8943, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833761038494775e-05, + "loss": 3.8865, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8329240816240962e-05, + "loss": 3.8929, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8320854868730442e-05, + "loss": 3.8836, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831246892121992e-05, + "loss": 3.8794, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.83040829737094e-05, + "loss": 3.8779, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295697026198878e-05, + "loss": 3.8754, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828731107868836e-05, + "loss": 3.8828, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.827894150998157e-05, + "loss": 3.8699, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827055556247105e-05, + "loss": 3.8934, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826216961496053e-05, + "loss": 3.8812, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825378366745001e-05, + "loss": 3.877, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824539771993949e-05, + "loss": 3.8991, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8237044530036436e-05, + "loss": 3.8722, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228658582525916e-05, + "loss": 3.8681, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220272635015392e-05, + "loss": 3.89, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211886687504872e-05, + "loss": 3.8886, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8203500739994352e-05, + "loss": 3.8777, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8195114792483832e-05, + "loss": 3.88, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8186728844973315e-05, + "loss": 3.8677, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178342897462795e-05, + "loss": 3.8854, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169956949952275e-05, + "loss": 3.8878, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161587381245484e-05, + "loss": 3.889, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8153201433734964e-05, + "loss": 3.8853, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8144815486224444e-05, + "loss": 3.8908, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136429538713924e-05, + "loss": 3.9049, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8128043591203404e-05, + "loss": 3.8772, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119657643692884e-05, + "loss": 3.8916, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111271696182364e-05, + "loss": 3.8846, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102885748671844e-05, + "loss": 3.881, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094532558768786e-05, + "loss": 3.8791, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8086146611258266e-05, + "loss": 3.8977, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.807776066374775e-05, + "loss": 3.8888, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069374716237225e-05, + "loss": 3.8954, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060988768726705e-05, + "loss": 3.8742, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052602821216185e-05, + "loss": 3.8794, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044233252509394e-05, + "loss": 3.8822, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035847304998878e-05, + "loss": 3.8854, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027461357488358e-05, + "loss": 3.8888, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.801909178878157e-05, + "loss": 3.8841, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8010705841271047e-05, + "loss": 3.8731, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002319893760527e-05, + "loss": 3.887, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993933946250007e-05, + "loss": 3.8773, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985547998739487e-05, + "loss": 3.8787, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797716205122897e-05, + "loss": 3.8911, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.796877610371845e-05, + "loss": 3.8931, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796039015620793e-05, + "loss": 3.8854, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7952004208697407e-05, + "loss": 3.8796, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943618261186886e-05, + "loss": 3.8832, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935232313676366e-05, + "loss": 3.881, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926846366165846e-05, + "loss": 3.8897, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918460418655326e-05, + "loss": 3.8834, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791007447114481e-05, + "loss": 3.88, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790170490243802e-05, + "loss": 3.8879, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.78933189549275e-05, + "loss": 3.8908, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788493300741698e-05, + "loss": 3.8694, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7876563438710188e-05, + "loss": 3.8827, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786817749119967e-05, + "loss": 3.8754, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.785979154368915e-05, + "loss": 3.8906, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785140559617863e-05, + "loss": 3.875, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784301964866811e-05, + "loss": 3.8872, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783465007996132e-05, + "loss": 3.8732, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.78262641324508e-05, + "loss": 3.8893, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781787818494028e-05, + "loss": 3.8824, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.780949223742976e-05, + "loss": 3.8776, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780110628991924e-05, + "loss": 3.8837, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7792736721212452e-05, + "loss": 3.8987, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7784350773701932e-05, + "loss": 3.885, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777596482619141e-05, + "loss": 3.8883, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.776757887868089e-05, + "loss": 3.8823, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7759192931170372e-05, + "loss": 3.8875, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750806983659852e-05, + "loss": 3.8886, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7742421036149332e-05, + "loss": 3.8799, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7734035088638812e-05, + "loss": 3.8714, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7725681898735754e-05, + "loss": 3.8813, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7717295951225234e-05, + "loss": 3.881, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708926382518446e-05, + "loss": 3.8812, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700540435007926e-05, + "loss": 3.8798, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7692154487497406e-05, + "loss": 3.8799, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683768539986883e-05, + "loss": 3.8766, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7675382592476363e-05, + "loss": 3.8932, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666996644965843e-05, + "loss": 3.8822, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658610697455326e-05, + "loss": 3.8902, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650224749944806e-05, + "loss": 3.8686, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641838802434286e-05, + "loss": 3.8955, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633452854923766e-05, + "loss": 3.8885, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7625066907413242e-05, + "loss": 3.8863, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7616697338706455e-05, + "loss": 3.8843, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7608311391195935e-05, + "loss": 3.8822, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599925443685415e-05, + "loss": 3.8861, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591539496174895e-05, + "loss": 3.8987, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7583153548664375e-05, + "loss": 3.8715, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574767601153855e-05, + "loss": 3.8909, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566381653643335e-05, + "loss": 3.8813, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557995706132815e-05, + "loss": 3.8801, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549626137426027e-05, + "loss": 3.8839, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7541240189915507e-05, + "loss": 3.8794, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532854242404987e-05, + "loss": 3.8906, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524468294894467e-05, + "loss": 3.8877, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7516098726187676e-05, + "loss": 3.8823, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.985478401184082, + "eval_runtime": 290.3594, + "eval_samples_per_second": 1314.202, + "eval_steps_per_second": 41.07, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7507712778677156e-05, + "loss": 3.8844, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7499326831166636e-05, + "loss": 3.8827, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749094088365612e-05, + "loss": 3.8815, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482554936145596e-05, + "loss": 3.887, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7474168988635076e-05, + "loss": 3.8916, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465783041124556e-05, + "loss": 3.8776, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457397093614036e-05, + "loss": 3.8831, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7449011146103516e-05, + "loss": 3.8826, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7440625198592996e-05, + "loss": 3.8837, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.743223925108248e-05, + "loss": 3.8888, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423853303571955e-05, + "loss": 3.8803, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415467356061435e-05, + "loss": 3.8884, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7407097787354648e-05, + "loss": 3.8913, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398711839844124e-05, + "loss": 3.8723, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7390325892333604e-05, + "loss": 3.8829, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7381939944823088e-05, + "loss": 3.8695, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7373553997312568e-05, + "loss": 3.8857, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7365168049802048e-05, + "loss": 3.8779, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356782102291528e-05, + "loss": 3.8767, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348396154781008e-05, + "loss": 3.8895, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7340010207270484e-05, + "loss": 3.8892, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7331624259759964e-05, + "loss": 3.8933, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7323238312249444e-05, + "loss": 3.8877, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7314852364738927e-05, + "loss": 3.8815, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7306482796032137e-05, + "loss": 3.8817, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7298096848521616e-05, + "loss": 3.8819, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289710901011096e-05, + "loss": 3.8818, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281324953500576e-05, + "loss": 3.8835, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7272939005990056e-05, + "loss": 3.8764, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726456943728327e-05, + "loss": 3.8764, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725619986857648e-05, + "loss": 3.8779, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7247813921065958e-05, + "loss": 3.8843, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7239427973555438e-05, + "loss": 3.8926, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723105840484865e-05, + "loss": 3.882, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222672457338134e-05, + "loss": 3.8811, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7214302888631343e-05, + "loss": 3.8771, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7205916941120823e-05, + "loss": 3.8893, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7197530993610303e-05, + "loss": 3.881, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.718914504609978e-05, + "loss": 3.8806, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718075909858926e-05, + "loss": 3.8684, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172373151078743e-05, + "loss": 3.8795, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163987203568222e-05, + "loss": 3.8804, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155601256057702e-05, + "loss": 3.886, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7147215308547182e-05, + "loss": 3.8815, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7138829361036662e-05, + "loss": 3.8798, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713044341352614e-05, + "loss": 3.8788, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.712205746601562e-05, + "loss": 3.8857, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113671518505102e-05, + "loss": 3.8819, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105301949798315e-05, + "loss": 3.8549, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709691600228779e-05, + "loss": 3.8875, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.708853005477727e-05, + "loss": 3.8768, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7080160486070484e-05, + "loss": 3.8886, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071774538559964e-05, + "loss": 3.8759, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063388591049444e-05, + "loss": 3.8742, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7055002643538924e-05, + "loss": 3.8722, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7046616696028404e-05, + "loss": 3.8719, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7038230748517883e-05, + "loss": 3.8818, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7029844801007363e-05, + "loss": 3.8614, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7021458853496843e-05, + "loss": 3.8903, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701307290598632e-05, + "loss": 3.8726, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004703337279536e-05, + "loss": 3.8706, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996317389769016e-05, + "loss": 3.8943, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987931442258496e-05, + "loss": 3.8697, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979545494747972e-05, + "loss": 3.8625, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6971175926041185e-05, + "loss": 3.8842, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6962789978530665e-05, + "loss": 3.8822, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6954404031020145e-05, + "loss": 3.8709, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6946018083509625e-05, + "loss": 3.8773, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937648514802837e-05, + "loss": 3.8642, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929262567292317e-05, + "loss": 3.8754, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920876619781794e-05, + "loss": 3.8858, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912490672271274e-05, + "loss": 3.8816, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6904104724760757e-05, + "loss": 3.8794, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895718777250237e-05, + "loss": 3.8863, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887332829739717e-05, + "loss": 3.899, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878946882229197e-05, + "loss": 3.8767, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870560934718673e-05, + "loss": 3.8827, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6862191366011886e-05, + "loss": 3.8756, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6853805418501366e-05, + "loss": 3.8764, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684543584979458e-05, + "loss": 3.8726, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6837049902284058e-05, + "loss": 3.8918, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828663954773538e-05, + "loss": 3.8842, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820278007263018e-05, + "loss": 3.8915, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811892059752498e-05, + "loss": 3.8664, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6803506112241975e-05, + "loss": 3.8755, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679513654353519e-05, + "loss": 3.8767, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.678675059602467e-05, + "loss": 3.8788, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778364648514147e-05, + "loss": 3.8815, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6769978701003627e-05, + "loss": 3.8822, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761592753493107e-05, + "loss": 3.8679, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753206805982587e-05, + "loss": 3.8785, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744820858472067e-05, + "loss": 3.8744, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.673643491096155e-05, + "loss": 3.871, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.672804896345103e-05, + "loss": 3.8853, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.671967939474424e-05, + "loss": 3.8909, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671129344723372e-05, + "loss": 3.877, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.67029074997232e-05, + "loss": 3.8756, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694537931016412e-05, + "loss": 3.879, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6686151983505892e-05, + "loss": 3.872, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.667776603599537e-05, + "loss": 3.8862, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.666938008848485e-05, + "loss": 3.8792, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6660994140974328e-05, + "loss": 3.8782, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6652608193463808e-05, + "loss": 3.8807, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644222245953288e-05, + "loss": 3.8776, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635836298442768e-05, + "loss": 3.8741, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.662746672973598e-05, + "loss": 3.8752, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.661908078222546e-05, + "loss": 3.8675, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661069483471494e-05, + "loss": 3.8831, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660230888720442e-05, + "loss": 3.8749, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.65939229396939e-05, + "loss": 3.8783, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585553370987113e-05, + "loss": 3.8644, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6577167423476593e-05, + "loss": 3.8834, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568781475966073e-05, + "loss": 3.8817, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6560395528455553e-05, + "loss": 3.8729, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6552009580945033e-05, + "loss": 3.8807, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6543640012238242e-05, + "loss": 3.8921, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6535254064727722e-05, + "loss": 3.8764, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526868117217205e-05, + "loss": 3.8838, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518482169706685e-05, + "loss": 3.8774, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651009622219616e-05, + "loss": 3.8817, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650171027468564e-05, + "loss": 3.8829, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649332432717512e-05, + "loss": 3.8728, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.64849383796646e-05, + "loss": 3.8711, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476568810957814e-05, + "loss": 3.8774, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468182863447294e-05, + "loss": 3.8784, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459796915936774e-05, + "loss": 3.8771, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451427347229983e-05, + "loss": 3.8693, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6443041399719463e-05, + "loss": 3.877, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434655452208943e-05, + "loss": 3.8688, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426269504698423e-05, + "loss": 3.8904, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417883557187906e-05, + "loss": 3.8766, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6409497609677386e-05, + "loss": 3.8858, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6401111662166866e-05, + "loss": 3.8665, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6392725714656343e-05, + "loss": 3.8873, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6384356145949555e-05, + "loss": 3.8823, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6375970198439035e-05, + "loss": 3.8801, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6367584250928515e-05, + "loss": 3.8833, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6359198303417995e-05, + "loss": 3.8769, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350828734711207e-05, + "loss": 3.8803, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342442787200687e-05, + "loss": 3.8923, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6334056839690164e-05, + "loss": 3.8665, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6325670892179644e-05, + "loss": 3.8844, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631730132347286e-05, + "loss": 3.8742, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.630891537596234e-05, + "loss": 3.878, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630054580725555e-05, + "loss": 3.8779, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629215985974503e-05, + "loss": 3.8728, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628377391223451e-05, + "loss": 3.885, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627538796472399e-05, + "loss": 3.883, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626700201721347e-05, + "loss": 3.8771, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.9836487770080566, + "eval_runtime": 286.17, + "eval_samples_per_second": 1333.442, + "eval_steps_per_second": 41.671, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.625863244850668e-05, + "loss": 3.873, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625024650099616e-05, + "loss": 3.8766, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6241860553485638e-05, + "loss": 3.8783, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6233474605975118e-05, + "loss": 3.8784, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.622510503726833e-05, + "loss": 3.887, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6216719089757813e-05, + "loss": 3.8731, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.620833314224729e-05, + "loss": 3.8795, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6199963573540503e-05, + "loss": 3.8785, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6191577626029982e-05, + "loss": 3.8766, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618319167851946e-05, + "loss": 3.8792, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617480573100894e-05, + "loss": 3.8838, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6166419783498422e-05, + "loss": 3.8784, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6158050214791635e-05, + "loss": 3.8846, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.614966426728111e-05, + "loss": 3.8684, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.614127831977059e-05, + "loss": 3.8762, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.613289237226007e-05, + "loss": 3.8651, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.612450642474955e-05, + "loss": 3.8847, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611612047723903e-05, + "loss": 3.874, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6107734529728515e-05, + "loss": 3.8709, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6099348582217995e-05, + "loss": 3.8855, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.609096263470747e-05, + "loss": 3.8843, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608257668719695e-05, + "loss": 3.8839, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607419073968643e-05, + "loss": 3.8841, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606580479217591e-05, + "loss": 3.8772, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6057435223469123e-05, + "loss": 3.8788, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6049049275958603e-05, + "loss": 3.8812, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6040663328448083e-05, + "loss": 3.8684, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6032277380937563e-05, + "loss": 3.8774, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6023907812230772e-05, + "loss": 3.8745, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6015538243523985e-05, + "loss": 3.872, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6007152296013468e-05, + "loss": 3.8739, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.5998766348502945e-05, + "loss": 3.8825, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5990380400992425e-05, + "loss": 3.8831, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5982010832285637e-05, + "loss": 3.8844, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5973624884775114e-05, + "loss": 3.8729, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596525531606833e-05, + "loss": 3.8708, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.595686936855781e-05, + "loss": 3.8848, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.594848342104729e-05, + "loss": 3.8728, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5940097473536766e-05, + "loss": 3.8784, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5931711526026246e-05, + "loss": 3.8671, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5923325578515726e-05, + "loss": 3.8697, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5914939631005206e-05, + "loss": 3.8751, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5906553683494686e-05, + "loss": 3.8824, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.589816773598417e-05, + "loss": 3.876, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.588978178847365e-05, + "loss": 3.8725, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5881395840963126e-05, + "loss": 3.8768, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587302627225634e-05, + "loss": 3.8774, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5864640324745818e-05, + "loss": 3.8789, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5856254377235298e-05, + "loss": 3.8524, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5847868429724778e-05, + "loss": 3.8798, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5839482482214258e-05, + "loss": 3.8731, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5831096534703738e-05, + "loss": 3.8845, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5822710587193218e-05, + "loss": 3.8712, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5814324639682698e-05, + "loss": 3.8674, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5805955070975907e-05, + "loss": 3.8693, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.579756912346539e-05, + "loss": 3.8644, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.578918317595487e-05, + "loss": 3.8792, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.578081360724808e-05, + "loss": 3.8547, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.577242765973756e-05, + "loss": 3.8863, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.576404171222704e-05, + "loss": 3.871, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575565576471652e-05, + "loss": 3.8634, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5747286196009732e-05, + "loss": 3.8878, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5738900248499212e-05, + "loss": 3.8654, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5730514300988692e-05, + "loss": 3.8566, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5722128353478172e-05, + "loss": 3.8777, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571375878477138e-05, + "loss": 3.8782, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.570537283726086e-05, + "loss": 3.8631, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5696986889750344e-05, + "loss": 3.8752, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5688600942239824e-05, + "loss": 3.8561, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.56802149947293e-05, + "loss": 3.8697, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5671845426022513e-05, + "loss": 3.8824, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5663475857315722e-05, + "loss": 3.8772, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5655089909805206e-05, + "loss": 3.8756, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5646703962294686e-05, + "loss": 3.8795, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5638318014784165e-05, + "loss": 3.895, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5629932067273645e-05, + "loss": 3.8731, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5621562498566855e-05, + "loss": 3.8791, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5613176551056335e-05, + "loss": 3.8693, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5604790603545814e-05, + "loss": 3.8727, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5596404656035294e-05, + "loss": 3.8696, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5588018708524774e-05, + "loss": 3.8845, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5579632761014254e-05, + "loss": 3.8808, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5571246813503734e-05, + "loss": 3.8863, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5562860865993214e-05, + "loss": 3.8656, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5554491297286423e-05, + "loss": 3.8703, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5546105349775907e-05, + "loss": 3.8701, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5537719402265387e-05, + "loss": 3.8719, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5529333454754867e-05, + "loss": 3.8756, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5520963886048076e-05, + "loss": 3.88, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5512577938537556e-05, + "loss": 3.8674, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5504191991027036e-05, + "loss": 3.8742, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5495806043516516e-05, + "loss": 3.8704, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5487420096006e-05, + "loss": 3.8635, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.547903414849548e-05, + "loss": 3.8813, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5470648200984955e-05, + "loss": 3.8868, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5462262253474435e-05, + "loss": 3.876, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5453892684767648e-05, + "loss": 3.8658, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5445506737257128e-05, + "loss": 3.8766, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5437120789746608e-05, + "loss": 3.8693, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5428734842236088e-05, + "loss": 3.8775, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.54203652735293e-05, + "loss": 3.8772, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541197932601878e-05, + "loss": 3.8694, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5403593378508257e-05, + "loss": 3.8777, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5395207430997737e-05, + "loss": 3.8714, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5386821483487217e-05, + "loss": 3.8707, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.537845191478043e-05, + "loss": 3.8672, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.537006596726991e-05, + "loss": 3.8652, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.536168001975939e-05, + "loss": 3.8749, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.535329407224887e-05, + "loss": 3.8745, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.534490812473835e-05, + "loss": 3.8713, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533652217722783e-05, + "loss": 3.8618, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.532813622971731e-05, + "loss": 3.8739, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.531975028220679e-05, + "loss": 3.8793, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.531136433469627e-05, + "loss": 3.8669, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.530301114479321e-05, + "loss": 3.8774, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529462519728269e-05, + "loss": 3.8847, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5286255628575903e-05, + "loss": 3.8768, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5277869681065383e-05, + "loss": 3.8758, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5269483733554863e-05, + "loss": 3.8763, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5261097786044343e-05, + "loss": 3.8755, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5252711838533823e-05, + "loss": 3.8789, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5244342269827033e-05, + "loss": 3.8669, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5235956322316513e-05, + "loss": 3.8661, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5227570374805993e-05, + "loss": 3.8723, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5219184427295475e-05, + "loss": 3.8735, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5210798479784955e-05, + "loss": 3.8671, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5202412532274435e-05, + "loss": 3.8697, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5194026584763913e-05, + "loss": 3.8667, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5185640637253393e-05, + "loss": 3.8651, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5177254689742873e-05, + "loss": 3.886, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5168885121036084e-05, + "loss": 3.8717, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5160499173525564e-05, + "loss": 3.8851, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5152113226015044e-05, + "loss": 3.8602, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5143727278504524e-05, + "loss": 3.8846, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5135341330994004e-05, + "loss": 3.8793, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5126971762287214e-05, + "loss": 3.8762, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5118585814776694e-05, + "loss": 3.8718, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5110199867266176e-05, + "loss": 3.8764, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5101813919755656e-05, + "loss": 3.8775, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5093444351048867e-05, + "loss": 3.8839, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5085058403538347e-05, + "loss": 3.8683, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5076672456027827e-05, + "loss": 3.8743, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5068286508517307e-05, + "loss": 3.8741, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5059900561006787e-05, + "loss": 3.8727, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5051514613496265e-05, + "loss": 3.8705, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5043128665985745e-05, + "loss": 3.8739, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5034742718475225e-05, + "loss": 3.8786, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5026373149768439e-05, + "loss": 3.8774, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5017987202257916e-05, + "loss": 3.871, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.982069253921509, + "eval_runtime": 285.513, + "eval_samples_per_second": 1336.51, + "eval_steps_per_second": 41.767, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.500961763355113e-05, + "loss": 3.8787, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.500123168604061e-05, + "loss": 3.8685, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4992845738530086e-05, + "loss": 3.8764, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4984459791019568e-05, + "loss": 3.8771, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4976073843509048e-05, + "loss": 3.876, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4967687895998528e-05, + "loss": 3.8742, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4959301948488008e-05, + "loss": 3.8758, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4950916000977488e-05, + "loss": 3.8735, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.494253005346697e-05, + "loss": 3.8699, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4934144105956446e-05, + "loss": 3.8759, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925758158445926e-05, + "loss": 3.8799, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4917372210935408e-05, + "loss": 3.8725, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.490900264222862e-05, + "loss": 3.8854, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900616694718098e-05, + "loss": 3.859, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4892230747207578e-05, + "loss": 3.8694, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883844799697058e-05, + "loss": 3.8629, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875458852186538e-05, + "loss": 3.8819, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4867072904676018e-05, + "loss": 3.8676, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.48586869571655e-05, + "loss": 3.8666, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4850301009654976e-05, + "loss": 3.8759, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4841915062144456e-05, + "loss": 3.8832, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.483354549343767e-05, + "loss": 3.8823, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.482515954592715e-05, + "loss": 3.8786, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816773598416627e-05, + "loss": 3.8738, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808387650906109e-05, + "loss": 3.876, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4800001703395589e-05, + "loss": 3.8752, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4791615755885069e-05, + "loss": 3.8648, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.478324618717828e-05, + "loss": 3.8726, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.477486023966776e-05, + "loss": 3.869, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.476647429215724e-05, + "loss": 3.8649, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.475808834464672e-05, + "loss": 3.872, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749702397136201e-05, + "loss": 3.8751, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.474133282842941e-05, + "loss": 3.8804, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4732946880918892e-05, + "loss": 3.8813, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.47245773122121e-05, + "loss": 3.8705, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4716207743505315e-05, + "loss": 3.8672, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4707821795994795e-05, + "loss": 3.88, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4699435848484275e-05, + "loss": 3.8653, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4691049900973753e-05, + "loss": 3.8752, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4682663953463233e-05, + "loss": 3.867, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4674278005952713e-05, + "loss": 3.8629, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4665892058442193e-05, + "loss": 3.8725, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657506110931673e-05, + "loss": 3.8786, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4649120163421155e-05, + "loss": 3.8707, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640734215910631e-05, + "loss": 3.8703, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632348268400111e-05, + "loss": 3.8732, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4623962320889593e-05, + "loss": 3.8702, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4615576373379073e-05, + "loss": 3.8769, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4607190425868553e-05, + "loss": 3.8505, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598804478358033e-05, + "loss": 3.8777, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590418530847513e-05, + "loss": 3.8677, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4582048962140723e-05, + "loss": 3.8818, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4573663014630203e-05, + "loss": 3.8667, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4565277067119685e-05, + "loss": 3.868, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4556891119609165e-05, + "loss": 3.8628, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4548521550902374e-05, + "loss": 3.863, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4540135603391856e-05, + "loss": 3.8719, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4531749655881336e-05, + "loss": 3.8497, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4523363708370812e-05, + "loss": 3.8815, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4514994139664026e-05, + "loss": 3.8678, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4506608192153506e-05, + "loss": 3.8581, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4498238623446717e-05, + "loss": 3.8869, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4489852675936197e-05, + "loss": 3.8579, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4481466728425677e-05, + "loss": 3.8567, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4473080780915157e-05, + "loss": 3.8702, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4464694833404635e-05, + "loss": 3.8764, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4456308885894115e-05, + "loss": 3.8604, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4447939317187328e-05, + "loss": 3.8702, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.443955336967681e-05, + "loss": 3.8516, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4431167422166286e-05, + "loss": 3.8673, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4422781474655766e-05, + "loss": 3.8774, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4414395527145247e-05, + "loss": 3.8765, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4406009579634727e-05, + "loss": 3.8692, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4397640010927938e-05, + "loss": 3.8736, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4389254063417418e-05, + "loss": 3.8889, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4380868115906898e-05, + "loss": 3.8681, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4372482168396378e-05, + "loss": 3.8799, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4364096220885858e-05, + "loss": 3.8626, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355726652179069e-05, + "loss": 3.8712, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4347340704668549e-05, + "loss": 3.8632, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4338954757158029e-05, + "loss": 3.8801, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.433056880964751e-05, + "loss": 3.8746, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.432218286213699e-05, + "loss": 3.8836, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313813293430201e-05, + "loss": 3.8615, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4305427345919681e-05, + "loss": 3.8656, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4297041398409161e-05, + "loss": 3.8625, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4288655450898641e-05, + "loss": 3.8749, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.428026950338812e-05, + "loss": 3.869, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4271899934681332e-05, + "loss": 3.8726, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263530365974543e-05, + "loss": 3.8634, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4255144418464023e-05, + "loss": 3.8678, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246758470953502e-05, + "loss": 3.8648, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4238372523442982e-05, + "loss": 3.8618, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4229986575932464e-05, + "loss": 3.8737, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.422160062842194e-05, + "loss": 3.8856, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.421321468091142e-05, + "loss": 3.8726, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204845112204635e-05, + "loss": 3.8646, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4196459164694115e-05, + "loss": 3.869, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4188073217183593e-05, + "loss": 3.866, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4179687269673073e-05, + "loss": 3.8748, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4171301322162553e-05, + "loss": 3.872, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4162915374652033e-05, + "loss": 3.8622, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4154529427141513e-05, + "loss": 3.8736, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4146143479630994e-05, + "loss": 3.8707, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4137757532120471e-05, + "loss": 3.8661, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129371584609951e-05, + "loss": 3.8656, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4120985637099433e-05, + "loss": 3.8649, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4112599689588913e-05, + "loss": 3.8676, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4104230120882123e-05, + "loss": 3.8718, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095844173371603e-05, + "loss": 3.8661, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087458225861083e-05, + "loss": 3.8566, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4079072278350563e-05, + "loss": 3.8684, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4070702709643774e-05, + "loss": 3.8754, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4062333140936987e-05, + "loss": 3.8655, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4053947193426466e-05, + "loss": 3.8704, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045561245915945e-05, + "loss": 3.8796, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4037175298405425e-05, + "loss": 3.8716, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4028789350894905e-05, + "loss": 3.872, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020403403384386e-05, + "loss": 3.8722, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4012017455873866e-05, + "loss": 3.8744, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4003647887167075e-05, + "loss": 3.8795, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3995261939656557e-05, + "loss": 3.8586, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3986875992146037e-05, + "loss": 3.8667, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3978490044635517e-05, + "loss": 3.8649, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3970104097124997e-05, + "loss": 3.8712, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3961734528418208e-05, + "loss": 3.8667, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3953348580907688e-05, + "loss": 3.8637, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3944962633397168e-05, + "loss": 3.8585, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.393657668588665e-05, + "loss": 3.8628, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3928190738376126e-05, + "loss": 3.8801, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.391982116966934e-05, + "loss": 3.8704, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3911451600962549e-05, + "loss": 3.8753, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3903065653452029e-05, + "loss": 3.862, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.389467970594151e-05, + "loss": 3.876, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.388629375843099e-05, + "loss": 3.8773, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.387790781092047e-05, + "loss": 3.8707, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3869521863409949e-05, + "loss": 3.8653, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3861135915899429e-05, + "loss": 3.8715, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3852749968388909e-05, + "loss": 3.8748, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3844364020878389e-05, + "loss": 3.8791, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.38359944521716e-05, + "loss": 3.8633, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.382760850466108e-05, + "loss": 3.8689, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3819238935954294e-05, + "loss": 3.8702, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3810852988443774e-05, + "loss": 3.872, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.380246704093325e-05, + "loss": 3.8633, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3794081093422732e-05, + "loss": 3.871, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3785695145912212e-05, + "loss": 3.8685, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3777309198401692e-05, + "loss": 3.8797, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3768923250891172e-05, + "loss": 3.8663, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9806528091430664, + "eval_runtime": 298.9561, + "eval_samples_per_second": 1276.412, + "eval_steps_per_second": 39.889, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3760537303380652e-05, + "loss": 3.868, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3752167734673862e-05, + "loss": 3.8635, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3743781787163342e-05, + "loss": 3.8702, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3735395839652822e-05, + "loss": 3.8755, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3727009892142304e-05, + "loss": 3.8716, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.371862394463178e-05, + "loss": 3.8731, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.371023799712126e-05, + "loss": 3.8682, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3701852049610742e-05, + "loss": 3.8685, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3693482480903955e-05, + "loss": 3.8653, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3685096533393433e-05, + "loss": 3.8764, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3676710585882913e-05, + "loss": 3.8685, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3668341017176125e-05, + "loss": 3.8734, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3659955069665604e-05, + "loss": 3.8809, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3651569122155084e-05, + "loss": 3.856, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3643183174644564e-05, + "loss": 3.8675, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3634797227134043e-05, + "loss": 3.8573, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3626411279623525e-05, + "loss": 3.8792, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3618025332113005e-05, + "loss": 3.8617, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3609639384602485e-05, + "loss": 3.8649, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3601253437091963e-05, + "loss": 3.8674, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3592883868385176e-05, + "loss": 3.8803, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3584497920874656e-05, + "loss": 3.8736, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3576128352167867e-05, + "loss": 3.8768, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3567742404657346e-05, + "loss": 3.8688, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3559356457146826e-05, + "loss": 3.8748, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3550970509636306e-05, + "loss": 3.8654, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3542584562125785e-05, + "loss": 3.8656, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3534198614615265e-05, + "loss": 3.8676, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3525812667104745e-05, + "loss": 3.8662, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3517426719594226e-05, + "loss": 3.8609, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3509040772083706e-05, + "loss": 3.866, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3500654824573186e-05, + "loss": 3.8705, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3492268877062666e-05, + "loss": 3.8782, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3483882929552144e-05, + "loss": 3.8729, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3475513360845357e-05, + "loss": 3.8653, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3467143792138568e-05, + "loss": 3.8658, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3458757844628048e-05, + "loss": 3.8793, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3450371897117528e-05, + "loss": 3.8545, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3441985949607007e-05, + "loss": 3.8749, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3433616380900218e-05, + "loss": 3.8636, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3425230433389698e-05, + "loss": 3.8548, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.341684448587918e-05, + "loss": 3.8685, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.340845853836866e-05, + "loss": 3.8751, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.340007259085814e-05, + "loss": 3.8679, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.339170302215135e-05, + "loss": 3.8673, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.338331707464083e-05, + "loss": 3.8662, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.337493112713031e-05, + "loss": 3.867, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.336654517961979e-05, + "loss": 3.8734, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3358159232109269e-05, + "loss": 3.8483, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3349773284598749e-05, + "loss": 3.8672, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3341387337088229e-05, + "loss": 3.8667, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.333301776838144e-05, + "loss": 3.8797, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.332463182087092e-05, + "loss": 3.8602, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.33162458733604e-05, + "loss": 3.8652, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3307859925849881e-05, + "loss": 3.8514, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.329949035714309e-05, + "loss": 3.8604, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3291104409632572e-05, + "loss": 3.8724, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282718462122052e-05, + "loss": 3.8467, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274332514611532e-05, + "loss": 3.8757, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3265946567101012e-05, + "loss": 3.8664, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257560619590492e-05, + "loss": 3.8566, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.324917467207997e-05, + "loss": 3.8798, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.324078872456945e-05, + "loss": 3.8532, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.323240277705893e-05, + "loss": 3.8515, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3224016829548411e-05, + "loss": 3.8629, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3215630882037891e-05, + "loss": 3.8755, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3207261313331102e-05, + "loss": 3.8587, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3198875365820582e-05, + "loss": 3.8636, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3190489418310062e-05, + "loss": 3.8487, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3182103470799542e-05, + "loss": 3.863, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3173717523289022e-05, + "loss": 3.8703, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3165331575778504e-05, + "loss": 3.8764, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.315694562826798e-05, + "loss": 3.8629, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.314855968075746e-05, + "loss": 3.8713, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3140190112050674e-05, + "loss": 3.8805, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3131820543343883e-05, + "loss": 3.865, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3123434595833365e-05, + "loss": 3.8689, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3115048648322845e-05, + "loss": 3.8649, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3106662700812325e-05, + "loss": 3.8678, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3098276753301803e-05, + "loss": 3.8599, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3089907184595016e-05, + "loss": 3.8726, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3081521237084496e-05, + "loss": 3.8685, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3073135289573976e-05, + "loss": 3.8824, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3064749342063454e-05, + "loss": 3.8657, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3056363394552934e-05, + "loss": 3.8556, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3047977447042414e-05, + "loss": 3.8569, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3039591499531895e-05, + "loss": 3.8724, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3031221930825105e-05, + "loss": 3.8586, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3022852362118319e-05, + "loss": 3.8707, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3014466414607799e-05, + "loss": 3.8645, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3006080467097275e-05, + "loss": 3.8604, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997694519586757e-05, + "loss": 3.8633, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2989308572076237e-05, + "loss": 3.8595, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2980922624565717e-05, + "loss": 3.8684, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2972536677055197e-05, + "loss": 3.8767, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2964150729544677e-05, + "loss": 3.8728, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2955764782034158e-05, + "loss": 3.8569, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2947395213327367e-05, + "loss": 3.8671, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2939009265816847e-05, + "loss": 3.8604, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2930623318306329e-05, + "loss": 3.8714, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2922237370795806e-05, + "loss": 3.8714, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.291386780208902e-05, + "loss": 3.855, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.29054818545785e-05, + "loss": 3.871, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.289711228587171e-05, + "loss": 3.8655, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.288872633836119e-05, + "loss": 3.8625, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.288034039085067e-05, + "loss": 3.861, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.287195444334015e-05, + "loss": 3.8594, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.286356849582963e-05, + "loss": 3.8643, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2855182548319109e-05, + "loss": 3.8695, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2846796600808589e-05, + "loss": 3.8612, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2838410653298069e-05, + "loss": 3.8536, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.283002470578755e-05, + "loss": 3.8624, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.282163875827703e-05, + "loss": 3.8744, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.281325281076651e-05, + "loss": 3.8625, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2804866863255988e-05, + "loss": 3.8652, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.27964972945492e-05, + "loss": 3.8688, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2788144104646144e-05, + "loss": 3.8767, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2779758157135624e-05, + "loss": 3.8668, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2771372209625104e-05, + "loss": 3.8666, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2762986262114582e-05, + "loss": 3.8716, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2754600314604062e-05, + "loss": 3.872, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2746214367093542e-05, + "loss": 3.8579, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2737828419583022e-05, + "loss": 3.8635, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2729442472072504e-05, + "loss": 3.8548, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2721056524561984e-05, + "loss": 3.8687, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.271267057705146e-05, + "loss": 3.864, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2704284629540942e-05, + "loss": 3.8576, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2695898682030422e-05, + "loss": 3.8553, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2687529113323634e-05, + "loss": 3.8627, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2679143165813113e-05, + "loss": 3.8745, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2670757218302593e-05, + "loss": 3.8685, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2662371270792073e-05, + "loss": 3.8683, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2653985323281553e-05, + "loss": 3.857, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2645599375771033e-05, + "loss": 3.872, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2637213428260514e-05, + "loss": 3.8726, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2628843859553723e-05, + "loss": 3.8684, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2620457912043205e-05, + "loss": 3.8614, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2612088343336414e-05, + "loss": 3.866, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2603702395825896e-05, + "loss": 3.871, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2595316448315376e-05, + "loss": 3.8748, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2586930500804856e-05, + "loss": 3.8624, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2578544553294336e-05, + "loss": 3.8592, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2570158605783816e-05, + "loss": 3.868, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2561772658273294e-05, + "loss": 3.8663, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2553386710762774e-05, + "loss": 3.8562, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2545000763252254e-05, + "loss": 3.8714, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2536631194545464e-05, + "loss": 3.8631, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2528245247034944e-05, + "loss": 3.877, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2519859299524424e-05, + "loss": 3.8558, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9791452884674072, + "eval_runtime": 298.2804, + "eval_samples_per_second": 1279.303, + "eval_steps_per_second": 39.979, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2511489730817639e-05, + "loss": 3.8809, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2503103783307115e-05, + "loss": 3.8615, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2494717835796597e-05, + "loss": 3.8667, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2486331888286077e-05, + "loss": 3.8719, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2477945940775557e-05, + "loss": 3.8668, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2469559993265037e-05, + "loss": 3.8685, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2461174045754517e-05, + "loss": 3.8634, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2452788098243997e-05, + "loss": 3.8649, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2444402150733477e-05, + "loss": 3.8633, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2436016203222955e-05, + "loss": 3.8704, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2427630255712436e-05, + "loss": 3.868, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2419244308201916e-05, + "loss": 3.8715, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2410874739495127e-05, + "loss": 3.8746, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2402488791984607e-05, + "loss": 3.8521, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2394102844474087e-05, + "loss": 3.8615, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2385716896963567e-05, + "loss": 3.8518, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2377330949453047e-05, + "loss": 3.876, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2368945001942527e-05, + "loss": 3.8581, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2360559054432007e-05, + "loss": 3.8608, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2352173106921487e-05, + "loss": 3.8687, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2343787159410967e-05, + "loss": 3.8745, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2335401211900447e-05, + "loss": 3.8696, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2327015264389927e-05, + "loss": 3.8687, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2318629316879405e-05, + "loss": 3.8658, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2310243369368887e-05, + "loss": 3.8724, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2301873800662097e-05, + "loss": 3.8587, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2293487853151577e-05, + "loss": 3.8624, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2285118284444788e-05, + "loss": 3.8652, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2276732336934268e-05, + "loss": 3.8607, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2268346389423748e-05, + "loss": 3.8527, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2259960441913228e-05, + "loss": 3.8635, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2251574494402708e-05, + "loss": 3.8653, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2243188546892188e-05, + "loss": 3.8766, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2234802599381668e-05, + "loss": 3.8724, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2226433030674879e-05, + "loss": 3.8605, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2218063461968091e-05, + "loss": 3.8653, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2209677514457571e-05, + "loss": 3.8741, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2201291566947051e-05, + "loss": 3.8516, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.219290561943653e-05, + "loss": 3.8724, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2184519671926011e-05, + "loss": 3.8536, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2176133724415491e-05, + "loss": 3.8534, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.216774777690497e-05, + "loss": 3.8636, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.215936182939445e-05, + "loss": 3.8772, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215097588188393e-05, + "loss": 3.858, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.214260631317714e-05, + "loss": 3.8632, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2134220365666622e-05, + "loss": 3.8643, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2125834418156102e-05, + "loss": 3.8621, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2117448470645581e-05, + "loss": 3.867, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.210906252313506e-05, + "loss": 3.8457, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2100676575624541e-05, + "loss": 3.8651, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2092290628114021e-05, + "loss": 3.8662, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.20839046806035e-05, + "loss": 3.8723, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2075535111896712e-05, + "loss": 3.8538, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2067149164386192e-05, + "loss": 3.855, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2058763216875672e-05, + "loss": 3.8571, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2050377269365152e-05, + "loss": 3.8508, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2042007700658363e-05, + "loss": 3.8705, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2033621753147843e-05, + "loss": 3.8413, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2025252184441055e-05, + "loss": 3.8694, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2016866236930533e-05, + "loss": 3.8644, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2008480289420013e-05, + "loss": 3.8556, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2000094341909495e-05, + "loss": 3.8729, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1991708394398973e-05, + "loss": 3.8527, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1983322446888453e-05, + "loss": 3.8484, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1974952878181666e-05, + "loss": 3.8531, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1966566930671146e-05, + "loss": 3.8755, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1958180983160624e-05, + "loss": 3.8563, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1949795035650106e-05, + "loss": 3.8541, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1941409088139586e-05, + "loss": 3.8476, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1933023140629064e-05, + "loss": 3.8558, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1924653571922276e-05, + "loss": 3.8677, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1916267624411756e-05, + "loss": 3.872, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1907881676901236e-05, + "loss": 3.8571, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1899495729390715e-05, + "loss": 3.8716, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1891109781880196e-05, + "loss": 3.8764, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1882723834369676e-05, + "loss": 3.8643, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1874337886859154e-05, + "loss": 3.8636, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1865968318152367e-05, + "loss": 3.8603, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1857582370641847e-05, + "loss": 3.8656, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1849196423131327e-05, + "loss": 3.8586, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1840810475620807e-05, + "loss": 3.8668, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1832424528110287e-05, + "loss": 3.8669, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1824054959403497e-05, + "loss": 3.8765, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1815669011892977e-05, + "loss": 3.8639, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1807299443186188e-05, + "loss": 3.8508, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1798913495675668e-05, + "loss": 3.8534, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179052754816515e-05, + "loss": 3.8681, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1782141600654628e-05, + "loss": 3.8548, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1773755653144108e-05, + "loss": 3.8679, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1765369705633588e-05, + "loss": 3.8623, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1756983758123068e-05, + "loss": 3.8571, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1748597810612548e-05, + "loss": 3.8541, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.174022824190576e-05, + "loss": 3.8589, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.173184229439524e-05, + "loss": 3.8654, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1723456346884719e-05, + "loss": 3.8716, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1715070399374199e-05, + "loss": 3.8664, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.170668445186368e-05, + "loss": 3.8546, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1698298504353158e-05, + "loss": 3.8631, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1689912556842638e-05, + "loss": 3.8605, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1681526609332118e-05, + "loss": 3.8635, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1673157040625331e-05, + "loss": 3.8672, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1664803850722274e-05, + "loss": 3.8494, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1656417903211752e-05, + "loss": 3.8663, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1648031955701232e-05, + "loss": 3.8626, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1639646008190714e-05, + "loss": 3.8582, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1631260060680192e-05, + "loss": 3.8564, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1622874113169672e-05, + "loss": 3.8578, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1614488165659152e-05, + "loss": 3.8596, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1606102218148632e-05, + "loss": 3.8659, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1597716270638112e-05, + "loss": 3.8562, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1589330323127592e-05, + "loss": 3.8485, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1580960754420805e-05, + "loss": 3.8561, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1572574806910283e-05, + "loss": 3.8714, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1564205238203495e-05, + "loss": 3.8582, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1555819290692975e-05, + "loss": 3.8587, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1547433343182454e-05, + "loss": 3.8681, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1539047395671934e-05, + "loss": 3.8701, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1530661448161415e-05, + "loss": 3.8637, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1522275500650895e-05, + "loss": 3.8652, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1513889553140373e-05, + "loss": 3.8683, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1505503605629853e-05, + "loss": 3.866, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1497117658119335e-05, + "loss": 3.8536, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1488731710608813e-05, + "loss": 3.8598, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1480362141902026e-05, + "loss": 3.857, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1471976194391506e-05, + "loss": 3.8606, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1463590246880986e-05, + "loss": 3.8578, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1455204299370464e-05, + "loss": 3.853, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1446818351859946e-05, + "loss": 3.8556, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1438448783153156e-05, + "loss": 3.8606, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1430062835642635e-05, + "loss": 3.8601, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1421676888132116e-05, + "loss": 3.8704, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1413290940621596e-05, + "loss": 3.8683, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1404904993111076e-05, + "loss": 3.8527, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1396519045600554e-05, + "loss": 3.8671, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1388149476893767e-05, + "loss": 3.8665, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1379763529383247e-05, + "loss": 3.8678, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1371377581872727e-05, + "loss": 3.8575, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1362991634362207e-05, + "loss": 3.8657, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1354622065655418e-05, + "loss": 3.8671, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.13462361181449e-05, + "loss": 3.8669, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1337850170634377e-05, + "loss": 3.8576, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1329464223123857e-05, + "loss": 3.8592, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1321078275613337e-05, + "loss": 3.8638, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1312692328102817e-05, + "loss": 3.8591, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1304306380592297e-05, + "loss": 3.8529, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1295936811885508e-05, + "loss": 3.8661, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.128755086437499e-05, + "loss": 3.8592, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1279164916864468e-05, + "loss": 3.8747, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1270778969353948e-05, + "loss": 3.853, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.9776360988616943, + "eval_runtime": 301.3546, + "eval_samples_per_second": 1266.253, + "eval_steps_per_second": 39.571, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1262393021843428e-05, + "loss": 3.8609, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1254007074332908e-05, + "loss": 3.8622, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1245621126822388e-05, + "loss": 3.8596, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1237235179311868e-05, + "loss": 3.8695, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1228849231801348e-05, + "loss": 3.8619, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1220463284290828e-05, + "loss": 3.8665, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1212077336780308e-05, + "loss": 3.8585, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.120370776807352e-05, + "loss": 3.8592, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1195338199366731e-05, + "loss": 3.8603, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1186952251856211e-05, + "loss": 3.8656, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.117856630434569e-05, + "loss": 3.8599, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.117018035683517e-05, + "loss": 3.8735, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1161810788128382e-05, + "loss": 3.873, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1153424840617862e-05, + "loss": 3.8504, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1145038893107341e-05, + "loss": 3.8539, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1136652945596821e-05, + "loss": 3.8525, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1128266998086301e-05, + "loss": 3.8675, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1119881050575781e-05, + "loss": 3.8609, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1111495103065261e-05, + "loss": 3.8557, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.110310915555474e-05, + "loss": 3.8612, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1094739586847952e-05, + "loss": 3.8709, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1086353639337432e-05, + "loss": 3.868, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1077984070630644e-05, + "loss": 3.8655, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1069598123120123e-05, + "loss": 3.8629, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1061212175609603e-05, + "loss": 3.8741, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1052826228099084e-05, + "loss": 3.8534, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1044440280588563e-05, + "loss": 3.8596, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1036054333078043e-05, + "loss": 3.8636, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1027668385567523e-05, + "loss": 3.853, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1019282438057004e-05, + "loss": 3.856, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1010896490546482e-05, + "loss": 3.858, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1002510543035962e-05, + "loss": 3.8623, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0994124595525442e-05, + "loss": 3.8732, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0985755026818653e-05, + "loss": 3.8643, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0977369079308133e-05, + "loss": 3.8603, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0968999510601346e-05, + "loss": 3.8583, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0960613563090826e-05, + "loss": 3.8678, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0952227615580304e-05, + "loss": 3.8492, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0943841668069785e-05, + "loss": 3.8671, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0935455720559265e-05, + "loss": 3.8538, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0927069773048744e-05, + "loss": 3.8509, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0918683825538224e-05, + "loss": 3.8597, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0910297878027705e-05, + "loss": 3.8739, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0901928309320916e-05, + "loss": 3.848, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0893542361810394e-05, + "loss": 3.8631, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0885156414299876e-05, + "loss": 3.861, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0876770466789356e-05, + "loss": 3.8617, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0868384519278834e-05, + "loss": 3.8649, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0859998571768316e-05, + "loss": 3.8386, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0851612624257796e-05, + "loss": 3.8598, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0843226676747274e-05, + "loss": 3.8669, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0834857108040487e-05, + "loss": 3.8641, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0826487539333697e-05, + "loss": 3.8517, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0818101591823177e-05, + "loss": 3.851, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0809715644312657e-05, + "loss": 3.8545, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0801329696802137e-05, + "loss": 3.8467, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0792943749291617e-05, + "loss": 3.87, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.078457418058483e-05, + "loss": 3.8386, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0776188233074308e-05, + "loss": 3.8629, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0767802285563788e-05, + "loss": 3.8609, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0759416338053268e-05, + "loss": 3.85, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.075104676934648e-05, + "loss": 3.8655, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0742660821835959e-05, + "loss": 3.8523, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.073427487432544e-05, + "loss": 3.8457, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.072588892681492e-05, + "loss": 3.8493, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0717502979304398e-05, + "loss": 3.8751, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0709117031793878e-05, + "loss": 3.8508, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.070073108428336e-05, + "loss": 3.8518, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.069236151557657e-05, + "loss": 3.845, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.068397556806605e-05, + "loss": 3.8526, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.067558962055553e-05, + "loss": 3.8645, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.066720367304501e-05, + "loss": 3.868, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0658834104338221e-05, + "loss": 3.851, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0650448156827701e-05, + "loss": 3.8669, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0642062209317181e-05, + "loss": 3.8752, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0633676261806661e-05, + "loss": 3.8629, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0625290314296141e-05, + "loss": 3.855, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0616904366785621e-05, + "loss": 3.8597, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0608518419275101e-05, + "loss": 3.8619, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060013247176458e-05, + "loss": 3.8582, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0591762903057792e-05, + "loss": 3.8557, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0583376955547272e-05, + "loss": 3.8687, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0574991008036752e-05, + "loss": 3.8722, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0566621439329963e-05, + "loss": 3.8648, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0558235491819443e-05, + "loss": 3.8443, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0549849544308924e-05, + "loss": 3.8511, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0541463596798403e-05, + "loss": 3.8635, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0533077649287882e-05, + "loss": 3.853, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0524708080581095e-05, + "loss": 3.8639, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0516338511874306e-05, + "loss": 3.855, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0507952564363786e-05, + "loss": 3.8539, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0499566616853266e-05, + "loss": 3.849, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0491180669342746e-05, + "loss": 3.8578, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0482794721832226e-05, + "loss": 3.859, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0474408774321706e-05, + "loss": 3.8676, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0466022826811185e-05, + "loss": 3.8662, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0457636879300665e-05, + "loss": 3.848, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0449250931790144e-05, + "loss": 3.8609, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0440864984279625e-05, + "loss": 3.8573, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0432479036769105e-05, + "loss": 3.86, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0424093089258584e-05, + "loss": 3.8638, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0415707141748064e-05, + "loss": 3.8501, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0407353951845007e-05, + "loss": 3.858, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0398968004334487e-05, + "loss": 3.8602, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0390582056823967e-05, + "loss": 3.8571, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0382196109313447e-05, + "loss": 3.852, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0373810161802927e-05, + "loss": 3.8549, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0365424214292407e-05, + "loss": 3.8572, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0357054645585617e-05, + "loss": 3.8617, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0348668698075097e-05, + "loss": 3.8513, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0340282750564579e-05, + "loss": 3.8509, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0331896803054057e-05, + "loss": 3.8493, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0323510855543537e-05, + "loss": 3.8673, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.031514128683675e-05, + "loss": 3.8553, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.030675533932623e-05, + "loss": 3.8555, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0298369391815708e-05, + "loss": 3.8666, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0289983444305188e-05, + "loss": 3.8694, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.02816138755984e-05, + "loss": 3.8593, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0273227928087879e-05, + "loss": 3.8605, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.026484198057736e-05, + "loss": 3.8672, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.025645603306684e-05, + "loss": 3.8616, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0248086464360051e-05, + "loss": 3.8526, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0239700516849531e-05, + "loss": 3.8589, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0231330948142742e-05, + "loss": 3.852, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0222945000632222e-05, + "loss": 3.8583, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0214559053121703e-05, + "loss": 3.8527, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0206173105611182e-05, + "loss": 3.8542, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0197787158100662e-05, + "loss": 3.8538, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0189401210590142e-05, + "loss": 3.8566, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0181015263079622e-05, + "loss": 3.8557, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0172629315569101e-05, + "loss": 3.8664, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0164243368058581e-05, + "loss": 3.8657, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0155857420548061e-05, + "loss": 3.8563, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0147471473037541e-05, + "loss": 3.8574, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0139085525527021e-05, + "loss": 3.8613, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0130699578016501e-05, + "loss": 3.8649, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0122346388113443e-05, + "loss": 3.86, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0113960440602925e-05, + "loss": 3.8613, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0105574493092404e-05, + "loss": 3.8649, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0097188545581884e-05, + "loss": 3.862, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0088802598071363e-05, + "loss": 3.8591, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0080416650560844e-05, + "loss": 3.8543, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0072047081854055e-05, + "loss": 3.8596, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0063661134343533e-05, + "loss": 3.8568, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0055291565636746e-05, + "loss": 3.8508, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0046905618126226e-05, + "loss": 3.8664, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0038519670615706e-05, + "loss": 3.8578, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0030133723105186e-05, + "loss": 3.8666, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0021747775594666e-05, + "loss": 3.8519, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0013378206887877e-05, + "loss": 3.8596, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.976557493209839, + "eval_runtime": 299.4561, + "eval_samples_per_second": 1274.28, + "eval_steps_per_second": 39.822, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0004992259377358e-05, + "loss": 3.8588, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.996606311866836e-06, + "loss": 3.8504, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.988220364356316e-06, + "loss": 3.8676, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.979834416845796e-06, + "loss": 3.8577, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.971448469335276e-06, + "loss": 3.864, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.963062521824756e-06, + "loss": 3.8545, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.954676574314236e-06, + "loss": 3.8591, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.946290626803716e-06, + "loss": 3.8534, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.937904679293196e-06, + "loss": 3.8651, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.929518731782676e-06, + "loss": 3.8563, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.921132784272156e-06, + "loss": 3.8708, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.912746836761636e-06, + "loss": 3.8662, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.904377268054847e-06, + "loss": 3.8525, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.895991320544327e-06, + "loss": 3.8525, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.887605373033807e-06, + "loss": 3.8458, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.879219425523287e-06, + "loss": 3.862, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.870833478012767e-06, + "loss": 3.8562, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.862447530502247e-06, + "loss": 3.856, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.854077961795457e-06, + "loss": 3.8538, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.845692014284937e-06, + "loss": 3.8713, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.837306066774419e-06, + "loss": 3.8602, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.828920119263897e-06, + "loss": 3.8637, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.820534171753377e-06, + "loss": 3.8615, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.812148224242857e-06, + "loss": 3.8684, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.803762276732337e-06, + "loss": 3.8514, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.795376329221817e-06, + "loss": 3.8591, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.786990381711297e-06, + "loss": 3.8533, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.778604434200777e-06, + "loss": 3.8522, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.770234865493988e-06, + "loss": 3.8514, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.761848917983468e-06, + "loss": 3.8535, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.75346297047295e-06, + "loss": 3.8576, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.745077022962428e-06, + "loss": 3.8692, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.736707454255638e-06, + "loss": 3.8607, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.72832150674512e-06, + "loss": 3.8561, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.71995193803833e-06, + "loss": 3.8583, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.71156599052781e-06, + "loss": 3.8626, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.70318004301729e-06, + "loss": 3.85, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.69479409550677e-06, + "loss": 3.8642, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.68640814799625e-06, + "loss": 3.847, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.67802220048573e-06, + "loss": 3.8519, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.66963625297521e-06, + "loss": 3.8583, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.66125030546469e-06, + "loss": 3.8688, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.652864357954169e-06, + "loss": 3.8501, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.64447841044365e-06, + "loss": 3.8578, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.63609246293313e-06, + "loss": 3.8556, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.627722894226341e-06, + "loss": 3.8538, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.619353325519552e-06, + "loss": 3.8655, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.610967378009032e-06, + "loss": 3.8347, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.602581430498512e-06, + "loss": 3.8539, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.594195482987992e-06, + "loss": 3.8638, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.585809535477472e-06, + "loss": 3.8639, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.577423587966952e-06, + "loss": 3.8528, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.569037640456432e-06, + "loss": 3.8434, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.560651692945912e-06, + "loss": 3.8538, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.552282124239122e-06, + "loss": 3.8406, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.543896176728604e-06, + "loss": 3.8674, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.535510229218082e-06, + "loss": 3.8353, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.527124281707562e-06, + "loss": 3.8602, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.518738334197042e-06, + "loss": 3.8553, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.510368765490255e-06, + "loss": 3.8499, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.501982817979733e-06, + "loss": 3.8621, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.493596870469213e-06, + "loss": 3.8506, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.485210922958695e-06, + "loss": 3.8412, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.476824975448173e-06, + "loss": 3.8459, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.468439027937653e-06, + "loss": 3.8677, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.460069459230865e-06, + "loss": 3.8501, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.451683511720345e-06, + "loss": 3.8505, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.443297564209824e-06, + "loss": 3.841, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.434911616699305e-06, + "loss": 3.8475, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.426525669188785e-06, + "loss": 3.8619, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.418156100481996e-06, + "loss": 3.8666, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.409770152971476e-06, + "loss": 3.8482, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.401384205460956e-06, + "loss": 3.862, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.392998257950436e-06, + "loss": 3.8706, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.384628689243647e-06, + "loss": 3.8616, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.376242741733127e-06, + "loss": 3.847, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.367856794222606e-06, + "loss": 3.8586, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.359470846712086e-06, + "loss": 3.8576, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.351084899201566e-06, + "loss": 3.856, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.342715330494777e-06, + "loss": 3.8549, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.334329382984259e-06, + "loss": 3.8587, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.325943435473737e-06, + "loss": 3.868, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.317557487963217e-06, + "loss": 3.8634, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.309171540452697e-06, + "loss": 3.8421, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.30080197174591e-06, + "loss": 3.8524, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.292416024235388e-06, + "loss": 3.8569, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.28403007672487e-06, + "loss": 3.8561, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.27564412921435e-06, + "loss": 3.8573, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.26727456050756e-06, + "loss": 3.8554, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.25888861299704e-06, + "loss": 3.8523, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.25050266548652e-06, + "loss": 3.8445, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.242116717976e-06, + "loss": 3.8548, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.233730770465478e-06, + "loss": 3.8558, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.22534482295496e-06, + "loss": 3.8605, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.21695887544444e-06, + "loss": 3.8639, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.208572927933918e-06, + "loss": 3.8488, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.20020335922713e-06, + "loss": 3.856, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.19181741171661e-06, + "loss": 3.8571, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.183447843009823e-06, + "loss": 3.8563, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.175061895499301e-06, + "loss": 3.8624, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.166675947988781e-06, + "loss": 3.8467, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.158290000478261e-06, + "loss": 3.854, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.149904052967741e-06, + "loss": 3.8559, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.141518105457221e-06, + "loss": 3.8557, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.133132157946701e-06, + "loss": 3.847, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.124762589239914e-06, + "loss": 3.8496, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.116376641729392e-06, + "loss": 3.8561, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.107990694218872e-06, + "loss": 3.8546, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.099604746708352e-06, + "loss": 3.8511, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.091218799197832e-06, + "loss": 3.8485, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.082849230491043e-06, + "loss": 3.8458, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.074463282980524e-06, + "loss": 3.8668, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.066077335470004e-06, + "loss": 3.851, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.057691387959482e-06, + "loss": 3.8552, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.049321819252695e-06, + "loss": 3.8605, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.040935871742175e-06, + "loss": 3.8658, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.032549924231655e-06, + "loss": 3.8527, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.024163976721133e-06, + "loss": 3.8566, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.015778029210615e-06, + "loss": 3.8665, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.007392081700095e-06, + "loss": 3.8578, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 8.999006134189573e-06, + "loss": 3.8471, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.990620186679055e-06, + "loss": 3.8532, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.982234239168535e-06, + "loss": 3.8485, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.973864670461745e-06, + "loss": 3.8535, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.965478722951225e-06, + "loss": 3.8495, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.957109154244436e-06, + "loss": 3.8546, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.948723206733916e-06, + "loss": 3.8475, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.940337259223396e-06, + "loss": 3.8511, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.931951311712876e-06, + "loss": 3.8499, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.923581743006087e-06, + "loss": 3.8703, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.915195795495568e-06, + "loss": 3.8653, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.906809847985047e-06, + "loss": 3.85, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.898423900474527e-06, + "loss": 3.8521, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.890037952964007e-06, + "loss": 3.8556, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.881652005453486e-06, + "loss": 3.861, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.873266057942966e-06, + "loss": 3.859, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.864880110432446e-06, + "loss": 3.8549, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.856494162921928e-06, + "loss": 3.8621, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.848124594215137e-06, + "loss": 3.8572, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.839738646704617e-06, + "loss": 3.8562, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.831352699194099e-06, + "loss": 3.8525, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.822966751683577e-06, + "loss": 3.8612, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.81459718297679e-06, + "loss": 3.8533, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.80621123546627e-06, + "loss": 3.8432, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.79782528795575e-06, + "loss": 3.8611, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.789439340445228e-06, + "loss": 3.8569, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.78105339293471e-06, + "loss": 3.8661, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.77266744542419e-06, + "loss": 3.8483, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.7642978767174e-06, + "loss": 3.8526, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.9757845401763916, + "eval_runtime": 296.0111, + "eval_samples_per_second": 1289.111, + "eval_steps_per_second": 40.286, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.755928308010611e-06, + "loss": 3.8565, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.74754236050009e-06, + "loss": 3.8524, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.73915641298957e-06, + "loss": 3.8641, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.73077046547905e-06, + "loss": 3.8533, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.72238451796853e-06, + "loss": 3.8616, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.71399857045801e-06, + "loss": 3.8497, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.70561262294749e-06, + "loss": 3.8586, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.69722667543697e-06, + "loss": 3.8498, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.68884072792645e-06, + "loss": 3.861, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.680471159219663e-06, + "loss": 3.8572, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.672101590512874e-06, + "loss": 3.8663, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.663715643002352e-06, + "loss": 3.861, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.655329695491834e-06, + "loss": 3.8493, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.646943747981314e-06, + "loss": 3.8514, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.638557800470792e-06, + "loss": 3.8518, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.630171852960272e-06, + "loss": 3.849, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.621785905449754e-06, + "loss": 3.8538, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.613399957939232e-06, + "loss": 3.852, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.605014010428712e-06, + "loss": 3.853, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.596628062918192e-06, + "loss": 3.8716, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.588242115407672e-06, + "loss": 3.858, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.579872546700882e-06, + "loss": 3.8628, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.571486599190364e-06, + "loss": 3.8552, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.563100651679844e-06, + "loss": 3.867, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.554714704169322e-06, + "loss": 3.8422, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.546328756658802e-06, + "loss": 3.8597, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.537942809148284e-06, + "loss": 3.8486, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.529573240441495e-06, + "loss": 3.8531, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.521187292930975e-06, + "loss": 3.8492, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.512801345420455e-06, + "loss": 3.846, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.504415397909935e-06, + "loss": 3.8577, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.496029450399413e-06, + "loss": 3.8661, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.487643502888894e-06, + "loss": 3.8546, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.479257555378374e-06, + "loss": 3.8603, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.470904365475318e-06, + "loss": 3.851, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.462518417964796e-06, + "loss": 3.8566, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.454132470454276e-06, + "loss": 3.8488, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.445746522943756e-06, + "loss": 3.8597, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.437360575433236e-06, + "loss": 3.8432, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.428974627922716e-06, + "loss": 3.8499, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.420588680412196e-06, + "loss": 3.8515, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.412202732901676e-06, + "loss": 3.866, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.403816785391156e-06, + "loss": 3.844, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.395447216684366e-06, + "loss": 3.8567, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.387061269173848e-06, + "loss": 3.8564, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.378675321663326e-06, + "loss": 3.8512, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.370289374152806e-06, + "loss": 3.8609, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.361903426642286e-06, + "loss": 3.8364, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.353533857935499e-06, + "loss": 3.8505, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.345147910424977e-06, + "loss": 3.8616, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.336761962914457e-06, + "loss": 3.8561, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.328376015403939e-06, + "loss": 3.8479, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.319990067893417e-06, + "loss": 3.8476, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.311604120382897e-06, + "loss": 3.8511, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.303218172872377e-06, + "loss": 3.8412, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.294832225361858e-06, + "loss": 3.8592, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.286462656655068e-06, + "loss": 3.8362, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.27807670914455e-06, + "loss": 3.8533, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.26969076163403e-06, + "loss": 3.8536, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.261304814123507e-06, + "loss": 3.8494, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.25293524541672e-06, + "loss": 3.8588, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.2445492979062e-06, + "loss": 3.8507, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.23616335039568e-06, + "loss": 3.8373, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.22779378168889e-06, + "loss": 3.8384, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.21940783417837e-06, + "loss": 3.8676, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.21102188666785e-06, + "loss": 3.8486, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.20263593915733e-06, + "loss": 3.845, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.19424999164681e-06, + "loss": 3.8399, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.18586404413629e-06, + "loss": 3.8453, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.177494475429503e-06, + "loss": 3.8547, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.169108527918981e-06, + "loss": 3.8621, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.160722580408461e-06, + "loss": 3.8491, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.152336632897941e-06, + "loss": 3.8612, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.143950685387423e-06, + "loss": 3.8647, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.135564737876901e-06, + "loss": 3.8655, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.127178790366381e-06, + "loss": 3.8441, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.118792842855861e-06, + "loss": 3.8578, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.110423274149072e-06, + "loss": 3.8516, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.102053705442284e-06, + "loss": 3.8545, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.093684136735495e-06, + "loss": 3.8502, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.085330946832438e-06, + "loss": 3.8553, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.076944999321918e-06, + "loss": 3.8653, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.068559051811398e-06, + "loss": 3.8589, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.060173104300878e-06, + "loss": 3.8387, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.051787156790358e-06, + "loss": 3.8472, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.043401209279836e-06, + "loss": 3.8509, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.035015261769318e-06, + "loss": 3.8567, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.026629314258798e-06, + "loss": 3.8576, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.018243366748278e-06, + "loss": 3.8504, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.009857419237756e-06, + "loss": 3.8541, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.001471471727238e-06, + "loss": 3.8386, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.993085524216718e-06, + "loss": 3.8511, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.984699576706196e-06, + "loss": 3.8539, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.976330007999409e-06, + "loss": 3.855, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.967944060488888e-06, + "loss": 3.8618, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.959558112978367e-06, + "loss": 3.8493, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.951172165467847e-06, + "loss": 3.8524, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.942786217957328e-06, + "loss": 3.8548, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.934400270446808e-06, + "loss": 3.8553, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.926014322936287e-06, + "loss": 3.8533, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.917628375425768e-06, + "loss": 3.8486, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.909258806718979e-06, + "loss": 3.8502, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.900872859208457e-06, + "loss": 3.8544, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.892486911697939e-06, + "loss": 3.8566, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.884100964187419e-06, + "loss": 3.8391, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.875715016676899e-06, + "loss": 3.8507, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.86734544797011e-06, + "loss": 3.8563, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.85895950045959e-06, + "loss": 3.8516, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.85057355294907e-06, + "loss": 3.8464, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.84218760543855e-06, + "loss": 3.8452, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.83380165792803e-06, + "loss": 3.8415, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.82541571041751e-06, + "loss": 3.8641, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.81704614171072e-06, + "loss": 3.8486, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.8086601942002e-06, + "loss": 3.8538, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.80027424668968e-06, + "loss": 3.8532, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.79188829917916e-06, + "loss": 3.8671, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.78350235166864e-06, + "loss": 3.8497, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.77513278296185e-06, + "loss": 3.8556, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.76674683545133e-06, + "loss": 3.8615, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.758360887940812e-06, + "loss": 3.8552, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.749991319234022e-06, + "loss": 3.848, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.741605371723503e-06, + "loss": 3.8533, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.733219424212983e-06, + "loss": 3.8436, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.724833476702463e-06, + "loss": 3.8498, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.716447529191941e-06, + "loss": 3.8513, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.708061581681423e-06, + "loss": 3.8477, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.699675634170903e-06, + "loss": 3.8455, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.691289686660381e-06, + "loss": 3.8489, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.682903739149861e-06, + "loss": 3.8483, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.674517791639343e-06, + "loss": 3.8636, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.666131844128821e-06, + "loss": 3.8638, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.657745896618301e-06, + "loss": 3.8516, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.649376327911514e-06, + "loss": 3.8442, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.640990380400993e-06, + "loss": 3.857, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.632604432890472e-06, + "loss": 3.8562, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.624234864183684e-06, + "loss": 3.8565, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.615848916673164e-06, + "loss": 3.8505, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.607462969162644e-06, + "loss": 3.8602, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.599077021652123e-06, + "loss": 3.8523, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.590691074141604e-06, + "loss": 3.8536, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.582321505434816e-06, + "loss": 3.8519, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.573935557924294e-06, + "loss": 3.8541, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.565549610413775e-06, + "loss": 3.8509, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.557180041706986e-06, + "loss": 3.8442, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.548794094196466e-06, + "loss": 3.858, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.5404081466859454e-06, + "loss": 3.8556, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.532022199175426e-06, + "loss": 3.8619, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.523636251664906e-06, + "loss": 3.8473, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.515250304154385e-06, + "loss": 3.8496, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.9751107692718506, + "eval_runtime": 295.0268, + "eval_samples_per_second": 1293.411, + "eval_steps_per_second": 40.42, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.506864356643865e-06, + "loss": 3.8524, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.498478409133346e-06, + "loss": 3.8502, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.490092461622826e-06, + "loss": 3.8617, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.481706514112305e-06, + "loss": 3.8507, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.473320566601785e-06, + "loss": 3.8619, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.464934619091266e-06, + "loss": 3.846, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.456548671580744e-06, + "loss": 3.8539, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.448162724070225e-06, + "loss": 3.8466, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.439776776559705e-06, + "loss": 3.8602, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.431390829049184e-06, + "loss": 3.8517, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.423004881538664e-06, + "loss": 3.8614, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.414618934028145e-06, + "loss": 3.8575, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.406249365321356e-06, + "loss": 3.8427, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.3978634178108355e-06, + "loss": 3.8499, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.3894774703003155e-06, + "loss": 3.8499, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.381091522789796e-06, + "loss": 3.8499, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.3727055752792745e-06, + "loss": 3.8514, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.364319627768755e-06, + "loss": 3.8467, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.355950059061967e-06, + "loss": 3.8494, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.347564111551447e-06, + "loss": 3.8687, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.339178164040926e-06, + "loss": 3.8565, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.330792216530406e-06, + "loss": 3.8571, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.322406269019887e-06, + "loss": 3.8568, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.314020321509366e-06, + "loss": 3.8603, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.3056507528025776e-06, + "loss": 3.8404, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.2972648052920575e-06, + "loss": 3.8539, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.2888788577815375e-06, + "loss": 3.8507, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.2804929102710166e-06, + "loss": 3.8489, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.272106962760497e-06, + "loss": 3.8445, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.263721015249977e-06, + "loss": 3.8448, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.2553350677394564e-06, + "loss": 3.8539, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.246949120228936e-06, + "loss": 3.865, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.238579551522148e-06, + "loss": 3.8509, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.230193604011629e-06, + "loss": 3.8571, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.2218404141085705e-06, + "loss": 3.8504, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.21345446659805e-06, + "loss": 3.8508, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.205068519087531e-06, + "loss": 3.8441, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.196682571577011e-06, + "loss": 3.8613, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.18829662406649e-06, + "loss": 3.841, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.17991067655597e-06, + "loss": 3.8497, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.171524729045451e-06, + "loss": 3.8469, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.163138781534929e-06, + "loss": 3.8649, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.15475283402441e-06, + "loss": 3.8449, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.14636688651389e-06, + "loss": 3.8533, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.137980939003369e-06, + "loss": 3.854, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.129594991492849e-06, + "loss": 3.8496, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.12120904398233e-06, + "loss": 3.8553, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.1128394752755416e-06, + "loss": 3.8368, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.104453527765021e-06, + "loss": 3.8466, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.096067580254501e-06, + "loss": 3.8586, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.087681632743981e-06, + "loss": 3.8499, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.07929568523346e-06, + "loss": 3.8463, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.0709097377229405e-06, + "loss": 3.8454, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.0625237902124204e-06, + "loss": 3.8502, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.054137842701901e-06, + "loss": 3.8379, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.045768273995111e-06, + "loss": 3.8539, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.037398705288323e-06, + "loss": 3.8329, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.029012757777803e-06, + "loss": 3.8518, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.020626810267284e-06, + "loss": 3.8548, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.012240862756763e-06, + "loss": 3.8441, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.003871294049974e-06, + "loss": 3.8513, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.995485346539454e-06, + "loss": 3.854, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.987099399028933e-06, + "loss": 3.8313, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.978713451518413e-06, + "loss": 3.8415, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.970327504007894e-06, + "loss": 3.8558, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.961941556497374e-06, + "loss": 3.8522, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.953571987790584e-06, + "loss": 3.845, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.945186040280065e-06, + "loss": 3.8345, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.936800092769545e-06, + "loss": 3.8406, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.928414145259024e-06, + "loss": 3.8563, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.920028197748504e-06, + "loss": 3.8583, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.911642250237985e-06, + "loss": 3.8438, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.903256302727465e-06, + "loss": 3.8607, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.8948867340206754e-06, + "loss": 3.8599, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.886500786510155e-06, + "loss": 3.8661, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.878131217803367e-06, + "loss": 3.8337, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.869745270292848e-06, + "loss": 3.8589, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.861359322782326e-06, + "loss": 3.8485, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.852973375271807e-06, + "loss": 3.8483, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.844587427761287e-06, + "loss": 3.8517, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.836201480250766e-06, + "loss": 3.854, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.827815532740246e-06, + "loss": 3.8603, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.819429585229727e-06, + "loss": 3.8599, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.811043637719206e-06, + "loss": 3.8352, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.802657690208686e-06, + "loss": 3.8454, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.794271742698166e-06, + "loss": 3.8483, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.785902173991377e-06, + "loss": 3.8535, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.7775162264808565e-06, + "loss": 3.8562, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.769130278970337e-06, + "loss": 3.8458, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.760744331459817e-06, + "loss": 3.8524, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.752358383949296e-06, + "loss": 3.8385, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.743972436438776e-06, + "loss": 3.8492, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.735602867731988e-06, + "loss": 3.8498, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.727216920221469e-06, + "loss": 3.8509, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.718847351514679e-06, + "loss": 3.857, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.7104614040041595e-06, + "loss": 3.8527, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.7020754564936394e-06, + "loss": 3.8438, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6936895089831186e-06, + "loss": 3.8538, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.68531994027633e-06, + "loss": 3.8542, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.67693399276581e-06, + "loss": 3.8524, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.668548045255291e-06, + "loss": 3.8433, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.660162097744769e-06, + "loss": 3.8489, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.65177615023425e-06, + "loss": 3.8526, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.64339020272373e-06, + "loss": 3.8538, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.635004255213209e-06, + "loss": 3.8347, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.626618307702689e-06, + "loss": 3.8461, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.61823236019217e-06, + "loss": 3.8567, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.6098627914853815e-06, + "loss": 3.849, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.601476843974861e-06, + "loss": 3.8431, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.5930908964643405e-06, + "loss": 3.8467, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.584704948953821e-06, + "loss": 3.8414, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.576335380247033e-06, + "loss": 3.8588, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.567949432736511e-06, + "loss": 3.8424, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.559563485225992e-06, + "loss": 3.8539, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.551177537715472e-06, + "loss": 3.8527, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.542791590204951e-06, + "loss": 3.8603, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.534405642694431e-06, + "loss": 3.8462, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.526019695183912e-06, + "loss": 3.8551, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.517633747673391e-06, + "loss": 3.8602, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.509264178966603e-06, + "loss": 3.8523, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.500894610259814e-06, + "loss": 3.8428, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.492508662749294e-06, + "loss": 3.85, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.484122715238773e-06, + "loss": 3.8419, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.475736767728253e-06, + "loss": 3.8514, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.467350820217734e-06, + "loss": 3.8452, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.458981251510946e-06, + "loss": 3.849, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.450595304000424e-06, + "loss": 3.8394, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.442209356489905e-06, + "loss": 3.8453, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.433823408979385e-06, + "loss": 3.8432, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.425437461468864e-06, + "loss": 3.8627, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.417051513958345e-06, + "loss": 3.8603, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.408665566447825e-06, + "loss": 3.8537, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.400295997741036e-06, + "loss": 3.8408, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.391910050230515e-06, + "loss": 3.853, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.383524102719995e-06, + "loss": 3.8575, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.375154534013207e-06, + "loss": 3.8509, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.366768586502688e-06, + "loss": 3.8493, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.358382638992166e-06, + "loss": 3.8549, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.349996691481647e-06, + "loss": 3.8495, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.341610743971127e-06, + "loss": 3.8566, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.333224796460606e-06, + "loss": 3.8439, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.324838848950086e-06, + "loss": 3.8563, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.316452901439567e-06, + "loss": 3.8468, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.308083332732778e-06, + "loss": 3.8398, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.299697385222257e-06, + "loss": 3.8528, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.291311437711737e-06, + "loss": 3.8554, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.282925490201218e-06, + "loss": 3.8541, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.274539542690696e-06, + "loss": 3.8463, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.266153595180177e-06, + "loss": 3.8438, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.974538803100586, + "eval_runtime": 297.0747, + "eval_samples_per_second": 1284.495, + "eval_steps_per_second": 40.141, + "step": 2671200 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1039289673118435e+18, + "trial_name": null, + "trial_params": null +}