diff --git "a/checkpoint-1373760/trainer_state.json" "b/checkpoint-1373760/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1373760/trainer_state.json" @@ -0,0 +1,16267 @@ +{ + "best_metric": 4.010195255279541, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/lstm/0/checkpoints/checkpoint-1373760", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1373760, + "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": 10.8204, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5528, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0599, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9953, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9468, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9288, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7821, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6636, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5615, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4842, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4163, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3404, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.2619, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.1988, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.1375, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987424354494966e-05, + "loss": 6.0821, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986585759743914e-05, + "loss": 6.0391, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985747164992862e-05, + "loss": 6.0008, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.98490857024181e-05, + "loss": 5.9575, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984069975490758e-05, + "loss": 5.9175, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.884, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8381, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.8192, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7822, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7643, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7258, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 5.6998, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.6753, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6586, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6354, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6124, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6026, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5661, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5599, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5416, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.525, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5098, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4703, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4769, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4427, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4463, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4259, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4284, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.3993, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.385, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3903, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3789, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3669, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959757279231743e-05, + "loss": 5.3498, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3288, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3392, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3211, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3209, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2901, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 5.2946, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2708, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.2937, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.256, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2591, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2445, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2331, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2339, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2226, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1971, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.2012, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2126, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1889, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1798, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1606, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1633, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1802, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1634, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1502, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1533, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1509, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.1326, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936284815604152e-05, + "loss": 5.1162, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1218, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1021, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1041, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.1089, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0958, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.0974, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0868, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0668, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0692, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0661, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0718, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0522, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0525, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0502, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0426, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0402, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0289, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.016, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0246, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 5.0119, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0061, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.9987, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9984, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 5.002, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9901, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9799, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9762, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9685, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9551, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9509, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.9552, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.9523, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.9392, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907784059230996e-05, + "loss": 4.9369, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906945464479944e-05, + "loss": 4.9364, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906106869728892e-05, + "loss": 4.9418, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905269912858213e-05, + "loss": 4.9357, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904431318107161e-05, + "loss": 4.9279, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903592723356109e-05, + "loss": 4.9264, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027541286050565e-05, + "loss": 4.9251, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019155338540045e-05, + "loss": 4.9128, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010769391029525e-05, + "loss": 4.9065, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002383443519005e-05, + "loss": 4.9114, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.91, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.8883, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.8903, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896885603228066e-05, + "loss": 4.8877, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896047008477014e-05, + "loss": 4.8764, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895208413725962e-05, + "loss": 4.88, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.89436981897491e-05, + "loss": 4.8853, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893531224223858e-05, + "loss": 4.8682, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892694267353179e-05, + "loss": 4.8702, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891855672602127e-05, + "loss": 4.8594, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891018715731448e-05, + "loss": 4.874, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890180120980396e-05, + "loss": 4.8653, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889341526229344e-05, + "loss": 4.856, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888502931478292e-05, + "loss": 4.8532, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766433672724e-05, + "loss": 4.8541, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886825741976188e-05, + "loss": 4.8524, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859871472251365e-05, + "loss": 4.8423, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851501903544574e-05, + "loss": 4.8403, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843115956034054e-05, + "loss": 4.8416, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8371, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8359, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.816, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.8273, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.8126, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879281664977466e-05, + "loss": 4.8023, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878443070226414e-05, + "loss": 4.8209, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877604475475362e-05, + "loss": 4.8096, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87676588072431e-05, + "loss": 4.8104, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875927285973258e-05, + "loss": 4.8118, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875088691222206e-05, + "loss": 4.7911, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.767621994018555, + "eval_runtime": 290.1884, + "eval_samples_per_second": 1314.977, + "eval_steps_per_second": 41.094, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874251734351528e-05, + "loss": 4.7945, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873413139600475e-05, + "loss": 4.7912, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872574544849423e-05, + "loss": 4.807, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871735950098371e-05, + "loss": 4.7866, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870897355347319e-05, + "loss": 4.7944, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870058760596267e-05, + "loss": 4.7739, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869220165845215e-05, + "loss": 4.78, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868381571094163e-05, + "loss": 4.7678, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867544614223484e-05, + "loss": 4.7741, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7741, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7761, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.7763, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8641918730996496e-05, + "loss": 4.7559, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633532783485976e-05, + "loss": 4.7565, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625146835975456e-05, + "loss": 4.7519, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616760888464936e-05, + "loss": 4.7441, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608391319758145e-05, + "loss": 4.7567, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600005372247625e-05, + "loss": 4.7417, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591619424737105e-05, + "loss": 4.7409, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583233477226585e-05, + "loss": 4.76, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574847529716065e-05, + "loss": 4.7387, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566461582205545e-05, + "loss": 4.7389, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7365, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854970606598824e-05, + "loss": 4.7422, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854132011847772e-05, + "loss": 4.7294, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.85329341709672e-05, + "loss": 4.7239, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852454822345668e-05, + "loss": 4.7181, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851616227594616e-05, + "loss": 4.7271, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850777632843564e-05, + "loss": 4.7098, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499390380925114e-05, + "loss": 4.7163, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849102081221833e-05, + "loss": 4.7166, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848263486470781e-05, + "loss": 4.7107, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847424891719729e-05, + "loss": 4.7168, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846586296968676e-05, + "loss": 4.7051, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845749340097998e-05, + "loss": 4.706, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844910745346946e-05, + "loss": 4.7077, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844072150595894e-05, + "loss": 4.6833, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843233555844842e-05, + "loss": 4.6945, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.84239496109379e-05, + "loss": 4.6777, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.6894, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840719409472059e-05, + "loss": 4.6893, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839880814721007e-05, + "loss": 4.6933, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839042219969955e-05, + "loss": 4.6832, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838203625218903e-05, + "loss": 4.6821, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.688, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365280735971716e-05, + "loss": 4.6818, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.6783, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348508840950676e-05, + "loss": 4.6702, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.658, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6753, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.6692, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831498142971233e-05, + "loss": 4.6684, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830659548220181e-05, + "loss": 4.6562, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.6629, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.82898399659845e-05, + "loss": 4.6472, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828145401847398e-05, + "loss": 4.6685, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827306807096346e-05, + "loss": 4.6491, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826468212345294e-05, + "loss": 4.6577, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6481, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.6395, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.643, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.82311547122146e-05, + "loss": 4.6481, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222768764704077e-05, + "loss": 4.6225, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214382817193557e-05, + "loss": 4.631, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6438, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197627300976246e-05, + "loss": 4.6309, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189241353465726e-05, + "loss": 4.6254, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180855405955206e-05, + "loss": 4.6214, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172469458444685e-05, + "loss": 4.6213, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164083510934165e-05, + "loss": 4.6422, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155697563423645e-05, + "loss": 4.6325, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147311615913125e-05, + "loss": 4.6245, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138942047206334e-05, + "loss": 4.6295, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6311, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.624, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.6068, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810541463596799e-05, + "loss": 4.6206, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809702868845747e-05, + "loss": 4.6111, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.6071, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6199, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.6081, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806351765602285e-05, + "loss": 4.6185, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805513170851233e-05, + "loss": 4.6115, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804674576100181e-05, + "loss": 4.5897, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803835981349129e-05, + "loss": 4.6042, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.5977, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.6109, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013218349763464e-05, + "loss": 4.5995, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.6026, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996446454742424e-05, + "loss": 4.6004, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.5972, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797969093852511e-05, + "loss": 4.5997, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797130499101459e-05, + "loss": 4.5926, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.5803, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.592, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946147148483026e-05, + "loss": 4.5898, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937761200972506e-05, + "loss": 4.5813, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929375253461986e-05, + "loss": 4.5877, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5848, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791260335844095e-05, + "loss": 4.5954, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790421741093043e-05, + "loss": 4.5799, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789584784222364e-05, + "loss": 4.5726, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788746189471312e-05, + "loss": 4.5754, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.78790759472026e-05, + "loss": 4.5731, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787068999969208e-05, + "loss": 4.5542, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5696, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785393448347477e-05, + "loss": 4.5659, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5667, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.5606, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782877664094321e-05, + "loss": 4.552, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782040707223642e-05, + "loss": 4.5597, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812021124725906e-05, + "loss": 4.5707, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803635177215386e-05, + "loss": 4.5639, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795249229704866e-05, + "loss": 4.5629, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786863282194346e-05, + "loss": 4.5598, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778493713487555e-05, + "loss": 4.57, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770107765977035e-05, + "loss": 4.5527, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761721818466515e-05, + "loss": 4.5498, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.556, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744949923445475e-05, + "loss": 4.558, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736563975934955e-05, + "loss": 4.5402, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.5427, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719808459717644e-05, + "loss": 4.5465, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711422512207124e-05, + "loss": 4.5389, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703036564696604e-05, + "loss": 4.5434, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694650617186084e-05, + "loss": 4.5513, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686264669675564e-05, + "loss": 4.5296, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7677878722165044e-05, + "loss": 4.5412, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766950915345826e-05, + "loss": 4.5298, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.553, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5437, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5327, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.5354, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5334, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5409, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5354, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760245433098156e-05, + "loss": 4.5315, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759406838347104e-05, + "loss": 4.5306, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5277, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5314, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5165, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5267, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5146, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5082, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.5279, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527013560994335e-05, + "loss": 4.5164, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518627613483815e-05, + "loss": 4.5186, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.522, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5068, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.4849019050598145, + "eval_runtime": 290.2875, + "eval_samples_per_second": 1314.528, + "eval_steps_per_second": 41.08, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749348614975599e-05, + "loss": 4.512, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748510020224547e-05, + "loss": 4.5032, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747671425473495e-05, + "loss": 4.5266, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746832830722443e-05, + "loss": 4.5037, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745994235971391e-05, + "loss": 4.5192, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745155641220339e-05, + "loss": 4.4993, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744317046469287e-05, + "loss": 4.5034, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743478451718235e-05, + "loss": 4.4941, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742639856967183e-05, + "loss": 4.5058, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741801262216131e-05, + "loss": 4.5045, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740962667465079e-05, + "loss": 4.5072, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401240727140264e-05, + "loss": 4.51, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.4916, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384485210922966e-05, + "loss": 4.4956, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376099263412446e-05, + "loss": 4.4894, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736771331590192e-05, + "loss": 4.4864, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.73593273683914e-05, + "loss": 4.4954, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735094142088088e-05, + "loss": 4.4873, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734255547337036e-05, + "loss": 4.4851, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733416952585984e-05, + "loss": 4.5013, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.4868, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.4878, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.4882, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.496, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4818, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.481, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.4774, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.4808, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258728755872624e-05, + "loss": 4.4706, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4764, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4777, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4733, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722523410224174e-05, + "loss": 4.4828, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721684815473121e-05, + "loss": 4.4691, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720846220722069e-05, + "loss": 4.4718, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720007625971017e-05, + "loss": 4.4725, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4557, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4602, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.453, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4609, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715814652215758e-05, + "loss": 4.4673, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4679, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4597, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4596, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124635489722956e-05, + "loss": 4.4684, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116265921016165e-05, + "loss": 4.4554, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107879973505645e-05, + "loss": 4.4599, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099494025995125e-05, + "loss": 4.4544, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091108078484605e-05, + "loss": 4.4383, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708272213097409e-05, + "loss": 4.4603, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074368941071037e-05, + "loss": 4.4497, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065982993560517e-05, + "loss": 4.4548, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705759704604999e-05, + "loss": 4.4455, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704921109853947e-05, + "loss": 4.4493, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704082515102895e-05, + "loss": 4.4338, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703243920351843e-05, + "loss": 4.4606, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702405325600791e-05, + "loss": 4.4365, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701566730849739e-05, + "loss": 4.454, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700728136098687e-05, + "loss": 4.4393, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699889541347635e-05, + "loss": 4.4394, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699050946596583e-05, + "loss": 4.4337, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698212351845531e-05, + "loss": 4.4453, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973753949748525e-05, + "loss": 4.4201, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965368002238005e-05, + "loss": 4.4314, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956982054727485e-05, + "loss": 4.4382, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948596107216965e-05, + "loss": 4.4328, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940210159706445e-05, + "loss": 4.427, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931824212195925e-05, + "loss": 4.4221, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.69234382646854e-05, + "loss": 4.4246, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691505231717488e-05, + "loss": 4.4484, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690666636966436e-05, + "loss": 4.4348, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689828042215384e-05, + "loss": 4.4281, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4386, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688152490593653e-05, + "loss": 4.437, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873138958426014e-05, + "loss": 4.4343, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686476938971923e-05, + "loss": 4.4141, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.68563834422087e-05, + "loss": 4.4297, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684799749469818e-05, + "loss": 4.4272, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683961154718766e-05, + "loss": 4.4155, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4334, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4216, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4278, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4284, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.4091, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789328619732e-05, + "loss": 4.4195, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678094267222148e-05, + "loss": 4.4133, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772573103514697e-05, + "loss": 4.4245, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764187156004177e-05, + "loss": 4.4239, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755801208493657e-05, + "loss": 4.4194, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747415260983136e-05, + "loss": 4.4216, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739029313472616e-05, + "loss": 4.4189, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730643365962096e-05, + "loss": 4.4178, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722257418451576e-05, + "loss": 4.4134, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713871470941056e-05, + "loss": 4.4108, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705485523430536e-05, + "loss": 4.4173, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697099575920016e-05, + "loss": 4.4087, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688713628409496e-05, + "loss": 4.4074, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.4124, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.412, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.4242, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.4048, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.4028, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.4049, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.4032, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.3829, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661327285842228e-05, + "loss": 4.3983, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660488691091176e-05, + "loss": 4.4001, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596500963401234e-05, + "loss": 4.3946, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.3991, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.3864, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.3897, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.4105, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.3964, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.4033, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.3954, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652942976212081e-05, + "loss": 4.4075, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652106019341402e-05, + "loss": 4.3941, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.65126742459035e-05, + "loss": 4.3905, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650428829839298e-05, + "loss": 4.3924, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649590235088246e-05, + "loss": 4.3992, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648751640337194e-05, + "loss": 4.3814, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647913045586142e-05, + "loss": 4.3834, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.64707445083509e-05, + "loss": 4.3836, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646235856084038e-05, + "loss": 4.3875, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645400537093732e-05, + "loss": 4.3869, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.64456194234268e-05, + "loss": 4.3944, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643723347591628e-05, + "loss": 4.3733, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642884752840576e-05, + "loss": 4.3841, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642046158089524e-05, + "loss": 4.3739, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3972, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3955, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639532011716741e-05, + "loss": 4.3816, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638693416965689e-05, + "loss": 4.3792, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637854822214637e-05, + "loss": 4.384, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.387, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.3882, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.3775, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634502081090802e-05, + "loss": 4.382, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633663486339751e-05, + "loss": 4.3793, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632824891588699e-05, + "loss": 4.3847, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.37, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3758, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303123830962886e-05, + "loss": 4.373, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294754262256095e-05, + "loss": 4.3587, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286368314745575e-05, + "loss": 4.3835, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277982367235055e-05, + "loss": 4.3712, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269596419724535e-05, + "loss": 4.3743, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261210472214015e-05, + "loss": 4.3772, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252824524703495e-05, + "loss": 4.3624, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.348172187805176, + "eval_runtime": 292.808, + "eval_samples_per_second": 1303.212, + "eval_steps_per_second": 40.726, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244438577192975e-05, + "loss": 4.3703, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623605262968246e-05, + "loss": 4.3573, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622766668217194e-05, + "loss": 4.381, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621928073466142e-05, + "loss": 4.3621, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210894787150895e-05, + "loss": 4.385, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202508839640374e-05, + "loss": 4.3544, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194122892129854e-05, + "loss": 4.3642, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618575332342307e-05, + "loss": 4.3501, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617738375471628e-05, + "loss": 4.3698, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616899780720576e-05, + "loss": 4.3658, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616061185969524e-05, + "loss": 4.3638, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615222591218472e-05, + "loss": 4.3785, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.61438399646742e-05, + "loss": 4.3537, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613545401716368e-05, + "loss": 4.3603, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612706806965316e-05, + "loss": 4.3519, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611868212214264e-05, + "loss": 4.3515, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611029617463212e-05, + "loss": 4.3574, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.61019102271216e-05, + "loss": 4.3537, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609352427961108e-05, + "loss": 4.3518, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608513833210056e-05, + "loss": 4.3656, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607675238459004e-05, + "loss": 4.3567, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606838281588325e-05, + "loss": 4.3539, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605999686837273e-05, + "loss": 4.3568, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605162729966594e-05, + "loss": 4.3611, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604324135215542e-05, + "loss": 4.3499, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.60348554046449e-05, + "loss": 4.3498, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602646945713438e-05, + "loss": 4.3476, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018083509623864e-05, + "loss": 4.3439, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600971394091707e-05, + "loss": 4.344, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600132799340655e-05, + "loss": 4.344, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599294204589603e-05, + "loss": 4.3529, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598455609838551e-05, + "loss": 4.3454, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597620290848245e-05, + "loss": 4.3552, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596781696097193e-05, + "loss": 4.345, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595943101346141e-05, + "loss": 4.3411, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595104506595089e-05, + "loss": 4.3437, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.59426754972441e-05, + "loss": 4.3324, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934289549733587e-05, + "loss": 4.3331, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925903602223066e-05, + "loss": 4.3292, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917517654712546e-05, + "loss": 4.3337, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909131707202026e-05, + "loss": 4.3428, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900745759691506e-05, + "loss": 4.3414, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892359812180986e-05, + "loss": 4.3383, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883973864670466e-05, + "loss": 4.3372, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875587917159946e-05, + "loss": 4.3471, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867201969649426e-05, + "loss": 4.3328, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858816022138906e-05, + "loss": 4.3364, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585043007462838e-05, + "loss": 4.3305, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842060505921595e-05, + "loss": 4.3194, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833690937214804e-05, + "loss": 4.3428, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825304989704284e-05, + "loss": 4.3274, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581691904219377e-05, + "loss": 4.3336, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580853309468325e-05, + "loss": 4.3233, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580014714717273e-05, + "loss": 4.3356, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791761199662204e-05, + "loss": 4.3133, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783375252151684e-05, + "loss": 4.3396, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774989304641164e-05, + "loss": 4.3221, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766603357130644e-05, + "loss": 4.3324, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758217409620124e-05, + "loss": 4.3271, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3187, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574146189340281e-05, + "loss": 4.3162, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573307594589229e-05, + "loss": 4.3332, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572468999838177e-05, + "loss": 4.3071, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571632042967499e-05, + "loss": 4.3105, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570793448216447e-05, + "loss": 4.3248, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569954853465395e-05, + "loss": 4.3216, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569116258714343e-05, + "loss": 4.31, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568277663963291e-05, + "loss": 4.3123, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567440707092612e-05, + "loss": 4.3092, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566603750221933e-05, + "loss": 4.3314, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565765155470881e-05, + "loss": 4.3194, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564926560719829e-05, + "loss": 4.3157, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5640879659687767e-05, + "loss": 4.3213, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632493712177247e-05, + "loss": 4.3278, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562412414347046e-05, + "loss": 4.3237, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561573819595994e-05, + "loss": 4.3026, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.317, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55989663009389e-05, + "loss": 4.3144, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559058035342838e-05, + "loss": 4.304, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558219440591786e-05, + "loss": 4.3256, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557380845840734e-05, + "loss": 4.3085, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3188, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555705294219003e-05, + "loss": 4.3196, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554866699467951e-05, + "loss": 4.3036, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.3092, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3067, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552350915214795e-05, + "loss": 4.3124, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551512320463743e-05, + "loss": 4.3136, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550673725712691e-05, + "loss": 4.3088, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549835130961639e-05, + "loss": 4.3141, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548996536210587e-05, + "loss": 4.3151, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548159579339909e-05, + "loss": 4.3099, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547320984588857e-05, + "loss": 4.3079, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546482389837804e-05, + "loss": 4.3028, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456454329671256e-05, + "loss": 4.3142, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448068382160736e-05, + "loss": 4.3041, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439682434650216e-05, + "loss": 4.3039, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543129648713969e-05, + "loss": 4.3073, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542291053962917e-05, + "loss": 4.3039, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541452459211865e-05, + "loss": 4.3185, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540613864460813e-05, + "loss": 4.3013, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539775269709761e-05, + "loss": 4.3008, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389383128390824e-05, + "loss": 4.3003, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380997180880304e-05, + "loss": 4.3026, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372611233369784e-05, + "loss": 4.2815, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364225285859264e-05, + "loss": 4.2937, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355839338348744e-05, + "loss": 4.2999, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347469769641953e-05, + "loss": 4.2955, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533908382213143e-05, + "loss": 4.2933, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533069787462091e-05, + "loss": 4.2881, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532231192711039e-05, + "loss": 4.2883, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.53139423584036e-05, + "loss": 4.3117, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530555641089308e-05, + "loss": 4.2918, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529717046338256e-05, + "loss": 4.3012, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528878451587205e-05, + "loss": 4.2962, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528039856836153e-05, + "loss": 4.3097, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527202899965474e-05, + "loss": 4.296, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526364305214422e-05, + "loss": 4.2864, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.52552571046337e-05, + "loss": 4.295, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524687115712318e-05, + "loss": 4.2992, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2825, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2851, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2909, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213360124688556e-05, + "loss": 4.2909, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.2862, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196588229667516e-05, + "loss": 4.3016, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.275, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517981633464648e-05, + "loss": 4.2884, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517143038713596e-05, + "loss": 4.2766, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516304443962544e-05, + "loss": 4.3003, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515465849211492e-05, + "loss": 4.2992, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.51462725446044e-05, + "loss": 4.288, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2815, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.2904, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512113108087657e-05, + "loss": 4.2911, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112745133366045e-05, + "loss": 4.2903, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104359185855525e-05, + "loss": 4.2862, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095973238345005e-05, + "loss": 4.2841, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087587290834485e-05, + "loss": 4.2871, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507920134332397e-05, + "loss": 4.2949, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507083177461718e-05, + "loss": 4.2769, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506244582710666e-05, + "loss": 4.2787, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505405987959614e-05, + "loss": 4.2796, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504569031088935e-05, + "loss": 4.2711, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503730436337883e-05, + "loss": 4.2881, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502891841586831e-05, + "loss": 4.2782, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502053246835779e-05, + "loss": 4.2825, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501214652084727e-05, + "loss": 4.2815, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500376057333675e-05, + "loss": 4.2756, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.265038013458252, + "eval_runtime": 299.0876, + "eval_samples_per_second": 1275.85, + "eval_steps_per_second": 39.871, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499537462582623e-05, + "loss": 4.2807, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498698867831571e-05, + "loss": 4.2656, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497860273080519e-05, + "loss": 4.2887, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497021678329467e-05, + "loss": 4.2716, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496183083578415e-05, + "loss": 4.2926, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953444888273636e-05, + "loss": 4.2721, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945058940763116e-05, + "loss": 4.2698, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493667299325259e-05, + "loss": 4.2625, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492828704574207e-05, + "loss": 4.2757, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491990109823155e-05, + "loss": 4.2815, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491151515072103e-05, + "loss": 4.2762, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490312920321051e-05, + "loss": 4.284, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489474325569999e-05, + "loss": 4.267, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488635730818947e-05, + "loss": 4.2709, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487797136067895e-05, + "loss": 4.2646, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2591, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2731, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485282989695112e-05, + "loss": 4.2695, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844443949440604e-05, + "loss": 4.2643, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836058001930084e-05, + "loss": 4.277, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827672054419564e-05, + "loss": 4.2714, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819286106909044e-05, + "loss": 4.2709, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4810900159398524e-05, + "loss": 4.267, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802514211888004e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479414464318121e-05, + "loss": 4.2607, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478575869567069e-05, + "loss": 4.2688, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477737274816017e-05, + "loss": 4.2563, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476900317945338e-05, + "loss": 4.2611, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476061723194286e-05, + "loss": 4.2596, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475223128443234e-05, + "loss": 4.2597, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474384533692182e-05, + "loss": 4.2651, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47354593894113e-05, + "loss": 4.2646, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472707344190078e-05, + "loss": 4.2668, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471868749439026e-05, + "loss": 4.2611, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471031792568348e-05, + "loss": 4.2558, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470193197817295e-05, + "loss": 4.2621, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469354603066243e-05, + "loss": 4.2529, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468516008315191e-05, + "loss": 4.2465, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467677413564139e-05, + "loss": 4.248, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466838818813087e-05, + "loss": 4.2482, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.26, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2627, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2554, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4634860776892526e-05, + "loss": 4.2514, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626491208185736e-05, + "loss": 4.2667, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618105260675215e-05, + "loss": 4.2555, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609735691968425e-05, + "loss": 4.2543, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601349744457905e-05, + "loss": 4.249, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592963796947384e-05, + "loss": 4.2368, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584594228240594e-05, + "loss": 4.2618, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576208280730074e-05, + "loss": 4.2466, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567822333219554e-05, + "loss": 4.2554, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559436385709033e-05, + "loss": 4.2466, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551050438198513e-05, + "loss": 4.2464, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454266449068799e-05, + "loss": 4.2399, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453427854317748e-05, + "loss": 4.2515, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452589259566696e-05, + "loss": 4.2448, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451752302696017e-05, + "loss": 4.256, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450913707944965e-05, + "loss": 4.2466, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450075113193913e-05, + "loss": 4.2403, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449236518442861e-05, + "loss": 4.2374, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448397923691809e-05, + "loss": 4.2547, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447559328940757e-05, + "loss": 4.2311, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446720734189705e-05, + "loss": 4.2327, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445882139438653e-05, + "loss": 4.2433, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.2464, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.2336, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44336799306587e-05, + "loss": 4.233, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442529398314818e-05, + "loss": 4.2308, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441690803563766e-05, + "loss": 4.2496, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2454, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2418, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2446, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383380624399314e-05, + "loss": 4.2468, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437499467688879e-05, + "loss": 4.2514, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436660872937827e-05, + "loss": 4.2284, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358222781867747e-05, + "loss": 4.2354, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2399, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2257, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333081318139916e-05, + "loss": 4.2526, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324695370629396e-05, + "loss": 4.2335, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431630942311888e-05, + "loss": 4.2438, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430792347560836e-05, + "loss": 4.2499, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2272, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429116795939105e-05, + "loss": 4.2341, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428278201188053e-05, + "loss": 4.2326, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427441244317374e-05, + "loss": 4.2364, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426602649566322e-05, + "loss": 4.2391, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42576405481527e-05, + "loss": 4.2367, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.239, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424086865313166e-05, + "loss": 4.2411, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.2323, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2368, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157108106001e-05, + "loss": 4.2315, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.241, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198955294382796e-05, + "loss": 4.2323, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190569346872276e-05, + "loss": 4.2286, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182183399361756e-05, + "loss": 4.2341, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173797451851236e-05, + "loss": 4.2327, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165411504340716e-05, + "loss": 4.2495, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157041935633925e-05, + "loss": 4.2302, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148655988123405e-05, + "loss": 4.2276, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140270040612885e-05, + "loss": 4.2261, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131884093102365e-05, + "loss": 4.2332, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123498145591845e-05, + "loss": 4.2096, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115128576885054e-05, + "loss": 4.2196, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106742629374534e-05, + "loss": 4.2276, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409835668186402e-05, + "loss": 4.2281, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.40899707343535e-05, + "loss": 4.224, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081584786842974e-05, + "loss": 4.2157, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073198839332453e-05, + "loss": 4.2188, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064812891821933e-05, + "loss": 4.2373, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.227, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404804099680089e-05, + "loss": 4.229, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40396714280941e-05, + "loss": 4.2288, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403128548058358e-05, + "loss": 4.2373, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402291591187679e-05, + "loss": 4.2304, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401452996436627e-05, + "loss": 4.2168, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400614401685576e-05, + "loss": 4.222, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399775806934524e-05, + "loss": 4.2303, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398937212183472e-05, + "loss": 4.2145, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398100255312793e-05, + "loss": 4.2178, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397261660561741e-05, + "loss": 4.2196, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396423065810689e-05, + "loss": 4.2221, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3955861089400096e-05, + "loss": 4.2185, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947475141889576e-05, + "loss": 4.2324, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939089194379056e-05, + "loss": 4.2043, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930703246868536e-05, + "loss": 4.2213, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922317299358016e-05, + "loss": 4.2081, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913931351847496e-05, + "loss": 4.2352, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905545404336976e-05, + "loss": 4.2227, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897159456826456e-05, + "loss": 4.2263, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388878988811967e-05, + "loss": 4.208, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388040394060915e-05, + "loss": 4.2236, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387201799309863e-05, + "loss": 4.2299, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386363204558811e-05, + "loss": 4.2199, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385524609807759e-05, + "loss": 4.2175, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.2253, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383849058186028e-05, + "loss": 4.2174, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383010463434976e-05, + "loss": 4.2276, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382171868683924e-05, + "loss": 4.2074, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381333273932872e-05, + "loss": 4.2163, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.38049467918182e-05, + "loss": 4.2116, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379656084430768e-05, + "loss": 4.2059, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378817489679716e-05, + "loss": 4.219, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2138, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771435759383585e-05, + "loss": 4.2172, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763049811873065e-05, + "loss": 4.2145, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754663864362545e-05, + "loss": 4.2135, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.207745552062988, + "eval_runtime": 294.4896, + "eval_samples_per_second": 1295.771, + "eval_steps_per_second": 40.494, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746277916852025e-05, + "loss": 4.2103, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737891969341505e-05, + "loss": 4.1977, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372950602183098e-05, + "loss": 4.2239, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721136453124194e-05, + "loss": 4.2086, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712750505613674e-05, + "loss": 4.2243, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704364558103154e-05, + "loss": 4.2088, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369597861059263e-05, + "loss": 4.2021, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368760904188584e-05, + "loss": 4.1992, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367922309437533e-05, + "loss": 4.2088, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367083714686481e-05, + "loss": 4.218, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366245119935428e-05, + "loss": 4.2108, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365406525184376e-05, + "loss": 4.2215, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364567930433324e-05, + "loss": 4.2045, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363729335682272e-05, + "loss": 4.2102, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362892378811593e-05, + "loss": 4.2034, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362053784060541e-05, + "loss": 4.1941, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361215189309489e-05, + "loss": 4.2073, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360376594558437e-05, + "loss": 4.204, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359537999807385e-05, + "loss": 4.2013, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358699405056333e-05, + "loss": 4.2119, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357860810305281e-05, + "loss": 4.2131, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357025491314976e-05, + "loss": 4.2072, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356186896563924e-05, + "loss": 4.2042, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355348301812872e-05, + "loss": 4.2092, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.35450970706182e-05, + "loss": 4.1988, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536711123107677e-05, + "loss": 4.2069, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528325175597157e-05, + "loss": 4.1967, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519939228086636e-05, + "loss": 4.1992, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511553280576116e-05, + "loss": 4.2004, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503167333065596e-05, + "loss": 4.1952, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494781385555076e-05, + "loss": 4.2015, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486395438044556e-05, + "loss": 4.2042, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478009490534036e-05, + "loss": 4.2051, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469623543023516e-05, + "loss": 4.1983, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461237595512996e-05, + "loss": 4.193, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345286802680621e-05, + "loss": 4.2058, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344448207929569e-05, + "loss": 4.1929, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436096131785165e-05, + "loss": 4.1809, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427710184274645e-05, + "loss": 4.1902, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419324236764125e-05, + "loss": 4.1875, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341095466805734e-05, + "loss": 4.1958, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402568720546814e-05, + "loss": 4.2049, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394182773036294e-05, + "loss": 4.1934, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385796825525774e-05, + "loss": 4.1964, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377410878015254e-05, + "loss": 4.2028, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369024930504734e-05, + "loss": 4.1917, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360638982994214e-05, + "loss": 4.1974, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.33522530354837e-05, + "loss": 4.1896, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334388346677691e-05, + "loss": 4.1727, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333549751926639e-05, + "loss": 4.2048, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327144329363335e-05, + "loss": 4.1874, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318758381852815e-05, + "loss": 4.1986, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331037243434229e-05, + "loss": 4.1877, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330198648683177e-05, + "loss": 4.1853, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329360053932125e-05, + "loss": 4.1843, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328521459181073e-05, + "loss": 4.1893, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327682864430021e-05, + "loss": 4.1909, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326844269678969e-05, + "loss": 4.1981, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326005674927917e-05, + "loss": 4.1886, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3251670801768654e-05, + "loss": 4.1879, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243284854258134e-05, + "loss": 4.1728, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234898906747614e-05, + "loss": 4.1983, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322652933804082e-05, + "loss": 4.1733, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321815976933403e-05, + "loss": 4.1731, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320977382182351e-05, + "loss": 4.1859, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320140425311672e-05, + "loss": 4.191, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.31930183056062e-05, + "loss": 4.1721, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318463235809568e-05, + "loss": 4.1798, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317624641058516e-05, + "loss": 4.1675, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316786046307464e-05, + "loss": 4.1949, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315947451556412e-05, + "loss": 4.1854, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315108856805361e-05, + "loss": 4.1869, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314270262054309e-05, + "loss": 4.1845, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313431667303257e-05, + "loss": 4.1885, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312594710432578e-05, + "loss": 4.197, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311756115681526e-05, + "loss": 4.1704, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310917520930474e-05, + "loss": 4.1847, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310078926179422e-05, + "loss": 4.1841, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30924033142837e-05, + "loss": 4.1698, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308401736677318e-05, + "loss": 4.1911, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307563141926265e-05, + "loss": 4.1836, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306724547175213e-05, + "loss": 4.1862, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305885952424161e-05, + "loss": 4.1943, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050489955534826e-05, + "loss": 4.1732, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304212038682804e-05, + "loss": 4.1794, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303373443931752e-05, + "loss": 4.1739, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025348491807e-05, + "loss": 4.1808, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016962544296475e-05, + "loss": 4.1844, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300859297558969e-05, + "loss": 4.1832, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300020702807917e-05, + "loss": 4.1809, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299182108056865e-05, + "loss": 4.1873, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983435133058124e-05, + "loss": 4.1779, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297506556435134e-05, + "loss": 4.1797, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296667961684082e-05, + "loss": 4.1799, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295831004813403e-05, + "loss": 4.1836, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949924100623515e-05, + "loss": 4.1822, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941538153112995e-05, + "loss": 4.1694, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933152205602475e-05, + "loss": 4.1807, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292476625809195e-05, + "loss": 4.1802, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291638031058143e-05, + "loss": 4.1898, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908010741874644e-05, + "loss": 4.1781, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2899624794364124e-05, + "loss": 4.174, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.28912388468536e-05, + "loss": 4.1699, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288285289934308e-05, + "loss": 4.1859, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287446695183256e-05, + "loss": 4.1551, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866097383125766e-05, + "loss": 4.1709, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285771143561525e-05, + "loss": 4.1734, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284932548810473e-05, + "loss": 4.1717, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284093954059421e-05, + "loss": 4.1704, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283255359308369e-05, + "loss": 4.1644, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282416764557317e-05, + "loss": 4.1688, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281578169806265e-05, + "loss": 4.182, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280739575055213e-05, + "loss": 4.1773, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279900980304161e-05, + "loss": 4.17, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279062385553109e-05, + "loss": 4.1791, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278223790802057e-05, + "loss": 4.1844, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277386833931378e-05, + "loss": 4.1774, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276548239180326e-05, + "loss": 4.1657, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275709644429274e-05, + "loss": 4.1707, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274871049678222e-05, + "loss": 4.1763, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27403245492717e-05, + "loss": 4.1607, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273197135936865e-05, + "loss": 4.1642, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2723585411858127e-05, + "loss": 4.1686, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715199464347607e-05, + "loss": 4.1678, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2706813516837087e-05, + "loss": 4.168, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698427569326566e-05, + "loss": 4.1776, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690058000619776e-05, + "loss": 4.1567, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681672053109256e-05, + "loss": 4.1682, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673286105598735e-05, + "loss": 4.161, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664900158088215e-05, + "loss": 4.1797, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656514210577695e-05, + "loss": 4.1727, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648128263067175e-05, + "loss": 4.1728, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639742315556655e-05, + "loss": 4.1614, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631356368046135e-05, + "loss": 4.173, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262298679933935e-05, + "loss": 4.1781, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261460085182883e-05, + "loss": 4.1689, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260621490431831e-05, + "loss": 4.169, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597828956807784e-05, + "loss": 4.1723, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589443009297264e-05, + "loss": 4.1651, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581057061786744e-05, + "loss": 4.1773, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572671114276224e-05, + "loss": 4.158, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564285166765704e-05, + "loss": 4.1678, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255591559805891e-05, + "loss": 4.1558, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254752965054839e-05, + "loss": 4.1592, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253914370303787e-05, + "loss": 4.1718, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253075775552735e-05, + "loss": 4.1575, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252238818682057e-05, + "loss": 4.1752, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251400223931005e-05, + "loss": 4.1569, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250561629179953e-05, + "loss": 4.1691, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.166093826293945, + "eval_runtime": 293.7891, + "eval_samples_per_second": 1298.86, + "eval_steps_per_second": 40.59, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249724672309274e-05, + "loss": 4.1743, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248886077558222e-05, + "loss": 4.1463, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.24804748280717e-05, + "loss": 4.1708, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247208888056118e-05, + "loss": 4.1633, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246370293305066e-05, + "loss": 4.1734, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245531698554014e-05, + "loss": 4.1611, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244693103802962e-05, + "loss": 4.1503, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24385450905191e-05, + "loss": 4.1538, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243015914300858e-05, + "loss": 4.16, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242177319549806e-05, + "loss": 4.166, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241338724798754e-05, + "loss": 4.1632, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405001300477024e-05, + "loss": 4.1707, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239663173177023e-05, + "loss": 4.1587, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238824578425971e-05, + "loss": 4.1606, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237985983674919e-05, + "loss": 4.154, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237147388923867e-05, + "loss": 4.142, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363087941728146e-05, + "loss": 4.1623, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2354701994217626e-05, + "loss": 4.1543, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346316046707106e-05, + "loss": 4.1536, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337930099196586e-05, + "loss": 4.1637, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329560530489795e-05, + "loss": 4.1672, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321174582979275e-05, + "loss": 4.1593, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231278863546876e-05, + "loss": 4.1556, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230440268795824e-05, + "loss": 4.1608, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229603311925145e-05, + "loss": 4.1558, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228764717174093e-05, + "loss": 4.1563, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227926122423041e-05, + "loss": 4.1486, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227087527671989e-05, + "loss": 4.1545, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226248932920937e-05, + "loss": 4.1551, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225410338169885e-05, + "loss": 4.1503, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224571743418833e-05, + "loss": 4.1526, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223733148667781e-05, + "loss": 4.1566, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222894553916729e-05, + "loss": 4.158, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222055959165677e-05, + "loss": 4.1543, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221217364414625e-05, + "loss": 4.1463, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220380407543946e-05, + "loss": 4.1568, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219541812792894e-05, + "loss": 4.1513, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187032180418426e-05, + "loss": 4.1369, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178646232907906e-05, + "loss": 4.141, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170260285397386e-05, + "loss": 4.1409, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216187433788686e-05, + "loss": 4.1471, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153504769180075e-05, + "loss": 4.1569, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145118821669555e-05, + "loss": 4.1471, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136732874159035e-05, + "loss": 4.1537, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212834692664851e-05, + "loss": 4.1572, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119977357941724e-05, + "loss": 4.1449, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211160778923493e-05, + "loss": 4.1499, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210323822052815e-05, + "loss": 4.148, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209485227301763e-05, + "loss": 4.1208, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208646632550711e-05, + "loss": 4.1632, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207808037799659e-05, + "loss": 4.1399, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206969443048607e-05, + "loss": 4.1587, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206130848297555e-05, + "loss": 4.1371, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205292253546503e-05, + "loss": 4.1436, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204453658795451e-05, + "loss": 4.1382, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203615064044398e-05, + "loss": 4.1419, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202776469293346e-05, + "loss": 4.1453, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201937874542294e-05, + "loss": 4.1534, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201099279791242e-05, + "loss": 4.149, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.20026068504019e-05, + "loss": 4.1361, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199422090289138e-05, + "loss": 4.1283, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198583495538086e-05, + "loss": 4.1592, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197744900787035e-05, + "loss": 4.1255, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196906306035983e-05, + "loss": 4.1255, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196067711284931e-05, + "loss": 4.1427, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195230754414252e-05, + "loss": 4.1519, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943921596632e-05, + "loss": 4.1246, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193553564912148e-05, + "loss": 4.1361, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192714970161096e-05, + "loss": 4.1254, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918780132904167e-05, + "loss": 4.1488, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910394185393647e-05, + "loss": 4.1431, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902008237883126e-05, + "loss": 4.1429, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893622290372606e-05, + "loss": 4.1361, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885236342862086e-05, + "loss": 4.1445, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768667741553e-05, + "loss": 4.1559, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186848082664478e-05, + "loss": 4.1238, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186011125793799e-05, + "loss": 4.1406, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185172531042747e-05, + "loss": 4.1419, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184333936291695e-05, + "loss": 4.1258, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183495341540643e-05, + "loss": 4.1449, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182658384669964e-05, + "loss": 4.1446, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181821427799285e-05, + "loss": 4.1435, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180984470928606e-05, + "loss": 4.1516, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180145876177554e-05, + "loss": 4.129, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793072814265025e-05, + "loss": 4.1358, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784686866754505e-05, + "loss": 4.1318, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776300919243985e-05, + "loss": 4.1383, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767914971733465e-05, + "loss": 4.1395, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759529024222945e-05, + "loss": 4.1452, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751143076712425e-05, + "loss": 4.1309, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1742757129201905e-05, + "loss": 4.1488, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734371181691385e-05, + "loss": 4.1372, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1725985234180865e-05, + "loss": 4.1363, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171759928667034e-05, + "loss": 4.1377, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170921333915982e-05, + "loss": 4.1397, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.17008273916493e-05, + "loss": 4.1432, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1692457822942514e-05, + "loss": 4.1263, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168407187543199e-05, + "loss": 4.1372, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1675685927921474e-05, + "loss": 4.1401, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667299980410954e-05, + "loss": 4.1439, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658914032900434e-05, + "loss": 4.1403, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650528085389914e-05, + "loss": 4.1316, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164215851668312e-05, + "loss": 4.1315, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16337725691726e-05, + "loss": 4.1411, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162538662166208e-05, + "loss": 4.1126, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161700067415156e-05, + "loss": 4.1279, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160863110544477e-05, + "loss": 4.129, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160024515793425e-05, + "loss": 4.1321, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159185921042373e-05, + "loss": 4.1265, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158347326291321e-05, + "loss": 4.1288, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157510369420643e-05, + "loss": 4.1263, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156671774669591e-05, + "loss": 4.14, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155833179918539e-05, + "loss": 4.1379, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154994585167487e-05, + "loss": 4.1265, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154155990416435e-05, + "loss": 4.1396, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153317395665383e-05, + "loss": 4.1442, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152478800914331e-05, + "loss": 4.1396, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151640206163279e-05, + "loss": 4.1229, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508032492925996e-05, + "loss": 4.1294, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499662924219205e-05, + "loss": 4.1351, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491276976708685e-05, + "loss": 4.1185, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482891029198165e-05, + "loss": 4.1241, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474505081687645e-05, + "loss": 4.1293, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466119134177125e-05, + "loss": 4.1258, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145773318666661e-05, + "loss": 4.1304, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144934723915609e-05, + "loss": 4.1371, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144096129164557e-05, + "loss": 4.1206, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143257534413505e-05, + "loss": 4.125, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142420577542826e-05, + "loss": 4.1265, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141581982791774e-05, + "loss": 4.1363, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140743388040722e-05, + "loss": 4.132, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13990479328967e-05, + "loss": 4.1346, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390661985386174e-05, + "loss": 4.1202, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382276037875654e-05, + "loss": 4.1325, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137390646916887e-05, + "loss": 4.1379, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136552052165835e-05, + "loss": 4.1287, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135713457414783e-05, + "loss": 4.1302, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134874862663731e-05, + "loss": 4.1308, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340379057930525e-05, + "loss": 4.1262, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1331993110420005e-05, + "loss": 4.1393, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132360716290948e-05, + "loss": 4.1202, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131522121539896e-05, + "loss": 4.1258, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130683526788844e-05, + "loss": 4.1187, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1182, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12900633728674e-05, + "loss": 4.1279, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128167742535688e-05, + "loss": 4.1223, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1346, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649382879433e-05, + "loss": 4.1201, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125655234043278e-05, + "loss": 4.1315, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.134369373321533, + "eval_runtime": 303.3556, + "eval_samples_per_second": 1257.9, + "eval_steps_per_second": 39.31, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124816639292226e-05, + "loss": 4.1188, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123978044541174e-05, + "loss": 4.1095, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123139449790122e-05, + "loss": 4.1314, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230085503907e-05, + "loss": 4.1214, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121463898168391e-05, + "loss": 4.1316, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120625303417339e-05, + "loss": 4.1241, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119786708666287e-05, + "loss": 4.1151, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118948113915235e-05, + "loss": 4.1165, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118109519164183e-05, + "loss": 4.123, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117270924413131e-05, + "loss": 4.1266, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116433967542452e-05, + "loss": 4.1234, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155953727914e-05, + "loss": 4.1319, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114758415920722e-05, + "loss": 4.1225, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.11391982116967e-05, + "loss": 4.1225, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113081226418618e-05, + "loss": 4.1154, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112242631667566e-05, + "loss": 4.1065, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114056747968866e-05, + "loss": 4.1231, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1105670800458346e-05, + "loss": 4.1185, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097284852947826e-05, + "loss": 4.1163, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1088898905437306e-05, + "loss": 4.1178, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080512957926786e-05, + "loss": 4.1346, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072127010416266e-05, + "loss": 4.1221, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063741062905746e-05, + "loss": 4.1174, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055355115395225e-05, + "loss": 4.1192, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1046969167884705e-05, + "loss": 4.1193, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038583220374185e-05, + "loss": 4.119, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.1124, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102182770415688e-05, + "loss": 4.1179, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101345813545009e-05, + "loss": 4.1135, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100507218793957e-05, + "loss": 4.1097, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099668624042905e-05, + "loss": 4.1136, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098830029291853e-05, + "loss": 4.121, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097991434540801e-05, + "loss": 4.1217, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097152839789748e-05, + "loss": 4.1194, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096314245038696e-05, + "loss": 4.1095, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095475650287644e-05, + "loss": 4.1152, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094637055536592e-05, + "loss": 4.1132, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093800098665914e-05, + "loss": 4.1042, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092961503914862e-05, + "loss": 4.1038, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.09212290916381e-05, + "loss": 4.1038, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091284314412758e-05, + "loss": 4.1107, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090445719661706e-05, + "loss": 4.1157, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089607124910654e-05, + "loss": 4.1095, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088770168039975e-05, + "loss": 4.1194, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087933211169296e-05, + "loss": 4.1173, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087094616418244e-05, + "loss": 4.1096, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086256021667192e-05, + "loss": 4.1151, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08541742691614e-05, + "loss": 4.1108, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084578832165088e-05, + "loss": 4.0878, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083740237414036e-05, + "loss": 4.1222, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829016426629844e-05, + "loss": 4.1031, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820630479119323e-05, + "loss": 4.1225, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1056, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1052, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079548901539149e-05, + "loss": 4.1006, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078710306788097e-05, + "loss": 4.1044, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077873349917418e-05, + "loss": 4.1132, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077034755166366e-05, + "loss": 4.1122, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076196160415314e-05, + "loss": 4.1139, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075357565664262e-05, + "loss": 4.1047, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07451897091321e-05, + "loss": 4.0917, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073682014042531e-05, + "loss": 4.1218, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.07284341929148e-05, + "loss": 4.0935, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072004824540428e-05, + "loss": 4.0856, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071166229789376e-05, + "loss": 4.1069, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070327635038324e-05, + "loss": 4.1141, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069489040287272e-05, + "loss": 4.0929, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1013, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678134886655406e-05, + "loss": 4.0892, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0669748939144886e-05, + "loss": 4.1108, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661362991634366e-05, + "loss": 4.1097, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652977044123846e-05, + "loss": 4.1049, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1034, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636221527906535e-05, + "loss": 4.1092, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627835580396015e-05, + "loss": 4.1185, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619449632885495e-05, + "loss": 4.09, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061108006417871e-05, + "loss": 4.1073, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060269411666819e-05, + "loss": 4.1024, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059430816915767e-05, + "loss": 4.097, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585922221647144e-05, + "loss": 4.1078, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577536274136624e-05, + "loss": 4.1118, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569150326626104e-05, + "loss": 4.105, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560764379115584e-05, + "loss": 4.1197, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552378431605064e-05, + "loss": 4.0925, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543992484094544e-05, + "loss": 4.0992, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535606536584024e-05, + "loss": 4.0982, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527220589073504e-05, + "loss": 4.1062, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518834641562984e-05, + "loss": 4.1025, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.05104650728562e-05, + "loss": 4.1109, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050207912534568e-05, + "loss": 4.0961, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049369317783516e-05, + "loss": 4.1153, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048532360912837e-05, + "loss": 4.1065, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047693766161785e-05, + "loss": 4.0993, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046855171410733e-05, + "loss": 4.102, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.1074, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045177981908629e-05, + "loss": 4.1102, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044339387157577e-05, + "loss": 4.0949, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043500792406525e-05, + "loss": 4.1006, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042662197655473e-05, + "loss": 4.1033, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.112, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1073, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.04014805128269e-05, + "loss": 4.0948, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039311094412011e-05, + "loss": 4.0986, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038472499660959e-05, + "loss": 4.1074, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037633904909907e-05, + "loss": 4.0773, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.0951, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035958353288176e-05, + "loss": 4.095, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035119758537124e-05, + "loss": 4.1009, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034281163786072e-05, + "loss": 4.0894, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.03344256903502e-05, + "loss": 4.0975, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032603974283968e-05, + "loss": 4.0971, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317653795329155e-05, + "loss": 4.1019, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309267847818635e-05, + "loss": 4.1019, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030088190030812e-05, + "loss": 4.0956, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029251233160133e-05, + "loss": 4.1052, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028412638409081e-05, + "loss": 4.113, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027574043658029e-05, + "loss": 4.1053, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026735448906977e-05, + "loss": 4.0907, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025896854155925e-05, + "loss": 4.0972, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025058259404873e-05, + "loss": 4.1034, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024221302534194e-05, + "loss": 4.0839, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233859835438885e-05, + "loss": 4.0921, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225473887928365e-05, + "loss": 4.0978, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217087940417845e-05, + "loss": 4.0927, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208701992907324e-05, + "loss": 4.0942, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200316045396804e-05, + "loss": 4.1036, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191930097886284e-05, + "loss": 4.0888, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183544150375764e-05, + "loss": 4.0932, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175158202865244e-05, + "loss": 4.0898, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166772255354724e-05, + "loss": 4.1072, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015840268664793e-05, + "loss": 4.097, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015001673913741e-05, + "loss": 4.1044, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014163079162689e-05, + "loss": 4.0871, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013324484411637e-05, + "loss": 4.1008, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012487527540958e-05, + "loss": 4.105, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011648932789906e-05, + "loss": 4.0974, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010810338038854e-05, + "loss": 4.0972, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009971743287803e-05, + "loss": 4.0956, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009134786417124e-05, + "loss": 4.0955, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008296191666072e-05, + "loss": 4.1062, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.00745759691502e-05, + "loss": 4.0893, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006619002163968e-05, + "loss": 4.0955, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005780407412916e-05, + "loss": 4.0905, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004943450542237e-05, + "loss": 4.086, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004104855791185e-05, + "loss": 4.0884, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003266261040133e-05, + "loss": 4.0915, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002427666289081e-05, + "loss": 4.1042, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001589071538029e-05, + "loss": 4.0878, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007521146673496e-05, + "loss": 4.0983, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.110284805297852, + "eval_runtime": 303.7838, + "eval_samples_per_second": 1256.127, + "eval_steps_per_second": 39.255, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999913519916298e-05, + "loss": 4.0962, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999074925165246e-05, + "loss": 4.0792, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998236330414194e-05, + "loss": 4.0989, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997397735663142e-05, + "loss": 4.0924, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.99655914091209e-05, + "loss": 4.0993, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995720546161038e-05, + "loss": 4.09, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994881951409986e-05, + "loss": 4.0889, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994043356658934e-05, + "loss": 4.081, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932047619078815e-05, + "loss": 4.0888, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9923661671568295e-05, + "loss": 4.0976, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915275724057775e-05, + "loss": 4.0906, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906889776547255e-05, + "loss": 4.0989, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898520207840464e-05, + "loss": 4.1007, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890134260329944e-05, + "loss": 4.0823, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988174831281943e-05, + "loss": 4.0819, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987336236530891e-05, + "loss": 4.0802, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986497641779839e-05, + "loss": 4.0899, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985659047028787e-05, + "loss": 4.0882, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984820452277735e-05, + "loss": 4.0836, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983983495407056e-05, + "loss": 4.0896, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983144900656004e-05, + "loss": 4.1004, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982306305904952e-05, + "loss": 4.0926, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814677111539e-05, + "loss": 4.0906, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980629116402848e-05, + "loss": 4.0854, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979790521651796e-05, + "loss": 4.0891, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978953564781117e-05, + "loss": 4.0886, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978114970030065e-05, + "loss": 4.0781, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977276375279013e-05, + "loss": 4.094, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764377805279616e-05, + "loss": 4.082, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755991857769096e-05, + "loss": 4.0762, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747605910258575e-05, + "loss": 4.0857, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739219962748055e-05, + "loss": 4.0838, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973083401523753e-05, + "loss": 4.0898, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972244806772701e-05, + "loss": 4.0908, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714078499020224e-05, + "loss": 4.08, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705692551509704e-05, + "loss": 4.0828, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969730660399918e-05, + "loss": 4.0883, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968892065648866e-05, + "loss": 4.068, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968053470897814e-05, + "loss": 4.0765, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967214876146762e-05, + "loss": 4.0741, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.96637628139571e-05, + "loss": 4.0768, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655376866446584e-05, + "loss": 4.084, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964700729773979e-05, + "loss": 4.0815, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963862135022927e-05, + "loss": 4.0925, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963023540271875e-05, + "loss": 4.0812, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962186583401196e-05, + "loss": 4.0816, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961349626530518e-05, + "loss": 4.0828, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960511031779465e-05, + "loss": 4.0825, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959672437028413e-05, + "loss": 4.0569, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958833842277361e-05, + "loss": 4.0918, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957995247526309e-05, + "loss": 4.0755, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957156652775257e-05, + "loss": 4.0907, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956318058024205e-05, + "loss": 4.0749, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955479463273154e-05, + "loss": 4.0784, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954640868522102e-05, + "loss": 4.0683, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.95380227377105e-05, + "loss": 4.0752, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952963679019998e-05, + "loss": 4.0861, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952125084268946e-05, + "loss": 4.076, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951286489517894e-05, + "loss": 4.0836, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950449532647215e-05, + "loss": 4.0796, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949610937896163e-05, + "loss": 4.057, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9487723431451107e-05, + "loss": 4.0916, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479337483940587e-05, + "loss": 4.0673, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9470967915233796e-05, + "loss": 4.0583, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462581967723276e-05, + "loss": 4.0805, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454196020212756e-05, + "loss": 4.0787, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944582645150597e-05, + "loss": 4.0625, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943745688279918e-05, + "loss": 4.0714, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942907093528866e-05, + "loss": 4.0642, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942068498777814e-05, + "loss": 4.0773, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941229904026762e-05, + "loss": 4.0798, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.94039130927571e-05, + "loss": 4.0743, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939552714524658e-05, + "loss": 4.0764, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938714119773606e-05, + "loss": 4.0777, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378755250225533e-05, + "loss": 4.0886, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937036930271501e-05, + "loss": 4.0624, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936198335520449e-05, + "loss": 4.0747, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935359740769397e-05, + "loss": 4.0726, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934521146018345e-05, + "loss": 4.0685, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933684189147667e-05, + "loss": 4.0788, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932845594396615e-05, + "loss": 4.0808, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932006999645563e-05, + "loss": 4.0788, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931168404894511e-05, + "loss": 4.0911, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930329810143459e-05, + "loss": 4.0627, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.92949285327278e-05, + "loss": 4.0703, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928654258521728e-05, + "loss": 4.0687, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927815663770676e-05, + "loss": 4.0754, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926977069019624e-05, + "loss": 4.0715, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926141750029318e-05, + "loss": 4.0815, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925303155278266e-05, + "loss": 4.071, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924464560527214e-05, + "loss": 4.0827, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923625965776162e-05, + "loss": 4.0752, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92278737102511e-05, + "loss": 4.0708, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921948776274058e-05, + "loss": 4.0757, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921111819403379e-05, + "loss": 4.0763, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920273224652327e-05, + "loss": 4.0817, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919434629901275e-05, + "loss": 4.0676, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918596035150223e-05, + "loss": 4.0681, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917757440399171e-05, + "loss": 4.0779, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916920483528492e-05, + "loss": 4.0832, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608188877744e-05, + "loss": 4.076, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915243294026388e-05, + "loss": 4.0739, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914404699275336e-05, + "loss": 4.0703, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913566104524285e-05, + "loss": 4.0767, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912727509773233e-05, + "loss": 4.0514, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911888915022181e-05, + "loss": 4.0694, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110519581515016e-05, + "loss": 4.0558, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102133634004496e-05, + "loss": 4.0732, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9093747686493976e-05, + "loss": 4.0626, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085361738983456e-05, + "loss": 4.0733, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9076975791472936e-05, + "loss": 4.0653, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068589843962416e-05, + "loss": 4.0738, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060220275255625e-05, + "loss": 4.0736, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051834327745105e-05, + "loss": 4.0685, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043448380234585e-05, + "loss": 4.0766, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035062432724065e-05, + "loss": 4.0791, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026676485213545e-05, + "loss": 4.077, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018290537703025e-05, + "loss": 4.0686, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900992096899624e-05, + "loss": 4.0641, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900153502148572e-05, + "loss": 4.0743, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.89931490739752e-05, + "loss": 4.0618, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898477950526841e-05, + "loss": 4.0616, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897639355775789e-05, + "loss": 4.065, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896800761024737e-05, + "loss": 4.0656, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895962166273684e-05, + "loss": 4.064, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895123571522632e-05, + "loss": 4.0769, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.89428497677158e-05, + "loss": 4.0637, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893446382020528e-05, + "loss": 4.0666, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.89260942514985e-05, + "loss": 4.0611, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891770830398798e-05, + "loss": 4.0771, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890932235647746e-05, + "loss": 4.0723, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890093640896694e-05, + "loss": 4.069, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889255046145642e-05, + "loss": 4.0603, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88841645139459e-05, + "loss": 4.0746, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887577856643538e-05, + "loss": 4.0784, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886739261892486e-05, + "loss": 4.0709, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885902305021807e-05, + "loss": 4.071, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885063710270755e-05, + "loss": 4.0629, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884225115519703e-05, + "loss": 4.0692, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883386520768651e-05, + "loss": 4.0796, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882547926017599e-05, + "loss": 4.0609, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881709331266547e-05, + "loss": 4.0662, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880870736515495e-05, + "loss": 4.0646, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800321417644434e-05, + "loss": 4.0602, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879196822774137e-05, + "loss": 4.0601, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878358228023085e-05, + "loss": 4.0649, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877519633272033e-05, + "loss": 4.0746, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876681038520981e-05, + "loss": 4.0655, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875842443769929e-05, + "loss": 4.0679, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.09051513671875, + "eval_runtime": 293.8662, + "eval_samples_per_second": 1298.52, + "eval_steps_per_second": 40.58, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875003849018877e-05, + "loss": 4.0553, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874165254267825e-05, + "loss": 4.0538, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873326659516773e-05, + "loss": 4.0703, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724880647657205e-05, + "loss": 4.0623, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871651107895042e-05, + "loss": 4.0756, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.87081251314399e-05, + "loss": 4.0604, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869975556273312e-05, + "loss": 4.0625, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86913696152226e-05, + "loss": 4.0522, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868298366771208e-05, + "loss": 4.0627, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674597720201557e-05, + "loss": 4.0701, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866621177269103e-05, + "loss": 4.0633, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8657842203984246e-05, + "loss": 4.0719, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649472635277455e-05, + "loss": 4.0766, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641086687766935e-05, + "loss": 4.0526, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632700740256415e-05, + "loss": 4.0561, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624314792745895e-05, + "loss": 4.0516, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615928845235375e-05, + "loss": 4.0663, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607542897724855e-05, + "loss": 4.0542, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599156950214334e-05, + "loss": 4.0585, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590771002703814e-05, + "loss": 4.0627, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582385055193294e-05, + "loss": 4.0717, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573999107682774e-05, + "loss": 4.0679, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565613160172254e-05, + "loss": 4.0624, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557243591465463e-05, + "loss": 4.062, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854885764395494e-05, + "loss": 4.0613, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854047169644442e-05, + "loss": 4.0644, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85320857489339e-05, + "loss": 4.0453, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852369980142338e-05, + "loss": 4.0671, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851531385391286e-05, + "loss": 4.0559, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850694428520608e-05, + "loss": 4.0504, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849855833769556e-05, + "loss": 4.0618, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849017239018504e-05, + "loss": 4.0592, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848180282147825e-05, + "loss": 4.0585, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847341687396773e-05, + "loss": 4.0671, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846503092645721e-05, + "loss": 4.0507, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845664497894669e-05, + "loss": 4.058, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844825903143617e-05, + "loss": 4.0603, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843988946272938e-05, + "loss": 4.0393, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843150351521886e-05, + "loss": 4.0517, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842311756770834e-05, + "loss": 4.0514, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841473162019782e-05, + "loss": 4.0498, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84063456726873e-05, + "loss": 4.0603, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839795972517678e-05, + "loss": 4.0517, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838957377766626e-05, + "loss": 4.0658, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381187830155743e-05, + "loss": 4.0555, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372801882645223e-05, + "loss": 4.0592, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836443231393843e-05, + "loss": 4.0552, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835604636642791e-05, + "loss": 4.0564, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834766041891739e-05, + "loss": 4.0345, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339274471406866e-05, + "loss": 4.0609, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8330888523896346e-05, + "loss": 4.0491, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322502576385826e-05, + "loss": 4.0651, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314116628875305e-05, + "loss": 4.0476, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305730681364785e-05, + "loss": 4.0497, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297344733854265e-05, + "loss": 4.0446, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8288958786343745e-05, + "loss": 4.0499, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828058921763696e-05, + "loss": 4.0599, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827221964893017e-05, + "loss": 4.0488, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826383370141965e-05, + "loss": 4.0646, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825544775390913e-05, + "loss": 4.0537, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824706180639861e-05, + "loss": 4.0274, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823867585888809e-05, + "loss": 4.0663, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.82303062901813e-05, + "loss": 4.0397, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822192034267078e-05, + "loss": 4.0363, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821353439516026e-05, + "loss": 4.0524, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820514844764974e-05, + "loss": 4.0555, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819676250013922e-05, + "loss": 4.0397, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.81883765526287e-05, + "loss": 4.0447, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.817999060511818e-05, + "loss": 4.0357, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171621036411395e-05, + "loss": 4.054, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163235088900875e-05, + "loss": 4.057, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154849141390355e-05, + "loss": 4.0457, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146463193879835e-05, + "loss": 4.0543, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138093625173044e-05, + "loss": 4.0509, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129707677662524e-05, + "loss": 4.0628, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8121321730152004e-05, + "loss": 4.0391, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8112935782641484e-05, + "loss": 4.0489, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8104549835130964e-05, + "loss": 4.0471, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096163887620444e-05, + "loss": 4.0462, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808779431891365e-05, + "loss": 4.0512, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807940837140313e-05, + "loss": 4.0511, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807102242389262e-05, + "loss": 4.0581, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80626364763821e-05, + "loss": 4.0625, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805426690767531e-05, + "loss": 4.0439, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804588096016479e-05, + "loss": 4.0432, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803749501265427e-05, + "loss": 4.0428, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802910906514375e-05, + "loss": 4.0517, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802072311763323e-05, + "loss": 4.0469, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.80123371701227e-05, + "loss": 4.0511, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800395122261218e-05, + "loss": 4.0536, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799556527510166e-05, + "loss": 4.0536, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798719570639488e-05, + "loss": 4.0521, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797880975888436e-05, + "loss": 4.0447, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797042381137384e-05, + "loss": 4.0508, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796203786386332e-05, + "loss": 4.0552, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79536519163528e-05, + "loss": 4.0547, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945282347646006e-05, + "loss": 4.0395, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7936896400135486e-05, + "loss": 4.0489, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928510452624966e-05, + "loss": 4.0506, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920140883918175e-05, + "loss": 4.0588, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7911754936407655e-05, + "loss": 4.0527, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790338536770087e-05, + "loss": 4.0499, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789499942019035e-05, + "loss": 4.0474, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886613472679824e-05, + "loss": 4.0494, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787822752516931e-05, + "loss": 4.0308, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786984157765879e-05, + "loss": 4.0414, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861472008952e-05, + "loss": 4.0327, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785308606144148e-05, + "loss": 4.0494, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784470011393096e-05, + "loss": 4.0414, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783631416642044e-05, + "loss": 4.0461, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782792821890992e-05, + "loss": 4.0431, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.78195422713994e-05, + "loss": 4.0474, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781115632388888e-05, + "loss": 4.0527, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780277037637836e-05, + "loss": 4.0441, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779440080767157e-05, + "loss": 4.0517, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778601486016105e-05, + "loss": 4.056, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777762891265053e-05, + "loss": 4.05, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776924296514001e-05, + "loss": 4.0487, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776085701762949e-05, + "loss": 4.0384, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7752471070118975e-05, + "loss": 4.0469, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744085122608455e-05, + "loss": 4.0452, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7735715553901664e-05, + "loss": 4.0311, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727329606391144e-05, + "loss": 4.0412, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7718943658880624e-05, + "loss": 4.0416, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7710557711370104e-05, + "loss": 4.0443, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702171763859584e-05, + "loss": 4.05, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7693785816349064e-05, + "loss": 4.04, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768541624764227e-05, + "loss": 4.0407, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767703030013175e-05, + "loss": 4.0389, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766864435262123e-05, + "loss": 4.0544, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766025840511071e-05, + "loss": 4.0459, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765187245760019e-05, + "loss": 4.0507, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764350288889341e-05, + "loss": 4.0307, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763511694138289e-05, + "loss": 4.056, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762673099387236e-05, + "loss": 4.0525, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761834504636184e-05, + "loss": 4.0477, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760995909885132e-05, + "loss": 4.0459, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.76015731513408e-05, + "loss": 4.0408, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759320358263401e-05, + "loss": 4.0428, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758481763512349e-05, + "loss": 4.0626, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757643168761297e-05, + "loss": 4.0332, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756804574010245e-05, + "loss": 4.0457, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755965979259193e-05, + "loss": 4.0424, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755129022388515e-05, + "loss": 4.0322, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542904276374627e-05, + "loss": 4.0389, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534518328864107e-05, + "loss": 4.042, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526132381353586e-05, + "loss": 4.0486, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517746433843066e-05, + "loss": 4.0422, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509360486332546e-05, + "loss": 4.043, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.074568271636963, + "eval_runtime": 293.2426, + "eval_samples_per_second": 1301.281, + "eval_steps_per_second": 40.666, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7500974538822026e-05, + "loss": 4.0445, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492588591311506e-05, + "loss": 4.0328, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484202643800986e-05, + "loss": 4.0465, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.0423, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0514, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0414, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0372, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744227290624838e-05, + "loss": 4.0319, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433886958737866e-05, + "loss": 4.036, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425501011227346e-05, + "loss": 4.0472, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417115063716826e-05, + "loss": 4.0435, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408729116206306e-05, + "loss": 4.0501, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400359547499515e-05, + "loss": 4.051, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7391973599988995e-05, + "loss": 4.0315, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383587652478475e-05, + "loss": 4.0305, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375201704967955e-05, + "loss": 4.0296, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7366815757457435e-05, + "loss": 4.0464, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358429809946915e-05, + "loss": 4.0356, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350043862436395e-05, + "loss": 4.0337, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341657914925875e-05, + "loss": 4.0372, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0503, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324886019904835e-05, + "loss": 4.0398, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316516451198044e-05, + "loss": 4.0439, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730813050368753e-05, + "loss": 4.0371, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729974455617701e-05, + "loss": 4.0422, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729135860866649e-05, + "loss": 4.0398, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282972661155963e-05, + "loss": 4.0233, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274586713645443e-05, + "loss": 4.0441, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726620076613492e-05, + "loss": 4.0328, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.72578148186244e-05, + "loss": 4.0254, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724944524991761e-05, + "loss": 4.0438, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724105930240709e-05, + "loss": 4.0351, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723267335489657e-05, + "loss": 4.035, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722428740738605e-05, + "loss": 4.0463, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721591783867927e-05, + "loss": 4.0287, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720753189116875e-05, + "loss": 4.0389, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719914594365823e-05, + "loss": 4.0371, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719075999614771e-05, + "loss": 4.0154, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718239042744092e-05, + "loss": 4.03, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.71740044799304e-05, + "loss": 4.0265, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716561853241988e-05, + "loss": 4.0278, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715723258490936e-05, + "loss": 4.0391, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714884663739884e-05, + "loss": 4.0327, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714046068988832e-05, + "loss": 4.0415, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.71320747423778e-05, + "loss": 4.035, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712368879486728e-05, + "loss": 4.0346, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115319226160486e-05, + "loss": 4.0321, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71069496574537e-05, + "loss": 4.0334, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709856370994318e-05, + "loss": 4.0115, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709017776243266e-05, + "loss": 4.038, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708179181492214e-05, + "loss": 4.0282, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707340586741162e-05, + "loss": 4.0442, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.70650199199011e-05, + "loss": 4.0279, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705663397239058e-05, + "loss": 4.0237, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704824802488006e-05, + "loss": 4.026, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703986207736954e-05, + "loss": 4.0264, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703149250866275e-05, + "loss": 4.0368, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702312293995596e-05, + "loss": 4.0244, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701473699244544e-05, + "loss": 4.0437, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700635104493492e-05, + "loss": 4.0346, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997965097424406e-05, + "loss": 4.0033, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989579149913886e-05, + "loss": 4.0452, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981193202403366e-05, + "loss": 4.0195, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972807254892846e-05, + "loss": 4.015, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964421307382326e-05, + "loss": 4.0262, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956051738675535e-05, + "loss": 4.0356, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947665791165015e-05, + "loss": 4.019, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939279843654495e-05, + "loss": 4.0236, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6930893896143975e-05, + "loss": 4.016, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6922524327437184e-05, + "loss": 4.0265, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691415475873039e-05, + "loss": 4.039, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690576881121987e-05, + "loss": 4.024, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689738286370936e-05, + "loss": 4.0324, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688899691619884e-05, + "loss": 4.0271, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688061096868832e-05, + "loss": 4.0383, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68722250211778e-05, + "loss": 4.02, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686383907366727e-05, + "loss": 4.0317, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685545312615675e-05, + "loss": 4.0221, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684708355744997e-05, + "loss": 4.024, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683869760993945e-05, + "loss": 4.0325, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683031166242892e-05, + "loss": 4.0277, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68219257149184e-05, + "loss": 4.0335, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681355614621162e-05, + "loss": 4.0441, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.68051701987011e-05, + "loss": 4.0276, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679678425119058e-05, + "loss": 4.0193, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678839830368006e-05, + "loss": 4.0194, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678001235616954e-05, + "loss": 4.0322, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677162640865902e-05, + "loss": 4.0236, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676325683995223e-05, + "loss": 4.0334, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675487089244171e-05, + "loss": 4.0338, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746484944931187e-05, + "loss": 4.0307, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738098997420667e-05, + "loss": 4.0289, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729729428713876e-05, + "loss": 4.0226, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721343481203356e-05, + "loss": 4.0327, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712957533692836e-05, + "loss": 4.0287, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704571586182315e-05, + "loss": 4.034, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6696185638671795e-05, + "loss": 4.0223, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6687799691161275e-05, + "loss": 4.0238, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667941374365076e-05, + "loss": 4.031, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667102779614024e-05, + "loss": 4.0382, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666265822743345e-05, + "loss": 4.0339, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665427227992293e-05, + "loss": 4.0263, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664588633241241e-05, + "loss": 4.0281, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663751676370562e-05, + "loss": 4.0253, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66291308161951e-05, + "loss": 4.0146, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662074486868458e-05, + "loss": 4.0165, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661235892117406e-05, + "loss": 4.0129, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660398935246727e-05, + "loss": 4.0309, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659560340495675e-05, + "loss": 4.0217, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658721745744623e-05, + "loss": 4.0249, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578831509935716e-05, + "loss": 4.0188, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570445562425196e-05, + "loss": 4.0312, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562075993718405e-05, + "loss": 4.0286, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553690046207885e-05, + "loss": 4.0245, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545304098697365e-05, + "loss": 4.0326, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6536918151186845e-05, + "loss": 4.0343, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6528532203676325e-05, + "loss": 4.0312, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6520162634969534e-05, + "loss": 4.0248, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6511776687459014e-05, + "loss": 4.0167, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6503390739948494e-05, + "loss": 4.0263, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64950211712417e-05, + "loss": 4.0262, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648663522373118e-05, + "loss": 4.0054, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647824927622067e-05, + "loss": 4.026, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646986332871015e-05, + "loss": 4.0218, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646147738119963e-05, + "loss": 4.0219, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645309143368911e-05, + "loss": 4.0302, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644470548617858e-05, + "loss": 4.019, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64363359174718e-05, + "loss": 4.0205, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642794996996128e-05, + "loss": 4.0127, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641956402245075e-05, + "loss": 4.0374, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641117807494023e-05, + "loss": 4.0243, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640279212742971e-05, + "loss": 4.0305, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639440617991919e-05, + "loss": 4.0134, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638602023240867e-05, + "loss": 4.0308, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637763428489815e-05, + "loss": 4.0307, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636924833738764e-05, + "loss": 4.0287, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636086238987712e-05, + "loss": 4.0264, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63524764423666e-05, + "loss": 4.0176, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634410687365981e-05, + "loss": 4.0258, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633572092614929e-05, + "loss": 4.0408, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632733497863877e-05, + "loss": 4.0147, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631894903112825e-05, + "loss": 4.0226, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631056308361773e-05, + "loss": 4.0195, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630217713610721e-05, + "loss": 4.0203, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293807567400416e-05, + "loss": 4.0158, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6285421619889896e-05, + "loss": 4.0216, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277035672379376e-05, + "loss": 4.0258, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268649724868856e-05, + "loss": 4.0301, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260263777358336e-05, + "loss": 4.02, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.0614471435546875, + "eval_runtime": 294.3808, + "eval_samples_per_second": 1296.25, + "eval_steps_per_second": 40.509, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251877829847816e-05, + "loss": 4.0097, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243491882337296e-05, + "loss": 4.0119, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6235105934826776e-05, + "loss": 4.0259, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622673636611999e-05, + "loss": 4.0241, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621835041860947e-05, + "loss": 4.0309, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6209964471098945e-05, + "loss": 4.0227, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620159490239216e-05, + "loss": 4.0188, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619322533368537e-05, + "loss": 4.0123, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618483938617485e-05, + "loss": 4.0146, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617645343866433e-05, + "loss": 4.0188, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616806749115381e-05, + "loss": 4.0282, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615968154364329e-05, + "loss": 4.0307, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151311974936505e-05, + "loss": 4.0368, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142926027425985e-05, + "loss": 4.0065, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134540079915465e-05, + "loss": 4.0182, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126154132404945e-05, + "loss": 4.0034, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611776818489442e-05, + "loss": 4.028, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.61093822373839e-05, + "loss": 4.0177, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610099628987338e-05, + "loss": 4.0122, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609261034236286e-05, + "loss": 4.0191, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608422439485234e-05, + "loss": 4.0354, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607583844734182e-05, + "loss": 4.0155, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606746887863503e-05, + "loss": 4.026, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605908293112451e-05, + "loss": 4.019, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050696983613994e-05, + "loss": 4.0226, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6042311036103474e-05, + "loss": 4.0185, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6033925088592954e-05, + "loss": 4.0073, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6025539141082434e-05, + "loss": 4.0205, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601716957237564e-05, + "loss": 4.0171, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600878362486512e-05, + "loss": 4.0084, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60003976773546e-05, + "loss": 4.0208, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599201172984408e-05, + "loss": 4.0155, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598362578233356e-05, + "loss": 4.0186, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597523983482304e-05, + "loss": 4.0254, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596685388731252e-05, + "loss": 4.0103, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5958467939802e-05, + "loss": 4.018, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595009837109521e-05, + "loss": 4.0169, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594172880238843e-05, + "loss": 3.9965, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593334285487791e-05, + "loss": 4.0122, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592495690736739e-05, + "loss": 4.005, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591657095985687e-05, + "loss": 4.0067, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590818501234635e-05, + "loss": 4.0198, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589979906483583e-05, + "loss": 4.0218, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589141311732531e-05, + "loss": 4.0149, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883043548618516e-05, + "loss": 4.0206, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874657601107996e-05, + "loss": 4.0137, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866271653597476e-05, + "loss": 4.0161, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585788570608695e-05, + "loss": 4.0107, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.584949975857643e-05, + "loss": 3.9983, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841113811065916e-05, + "loss": 4.0159, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583274424235913e-05, + "loss": 4.0128, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824358294848605e-05, + "loss": 4.0238, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5815972347338085e-05, + "loss": 4.0118, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807586399827565e-05, + "loss": 4.0066, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799216831120774e-05, + "loss": 4.0052, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790830883610254e-05, + "loss": 4.0053, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5782444936099734e-05, + "loss": 4.0226, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5774058988589214e-05, + "loss": 4.0021, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5765673041078694e-05, + "loss": 4.0266, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57573034723719e-05, + "loss": 4.0167, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574891752486138e-05, + "loss": 3.9887, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574053157735087e-05, + "loss": 4.0201, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573214562984035e-05, + "loss": 4.0026, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572375968232983e-05, + "loss": 3.9963, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571537373481931e-05, + "loss": 4.0086, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570700416611252e-05, + "loss": 4.0149, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698618218602e-05, + "loss": 3.9993, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569023227109148e-05, + "loss": 4.0103, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568184632358096e-05, + "loss": 3.9948, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567346037607044e-05, + "loss": 4.009, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566510718616738e-05, + "loss": 4.019, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565672123865686e-05, + "loss": 4.0074, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564833529114634e-05, + "loss": 4.0165, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5639949343635823e-05, + "loss": 4.0069, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631563396125303e-05, + "loss": 4.0212, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562319382741851e-05, + "loss": 4.005, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561480787990799e-05, + "loss": 4.0108, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560642193239747e-05, + "loss": 4.0046, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559803598488695e-05, + "loss": 4.0066, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558965003737643e-05, + "loss": 4.016, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558126408986591e-05, + "loss": 4.0045, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557287814235539e-05, + "loss": 4.0155, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556449219484487e-05, + "loss": 4.0263, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555610624733435e-05, + "loss": 4.0105, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554772029982383e-05, + "loss": 3.995, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553933435231331e-05, + "loss": 4.0066, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5530948404802785e-05, + "loss": 4.0114, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522578836096e-05, + "loss": 4.0079, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551420926738922e-05, + "loss": 4.0123, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55058233198787e-05, + "loss": 4.0162, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549743737236818e-05, + "loss": 4.0105, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548905142485766e-05, + "loss": 4.0125, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548066547734714e-05, + "loss": 4.0049, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472295908640346e-05, + "loss": 4.0137, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463909961129826e-05, + "loss": 4.0113, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455524013619306e-05, + "loss": 4.0216, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447138066108786e-05, + "loss": 3.9972, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543875211859826e-05, + "loss": 4.0118, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543036617108774e-05, + "loss": 4.0121, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5421980223577226e-05, + "loss": 4.0148, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541361065487044e-05, + "loss": 4.0167, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405224707359915e-05, + "loss": 4.005, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5396838759849395e-05, + "loss": 4.0102, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5388452812338875e-05, + "loss": 4.0078, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5380066864828355e-05, + "loss": 4.0023, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371680917317835e-05, + "loss": 3.996, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5363311348611044e-05, + "loss": 3.9974, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5354925401100524e-05, + "loss": 4.01, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5346539453590004e-05, + "loss": 4.0065, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5338153506079483e-05, + "loss": 4.0025, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5329767558568963e-05, + "loss": 3.9983, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532138161105844e-05, + "loss": 4.0146, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531301204235166e-05, + "loss": 4.0124, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530462609484114e-05, + "loss": 4.0049, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529624014733062e-05, + "loss": 4.0158, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.52878541998201e-05, + "loss": 4.0167, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527946825230958e-05, + "loss": 4.0109, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527108230479906e-05, + "loss": 4.0053, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526269635728854e-05, + "loss": 4.0026, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525432678858175e-05, + "loss": 4.0061, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524594084107123e-05, + "loss": 4.0161, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523757127236444e-05, + "loss": 3.9864, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522918532485392e-05, + "loss": 4.0067, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52207993773434e-05, + "loss": 4.0054, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521241342983288e-05, + "loss": 4.0062, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204027482322364e-05, + "loss": 4.0108, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5195641534811844e-05, + "loss": 4.0037, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5187255587301324e-05, + "loss": 4.004, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51788696397908e-05, + "loss": 3.9951, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517048369228028e-05, + "loss": 4.0184, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516209774476976e-05, + "loss": 4.004, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515371179725924e-05, + "loss": 4.0158, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514532584974872e-05, + "loss": 3.9946, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5136956281041926e-05, + "loss": 4.0112, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128570333531406e-05, + "loss": 4.0165, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120184386020886e-05, + "loss": 4.0078, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111798438510366e-05, + "loss": 4.0094, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103412490999846e-05, + "loss": 4.0027, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095026543489326e-05, + "loss": 4.0065, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508664059597881e-05, + "loss": 4.0199, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507825464846829e-05, + "loss": 4.0024, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.50698850797615e-05, + "loss": 4.0037, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506149913225098e-05, + "loss": 4.0044, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505311318474046e-05, + "loss": 4.0004, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504474361603367e-05, + "loss": 4.0003, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503635766852315e-05, + "loss": 4.007, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502797172101263e-05, + "loss": 4.0032, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501958577350211e-05, + "loss": 4.0113, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501119982599159e-05, + "loss": 4.0043, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.050779342651367, + "eval_runtime": 294.0752, + "eval_samples_per_second": 1297.597, + "eval_steps_per_second": 40.551, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500281387848107e-05, + "loss": 4.0287, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499442793097055e-05, + "loss": 3.9903, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498604198346003e-05, + "loss": 4.0062, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497765603594951e-05, + "loss": 4.0107, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496927008843899e-05, + "loss": 4.0089, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496088414092847e-05, + "loss": 4.007, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495249819341795e-05, + "loss": 4.0023, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494411224590743e-05, + "loss": 3.9961, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493572629839691e-05, + "loss": 3.9974, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492734035088639e-05, + "loss": 4.0022, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491895440337587e-05, + "loss": 4.0108, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491056845586535e-05, + "loss": 4.0115, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490219888715856e-05, + "loss": 4.0245, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489381293964804e-05, + "loss": 3.9878, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488542699213752e-05, + "loss": 3.998, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877041044627e-05, + "loss": 3.9847, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486865509711648e-05, + "loss": 4.0123, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860269149605965e-05, + "loss": 4.0013, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4851883202095445e-05, + "loss": 3.9938, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843497254584925e-05, + "loss": 3.9997, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835127685878134e-05, + "loss": 4.0165, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4826741738367614e-05, + "loss": 4.0012, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4818355790857094e-05, + "loss": 4.0072, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4809969843346574e-05, + "loss": 4.0033, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480158389583605e-05, + "loss": 4.0087, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479319794832553e-05, + "loss": 4.0011, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478481200081501e-05, + "loss": 3.9908, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477644243210822e-05, + "loss": 4.0059, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.47680564845977e-05, + "loss": 3.9915, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475967053708718e-05, + "loss": 3.9909, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475128458957666e-05, + "loss": 4.0051, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474289864206614e-05, + "loss": 3.999, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473451269455562e-05, + "loss": 3.9981, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.47261267470451e-05, + "loss": 4.0089, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471774079953458e-05, + "loss": 3.9936, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.470938760963152e-05, + "loss": 4.0004, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701001662121e-05, + "loss": 4.0025, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469261571461048e-05, + "loss": 3.9795, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468422976709996e-05, + "loss": 3.9983, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467584381958944e-05, + "loss": 3.9859, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466745787207892e-05, + "loss": 3.9922, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.46590719245684e-05, + "loss": 3.9988, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465068597705788e-05, + "loss": 4.0048, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464230002954737e-05, + "loss": 3.9993, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4633946839644306e-05, + "loss": 4.0005, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4625560892133786e-05, + "loss": 4.0013, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617174944623266e-05, + "loss": 3.9977, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608805375916475e-05, + "loss": 3.9966, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600419428405955e-05, + "loss": 3.9782, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592033480895435e-05, + "loss": 3.9968, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583663912188644e-05, + "loss": 4.0002, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575277964678124e-05, + "loss": 4.0046, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566892017167604e-05, + "loss": 3.997, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455850606965709e-05, + "loss": 3.9886, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455012012214657e-05, + "loss": 3.9891, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454173417463605e-05, + "loss": 3.9862, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453334822712553e-05, + "loss": 4.0073, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452496227961501e-05, + "loss": 3.9869, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451657633210449e-05, + "loss": 4.0098, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450819038459397e-05, + "loss": 3.9957, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449980443708345e-05, + "loss": 3.9789, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449141848957293e-05, + "loss": 3.9996, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448304892086614e-05, + "loss": 3.9844, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447466297335562e-05, + "loss": 3.9806, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.44662770258451e-05, + "loss": 3.9869, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445789107833458e-05, + "loss": 4.0007, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444952150962779e-05, + "loss": 3.9831, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4441135562117275e-05, + "loss": 3.9972, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4432749614606755e-05, + "loss": 3.9767, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4424363667096235e-05, + "loss": 3.991, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441597771958571e-05, + "loss": 4.0036, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440759177207519e-05, + "loss": 3.9922, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439920582456467e-05, + "loss": 3.9974, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4390836255857884e-05, + "loss": 3.9906, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438245030834736e-05, + "loss": 4.0042, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437406436083684e-05, + "loss": 3.988, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436567841332632e-05, + "loss": 3.994, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.43572924658158e-05, + "loss": 3.9904, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434890651830528e-05, + "loss": 3.989, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340520570794757e-05, + "loss": 3.9957, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433213462328424e-05, + "loss": 3.9872, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432376505457745e-05, + "loss": 4.0014, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431539548587066e-05, + "loss": 4.0054, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430700953836014e-05, + "loss": 3.9963, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429862359084962e-05, + "loss": 3.9801, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.42902376433391e-05, + "loss": 3.987, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428185169582858e-05, + "loss": 3.995, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427346574831806e-05, + "loss": 3.9942, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426509617961127e-05, + "loss": 3.9927, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425671023210075e-05, + "loss": 3.9988, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424832428459023e-05, + "loss": 3.9963, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.423993833707971e-05, + "loss": 3.9951, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.42315523895692e-05, + "loss": 3.9909, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422316644205868e-05, + "loss": 3.9963, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421478049454816e-05, + "loss": 3.9946, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420639454703764e-05, + "loss": 4.0029, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419800859952712e-05, + "loss": 3.983, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4189639030820326e-05, + "loss": 3.9933, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181253083309806e-05, + "loss": 3.9966, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4172867135799286e-05, + "loss": 3.9982, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4164481188288766e-05, + "loss": 4.0027, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156095240778246e-05, + "loss": 3.9883, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414770929326772e-05, + "loss": 3.9929, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139356103364664e-05, + "loss": 3.9901, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4130970155854144e-05, + "loss": 3.9878, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412258420834363e-05, + "loss": 3.9795, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411419826083311e-05, + "loss": 3.9815, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410581231332259e-05, + "loss": 3.9912, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409742636581207e-05, + "loss": 3.9908, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4089040418301544e-05, + "loss": 3.9878, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4080654470791024e-05, + "loss": 3.9796, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407228490208424e-05, + "loss": 4.0005, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406389895457372e-05, + "loss": 3.9954, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405551300706319e-05, + "loss": 3.9917, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404712705955267e-05, + "loss": 4.0002, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403875749084589e-05, + "loss": 4.0011, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403037154333537e-05, + "loss": 3.9936, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402198559582485e-05, + "loss": 3.99, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401359964831433e-05, + "loss": 3.9876, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005230079607544e-05, + "loss": 3.9936, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399684413209702e-05, + "loss": 3.999, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398847456339023e-05, + "loss": 3.9691, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398008861587971e-05, + "loss": 3.9919, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397170266836919e-05, + "loss": 3.9877, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.39633330996624e-05, + "loss": 3.9878, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395494715215188e-05, + "loss": 3.9956, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394656120464136e-05, + "loss": 3.9871, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938175257130835e-05, + "loss": 3.985, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392978930962032e-05, + "loss": 3.9814, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.39214033621098e-05, + "loss": 4.0014, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391301741459928e-05, + "loss": 3.9881, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390463146708876e-05, + "loss": 3.9972, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389624551957824e-05, + "loss": 3.9835, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388785957206772e-05, + "loss": 3.9958, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387949000336093e-05, + "loss": 3.9976, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387110405585041e-05, + "loss": 3.9933, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386271810833989e-05, + "loss": 3.9916, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385433216082937e-05, + "loss": 3.9865, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384594621331885e-05, + "loss": 3.993, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383756026580833e-05, + "loss": 4.0069, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382917431829781e-05, + "loss": 3.986, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382078837078729e-05, + "loss": 3.9852, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812418802080507e-05, + "loss": 3.9902, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804032854569986e-05, + "loss": 3.986, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3795663285863196e-05, + "loss": 3.9793, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3787277338352676e-05, + "loss": 3.9963, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3778907769645885e-05, + "loss": 3.9836, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3770521822135365e-05, + "loss": 3.9929, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3762135874624845e-05, + "loss": 3.9927, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.041419506072998, + "eval_runtime": 291.4606, + "eval_samples_per_second": 1309.237, + "eval_steps_per_second": 40.915, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3753749927114324e-05, + "loss": 3.9793, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3745363979603804e-05, + "loss": 3.9779, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3736978032093284e-05, + "loss": 3.9857, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728592084582764e-05, + "loss": 3.9998, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720206137072244e-05, + "loss": 3.9926, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3711820189561724e-05, + "loss": 3.9943, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3703434242051204e-05, + "loss": 3.9821, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3695048294540684e-05, + "loss": 3.9816, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3686662347030164e-05, + "loss": 3.9802, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367829277832338e-05, + "loss": 3.9923, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366990683081285e-05, + "loss": 3.9872, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366152088330233e-05, + "loss": 4.0004, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365316769339928e-05, + "loss": 4.0048, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364478174588876e-05, + "loss": 3.9736, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363639579837824e-05, + "loss": 3.9845, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362800985086772e-05, + "loss": 3.9739, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.36196239033572e-05, + "loss": 3.9952, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361123795584668e-05, + "loss": 3.9847, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360285200833616e-05, + "loss": 3.9791, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359446606082564e-05, + "loss": 3.9852, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358608011331512e-05, + "loss": 3.997, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.35776941658046e-05, + "loss": 3.9883, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356930821829408e-05, + "loss": 3.9893, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356092227078356e-05, + "loss": 3.9891, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355253632327304e-05, + "loss": 3.9893, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354415037576252e-05, + "loss": 3.9889, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353578080705573e-05, + "loss": 3.9756, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352739485954521e-05, + "loss": 3.9908, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3519008912034687e-05, + "loss": 3.9749, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3510622964524167e-05, + "loss": 3.9816, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502237017013646e-05, + "loss": 3.9882, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493851069503126e-05, + "loss": 3.9802, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485465121992606e-05, + "loss": 3.9849, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347707917448209e-05, + "loss": 3.9921, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.34687096057753e-05, + "loss": 3.9819, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346034003706851e-05, + "loss": 3.9867, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345195408955799e-05, + "loss": 3.9843, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344356814204747e-05, + "loss": 3.9665, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343518219453695e-05, + "loss": 3.983, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342679624702643e-05, + "loss": 3.9696, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341841029951591e-05, + "loss": 3.9814, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3410024352005384e-05, + "loss": 3.9801, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3401638404494864e-05, + "loss": 3.9898, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339326883578808e-05, + "loss": 3.9824, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338488288827756e-05, + "loss": 3.9859, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337649694076704e-05, + "loss": 3.9844, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336811099325652e-05, + "loss": 3.9826, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3359725045746e-05, + "loss": 3.981, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3351355477039216e-05, + "loss": 3.965, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334296952952869e-05, + "loss": 3.9796, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333458358201817e-05, + "loss": 3.9886, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332619763450765e-05, + "loss": 3.9883, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331782806580086e-05, + "loss": 3.9791, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330944211829034e-05, + "loss": 3.9722, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330105617077982e-05, + "loss": 3.9753, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.32926702232693e-05, + "loss": 3.9678, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3284300654562514e-05, + "loss": 3.9983, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3275914707051994e-05, + "loss": 3.9695, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3267528759541474e-05, + "loss": 3.9912, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3259142812030954e-05, + "loss": 3.9805, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3250756864520434e-05, + "loss": 3.9655, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324238729581364e-05, + "loss": 3.9834, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323400134830312e-05, + "loss": 3.9701, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.32256154007926e-05, + "loss": 3.9684, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321724583208581e-05, + "loss": 3.9704, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320885988457529e-05, + "loss": 3.9855, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320047393706477e-05, + "loss": 3.9682, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319208798955425e-05, + "loss": 3.9791, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318370204204374e-05, + "loss": 3.9623, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317531609453322e-05, + "loss": 3.9749, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316694652582643e-05, + "loss": 3.9881, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315856057831591e-05, + "loss": 3.9805, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315017463080539e-05, + "loss": 3.9818, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3141805062098596e-05, + "loss": 3.9753, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133419114588076e-05, + "loss": 3.9887, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125033167077556e-05, + "loss": 3.9715, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116647219567036e-05, + "loss": 3.9778, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108277650860245e-05, + "loss": 3.9766, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3099891703349725e-05, + "loss": 3.9744, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091505755839205e-05, + "loss": 3.979, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308311980832869e-05, + "loss": 3.9751, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307473386081817e-05, + "loss": 3.9859, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306634791330765e-05, + "loss": 3.994, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305796196579713e-05, + "loss": 3.9775, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304957601828661e-05, + "loss": 3.9669, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304119007077609e-05, + "loss": 3.9729, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303280412326557e-05, + "loss": 3.9796, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302441817575505e-05, + "loss": 3.9801, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016032228244525e-05, + "loss": 3.9781, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300766265953774e-05, + "loss": 3.9852, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299927671202722e-05, + "loss": 3.9788, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2990890764516694e-05, + "loss": 3.9796, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2982504817006174e-05, + "loss": 3.9801, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974118869495654e-05, + "loss": 3.9812, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296573292198514e-05, + "loss": 3.9764, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295734697447462e-05, + "loss": 3.9895, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.29489610269641e-05, + "loss": 3.9654, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294059145825731e-05, + "loss": 3.9844, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293220551074679e-05, + "loss": 3.9845, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292381956323627e-05, + "loss": 3.9821, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2915466373333214e-05, + "loss": 3.9885, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2907080425822694e-05, + "loss": 3.9759, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289869447831217e-05, + "loss": 3.9786, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289030853080165e-05, + "loss": 3.977, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288192258329113e-05, + "loss": 3.9754, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287353663578061e-05, + "loss": 3.9633, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2865150688270094e-05, + "loss": 3.9723, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2856764740759574e-05, + "loss": 3.9714, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284839517205278e-05, + "loss": 3.9795, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284000922454226e-05, + "loss": 3.9712, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283163965583547e-05, + "loss": 3.966, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282325370832495e-05, + "loss": 3.9807, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281486776081443e-05, + "loss": 3.9808, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280648181330391e-05, + "loss": 3.9755, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279809586579339e-05, + "loss": 3.9862, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278970991828287e-05, + "loss": 3.9833, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278134034957608e-05, + "loss": 3.9849, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277295440206556e-05, + "loss": 3.9732, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276456845455505e-05, + "loss": 3.9731, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275618250704453e-05, + "loss": 3.9749, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274779655953401e-05, + "loss": 3.9866, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273941061202349e-05, + "loss": 3.9595, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273102466451297e-05, + "loss": 3.976, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272263871700245e-05, + "loss": 3.9697, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271425276949193e-05, + "loss": 3.9769, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270586682198141e-05, + "loss": 3.981, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269748087447088e-05, + "loss": 3.9741, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268909492696036e-05, + "loss": 3.9666, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2680725358253576e-05, + "loss": 3.9675, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672339410743056e-05, + "loss": 3.9878, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266395346323253e-05, + "loss": 3.9739, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2655567515722016e-05, + "loss": 3.9848, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2647181568211496e-05, + "loss": 3.9654, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263881199950471e-05, + "loss": 3.9834, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630426051994185e-05, + "loss": 3.9826, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.26220564832874e-05, + "loss": 3.9776, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261367053577688e-05, + "loss": 3.9729, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2605284588266354e-05, + "loss": 3.9758, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596898640755834e-05, + "loss": 3.9802, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588512693245314e-05, + "loss": 3.9882, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580126745734794e-05, + "loss": 3.976, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2571757177028e-05, + "loss": 3.9681, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256337122951748e-05, + "loss": 3.9794, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255498528200697e-05, + "loss": 3.9677, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254659933449645e-05, + "loss": 3.9642, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253821338698593e-05, + "loss": 3.9842, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252982743947541e-05, + "loss": 3.9685, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252144149196489e-05, + "loss": 3.9832, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251305554445437e-05, + "loss": 3.9731, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.03264856338501, + "eval_runtime": 290.8906, + "eval_samples_per_second": 1311.802, + "eval_steps_per_second": 40.995, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250468597574758e-05, + "loss": 3.9788, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249630002823706e-05, + "loss": 3.9677, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248791408072654e-05, + "loss": 3.9685, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247952813321602e-05, + "loss": 3.9838, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.24711421857055e-05, + "loss": 3.9786, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246275623819498e-05, + "loss": 3.9783, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245437029068446e-05, + "loss": 3.9671, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244598434317394e-05, + "loss": 3.9668, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243759839566342e-05, + "loss": 3.9658, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.24292124481529e-05, + "loss": 3.9754, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242082650064238e-05, + "loss": 3.9753, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241244055313186e-05, + "loss": 3.9855, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2404070984425074e-05, + "loss": 3.9902, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239568503691455e-05, + "loss": 3.9588, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238729908940403e-05, + "loss": 3.9684, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237891314189351e-05, + "loss": 3.9601, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237052719438299e-05, + "loss": 3.9786, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236214124687247e-05, + "loss": 3.9696, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235375529936195e-05, + "loss": 3.9671, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234536935185143e-05, + "loss": 3.9687, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233698340434091e-05, + "loss": 3.9822, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232859745683039e-05, + "loss": 3.9707, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232021150931987e-05, + "loss": 3.9764, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231182556180935e-05, + "loss": 3.9738, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230345599310256e-05, + "loss": 3.9784, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229507004559204e-05, + "loss": 3.9718, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228668409808152e-05, + "loss": 3.9612, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278298150571e-05, + "loss": 3.9716, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.226991220306048e-05, + "loss": 3.9623, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226154263435369e-05, + "loss": 3.9661, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225315668684317e-05, + "loss": 3.9705, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224477073933265e-05, + "loss": 3.9723, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223638479182213e-05, + "loss": 3.9685, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2227998844311605e-05, + "loss": 3.978, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221962927560482e-05, + "loss": 3.9691, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2211259706898037e-05, + "loss": 3.9707, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2202873759387517e-05, + "loss": 3.9697, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2194487811876996e-05, + "loss": 3.9532, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2186101864366476e-05, + "loss": 3.9668, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2177715916855956e-05, + "loss": 3.9572, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216932996934543e-05, + "loss": 3.9639, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2160960400638645e-05, + "loss": 3.9636, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2152574453128125e-05, + "loss": 3.9775, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2144188505617605e-05, + "loss": 3.9689, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213580255810708e-05, + "loss": 3.9702, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212741661059656e-05, + "loss": 3.9709, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119047041889774e-05, + "loss": 3.9698, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110661094379254e-05, + "loss": 3.966, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102275146868734e-05, + "loss": 3.9531, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2093889199358214e-05, + "loss": 3.9621, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2085503251847694e-05, + "loss": 3.9743, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2077117304337174e-05, + "loss": 3.9723, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2068731356826654e-05, + "loss": 3.9654, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060345409316134e-05, + "loss": 3.9555, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205197584060934e-05, + "loss": 3.9662, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204358989309882e-05, + "loss": 3.9534, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20352039455883e-05, + "loss": 3.9871, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202681799807778e-05, + "loss": 3.9525, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201844842937099e-05, + "loss": 3.9775, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201006248186048e-05, + "loss": 3.9657, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200169291315369e-05, + "loss": 3.9549, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199330696564317e-05, + "loss": 3.964, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198492101813265e-05, + "loss": 3.9629, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197653507062213e-05, + "loss": 3.9535, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196814912311161e-05, + "loss": 3.9516, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195976317560109e-05, + "loss": 3.9765, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195137722809057e-05, + "loss": 3.9592, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194299128058005e-05, + "loss": 3.9588, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193462171187326e-05, + "loss": 3.951, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192623576436274e-05, + "loss": 3.9616, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191784981685222e-05, + "loss": 3.9733, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909463869341697e-05, + "loss": 3.9673, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1901077921831177e-05, + "loss": 3.9638, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189270835312439e-05, + "loss": 3.9661, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188432240561387e-05, + "loss": 3.9711, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187593645810335e-05, + "loss": 3.9609, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186755051059283e-05, + "loss": 3.9616, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.185918094188604e-05, + "loss": 3.9614, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185079499437552e-05, + "loss": 3.9647, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842409046865e-05, + "loss": 3.9633, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183402309935448e-05, + "loss": 3.9646, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182563715184396e-05, + "loss": 3.9678, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181726758313717e-05, + "loss": 3.9767, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180889801443038e-05, + "loss": 3.9648, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800512066919866e-05, + "loss": 3.9522, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792126119409346e-05, + "loss": 3.961, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783740171898826e-05, + "loss": 3.9686, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1775354224388306e-05, + "loss": 3.9641, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1766968276877786e-05, + "loss": 3.9651, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1758598708170995e-05, + "loss": 3.9721, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1750212760660475e-05, + "loss": 3.9687, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1741826813149955e-05, + "loss": 3.9643, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1733440865639435e-05, + "loss": 3.9614, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1725054918128915e-05, + "loss": 3.9695, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171666897061839e-05, + "loss": 3.9612, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170828302310787e-05, + "loss": 3.9767, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169989707559735e-05, + "loss": 3.9499, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1691527506890564e-05, + "loss": 3.9687, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683141559380044e-05, + "loss": 3.9701, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674755611869524e-05, + "loss": 3.9682, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1666369664359004e-05, + "loss": 3.9731, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165800009565221e-05, + "loss": 3.9648, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164961414814169e-05, + "loss": 3.9632, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164124457943491e-05, + "loss": 3.966, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163285863192439e-05, + "loss": 3.956, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162447268441386e-05, + "loss": 3.9582, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161608673690334e-05, + "loss": 3.9543, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160770078939282e-05, + "loss": 3.961, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.15993148418823e-05, + "loss": 3.9648, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159092889437179e-05, + "loss": 3.9551, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158254294686127e-05, + "loss": 3.9495, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157417337815448e-05, + "loss": 3.9678, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156578743064396e-05, + "loss": 3.9729, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155740148313344e-05, + "loss": 3.9662, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1549031914426646e-05, + "loss": 3.9673, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1540645966916126e-05, + "loss": 3.9689, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1532260019405606e-05, + "loss": 3.9697, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1523874071895086e-05, + "loss": 3.9643, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1515488124384566e-05, + "loss": 3.96, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1507102176874046e-05, + "loss": 3.9645, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1498732608167255e-05, + "loss": 3.9706, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149036303946047e-05, + "loss": 3.9448, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148197709194995e-05, + "loss": 3.9646, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147359114443943e-05, + "loss": 3.9544, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146520519692891e-05, + "loss": 3.9618, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145681924941839e-05, + "loss": 3.9671, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.14484496807116e-05, + "loss": 3.9651, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144006373320108e-05, + "loss": 3.9519, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143167778569056e-05, + "loss": 3.9573, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142329183818004e-05, + "loss": 3.9689, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141490589066952e-05, + "loss": 3.9624, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140653632196273e-05, + "loss": 3.9689, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139815037445221e-05, + "loss": 3.9575, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389764426941696e-05, + "loss": 3.9675, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381378479431176e-05, + "loss": 3.972, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1372992531920656e-05, + "loss": 3.9672, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1364606584410136e-05, + "loss": 3.963, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356220636899616e-05, + "loss": 3.9598, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347834689389095e-05, + "loss": 3.9703, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339465120682305e-05, + "loss": 3.9732, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1331079173171785e-05, + "loss": 3.9629, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1322693225661264e-05, + "loss": 3.9532, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1314307278150744e-05, + "loss": 3.966, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1305921330640224e-05, + "loss": 3.9567, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.12975353831297e-05, + "loss": 3.9498, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128914943561918e-05, + "loss": 3.9712, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128076348810866e-05, + "loss": 3.9563, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1272377540598144e-05, + "loss": 3.9693, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1263991593087624e-05, + "loss": 3.9597, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.026484489440918, + "eval_runtime": 296.3877, + "eval_samples_per_second": 1287.473, + "eval_steps_per_second": 40.234, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255605645577104e-05, + "loss": 3.9506, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124723607687031e-05, + "loss": 3.9579, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123885012935979e-05, + "loss": 3.9567, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123046418184927e-05, + "loss": 3.968, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122209461314248e-05, + "loss": 3.9679, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121370866563196e-05, + "loss": 3.9669, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120532271812144e-05, + "loss": 3.957, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119693677061092e-05, + "loss": 3.9522, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118856720190413e-05, + "loss": 3.9543, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118018125439361e-05, + "loss": 3.9653, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.11717953068831e-05, + "loss": 3.9574, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116340935937258e-05, + "loss": 3.9774, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115503979066579e-05, + "loss": 3.978, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114665384315527e-05, + "loss": 3.9501, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113826789564475e-05, + "loss": 3.9505, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.112988194813423e-05, + "loss": 3.9491, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112149600062371e-05, + "loss": 3.9644, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111311005311319e-05, + "loss": 3.9601, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110472410560267e-05, + "loss": 3.9535, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109633815809215e-05, + "loss": 3.951, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1087952210581627e-05, + "loss": 3.9759, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079566263071107e-05, + "loss": 3.9548, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107118031556058e-05, + "loss": 3.9643, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1062794368050066e-05, + "loss": 3.9618, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105442479934328e-05, + "loss": 3.9695, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104605523063649e-05, + "loss": 3.9558, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103766928312597e-05, + "loss": 3.9523, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102928333561545e-05, + "loss": 3.9542, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102089738810493e-05, + "loss": 3.9582, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101251144059441e-05, + "loss": 3.9529, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1004125493083884e-05, + "loss": 3.9558, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0995739545573364e-05, + "loss": 3.9594, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0987353598062844e-05, + "loss": 3.9564, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0978984029356053e-05, + "loss": 3.9613, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970598081845533e-05, + "loss": 3.9577, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096222851313875e-05, + "loss": 3.959, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953842565628236e-05, + "loss": 3.9549, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094545661811771e-05, + "loss": 3.9429, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093707067060719e-05, + "loss": 3.9543, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092868472309667e-05, + "loss": 3.9436, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092029877558615e-05, + "loss": 3.9541, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091192920687936e-05, + "loss": 3.9519, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090354325936884e-05, + "loss": 3.9675, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089515731185832e-05, + "loss": 3.9546, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08867713643478e-05, + "loss": 3.9563, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087838541683728e-05, + "loss": 3.9641, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.086999946932676e-05, + "loss": 3.9566, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086161352181624e-05, + "loss": 3.9535, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085322757430572e-05, + "loss": 3.9411, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084487438440266e-05, + "loss": 3.9525, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9594, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.959, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.9585, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9413, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080296102565379e-05, + "loss": 3.9549, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079457507814327e-05, + "loss": 3.9403, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078618913063275e-05, + "loss": 3.9734, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077780318312223e-05, + "loss": 3.9418, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076941723561171e-05, + "loss": 3.9708, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076104766690493e-05, + "loss": 3.955, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075266171939441e-05, + "loss": 3.9391, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074427577188389e-05, + "loss": 3.9516, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073588982437337e-05, + "loss": 3.9527, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072750387686285e-05, + "loss": 3.9389, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.071911792935233e-05, + "loss": 3.9399, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071073198184181e-05, + "loss": 3.9633, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070234603433129e-05, + "loss": 3.9494, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0693976465624496e-05, + "loss": 3.9437, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685590518113976e-05, + "loss": 3.9397, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677204570603456e-05, + "loss": 3.9492, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668818623092936e-05, + "loss": 3.9617, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660432675582416e-05, + "loss": 3.9554, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652063106875625e-05, + "loss": 3.9522, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0643677159365105e-05, + "loss": 3.9555, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063529121185459e-05, + "loss": 3.9604, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062690526434407e-05, + "loss": 3.9484, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061853569563728e-05, + "loss": 3.9516, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061014974812676e-05, + "loss": 3.9545, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060176380061624e-05, + "loss": 3.9501, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059337785310572e-05, + "loss": 3.9508, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0584991905595194e-05, + "loss": 3.9531, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057662233688841e-05, + "loss": 3.9547, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056825276818162e-05, + "loss": 3.9659, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.05598668206711e-05, + "loss": 3.9526, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055148087316058e-05, + "loss": 3.9396, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543111304453795e-05, + "loss": 3.9498, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534725356943275e-05, + "loss": 3.9548, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526339409432755e-05, + "loss": 3.957, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0517953461922235e-05, + "loss": 3.9496, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509583893215444e-05, + "loss": 3.9572, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501197945704924e-05, + "loss": 3.9616, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492811998194404e-05, + "loss": 3.9493, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484426050683884e-05, + "loss": 3.9497, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476040103173363e-05, + "loss": 3.9618, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046765415566284e-05, + "loss": 3.9452, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.045926820815232e-05, + "loss": 3.9633, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.04508822606418e-05, + "loss": 3.945, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044249631313128e-05, + "loss": 3.9555, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043411036562076e-05, + "loss": 3.9618, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042572441811024e-05, + "loss": 3.9527, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041733847059972e-05, + "loss": 3.9655, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0408968901892932e-05, + "loss": 3.9516, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400582954382412e-05, + "loss": 3.9497, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392197006871892e-05, + "loss": 3.9507, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383811059361372e-05, + "loss": 3.9504, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375425111850852e-05, + "loss": 3.9428, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0367039164340332e-05, + "loss": 3.9439, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358653216829812e-05, + "loss": 3.9525, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350267269319292e-05, + "loss": 3.9518, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341897700612504e-05, + "loss": 3.9426, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333511753101984e-05, + "loss": 3.9382, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325125805591464e-05, + "loss": 3.9509, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316739858080944e-05, + "loss": 3.9637, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308353910570424e-05, + "loss": 3.9519, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0299967963059904e-05, + "loss": 3.9565, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029158201554938e-05, + "loss": 3.9547, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028319606803886e-05, + "loss": 3.9657, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274826499332077e-05, + "loss": 3.9466, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026644055182155e-05, + "loss": 3.9494, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025805460431103e-05, + "loss": 3.953, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249668656800513e-05, + "loss": 3.9576, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241315466897458e-05, + "loss": 3.9369, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232929519386938e-05, + "loss": 3.95, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224543571876418e-05, + "loss": 3.9466, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216157624365898e-05, + "loss": 3.9472, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207771676855378e-05, + "loss": 3.9509, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019940210814859e-05, + "loss": 3.9595, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019101616063807e-05, + "loss": 3.9414, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018263021312755e-05, + "loss": 3.9459, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174244265617024e-05, + "loss": 3.9502, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0165858318106503e-05, + "loss": 3.9599, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157472370595983e-05, + "loss": 3.9556, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149086423085467e-05, + "loss": 3.9456, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140716854378676e-05, + "loss": 3.9538, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132330906868156e-05, + "loss": 3.9607, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0123944959357636e-05, + "loss": 3.9588, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115559011847116e-05, + "loss": 3.9497, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107173064336596e-05, + "loss": 3.9497, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098787116826076e-05, + "loss": 3.9612, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009040116931556e-05, + "loss": 3.9582, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008201522180504e-05, + "loss": 3.9568, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007362927429452e-05, + "loss": 3.9431, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065259705587728e-05, + "loss": 3.9523, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056890136880937e-05, + "loss": 3.9402, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004852056817415e-05, + "loss": 3.9386, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004013462066363e-05, + "loss": 3.9577, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003174867315311e-05, + "loss": 3.9478, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002336272564259e-05, + "loss": 3.9563, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001497677813207e-05, + "loss": 3.9499, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000659083062155e-05, + "loss": 3.9406, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.020003795623779, + "eval_runtime": 295.5876, + "eval_samples_per_second": 1290.958, + "eval_steps_per_second": 40.343, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999820488311103e-05, + "loss": 3.9481, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989818935600513e-05, + "loss": 3.9444, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981432988089993e-05, + "loss": 3.9595, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973047040579473e-05, + "loss": 3.9528, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964661093068953e-05, + "loss": 3.9547, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956275145558432e-05, + "loss": 3.945, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947889198047912e-05, + "loss": 3.9434, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.993950325053739e-05, + "loss": 3.939, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993111730302687e-05, + "loss": 3.9556, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992273135551635e-05, + "loss": 3.9482, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991434540800583e-05, + "loss": 3.9631, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990595946049531e-05, + "loss": 3.9621, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897589891788518e-05, + "loss": 3.9466, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889203944277998e-05, + "loss": 3.9416, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880817996767478e-05, + "loss": 3.9423, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987243204925696e-05, + "loss": 3.9449, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986404610174644e-05, + "loss": 3.9485, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985566015423592e-05, + "loss": 3.9407, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.98472742067254e-05, + "loss": 3.9418, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.983888825921488e-05, + "loss": 3.9695, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983050231170436e-05, + "loss": 3.9395, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982211636419384e-05, + "loss": 3.9595, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981373041668332e-05, + "loss": 3.9496, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805377226780262e-05, + "loss": 3.9582, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796991279269742e-05, + "loss": 3.9438, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788605331759222e-05, + "loss": 3.9415, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780219384248702e-05, + "loss": 3.9406, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771833436738182e-05, + "loss": 3.9476, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763447489227662e-05, + "loss": 3.9425, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755061541717146e-05, + "loss": 3.9442, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9746675594206626e-05, + "loss": 3.9508, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.97382896466961e-05, + "loss": 3.9471, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9729936456793044e-05, + "loss": 3.9504, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721550509282524e-05, + "loss": 3.9487, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713180940575736e-05, + "loss": 3.9473, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704794993065216e-05, + "loss": 3.943, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696409045554696e-05, + "loss": 3.9299, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688023098044176e-05, + "loss": 3.9477, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679637150533656e-05, + "loss": 3.9323, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671251203023136e-05, + "loss": 3.9417, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662865255512616e-05, + "loss": 3.9409, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96544793080021e-05, + "loss": 3.9548, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646093360491572e-05, + "loss": 3.9476, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9637707412981052e-05, + "loss": 3.9416, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629321465470532e-05, + "loss": 3.9525, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620935517960012e-05, + "loss": 3.9485, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612549570449492e-05, + "loss": 3.9435, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604180001742705e-05, + "loss": 3.9338, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595794054232185e-05, + "loss": 3.9339, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587408106721665e-05, + "loss": 3.9515, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579038538014874e-05, + "loss": 3.9452, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570652590504354e-05, + "loss": 3.9452, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562266642993837e-05, + "loss": 3.9354, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553880695483317e-05, + "loss": 3.9425, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545494747972797e-05, + "loss": 3.9285, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537125179266006e-05, + "loss": 3.9575, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528739231755486e-05, + "loss": 3.9347, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520353284244966e-05, + "loss": 3.9545, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511967336734446e-05, + "loss": 3.9436, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950358138922393e-05, + "loss": 3.9316, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949521182051714e-05, + "loss": 3.9432, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948682587300662e-05, + "loss": 3.9436, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478456304299827e-05, + "loss": 3.9275, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470070356789307e-05, + "loss": 3.9277, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946168440927879e-05, + "loss": 3.9529, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945329846176827e-05, + "loss": 3.9408, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944491251425775e-05, + "loss": 3.9318, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943652656674723e-05, + "loss": 3.9271, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942814061923671e-05, + "loss": 3.9363, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.941977105052992e-05, + "loss": 3.953, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.94113851030194e-05, + "loss": 3.9452, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9402999155508883e-05, + "loss": 3.9389, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394613207998363e-05, + "loss": 3.9446, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386227260487843e-05, + "loss": 3.9495, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377841312977323e-05, + "loss": 3.9392, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369455365466803e-05, + "loss": 3.9352, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361069417956283e-05, + "loss": 3.944, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935268347044576e-05, + "loss": 3.9391, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934429752293524e-05, + "loss": 3.9434, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335927954228455e-05, + "loss": 3.9409, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327542006717935e-05, + "loss": 3.9449, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319156059207408e-05, + "loss": 3.9527, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310770111696888e-05, + "loss": 3.9418, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302384164186368e-05, + "loss": 3.9336, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294014595479584e-05, + "loss": 3.9394, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928562864796906e-05, + "loss": 3.9409, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927724270045854e-05, + "loss": 3.9476, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.926885675294802e-05, + "loss": 3.9429, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926048718424123e-05, + "loss": 3.9447, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925210123673071e-05, + "loss": 3.9468, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243715289220193e-05, + "loss": 3.9423, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235329341709673e-05, + "loss": 3.9406, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226943394199153e-05, + "loss": 3.9448, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218557446688633e-05, + "loss": 3.937, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210171499178113e-05, + "loss": 3.9501, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201785551667593e-05, + "loss": 3.9389, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193415982960802e-05, + "loss": 3.9427, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185030035450285e-05, + "loss": 3.9472, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176644087939765e-05, + "loss": 3.9476, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168274519232974e-05, + "loss": 3.9501, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159888571722454e-05, + "loss": 3.9452, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151502624211934e-05, + "loss": 3.9368, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143116676701414e-05, + "loss": 3.9402, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134730729190894e-05, + "loss": 3.9431, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126344781680377e-05, + "loss": 3.929, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9117958834169857e-05, + "loss": 3.9288, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109589265463066e-05, + "loss": 3.9446, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101203317952546e-05, + "loss": 3.943, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092817370442026e-05, + "loss": 3.9311, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084431422931506e-05, + "loss": 3.9322, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076045475420986e-05, + "loss": 3.9385, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.90676759067142e-05, + "loss": 3.9516, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.905928995920368e-05, + "loss": 3.9451, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050920390496888e-05, + "loss": 3.939, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042534442986368e-05, + "loss": 3.9483, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034148495475848e-05, + "loss": 3.9538, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902576254796533e-05, + "loss": 3.9385, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901737660045481e-05, + "loss": 3.9375, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.900899065294429e-05, + "loss": 3.9455, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900060470543377e-05, + "loss": 3.9428, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992218757923244e-05, + "loss": 3.9305, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983832810412724e-05, + "loss": 3.9334, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975446862902207e-05, + "loss": 3.9376, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967060915391687e-05, + "loss": 3.9363, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958674967881167e-05, + "loss": 3.9416, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950305399174376e-05, + "loss": 3.9503, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941919451663856e-05, + "loss": 3.9341, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893354988295707e-05, + "loss": 3.9381, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925180314250285e-05, + "loss": 3.9326, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916794366739765e-05, + "loss": 3.9504, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908408419229245e-05, + "loss": 3.9464, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900022471718718e-05, + "loss": 3.9388, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891636524208198e-05, + "loss": 3.9417, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883250576697678e-05, + "loss": 3.9473, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887486462918716e-05, + "loss": 3.9493, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886647868167664e-05, + "loss": 3.9417, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885809273416612e-05, + "loss": 3.9374, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.884972316545933e-05, + "loss": 3.948, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884133721794881e-05, + "loss": 3.9476, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883295127043829e-05, + "loss": 3.9455, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882456532292777e-05, + "loss": 3.9329, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816195754220982e-05, + "loss": 3.9428, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807809806710462e-05, + "loss": 3.9347, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799423859199942e-05, + "loss": 3.9258, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791037911689422e-05, + "loss": 3.9494, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782651964178902e-05, + "loss": 3.9383, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774266016668382e-05, + "loss": 3.9468, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765880069157862e-05, + "loss": 3.94, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757494121647342e-05, + "loss": 3.9236, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.015361785888672, + "eval_runtime": 301.6192, + "eval_samples_per_second": 1265.142, + "eval_steps_per_second": 39.537, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749124552940555e-05, + "loss": 3.9373, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740738605430035e-05, + "loss": 3.9342, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8732369036723244e-05, + "loss": 3.9507, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8723999468016456e-05, + "loss": 3.9388, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715613520505936e-05, + "loss": 3.9483, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707227572995416e-05, + "loss": 3.9315, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698841625484896e-05, + "loss": 3.9349, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690455677974376e-05, + "loss": 3.9323, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682086109267585e-05, + "loss": 3.9415, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673700161757065e-05, + "loss": 3.9379, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866531421424655e-05, + "loss": 3.9506, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8656928266736028e-05, + "loss": 3.9506, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648558698029237e-05, + "loss": 3.9361, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640172750518717e-05, + "loss": 3.9339, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631786803008197e-05, + "loss": 3.935, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623400855497677e-05, + "loss": 3.9292, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615014907987157e-05, + "loss": 3.9418, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860662896047664e-05, + "loss": 3.93, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859824301296612e-05, + "loss": 3.9316, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.85898570654556e-05, + "loss": 3.9608, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858147111794508e-05, + "loss": 3.9337, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573085170434554e-05, + "loss": 3.9417, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564699222924034e-05, + "loss": 3.9417, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556313275413517e-05, + "loss": 3.9442, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547927327902997e-05, + "loss": 3.9356, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539557759196206e-05, + "loss": 3.9345, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531171811685686e-05, + "loss": 3.9301, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522785864175166e-05, + "loss": 3.9415, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514399916664646e-05, + "loss": 3.9234, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506013969154126e-05, + "loss": 3.9373, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497644400447338e-05, + "loss": 3.9384, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489258452936818e-05, + "loss": 3.9364, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480872505426298e-05, + "loss": 3.943, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472486557915778e-05, + "loss": 3.936, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464116989208987e-05, + "loss": 3.9351, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845573104169847e-05, + "loss": 3.935, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844734509418795e-05, + "loss": 3.9211, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.843895914667743e-05, + "loss": 3.9342, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843057319916691e-05, + "loss": 3.923, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842218725165639e-05, + "loss": 3.9296, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841380130414587e-05, + "loss": 3.9352, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840543173543908e-05, + "loss": 3.9461, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397045787928563e-05, + "loss": 3.937, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388659840418043e-05, + "loss": 3.9318, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380273892907523e-05, + "loss": 3.9435, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371887945397003e-05, + "loss": 3.937, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363518376690212e-05, + "loss": 3.9305, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835513242917969e-05, + "loss": 3.9275, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834674648166917e-05, + "loss": 3.9224, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338360534158655e-05, + "loss": 3.9402, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329990965451864e-05, + "loss": 3.9371, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321605017941344e-05, + "loss": 3.9331, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313219070430824e-05, + "loss": 3.9281, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304833122920304e-05, + "loss": 3.9357, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296447175409784e-05, + "loss": 3.9201, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288061227899264e-05, + "loss": 3.9423, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827967528038874e-05, + "loss": 3.9245, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827128933287822e-05, + "loss": 3.9447, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262919764171436e-05, + "loss": 3.9325, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254533816660916e-05, + "loss": 3.9237, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246147869150393e-05, + "loss": 3.9264, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237761921639873e-05, + "loss": 3.9346, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229375974129353e-05, + "loss": 3.9172, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221006405422562e-05, + "loss": 3.9204, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212620457912042e-05, + "loss": 3.94, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204234510401522e-05, + "loss": 3.9317, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195848562891e-05, + "loss": 3.9226, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8187478994184214e-05, + "loss": 3.9202, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179093046673694e-05, + "loss": 3.9243, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170707099163174e-05, + "loss": 3.9405, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162321151652654e-05, + "loss": 3.9374, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8153951582945863e-05, + "loss": 3.9307, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145565635435343e-05, + "loss": 3.9357, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813719606672856e-05, + "loss": 3.9346, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128810119218036e-05, + "loss": 3.9344, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120424171707515e-05, + "loss": 3.9218, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811205460300073e-05, + "loss": 3.9347, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810366865549021e-05, + "loss": 3.932, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8095282707979688e-05, + "loss": 3.9298, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086896760469168e-05, + "loss": 3.9366, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078510812958648e-05, + "loss": 3.932, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070124865448128e-05, + "loss": 3.9423, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061738917937608e-05, + "loss": 3.9333, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053352970427088e-05, + "loss": 3.9169, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044967022916568e-05, + "loss": 3.9313, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036581075406048e-05, + "loss": 3.9291, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028195127895527e-05, + "loss": 3.9376, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801980918038501e-05, + "loss": 3.9332, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801143961167822e-05, + "loss": 3.9326, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.80030536641677e-05, + "loss": 3.9351, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799466771665718e-05, + "loss": 3.9336, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798628176914666e-05, + "loss": 3.933, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797789582163614e-05, + "loss": 3.9349, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7969526252929352e-05, + "loss": 3.9245, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961140305418832e-05, + "loss": 3.9386, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952754357908312e-05, + "loss": 3.9352, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944368410397792e-05, + "loss": 3.9277, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935982462887272e-05, + "loss": 3.9406, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792759651537675e-05, + "loss": 3.9353, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.791921056786623e-05, + "loss": 3.9445, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910840999159444e-05, + "loss": 3.9331, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902455051648924e-05, + "loss": 3.9263, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894069104138398e-05, + "loss": 3.9321, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885683156627878e-05, + "loss": 3.935, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877297209117358e-05, + "loss": 3.9131, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.786891126160684e-05, + "loss": 3.9281, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786052531409632e-05, + "loss": 3.9316, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.78521393665858e-05, + "loss": 3.9342, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784376979787901e-05, + "loss": 3.9245, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783538385036849e-05, + "loss": 3.9175, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827014281661702e-05, + "loss": 3.9277, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818628334151182e-05, + "loss": 3.942, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810242386640662e-05, + "loss": 3.9346, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801856439130142e-05, + "loss": 3.9347, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793470491619622e-05, + "loss": 3.9345, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785084544109102e-05, + "loss": 3.9491, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776698596598582e-05, + "loss": 3.9264, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768312649088062e-05, + "loss": 3.9271, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7759926701577542e-05, + "loss": 3.934, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751540754067022e-05, + "loss": 3.9353, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743171185360234e-05, + "loss": 3.9209, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734785237849714e-05, + "loss": 3.9202, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726399290339194e-05, + "loss": 3.9328, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718013342828674e-05, + "loss": 3.9267, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709627395318154e-05, + "loss": 3.932, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701241447807634e-05, + "loss": 3.9391, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769285550029711e-05, + "loss": 3.9228, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684485931590327e-05, + "loss": 3.9293, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676099984079807e-05, + "loss": 3.9211, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667714036569287e-05, + "loss": 3.9429, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.765932808905876e-05, + "loss": 3.9385, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7650942141548243e-05, + "loss": 3.926, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642556194037723e-05, + "loss": 3.9318, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634170246527203e-05, + "loss": 3.9346, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625800677820412e-05, + "loss": 3.9408, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617414730309892e-05, + "loss": 3.9347, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609028782799372e-05, + "loss": 3.9321, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600642835288852e-05, + "loss": 3.9339, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592256887778335e-05, + "loss": 3.9361, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583870940267815e-05, + "loss": 3.9353, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575484992757295e-05, + "loss": 3.9241, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567099045246775e-05, + "loss": 3.9327, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558729476539984e-05, + "loss": 3.9272, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550359907833197e-05, + "loss": 3.9157, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7541990339126406e-05, + "loss": 3.9406, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533604391615886e-05, + "loss": 3.9283, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525218444105366e-05, + "loss": 3.9364, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516832496594846e-05, + "loss": 3.9304, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508446549084326e-05, + "loss": 3.9186, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.010195255279541, + "eval_runtime": 296.7904, + "eval_samples_per_second": 1285.725, + "eval_steps_per_second": 40.18, + "step": 1373760 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 5.6455515676440115e+17, + "trial_name": null, + "trial_params": null +}