diff --git "a/checkpoint-915840/trainer_state.json" "b/checkpoint-915840/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-915840/trainer_state.json" @@ -0,0 +1,10849 @@ +{ + "best_metric": 4.048203468322754, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/4/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 915840, + "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 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 3.784899316497751e+17, + "trial_name": null, + "trial_params": null +}