diff --git "a/checkpoint-2823828/trainer_state.json" "b/checkpoint-2823828/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2823828/trainer_state.json" @@ -0,0 +1,33411 @@ +{ + "best_metric": 3.8915772438049316, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/transformer/3/checkpoints/checkpoint-992148", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2823828, + "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": 11.0542, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8397, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1966, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9673, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8145, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.689, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5976, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5186, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4556, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3853, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3386, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2945, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2612, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1969, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.156, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1285, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0867, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0591, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0382, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0053, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9929, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.965, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9348, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9286, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.901, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8779, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8644, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8556, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8212, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.811, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7886, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7793, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7809, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7565, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7464, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7362, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7278, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7131, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.6994, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6917, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6737, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6699, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6434, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6534, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6471, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.636, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6168, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.616, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6087, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5917, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5816, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5756, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5856, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5529, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.577, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5391, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5471, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5396, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5361, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5242, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5207, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5045, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5143, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4978, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4999, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4935, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4827, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4648, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4785, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4695, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4551, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.462, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4524, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4533, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4536, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4467, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4372, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4218, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4294, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.426, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4269, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4225, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4079, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.3935, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3973, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3988, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4002, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.395, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3877, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3779, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3743, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3734, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3801, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3727, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3496, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3525, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3598, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3608, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3534, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3487, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3467, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3399, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3468, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3429, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3222, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3342, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3115, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3221, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3212, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3143, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3165, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3029, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3006, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3037, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3188, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.2902, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.2861, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2872, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3018, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2895, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.291, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2871, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2893, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2779, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2769, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2734, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2834, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2619, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.273, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.2685, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2571, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2674, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2623, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2658, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2633, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2467, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2431, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2474, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2553, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.257, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2488, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.238, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2385, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2412, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2389, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878452897508653e-05, + "loss": 4.233, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2513, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876775708006549e-05, + "loss": 4.2348, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2272, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2242, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.240949630737305, + "eval_runtime": 572.3683, + "eval_samples_per_second": 666.688, + "eval_steps_per_second": 20.834, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874261561633766e-05, + "loss": 4.2301, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873422966882714e-05, + "loss": 4.2271, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872584372131662e-05, + "loss": 4.2151, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.2161, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2071, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2065, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2004, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2012, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2067, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2042, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2019, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.205, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1961, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1907, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1879, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1625, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1839, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1816, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1823, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1948, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1758, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1789, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1776, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1762, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1681, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1661, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1715, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1575, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1645, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1495, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1529, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1656, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1565, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1579, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1545, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1561, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1526, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1506, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1492, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1375, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1462, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1303, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1416, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1459, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1426, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1319, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1345, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1398, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1198, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1231, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1218, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1356, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1143, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1358, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1056, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1216, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1181, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1222, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1125, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.117, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.1055, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1141, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1066, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1103, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1068, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1045, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.0875, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1111, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0985, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.0917, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1018, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.0965, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.0968, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1069, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1013, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0959, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0855, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0909, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0939, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.101, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0919, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.0865, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.0706, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0782, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0814, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0831, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0873, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0814, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0712, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0779, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0687, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0787, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0772, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0596, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0579, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0685, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0781, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0644, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0732, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0646, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0629, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0697, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0671, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0527, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.0659, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0474, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0514, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0601, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0493, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0544, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0484, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0442, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0491, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0647, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.042, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0415, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0412, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0504, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0481, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0467, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0461, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0489, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.0419, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0373, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0389, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0498, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0335, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.767799337379116e-05, + "loss": 4.0356, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0482, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.025, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0405, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764446596255282e-05, + "loss": 4.0336, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0439, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0368, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0242, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.7610938551314466e-05, + "loss": 4.0231, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0285, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0367, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0411, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0361, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0224, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0249, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0309, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0282, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0235, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0434, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0209, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.025, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.02, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.072732448577881, + "eval_runtime": 571.302, + "eval_samples_per_second": 667.932, + "eval_steps_per_second": 20.873, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749358442257838e-05, + "loss": 4.0287, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748519847506786e-05, + "loss": 4.024, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747681252755734e-05, + "loss": 4.0159, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746842658004682e-05, + "loss": 4.0175, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.74600406325363e-05, + "loss": 4.0091, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745165468502578e-05, + "loss": 4.0096, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744326873751526e-05, + "loss": 4.0081, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743488279000474e-05, + "loss": 4.0074, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.0128, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418127273787435e-05, + "loss": 4.0138, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.0121, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740135537876639e-05, + "loss": 4.0112, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392985810059604e-05, + "loss": 4.0055, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384599862549084e-05, + "loss": 4.0014, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737621391503856e-05, + "loss": 4.003, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736782796752804e-05, + "loss": 3.977, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 4.0009, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9981, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.9981, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.0155, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 3.9963, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0027, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 3.9996, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 3.9979, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.992, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9888, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9993, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9851, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9909, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9757, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9869, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9956, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9842, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9918, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9877, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 3.9899, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.991, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9867, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9834, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9755, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9835, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9697, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9861, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9817, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9848, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9749, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9727, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9847, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9639, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9692, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9649, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9827, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9635, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9839, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9541, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9671, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9708, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9702, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9656, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9762, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9497, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9638, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9608, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9688, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9572, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9638, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9438, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9653, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9569, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9528, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9581, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9558, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.955, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9705, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9629, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9587, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9478, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9513, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9582, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9634, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9531, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9546, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9378, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.946, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9408, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9495, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.957, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9475, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9385, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9474, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.938, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9487, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9459, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9327, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9326, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9374, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9479, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9388, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9479, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9364, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9364, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9425, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.942, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9307, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9471, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9218, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.927, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9401, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9248, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.937, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.926, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656312096139647e-05, + "loss": 3.9204, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.9274, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.9472, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.9223, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9257, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9186, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9285, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9351, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9283, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.926, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.9283, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9269, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9251, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9227, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9327, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9193, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9205, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9341, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9115, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9245, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9226, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9313, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9241, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9196, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9101, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9158, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9268, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9297, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9266, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9139, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9119, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9269, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9154, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9159, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9312, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9134, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.919, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9131, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9988486766815186, + "eval_runtime": 576.8122, + "eval_samples_per_second": 661.552, + "eval_steps_per_second": 20.674, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9218, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9198, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9111, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.9107, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9063, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.9038, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9057, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9013, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.908, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9137, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9059, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9073, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9053, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9022, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.8784, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.897, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.898, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8978, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9141, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607691617262736e-05, + "loss": 3.8968, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9067, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.8961, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.8968, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.8933, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.8955, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602661686636796e-05, + "loss": 3.8955, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.89, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.8903, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600147540264013e-05, + "loss": 3.8783, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.8897, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984703507619095e-05, + "loss": 3.8982, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.8913, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.8943, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.8918, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951176096380744e-05, + "loss": 3.8944, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942790148870224e-05, + "loss": 3.8924, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934404201359704e-05, + "loss": 3.8957, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8884, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.881, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590926273763187e-05, + "loss": 3.8888, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.8733, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8953, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8909, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.8888, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8824, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.881, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.8928, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.8702, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.8782, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.8775, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.8898, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8713, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.8934, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.868, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8713, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8844, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576676714516796e-05, + "loss": 3.8742, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575838119765744e-05, + "loss": 3.8839, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574999525014692e-05, + "loss": 3.889, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8647, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573323973392961e-05, + "loss": 3.8711, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572485378641909e-05, + "loss": 3.8753, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571646783890857e-05, + "loss": 3.878, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8685, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569971232269126e-05, + "loss": 3.874, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569132637518074e-05, + "loss": 3.8554, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8796, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567455448015971e-05, + "loss": 3.8678, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566616853264919e-05, + "loss": 3.866, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8718, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.871, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.8687, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8801, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8799, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8741, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.5607499657683005e-05, + "loss": 3.8651, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.8675, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8692, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8813, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5573972246444654e-05, + "loss": 3.872, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8646, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8575, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8618, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8607, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8651, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8672, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.8664, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550690104516422e-05, + "loss": 3.8588, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.869, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8571, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8625, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547337363392588e-05, + "loss": 3.8637, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8518, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545661811770857e-05, + "loss": 3.8505, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.863, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.8602, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8649, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8631, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8557, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8555, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.8638, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389563295231865e-05, + "loss": 3.8633, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8516, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537280777901456e-05, + "loss": 3.8675, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8418, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535603588399352e-05, + "loss": 3.8486, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8635, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8452, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8584, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.845, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531412252524465e-05, + "loss": 3.8416, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.8495, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529735063022361e-05, + "loss": 3.8688, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8491, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.52805951140063e-05, + "loss": 3.8468, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5272209166495786e-05, + "loss": 3.8412, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263823218985266e-05, + "loss": 3.8503, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8565, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247067702767955e-05, + "loss": 3.8533, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238681755257435e-05, + "loss": 3.8468, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230295807746915e-05, + "loss": 3.8555, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8506, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8484, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8457, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8552, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8437, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8447, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8569, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8366, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8481, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514645271144545e-05, + "loss": 3.8518, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8558, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8466, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8476, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.51129253002071e-05, + "loss": 3.8367, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8432, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8502, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.854, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.854, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8427, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8367, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8503, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8414, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8454, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8572, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8444, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8446, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8422, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9590904712677, + "eval_runtime": 583.4335, + "eval_samples_per_second": 654.044, + "eval_steps_per_second": 20.439, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8527, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8477, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8395, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8378, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8389, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8325, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8338, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8275, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8377, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492014678028752e-05, + "loss": 3.8469, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911760832777e-05, + "loss": 3.8324, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490337488526648e-05, + "loss": 3.8326, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8377, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.8331, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.8295, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8087, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.8263, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8278, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8276, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.848, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827917736475535e-05, + "loss": 3.8248, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.8407, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8256, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8332, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.8206, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8269, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8287, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8242, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.823, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8135, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8171, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8311, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.8261, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8277, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8235, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8287, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8256, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.8269, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8236, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8129, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.829, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8057, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8277, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8227, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8304, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8187, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8131, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8281, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8079, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8117, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8152, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8201, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.8118, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8224, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8059, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8089, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8194, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8064, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509415519113085e-05, + "loss": 3.8248, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501029571602565e-05, + "loss": 3.8286, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.7972, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8065, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475888107874734e-05, + "loss": 3.813, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467502160364214e-05, + "loss": 3.8199, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8061, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8082, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444236069663639e-05, + "loss": 3.7969, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443397474912587e-05, + "loss": 3.8127, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442558880161535e-05, + "loss": 3.8074, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441721923290856e-05, + "loss": 3.8026, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440883328539804e-05, + "loss": 3.8106, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440044733788752e-05, + "loss": 3.81, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392061390377e-05, + "loss": 3.8067, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438369182167021e-05, + "loss": 3.819, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437530587415969e-05, + "loss": 3.8159, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436691992664917e-05, + "loss": 3.813, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435853397913865e-05, + "loss": 3.8056, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350164410431864e-05, + "loss": 3.8087, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341778462921344e-05, + "loss": 3.8032, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333392515410824e-05, + "loss": 3.8224, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43250065679003e-05, + "loss": 3.8107, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431663699919351e-05, + "loss": 3.8061, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430825105168299e-05, + "loss": 3.7914, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429986510417247e-05, + "loss": 3.808, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291479156661946e-05, + "loss": 3.7969, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428310958795516e-05, + "loss": 3.8092, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427472364044464e-05, + "loss": 3.8041, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426633769293412e-05, + "loss": 3.8052, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42579517454236e-05, + "loss": 3.7994, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424958217671682e-05, + "loss": 3.8136, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42411962292063e-05, + "loss": 3.7956, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423281028169577e-05, + "loss": 3.8026, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422442433418525e-05, + "loss": 3.8087, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216054765478466e-05, + "loss": 3.7883, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207668817967946e-05, + "loss": 3.7916, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419928287045742e-05, + "loss": 3.806, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.41908969229469e-05, + "loss": 3.7969, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182527354240115e-05, + "loss": 3.8125, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174141406729595e-05, + "loss": 3.8033, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.7925, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157369511708555e-05, + "loss": 3.7974, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414899994300177e-05, + "loss": 3.8044, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140613995491244e-05, + "loss": 3.8051, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.7958, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.8081, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411547253176342e-05, + "loss": 3.7851, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410708658425289e-05, + "loss": 3.7908, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409870063674237e-05, + "loss": 3.8036, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409031468923185e-05, + "loss": 3.7841, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408192874172133e-05, + "loss": 3.8005, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407354279421081e-05, + "loss": 3.7966, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406517322550402e-05, + "loss": 3.7773, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405678727799351e-05, + "loss": 3.7922, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.8097, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.7911, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403164581426568e-05, + "loss": 3.7923, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402325986675516e-05, + "loss": 3.7879, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.7912, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.8007, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.7966, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.7898, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.7939, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7948, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964590991788976e-05, + "loss": 3.7925, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956205044278456e-05, + "loss": 3.7892, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394781909676794e-05, + "loss": 3.7989, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393943314925742e-05, + "loss": 3.7836, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393106358055063e-05, + "loss": 3.7946, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392267763304011e-05, + "loss": 3.7976, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.784, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.7889, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389753616931228e-05, + "loss": 3.7972, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388915022180176e-05, + "loss": 3.7959, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.7952, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.7904, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.781, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385562281056341e-05, + "loss": 3.7891, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.7929, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.7996, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.8009, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822095399325065e-05, + "loss": 3.7896, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.7824, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.7962, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7854, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.79, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.8046, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.793, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376342652435888e-05, + "loss": 3.7833, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375504057684836e-05, + "loss": 3.7903, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.93572735786438, + "eval_runtime": 576.4532, + "eval_samples_per_second": 661.964, + "eval_steps_per_second": 20.687, + "step": 381595 + }, + { + "epoch": 1.0, + "learning_rate": 4.374665462933785e-05, + "loss": 3.7941, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373826868182733e-05, + "loss": 3.7962, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372988273431681e-05, + "loss": 3.7825, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372151316561002e-05, + "loss": 3.7804, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.37131272180995e-05, + "loss": 3.7887, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370475764939271e-05, + "loss": 3.7806, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369637170188219e-05, + "loss": 3.7819, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368798575437167e-05, + "loss": 3.7712, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367959980686115e-05, + "loss": 3.7852, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7972, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.7765, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365445834313332e-05, + "loss": 3.7784, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7864, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7781, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.78, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7568, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7708, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360415903687393e-05, + "loss": 3.7761, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359577308936341e-05, + "loss": 3.7742, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.7972, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7729, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357063162563558e-05, + "loss": 3.788, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356224567812506e-05, + "loss": 3.7743, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355385973061454e-05, + "loss": 3.7805, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.7681, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353710421439724e-05, + "loss": 3.773, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352871826688672e-05, + "loss": 3.7779, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35203323193762e-05, + "loss": 3.7755, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.7704, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503576803158886e-05, + "loss": 3.7667, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495190855648366e-05, + "loss": 3.7606, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486804908137846e-05, + "loss": 3.782, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.7776, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.7744, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7746, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7776, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344487517058524e-05, + "loss": 3.7783, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7729, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.7751, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7633, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7757, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.759, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.778, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7692, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7781, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7688, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.7649, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.7807, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7555, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.7643, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7644, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7674, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.7643, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330239595692506e-05, + "loss": 3.7694, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329401000941454e-05, + "loss": 3.76, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328562406190402e-05, + "loss": 3.7574, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7711, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7613, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.7722, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7768, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324372708195888e-05, + "loss": 3.7529, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7573, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7599, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321856923942732e-05, + "loss": 3.7756, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321019967072053e-05, + "loss": 3.7575, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7623, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319344415450322e-05, + "loss": 3.749, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.31850582069927e-05, + "loss": 3.766, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.7553, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7556, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.7614, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315151441695062e-05, + "loss": 3.7623, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431284694401e-05, + "loss": 3.7582, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7699, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.7704, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117987005712276e-05, + "loss": 3.7647, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109601058201756e-05, + "loss": 3.7546, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101215110691236e-05, + "loss": 3.765, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092829163180715e-05, + "loss": 3.7549, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.7741, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7594, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067687699452885e-05, + "loss": 3.7631, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059301751942364e-05, + "loss": 3.7454, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.7603, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.7464, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.7637, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302579071950775e-05, + "loss": 3.758, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301740477199723e-05, + "loss": 3.7583, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300901882448671e-05, + "loss": 3.7571, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300063287697619e-05, + "loss": 3.7691, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299224692946567e-05, + "loss": 3.742, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.7551, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7619, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296710546573784e-05, + "loss": 3.7442, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295871951822732e-05, + "loss": 3.7466, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7606, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7466, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293357805449949e-05, + "loss": 3.7708, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925192106988974e-05, + "loss": 3.7544, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916806159478454e-05, + "loss": 3.7468, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290842021196793e-05, + "loss": 3.7511, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7599, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7606, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288329512704383e-05, + "loss": 3.7477, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287490917953331e-05, + "loss": 3.7627, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286652323202279e-05, + "loss": 3.7392, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285813728451227e-05, + "loss": 3.7457, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7561, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284138176829496e-05, + "loss": 3.7415, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283299582078444e-05, + "loss": 3.7516, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282460987327393e-05, + "loss": 3.7565, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.28162239257634e-05, + "loss": 3.7294, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280783797825288e-05, + "loss": 3.7491, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799468409546097e-05, + "loss": 3.7604, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791082462035576e-05, + "loss": 3.7505, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278269651452505e-05, + "loss": 3.7427, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7407, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.7477, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7564, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.27491691032867e-05, + "loss": 3.7534, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274078315577618e-05, + "loss": 3.7432, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732397208265665e-05, + "loss": 3.7481, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724011260755145e-05, + "loss": 3.7499, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7499, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7426, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.7505, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7431, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7512, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7521, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7367, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7455, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7541, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7517, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7479, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7481, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.7359, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260665713201906e-05, + "loss": 3.7418, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259827118450854e-05, + "loss": 3.7485, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7603, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258151566829123e-05, + "loss": 3.7545, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257312972078071e-05, + "loss": 3.7429, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256474377327019e-05, + "loss": 3.7451, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7488, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7451, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253960230954236e-05, + "loss": 3.7449, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253121636203184e-05, + "loss": 3.762, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7476, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7391, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.7462, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.919872999191284, + "eval_runtime": 554.6551, + "eval_samples_per_second": 687.979, + "eval_steps_per_second": 21.5, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249768895079349e-05, + "loss": 3.7548, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248930300328297e-05, + "loss": 3.7516, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248091705577245e-05, + "loss": 3.7438, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247253110826193e-05, + "loss": 3.7407, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7424, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7366, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7381, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7295, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.74, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422231802002534e-05, + "loss": 3.7558, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7358, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7352, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239709033827471e-05, + "loss": 3.7438, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238870439076419e-05, + "loss": 3.7353, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238031844325367e-05, + "loss": 3.7408, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371948874546886e-05, + "loss": 3.7145, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236356292703636e-05, + "loss": 3.7262, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235517697952584e-05, + "loss": 3.7343, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234679103201532e-05, + "loss": 3.7323, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.23384050845048e-05, + "loss": 3.7578, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233001913699428e-05, + "loss": 3.7314, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232163318948376e-05, + "loss": 3.7465, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231324724197324e-05, + "loss": 3.7288, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.737, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7269, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7335, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7363, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271350262028104e-05, + "loss": 3.7298, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7333, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.7214, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7186, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223782285078975e-05, + "loss": 3.7397, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7363, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.7369, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221266500825819e-05, + "loss": 3.7298, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7384, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219589311323716e-05, + "loss": 3.7323, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218750716572664e-05, + "loss": 3.7371, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217913759701985e-05, + "loss": 3.7309, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217075164950933e-05, + "loss": 3.7245, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216236570199881e-05, + "loss": 3.7361, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215397975448829e-05, + "loss": 3.7155, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214559380697777e-05, + "loss": 3.7369, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213722423827098e-05, + "loss": 3.7301, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212883829076046e-05, + "loss": 3.7372, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212045234324994e-05, + "loss": 3.7301, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211206639573942e-05, + "loss": 3.7224, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21036804482289e-05, + "loss": 3.7384, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209531087952211e-05, + "loss": 3.7192, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208692493201159e-05, + "loss": 3.7238, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207853898450107e-05, + "loss": 3.7235, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070153036990546e-05, + "loss": 3.726, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206178346828376e-05, + "loss": 3.7274, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205339752077324e-05, + "loss": 3.7248, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204501157326272e-05, + "loss": 3.7206, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036625625752195e-05, + "loss": 3.7232, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202825605704541e-05, + "loss": 3.7264, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201987010953489e-05, + "loss": 3.7227, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011484162024364e-05, + "loss": 3.7319, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200309821451385e-05, + "loss": 3.738, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199471226700333e-05, + "loss": 3.7156, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986342698296547e-05, + "loss": 3.7148, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197795675078602e-05, + "loss": 3.7181, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.19695708032755e-05, + "loss": 3.7393, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196118485576498e-05, + "loss": 3.7211, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195279890825446e-05, + "loss": 3.7209, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194442933954767e-05, + "loss": 3.7115, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193604339203715e-05, + "loss": 3.7217, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192765744452663e-05, + "loss": 3.7191, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191927149701611e-05, + "loss": 3.7166, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191088554950559e-05, + "loss": 3.7221, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190249960199507e-05, + "loss": 3.7207, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894130033288284e-05, + "loss": 3.7204, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885744085777764e-05, + "loss": 3.7264, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877358138267244e-05, + "loss": 3.7317, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868972190756724e-05, + "loss": 3.726, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186060262204993e-05, + "loss": 3.7181, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185221667453941e-05, + "loss": 3.7227, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184383072702889e-05, + "loss": 3.7184, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183544477951837e-05, + "loss": 3.7353, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182705883200785e-05, + "loss": 3.7223, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181868926330106e-05, + "loss": 3.7256, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181030331579054e-05, + "loss": 3.7055, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180191736828002e-05, + "loss": 3.7261, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935314207695e-05, + "loss": 3.7053, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178516185206272e-05, + "loss": 3.7244, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.17767759045522e-05, + "loss": 3.7204, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176838995704168e-05, + "loss": 3.721, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176000400953116e-05, + "loss": 3.7173, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175161806202064e-05, + "loss": 3.7287, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174324849331385e-05, + "loss": 3.7095, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173486254580333e-05, + "loss": 3.7174, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172647659829281e-05, + "loss": 3.7237, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171809065078229e-05, + "loss": 3.7085, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709721082075496e-05, + "loss": 3.7096, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701335134564976e-05, + "loss": 3.7185, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1692949187054456e-05, + "loss": 3.7097, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684563239543936e-05, + "loss": 3.734, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167617729203342e-05, + "loss": 3.7163, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166780772332663e-05, + "loss": 3.7119, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165942177581611e-05, + "loss": 3.7134, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165103582830559e-05, + "loss": 3.7201, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164264988079507e-05, + "loss": 3.7233, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163428031208828e-05, + "loss": 3.7108, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162589436457776e-05, + "loss": 3.7229, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161750841706724e-05, + "loss": 3.7048, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160912246955672e-05, + "loss": 3.7058, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160075290084993e-05, + "loss": 3.7158, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159236695333941e-05, + "loss": 3.7079, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158398100582889e-05, + "loss": 3.7139, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575595058318376e-05, + "loss": 3.7176, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567225489611585e-05, + "loss": 3.6935, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558839542101065e-05, + "loss": 3.7115, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550453594590545e-05, + "loss": 3.7277, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1542067647080025e-05, + "loss": 3.7158, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.15336816995695e-05, + "loss": 3.7015, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525312130862714e-05, + "loss": 3.7037, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516926183352194e-05, + "loss": 3.7096, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508540235841674e-05, + "loss": 3.7167, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150015428833115e-05, + "loss": 3.7165, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149178471962436e-05, + "loss": 3.7061, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148339877211384e-05, + "loss": 3.7105, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147501282460333e-05, + "loss": 3.7143, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.14666268770928e-05, + "loss": 3.7126, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145825730838602e-05, + "loss": 3.7041, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.14498713608755e-05, + "loss": 3.715, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144148541336497e-05, + "loss": 3.707, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143309946585445e-05, + "loss": 3.7151, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142471351834393e-05, + "loss": 3.7136, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141632757083341e-05, + "loss": 3.6993, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140795800212662e-05, + "loss": 3.7095, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13995720546161e-05, + "loss": 3.7145, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139118610710558e-05, + "loss": 3.7163, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138280015959507e-05, + "loss": 3.7118, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137443059088828e-05, + "loss": 3.714, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136604464337776e-05, + "loss": 3.6988, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357658695867237e-05, + "loss": 3.7022, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349272748356717e-05, + "loss": 3.712, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340903179649926e-05, + "loss": 3.7248, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332517232139406e-05, + "loss": 3.7176, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324131284628886e-05, + "loss": 3.708, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315745337118366e-05, + "loss": 3.7039, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307375768411575e-05, + "loss": 3.7147, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298989820901055e-05, + "loss": 3.7074, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290603873390535e-05, + "loss": 3.7087, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128221792588002e-05, + "loss": 3.7263, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127384835717323e-05, + "loss": 3.7138, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126546240966271e-05, + "loss": 3.7031, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125707646215219e-05, + "loss": 3.7113, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.910520076751709, + "eval_runtime": 572.6756, + "eval_samples_per_second": 666.33, + "eval_steps_per_second": 20.823, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124869051464167e-05, + "loss": 3.7176, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124030456713115e-05, + "loss": 3.7165, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123191861962063e-05, + "loss": 3.7093, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122353267211011e-05, + "loss": 3.7046, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121516310340332e-05, + "loss": 3.7036, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.12067771558928e-05, + "loss": 3.7056, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119839120838228e-05, + "loss": 3.7012, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119000526087176e-05, + "loss": 3.6956, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118163569216497e-05, + "loss": 3.7024, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173249744654455e-05, + "loss": 3.7172, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164880175947664e-05, + "loss": 3.7013, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156494228437144e-05, + "loss": 3.6992, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148108280926624e-05, + "loss": 3.7123, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139722333416104e-05, + "loss": 3.6965, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1131336385905584e-05, + "loss": 3.7088, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1122950438395064e-05, + "loss": 3.6817, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.1114564490884544e-05, + "loss": 3.6859, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.1106178543374024e-05, + "loss": 3.7033, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109780897466723e-05, + "loss": 3.6948, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108942302715671e-05, + "loss": 3.7212, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108103707964619e-05, + "loss": 3.6988, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107265113213567e-05, + "loss": 3.7093, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106428156342889e-05, + "loss": 3.6953, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105589561591837e-05, + "loss": 3.7063, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104750966840785e-05, + "loss": 3.6892, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103912372089733e-05, + "loss": 3.698, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103075415219054e-05, + "loss": 3.7017, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102236820468002e-05, + "loss": 3.6983, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.10139822571695e-05, + "loss": 3.6939, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100559630965898e-05, + "loss": 3.6918, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997226740952186e-05, + "loss": 3.6826, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988840793441666e-05, + "loss": 3.7051, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980454845931146e-05, + "loss": 3.7007, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972068898420626e-05, + "loss": 3.6987, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963682950910106e-05, + "loss": 3.6983, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095531338220332e-05, + "loss": 3.7044, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.09469274346928e-05, + "loss": 3.696, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093854148718228e-05, + "loss": 3.6978, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930155539671755e-05, + "loss": 3.6966, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092178597096497e-05, + "loss": 3.6968, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091340002345445e-05, + "loss": 3.6975, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090501407594393e-05, + "loss": 3.6843, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896628128433404e-05, + "loss": 3.7069, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088825855972662e-05, + "loss": 3.6928, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.08798726122161e-05, + "loss": 3.7049, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087148666470558e-05, + "loss": 3.6982, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086310071719506e-05, + "loss": 3.6878, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085471476968454e-05, + "loss": 3.7056, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846345200977756e-05, + "loss": 3.6839, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083795925346723e-05, + "loss": 3.692, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082957330595671e-05, + "loss": 3.6843, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082118735844619e-05, + "loss": 3.6944, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.0812817789739405e-05, + "loss": 3.6925, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080443184222888e-05, + "loss": 3.6904, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079604589471836e-05, + "loss": 3.6884, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078765994720784e-05, + "loss": 3.6884, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779290378501054e-05, + "loss": 3.692, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770904430990534e-05, + "loss": 3.6921, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0762518483480014e-05, + "loss": 3.701, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0754132535969494e-05, + "loss": 3.6991, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.07457629672627e-05, + "loss": 3.6852, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073737701975218e-05, + "loss": 3.6791, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072899107224166e-05, + "loss": 3.6886, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072060512473114e-05, + "loss": 3.7021, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071223555602435e-05, + "loss": 3.6893, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070384960851383e-05, + "loss": 3.683, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069546366100331e-05, + "loss": 3.6833, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068707771349279e-05, + "loss": 3.6875, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067870814478601e-05, + "loss": 3.6818, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067032219727549e-05, + "loss": 3.6858, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066193624976497e-05, + "loss": 3.6891, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065355030225445e-05, + "loss": 3.6843, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064516435474393e-05, + "loss": 3.6909, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636794786037136e-05, + "loss": 3.6954, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628408838526616e-05, + "loss": 3.6959, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620022891016096e-05, + "loss": 3.6909, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611636943505576e-05, + "loss": 3.6872, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603267374798785e-05, + "loss": 3.6896, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594881427288265e-05, + "loss": 3.6865, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.6994, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578109532267225e-05, + "loss": 3.6948, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056973996356044e-05, + "loss": 3.693, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056135401604992e-05, + "loss": 3.6733, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6884, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054458212102888e-05, + "loss": 3.6741, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053621255232209e-05, + "loss": 3.6887, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052782660481157e-05, + "loss": 3.6881, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.6859, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051105470979053e-05, + "loss": 3.6871, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050268514108374e-05, + "loss": 3.6936, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049429919357322e-05, + "loss": 3.6783, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6849, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047752729855218e-05, + "loss": 3.6907, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469157729845395e-05, + "loss": 3.6786, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460771782334875e-05, + "loss": 3.6782, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452385834824355e-05, + "loss": 3.6799, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.6823, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435630318607044e-05, + "loss": 3.7017, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427244371096524e-05, + "loss": 3.6814, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.0418858423586004e-05, + "loss": 3.6834, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.0410472476075483e-05, + "loss": 3.68, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040210290736869e-05, + "loss": 3.6929, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039371695985817e-05, + "loss": 3.6862, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038533101234765e-05, + "loss": 3.6781, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037694506483713e-05, + "loss": 3.6923, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036857549613035e-05, + "loss": 3.6704, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036018954861983e-05, + "loss": 3.6738, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035180360110931e-05, + "loss": 3.6858, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6771, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335048084892e-05, + "loss": 3.6828, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032666213738148e-05, + "loss": 3.6832, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031827618987096e-05, + "loss": 3.6578, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030989024236044e-05, + "loss": 3.6819, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301520673653646e-05, + "loss": 3.6942, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293134726143126e-05, + "loss": 3.6829, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284748778632606e-05, + "loss": 3.674, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276362831122086e-05, + "loss": 3.6728, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0267976883611566e-05, + "loss": 3.6755, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025960731490478e-05, + "loss": 3.6862, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025123774619799e-05, + "loss": 3.6854, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024285179868747e-05, + "loss": 3.6759, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023446585117695e-05, + "loss": 3.6755, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022607990366643e-05, + "loss": 3.6859, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021769395615591e-05, + "loss": 3.6804, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020930800864539e-05, + "loss": 3.6711, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020092206113487e-05, + "loss": 3.6848, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019253611362435e-05, + "loss": 3.6769, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018415016611383e-05, + "loss": 3.6774, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017578059740704e-05, + "loss": 3.6893, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016739464989652e-05, + "loss": 3.6654, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159008702386e-05, + "loss": 3.6791, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150622754875486e-05, + "loss": 3.6868, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0142253186168696e-05, + "loss": 3.6832, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133867238658175e-05, + "loss": 3.6786, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125481291147655e-05, + "loss": 3.6827, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.6695, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108725774930344e-05, + "loss": 3.6712, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100339827419824e-05, + "loss": 3.6826, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091953879909304e-05, + "loss": 3.687, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008356793239878e-05, + "loss": 3.6904, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075198363691993e-05, + "loss": 3.6778, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006681241618147e-05, + "loss": 3.6737, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005842646867095e-05, + "loss": 3.684, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005004052116043e-05, + "loss": 3.6725, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004167095245365e-05, + "loss": 3.681, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003328500494313e-05, + "loss": 3.6911, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.00248990574326e-05, + "loss": 3.6867, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001651310992208e-05, + "loss": 3.6714, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.00081435412153e-05, + "loss": 3.6838, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.9045441150665283, + "eval_runtime": 564.5634, + "eval_samples_per_second": 675.905, + "eval_steps_per_second": 21.123, + "step": 610552 + }, + { + "epoch": 1.0, + "learning_rate": 3.999975759370478e-05, + "loss": 3.6758, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999137164619425e-05, + "loss": 3.6878, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998298569868373e-05, + "loss": 3.6765, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997461612997695e-05, + "loss": 3.6774, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996623018246643e-05, + "loss": 3.6705, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995784423495591e-05, + "loss": 3.676, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994945828744539e-05, + "loss": 3.6737, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.99410887187386e-05, + "loss": 3.6608, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9932702771228076e-05, + "loss": 3.671, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9924316823717556e-05, + "loss": 3.6883, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6733, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.6678, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.9899175359989725e-05, + "loss": 3.6823, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.9890789412479205e-05, + "loss": 3.6677, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.9882403464968685e-05, + "loss": 3.6777, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.9874017517458165e-05, + "loss": 3.6532, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9865631569947645e-05, + "loss": 3.654, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985724562243713e-05, + "loss": 3.6748, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984887605373034e-05, + "loss": 3.6627, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984049010621982e-05, + "loss": 3.6901, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.98321041587093e-05, + "loss": 3.6707, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982371821119878e-05, + "loss": 3.6767, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.6654, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.678, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.661, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979019079996043e-05, + "loss": 3.6666, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6687, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.6715, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.97650493362326e-05, + "loss": 3.6664, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.9756663388722085e-05, + "loss": 3.659, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6544, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.9739907872504774e-05, + "loss": 3.6728, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.9731521924994254e-05, + "loss": 3.6741, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.9723135977483734e-05, + "loss": 3.6679, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6682, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6729, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.6686, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968960856624538e-05, + "loss": 3.6694, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6662, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967285305002807e-05, + "loss": 3.6635, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6697, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965608115500703e-05, + "loss": 3.6531, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.6724, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.67, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.672, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.6699, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6555, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.678, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6561, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.6641, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6563, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.6609, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6714, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.9555498921291986e-05, + "loss": 3.6562, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.95471293525852e-05, + "loss": 3.6619, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953874340507468e-05, + "loss": 3.6572, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953035745756416e-05, + "loss": 3.6673, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952197151005364e-05, + "loss": 3.6602, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6722, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.666, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6577, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.6539, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6604, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6664, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6621, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6592, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.655, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6544, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6546, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6567, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6596, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6581, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6614, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.671, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6659, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6601, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936272040137241e-05, + "loss": 3.661, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935433445386189e-05, + "loss": 3.6626, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6548, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.671, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.667, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6652, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6481, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6579, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6452, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6666, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.66, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927052411516789e-05, + "loss": 3.6542, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6595, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6644, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6508, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.6538, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6619, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6522, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6516, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920346929269119e-05, + "loss": 3.6498, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6548, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6737, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.6544, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6574, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.6548, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6601, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914478403892128e-05, + "loss": 3.6596, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6529, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6628, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.6409, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911125662768293e-05, + "loss": 3.6473, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6577, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6543, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6499, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907772921644458e-05, + "loss": 3.6559, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6331, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.6567, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6601, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6564, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6444, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902744628898892e-05, + "loss": 3.6473, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.90190603414784e-05, + "loss": 3.6459, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901067439396788e-05, + "loss": 3.6598, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6548, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899391887775057e-05, + "loss": 3.6525, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898553293024005e-05, + "loss": 3.6481, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897714698272953e-05, + "loss": 3.6593, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.6523, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896037508770849e-05, + "loss": 3.6455, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895198914019798e-05, + "loss": 3.6523, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894360319268746e-05, + "loss": 3.6507, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893523362398067e-05, + "loss": 3.652, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892684767647015e-05, + "loss": 3.6591, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891846172895963e-05, + "loss": 3.6438, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891007578144911e-05, + "loss": 3.6498, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890170621274232e-05, + "loss": 3.6604, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8893320265231797e-05, + "loss": 3.6519, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884934317721277e-05, + "loss": 3.6516, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8876548370210757e-05, + "loss": 3.6551, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6454, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859792853993446e-05, + "loss": 3.6454, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885140690648293e-05, + "loss": 3.653, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884302095897241e-05, + "loss": 3.664, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883465139026562e-05, + "loss": 3.6592, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.88262654427551e-05, + "loss": 3.65, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881787949524458e-05, + "loss": 3.6504, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6522, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880112397902727e-05, + "loss": 3.6492, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879273803151675e-05, + "loss": 3.6536, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878435208400623e-05, + "loss": 3.6613, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877596613649571e-05, + "loss": 3.66, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876759656778892e-05, + "loss": 3.6434, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.87592106202784e-05, + "loss": 3.6564, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8993594646453857, + "eval_runtime": 551.7316, + "eval_samples_per_second": 691.624, + "eval_steps_per_second": 21.614, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875082467276788e-05, + "loss": 3.6594, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742438725257366e-05, + "loss": 3.6602, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8734052777746846e-05, + "loss": 3.6521, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725666830236326e-05, + "loss": 3.6474, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717297261529535e-05, + "loss": 3.6448, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708911314019015e-05, + "loss": 3.6474, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8700525366508495e-05, + "loss": 3.648, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8692139418997975e-05, + "loss": 3.6348, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683769850291184e-05, + "loss": 3.6423, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675383902780664e-05, + "loss": 3.6615, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866701433407387e-05, + "loss": 3.646, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865862838656335e-05, + "loss": 3.6397, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865024243905283e-05, + "loss": 3.6583, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864185649154232e-05, + "loss": 3.6405, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.86334705440318e-05, + "loss": 3.6505, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862508459652128e-05, + "loss": 3.6267, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861669864901076e-05, + "loss": 3.6285, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860831270150023e-05, + "loss": 3.6485, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859994313279345e-05, + "loss": 3.6378, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859155718528293e-05, + "loss": 3.6607, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858317123777241e-05, + "loss": 3.6432, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857478529026188e-05, + "loss": 3.6572, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.85664157215551e-05, + "loss": 3.6387, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855802977404458e-05, + "loss": 3.6461, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854964382653406e-05, + "loss": 3.6365, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854125787902354e-05, + "loss": 3.643, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853288831031675e-05, + "loss": 3.6436, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852450236280623e-05, + "loss": 3.6458, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8516116415295706e-05, + "loss": 3.638, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6341, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.84993608990784e-05, + "loss": 3.6279, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849097495156788e-05, + "loss": 3.6487, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482589004057355e-05, + "loss": 3.645, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474203056546835e-05, + "loss": 3.6421, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846583348784005e-05, + "loss": 3.6423, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457447540329524e-05, + "loss": 3.6474, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844906159281901e-05, + "loss": 3.6398, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844067564530849e-05, + "loss": 3.6426, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843230607660171e-05, + "loss": 3.642, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842392012909118e-05, + "loss": 3.6376, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841553418158066e-05, + "loss": 3.6416, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8407164612873876e-05, + "loss": 3.6347, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.8398778665363356e-05, + "loss": 3.643, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839039271785283e-05, + "loss": 3.6463, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838200677034231e-05, + "loss": 3.6461, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373637201635525e-05, + "loss": 3.6447, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365251254125e-05, + "loss": 3.631, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835686530661448e-05, + "loss": 3.6504, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.8348479359103965e-05, + "loss": 3.6337, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834010979039718e-05, + "loss": 3.6363, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331723842886654e-05, + "loss": 3.6316, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323337895376134e-05, + "loss": 3.6322, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314951947865614e-05, + "loss": 3.65, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830658237915883e-05, + "loss": 3.6281, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.82981964316483e-05, + "loss": 3.6418, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828981048413778e-05, + "loss": 3.6255, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828142453662726e-05, + "loss": 3.6414, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827305496792047e-05, + "loss": 3.6335, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826466902040995e-05, + "loss": 3.6485, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825628307289943e-05, + "loss": 3.6432, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824789712538892e-05, + "loss": 3.6323, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823952755668213e-05, + "loss": 3.6295, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823114160917161e-05, + "loss": 3.6317, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822275566166109e-05, + "loss": 3.6368, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821436971415057e-05, + "loss": 3.6397, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8206000145443776e-05, + "loss": 3.6333, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8197614197933256e-05, + "loss": 3.629, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8189228250422736e-05, + "loss": 3.632, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8180842302912216e-05, + "loss": 3.6292, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8172472734205425e-05, + "loss": 3.6341, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8164086786694905e-05, + "loss": 3.6332, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155700839184385e-05, + "loss": 3.6303, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814731489167387e-05, + "loss": 3.6405, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813894532296708e-05, + "loss": 3.6424, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813055937545656e-05, + "loss": 3.6403, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812217342794604e-05, + "loss": 3.6388, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811378748043552e-05, + "loss": 3.633, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.6408, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809703196421821e-05, + "loss": 3.6303, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808864601670769e-05, + "loss": 3.642, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808026006919717e-05, + "loss": 3.6441, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807189050049038e-05, + "loss": 3.6415, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806350455297986e-05, + "loss": 3.6252, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805511860546934e-05, + "loss": 3.6291, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046732657958826e-05, + "loss": 3.6178, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6423, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029977141741515e-05, + "loss": 3.6353, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021591194230995e-05, + "loss": 3.634, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013205246720475e-05, + "loss": 3.636, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8004835678013684e-05, + "loss": 3.6397, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.6257, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7988063782992644e-05, + "loss": 3.628, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979677835482124e-05, + "loss": 3.6417, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797130826677533e-05, + "loss": 3.6232, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796292231926481e-05, + "loss": 3.6268, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795453637175429e-05, + "loss": 3.6252, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794615042424377e-05, + "loss": 3.6314, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793778085553699e-05, + "loss": 3.6451, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792939490802647e-05, + "loss": 3.6272, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792100896051595e-05, + "loss": 3.6343, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791262301300543e-05, + "loss": 3.6284, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790425344429864e-05, + "loss": 3.6351, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789586749678812e-05, + "loss": 3.6329, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.78874815492776e-05, + "loss": 3.6299, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787909560176708e-05, + "loss": 3.6336, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870726033060286e-05, + "loss": 3.6207, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862340085549766e-05, + "loss": 3.6228, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853954138039246e-05, + "loss": 3.629, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6287, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783719862182194e-05, + "loss": 3.6238, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782881267431142e-05, + "loss": 3.6347, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.78204267268009e-05, + "loss": 3.6082, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781204077929038e-05, + "loss": 3.6306, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780367121058359e-05, + "loss": 3.6356, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779528526307307e-05, + "loss": 3.6333, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778689931556255e-05, + "loss": 3.6233, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777851336805203e-05, + "loss": 3.6222, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777014379934524e-05, + "loss": 3.6218, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776175785183472e-05, + "loss": 3.6318, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7753388283127936e-05, + "loss": 3.6315, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7745002335617416e-05, + "loss": 3.6326, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736616388106896e-05, + "loss": 3.6166, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.7728230440596376e-05, + "loss": 3.6374, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719844493085856e-05, + "loss": 3.6257, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7711458545575336e-05, + "loss": 3.6233, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7703072598064816e-05, + "loss": 3.6244, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7694686650554296e-05, + "loss": 3.6313, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7686317081847505e-05, + "loss": 3.6264, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677931134336985e-05, + "loss": 3.6325, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669545186826465e-05, + "loss": 3.6206, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661159239315945e-05, + "loss": 3.6255, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652789670609154e-05, + "loss": 3.6371, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644403723098634e-05, + "loss": 3.6255, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763601777558812e-05, + "loss": 3.6265, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.76276318280776e-05, + "loss": 3.6325, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761926225937081e-05, + "loss": 3.6188, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761087631186029e-05, + "loss": 3.6227, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760249036434977e-05, + "loss": 3.6265, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759410441683925e-05, + "loss": 3.6322, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758573484813246e-05, + "loss": 3.6421, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757734890062194e-05, + "loss": 3.6242, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756896295311142e-05, + "loss": 3.6279, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.75605770056009e-05, + "loss": 3.6267, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755220743689411e-05, + "loss": 3.6256, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754382148938359e-05, + "loss": 3.6309, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535435541873074e-05, + "loss": 3.6353, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7527049594362554e-05, + "loss": 3.6362, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751868002565576e-05, + "loss": 3.6218, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751029407814524e-05, + "loss": 3.63, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.897984266281128, + "eval_runtime": 578.1247, + "eval_samples_per_second": 660.05, + "eval_steps_per_second": 20.627, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.750190813063472e-05, + "loss": 3.6407, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74935221831242e-05, + "loss": 3.6345, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485136235613676e-05, + "loss": 3.6286, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476750288103156e-05, + "loss": 3.6216, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746838071939637e-05, + "loss": 3.6244, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459994771885845e-05, + "loss": 3.6226, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451608824375325e-05, + "loss": 3.6261, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744322287686481e-05, + "loss": 3.6061, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743485330815803e-05, + "loss": 3.6205, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.74264673606475e-05, + "loss": 3.6378, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741809779194072e-05, + "loss": 3.6244, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74097118444302e-05, + "loss": 3.6192, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740132589691968e-05, + "loss": 3.6308, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739293994940915e-05, + "loss": 3.6164, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738455400189863e-05, + "loss": 3.6269, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737616805438811e-05, + "loss": 3.6017, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736778210687759e-05, + "loss": 3.6036, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735939615936707e-05, + "loss": 3.6258, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735102659066028e-05, + "loss": 3.6151, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342640643149765e-05, + "loss": 3.6387, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334254695639245e-05, + "loss": 3.6153, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325868748128725e-05, + "loss": 3.6332, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317499179421934e-05, + "loss": 3.6202, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309113231911414e-05, + "loss": 3.6208, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300727284400894e-05, + "loss": 3.6118, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6201, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283971768183583e-05, + "loss": 3.621, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727558582067306e-05, + "loss": 3.624, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726719987316254e-05, + "loss": 3.6113, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725881392565202e-05, + "loss": 3.6155, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725044435694523e-05, + "loss": 3.5986, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724205840943472e-05, + "loss": 3.6268, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72336724619242e-05, + "loss": 3.6207, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722530289321741e-05, + "loss": 3.6186, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721691694570689e-05, + "loss": 3.6207, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720853099819637e-05, + "loss": 3.6232, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720014505068585e-05, + "loss": 3.6203, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719177548197906e-05, + "loss": 3.6204, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718338953446854e-05, + "loss": 3.6188, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717500358695802e-05, + "loss": 3.6159, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71666176394475e-05, + "loss": 3.6189, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158248070740706e-05, + "loss": 3.6135, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149862123230186e-05, + "loss": 3.6189, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714147617571967e-05, + "loss": 3.6217, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713309022820915e-05, + "loss": 3.6204, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712472065950236e-05, + "loss": 3.6217, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711633471199184e-05, + "loss": 3.6078, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710794876448132e-05, + "loss": 3.6267, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.70995628169708e-05, + "loss": 3.6131, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709119324826401e-05, + "loss": 3.611, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708280730075349e-05, + "loss": 3.612, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707442135324297e-05, + "loss": 3.6098, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706603540573245e-05, + "loss": 3.6231, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705766583702566e-05, + "loss": 3.6085, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704927988951514e-05, + "loss": 3.6158, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704089394200462e-05, + "loss": 3.6032, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032507994494106e-05, + "loss": 3.6199, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024138425787316e-05, + "loss": 3.6098, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015752478276795e-05, + "loss": 3.6233, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007366530766275e-05, + "loss": 3.6206, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998980583255755e-05, + "loss": 3.6127, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990611014548964e-05, + "loss": 3.6088, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982225067038444e-05, + "loss": 3.6047, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973839119527924e-05, + "loss": 3.6125, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965453172017404e-05, + "loss": 3.6195, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957083603310613e-05, + "loss": 3.6137, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948697655800093e-05, + "loss": 3.6054, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694031170828957e-05, + "loss": 3.608, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693192576077906e-05, + "loss": 3.6078, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692355619207227e-05, + "loss": 3.6114, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691517024456175e-05, + "loss": 3.6104, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690678429705123e-05, + "loss": 3.6096, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689839834954071e-05, + "loss": 3.6124, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689002878083392e-05, + "loss": 3.6198, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.68816428333234e-05, + "loss": 3.6178, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687325688581288e-05, + "loss": 3.6132, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686487093830236e-05, + "loss": 3.6116, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685650136959557e-05, + "loss": 3.6179, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684811542208505e-05, + "loss": 3.6116, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683972947457453e-05, + "loss": 3.618, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831343527064014e-05, + "loss": 3.6227, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682297395835722e-05, + "loss": 3.6197, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.68145880108467e-05, + "loss": 3.6047, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680620206333618e-05, + "loss": 3.6029, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679781611582566e-05, + "loss": 3.597, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678944654711887e-05, + "loss": 3.619, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678106059960835e-05, + "loss": 3.6105, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677267465209783e-05, + "loss": 3.6153, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676428870458731e-05, + "loss": 3.613, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675591913588052e-05, + "loss": 3.6164, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674753318837e-05, + "loss": 3.6045, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673914724085948e-05, + "loss": 3.6047, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673076129334897e-05, + "loss": 3.6173, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722391724642177e-05, + "loss": 3.6014, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714005777131656e-05, + "loss": 3.603, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705619829621136e-05, + "loss": 3.6025, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697233882110616e-05, + "loss": 3.6133, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688864313403825e-05, + "loss": 3.617, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680478365893305e-05, + "loss": 3.6105, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672092418382785e-05, + "loss": 3.613, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663706470872265e-05, + "loss": 3.6055, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655336902165474e-05, + "loss": 3.6136, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646950954654954e-05, + "loss": 3.6091, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638565007144434e-05, + "loss": 3.6118, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663017905963392e-05, + "loss": 3.6097, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662180949092713e-05, + "loss": 3.5969, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661342354341661e-05, + "loss": 3.601, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660503759590609e-05, + "loss": 3.6095, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659665164839557e-05, + "loss": 3.6077, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658828207968878e-05, + "loss": 3.6012, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657989613217826e-05, + "loss": 3.613, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657151018466774e-05, + "loss": 3.5905, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656312423715722e-05, + "loss": 3.6041, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655475466845043e-05, + "loss": 3.6113, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654636872093991e-05, + "loss": 3.6142, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653798277342939e-05, + "loss": 3.601, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529596825918875e-05, + "loss": 3.6038, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521227257212084e-05, + "loss": 3.5969, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512841309701564e-05, + "loss": 3.6092, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650447174099477e-05, + "loss": 3.6117, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649608579348425e-05, + "loss": 3.6089, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648769984597373e-05, + "loss": 3.5967, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647931389846321e-05, + "loss": 3.6125, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647092795095269e-05, + "loss": 3.6055, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646254200344217e-05, + "loss": 3.6015, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454156055931646e-05, + "loss": 3.5988, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445770108421126e-05, + "loss": 3.6132, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643740053971434e-05, + "loss": 3.6037, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642901459220382e-05, + "loss": 3.6097, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.64206286446933e-05, + "loss": 3.6006, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641224269718278e-05, + "loss": 3.6017, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403873128476e-05, + "loss": 3.6117, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639548718096547e-05, + "loss": 3.6078, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638710123345495e-05, + "loss": 3.6048, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637871528594443e-05, + "loss": 3.6137, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370345717237646e-05, + "loss": 3.5969, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636195976972712e-05, + "loss": 3.5983, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63535738222166e-05, + "loss": 3.6053, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634518787470608e-05, + "loss": 3.6133, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336818305999295e-05, + "loss": 3.6205, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328432358488775e-05, + "loss": 3.6039, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320046410978255e-05, + "loss": 3.6066, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311660463467735e-05, + "loss": 3.6032, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303290894760944e-05, + "loss": 3.6046, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294904947250424e-05, + "loss": 3.6082, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286518999739904e-05, + "loss": 3.6131, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278133052229384e-05, + "loss": 3.6179, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626976348352259e-05, + "loss": 3.5994, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626137753601207e-05, + "loss": 3.6086, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8966124057769775, + "eval_runtime": 330.182, + "eval_samples_per_second": 1155.699, + "eval_steps_per_second": 36.116, + "step": 839509 + }, + { + "epoch": 1.0, + "learning_rate": 3.625299158850155e-05, + "loss": 3.607, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624460564099103e-05, + "loss": 3.615, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623623607228425e-05, + "loss": 3.6052, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622785012477373e-05, + "loss": 3.6021, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621946417726321e-05, + "loss": 3.6048, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621107822975269e-05, + "loss": 3.6009, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.62027086610459e-05, + "loss": 3.6039, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619432271353538e-05, + "loss": 3.5869, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618593676602486e-05, + "loss": 3.6016, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617755081851434e-05, + "loss": 3.6141, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616918124980755e-05, + "loss": 3.601, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616079530229703e-05, + "loss": 3.5975, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615240935478651e-05, + "loss": 3.6119, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614402340727599e-05, + "loss": 3.5965, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613563745976547e-05, + "loss": 3.6023, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127251512254953e-05, + "loss": 3.5846, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118865564744433e-05, + "loss": 3.5784, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110479617233913e-05, + "loss": 3.6076, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610211004852712e-05, + "loss": 3.5931, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.60937241010166e-05, + "loss": 3.6146, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608533815350608e-05, + "loss": 3.5978, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607695220599556e-05, + "loss": 3.6069, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606858263728877e-05, + "loss": 3.5967, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606019668977825e-05, + "loss": 3.6058, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605181074226773e-05, + "loss": 3.5871, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604342479475721e-05, + "loss": 3.6002, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603505522605042e-05, + "loss": 3.5998, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602666927853991e-05, + "loss": 3.6011, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601828333102939e-05, + "loss": 3.5889, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600989738351887e-05, + "loss": 3.5949, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001527814812076e-05, + "loss": 3.5787, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5993141867301556e-05, + "loss": 3.6014, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984755919791036e-05, + "loss": 3.602, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976369972280516e-05, + "loss": 3.5969, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5968000403573725e-05, + "loss": 3.598, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959614456063205e-05, + "loss": 3.6057, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5951228508552685e-05, + "loss": 3.5952, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942858939845894e-05, + "loss": 3.6004, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934472992335374e-05, + "loss": 3.5982, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592608704482486e-05, + "loss": 3.5981, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591770109731434e-05, + "loss": 3.5969, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590933152860755e-05, + "loss": 3.5883, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590094558109703e-05, + "loss": 3.5983, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589255963358651e-05, + "loss": 3.6014, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588417368607599e-05, + "loss": 3.599, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.58758041173692e-05, + "loss": 3.5987, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586741816985868e-05, + "loss": 3.5895, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585903222234816e-05, + "loss": 3.6077, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585064627483764e-05, + "loss": 3.5938, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584227670613085e-05, + "loss": 3.5885, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583389075862033e-05, + "loss": 3.586, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825504811109814e-05, + "loss": 3.5933, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817118863599294e-05, + "loss": 3.601, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808749294892504e-05, + "loss": 3.5878, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800363347381984e-05, + "loss": 3.5962, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791977399871463e-05, + "loss": 3.5826, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783591452360943e-05, + "loss": 3.5998, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577522188365415e-05, + "loss": 3.594, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576683593614363e-05, + "loss": 3.6007, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575844998863311e-05, + "loss": 3.5967, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575006404112259e-05, + "loss": 3.5917, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.57416944724158e-05, + "loss": 3.5884, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573330852490528e-05, + "loss": 3.5858, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572492257739477e-05, + "loss": 3.5904, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571653662988425e-05, + "loss": 3.6013, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570816706117746e-05, + "loss": 3.5939, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699797492470666e-05, + "loss": 3.5798, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691411544960146e-05, + "loss": 3.5891, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5683025597449626e-05, + "loss": 3.588, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674639649939106e-05, + "loss": 3.5911, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666253702428586e-05, + "loss": 3.5856, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657867754918066e-05, + "loss": 3.5933, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649481807407546e-05, + "loss": 3.5908, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564109585989702e-05, + "loss": 3.5968, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632726291190235e-05, + "loss": 3.5991, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562434034367972e-05, + "loss": 3.5965, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.56159543961692e-05, + "loss": 3.5859, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607568448658675e-05, + "loss": 3.5951, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559919887995189e-05, + "loss": 3.5887, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559081293244137e-05, + "loss": 3.6035, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582426984930844e-05, + "loss": 3.5997, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574041037420324e-05, + "loss": 3.6029, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556567146871354e-05, + "loss": 3.5844, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555728552120302e-05, + "loss": 3.5843, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554889957369249e-05, + "loss": 3.5769, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554051362618197e-05, + "loss": 3.5971, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553214405747519e-05, + "loss": 3.59, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552375810996467e-05, + "loss": 3.5932, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551537216245415e-05, + "loss": 3.5942, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5507002593747365e-05, + "loss": 3.5974, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498616646236845e-05, + "loss": 3.5811, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549023069872632e-05, + "loss": 3.5881, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.54818447512158e-05, + "loss": 3.5943, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473475182509014e-05, + "loss": 3.5825, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5465089234998493e-05, + "loss": 3.5785, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545670328748797e-05, + "loss": 3.5852, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448317339977447e-05, + "loss": 3.5949, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543994777127066e-05, + "loss": 3.5943, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543156182376014e-05, + "loss": 3.5919, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542317587624962e-05, + "loss": 3.5946, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.54147899287391e-05, + "loss": 3.5839, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540642036003232e-05, + "loss": 3.5919, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539803441252179e-05, + "loss": 3.5925, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538964846501127e-05, + "loss": 3.5871, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538126251750075e-05, + "loss": 3.5864, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537289294879397e-05, + "loss": 3.5827, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536450700128344e-05, + "loss": 3.5816, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535612105377292e-05, + "loss": 3.584, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.53477351062624e-05, + "loss": 3.5861, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339365537555616e-05, + "loss": 3.5821, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330979590045096e-05, + "loss": 3.5911, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322593642534576e-05, + "loss": 3.5732, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314207695024056e-05, + "loss": 3.5819, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305838126317265e-05, + "loss": 3.5912, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297452178806745e-05, + "loss": 3.5953, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5289066231296225e-05, + "loss": 3.58, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280680283785705e-05, + "loss": 3.5844, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272310715078914e-05, + "loss": 3.5795, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263924767568394e-05, + "loss": 3.5869, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255538820057874e-05, + "loss": 3.5915, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524716925135109e-05, + "loss": 3.5885, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523878330384057e-05, + "loss": 3.5768, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523039735633005e-05, + "loss": 3.5931, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522201140881953e-05, + "loss": 3.5845, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521362546130901e-05, + "loss": 3.587, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520523951379849e-05, + "loss": 3.577, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519685356628797e-05, + "loss": 3.5919, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518848399758118e-05, + "loss": 3.5831, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.518009805007066e-05, + "loss": 3.5893, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517171210256014e-05, + "loss": 3.581, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516332615504962e-05, + "loss": 3.5828, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515495658634283e-05, + "loss": 3.5891, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514657063883231e-05, + "loss": 3.5916, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513818469132179e-05, + "loss": 3.5822, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512979874381127e-05, + "loss": 3.592, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121429175104483e-05, + "loss": 3.5794, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511304322759396e-05, + "loss": 3.5804, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510465728008344e-05, + "loss": 3.5859, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509627133257292e-05, + "loss": 3.5901, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508790176386613e-05, + "loss": 3.6014, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507951581635561e-05, + "loss": 3.5868, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507112986884509e-05, + "loss": 3.5871, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506274392133457e-05, + "loss": 3.5844, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505437435262778e-05, + "loss": 3.5817, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504598840511726e-05, + "loss": 3.5906, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503760245760674e-05, + "loss": 3.5962, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502921651009622e-05, + "loss": 3.5976, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502084694138944e-05, + "loss": 3.5796, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501246099387892e-05, + "loss": 3.5902, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.897824764251709, + "eval_runtime": 316.0109, + "eval_samples_per_second": 1207.525, + "eval_steps_per_second": 37.736, + "step": 915828 + }, + { + "epoch": 0.0, + "learning_rate": 3.50040750463684e-05, + "loss": 3.5939, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499568909885788e-05, + "loss": 3.5881, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498730315134736e-05, + "loss": 3.5913, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497891720383684e-05, + "loss": 3.5914, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970547635130046e-05, + "loss": 3.5994, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4962161687619526e-05, + "loss": 3.5893, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953775740109006e-05, + "loss": 3.5844, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945389792598486e-05, + "loss": 3.5876, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4937020223891695e-05, + "loss": 3.5872, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928634276381175e-05, + "loss": 3.588, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492024832887066e-05, + "loss": 3.5903, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491186238136014e-05, + "loss": 3.5897, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490350919145708e-05, + "loss": 3.5966, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489512324394656e-05, + "loss": 3.5782, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488673729643604e-05, + "loss": 3.5834, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487835134892552e-05, + "loss": 3.577, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869965401415e-05, + "loss": 3.5784, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486157945390448e-05, + "loss": 3.5818, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485319350639396e-05, + "loss": 3.5775, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484480755888344e-05, + "loss": 3.5987, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483643799017665e-05, + "loss": 3.5971, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482805204266613e-05, + "loss": 3.5849, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819666095155615e-05, + "loss": 3.586, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811280147645095e-05, + "loss": 3.5878, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4802910578938304e-05, + "loss": 3.5746, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794524631427784e-05, + "loss": 3.5934, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786138683917264e-05, + "loss": 3.5804, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777752736406744e-05, + "loss": 3.5682, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476938316769995e-05, + "loss": 3.5844, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476099722018943e-05, + "loss": 3.5765, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475261127267891e-05, + "loss": 3.5829, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474422532516839e-05, + "loss": 3.5814, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.47358557564616e-05, + "loss": 3.589, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472746980895108e-05, + "loss": 3.5853, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471908386144057e-05, + "loss": 3.5801, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471069791393005e-05, + "loss": 3.5899, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470232834522326e-05, + "loss": 3.5893, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469394239771274e-05, + "loss": 3.5793, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468555645020222e-05, + "loss": 3.5778, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467717050269169e-05, + "loss": 3.5794, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466880093398491e-05, + "loss": 3.5737, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466041498647439e-05, + "loss": 3.585, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465202903896387e-05, + "loss": 3.5862, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464364309145334e-05, + "loss": 3.5911, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635273522746556e-05, + "loss": 3.5846, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626887575236036e-05, + "loss": 3.5816, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618501627725516e-05, + "loss": 3.5861, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610115680214996e-05, + "loss": 3.5838, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460174611150821e-05, + "loss": 3.5596, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459336016399769e-05, + "loss": 3.5897, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584974216487165e-05, + "loss": 3.5767, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576588268976645e-05, + "loss": 3.5893, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456821870026986e-05, + "loss": 3.5823, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455983275275934e-05, + "loss": 3.5805, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551446805248814e-05, + "loss": 3.5674, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543060857738294e-05, + "loss": 3.5762, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453469128903151e-05, + "loss": 3.5981, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452630534152099e-05, + "loss": 3.5799, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451791939401047e-05, + "loss": 3.5913, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509549825303685e-05, + "loss": 3.5775, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4501163877793165e-05, + "loss": 3.5597, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449277793028264e-05, + "loss": 3.5999, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448439198277212e-05, + "loss": 3.5763, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4476022414065334e-05, + "loss": 3.5683, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467636466554814e-05, + "loss": 3.5813, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445925051904429e-05, + "loss": 3.5773, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445086457153377e-05, + "loss": 3.5726, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444249500282698e-05, + "loss": 3.5703, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443410905531646e-05, + "loss": 3.5662, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442572310780594e-05, + "loss": 3.576, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441733716029542e-05, + "loss": 3.5849, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440896759158864e-05, + "loss": 3.5788, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440058164407811e-05, + "loss": 3.5808, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439219569656759e-05, + "loss": 3.5674, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438380974905707e-05, + "loss": 3.5882, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437544018035029e-05, + "loss": 3.5824, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436705423283976e-05, + "loss": 3.5895, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435866828532924e-05, + "loss": 3.5723, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435028233781872e-05, + "loss": 3.574, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434191276911194e-05, + "loss": 3.5859, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433352682160142e-05, + "loss": 3.5894, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43251408740909e-05, + "loss": 3.5779, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431675492658038e-05, + "loss": 3.5829, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308385357873586e-05, + "loss": 3.5665, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299999410363066e-05, + "loss": 3.5754, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291613462852546e-05, + "loss": 3.5764, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4283227515342026e-05, + "loss": 3.5866, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274857946635235e-05, + "loss": 3.5699, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266471999124715e-05, + "loss": 3.5753, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258086051614195e-05, + "loss": 3.5777, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249700104103675e-05, + "loss": 3.577, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241330535396884e-05, + "loss": 3.5784, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423294458788637e-05, + "loss": 3.5699, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422455864037585e-05, + "loss": 3.5765, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421617269286533e-05, + "loss": 3.5872, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420780312415854e-05, + "loss": 3.586, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419941717664802e-05, + "loss": 3.5527, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41910312291375e-05, + "loss": 3.5721, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418264528162698e-05, + "loss": 3.5723, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417427571292019e-05, + "loss": 3.5843, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416588976540967e-05, + "loss": 3.5839, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415750381789915e-05, + "loss": 3.5736, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414911787038863e-05, + "loss": 3.568, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414074830168184e-05, + "loss": 3.5764, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413237873297505e-05, + "loss": 3.571, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412399278546453e-05, + "loss": 3.5738, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411560683795401e-05, + "loss": 3.5658, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410722089044349e-05, + "loss": 3.5785, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409883494293297e-05, + "loss": 3.5712, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409044899542245e-05, + "loss": 3.5584, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408206304791193e-05, + "loss": 3.5652, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407367710040141e-05, + "loss": 3.5649, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406530753169462e-05, + "loss": 3.5794, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.40569215841841e-05, + "loss": 3.5697, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404853563667358e-05, + "loss": 3.5781, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404014968916306e-05, + "loss": 3.5727, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403178012045628e-05, + "loss": 3.5727, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402341055174949e-05, + "loss": 3.5775, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401502460423897e-05, + "loss": 3.5742, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400663865672845e-05, + "loss": 3.5746, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399825270921793e-05, + "loss": 3.5677, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398986676170741e-05, + "loss": 3.5637, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398148081419689e-05, + "loss": 3.5761, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397309486668637e-05, + "loss": 3.5695, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396470891917585e-05, + "loss": 3.5735, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956339350469056e-05, + "loss": 3.5692, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947953402958536e-05, + "loss": 3.5705, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939567455448016e-05, + "loss": 3.5716, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931181507937496e-05, + "loss": 3.563, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392281193923071e-05, + "loss": 3.5752, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391442599172019e-05, + "loss": 3.5711, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390604004420967e-05, + "loss": 3.5839, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389765409669915e-05, + "loss": 3.5639, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388928452799236e-05, + "loss": 3.5724, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388089858048184e-05, + "loss": 3.5763, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387251263297132e-05, + "loss": 3.5656, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.38641266854608e-05, + "loss": 3.573, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385575711675401e-05, + "loss": 3.5718, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384737116924349e-05, + "loss": 3.5793, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383898522173297e-05, + "loss": 3.579, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830615653026185e-05, + "loss": 3.5759, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822229705515665e-05, + "loss": 3.5653, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813843758005145e-05, + "loss": 3.5742, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805457810494625e-05, + "loss": 3.5784, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3797088241787834e-05, + "loss": 3.561, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788702294277314e-05, + "loss": 3.5876, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780316346766794e-05, + "loss": 3.5665, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771930399256274e-05, + "loss": 3.5766, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763544451745754e-05, + "loss": 3.5709, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8915772438049316, + "eval_runtime": 308.5538, + "eval_samples_per_second": 1236.708, + "eval_steps_per_second": 38.648, + "step": 992148 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755158504235234e-05, + "loss": 3.5733, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746772556724714e-05, + "loss": 3.5674, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373838660921419e-05, + "loss": 3.5688, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.37300170405074e-05, + "loss": 3.5748, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372163109299688e-05, + "loss": 3.5754, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371324514548636e-05, + "loss": 3.5709, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370485919797584e-05, + "loss": 3.5633, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369648962926906e-05, + "loss": 3.5646, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368810368175854e-05, + "loss": 3.568, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367971773424802e-05, + "loss": 3.5697, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367133178673749e-05, + "loss": 3.5701, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366296221803071e-05, + "loss": 3.5727, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365459264932392e-05, + "loss": 3.5748, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36462067018134e-05, + "loss": 3.5551, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363782075430288e-05, + "loss": 3.5651, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362943480679236e-05, + "loss": 3.5564, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3621048859281837e-05, + "loss": 3.5513, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612662911771317e-05, + "loss": 3.5682, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3604276964260797e-05, + "loss": 3.5553, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595891016750276e-05, + "loss": 3.5753, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587521448043486e-05, + "loss": 3.5789, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3579135500532966e-05, + "loss": 3.5674, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570749553022445e-05, + "loss": 3.5657, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562363605511925e-05, + "loss": 3.5686, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553994036805135e-05, + "loss": 3.5513, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545608089294614e-05, + "loss": 3.5758, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537222141784094e-05, + "loss": 3.5601, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528836194273574e-05, + "loss": 3.5563, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352046662556679e-05, + "loss": 3.5612, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351208067805627e-05, + "loss": 3.5552, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350369473054575e-05, + "loss": 3.5631, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349530878303523e-05, + "loss": 3.5625, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348693921432844e-05, + "loss": 3.5694, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347855326681792e-05, + "loss": 3.5648, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.34701673193074e-05, + "loss": 3.5591, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346178137179688e-05, + "loss": 3.5614, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345341180309009e-05, + "loss": 3.5713, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344502585557957e-05, + "loss": 3.5599, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343663990806905e-05, + "loss": 3.5598, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342825396055853e-05, + "loss": 3.5592, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419884391851744e-05, + "loss": 3.5627, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411498444341224e-05, + "loss": 3.5594, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403112496830704e-05, + "loss": 3.567, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394726549320184e-05, + "loss": 3.5723, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338635698061339e-05, + "loss": 3.566, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337797103310287e-05, + "loss": 3.5628, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336958508559235e-05, + "loss": 3.5621, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336119913808183e-05, + "loss": 3.567, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335282956937504e-05, + "loss": 3.5405, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334444362186452e-05, + "loss": 3.5675, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3336057674354e-05, + "loss": 3.5589, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332768810564722e-05, + "loss": 3.5677, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.33193021581367e-05, + "loss": 3.5615, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331091621062618e-05, + "loss": 3.5586, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330253026311566e-05, + "loss": 3.5517, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329416069440887e-05, + "loss": 3.5542, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285774746898347e-05, + "loss": 3.579, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277388799387827e-05, + "loss": 3.5563, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3269002851877306e-05, + "loss": 3.5759, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260633283170516e-05, + "loss": 3.559, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252247335659996e-05, + "loss": 3.5441, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243861388149475e-05, + "loss": 3.5783, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235475440638955e-05, + "loss": 3.5591, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322710587193217e-05, + "loss": 3.5439, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321871992442165e-05, + "loss": 3.5575, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321033397691113e-05, + "loss": 3.5599, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320194802940061e-05, + "loss": 3.5516, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319357846069382e-05, + "loss": 3.5528, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.31851925131833e-05, + "loss": 3.5499, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317680656567278e-05, + "loss": 3.5478, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316842061816226e-05, + "loss": 3.5666, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.316005104945547e-05, + "loss": 3.5628, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315166510194495e-05, + "loss": 3.5594, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314327915443443e-05, + "loss": 3.5479, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313489320692391e-05, + "loss": 3.567, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126523638217125e-05, + "loss": 3.5601, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3118137690706605e-05, + "loss": 3.5725, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109751743196085e-05, + "loss": 3.5534, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101365795685565e-05, + "loss": 3.5561, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092996226978774e-05, + "loss": 3.5651, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084610279468254e-05, + "loss": 3.5665, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3076224331957734e-05, + "loss": 3.5616, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067838384447214e-05, + "loss": 3.5648, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059452436936694e-05, + "loss": 3.5497, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3051066489426174e-05, + "loss": 3.5521, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042680541915654e-05, + "loss": 3.5586, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034294594405134e-05, + "loss": 3.5643, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302592502569834e-05, + "loss": 3.5576, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301753907818782e-05, + "loss": 3.5523, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300915313067731e-05, + "loss": 3.557, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300076718316679e-05, + "loss": 3.5605, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299239761446e-05, + "loss": 3.5528, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298401166694948e-05, + "loss": 3.555, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297562571943896e-05, + "loss": 3.5574, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296723977192844e-05, + "loss": 3.5658, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295887020322165e-05, + "loss": 3.5663, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295048425571113e-05, + "loss": 3.5359, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294209830820061e-05, + "loss": 3.5507, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293371236069009e-05, + "loss": 3.5516, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925342791983296e-05, + "loss": 3.5664, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916956844472776e-05, + "loss": 3.5637, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908570896962256e-05, + "loss": 3.5585, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290018494945174e-05, + "loss": 3.5459, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289181538074495e-05, + "loss": 3.5619, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288342943323443e-05, + "loss": 3.552, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287504348572391e-05, + "loss": 3.5545, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286665753821339e-05, + "loss": 3.547, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.28582879695066e-05, + "loss": 3.5566, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284990202199608e-05, + "loss": 3.555, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284151607448556e-05, + "loss": 3.5399, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833130126975034e-05, + "loss": 3.5489, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282476055826825e-05, + "loss": 3.5424, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281637461075773e-05, + "loss": 3.5612, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280798866324721e-05, + "loss": 3.5508, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799619094540426e-05, + "loss": 3.5561, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791233147029906e-05, + "loss": 3.5552, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782847199519386e-05, + "loss": 3.5552, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774477630812595e-05, + "loss": 3.5541, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2766091683302075e-05, + "loss": 3.5572, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757705735791555e-05, + "loss": 3.5593, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749319788281035e-05, + "loss": 3.5465, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274093384077051e-05, + "loss": 3.545, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273254789325999e-05, + "loss": 3.5581, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272416194574947e-05, + "loss": 3.5528, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271577599823895e-05, + "loss": 3.5536, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707406429532164e-05, + "loss": 3.5468, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2699020482021644e-05, + "loss": 3.5552, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690634534511124e-05, + "loss": 3.5553, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268226496580434e-05, + "loss": 3.5456, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267387901829381e-05, + "loss": 3.5477, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266549307078329e-05, + "loss": 3.5568, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265710712327277e-05, + "loss": 3.5685, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264872117576225e-05, + "loss": 3.546, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264033522825173e-05, + "loss": 3.5487, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263194928074121e-05, + "loss": 3.5617, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262356333323069e-05, + "loss": 3.5486, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.26151937645239e-05, + "loss": 3.5512, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260680781701339e-05, + "loss": 3.5505, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259842186950287e-05, + "loss": 3.5613, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.259003592199235e-05, + "loss": 3.5611, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258166635328556e-05, + "loss": 3.5541, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257328040577504e-05, + "loss": 3.5473, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256489445826452e-05, + "loss": 3.5544, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556508510754e-05, + "loss": 3.5584, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2548155320850935e-05, + "loss": 3.5461, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539769373340415e-05, + "loss": 3.5686, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531383425829895e-05, + "loss": 3.5489, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522997478319375e-05, + "loss": 3.5584, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251462790961259e-05, + "loss": 3.5523, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.893230438232422, + "eval_runtime": 308.1202, + "eval_samples_per_second": 1238.448, + "eval_steps_per_second": 38.702, + "step": 1068468 + }, + { + "epoch": 0.0, + "learning_rate": 3.250624196210207e-05, + "loss": 3.5838, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249785601459155e-05, + "loss": 3.5454, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248947006708103e-05, + "loss": 3.5497, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248108411957051e-05, + "loss": 3.5585, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247271455086372e-05, + "loss": 3.5539, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.24643286033532e-05, + "loss": 3.5555, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245594265584268e-05, + "loss": 3.5474, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244755670833216e-05, + "loss": 3.5465, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243918713962537e-05, + "loss": 3.5489, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243080119211485e-05, + "loss": 3.554, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242241524460433e-05, + "loss": 3.549, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241402929709381e-05, + "loss": 3.558, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240567610719076e-05, + "loss": 3.5583, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397290159680234e-05, + "loss": 3.5359, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388904212169714e-05, + "loss": 3.5495, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380518264659194e-05, + "loss": 3.5361, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2372132317148674e-05, + "loss": 3.5351, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363746369638154e-05, + "loss": 3.5512, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355360422127634e-05, + "loss": 3.5348, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346974474617113e-05, + "loss": 3.56, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233860490591032e-05, + "loss": 3.5634, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.23302189583998e-05, + "loss": 3.5437, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232183301088928e-05, + "loss": 3.5521, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231344706337876e-05, + "loss": 3.5496, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230507749467198e-05, + "loss": 3.5355, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229669154716146e-05, + "loss": 3.553, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228830559965094e-05, + "loss": 3.5413, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227991965214042e-05, + "loss": 3.5385, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227155008343363e-05, + "loss": 3.5413, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226316413592311e-05, + "loss": 3.538, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225477818841259e-05, + "loss": 3.5435, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224639224090207e-05, + "loss": 3.5486, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2238022672195276e-05, + "loss": 3.5535, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229636724684756e-05, + "loss": 3.5437, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221250777174236e-05, + "loss": 3.5417, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212864829663716e-05, + "loss": 3.5431, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220449526095693e-05, + "loss": 3.5588, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219610931344641e-05, + "loss": 3.5391, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218772336593589e-05, + "loss": 3.5438, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217933741842537e-05, + "loss": 3.5413, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217096784971858e-05, + "loss": 3.5401, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216258190220806e-05, + "loss": 3.5415, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215419595469754e-05, + "loss": 3.5513, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214582638599075e-05, + "loss": 3.5552, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213744043848023e-05, + "loss": 3.5467, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212905449096971e-05, + "loss": 3.5441, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212066854345919e-05, + "loss": 3.5421, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211228259594867e-05, + "loss": 3.5513, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103896648438157e-05, + "loss": 3.5235, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095510700927636e-05, + "loss": 3.5495, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2087124753417116e-05, + "loss": 3.544, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078755184710326e-05, + "loss": 3.5512, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070369237199805e-05, + "loss": 3.5411, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061983289689285e-05, + "loss": 3.5399, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053597342178765e-05, + "loss": 3.5376, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2045227773471974e-05, + "loss": 3.5358, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036841825961454e-05, + "loss": 3.5566, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028455878450934e-05, + "loss": 3.5448, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2020069930940414e-05, + "loss": 3.5581, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011700362233623e-05, + "loss": 3.5397, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003314414723103e-05, + "loss": 3.529, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199492846721259e-05, + "loss": 3.5599, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198654251970206e-05, + "loss": 3.5367, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197818932979901e-05, + "loss": 3.5305, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196980338228849e-05, + "loss": 3.5401, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196141743477797e-05, + "loss": 3.5418, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195303148726745e-05, + "loss": 3.5332, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194464553975693e-05, + "loss": 3.5372, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193625959224641e-05, + "loss": 3.5307, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192787364473589e-05, + "loss": 3.5307, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191948769722536e-05, + "loss": 3.5497, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191111812851858e-05, + "loss": 3.546, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190273218100806e-05, + "loss": 3.5419, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189434623349754e-05, + "loss": 3.5314, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188596028598702e-05, + "loss": 3.5515, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187759071728023e-05, + "loss": 3.5451, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186922114857344e-05, + "loss": 3.5519, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186083520106292e-05, + "loss": 3.5387, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.18524492535524e-05, + "loss": 3.5372, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184406330604188e-05, + "loss": 3.547, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183567735853136e-05, + "loss": 3.5488, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827291411020835e-05, + "loss": 3.5452, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818905463510315e-05, + "loss": 3.5479, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810519515999795e-05, + "loss": 3.5392, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180214994729301e-05, + "loss": 3.5303, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179376399978249e-05, + "loss": 3.542, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178537805227197e-05, + "loss": 3.5494, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177699210476145e-05, + "loss": 3.5375, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176862253605466e-05, + "loss": 3.5366, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176023658854414e-05, + "loss": 3.5369, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175185064103362e-05, + "loss": 3.5426, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.17434646935231e-05, + "loss": 3.5362, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173509512481631e-05, + "loss": 3.5391, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172670917730579e-05, + "loss": 3.5442, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171832322979527e-05, + "loss": 3.5457, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170993728228475e-05, + "loss": 3.5516, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701567713577964e-05, + "loss": 3.5164, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693181766067444e-05, + "loss": 3.5363, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684795818556924e-05, + "loss": 3.5368, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676426249850133e-05, + "loss": 3.5466, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166804030233961e-05, + "loss": 3.5461, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165965435482909e-05, + "loss": 3.5395, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165126840731857e-05, + "loss": 3.5283, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164289883861178e-05, + "loss": 3.5436, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163451289110126e-05, + "loss": 3.5385, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162612694359074e-05, + "loss": 3.5359, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161774099608022e-05, + "loss": 3.5299, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160937142737344e-05, + "loss": 3.5363, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160098547986292e-05, + "loss": 3.54, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.15925995323524e-05, + "loss": 3.5265, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158421358484188e-05, + "loss": 3.5358, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157584401613509e-05, + "loss": 3.5232, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156745806862457e-05, + "loss": 3.5441, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155907212111405e-05, + "loss": 3.5346, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155068617360353e-05, + "loss": 3.5351, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542316604896736e-05, + "loss": 3.5409, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533930657386216e-05, + "loss": 3.5403, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525561088679425e-05, + "loss": 3.5326, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151717514116891e-05, + "loss": 3.5405, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150878919365839e-05, + "loss": 3.5426, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150040324614787e-05, + "loss": 3.5286, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149201729863735e-05, + "loss": 3.5247, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148363135112683e-05, + "loss": 3.5426, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147524540361631e-05, + "loss": 3.5374, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146685945610579e-05, + "loss": 3.5377, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458489887399e-05, + "loss": 3.5318, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145012031869221e-05, + "loss": 3.5366, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144173437118169e-05, + "loss": 3.5369, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143334842367117e-05, + "loss": 3.5273, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142496247616065e-05, + "loss": 3.5278, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141657652865013e-05, + "loss": 3.543, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140819058113961e-05, + "loss": 3.5488, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399804633629096e-05, + "loss": 3.5325, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391418686118576e-05, + "loss": 3.5321, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1383049117411785e-05, + "loss": 3.5425, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374663169901265e-05, + "loss": 3.533, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366277222390745e-05, + "loss": 3.5357, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357891274880225e-05, + "loss": 3.5355, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349521706173434e-05, + "loss": 3.5467, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341135758662914e-05, + "loss": 3.543, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332749811152394e-05, + "loss": 3.5377, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.13243802424456e-05, + "loss": 3.5305, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131599429493508e-05, + "loss": 3.5395, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130760834742456e-05, + "loss": 3.5418, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129923877871778e-05, + "loss": 3.5278, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129085283120726e-05, + "loss": 3.5516, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128246688369674e-05, + "loss": 3.5294, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127408093618622e-05, + "loss": 3.5438, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126571136747943e-05, + "loss": 3.5349, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8944196701049805, + "eval_runtime": 302.2416, + "eval_samples_per_second": 1262.537, + "eval_steps_per_second": 39.455, + "step": 1144788 + }, + { + "epoch": 1.0, + "learning_rate": 3.125732541996891e-05, + "loss": 3.5391, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124893947245839e-05, + "loss": 3.5313, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124055352494787e-05, + "loss": 3.5341, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123216757743735e-05, + "loss": 3.5397, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122379800873056e-05, + "loss": 3.54, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121541206122004e-05, + "loss": 3.5384, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120702611370952e-05, + "loss": 3.5325, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198640166199004e-05, + "loss": 3.5336, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1190254218688484e-05, + "loss": 3.532, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181868271177964e-05, + "loss": 3.5379, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173482323667443e-05, + "loss": 3.5325, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116509637615692e-05, + "loss": 3.5406, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115674318625386e-05, + "loss": 3.5448, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114835723874334e-05, + "loss": 3.5193, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113997129123282e-05, + "loss": 3.5318, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.11315853437223e-05, + "loss": 3.518, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112319939621178e-05, + "loss": 3.5216, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111481344870126e-05, + "loss": 3.5325, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110642750119074e-05, + "loss": 3.5236, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109804155368022e-05, + "loss": 3.5359, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108967198497344e-05, + "loss": 3.5481, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108128603746292e-05, + "loss": 3.5322, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107290008995239e-05, + "loss": 3.5338, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106451414244187e-05, + "loss": 3.5346, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1056144573735086e-05, + "loss": 3.5251, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104775862622456e-05, + "loss": 3.5342, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103937267871404e-05, + "loss": 3.5209, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103098673120352e-05, + "loss": 3.528, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022617162496735e-05, + "loss": 3.5263, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101423121498621e-05, + "loss": 3.5194, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100584526747569e-05, + "loss": 3.5305, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997459319965175e-05, + "loss": 3.5258, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0989089751258384e-05, + "loss": 3.5371, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980703803747864e-05, + "loss": 3.5312, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972317856237344e-05, + "loss": 3.5219, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963931908726824e-05, + "loss": 3.5272, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095556234002003e-05, + "loss": 3.547, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094717639250951e-05, + "loss": 3.5202, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093879044499899e-05, + "loss": 3.529, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093040449748847e-05, + "loss": 3.5243, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092203492878168e-05, + "loss": 3.5212, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091364898127116e-05, + "loss": 3.5247, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090526303376064e-05, + "loss": 3.5393, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089689346505386e-05, + "loss": 3.5388, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088850751754334e-05, + "loss": 3.5306, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088012157003282e-05, + "loss": 3.5295, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08717356225223e-05, + "loss": 3.5237, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086334967501178e-05, + "loss": 3.5371, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085498010630499e-05, + "loss": 3.5078, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084659415879447e-05, + "loss": 3.5312, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083820821128395e-05, + "loss": 3.5279, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829822263773427e-05, + "loss": 3.5371, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821436316262907e-05, + "loss": 3.5288, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0813050368752387e-05, + "loss": 3.5165, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804664421241866e-05, + "loss": 3.5276, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796278473731346e-05, + "loss": 3.5138, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078790890502456e-05, + "loss": 3.5458, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077952295751404e-05, + "loss": 3.5257, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077113701000352e-05, + "loss": 3.5442, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762751062493e-05, + "loss": 3.5229, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075438149378621e-05, + "loss": 3.5137, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074599554627569e-05, + "loss": 3.539, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073760959876517e-05, + "loss": 3.5189, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072924003005838e-05, + "loss": 3.5205, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072085408254786e-05, + "loss": 3.519, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071246813503734e-05, + "loss": 3.531, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070408218752682e-05, + "loss": 3.5183, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.06956962400163e-05, + "loss": 3.5195, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068731029250578e-05, + "loss": 3.5165, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067892434499527e-05, + "loss": 3.5165, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067053839748475e-05, + "loss": 3.5338, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0662168828777956e-05, + "loss": 3.5318, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653782881267436e-05, + "loss": 3.5222, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645396933756916e-05, + "loss": 3.5207, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0637010986246396e-05, + "loss": 3.5335, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628641417539605e-05, + "loss": 3.5268, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620271848832814e-05, + "loss": 3.5338, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611885901322294e-05, + "loss": 3.5251, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603499953811774e-05, + "loss": 3.521, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595114006301254e-05, + "loss": 3.5294, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586728058790734e-05, + "loss": 3.5337, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057834211128022e-05, + "loss": 3.5281, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569956163769694e-05, + "loss": 3.5325, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561570216259174e-05, + "loss": 3.5274, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055320064755239e-05, + "loss": 3.5104, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054481470004187e-05, + "loss": 3.5261, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053642875253134e-05, + "loss": 3.5301, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052805918382456e-05, + "loss": 3.5241, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051967323631404e-05, + "loss": 3.5226, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051128728880352e-05, + "loss": 3.5211, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502901341292995e-05, + "loss": 3.5265, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494515393782475e-05, + "loss": 3.5215, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486129446271955e-05, + "loss": 3.524, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477743498761435e-05, + "loss": 3.5246, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469357551250915e-05, + "loss": 3.5257, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460987982544127e-05, + "loss": 3.538, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452602035033607e-05, + "loss": 3.5042, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444216087523087e-05, + "loss": 3.5184, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435846518816296e-05, + "loss": 3.5228, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427460571305776e-05, + "loss": 3.5292, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419074623795256e-05, + "loss": 3.5313, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410688676284736e-05, + "loss": 3.5261, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040231910757795e-05, + "loss": 3.5128, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039393316006743e-05, + "loss": 3.5259, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038554721255691e-05, + "loss": 3.527, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037716126504639e-05, + "loss": 3.5167, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368791696339598e-05, + "loss": 3.5126, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036040574882908e-05, + "loss": 3.5232, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035201980131856e-05, + "loss": 3.5277, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034363385380804e-05, + "loss": 3.5047, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033526428510125e-05, + "loss": 3.522, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032687833759073e-05, + "loss": 3.5092, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031849239008021e-05, + "loss": 3.5267, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031010644256969e-05, + "loss": 3.5201, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301736873862902e-05, + "loss": 3.5193, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293350926352382e-05, + "loss": 3.5248, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284964978841862e-05, + "loss": 3.5222, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027659541013507e-05, + "loss": 3.5197, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026820946262455e-05, + "loss": 3.5256, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259823515114035e-05, + "loss": 3.5261, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251437567603515e-05, + "loss": 3.513, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243051620092994e-05, + "loss": 3.5084, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234665672582474e-05, + "loss": 3.527, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226279725071954e-05, + "loss": 3.5207, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217893777561434e-05, + "loss": 3.5256, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209524208854643e-05, + "loss": 3.5113, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201154640147856e-05, + "loss": 3.5219, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192768692637336e-05, + "loss": 3.5238, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184382745126816e-05, + "loss": 3.5125, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175996797616296e-05, + "loss": 3.5095, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167610850105776e-05, + "loss": 3.5269, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159224902595256e-05, + "loss": 3.5337, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150838955084736e-05, + "loss": 3.5171, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142453007574216e-05, + "loss": 3.5173, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134083438867428e-05, + "loss": 3.5245, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125697491356908e-05, + "loss": 3.5188, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117311543846388e-05, + "loss": 3.5185, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108925596335868e-05, + "loss": 3.5202, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010055602762908e-05, + "loss": 3.5306, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009217008011856e-05, + "loss": 3.5238, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008378413260804e-05, + "loss": 3.5225, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007539818509752e-05, + "loss": 3.5162, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006702861639073e-05, + "loss": 3.5241, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005864266888021e-05, + "loss": 3.5214, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050273100173422e-05, + "loss": 3.5118, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041887152662902e-05, + "loss": 3.5426, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033501205152382e-05, + "loss": 3.5158, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025115257641862e-05, + "loss": 3.5269, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001674568893507e-05, + "loss": 3.518, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.897891044616699, + "eval_runtime": 302.9255, + "eval_samples_per_second": 1259.686, + "eval_steps_per_second": 39.366, + "step": 1221108 + }, + { + "epoch": 0.0, + "learning_rate": 3.000835974142455e-05, + "loss": 3.4995, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999997379391403e-05, + "loss": 3.5183, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991587846403514e-05, + "loss": 3.5185, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983201898892994e-05, + "loss": 3.5286, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974832330186203e-05, + "loss": 3.5235, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966446382675683e-05, + "loss": 3.5248, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958060435165163e-05, + "loss": 3.5134, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949674487654643e-05, + "loss": 3.5187, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941304918947855e-05, + "loss": 3.5148, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932918971437335e-05, + "loss": 3.5263, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924533023926815e-05, + "loss": 3.5168, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916147076416295e-05, + "loss": 3.5262, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907793886513237e-05, + "loss": 3.529, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899407939002717e-05, + "loss": 3.5074, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891021991492197e-05, + "loss": 3.5136, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882636043981677e-05, + "loss": 3.5061, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874250096471157e-05, + "loss": 3.5056, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865864148960637e-05, + "loss": 3.5163, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857478201450117e-05, + "loss": 3.5109, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849092253939597e-05, + "loss": 3.5159, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984072268523281e-05, + "loss": 3.5359, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983233673772229e-05, + "loss": 3.5156, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982395079021177e-05, + "loss": 3.5184, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815564842701242e-05, + "loss": 3.5137, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807195273994458e-05, + "loss": 3.514, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798809326483938e-05, + "loss": 3.5188, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979042337897342e-05, + "loss": 3.5037, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782037431462895e-05, + "loss": 3.5145, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977366786275611e-05, + "loss": 3.5097, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976529829404932e-05, + "loss": 3.5031, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.97569123465388e-05, + "loss": 3.5209, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748526399028283e-05, + "loss": 3.5098, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740140451517763e-05, + "loss": 3.5199, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731754504007243e-05, + "loss": 3.5173, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723368556496716e-05, + "loss": 3.5113, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714998987789932e-05, + "loss": 3.5123, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706613040279412e-05, + "loss": 3.528, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698227092768892e-05, + "loss": 3.5041, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968984114525837e-05, + "loss": 3.5136, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681455197747848e-05, + "loss": 3.5132, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673085629041064e-05, + "loss": 3.5028, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664699681530537e-05, + "loss": 3.5087, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965631373402002e-05, + "loss": 3.5281, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.96479277865095e-05, + "loss": 3.5206, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963954183899898e-05, + "loss": 3.5122, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963115589148846e-05, + "loss": 3.5208, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962276994397794e-05, + "loss": 3.5102, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961440037527115e-05, + "loss": 3.5199, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606030806564365e-05, + "loss": 3.4948, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597644859053842e-05, + "loss": 3.5122, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589258911543322e-05, + "loss": 3.5183, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580872964032802e-05, + "loss": 3.5142, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572487016522282e-05, + "loss": 3.5154, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564101069011762e-05, + "loss": 3.5005, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555715121501242e-05, + "loss": 3.5126, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547329173990722e-05, + "loss": 3.4969, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538959605283934e-05, + "loss": 3.5327, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530573657773414e-05, + "loss": 3.5125, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522187710262894e-05, + "loss": 3.5272, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513801762752374e-05, + "loss": 3.5059, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505432194045583e-05, + "loss": 3.5041, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497046246535067e-05, + "loss": 3.517, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488660299024547e-05, + "loss": 3.5063, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480290730317756e-05, + "loss": 3.5068, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471904782807236e-05, + "loss": 3.5049, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463518835296716e-05, + "loss": 3.5119, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455132887786195e-05, + "loss": 3.5053, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446746940275675e-05, + "loss": 3.5063, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943836099276516e-05, + "loss": 3.496, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942997504525464e-05, + "loss": 3.5023, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942158909774412e-05, + "loss": 3.5163, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413219529037328e-05, + "loss": 3.5206, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404833581526808e-05, + "loss": 3.5064, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396447634016288e-05, + "loss": 3.5059, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388061686505768e-05, + "loss": 3.5165, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937969211779898e-05, + "loss": 3.5147, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937132254909219e-05, + "loss": 3.5143, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936293660158167e-05, + "loss": 3.5145, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935455065407115e-05, + "loss": 3.5069, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934616470656063e-05, + "loss": 3.5136, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337778759050112e-05, + "loss": 3.5192, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329392811539592e-05, + "loss": 3.5159, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9321006864029072e-05, + "loss": 3.5174, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312620916518552e-05, + "loss": 3.5091, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930425134781176e-05, + "loss": 3.4935, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929586540030124e-05, + "loss": 3.5122, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928747945279072e-05, + "loss": 3.511, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92790935052802e-05, + "loss": 3.5122, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270723936573414e-05, + "loss": 3.5097, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262337989062894e-05, + "loss": 3.5032, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253968420356103e-05, + "loss": 3.5164, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245582472845583e-05, + "loss": 3.503, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237196525335063e-05, + "loss": 3.5083, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228810577824546e-05, + "loss": 3.5107, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220424630314026e-05, + "loss": 3.5097, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.92120386828035e-05, + "loss": 3.5216, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920365273529298e-05, + "loss": 3.4976, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919526678778246e-05, + "loss": 3.496, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186897219075675e-05, + "loss": 3.5119, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917851127156515e-05, + "loss": 3.5147, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.917012532405463e-05, + "loss": 3.515, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916173937654411e-05, + "loss": 3.5127, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915336980783732e-05, + "loss": 3.4971, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.91449838603268e-05, + "loss": 3.5095, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136614291620016e-05, + "loss": 3.5148, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.91282283441095e-05, + "loss": 3.4992, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119842396598973e-05, + "loss": 3.4987, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111456449088453e-05, + "loss": 3.5081, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103070501577933e-05, + "loss": 3.5138, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094684554067413e-05, + "loss": 3.4933, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086298606556893e-05, + "loss": 3.4994, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077912659046376e-05, + "loss": 3.4974, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069543090339585e-05, + "loss": 3.5131, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061157142829065e-05, + "loss": 3.5033, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052771195318545e-05, + "loss": 3.5037, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044385247808025e-05, + "loss": 3.5096, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036015679101238e-05, + "loss": 3.5117, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027646110394447e-05, + "loss": 3.5014, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019260162883927e-05, + "loss": 3.5117, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010874215373407e-05, + "loss": 3.5111, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002488267862886e-05, + "loss": 3.5046, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994102320352366e-05, + "loss": 3.4891, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985716372841846e-05, + "loss": 3.513, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897733042533133e-05, + "loss": 3.5041, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896894447782081e-05, + "loss": 3.514, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896057490911402e-05, + "loss": 3.4979, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952205340407228e-05, + "loss": 3.5092, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943819392896708e-05, + "loss": 3.505, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893543344538619e-05, + "loss": 3.4982, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892704749787567e-05, + "loss": 3.495, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891866155036515e-05, + "loss": 3.5143, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891027560285463e-05, + "loss": 3.5176, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890188965534411e-05, + "loss": 3.5068, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889350370783359e-05, + "loss": 3.4953, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88851341391268e-05, + "loss": 3.5086, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876748191616283e-05, + "loss": 3.505, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868362244105763e-05, + "loss": 3.5072, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859976296595243e-05, + "loss": 3.5056, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851606727888452e-05, + "loss": 3.5163, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843220780377932e-05, + "loss": 3.5054, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834834832867412e-05, + "loss": 3.5102, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826448885356892e-05, + "loss": 3.5037, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818079316650105e-05, + "loss": 3.5089, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809693369139585e-05, + "loss": 3.5068, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801323800432794e-05, + "loss": 3.4963, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792937852922274e-05, + "loss": 3.5257, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784551905411754e-05, + "loss": 3.503, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776165957901237e-05, + "loss": 3.51, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767796389194446e-05, + "loss": 3.5081, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759410441683926e-05, + "loss": 3.504, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8993799686431885, + "eval_runtime": 304.8441, + "eval_samples_per_second": 1251.758, + "eval_steps_per_second": 39.118, + "step": 1297428 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751024494173406e-05, + "loss": 3.5017, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742638546662886e-05, + "loss": 3.5069, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734252599152366e-05, + "loss": 3.5128, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872588303044558e-05, + "loss": 3.506, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871749708293506e-05, + "loss": 3.5146, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870911113542454e-05, + "loss": 3.4968, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870072518791402e-05, + "loss": 3.5042, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692339240403498e-05, + "loss": 3.4995, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683953292892978e-05, + "loss": 3.5122, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675567345382455e-05, + "loss": 3.499, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667181397871935e-05, + "loss": 3.514, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865881182916515e-05, + "loss": 3.5104, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865044226045836e-05, + "loss": 3.5006, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864205631294784e-05, + "loss": 3.4974, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863367036543732e-05, + "loss": 3.4915, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.86252844179268e-05, + "loss": 3.4952, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861689847041628e-05, + "loss": 3.4983, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608512522905756e-05, + "loss": 3.4944, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600126575395236e-05, + "loss": 3.4999, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591757006688452e-05, + "loss": 3.523, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858337105917793e-05, + "loss": 3.5002, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857498511166741e-05, + "loss": 3.5024, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856659916415689e-05, + "loss": 3.5043, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558229595450104e-05, + "loss": 3.5017, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549843647939577e-05, + "loss": 3.5024, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541457700429057e-05, + "loss": 3.4916, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533071752918537e-05, + "loss": 3.5011, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524702184211753e-05, + "loss": 3.4982, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851631623670123e-05, + "loss": 3.4866, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850793028919071e-05, + "loss": 3.5056, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849954434168019e-05, + "loss": 3.494, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.84911747729734e-05, + "loss": 3.5082, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482788825462882e-05, + "loss": 3.5033, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474402877952362e-05, + "loss": 3.4924, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466016930441842e-05, + "loss": 3.5042, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845764736173505e-05, + "loss": 3.513, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844926141422453e-05, + "loss": 3.4877, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844087546671401e-05, + "loss": 3.5025, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843248951920349e-05, + "loss": 3.4955, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424119950496704e-05, + "loss": 3.4915, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415734002986184e-05, + "loss": 3.4931, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407348055475663e-05, + "loss": 3.512, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398962107965143e-05, + "loss": 3.5064, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390576160454623e-05, + "loss": 3.497, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382190212944103e-05, + "loss": 3.5074, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373804265433583e-05, + "loss": 3.4975, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365418317923063e-05, + "loss": 3.5031, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357065128020005e-05, + "loss": 3.4833, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348679180509485e-05, + "loss": 3.496, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340293232998965e-05, + "loss": 3.5045, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331907285488445e-05, + "loss": 3.5045, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323521337977925e-05, + "loss": 3.4979, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315151769271137e-05, + "loss": 3.4868, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306765821760617e-05, + "loss": 3.5005, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298379874250097e-05, + "loss": 3.483, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289993926739577e-05, + "loss": 3.5148, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281607979229057e-05, + "loss": 3.4953, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273222031718537e-05, + "loss": 3.5136, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264836084208017e-05, + "loss": 3.4938, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.82564501366975e-05, + "loss": 3.491, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824808056799071e-05, + "loss": 3.4986, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823969462048019e-05, + "loss": 3.4999, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823130867296967e-05, + "loss": 3.4925, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822292272545915e-05, + "loss": 3.4879, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214553156752362e-05, + "loss": 3.4996, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820616720924184e-05, + "loss": 3.4932, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819778126173132e-05, + "loss": 3.4844, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.81893953142208e-05, + "loss": 3.4882, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818100936671028e-05, + "loss": 3.4891, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817262341919976e-05, + "loss": 3.5039, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164237471689238e-05, + "loss": 3.5073, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155867902982454e-05, + "loss": 3.4928, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147481955471934e-05, + "loss": 3.4916, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139096007961414e-05, + "loss": 3.4996, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130710060450887e-05, + "loss": 3.4993, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122340491744103e-05, + "loss": 3.5012, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113954544233583e-05, + "loss": 3.5009, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810556859672306e-05, + "loss": 3.4956, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809718264921254e-05, + "loss": 3.5031, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808879670170202e-05, + "loss": 3.5009, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.80804107541915e-05, + "loss": 3.5057, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807202480668098e-05, + "loss": 3.5011, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806363885917046e-05, + "loss": 3.497, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805526929046367e-05, + "loss": 3.4815, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804688334295315e-05, + "loss": 3.5005, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803849739544263e-05, + "loss": 3.4961, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803011144793211e-05, + "loss": 3.4991, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802174187922532e-05, + "loss": 3.4971, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.80133559317148e-05, + "loss": 3.4898, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004986363008013e-05, + "loss": 3.5003, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996600415497493e-05, + "loss": 3.4887, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988214467986973e-05, + "loss": 3.4991, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979828520476453e-05, + "loss": 3.4912, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971442572965933e-05, + "loss": 3.4978, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963056625455413e-05, + "loss": 3.507, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954670677944893e-05, + "loss": 3.4903, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946284730434373e-05, + "loss": 3.478, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937915161727585e-05, + "loss": 3.497, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929529214217065e-05, + "loss": 3.501, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921143266706545e-05, + "loss": 3.5034, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912757319196025e-05, + "loss": 3.497, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904387750489238e-05, + "loss": 3.4874, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896001802978718e-05, + "loss": 3.4887, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887632234271927e-05, + "loss": 3.5029, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879246286761407e-05, + "loss": 3.4837, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870860339250887e-05, + "loss": 3.4869, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862474391740367e-05, + "loss": 3.4942, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854088444229846e-05, + "loss": 3.5002, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845702496719326e-05, + "loss": 3.4773, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783731654920881e-05, + "loss": 3.4894, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782893060169829e-05, + "loss": 3.4835, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.78205610329915e-05, + "loss": 3.4955, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781217508548098e-05, + "loss": 3.495, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780378913797046e-05, + "loss": 3.4835, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779540319045994e-05, + "loss": 3.5016, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778703362175315e-05, + "loss": 3.4954, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777866405304636e-05, + "loss": 3.4879, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777027810553584e-05, + "loss": 3.4968, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776189215802532e-05, + "loss": 3.4967, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.77535062105148e-05, + "loss": 3.4889, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774512026300428e-05, + "loss": 3.4786, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736734315493763e-05, + "loss": 3.4999, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728348367983243e-05, + "loss": 3.4938, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719962420472717e-05, + "loss": 3.4969, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711592851765932e-05, + "loss": 3.4834, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770322328305914e-05, + "loss": 3.496, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694837335548625e-05, + "loss": 3.4931, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686451388038105e-05, + "loss": 3.4839, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678065440527585e-05, + "loss": 3.4747, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669679493017065e-05, + "loss": 3.5019, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661293545506545e-05, + "loss": 3.5036, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652907597996018e-05, + "loss": 3.4932, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.76445216504855e-05, + "loss": 3.4824, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636152081778717e-05, + "loss": 3.5006, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627782513071926e-05, + "loss": 3.4903, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619396565561406e-05, + "loss": 3.4923, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611010618050886e-05, + "loss": 3.491, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602624670540366e-05, + "loss": 3.5003, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594238723029843e-05, + "loss": 3.49, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585852775519323e-05, + "loss": 3.4977, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577466828008803e-05, + "loss": 3.4881, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.4967, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756071131179149e-05, + "loss": 3.4937, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552341743084707e-05, + "loss": 3.4873, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543955795574187e-05, + "loss": 3.5092, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535569848063664e-05, + "loss": 3.4898, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527183900553144e-05, + "loss": 3.4955, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751881433184636e-05, + "loss": 3.4923, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751042838433584e-05, + "loss": 3.4889, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.9015679359436035, + "eval_runtime": 303.7414, + "eval_samples_per_second": 1256.302, + "eval_steps_per_second": 39.26, + "step": 1373748 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502042436825316e-05, + "loss": 3.4859, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493672868118532e-05, + "loss": 3.4922, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485286920608012e-05, + "loss": 3.498, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476900973097492e-05, + "loss": 3.4953, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468515025586965e-05, + "loss": 3.5027, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460129078076445e-05, + "loss": 3.4782, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451743130565925e-05, + "loss": 3.4903, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443373561859138e-05, + "loss": 3.4849, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434987614348618e-05, + "loss": 3.4967, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426601666838098e-05, + "loss": 3.4904, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418215719327578e-05, + "loss": 3.4968, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409829771817058e-05, + "loss": 3.4967, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740146020311027e-05, + "loss": 3.4828, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739307425559975e-05, + "loss": 3.4866, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738468830808923e-05, + "loss": 3.4759, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737630236057871e-05, + "loss": 3.4844, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736791641306819e-05, + "loss": 3.4815, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735953046555767e-05, + "loss": 3.4826, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735114451804715e-05, + "loss": 3.4872, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342774949340362e-05, + "loss": 3.5094, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334389001829842e-05, + "loss": 3.4883, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326003054319322e-05, + "loss": 3.4861, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317617106808802e-05, + "loss": 3.4913, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730924753810201e-05, + "loss": 3.4892, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730086159059149e-05, + "loss": 3.486, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729247564308097e-05, + "loss": 3.4796, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284089695570454e-05, + "loss": 3.4862, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275720126863664e-05, + "loss": 3.4811, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267334179353144e-05, + "loss": 3.4722, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258948231842623e-05, + "loss": 3.494, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250562284332103e-05, + "loss": 3.4803, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242192715625316e-05, + "loss": 3.4939, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233806768114796e-05, + "loss": 3.4869, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225420820604276e-05, + "loss": 3.4793, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217034873093756e-05, + "loss": 3.4884, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208665304386965e-05, + "loss": 3.5026, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200279356876445e-05, + "loss": 3.4742, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191893409365925e-05, + "loss": 3.4903, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183507461855405e-05, + "loss": 3.4805, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175137893148617e-05, + "loss": 3.4793, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166751945638097e-05, + "loss": 3.4815, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158365998127577e-05, + "loss": 3.4996, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149980050617057e-05, + "loss": 3.4923, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714161048191027e-05, + "loss": 3.4842, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713322453439975e-05, + "loss": 3.4949, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712483858688923e-05, + "loss": 3.4806, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711645263937871e-05, + "loss": 3.4896, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710808307067192e-05, + "loss": 3.4748, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.70996971231614e-05, + "loss": 3.4768, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709131117565088e-05, + "loss": 3.4936, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708292522814036e-05, + "loss": 3.4907, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074539280629842e-05, + "loss": 3.4807, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066153333119322e-05, + "loss": 3.4742, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057767385608795e-05, + "loss": 3.4897, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049381438098275e-05, + "loss": 3.4683, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704101186939149e-05, + "loss": 3.4978, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703262592188097e-05, + "loss": 3.4866, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024256353174183e-05, + "loss": 3.4982, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015870405663663e-05, + "loss": 3.4822, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007484458153143e-05, + "loss": 3.4772, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999098510642623e-05, + "loss": 3.4832, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990728941935832e-05, + "loss": 3.4884, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982342994425312e-05, + "loss": 3.4777, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973957046914795e-05, + "loss": 3.4746, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696557109940427e-05, + "loss": 3.485, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695718515189375e-05, + "loss": 3.481, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694879920438323e-05, + "loss": 3.4689, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694041325687271e-05, + "loss": 3.4779, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693202730936219e-05, + "loss": 3.4741, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.69236577406554e-05, + "loss": 3.4872, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691527179314488e-05, + "loss": 3.4952, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690688584563436e-05, + "loss": 3.48, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689849989812384e-05, + "loss": 3.4832, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689013032941705e-05, + "loss": 3.4835, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881760760710266e-05, + "loss": 3.4869, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873374813199742e-05, + "loss": 3.4872, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864988865689222e-05, + "loss": 3.4894, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856602918178702e-05, + "loss": 3.4827, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848233349471918e-05, + "loss": 3.4891, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839847401961395e-05, + "loss": 3.4857, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831461454450875e-05, + "loss": 3.4908, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823075506940355e-05, + "loss": 3.4867, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814689559429835e-05, + "loss": 3.4866, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806303611919314e-05, + "loss": 3.471, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797917664408794e-05, + "loss": 3.4841, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789531716898274e-05, + "loss": 3.4828, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781162148191487e-05, + "loss": 3.4841, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772776200680967e-05, + "loss": 3.4857, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764390253170447e-05, + "loss": 3.4722, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756004305659927e-05, + "loss": 3.4852, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747634736953136e-05, + "loss": 3.48, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739248789442616e-05, + "loss": 3.4881, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730862841932096e-05, + "loss": 3.4733, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672247689442158e-05, + "loss": 3.4856, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671409094691106e-05, + "loss": 3.4954, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670570499940054e-05, + "loss": 3.4773, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669731905189002e-05, + "loss": 3.4656, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.66889331043795e-05, + "loss": 3.4837, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680563535672708e-05, + "loss": 3.487, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672177588162188e-05, + "loss": 3.4851, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666379164065167e-05, + "loss": 3.486, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665540569314115e-05, + "loss": 3.4753, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664703612443436e-05, + "loss": 3.4746, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663866655572757e-05, + "loss": 3.4908, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663028060821705e-05, + "loss": 3.4711, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621894660706533e-05, + "loss": 3.4749, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613508713196013e-05, + "loss": 3.4801, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605122765685493e-05, + "loss": 3.4901, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596736818174973e-05, + "loss": 3.4607, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588367249468182e-05, + "loss": 3.481, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657998130195766e-05, + "loss": 3.4685, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657159535444714e-05, + "loss": 3.4821, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563209406936625e-05, + "loss": 3.4816, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554823459426105e-05, + "loss": 3.4728, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546437511915578e-05, + "loss": 3.4873, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538051564405058e-05, + "loss": 3.4859, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529681995698274e-05, + "loss": 3.4707, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521296048187754e-05, + "loss": 3.4849, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651291010067723e-05, + "loss": 3.4811, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650452415316671e-05, + "loss": 3.4775, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649613820565619e-05, + "loss": 3.4619, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648775225814567e-05, + "loss": 3.4869, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647936631063515e-05, + "loss": 3.4778, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647098036312463e-05, + "loss": 3.4809, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462610794417843e-05, + "loss": 3.4744, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454241225711052e-05, + "loss": 3.4823, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445855278200532e-05, + "loss": 3.4778, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437469330690012e-05, + "loss": 3.4709, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642908338317949e-05, + "loss": 3.4636, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642069743566897e-05, + "loss": 3.4908, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641231148815845e-05, + "loss": 3.4826, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403925540647935e-05, + "loss": 3.4823, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395555971941144e-05, + "loss": 3.4701, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387170024430624e-05, + "loss": 3.4841, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378784076920104e-05, + "loss": 3.4791, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370398129409584e-05, + "loss": 3.4758, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362012181899064e-05, + "loss": 3.4773, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353626234388544e-05, + "loss": 3.4838, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345240286878027e-05, + "loss": 3.4797, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336854339367507e-05, + "loss": 3.4872, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328484770660716e-05, + "loss": 3.4751, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320098823150196e-05, + "loss": 3.4836, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311712875639676e-05, + "loss": 3.4789, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630334330693289e-05, + "loss": 3.4718, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629495735942237e-05, + "loss": 3.4968, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628657141191185e-05, + "loss": 3.4772, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627818546440133e-05, + "loss": 3.4827, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269815895694538e-05, + "loss": 3.4775, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261429948184018e-05, + "loss": 3.4773, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.9036898612976074, + "eval_runtime": 302.6891, + "eval_samples_per_second": 1260.67, + "eval_steps_per_second": 39.397, + "step": 1450068 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253044000673497e-05, + "loss": 3.4715, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624465805316298e-05, + "loss": 3.4829, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623627210565246e-05, + "loss": 3.4807, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622790253694567e-05, + "loss": 3.4809, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621951658943515e-05, + "loss": 3.4878, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.621113064192463e-05, + "loss": 3.4716, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620274469441411e-05, + "loss": 3.4745, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619435874690359e-05, + "loss": 3.4694, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185972799393066e-05, + "loss": 3.4873, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177586851882546e-05, + "loss": 3.4776, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169200904372026e-05, + "loss": 3.4861, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160831335665235e-05, + "loss": 3.4863, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.615244538815472e-05, + "loss": 3.4723, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.61440594406442e-05, + "loss": 3.4666, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135689871937414e-05, + "loss": 3.4695, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127303924426888e-05, + "loss": 3.4674, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118917976916368e-05, + "loss": 3.474, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110532029405848e-05, + "loss": 3.4676, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102146081895327e-05, + "loss": 3.4747, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609376013438481e-05, + "loss": 3.4928, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608537418687429e-05, + "loss": 3.4767, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607698823936377e-05, + "loss": 3.4742, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606861867065698e-05, + "loss": 3.4766, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606024910195019e-05, + "loss": 3.4791, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051863154439672e-05, + "loss": 3.4687, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043477206929152e-05, + "loss": 3.4654, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035091259418632e-05, + "loss": 3.4805, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026705311908112e-05, + "loss": 3.4638, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018319364397592e-05, + "loss": 3.4628, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009933416887072e-05, + "loss": 3.4782, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001547469376552e-05, + "loss": 3.4702, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993177900669765e-05, + "loss": 3.4755, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984791953159244e-05, + "loss": 3.4753, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976406005648724e-05, + "loss": 3.4675, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968036436941934e-05, + "loss": 3.4773, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959650489431413e-05, + "loss": 3.4881, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951264541920893e-05, + "loss": 3.4618, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942878594410373e-05, + "loss": 3.4795, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934492646899853e-05, + "loss": 3.4616, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926123078193066e-05, + "loss": 3.4736, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917737130682546e-05, + "loss": 3.4665, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909351183172026e-05, + "loss": 3.4852, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900965235661506e-05, + "loss": 3.4777, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892579288150986e-05, + "loss": 3.4767, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884193340640466e-05, + "loss": 3.4767, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875807393129946e-05, + "loss": 3.4688, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867421445619422e-05, + "loss": 3.478, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859068255716367e-05, + "loss": 3.4613, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850682308205847e-05, + "loss": 3.4648, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842296360695327e-05, + "loss": 3.4777, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833910413184807e-05, + "loss": 3.4742, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582552446567429e-05, + "loss": 3.4738, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581713851816377e-05, + "loss": 3.4622, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580875257065325e-05, + "loss": 3.4729, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800366623142723e-05, + "loss": 3.4572, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579199705443594e-05, + "loss": 3.4798, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.578361110692542e-05, + "loss": 3.4778, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775241538218632e-05, + "loss": 3.4837, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766855590708112e-05, + "loss": 3.4708, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575846964319759e-05, + "loss": 3.4693, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.575008369568707e-05, + "loss": 3.4672, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574171412698028e-05, + "loss": 3.477, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573332817946976e-05, + "loss": 3.4628, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724942231959244e-05, + "loss": 3.4628, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716556284448724e-05, + "loss": 3.4699, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708170336938197e-05, + "loss": 3.4725, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699784389427677e-05, + "loss": 3.4565, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691398441917157e-05, + "loss": 3.4605, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568302887321037e-05, + "loss": 3.4632, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567464292569985e-05, + "loss": 3.4758, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566625697818933e-05, + "loss": 3.4796, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565787103067881e-05, + "loss": 3.4666, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564948508316829e-05, + "loss": 3.4711, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564109913565777e-05, + "loss": 3.4654, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632729566950982e-05, + "loss": 3.4828, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624343619440462e-05, + "loss": 3.467, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615957671929942e-05, + "loss": 3.4825, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560757172441942e-05, + "loss": 3.4683, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559920215571263e-05, + "loss": 3.4742, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559081620820211e-05, + "loss": 3.4767, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558243026069159e-05, + "loss": 3.4763, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574044313181074e-05, + "loss": 3.4746, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565658365670554e-05, + "loss": 3.471, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557272418160034e-05, + "loss": 3.4602, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548886470649514e-05, + "loss": 3.4705, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540500523138994e-05, + "loss": 3.4691, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532130954432203e-05, + "loss": 3.4751, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523745006921683e-05, + "loss": 3.4718, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515359059411166e-05, + "loss": 3.4622, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506989490704375e-05, + "loss": 3.4722, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498603543193855e-05, + "loss": 3.4645, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490217595683335e-05, + "loss": 3.4737, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481831648172815e-05, + "loss": 3.4575, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473445700662295e-05, + "loss": 3.4751, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465059753151775e-05, + "loss": 3.4827, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545667380564126e-05, + "loss": 3.4626, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544828785813073e-05, + "loss": 3.452, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439918289423948e-05, + "loss": 3.4721, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431532341913427e-05, + "loss": 3.4715, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423146394402907e-05, + "loss": 3.4778, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414760446892384e-05, + "loss": 3.4727, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54063908781856e-05, + "loss": 3.461, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539802130947881e-05, + "loss": 3.4635, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538963536196829e-05, + "loss": 3.4743, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538124941445777e-05, + "loss": 3.456, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537286346694725e-05, + "loss": 3.4661, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536447751943673e-05, + "loss": 3.4649, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535610795072994e-05, + "loss": 3.4769, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534772200321942e-05, + "loss": 3.4471, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.53393360557089e-05, + "loss": 3.4679, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533095010819838e-05, + "loss": 3.4601, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322564160687858e-05, + "loss": 3.4638, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314178213177338e-05, + "loss": 3.4696, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305792265666818e-05, + "loss": 3.4603, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297406318156298e-05, + "loss": 3.4785, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289036749449507e-05, + "loss": 3.4683, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280667180742723e-05, + "loss": 3.4588, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272281233232202e-05, + "loss": 3.4724, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526389528572168e-05, + "loss": 3.4702, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525550933821116e-05, + "loss": 3.4675, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524712339070064e-05, + "loss": 3.4474, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238753821993855e-05, + "loss": 3.4759, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230367874483328e-05, + "loss": 3.4638, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522198192697281e-05, + "loss": 3.4672, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521359597946229e-05, + "loss": 3.4635, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.520521003195177e-05, + "loss": 3.4702, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.519682408444125e-05, + "loss": 3.4654, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518843813693073e-05, + "loss": 3.4598, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518006856822394e-05, + "loss": 3.4534, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517168262071342e-05, + "loss": 3.4753, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.51632966732029e-05, + "loss": 3.4723, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154910725692384e-05, + "loss": 3.4694, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4597, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138155209475073e-05, + "loss": 3.4696, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129769261964553e-05, + "loss": 3.4693, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121383314454033e-05, + "loss": 3.4614, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5112997366943512e-05, + "loss": 3.468, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104627798236725e-05, + "loss": 3.4675, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096241850726205e-05, + "loss": 3.4718, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087855903215685e-05, + "loss": 3.4744, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079469955705165e-05, + "loss": 3.4617, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071084008194645e-05, + "loss": 3.4688, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062698060684125e-05, + "loss": 3.4653, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054328491977337e-05, + "loss": 3.4609, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045942544466817e-05, + "loss": 3.4819, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037556596956297e-05, + "loss": 3.4645, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029170649445777e-05, + "loss": 3.4703, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020801080738986e-05, + "loss": 3.4634, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012415133228466e-05, + "loss": 3.4686, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.9061875343322754, + "eval_runtime": 321.6366, + "eval_samples_per_second": 1186.404, + "eval_steps_per_second": 37.076, + "step": 1526388 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004029185717946e-05, + "loss": 3.4632, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4995643238207426e-05, + "loss": 3.4688, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4987257290696906e-05, + "loss": 3.4703, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497888772199012e-05, + "loss": 3.4688, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.49705017744796e-05, + "loss": 3.4779, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962115826969075e-05, + "loss": 3.4574, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.495372987945856e-05, + "loss": 3.4642, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945343931948038e-05, + "loss": 3.453, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4936957984437518e-05, + "loss": 3.4756, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928572036926998e-05, + "loss": 3.4643, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4920186089416478e-05, + "loss": 3.4701, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911816520709687e-05, + "loss": 3.4695, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.49034469520029e-05, + "loss": 3.4634, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.489506100449238e-05, + "loss": 3.4517, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.488667505698186e-05, + "loss": 3.4602, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487828910947134e-05, + "loss": 3.4506, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.486990316196082e-05, + "loss": 3.4586, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.48615172144503e-05, + "loss": 3.4608, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.485313126693978e-05, + "loss": 3.4566, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.484474531942926e-05, + "loss": 3.4822, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836375750722472e-05, + "loss": 3.461, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4827989803211952e-05, + "loss": 3.4643, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481960385570143e-05, + "loss": 3.466, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.481123428699464e-05, + "loss": 3.4632, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802864718287853e-05, + "loss": 3.4586, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794478770777333e-05, + "loss": 3.4558, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786092823266813e-05, + "loss": 3.4672, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777706875756293e-05, + "loss": 3.4461, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769320928245773e-05, + "loss": 3.4562, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4760951359538982e-05, + "loss": 3.4585, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752565412028462e-05, + "loss": 3.4577, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744179464517946e-05, + "loss": 3.4683, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4735793517007426e-05, + "loss": 3.4592, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727423948300635e-05, + "loss": 3.4588, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719038000790115e-05, + "loss": 3.4647, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710652053279595e-05, + "loss": 3.4757, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702266105769075e-05, + "loss": 3.4509, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4693880158258555e-05, + "loss": 3.4636, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685510589551767e-05, + "loss": 3.4506, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677124642041247e-05, + "loss": 3.4637, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668738694530724e-05, + "loss": 3.4494, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660352747020203e-05, + "loss": 3.4751, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4651966799509683e-05, + "loss": 3.4664, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.46435972308029e-05, + "loss": 3.4592, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4635211283292376e-05, + "loss": 3.4681, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4626825335781856e-05, + "loss": 3.457, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618439388271336e-05, + "loss": 3.4638, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610069819564548e-05, + "loss": 3.4516, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601683872054028e-05, + "loss": 3.4491, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593297924543508e-05, + "loss": 3.4698, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4584911977032988e-05, + "loss": 3.4578, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576526029522468e-05, + "loss": 3.4627, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4568140082011948e-05, + "loss": 3.4478, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559754134501428e-05, + "loss": 3.4607, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551368186990905e-05, + "loss": 3.4482, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4542998618284117e-05, + "loss": 3.4669, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.45346126707736e-05, + "loss": 3.4605, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.452622672326308e-05, + "loss": 3.4727, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517840775752557e-05, + "loss": 3.4599, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.450947120704577e-05, + "loss": 3.4537, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.450108525953525e-05, + "loss": 3.455, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492715690828462e-05, + "loss": 3.4624, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484329743317942e-05, + "loss": 3.4523, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4475943795807422e-05, + "loss": 3.4517, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467557848296902e-05, + "loss": 3.4545, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459171900786378e-05, + "loss": 3.4628, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450785953275858e-05, + "loss": 3.4418, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442400005765338e-05, + "loss": 3.4512, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434030437058554e-05, + "loss": 3.449, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442564448954803e-05, + "loss": 3.4625, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441725854203751e-05, + "loss": 3.4641, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440887259452699e-05, + "loss": 3.4569, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.440048664701647e-05, + "loss": 3.4593, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392117078309683e-05, + "loss": 3.4514, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383731130799163e-05, + "loss": 3.4722, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375345183288643e-05, + "loss": 3.4528, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4366959235778123e-05, + "loss": 3.4673, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358573288267603e-05, + "loss": 3.4611, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350203719560812e-05, + "loss": 3.4588, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341817772050292e-05, + "loss": 3.4675, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333431824539775e-05, + "loss": 3.4626, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325045877029255e-05, + "loss": 3.4631, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4316659929518735e-05, + "loss": 3.46, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430827398200821e-05, + "loss": 3.4447, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.429988803449769e-05, + "loss": 3.4629, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429150208698717e-05, + "loss": 3.453, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283132518280384e-05, + "loss": 3.4641, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4274746570769864e-05, + "loss": 3.4593, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266360623259344e-05, + "loss": 3.449, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4257991054552556e-05, + "loss": 3.4609, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249605107042033e-05, + "loss": 3.4555, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241219159531513e-05, + "loss": 3.4603, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4232833212020993e-05, + "loss": 3.4461, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224447264510476e-05, + "loss": 3.4629, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216061316999956e-05, + "loss": 3.4711, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207675369489436e-05, + "loss": 3.4517, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199289421978916e-05, + "loss": 3.437, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4190919853272125e-05, + "loss": 3.4598, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182533905761605e-05, + "loss": 3.4598, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174147958251085e-05, + "loss": 3.4656, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4165762010740565e-05, + "loss": 3.4604, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157392442033778e-05, + "loss": 3.4529, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149006494523258e-05, + "loss": 3.4508, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140620547012738e-05, + "loss": 3.4644, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132234599502214e-05, + "loss": 3.4434, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412386503079543e-05, + "loss": 3.4514, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411547908328491e-05, + "loss": 3.4519, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410709313577439e-05, + "loss": 3.464, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4098707188263866e-05, + "loss": 3.4349, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.409033761955708e-05, + "loss": 3.458, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.408195167204656e-05, + "loss": 3.4477, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.407356572453604e-05, + "loss": 3.4509, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406517977702552e-05, + "loss": 3.4566, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405681020831873e-05, + "loss": 3.4494, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404842426080821e-05, + "loss": 3.464, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040038313297688e-05, + "loss": 3.4583, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.40316687445909e-05, + "loss": 3.4482, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023282797080384e-05, + "loss": 3.4566, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014896849569864e-05, + "loss": 3.4574, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.400651090205934e-05, + "loss": 3.4573, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399812495454882e-05, + "loss": 3.4373, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.39897390070383e-05, + "loss": 3.4616, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398135305952778e-05, + "loss": 3.4513, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397296711201726e-05, + "loss": 3.4567, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964597543310472e-05, + "loss": 3.4465, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956227974603685e-05, + "loss": 3.4625, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394784202709316e-05, + "loss": 3.456, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393945607958264e-05, + "loss": 3.447, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.393107013207212e-05, + "loss": 3.442, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.39226841845616e-05, + "loss": 3.4649, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914298237051085e-05, + "loss": 3.4548, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3905912289540565e-05, + "loss": 3.4592, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897526342030045e-05, + "loss": 3.4496, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889156773323254e-05, + "loss": 3.4569, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3880787204616463e-05, + "loss": 3.4581, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3872401257105946e-05, + "loss": 3.4487, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3864015309595426e-05, + "loss": 3.4544, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3855629362084906e-05, + "loss": 3.4568, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3847243414574386e-05, + "loss": 3.4586, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3838857467063866e-05, + "loss": 3.4627, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830471519553343e-05, + "loss": 3.4501, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822085572042823e-05, + "loss": 3.4571, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381371600333604e-05, + "loss": 3.4514, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805346434629247e-05, + "loss": 3.4519, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3796960487118727e-05, + "loss": 3.4667, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788574539608207e-05, + "loss": 3.4511, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780188592097687e-05, + "loss": 3.4619, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3771802644587164e-05, + "loss": 3.4436, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.376343307588038e-05, + "loss": 3.4615, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9089579582214355, + "eval_runtime": 317.5898, + "eval_samples_per_second": 1201.522, + "eval_steps_per_second": 37.548, + "step": 1602708 + }, + { + "epoch": 0.0, + "learning_rate": 2.375504712836986e-05, + "loss": 3.447, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374666118085934e-05, + "loss": 3.4586, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373829161215255e-05, + "loss": 3.4576, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.372990566464203e-05, + "loss": 3.4561, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.372151971713151e-05, + "loss": 3.4633, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713133769620992e-05, + "loss": 3.4493, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370474782211047e-05, + "loss": 3.4484, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369636187459995e-05, + "loss": 3.4469, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368797592708943e-05, + "loss": 3.4593, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679606358382638e-05, + "loss": 3.4571, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671220410872118e-05, + "loss": 3.4564, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.36628344633616e-05, + "loss": 3.4532, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654464894654813e-05, + "loss": 3.45, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364607894714429e-05, + "loss": 3.441, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363769299963377e-05, + "loss": 3.4507, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362930705212325e-05, + "loss": 3.4347, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362092110461273e-05, + "loss": 3.4465, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361253515710221e-05, + "loss": 3.4468, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604149209591693e-05, + "loss": 3.4425, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595763262081173e-05, + "loss": 3.4784, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587393693374382e-05, + "loss": 3.4473, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579007745863862e-05, + "loss": 3.4544, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570621798353342e-05, + "loss": 3.4515, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356223585084282e-05, + "loss": 3.4525, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553882660939764e-05, + "loss": 3.4441, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545496713429244e-05, + "loss": 3.4487, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537110765918724e-05, + "loss": 3.4526, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528724818408204e-05, + "loss": 3.4353, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520338870897684e-05, + "loss": 3.4422, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3511969302190896e-05, + "loss": 3.444, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503583354680376e-05, + "loss": 3.4471, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495197407169856e-05, + "loss": 3.4528, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486811459659336e-05, + "loss": 3.4495, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478441890952545e-05, + "loss": 3.451, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470055943442025e-05, + "loss": 3.4492, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461669995931508e-05, + "loss": 3.4561, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453284048420988e-05, + "loss": 3.4411, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3444898100910468e-05, + "loss": 3.4528, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436512153399945e-05, + "loss": 3.4401, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428142584693157e-05, + "loss": 3.4507, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419756637182637e-05, + "loss": 3.4377, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411370689672117e-05, + "loss": 3.4622, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3402984742161597e-05, + "loss": 3.4514, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394598794651077e-05, + "loss": 3.4486, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386212847140557e-05, + "loss": 3.4548, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377826899630037e-05, + "loss": 3.4525, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369457330923246e-05, + "loss": 3.4515, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361071383412726e-05, + "loss": 3.4363, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335268543590221e-05, + "loss": 3.4329, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334429948839169e-05, + "loss": 3.4582, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333591354088117e-05, + "loss": 3.4473, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332752759337065e-05, + "loss": 3.452, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331915802466386e-05, + "loss": 3.4415, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310772077153338e-05, + "loss": 3.4462, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302386129642818e-05, + "loss": 3.4359, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294000182132298e-05, + "loss": 3.4523, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285614234621778e-05, + "loss": 3.4516, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327724466591499e-05, + "loss": 3.4594, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326885871840447e-05, + "loss": 3.4493, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260472770893947e-05, + "loss": 3.4415, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325208682338343e-05, + "loss": 3.4452, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243717254676643e-05, + "loss": 3.4531, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235331307166123e-05, + "loss": 3.439, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.32269453596556e-05, + "loss": 3.4431, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321855941214508e-05, + "loss": 3.4431, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321017346463456e-05, + "loss": 3.4511, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320178751712404e-05, + "loss": 3.4301, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319340156961352e-05, + "loss": 3.4413, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185032000906732e-05, + "loss": 3.4342, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176646053396212e-05, + "loss": 3.4513, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168260105885692e-05, + "loss": 3.4493, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315987415837517e-05, + "loss": 3.4463, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315150458966838e-05, + "loss": 3.4477, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143118642157864e-05, + "loss": 3.4401, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134732694647344e-05, + "loss": 3.4602, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126346747136824e-05, + "loss": 3.44, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3117960799626304e-05, + "loss": 3.4575, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310957485211578e-05, + "loss": 3.4453, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101205283408993e-05, + "loss": 3.4489, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3092819335898473e-05, + "loss": 3.4552, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084433388387953e-05, + "loss": 3.4529, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076047440877433e-05, + "loss": 3.4512, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067661493366913e-05, + "loss": 3.4486, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059275545856393e-05, + "loss": 3.4321, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3050889598345873e-05, + "loss": 3.4507, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042503650835353e-05, + "loss": 3.4407, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034134082128565e-05, + "loss": 3.4525, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025748134618045e-05, + "loss": 3.4469, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017362187107525e-05, + "loss": 3.4348, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008992618400734e-05, + "loss": 3.4467, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000606670890214e-05, + "loss": 3.4466, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992220723379694e-05, + "loss": 3.4453, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983834775869174e-05, + "loss": 3.4337, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975448828358657e-05, + "loss": 3.4497, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967062880848134e-05, + "loss": 3.4613, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958676933337614e-05, + "loss": 3.4405, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950290985827094e-05, + "loss": 3.4263, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941921417120306e-05, + "loss": 3.4463, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933535469609786e-05, + "loss": 3.4452, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925149522099266e-05, + "loss": 3.4518, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916763574588746e-05, + "loss": 3.45, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908394005881955e-05, + "loss": 3.441, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900008058371435e-05, + "loss": 3.4415, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891638489664648e-05, + "loss": 3.4493, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883252542154128e-05, + "loss": 3.4319, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2874866594643608e-05, + "loss": 3.4396, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866480647133088e-05, + "loss": 3.4371, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858094699622568e-05, + "loss": 3.4514, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284972513091578e-05, + "loss": 3.426, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841339183405257e-05, + "loss": 3.4433, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283295323589474e-05, + "loss": 3.4376, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282456728838422e-05, + "loss": 3.4419, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.28161813408737e-05, + "loss": 3.4469, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280779539336318e-05, + "loss": 3.436, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279940944585266e-05, + "loss": 3.4486, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279103987714587e-05, + "loss": 3.4486, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278265392963535e-05, + "loss": 3.4324, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277428436092856e-05, + "loss": 3.4484, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276589841341804e-05, + "loss": 3.4399, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275751246590752e-05, + "loss": 3.4484, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749126518397e-05, + "loss": 3.4279, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274074057088648e-05, + "loss": 3.4458, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273235462337596e-05, + "loss": 3.434, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272396867586544e-05, + "loss": 3.4434, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715599107158654e-05, + "loss": 3.4374, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707213159648134e-05, + "loss": 3.4482, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269882721213761e-05, + "loss": 3.4442, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269044126462709e-05, + "loss": 3.4386, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682071695920303e-05, + "loss": 3.4239, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673685748409786e-05, + "loss": 3.4572, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665299800899262e-05, + "loss": 3.4404, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2656913853388742e-05, + "loss": 3.4501, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648544284681955e-05, + "loss": 3.435, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640158337171435e-05, + "loss": 3.4487, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263177238966091e-05, + "loss": 3.4452, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623386442150395e-05, + "loss": 3.439, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615000494639875e-05, + "loss": 3.4429, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606614547129355e-05, + "loss": 3.4445, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598228599618835e-05, + "loss": 3.444, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589842652108315e-05, + "loss": 3.456, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581489462205256e-05, + "loss": 3.4327, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573103514694736e-05, + "loss": 3.4463, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564717567184216e-05, + "loss": 3.4362, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556331619673696e-05, + "loss": 3.4459, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547945672163176e-05, + "loss": 3.4491, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539559724652656e-05, + "loss": 3.4368, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531173777142136e-05, + "loss": 3.4522, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522787829631616e-05, + "loss": 3.4384, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251441826092483e-05, + "loss": 3.449, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.9110541343688965, + "eval_runtime": 309.5374, + "eval_samples_per_second": 1232.778, + "eval_steps_per_second": 38.525, + "step": 1679028 + }, + { + "epoch": 1.0, + "learning_rate": 2.250603231341431e-05, + "loss": 3.4359, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497646365903788e-05, + "loss": 3.4468, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489260418393265e-05, + "loss": 3.4444, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2480890849686477e-05, + "loss": 3.4454, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472504902175957e-05, + "loss": 3.4508, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246411895466544e-05, + "loss": 3.4407, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455733007154917e-05, + "loss": 3.4311, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447347059644397e-05, + "loss": 3.4346, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438961112133877e-05, + "loss": 3.4486, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430575164623357e-05, + "loss": 3.4463, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422189217112837e-05, + "loss": 3.442, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241381964840605e-05, + "loss": 3.4483, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405450079699262e-05, + "loss": 3.4316, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239706413218874e-05, + "loss": 3.4334, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238867818467822e-05, + "loss": 3.4409, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.23802922371677e-05, + "loss": 3.4236, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237190628965718e-05, + "loss": 3.438, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236352034214666e-05, + "loss": 3.4313, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355134394636142e-05, + "loss": 3.4315, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2346748447125622e-05, + "loss": 3.4669, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233837887841883e-05, + "loss": 3.4389, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.232999293090831e-05, + "loss": 3.4374, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232160698339779e-05, + "loss": 3.4397, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231322103588727e-05, + "loss": 3.4419, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2304867845984212e-05, + "loss": 3.4279, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296481898473692e-05, + "loss": 3.4398, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288095950963172e-05, + "loss": 3.4385, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279710003452652e-05, + "loss": 3.426, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271324055942132e-05, + "loss": 3.4329, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2262954487235345e-05, + "loss": 3.4288, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254568539724825e-05, + "loss": 3.4381, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246182592214305e-05, + "loss": 3.4424, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2237796644703784e-05, + "loss": 3.4357, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229427075996994e-05, + "loss": 3.4414, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221041128486474e-05, + "loss": 3.4372, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212655180975957e-05, + "loss": 3.4436, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204269233465437e-05, + "loss": 3.4299, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195883285954917e-05, + "loss": 3.4433, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187497338444393e-05, + "loss": 3.4231, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179127769737606e-05, + "loss": 3.4412, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170741822227086e-05, + "loss": 3.4238, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162355874716566e-05, + "loss": 3.4551, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2153969927206046e-05, + "loss": 3.4406, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145600358499258e-05, + "loss": 3.4393, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137214410988738e-05, + "loss": 3.439, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2128828463478215e-05, + "loss": 3.4394, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120442515967695e-05, + "loss": 3.4377, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211207294726091e-05, + "loss": 3.4295, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210368699975039e-05, + "loss": 3.4176, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095301052239867e-05, + "loss": 3.4501, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2086915104729347e-05, + "loss": 3.4333, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078529157218827e-05, + "loss": 3.4421, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070143209708307e-05, + "loss": 3.4283, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061757262197787e-05, + "loss": 3.435, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053387693491e-05, + "loss": 3.4216, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204500174598048e-05, + "loss": 3.441, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203661579846996e-05, + "loss": 3.4401, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202822985095944e-05, + "loss": 3.4477, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.201984390344892e-05, + "loss": 3.4382, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011457955938396e-05, + "loss": 3.428, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200307200842788e-05, + "loss": 3.4353, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199470243972109e-05, + "loss": 3.4428, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198631649221057e-05, + "loss": 3.4259, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1977930544700048e-05, + "loss": 3.4312, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969544597189528e-05, + "loss": 3.4319, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961158649679008e-05, + "loss": 3.4398, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952772702168488e-05, + "loss": 3.4173, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.19444031334617e-05, + "loss": 3.4272, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193601718595118e-05, + "loss": 3.4274, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192763123844066e-05, + "loss": 3.4333, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191924529093014e-05, + "loss": 3.4402, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191085934341962e-05, + "loss": 3.434, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.190248977471283e-05, + "loss": 3.438, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894103827202313e-05, + "loss": 3.4261, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885717879691793e-05, + "loss": 3.4536, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877331932181273e-05, + "loss": 3.4267, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1868945984670753e-05, + "loss": 3.4454, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186056003716023e-05, + "loss": 3.4325, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185219046845344e-05, + "loss": 3.4353, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184380452094292e-05, + "loss": 3.4457, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835418573432405e-05, + "loss": 3.4423, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182703262592188e-05, + "loss": 3.4347, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.181864667841136e-05, + "loss": 3.4394, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.181026073090084e-05, + "loss": 3.4207, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180187478339032e-05, + "loss": 3.4349, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.17934888358798e-05, + "loss": 3.4326, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785135645976746e-05, + "loss": 3.4414, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776749698466226e-05, + "loss": 3.4302, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768363750955703e-05, + "loss": 3.4269, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1759977803445183e-05, + "loss": 3.433, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751608234738395e-05, + "loss": 3.4376, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743222287227875e-05, + "loss": 3.4332, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1734836339717355e-05, + "loss": 3.4223, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726450392206835e-05, + "loss": 3.4386, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718064444696315e-05, + "loss": 3.4482, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709678497185795e-05, + "loss": 3.4295, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701292549675275e-05, + "loss": 3.4144, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1692906602164755e-05, + "loss": 3.4339, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1684537033457967e-05, + "loss": 3.4326, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676151085947447e-05, + "loss": 3.439, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667765138436927e-05, + "loss": 3.4392, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659379190926407e-05, + "loss": 3.4317, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651009622219616e-05, + "loss": 3.4264, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642623674709096e-05, + "loss": 3.4396, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163425410600231e-05, + "loss": 3.4196, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162586815849179e-05, + "loss": 3.432, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161748221098127e-05, + "loss": 3.4222, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160909626347075e-05, + "loss": 3.4427, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160071031596023e-05, + "loss": 3.4165, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592324368449705e-05, + "loss": 3.4269, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158395479974292e-05, + "loss": 3.427, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.15755688522324e-05, + "loss": 3.4323, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156718290472188e-05, + "loss": 3.4322, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1558796957211358e-05, + "loss": 3.4274, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550411009700838e-05, + "loss": 3.4345, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542025062190318e-05, + "loss": 3.4357, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.153365549348353e-05, + "loss": 3.4208, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152526954597301e-05, + "loss": 3.4411, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151688359846249e-05, + "loss": 3.4269, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150849765095197e-05, + "loss": 3.4353, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150011170344145e-05, + "loss": 3.4201, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.149174213473466e-05, + "loss": 3.4298, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483356187224142e-05, + "loss": 3.4256, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1474970239713622e-05, + "loss": 3.431, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466584292203102e-05, + "loss": 3.4309, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145821472349631e-05, + "loss": 3.4321, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144982877598579e-05, + "loss": 3.4322, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144144282847527e-05, + "loss": 3.4299, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143305688096475e-05, + "loss": 3.4134, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424670933454234e-05, + "loss": 3.4411, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.141628498594371e-05, + "loss": 3.4277, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140789903843319e-05, + "loss": 3.4362, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399529469726404e-05, + "loss": 3.4254, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391143522215883e-05, + "loss": 3.4394, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138275757470536e-05, + "loss": 3.4299, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374371627194843e-05, + "loss": 3.4243, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1365985679684323e-05, + "loss": 3.4313, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357599732173803e-05, + "loss": 3.433, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349213784663283e-05, + "loss": 3.4325, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1340827837152763e-05, + "loss": 3.4491, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332458268445972e-05, + "loss": 3.4192, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324072320935452e-05, + "loss": 3.4356, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315702752228665e-05, + "loss": 3.4238, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307316804718145e-05, + "loss": 3.4361, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1298930857207625e-05, + "loss": 3.4353, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290544909697105e-05, + "loss": 3.4265, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282158962186585e-05, + "loss": 3.4438, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1273789393479797e-05, + "loss": 3.4242, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265403445969277e-05, + "loss": 3.4364, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.912324905395508, + "eval_runtime": 302.8728, + "eval_samples_per_second": 1259.905, + "eval_steps_per_second": 39.373, + "step": 1755348 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257017498458757e-05, + "loss": 3.4315, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248631550948237e-05, + "loss": 3.4268, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240261982241446e-05, + "loss": 3.4364, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1231876034730926e-05, + "loss": 3.4358, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223490087220406e-05, + "loss": 3.4382, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121510413970989e-05, + "loss": 3.429, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206718192199366e-05, + "loss": 3.4202, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119834862349258e-05, + "loss": 3.4208, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189962675982058e-05, + "loss": 3.4381, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181576728471538e-05, + "loss": 3.4353, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173190780961015e-05, + "loss": 3.4273, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1164804833450498e-05, + "loss": 3.4364, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115643526474371e-05, + "loss": 3.4223, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148049317233187e-05, + "loss": 3.4222, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139663369722667e-05, + "loss": 3.4297, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131277422212147e-05, + "loss": 3.4166, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1122891474701627e-05, + "loss": 3.4248, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114505527191107e-05, + "loss": 3.4217, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110611957968059e-05, + "loss": 3.4191, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109773363217007e-05, + "loss": 3.4553, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108936406346328e-05, + "loss": 3.4275, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108099449475649e-05, + "loss": 3.4259, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107260854724597e-05, + "loss": 3.4275, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064222599735452e-05, + "loss": 3.4345, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1055836652224932e-05, + "loss": 3.4149, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104746708351814e-05, + "loss": 3.4285, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103908113600762e-05, + "loss": 3.4257, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.10306951884971e-05, + "loss": 3.417, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102230924098658e-05, + "loss": 3.4198, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101392329347606e-05, + "loss": 3.4179, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005537345965544e-05, + "loss": 3.4269, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997167777258753e-05, + "loss": 3.4311, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0988781829748233e-05, + "loss": 3.4248, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980395882237713e-05, + "loss": 3.4248, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972009934727193e-05, + "loss": 3.4277, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096362398721667e-05, + "loss": 3.4302, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955238039706153e-05, + "loss": 3.4217, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0946852092195633e-05, + "loss": 3.4317, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938482523488842e-05, + "loss": 3.4156, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930112954782054e-05, + "loss": 3.4279, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0921727007271534e-05, + "loss": 3.4131, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913341059761014e-05, + "loss": 3.4427, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0904955112250494e-05, + "loss": 3.4265, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896569164739974e-05, + "loss": 3.4289, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888183217229454e-05, + "loss": 3.4331, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0879813648522667e-05, + "loss": 3.4261, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871427701012143e-05, + "loss": 3.4278, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863041753501623e-05, + "loss": 3.4208, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854655805991107e-05, + "loss": 3.4001, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846286237284316e-05, + "loss": 3.4416, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0837900289773796e-05, + "loss": 3.4198, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829514342263276e-05, + "loss": 3.4353, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821128394752756e-05, + "loss": 3.4162, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0812742447242235e-05, + "loss": 3.4217, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804356499731715e-05, + "loss": 3.4089, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.07959705522212e-05, + "loss": 3.4298, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787600983514408e-05, + "loss": 3.4318, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779215036003888e-05, + "loss": 3.4307, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0770829088493368e-05, + "loss": 3.4325, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762443140982848e-05, + "loss": 3.4141, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754057193472328e-05, + "loss": 3.4175, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074568762476554e-05, + "loss": 3.437, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073730167725502e-05, + "loss": 3.4146, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0728915729744497e-05, + "loss": 3.4161, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720529782233977e-05, + "loss": 3.4194, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712143834723457e-05, + "loss": 3.4276, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0703757887212937e-05, + "loss": 3.4094, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069538831850615e-05, + "loss": 3.4143, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068700237099563e-05, + "loss": 3.4147, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067861642348511e-05, + "loss": 3.4213, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067023047597459e-05, + "loss": 3.4273, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066184452846407e-05, + "loss": 3.4265, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065345858095355e-05, + "loss": 3.4231, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064508901224676e-05, + "loss": 3.4163, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063670306473624e-05, + "loss": 3.4415, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062831711722572e-05, + "loss": 3.4157, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.06199311697152e-05, + "loss": 3.4337, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611545222204678e-05, + "loss": 3.4216, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060317565349789e-05, + "loss": 3.422, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059478970598737e-05, + "loss": 3.4318, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586403758476854e-05, + "loss": 3.4321, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057801781096633e-05, + "loss": 3.4211, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.056963186345581e-05, + "loss": 3.4275, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056124591594529e-05, + "loss": 3.4111, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055285996843477e-05, + "loss": 3.4227, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054447402092425e-05, + "loss": 3.4198, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536104452217462e-05, + "loss": 3.4318, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527734883510675e-05, + "loss": 3.4193, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051934893600015e-05, + "loss": 3.4152, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051096298848963e-05, + "loss": 3.421, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050257704097911e-05, + "loss": 3.4296, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049419109346859e-05, + "loss": 3.4224, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0485821524761804e-05, + "loss": 3.4112, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477435577251284e-05, + "loss": 3.4303, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469049629740764e-05, + "loss": 3.4341, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0460663682230244e-05, + "loss": 3.4214, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452277734719724e-05, + "loss": 3.4036, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0443891787209204e-05, + "loss": 3.4244, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435505839698684e-05, + "loss": 3.4178, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427119892188164e-05, + "loss": 3.4307, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418750323481376e-05, + "loss": 3.4298, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410364375970856e-05, + "loss": 3.418, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0401978428460333e-05, + "loss": 3.4189, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393592480949812e-05, + "loss": 3.4243, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385222912243025e-05, + "loss": 3.4111, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0376836964732508e-05, + "loss": 3.4204, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368451017221985e-05, + "loss": 3.4095, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360065069711465e-05, + "loss": 3.4344, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351695501004677e-05, + "loss": 3.4043, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343309553494154e-05, + "loss": 3.4122, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0334923605983637e-05, + "loss": 3.4159, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0326537658473117e-05, + "loss": 3.4225, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318151710962597e-05, + "loss": 3.4182, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0309765763452077e-05, + "loss": 3.4168, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301379815941557e-05, + "loss": 3.4269, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0292993868431037e-05, + "loss": 3.4263, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028464067852798e-05, + "loss": 3.41, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027625473101746e-05, + "loss": 3.4277, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026786878350694e-05, + "loss": 3.4192, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025948283599642e-05, + "loss": 3.4196, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.02510968884859e-05, + "loss": 3.413, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0242727319779108e-05, + "loss": 3.4166, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023434137226859e-05, + "loss": 3.4139, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022595542475807e-05, + "loss": 3.4209, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021756947724755e-05, + "loss": 3.4209, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020918352973703e-05, + "loss": 3.4204, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020079758222651e-05, + "loss": 3.418, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192411634715987e-05, + "loss": 3.4172, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.01840420660092e-05, + "loss": 3.4053, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175656118498683e-05, + "loss": 3.4305, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167270170988163e-05, + "loss": 3.4185, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015888422347764e-05, + "loss": 3.4224, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015049827596712e-05, + "loss": 3.4138, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142128707260332e-05, + "loss": 3.4285, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013374275974981e-05, + "loss": 3.4195, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125356812239292e-05, + "loss": 3.41, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0116970864728772e-05, + "loss": 3.4232, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108584917218252e-05, + "loss": 3.4175, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100198969707732e-05, + "loss": 3.4186, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0091813022197212e-05, + "loss": 3.4382, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008344345349042e-05, + "loss": 3.4089, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075073884783633e-05, + "loss": 3.4277, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066687937273113e-05, + "loss": 3.4157, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058301989762593e-05, + "loss": 3.4213, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0049916042252073e-05, + "loss": 3.4213, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041530094741553e-05, + "loss": 3.42, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033144147231033e-05, + "loss": 3.4265, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0024758199720513e-05, + "loss": 3.4159, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016388631013726e-05, + "loss": 3.4251, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.915191173553467, + "eval_runtime": 304.0085, + "eval_samples_per_second": 1255.198, + "eval_steps_per_second": 39.226, + "step": 1831668 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008002683503206e-05, + "loss": 3.4226, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999616735992686e-05, + "loss": 3.4177, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991230788482165e-05, + "loss": 3.4201, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9982861219775375e-05, + "loss": 3.4237, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974475272264855e-05, + "loss": 3.4294, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966089324754338e-05, + "loss": 3.4135, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9957703377243818e-05, + "loss": 3.4129, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949317429733294e-05, + "loss": 3.4131, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9940931482222774e-05, + "loss": 3.4238, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9932545534712254e-05, + "loss": 3.4265, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924159587201734e-05, + "loss": 3.4135, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9915790018494947e-05, + "loss": 3.4259, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990742044978816e-05, + "loss": 3.4149, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989903450227764e-05, + "loss": 3.4082, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9890648554767116e-05, + "loss": 3.417, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882262607256596e-05, + "loss": 3.4035, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9873876659746076e-05, + "loss": 3.4149, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865490712235556e-05, + "loss": 3.4087, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985710476472504e-05, + "loss": 3.4057, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9848735196018248e-05, + "loss": 3.4441, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840349248507728e-05, + "loss": 3.4209, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9831963300997208e-05, + "loss": 3.4118, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823577353486688e-05, + "loss": 3.4179, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815191405976168e-05, + "loss": 3.4223, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980682183726938e-05, + "loss": 3.4019, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.979843588975886e-05, + "loss": 3.4179, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979004994224834e-05, + "loss": 3.4173, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978166399473782e-05, + "loss": 3.4038, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773278047227297e-05, + "loss": 3.4035, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976490847852051e-05, + "loss": 3.4117, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756522531009993e-05, + "loss": 3.4155, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974813658349947e-05, + "loss": 3.4194, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.973975063598895e-05, + "loss": 3.4141, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.973136468847843e-05, + "loss": 3.4149, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.972297874096791e-05, + "loss": 3.4157, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971459279345739e-05, + "loss": 3.42, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970620684594687e-05, + "loss": 3.4127, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.969783727724008e-05, + "loss": 3.4185, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.968945132972956e-05, + "loss": 3.4049, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.968108176102277e-05, + "loss": 3.4154, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967269581351225e-05, + "loss": 3.4052, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966430986600173e-05, + "loss": 3.4293, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965592391849121e-05, + "loss": 3.4206, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647554349784423e-05, + "loss": 3.4131, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639168402273903e-05, + "loss": 3.4214, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9630782454763383e-05, + "loss": 3.4149, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622396507252863e-05, + "loss": 3.4192, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614026938546072e-05, + "loss": 3.4096, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9605640991035555e-05, + "loss": 3.3867, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597255043525035e-05, + "loss": 3.43, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9588869096014515e-05, + "loss": 3.4088, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580483148503995e-05, + "loss": 3.426, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572113579797204e-05, + "loss": 3.4058, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9563727632286684e-05, + "loss": 3.414, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555341684776164e-05, + "loss": 3.3973, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9546955737265647e-05, + "loss": 3.4177, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9538569789755124e-05, + "loss": 3.4206, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530200221048336e-05, + "loss": 3.4189, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9521814273537816e-05, + "loss": 3.4224, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513428326027296e-05, + "loss": 3.4065, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505042378516776e-05, + "loss": 3.4053, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949667280980999e-05, + "loss": 3.4245, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948828686229947e-05, + "loss": 3.4052, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.947990091478895e-05, + "loss": 3.4058, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471514967278425e-05, + "loss": 3.4072, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463129019767905e-05, + "loss": 3.4155, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9454743072257385e-05, + "loss": 3.4017, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446373503550598e-05, + "loss": 3.4053, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9437987556040078e-05, + "loss": 3.4016, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9429601608529558e-05, + "loss": 3.4117, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421215661019038e-05, + "loss": 3.4179, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9412829713508517e-05, + "loss": 3.4109, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404460144801727e-05, + "loss": 3.4114, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.939607419729121e-05, + "loss": 3.409, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938768824978069e-05, + "loss": 3.4279, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937930230227017e-05, + "loss": 3.4045, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.937091635475965e-05, + "loss": 3.4231, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936253040724913e-05, + "loss": 3.4121, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935416083854234e-05, + "loss": 3.4092, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934577489103182e-05, + "loss": 3.425, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337388943521302e-05, + "loss": 3.424, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932900299601078e-05, + "loss": 3.4133, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932061704850026e-05, + "loss": 3.4131, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931223110098974e-05, + "loss": 3.4034, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930384515347922e-05, + "loss": 3.4069, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929547558477243e-05, + "loss": 3.4103, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928708963726191e-05, + "loss": 3.4232, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927870368975139e-05, + "loss": 3.4061, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927031774224087e-05, + "loss": 3.407, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926194817353408e-05, + "loss": 3.4061, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925356222602356e-05, + "loss": 3.4194, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924517627851304e-05, + "loss": 3.4122, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9236790331002523e-05, + "loss": 3.4003, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228404383492003e-05, + "loss": 3.4174, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220018435981483e-05, + "loss": 3.4203, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9211648867274692e-05, + "loss": 3.4118, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203262919764172e-05, + "loss": 3.3945, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9194876972253652e-05, + "loss": 3.4097, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9186491024743132e-05, + "loss": 3.4073, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178105077232612e-05, + "loss": 3.4203, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9169719129722092e-05, + "loss": 3.4163, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161333182211572e-05, + "loss": 3.4135, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915296361350478e-05, + "loss": 3.4042, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914457766599426e-05, + "loss": 3.4103, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913619171848374e-05, + "loss": 3.4061, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9127805770973224e-05, + "loss": 3.4065, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119419823462704e-05, + "loss": 3.3995, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111033875952184e-05, + "loss": 3.4203, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9102664307245393e-05, + "loss": 3.3986, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094278359734873e-05, + "loss": 3.4007, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9085892412224353e-05, + "loss": 3.4029, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077506464713833e-05, + "loss": 3.4091, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069120517203317e-05, + "loss": 3.4103, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9060734569692793e-05, + "loss": 3.4023, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052348622182273e-05, + "loss": 3.4151, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9043979053475486e-05, + "loss": 3.4177, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9035593105964962e-05, + "loss": 3.3993, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027223537258178e-05, + "loss": 3.4142, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9018837589747658e-05, + "loss": 3.4115, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010451642237138e-05, + "loss": 3.4109, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002065694726615e-05, + "loss": 3.4033, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8993696126019827e-05, + "loss": 3.404, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985310178509307e-05, + "loss": 3.4051, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8976924230998787e-05, + "loss": 3.4091, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8968538283488267e-05, + "loss": 3.41, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896016871478148e-05, + "loss": 3.4076, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895178276727096e-05, + "loss": 3.4082, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943396819760436e-05, + "loss": 3.4073, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935010872249916e-05, + "loss": 3.394, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8926624924739396e-05, + "loss": 3.4183, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891823897722888e-05, + "loss": 3.4023, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890985302971836e-05, + "loss": 3.4191, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890146708220784e-05, + "loss": 3.4019, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893097513501048e-05, + "loss": 3.4169, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8884711565990528e-05, + "loss": 3.4057, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876325618480008e-05, + "loss": 3.4046, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8867939670969488e-05, + "loss": 3.4117, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.88595701022627e-05, + "loss": 3.4056, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.885118415475218e-05, + "loss": 3.4103, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884279820724166e-05, + "loss": 3.424, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883441225973114e-05, + "loss": 3.3964, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826026312220617e-05, + "loss": 3.4193, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8817656743513833e-05, + "loss": 3.4009, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809270796003313e-05, + "loss": 3.4125, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8800884848492793e-05, + "loss": 3.4103, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879249890098227e-05, + "loss": 3.4089, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784129332275482e-05, + "loss": 3.4154, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8775743384764962e-05, + "loss": 3.4121, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876735743725444e-05, + "loss": 3.4097, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.9180495738983154, + "eval_runtime": 305.3143, + "eval_samples_per_second": 1249.83, + "eval_steps_per_second": 39.058, + "step": 1907988 + }, + { + "epoch": 0.0, + "learning_rate": 1.875897148974392e-05, + "loss": 3.4101, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.87505855422334e-05, + "loss": 3.4085, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742215973526614e-05, + "loss": 3.4113, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.873383002601609e-05, + "loss": 3.4105, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.872544407850557e-05, + "loss": 3.4154, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871705813099505e-05, + "loss": 3.4061, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8708672183484534e-05, + "loss": 3.4017, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700286235974014e-05, + "loss": 3.4044, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8691916667267223e-05, + "loss": 3.4102, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683530719756703e-05, + "loss": 3.416, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675144772246183e-05, + "loss": 3.4062, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8666758824735663e-05, + "loss": 3.4129, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658389256028875e-05, + "loss": 3.407, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650003308518355e-05, + "loss": 3.3974, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8641617361007835e-05, + "loss": 3.4043, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633231413497315e-05, + "loss": 3.3946, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8624845465986795e-05, + "loss": 3.3983, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.861645951847627e-05, + "loss": 3.3996, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860807357096575e-05, + "loss": 3.3984, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8599687623455235e-05, + "loss": 3.4274, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591318054748447e-05, + "loss": 3.4127, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8582948486041657e-05, + "loss": 3.4038, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8574562538531137e-05, + "loss": 3.4042, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566176591020616e-05, + "loss": 3.4095, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8557790643510096e-05, + "loss": 3.3921, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8549404695999576e-05, + "loss": 3.4038, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541018748489056e-05, + "loss": 3.4079, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853264917978227e-05, + "loss": 3.3916, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524263232271745e-05, + "loss": 3.3984, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8515877284761225e-05, + "loss": 3.4001, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507491337250705e-05, + "loss": 3.4038, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849910538974019e-05, + "loss": 3.4064, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849071944222967e-05, + "loss": 3.4023, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848233349471915e-05, + "loss": 3.4096, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847394754720863e-05, + "loss": 3.4016, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8465577978501838e-05, + "loss": 3.4049, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457192030991318e-05, + "loss": 3.406, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8448806083480798e-05, + "loss": 3.4043, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440420135970277e-05, + "loss": 3.3937, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843205056726349e-05, + "loss": 3.4051, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842366461975297e-05, + "loss": 3.3969, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841527867224245e-05, + "loss": 3.4135, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8406892724731926e-05, + "loss": 3.4081, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398523156025142e-05, + "loss": 3.4013, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390137208514622e-05, + "loss": 3.4125, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8381751261004102e-05, + "loss": 3.4004, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837336531349358e-05, + "loss": 3.4109, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836499574478679e-05, + "loss": 3.4011, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835660979727627e-05, + "loss": 3.3761, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834822384976575e-05, + "loss": 3.4175, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833983790225523e-05, + "loss": 3.3992, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.833145195474471e-05, + "loss": 3.4083, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832306600723419e-05, + "loss": 3.3984, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.83146964385274e-05, + "loss": 3.4006, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830631049101688e-05, + "loss": 3.3876, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8297924543506363e-05, + "loss": 3.4042, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8289538595995843e-05, + "loss": 3.4106, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281169027289053e-05, + "loss": 3.4077, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8272783079778532e-05, + "loss": 3.4148, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264397132268012e-05, + "loss": 3.3945, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256011184757492e-05, + "loss": 3.3922, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8247641616050705e-05, + "loss": 3.4156, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239255668540185e-05, + "loss": 3.3953, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8230869721029665e-05, + "loss": 3.3925, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8222483773519145e-05, + "loss": 3.4012, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214097826008625e-05, + "loss": 3.4043, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8205711878498105e-05, + "loss": 3.3922, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819732593098758e-05, + "loss": 3.3903, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8188956362280797e-05, + "loss": 3.3927, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8180570414770277e-05, + "loss": 3.3955, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172184467259757e-05, + "loss": 3.41, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8163798519749234e-05, + "loss": 3.3988, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155428951042446e-05, + "loss": 3.4057, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147043003531926e-05, + "loss": 3.3933, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8138657056021406e-05, + "loss": 3.4213, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130271108510886e-05, + "loss": 3.3954, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8121885161000366e-05, + "loss": 3.4119, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8113499213489846e-05, + "loss": 3.3991, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105129644783055e-05, + "loss": 3.3995, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8096743697272535e-05, + "loss": 3.4091, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088357749762018e-05, + "loss": 3.4124, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8079971802251498e-05, + "loss": 3.4029, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8071585854740978e-05, + "loss": 3.405, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063199907230458e-05, + "loss": 3.3936, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8054813959719935e-05, + "loss": 3.396, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046428012209415e-05, + "loss": 3.4009, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.803807482230636e-05, + "loss": 3.4064, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.802968887479584e-05, + "loss": 3.3962, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802130292728532e-05, + "loss": 3.3981, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.80129169797748e-05, + "loss": 3.3977, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.800453103226428e-05, + "loss": 3.4052, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799616146355749e-05, + "loss": 3.4016, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7987775516046972e-05, + "loss": 3.3901, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979389568536452e-05, + "loss": 3.4093, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971003621025932e-05, + "loss": 3.408, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796263405231914e-05, + "loss": 3.4046, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795424810480862e-05, + "loss": 3.3832, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.79458621572981e-05, + "loss": 3.397, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793747620978758e-05, + "loss": 3.3949, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792909026227706e-05, + "loss": 3.4095, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792070431476654e-05, + "loss": 3.404, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791231836725602e-05, + "loss": 3.4026, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.79039324197455e-05, + "loss": 3.399, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789556285103871e-05, + "loss": 3.3998, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887193282331922e-05, + "loss": 3.3921, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7878807334821405e-05, + "loss": 3.3992, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870421387310882e-05, + "loss": 3.3886, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862035439800362e-05, + "loss": 3.4058, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7853665871093575e-05, + "loss": 3.3918, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845279923583054e-05, + "loss": 3.3842, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7836893976072534e-05, + "loss": 3.3979, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7828508028562014e-05, + "loss": 3.3924, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820122081051494e-05, + "loss": 3.4008, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7811736133540974e-05, + "loss": 3.3945, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803350186030454e-05, + "loss": 3.406, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7794964238519934e-05, + "loss": 3.4053, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7786594669813143e-05, + "loss": 3.3905, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778208722302627e-05, + "loss": 3.402, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7769822774792107e-05, + "loss": 3.3986, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7761436827281587e-05, + "loss": 3.3984, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753067258574796e-05, + "loss": 3.3945, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7744681311064276e-05, + "loss": 3.3909, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736295363553756e-05, + "loss": 3.3963, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7727909416043236e-05, + "loss": 3.3949, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7719539847336448e-05, + "loss": 3.4, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711153899825928e-05, + "loss": 3.3967, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7702767952315408e-05, + "loss": 3.3959, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694382004804888e-05, + "loss": 3.4002, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7685996057294364e-05, + "loss": 3.381, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7677610109783844e-05, + "loss": 3.4099, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669224162273328e-05, + "loss": 3.3901, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7660838214762808e-05, + "loss": 3.4105, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652468646056017e-05, + "loss": 3.3899, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764409907734923e-05, + "loss": 3.4054, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763571312983871e-05, + "loss": 3.3982, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762732718232819e-05, + "loss": 3.3894, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761894123481767e-05, + "loss": 3.4011, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.761057166611088e-05, + "loss": 3.3942, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760218571860036e-05, + "loss": 3.4015, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7593799771089838e-05, + "loss": 3.4161, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7585413823579318e-05, + "loss": 3.3852, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577027876068798e-05, + "loss": 3.4026, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756864192855828e-05, + "loss": 3.3937, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756027235985149e-05, + "loss": 3.4002, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755188641234097e-05, + "loss": 3.3997, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754350046483045e-05, + "loss": 3.3996, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753511451731993e-05, + "loss": 3.4014, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752672856980941e-05, + "loss": 3.3992, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518359001102623e-05, + "loss": 3.3987, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.918891668319702, + "eval_runtime": 304.5773, + "eval_samples_per_second": 1252.854, + "eval_steps_per_second": 39.153, + "step": 1984308 + }, + { + "epoch": 0.0, + "learning_rate": 1.7509973053592103e-05, + "loss": 3.3938, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501587106081583e-05, + "loss": 3.3988, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493217537374792e-05, + "loss": 3.398, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7484831589864272e-05, + "loss": 3.4023, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476445642353752e-05, + "loss": 3.406, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468059694843235e-05, + "loss": 3.3955, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7459673747332715e-05, + "loss": 3.3914, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451304178625924e-05, + "loss": 3.3942, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7442918231115404e-05, + "loss": 3.3978, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434532283604884e-05, + "loss": 3.4052, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426146336094364e-05, + "loss": 3.3953, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7417760388583844e-05, + "loss": 3.3979, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409390819877056e-05, + "loss": 3.4008, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401004872366536e-05, + "loss": 3.3845, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392618924856013e-05, + "loss": 3.3981, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384232977345493e-05, + "loss": 3.3818, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7375847029834973e-05, + "loss": 3.3872, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7367461082324453e-05, + "loss": 3.3906, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359075134813936e-05, + "loss": 3.3863, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7350689187303416e-05, + "loss": 3.4101, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342319618596625e-05, + "loss": 3.4049, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7333933671086105e-05, + "loss": 3.3957, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325547723575585e-05, + "loss": 3.3949, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317161776065065e-05, + "loss": 3.3981, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730880858616201e-05, + "loss": 3.3828, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300422638651487e-05, + "loss": 3.3973, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292036691140967e-05, + "loss": 3.3937, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7283650743630447e-05, + "loss": 3.3787, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275264796119927e-05, + "loss": 3.3855, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726689522741314e-05, + "loss": 3.3877, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725850927990262e-05, + "loss": 3.3965, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.72501233323921e-05, + "loss": 3.3953, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724173738488158e-05, + "loss": 3.3917, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233367816174788e-05, + "loss": 3.4009, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7224981868664268e-05, + "loss": 3.3874, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721659592115375e-05, + "loss": 3.3971, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720820997364323e-05, + "loss": 3.3992, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719984040493644e-05, + "loss": 3.3863, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719145445742592e-05, + "loss": 3.3848, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.71830685099154e-05, + "loss": 3.3919, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717468256240488e-05, + "loss": 3.3871, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716629661489436e-05, + "loss": 3.3993, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7157910667383843e-05, + "loss": 3.3979, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149541098677053e-05, + "loss": 3.3971, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141155151166533e-05, + "loss": 3.3969, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7132769203656012e-05, + "loss": 3.3931, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124383256145492e-05, + "loss": 3.399, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.711599730863497e-05, + "loss": 3.394, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107627739928185e-05, + "loss": 3.364, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099241792417665e-05, + "loss": 3.4031, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709085584490714e-05, + "loss": 3.388, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.708246989739662e-05, + "loss": 3.4006, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074100328689834e-05, + "loss": 3.3905, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7065714381179314e-05, + "loss": 3.3902, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057328433668794e-05, + "loss": 3.3776, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7048942486158274e-05, + "loss": 3.3957, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040556538647754e-05, + "loss": 3.3989, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032186969940966e-05, + "loss": 3.3954, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7023801022430443e-05, + "loss": 3.4055, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7015415074919923e-05, + "loss": 3.3884, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007029127409406e-05, + "loss": 3.3751, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998659558702615e-05, + "loss": 3.4064, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990273611192095e-05, + "loss": 3.3856, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6981887663681575e-05, + "loss": 3.3768, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973501716171055e-05, + "loss": 3.394, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965115768660535e-05, + "loss": 3.3935, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6956729821150015e-05, + "loss": 3.3844, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948360252443227e-05, + "loss": 3.384, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6939974304932707e-05, + "loss": 3.3827, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931588357422187e-05, + "loss": 3.3797, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923202409911667e-05, + "loss": 3.3998, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6914816462401147e-05, + "loss": 3.3911, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906430514890624e-05, + "loss": 3.3919, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689806094618384e-05, + "loss": 3.3832, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688967499867332e-05, + "loss": 3.4039, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881289051162796e-05, + "loss": 3.3892, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6872903103652276e-05, + "loss": 3.4031, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864517156141756e-05, + "loss": 3.388, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.685614758743497e-05, + "loss": 3.3887, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684776163992445e-05, + "loss": 3.3989, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683937569241393e-05, + "loss": 3.4024, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683098974490341e-05, + "loss": 3.3904, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682260379739289e-05, + "loss": 3.399, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681421784988237e-05, + "loss": 3.3794, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6805831902371848e-05, + "loss": 3.3859, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797445954861328e-05, + "loss": 3.3905, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.678907638615454e-05, + "loss": 3.3945, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.678069043864402e-05, + "loss": 3.3872, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.67723044911335e-05, + "loss": 3.3851, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6763918543622977e-05, + "loss": 3.3893, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.675554897491619e-05, + "loss": 3.392, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.674716302740567e-05, + "loss": 3.3919, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6738777079895153e-05, + "loss": 3.3793, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.673039113238463e-05, + "loss": 3.3972, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.672200518487411e-05, + "loss": 3.3981, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671361923736359e-05, + "loss": 3.3946, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670523328985307e-05, + "loss": 3.3668, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6696863721146282e-05, + "loss": 3.3901, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688477773635762e-05, + "loss": 3.3849, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680091826125242e-05, + "loss": 3.399, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6671705878614722e-05, + "loss": 3.3941, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666333630990793e-05, + "loss": 3.3924, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665495036239741e-05, + "loss": 3.3843, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664656441488689e-05, + "loss": 3.3876, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638194846180103e-05, + "loss": 3.3818, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6629808898669583e-05, + "loss": 3.388, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621422951159063e-05, + "loss": 3.3808, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613037003648543e-05, + "loss": 3.3965, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604667434941752e-05, + "loss": 3.3816, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596281487431236e-05, + "loss": 3.3772, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6587895539920716e-05, + "loss": 3.3816, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579509592410196e-05, + "loss": 3.3847, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571123644899675e-05, + "loss": 3.3908, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6562737697389155e-05, + "loss": 3.3834, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554351749878632e-05, + "loss": 3.3943, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6545965802368112e-05, + "loss": 3.3962, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6537596233661324e-05, + "loss": 3.3797, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529210286150808e-05, + "loss": 3.3892, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6520824338640284e-05, + "loss": 3.3874, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512438391129764e-05, + "loss": 3.3893, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504068822422977e-05, + "loss": 3.3872, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6495682874912453e-05, + "loss": 3.3769, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487296927401937e-05, + "loss": 3.3894, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6478910979891417e-05, + "loss": 3.3832, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647054141118463e-05, + "loss": 3.3874, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462155463674106e-05, + "loss": 3.3856, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6453769516163586e-05, + "loss": 3.3843, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445383568653066e-05, + "loss": 3.3851, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6436997621142546e-05, + "loss": 3.3718, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642861167363203e-05, + "loss": 3.3958, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.642022572612151e-05, + "loss": 3.3814, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641183977861099e-05, + "loss": 3.4016, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403470209904198e-05, + "loss": 3.3791, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395100641197407e-05, + "loss": 3.3952, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638671469368689e-05, + "loss": 3.3916, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637832874617637e-05, + "loss": 3.3785, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.636994279866585e-05, + "loss": 3.3909, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636157322995906e-05, + "loss": 3.3807, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635318728244854e-05, + "loss": 3.3943, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634480133493802e-05, + "loss": 3.3952, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.63364153874275e-05, + "loss": 3.3814, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632802943991698e-05, + "loss": 3.3893, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319643492406463e-05, + "loss": 3.3845, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.631125754489594e-05, + "loss": 3.3911, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630288797618915e-05, + "loss": 3.3851, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629450202867863e-05, + "loss": 3.3964, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286116081168108e-05, + "loss": 3.3833, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627773013365759e-05, + "loss": 3.3938, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269360564950804e-05, + "loss": 3.3864, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.922898769378662, + "eval_runtime": 306.3964, + "eval_samples_per_second": 1245.416, + "eval_steps_per_second": 38.92, + "step": 2060628 + }, + { + "epoch": 0.0, + "learning_rate": 1.6260974617440284e-05, + "loss": 3.3832, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625258866992976e-05, + "loss": 3.3843, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244219101222973e-05, + "loss": 3.3884, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6235833153712453e-05, + "loss": 3.3913, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6227447206201933e-05, + "loss": 3.3992, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219061258691413e-05, + "loss": 3.3807, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6210675311180893e-05, + "loss": 3.3829, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202305742474105e-05, + "loss": 3.3849, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6193919794963582e-05, + "loss": 3.388, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6185533847453062e-05, + "loss": 3.3917, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6177147899942545e-05, + "loss": 3.3827, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6168761952432025e-05, + "loss": 3.3874, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6160392383725234e-05, + "loss": 3.3932, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152006436214714e-05, + "loss": 3.3747, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6143620488704194e-05, + "loss": 3.3827, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135234541193674e-05, + "loss": 3.3739, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6126848593683154e-05, + "loss": 3.3754, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118462646172637e-05, + "loss": 3.3818, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110093077465846e-05, + "loss": 3.3803, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6101707129955326e-05, + "loss": 3.3963, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093321182444806e-05, + "loss": 3.3944, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6084935234934286e-05, + "loss": 3.3853, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6076549287423763e-05, + "loss": 3.3846, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068163339913246e-05, + "loss": 3.3828, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6059777392402726e-05, + "loss": 3.3749, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.605140782369594e-05, + "loss": 3.3886, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043021876185415e-05, + "loss": 3.3824, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6034635928674895e-05, + "loss": 3.3687, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026249981164375e-05, + "loss": 3.3763, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6017864033653855e-05, + "loss": 3.3806, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6009494464947068e-05, + "loss": 3.3864, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001108517436548e-05, + "loss": 3.3801, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5992722569926027e-05, + "loss": 3.3838, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5984336622415507e-05, + "loss": 3.3867, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5975950674904987e-05, + "loss": 3.3759, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.59675811061982e-05, + "loss": 3.3899, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595919515868768e-05, + "loss": 3.3906, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595080921117716e-05, + "loss": 3.3756, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594242326366664e-05, + "loss": 3.3793, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593405369495985e-05, + "loss": 3.3771, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592566774744933e-05, + "loss": 3.3791, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591728179993881e-05, + "loss": 3.3878, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5908895852428292e-05, + "loss": 3.3854, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590050990491777e-05, + "loss": 3.3873, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.589214033621098e-05, + "loss": 3.3861, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.588375438870046e-05, + "loss": 3.3846, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587536844118994e-05, + "loss": 3.3845, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5866982493679418e-05, + "loss": 3.3825, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5858612924972633e-05, + "loss": 3.3571, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850226977462113e-05, + "loss": 3.3943, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5841841029951593e-05, + "loss": 3.376, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583345508244107e-05, + "loss": 3.3899, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582506913493055e-05, + "loss": 3.3816, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5816699566223762e-05, + "loss": 3.3765, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5808313618713242e-05, + "loss": 3.3698, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5799927671202722e-05, + "loss": 3.3812, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5791541723692202e-05, + "loss": 3.3966, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783172154985415e-05, + "loss": 3.3781, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577478620747489e-05, + "loss": 3.3974, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576640025996437e-05, + "loss": 3.3784, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758014312453855e-05, + "loss": 3.3613, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5749628364943335e-05, + "loss": 3.3941, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741258796236544e-05, + "loss": 3.3794, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5732872848726024e-05, + "loss": 3.3682, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5724486901215504e-05, + "loss": 3.3822, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716100953704984e-05, + "loss": 3.3798, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5707715006194464e-05, + "loss": 3.3695, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699345437487676e-05, + "loss": 3.3747, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5690959489977156e-05, + "loss": 3.3687, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5682573542466636e-05, + "loss": 3.3762, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674187594956116e-05, + "loss": 3.3878, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5665801647445596e-05, + "loss": 3.3801, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5657432078738808e-05, + "loss": 3.3837, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649046131228288e-05, + "loss": 3.3734, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5640660183717768e-05, + "loss": 3.3913, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632274236207245e-05, + "loss": 3.3848, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5623888288696725e-05, + "loss": 3.3908, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5615502341186205e-05, + "loss": 3.376, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607132772479417e-05, + "loss": 3.3764, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5598746824968897e-05, + "loss": 3.3867, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590360877458377e-05, + "loss": 3.3957, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5581974929947857e-05, + "loss": 3.3798, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5573588982437337e-05, + "loss": 3.3881, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565203034926817e-05, + "loss": 3.3681, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5556817087416297e-05, + "loss": 3.3754, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548431139905777e-05, + "loss": 3.3757, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.554006157119899e-05, + "loss": 3.3885, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553167562368847e-05, + "loss": 3.3762, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552330605498168e-05, + "loss": 3.3755, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551492010747116e-05, + "loss": 3.38, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550653415996064e-05, + "loss": 3.3784, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498148212450118e-05, + "loss": 3.3836, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548977864374333e-05, + "loss": 3.3702, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548139269623281e-05, + "loss": 3.3827, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547300674872229e-05, + "loss": 3.3917, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546462080121177e-05, + "loss": 3.3845, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545623485370125e-05, + "loss": 3.3594, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544784890619073e-05, + "loss": 3.3742, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.543946295868021e-05, + "loss": 3.3754, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431093389973423e-05, + "loss": 3.3887, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.54227074424629e-05, + "loss": 3.3869, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541432149495238e-05, + "loss": 3.3806, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540593554744186e-05, + "loss": 3.3751, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539754959993134e-05, + "loss": 3.3809, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389180031224552e-05, + "loss": 3.3702, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5380794083714032e-05, + "loss": 3.3778, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372408136203512e-05, + "loss": 3.3728, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364022188692992e-05, + "loss": 3.3813, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.53556526199862e-05, + "loss": 3.375, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5347266672475684e-05, + "loss": 3.364, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5338880724965164e-05, + "loss": 3.3732, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330494777454644e-05, + "loss": 3.371, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322108829944124e-05, + "loss": 3.3837, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5313722882433604e-05, + "loss": 3.3728, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530533693492308e-05, + "loss": 3.3817, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529695098741256e-05, + "loss": 3.3817, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5288581418705773e-05, + "loss": 3.3735, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280211849998986e-05, + "loss": 3.3806, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5271825902488465e-05, + "loss": 3.3801, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263439954977945e-05, + "loss": 3.3795, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255054007467425e-05, + "loss": 3.3718, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5246684438760636e-05, + "loss": 3.3689, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238298491250116e-05, + "loss": 3.3804, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5229912543739596e-05, + "loss": 3.3738, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5221526596229078e-05, + "loss": 3.3795, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213140648718554e-05, + "loss": 3.3772, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5204771080011768e-05, + "loss": 3.3723, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196385132501248e-05, + "loss": 3.3717, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5187999184990728e-05, + "loss": 3.365, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5179613237480207e-05, + "loss": 3.3828, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171227289969687e-05, + "loss": 3.3735, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5162841342459167e-05, + "loss": 3.3876, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154455394948647e-05, + "loss": 3.3663, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146085826241857e-05, + "loss": 3.3861, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5137699878731337e-05, + "loss": 3.3779, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129313931220817e-05, + "loss": 3.3681, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5120927983710297e-05, + "loss": 3.3775, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5112558415003508e-05, + "loss": 3.3738, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104172467492988e-05, + "loss": 3.3874, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.509578651998247e-05, + "loss": 3.3847, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.508740057247195e-05, + "loss": 3.3744, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.507901462496143e-05, + "loss": 3.373, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.507062867745091e-05, + "loss": 3.3772, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.506225910874412e-05, + "loss": 3.3837, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.50538731612336e-05, + "loss": 3.3716, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.504548721372308e-05, + "loss": 3.3875, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037101266212558e-05, + "loss": 3.3754, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5028715318702038e-05, + "loss": 3.3832, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.502034574999525e-05, + "loss": 3.375, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.9231534004211426, + "eval_runtime": 308.2309, + "eval_samples_per_second": 1238.004, + "eval_steps_per_second": 38.689, + "step": 2136948 + }, + { + "epoch": 1.0, + "learning_rate": 1.5011959802484732e-05, + "loss": 3.3764, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5003573854974209e-05, + "loss": 3.3747, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995187907463689e-05, + "loss": 3.3786, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.498680195995317e-05, + "loss": 3.3785, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978432391246383e-05, + "loss": 3.3892, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970046443735861e-05, + "loss": 3.3728, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4961660496225341e-05, + "loss": 3.3717, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953274548714821e-05, + "loss": 3.3772, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4944888601204301e-05, + "loss": 3.376, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4936502653693781e-05, + "loss": 3.3766, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928116706183263e-05, + "loss": 3.3763, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4919747137476472e-05, + "loss": 3.3791, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911377568769683e-05, + "loss": 3.3845, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4902991621259163e-05, + "loss": 3.3659, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4894605673748643e-05, + "loss": 3.3711, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886219726238124e-05, + "loss": 3.3628, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4877833778727604e-05, + "loss": 3.364, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4869447831217084e-05, + "loss": 3.3709, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861061883706564e-05, + "loss": 3.3681, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4852675936196042e-05, + "loss": 3.3852, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844306367489255e-05, + "loss": 3.3857, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4835920419978735e-05, + "loss": 3.3749, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4827534472468213e-05, + "loss": 3.3729, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819148524957693e-05, + "loss": 3.3751, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4810795335054636e-05, + "loss": 3.3626, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4802409387544116e-05, + "loss": 3.3804, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794023440033596e-05, + "loss": 3.367, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4785637492523078e-05, + "loss": 3.3587, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777251545012558e-05, + "loss": 3.3715, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4768881976305767e-05, + "loss": 3.3664, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4760496028795249e-05, + "loss": 3.3731, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752110081284729e-05, + "loss": 3.3696, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4743724133774209e-05, + "loss": 3.3791, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735338186263687e-05, + "loss": 3.3722, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4726952238753167e-05, + "loss": 3.3661, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471858267004638e-05, + "loss": 3.38, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.471019672253586e-05, + "loss": 3.3788, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4701810775025338e-05, + "loss": 3.3682, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4693424827514817e-05, + "loss": 3.3668, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685055258808032e-05, + "loss": 3.3686, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4676669311297512e-05, + "loss": 3.3652, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668283363786988e-05, + "loss": 3.3772, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.465989741627647e-05, + "loss": 3.3764, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.465151146876595e-05, + "loss": 3.3779, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.464312552125543e-05, + "loss": 3.3754, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.463473957374491e-05, + "loss": 3.3707, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462637000503812e-05, + "loss": 3.3783, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.46179840575276e-05, + "loss": 3.3724, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.460959811001708e-05, + "loss": 3.351, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601212162506562e-05, + "loss": 3.3812, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4592842593799771e-05, + "loss": 3.3667, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584456646289251e-05, + "loss": 3.3771, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576070698778733e-05, + "loss": 3.3694, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4567684751268213e-05, + "loss": 3.3711, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559315182561423e-05, + "loss": 3.3565, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4550929235050903e-05, + "loss": 3.3659, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4542543287540383e-05, + "loss": 3.3874, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534157340029863e-05, + "loss": 3.3726, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4525787771323074e-05, + "loss": 3.3835, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4517401823812554e-05, + "loss": 3.3665, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509015876302034e-05, + "loss": 3.3505, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4500629928791514e-05, + "loss": 3.3855, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492243981280992e-05, + "loss": 3.3677, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4483874412574205e-05, + "loss": 3.3592, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4475488465063686e-05, + "loss": 3.3729, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467102517553166e-05, + "loss": 3.368, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4458716570042643e-05, + "loss": 3.361, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450347001335857e-05, + "loss": 3.3643, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4441961053825337e-05, + "loss": 3.3591, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4433575106314814e-05, + "loss": 3.3664, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425189158804295e-05, + "loss": 3.3742, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4416803211293775e-05, + "loss": 3.3709, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408433642586988e-05, + "loss": 3.3733, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400047695076466e-05, + "loss": 3.3603, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4391661747565946e-05, + "loss": 3.3803, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383275800055426e-05, + "loss": 3.3721, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4374889852544906e-05, + "loss": 3.3823, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4366520283838117e-05, + "loss": 3.3656, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358134336327597e-05, + "loss": 3.3665, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4349748388817078e-05, + "loss": 3.3769, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341362441306558e-05, + "loss": 3.3805, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4332992872599767e-05, + "loss": 3.3733, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4324606925089249e-05, + "loss": 3.3772, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316220977578729e-05, + "loss": 3.3595, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4307835030068209e-05, + "loss": 3.3646, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299449082557689e-05, + "loss": 3.3678, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.429106313504717e-05, + "loss": 3.3793, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4282677187536647e-05, + "loss": 3.3653, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.427430761882986e-05, + "loss": 3.3687, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4265921671319341e-05, + "loss": 3.3686, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4257535723808818e-05, + "loss": 3.3681, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249149776298298e-05, + "loss": 3.3706, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424076382878778e-05, + "loss": 3.3634, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232394260080992e-05, + "loss": 3.3715, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422400831257047e-05, + "loss": 3.3809, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421562236505995e-05, + "loss": 3.3776, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420723641754943e-05, + "loss": 3.3478, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.419885047003891e-05, + "loss": 3.3688, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.419046452252839e-05, + "loss": 3.3637, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.41820949538216e-05, + "loss": 3.3776, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417370900631108e-05, + "loss": 3.3767, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.416532305880056e-05, + "loss": 3.3666, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4156937111290042e-05, + "loss": 3.3624, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4148551163779522e-05, + "loss": 3.3687, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140181595072733e-05, + "loss": 3.3663, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4131795647562213e-05, + "loss": 3.3671, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123409700051693e-05, + "loss": 3.3608, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115023752541173e-05, + "loss": 3.3709, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4106654183834384e-05, + "loss": 3.3658, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098268236323864e-05, + "loss": 3.3548, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4089882288813344e-05, + "loss": 3.3611, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4081496341302825e-05, + "loss": 3.3607, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073110393792302e-05, + "loss": 3.3721, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4064724446281782e-05, + "loss": 3.3622, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056354877574996e-05, + "loss": 3.3723, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4047968930064473e-05, + "loss": 3.37, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4039582982553952e-05, + "loss": 3.3687, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031197035043434e-05, + "loss": 3.3672, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4022811087532914e-05, + "loss": 3.3695, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4014441518826125e-05, + "loss": 3.3704, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006055571315605e-05, + "loss": 3.3614, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3997669623805085e-05, + "loss": 3.3587, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989283676294565e-05, + "loss": 3.3695, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3980914107587776e-05, + "loss": 3.3646, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3972528160077255e-05, + "loss": 3.3673, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964142212566735e-05, + "loss": 3.364, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3955756265056217e-05, + "loss": 3.3641, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947370317545697e-05, + "loss": 3.3619, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939000748838906e-05, + "loss": 3.3578, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3930614801328388e-05, + "loss": 3.3692, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922228853817868e-05, + "loss": 3.3684, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3913842906307348e-05, + "loss": 3.3767, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905456958796828e-05, + "loss": 3.3568, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897087390090038e-05, + "loss": 3.3687, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3888701442579518e-05, + "loss": 3.3699, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880315495068998e-05, + "loss": 3.3589, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.387192954755848e-05, + "loss": 3.366, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3863543600047957e-05, + "loss": 3.3648, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855174031341169e-05, + "loss": 3.3739, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.384678808383065e-05, + "loss": 3.3754, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838402136320127e-05, + "loss": 3.3684, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830016188809607e-05, + "loss": 3.3615, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3821646620102821e-05, + "loss": 3.3686, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813260672592301e-05, + "loss": 3.3728, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.380487472508178e-05, + "loss": 3.3585, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.379648877757126e-05, + "loss": 3.3815, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.378810283006074e-05, + "loss": 3.3625, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.377973326135395e-05, + "loss": 3.3727, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.377134731384343e-05, + "loss": 3.3676, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.924819231033325, + "eval_runtime": 311.0917, + "eval_samples_per_second": 1226.619, + "eval_steps_per_second": 38.333, + "step": 2213268 + }, + { + "epoch": 0.0, + "learning_rate": 1.376296136633291e-05, + "loss": 3.3743, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3754591797626123e-05, + "loss": 3.3639, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3746205850115601e-05, + "loss": 3.3652, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3737819902605081e-05, + "loss": 3.3704, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3729433955094561e-05, + "loss": 3.3754, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721048007584043e-05, + "loss": 3.3646, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3712662060073522e-05, + "loss": 3.3621, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704276112563002e-05, + "loss": 3.3617, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3695890165052482e-05, + "loss": 3.3664, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3687520596345693e-05, + "loss": 3.3694, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679134648835173e-05, + "loss": 3.365, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3670748701324653e-05, + "loss": 3.3699, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662379132617864e-05, + "loss": 3.3719, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3653993185107344e-05, + "loss": 3.353, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3645607237596826e-05, + "loss": 3.3626, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637221290086305e-05, + "loss": 3.3529, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3628835342575782e-05, + "loss": 3.3479, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3620449395065264e-05, + "loss": 3.365, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612063447554744e-05, + "loss": 3.3552, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3603677500044224e-05, + "loss": 3.3711, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595307931337434e-05, + "loss": 3.3775, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3586938362630647e-05, + "loss": 3.3657, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3578552415120127e-05, + "loss": 3.3631, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570166467609605e-05, + "loss": 3.3662, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3561780520099085e-05, + "loss": 3.3504, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553394572588565e-05, + "loss": 3.3715, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545008625078045e-05, + "loss": 3.3579, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3536622677567527e-05, + "loss": 3.3553, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528253108860736e-05, + "loss": 3.3587, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3519867161350216e-05, + "loss": 3.3542, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3511481213839697e-05, + "loss": 3.3636, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503095266329177e-05, + "loss": 3.3603, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3494709318818657e-05, + "loss": 3.3691, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486323371308137e-05, + "loss": 3.3629, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3477937423797615e-05, + "loss": 3.3558, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3469567855090828e-05, + "loss": 3.3613, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461181907580308e-05, + "loss": 3.3722, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3452795960069786e-05, + "loss": 3.3591, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444426391362999e-05, + "loss": 3.3572, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.343604044385248e-05, + "loss": 3.3562, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.342765449634196e-05, + "loss": 3.3617, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419268548831437e-05, + "loss": 3.3611, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3410882601320918e-05, + "loss": 3.3676, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3402513032614131e-05, + "loss": 3.3692, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394127085103611e-05, + "loss": 3.366, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3385741137593089e-05, + "loss": 3.3634, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377355190082569e-05, + "loss": 3.3625, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3368985621375782e-05, + "loss": 3.3647, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.336059967386526e-05, + "loss": 3.3397, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.335221372635474e-05, + "loss": 3.3693, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.334382777884422e-05, + "loss": 3.3602, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.33354418313337e-05, + "loss": 3.3669, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.332707226262691e-05, + "loss": 3.3598, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.331868631511639e-05, + "loss": 3.3579, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310300367605872e-05, + "loss": 3.3495, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3301914420095352e-05, + "loss": 3.3557, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3293544851388561e-05, + "loss": 3.3759, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285158903878043e-05, + "loss": 3.3559, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3276772956367523e-05, + "loss": 3.3759, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268387008857003e-05, + "loss": 3.3581, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260001061346483e-05, + "loss": 3.3465, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3251615113835963e-05, + "loss": 3.3739, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243245545129173e-05, + "loss": 3.3592, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3234859597618653e-05, + "loss": 3.3475, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3226473650108135e-05, + "loss": 3.3572, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218087702597615e-05, + "loss": 3.3615, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3209701755087092e-05, + "loss": 3.3491, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201332186380306e-05, + "loss": 3.3565, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3192946238869786e-05, + "loss": 3.3522, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3184560291359262e-05, + "loss": 3.3492, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176174343848744e-05, + "loss": 3.3696, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3167788396338224e-05, + "loss": 3.3629, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3159418827631436e-05, + "loss": 3.3585, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151032880120915e-05, + "loss": 3.3519, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3142646932610395e-05, + "loss": 3.3715, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134260985099875e-05, + "loss": 3.3619, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3125891416393089e-05, + "loss": 3.3746, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3117505468882565e-05, + "loss": 3.356, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109119521372045e-05, + "loss": 3.357, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3100733573861527e-05, + "loss": 3.3673, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092364005154736e-05, + "loss": 3.3677, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3083978057644216e-05, + "loss": 3.3628, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3075592110133698e-05, + "loss": 3.3667, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067206162623178e-05, + "loss": 3.3509, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3058820215112657e-05, + "loss": 3.3519, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050434267602137e-05, + "loss": 3.3587, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042064698895348e-05, + "loss": 3.3649, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3033678751384828e-05, + "loss": 3.3593, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025292803874308e-05, + "loss": 3.355, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.301690685636379e-05, + "loss": 3.3584, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3008537287656999e-05, + "loss": 3.36, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.300015134014648e-05, + "loss": 3.3546, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.299176539263596e-05, + "loss": 3.3576, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.298337944512544e-05, + "loss": 3.3629, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975009876418651e-05, + "loss": 3.3686, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2966623928908131e-05, + "loss": 3.3674, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958237981397611e-05, + "loss": 3.3392, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2949852033887091e-05, + "loss": 3.3564, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294146608637657e-05, + "loss": 3.3512, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.293308013886605e-05, + "loss": 3.3692, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.292469419135553e-05, + "loss": 3.3634, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.291630824384501e-05, + "loss": 3.3619, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290793867513822e-05, + "loss": 3.3507, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.28995527276277e-05, + "loss": 3.3631, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891166780117182e-05, + "loss": 3.3563, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2882780832606662e-05, + "loss": 3.3562, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874394885096142e-05, + "loss": 3.3501, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866008937585621e-05, + "loss": 3.3592, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.28576229900751e-05, + "loss": 3.3581, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849253421368312e-05, + "loss": 3.342, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2840883852661523e-05, + "loss": 3.354, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2832497905151003e-05, + "loss": 3.3461, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824111957640483e-05, + "loss": 3.363, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2815726010129963e-05, + "loss": 3.3562, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807340062619445e-05, + "loss": 3.3605, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2798954115108924e-05, + "loss": 3.3601, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2790568167598401e-05, + "loss": 3.3577, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782198598891615e-05, + "loss": 3.3541, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2773812651381095e-05, + "loss": 3.3589, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765426703870573e-05, + "loss": 3.3633, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757040756360053e-05, + "loss": 3.3501, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2748654808849533e-05, + "loss": 3.347, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740285240142746e-05, + "loss": 3.359, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2731899292632224e-05, + "loss": 3.3557, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2723513345121704e-05, + "loss": 3.356, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715127397611184e-05, + "loss": 3.3509, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2706757828904398e-05, + "loss": 3.3583, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698371881393875e-05, + "loss": 3.3566, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2689985933883355e-05, + "loss": 3.3482, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2681599986372836e-05, + "loss": 3.3511, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673214038862316e-05, + "loss": 3.36, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2664828091351796e-05, + "loss": 3.3697, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2656458522645007e-05, + "loss": 3.3479, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648072575134487e-05, + "loss": 3.3536, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2639686627623967e-05, + "loss": 3.365, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631300680113447e-05, + "loss": 3.3517, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2622931111406658e-05, + "loss": 3.3517, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2614545163896138e-05, + "loss": 3.3538, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606159216385618e-05, + "loss": 3.3652, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.25977732688751e-05, + "loss": 3.3688, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589387321364576e-05, + "loss": 3.3575, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581001373854056e-05, + "loss": 3.3483, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.257263180514727e-05, + "loss": 3.3583, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.256424585763675e-05, + "loss": 3.3623, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2555859910126228e-05, + "loss": 3.3494, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2547473962615708e-05, + "loss": 3.3701, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539088015105188e-05, + "loss": 3.3527, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.25307184463984e-05, + "loss": 3.3621, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2522332498887879e-05, + "loss": 3.3576, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.926471471786499, + "eval_runtime": 308.2362, + "eval_samples_per_second": 1237.983, + "eval_steps_per_second": 38.688, + "step": 2289588 + }, + { + "epoch": 1.0, + "learning_rate": 1.2513946551377359e-05, + "loss": 3.3613, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2505560603866839e-05, + "loss": 3.3507, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497191035160051e-05, + "loss": 3.3543, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2488805087649531e-05, + "loss": 3.3629, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.248041914013901e-05, + "loss": 3.361, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472033192628491e-05, + "loss": 3.3601, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2463647245117971e-05, + "loss": 3.3527, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455277676411182e-05, + "loss": 3.3526, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2446891728900662e-05, + "loss": 3.3544, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2438505781390142e-05, + "loss": 3.3608, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430119833879622e-05, + "loss": 3.3541, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2421733886369102e-05, + "loss": 3.3633, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413364317662312e-05, + "loss": 3.3623, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2404978370151792e-05, + "loss": 3.3396, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2396592422641274e-05, + "loss": 3.3559, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388206475130752e-05, + "loss": 3.34, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2379820527620232e-05, + "loss": 3.3398, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371434580109712e-05, + "loss": 3.3558, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363048632599192e-05, + "loss": 3.3435, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2354662685088672e-05, + "loss": 3.3627, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346293116381883e-05, + "loss": 3.3683, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2337907168871365e-05, + "loss": 3.3511, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2329521221360843e-05, + "loss": 3.3572, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321135273850323e-05, + "loss": 3.3562, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2312765705143535e-05, + "loss": 3.341, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304379757633014e-05, + "loss": 3.3586, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2295993810122494e-05, + "loss": 3.3476, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2287607862611975e-05, + "loss": 3.3476, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279221915101455e-05, + "loss": 3.3498, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2270852346394664e-05, + "loss": 3.3438, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2262466398884146e-05, + "loss": 3.3504, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254080451373626e-05, + "loss": 3.3536, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2245694503863104e-05, + "loss": 3.3604, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237308556352586e-05, + "loss": 3.3492, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2228922608842066e-05, + "loss": 3.3484, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2220536661331546e-05, + "loss": 3.3504, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212150713821024e-05, + "loss": 3.3665, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2203781145114236e-05, + "loss": 3.3469, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195411576407447e-05, + "loss": 3.3474, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187025628896929e-05, + "loss": 3.3472, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2178639681386407e-05, + "loss": 3.3486, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170253733875887e-05, + "loss": 3.3524, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2161867786365367e-05, + "loss": 3.3584, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2153498217658578e-05, + "loss": 3.3624, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145112270148058e-05, + "loss": 3.355, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2136726322637538e-05, + "loss": 3.3538, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.212834037512702e-05, + "loss": 3.3521, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2119954427616498e-05, + "loss": 3.3577, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.211158485890971e-05, + "loss": 3.3281, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.210319891139919e-05, + "loss": 3.3575, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2094812963888668e-05, + "loss": 3.3538, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2086427016378148e-05, + "loss": 3.357, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.207805744767136e-05, + "loss": 3.3457, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.206967150016084e-05, + "loss": 3.3456, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.206128555265032e-05, + "loss": 3.343, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.20528996051398e-05, + "loss": 3.3444, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.204451365762928e-05, + "loss": 3.3638, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036127710118759e-05, + "loss": 3.3502, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2027758141411971e-05, + "loss": 3.365, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2019372193901451e-05, + "loss": 3.3456, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2010986246390931e-05, + "loss": 3.3366, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2002600298880411e-05, + "loss": 3.3666, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994230730173622e-05, + "loss": 3.3463, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1985844782663102e-05, + "loss": 3.3375, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1977458835152582e-05, + "loss": 3.3483, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969072887642062e-05, + "loss": 3.3503, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1960686940131542e-05, + "loss": 3.3404, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952300992621022e-05, + "loss": 3.3459, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1943915045110502e-05, + "loss": 3.341, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1935545476403713e-05, + "loss": 3.3405, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927159528893194e-05, + "loss": 3.3566, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1918773581382672e-05, + "loss": 3.3555, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910387633872152e-05, + "loss": 3.3484, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902018065165365e-05, + "loss": 3.3422, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1893632117654845e-05, + "loss": 3.3594, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885246170144323e-05, + "loss": 3.3526, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1876860222633803e-05, + "loss": 3.3612, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1868474275123285e-05, + "loss": 3.3484, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860088327612763e-05, + "loss": 3.3443, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1851718758905975e-05, + "loss": 3.3568, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843332811395455e-05, + "loss": 3.3563, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1834946863884935e-05, + "loss": 3.3543, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1826560916374414e-05, + "loss": 3.3577, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818174968863895e-05, + "loss": 3.3472, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1809789021353375e-05, + "loss": 3.336, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801403073842853e-05, + "loss": 3.3496, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793033505136066e-05, + "loss": 3.3559, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1784647557625546e-05, + "loss": 3.346, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1776277988918757e-05, + "loss": 3.3473, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1767892041408237e-05, + "loss": 3.3469, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1759506093897717e-05, + "loss": 3.3505, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751120146387197e-05, + "loss": 3.3466, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1742750577680409e-05, + "loss": 3.3453, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734364630169887e-05, + "loss": 3.3555, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1725978682659367e-05, + "loss": 3.3527, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1717592735148849e-05, + "loss": 3.3608, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1709206787638327e-05, + "loss": 3.3263, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1700820840127807e-05, + "loss": 3.348, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1692434892617287e-05, + "loss": 3.3445, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1684048945106769e-05, + "loss": 3.3554, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1675679376399978e-05, + "loss": 3.3535, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1667293428889458e-05, + "loss": 3.3501, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.165892386018267e-05, + "loss": 3.3412, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.165053791267215e-05, + "loss": 3.3522, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.164215196516163e-05, + "loss": 3.3493, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.163376601765111e-05, + "loss": 3.3441, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.162538007014059e-05, + "loss": 3.3393, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1616994122630068e-05, + "loss": 3.3474, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1608624553923281e-05, + "loss": 3.3502, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.160023860641276e-05, + "loss": 3.3368, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.159185265890224e-05, + "loss": 3.3455, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158346671139172e-05, + "loss": 3.3308, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.15750807638812e-05, + "loss": 3.3536, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.156669481637068e-05, + "loss": 3.3416, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.155830886886016e-05, + "loss": 3.3464, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1549939300153371e-05, + "loss": 3.352, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1541553352642851e-05, + "loss": 3.3531, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533167405132331e-05, + "loss": 3.3408, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1524781457621811e-05, + "loss": 3.3506, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516411888915022e-05, + "loss": 3.3539, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508025941404504e-05, + "loss": 3.3363, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1499639993893982e-05, + "loss": 3.3349, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491254046383462e-05, + "loss": 3.3504, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1482868098872942e-05, + "loss": 3.3476, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1474482151362424e-05, + "loss": 3.3507, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466096203851902e-05, + "loss": 3.3434, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1457726635145114e-05, + "loss": 3.346, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449340687634594e-05, + "loss": 3.3459, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1440954740124072e-05, + "loss": 3.3366, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1432568792613552e-05, + "loss": 3.3377, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424182845103034e-05, + "loss": 3.3541, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1415796897592512e-05, + "loss": 3.3578, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1407427328885723e-05, + "loss": 3.342, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399041381375205e-05, + "loss": 3.3436, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1390655433864685e-05, + "loss": 3.3528, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382269486354163e-05, + "loss": 3.3431, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1373899917647376e-05, + "loss": 3.3425, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1365513970136855e-05, + "loss": 3.3439, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1357128022626335e-05, + "loss": 3.3583, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1348742075115815e-05, + "loss": 3.3531, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1340356127605295e-05, + "loss": 3.346, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1331970180094775e-05, + "loss": 3.3382, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1323600611387986e-05, + "loss": 3.3496, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1315214663877466e-05, + "loss": 3.3492, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1306828716366946e-05, + "loss": 3.3385, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1298442768856426e-05, + "loss": 3.3608, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1290056821345906e-05, + "loss": 3.3435, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1281687252639117e-05, + "loss": 3.3535, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1273301305128597e-05, + "loss": 3.3447, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.927700996398926, + "eval_runtime": 309.7579, + "eval_samples_per_second": 1231.901, + "eval_steps_per_second": 38.498, + "step": 2365908 + }, + { + "epoch": 0.0, + "learning_rate": 1.1264915357618077e-05, + "loss": 3.3717, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1256529410107557e-05, + "loss": 3.3411, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248159841400769e-05, + "loss": 3.3466, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1239773893890249e-05, + "loss": 3.35, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1231387946379727e-05, + "loss": 3.3531, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1223001998869207e-05, + "loss": 3.3466, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1214616051358689e-05, + "loss": 3.3424, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1206230103848167e-05, + "loss": 3.3459, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1197860535141378e-05, + "loss": 3.3436, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.118947458763086e-05, + "loss": 3.3508, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.118108864012034e-05, + "loss": 3.3427, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1172702692609818e-05, + "loss": 3.3531, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.116433312390303e-05, + "loss": 3.3543, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.115594717639251e-05, + "loss": 3.3295, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.114756122888199e-05, + "loss": 3.3446, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.113917528137147e-05, + "loss": 3.3305, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.113078933386095e-05, + "loss": 3.3324, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.112240338635043e-05, + "loss": 3.3435, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114017438839908e-05, + "loss": 3.3387, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.110563149132939e-05, + "loss": 3.3456, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.10972619226226e-05, + "loss": 3.3567, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.108887597511208e-05, + "loss": 3.343, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.108049002760156e-05, + "loss": 3.3453, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.107210408009104e-05, + "loss": 3.3463, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1063734511384251e-05, + "loss": 3.3385, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1055348563873731e-05, + "loss": 3.3469, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1046962616363211e-05, + "loss": 3.3334, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1038576668852691e-05, + "loss": 3.3417, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1030190721342173e-05, + "loss": 3.3389, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1021821152635382e-05, + "loss": 3.3316, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1013435205124862e-05, + "loss": 3.3429, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1005049257614344e-05, + "loss": 3.338, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0996663310103822e-05, + "loss": 3.3507, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0988277362593302e-05, + "loss": 3.3461, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0979891415082782e-05, + "loss": 3.3332, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0971521846375994e-05, + "loss": 3.3411, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963135898865473e-05, + "loss": 3.3583, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0954749951354954e-05, + "loss": 3.3357, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0946364003844434e-05, + "loss": 3.3382, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0937978056333912e-05, + "loss": 3.3345, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0929608487627125e-05, + "loss": 3.3364, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0921222540116605e-05, + "loss": 3.3399, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912836592606085e-05, + "loss": 3.353, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0904450645095563e-05, + "loss": 3.3499, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0896064697585045e-05, + "loss": 3.3446, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0887678750074525e-05, + "loss": 3.3416, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0879309181367735e-05, + "loss": 3.3387, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0870923233857215e-05, + "loss": 3.3491, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0862537286346695e-05, + "loss": 3.3196, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0854151338836175e-05, + "loss": 3.3464, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0845781770129386e-05, + "loss": 3.3419, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0837395822618866e-05, + "loss": 3.3493, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0829009875108346e-05, + "loss": 3.339, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0820623927597828e-05, + "loss": 3.3291, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0812254358891037e-05, + "loss": 3.3395, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0803868411380517e-05, + "loss": 3.3278, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0795482463869998e-05, + "loss": 3.3591, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0787096516359477e-05, + "loss": 3.339, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0778710568848957e-05, + "loss": 3.3548, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0770324621338437e-05, + "loss": 3.3369, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0761938673827917e-05, + "loss": 3.3303, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0753552726317396e-05, + "loss": 3.353, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0745183157610609e-05, + "loss": 3.3331, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0736797210100089e-05, + "loss": 3.3342, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0728411262589567e-05, + "loss": 3.3342, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720025315079047e-05, + "loss": 3.3429, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0711639367568529e-05, + "loss": 3.33, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703253420058007e-05, + "loss": 3.3341, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.069488385135122e-05, + "loss": 3.3322, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.06864979038407e-05, + "loss": 3.3308, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.067811195633018e-05, + "loss": 3.3486, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0669726008819658e-05, + "loss": 3.3438, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.066134006130914e-05, + "loss": 3.336, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.065297049260235e-05, + "loss": 3.3348, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064458454509183e-05, + "loss": 3.3486, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.063619859758131e-05, + "loss": 3.342, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.062781265007079e-05, + "loss": 3.3492, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0619443081364e-05, + "loss": 3.3411, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061105713385348e-05, + "loss": 3.3367, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.060267118634296e-05, + "loss": 3.3448, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.059428523883244e-05, + "loss": 3.3474, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058589929132192e-05, + "loss": 3.3446, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0577529722615131e-05, + "loss": 3.3458, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569143775104611e-05, + "loss": 3.3423, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0560757827594093e-05, + "loss": 3.3237, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0552371880083571e-05, + "loss": 3.3408, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0543985932573051e-05, + "loss": 3.3431, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0535599985062531e-05, + "loss": 3.3392, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0527230416355744e-05, + "loss": 3.3359, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0518844468845222e-05, + "loss": 3.3386, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0510458521334702e-05, + "loss": 3.3387, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502072573824184e-05, + "loss": 3.3334, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0493686626313662e-05, + "loss": 3.3398, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485317057606874e-05, + "loss": 3.3416, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0476931110096354e-05, + "loss": 3.3402, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0468545162585834e-05, + "loss": 3.3543, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0460159215075312e-05, + "loss": 3.3225, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0451773267564794e-05, + "loss": 3.3359, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0443387320054274e-05, + "loss": 3.3365, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435001372543752e-05, + "loss": 3.3448, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0426615425033232e-05, + "loss": 3.3425, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0418245856326445e-05, + "loss": 3.342, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0409876287619656e-05, + "loss": 3.33, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0401490340109136e-05, + "loss": 3.3406, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0393104392598615e-05, + "loss": 3.3407, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0384718445088095e-05, + "loss": 3.3323, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0376332497577575e-05, + "loss": 3.3289, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0367946550067055e-05, + "loss": 3.3392, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0359576981360266e-05, + "loss": 3.3407, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0351191033849748e-05, + "loss": 3.3214, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0342805086339226e-05, + "loss": 3.3402, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0334419138828706e-05, + "loss": 3.3239, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326033191318186e-05, + "loss": 3.343, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0317647243807668e-05, + "loss": 3.3372, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0309277675100877e-05, + "loss": 3.3347, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0300891727590357e-05, + "loss": 3.3428, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0292505780079838e-05, + "loss": 3.3407, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284119832569317e-05, + "loss": 3.3302, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0275733885058797e-05, + "loss": 3.3414, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267364316352009e-05, + "loss": 3.3427, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0258978368841489e-05, + "loss": 3.3287, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0250592421330967e-05, + "loss": 3.325, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0242206473820449e-05, + "loss": 3.3389, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0233820526309929e-05, + "loss": 3.336, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0225434578799407e-05, + "loss": 3.3416, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217048631288887e-05, + "loss": 3.329, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.02086790625821e-05, + "loss": 3.3376, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.020029311507158e-05, + "loss": 3.3359, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019190716756106e-05, + "loss": 3.3288, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018352122005054e-05, + "loss": 3.325, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.017513527254002e-05, + "loss": 3.3433, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0166749325029498e-05, + "loss": 3.3498, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.015837975632271e-05, + "loss": 3.3325, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.014999380881219e-05, + "loss": 3.3338, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.014160786130167e-05, + "loss": 3.3392, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.013322191379115e-05, + "loss": 3.3337, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.012485234508436e-05, + "loss": 3.3334, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.011646639757384e-05, + "loss": 3.3373, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.010808045006332e-05, + "loss": 3.3457, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.00996945025528e-05, + "loss": 3.3432, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.009130855504228e-05, + "loss": 3.3369, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0082938986335493e-05, + "loss": 3.3319, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0074553038824971e-05, + "loss": 3.3412, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0066167091314451e-05, + "loss": 3.3361, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0057781143803933e-05, + "loss": 3.3294, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0049395196293411e-05, + "loss": 3.3534, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041009248782891e-05, + "loss": 3.3344, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0032623301272371e-05, + "loss": 3.3425, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0024253732565584e-05, + "loss": 3.3337, + "step": 2441728 + }, + { + "epoch": 0.03, + "eval_loss": 3.9294445514678955, + "eval_runtime": 302.2756, + "eval_samples_per_second": 1262.394, + "eval_steps_per_second": 39.451, + "step": 2442228 + }, + { + "epoch": 1.0, + "learning_rate": 1.0015867785055062e-05, + "loss": 3.3374, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0007481837544542e-05, + "loss": 3.3341, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.999095890034023e-06, + "loss": 3.3363, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.990709942523502e-06, + "loss": 3.3452, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.982323995012982e-06, + "loss": 3.343, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.973954426306194e-06, + "loss": 3.3411, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.965568478795674e-06, + "loss": 3.3298, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.957182531285152e-06, + "loss": 3.3342, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.948796583774634e-06, + "loss": 3.3327, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.940410636264114e-06, + "loss": 3.3427, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.932024688753592e-06, + "loss": 3.3337, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.923638741243072e-06, + "loss": 3.3431, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.915269172536285e-06, + "loss": 3.3444, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.906883225025765e-06, + "loss": 3.3248, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.898497277515245e-06, + "loss": 3.331, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.890111330004725e-06, + "loss": 3.3235, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.881725382494204e-06, + "loss": 3.3216, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.873339434983683e-06, + "loss": 3.335, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.864953487473164e-06, + "loss": 3.3308, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.856567539962644e-06, + "loss": 3.3331, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.848197971255855e-06, + "loss": 3.3502, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.839812023745335e-06, + "loss": 3.3354, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.831426076234815e-06, + "loss": 3.3376, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.823040128724295e-06, + "loss": 3.3318, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.814670560017507e-06, + "loss": 3.3334, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.806284612506986e-06, + "loss": 3.3354, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.797898664996466e-06, + "loss": 3.3217, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.789512717485946e-06, + "loss": 3.3336, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.781126769975426e-06, + "loss": 3.3291, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.772757201268636e-06, + "loss": 3.3199, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.764371253758118e-06, + "loss": 3.3389, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.755985306247598e-06, + "loss": 3.3251, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.747599358737076e-06, + "loss": 3.3382, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.739213411226556e-06, + "loss": 3.3363, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.730827463716038e-06, + "loss": 3.3258, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.722441516205516e-06, + "loss": 3.3331, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.714055568694996e-06, + "loss": 3.3451, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.705685999988209e-06, + "loss": 3.3242, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.69731643128142e-06, + "loss": 3.3303, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.6889304837709e-06, + "loss": 3.3296, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.68054453626038e-06, + "loss": 3.3224, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.67215858874986e-06, + "loss": 3.329, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.663772641239338e-06, + "loss": 3.3472, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.65540307253255e-06, + "loss": 3.3373, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.64701712502203e-06, + "loss": 3.3317, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.63863117751151e-06, + "loss": 3.3397, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.63024523000099e-06, + "loss": 3.3287, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.6218756612942e-06, + "loss": 3.3379, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.61348971378368e-06, + "loss": 3.3117, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.60510376627316e-06, + "loss": 3.3338, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.59671781876264e-06, + "loss": 3.3403, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.58833187125212e-06, + "loss": 3.3327, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.5799459237416e-06, + "loss": 3.3312, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.571576355034811e-06, + "loss": 3.32, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.563190407524291e-06, + "loss": 3.3316, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.554804460013773e-06, + "loss": 3.3165, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.546418512503251e-06, + "loss": 3.3511, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.538048943796462e-06, + "loss": 3.3283, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.529662996285944e-06, + "loss": 3.3461, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.521277048775423e-06, + "loss": 3.3229, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.512891101264902e-06, + "loss": 3.3241, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.504505153754382e-06, + "loss": 3.3361, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.496135585047594e-06, + "loss": 3.3247, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.487749637537074e-06, + "loss": 3.3258, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.479363690026554e-06, + "loss": 3.327, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.470977742516034e-06, + "loss": 3.3315, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.462608173809245e-06, + "loss": 3.3229, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.454222226298725e-06, + "loss": 3.3249, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.445836278788205e-06, + "loss": 3.3194, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.437450331277685e-06, + "loss": 3.3223, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.429064383767165e-06, + "loss": 3.3343, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.420678436256645e-06, + "loss": 3.3395, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.412292488746125e-06, + "loss": 3.3261, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.403922920039335e-06, + "loss": 3.3276, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.395536972528815e-06, + "loss": 3.3341, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.387151025018295e-06, + "loss": 3.3345, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.378765077507775e-06, + "loss": 3.3324, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.370395508800988e-06, + "loss": 3.3357, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.362009561290466e-06, + "loss": 3.3291, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.353623613779946e-06, + "loss": 3.3343, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.345237666269428e-06, + "loss": 3.3395, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.336868097562638e-06, + "loss": 3.3363, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.328482150052117e-06, + "loss": 3.3389, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.320096202541598e-06, + "loss": 3.3299, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.311710255031078e-06, + "loss": 3.3121, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.303324307520557e-06, + "loss": 3.3308, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.294938360010038e-06, + "loss": 3.3279, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.286552412499518e-06, + "loss": 3.332, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.278182843792729e-06, + "loss": 3.3293, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.269796896282209e-06, + "loss": 3.324, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.261410948771689e-06, + "loss": 3.336, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.253025001261169e-06, + "loss": 3.3222, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.244639053750647e-06, + "loss": 3.3299, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.23626948504386e-06, + "loss": 3.3333, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22788353753334e-06, + "loss": 3.3287, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.21949759002282e-06, + "loss": 3.3418, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.2111116425123e-06, + "loss": 3.3186, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.20272569500178e-06, + "loss": 3.3188, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.19433974749126e-06, + "loss": 3.3327, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.18597017878447e-06, + "loss": 3.3332, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.17758423127395e-06, + "loss": 3.3348, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.16919828376343e-06, + "loss": 3.3315, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.160812336252912e-06, + "loss": 3.3189, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.15242638874239e-06, + "loss": 3.3299, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.1440568200356e-06, + "loss": 3.3341, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.135670872525082e-06, + "loss": 3.319, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.12728492501456e-06, + "loss": 3.3198, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.11889897750404e-06, + "loss": 3.3278, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.11051302999352e-06, + "loss": 3.3331, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.102127082483002e-06, + "loss": 3.312, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.09374113497248e-06, + "loss": 3.3221, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.08535518746196e-06, + "loss": 3.3176, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.076985618755173e-06, + "loss": 3.3324, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.068599671244651e-06, + "loss": 3.3246, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.060230102537864e-06, + "loss": 3.3263, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.051844155027344e-06, + "loss": 3.3313, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.043458207516824e-06, + "loss": 3.3345, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.035072260006302e-06, + "loss": 3.3215, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.026686312495783e-06, + "loss": 3.3302, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.018316743788994e-06, + "loss": 3.3319, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.009930796278474e-06, + "loss": 3.3243, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.001544848767954e-06, + "loss": 3.31, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.993158901257434e-06, + "loss": 3.3298, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.984772953746914e-06, + "loss": 3.3261, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.976387006236394e-06, + "loss": 3.3343, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.968001058725874e-06, + "loss": 3.3194, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.959631490019085e-06, + "loss": 3.3297, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.951245542508565e-06, + "loss": 3.3246, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.942859594998045e-06, + "loss": 3.3182, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.934473647487525e-06, + "loss": 3.3157, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.926087699977005e-06, + "loss": 3.334, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.917701752466485e-06, + "loss": 3.339, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.909332183759695e-06, + "loss": 3.3258, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.900946236249175e-06, + "loss": 3.3191, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.892560288738655e-06, + "loss": 3.3305, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.884174341228135e-06, + "loss": 3.3262, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.875804772521348e-06, + "loss": 3.3265, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.867418825010828e-06, + "loss": 3.3284, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.859032877500306e-06, + "loss": 3.3342, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.850646929989786e-06, + "loss": 3.3282, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842260982479267e-06, + "loss": 3.3302, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.833875034968746e-06, + "loss": 3.3236, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.825505466261958e-06, + "loss": 3.3293, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.817119518751438e-06, + "loss": 3.3285, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.808733571240918e-06, + "loss": 3.3193, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.800347623730396e-06, + "loss": 3.3432, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.791961676219878e-06, + "loss": 3.3239, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.783592107513089e-06, + "loss": 3.3323, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.775206160002569e-06, + "loss": 3.3287, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.766820212492049e-06, + "loss": 3.3247, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.931114673614502, + "eval_runtime": 302.7932, + "eval_samples_per_second": 1260.236, + "eval_steps_per_second": 39.383, + "step": 2518548 + }, + { + "epoch": 0.0, + "learning_rate": 8.75845064378526e-06, + "loss": 3.321, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.75006469627474e-06, + "loss": 3.3288, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.74167874876422e-06, + "loss": 3.3334, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.7332928012537e-06, + "loss": 3.3287, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.72492323254691e-06, + "loss": 3.3345, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.716537285036392e-06, + "loss": 3.3201, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.70815133752587e-06, + "loss": 3.3255, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.69976539001535e-06, + "loss": 3.3208, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.691379442504832e-06, + "loss": 3.3351, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.68299349499431e-06, + "loss": 3.3225, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.67460754748379e-06, + "loss": 3.3345, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.66622159997327e-06, + "loss": 3.3297, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.657852031266482e-06, + "loss": 3.321, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.64946608375596e-06, + "loss": 3.3211, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.64108013624544e-06, + "loss": 3.3109, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.632694188734922e-06, + "loss": 3.3167, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.6243082412244e-06, + "loss": 3.3222, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.61592229371388e-06, + "loss": 3.3193, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.60753634620336e-06, + "loss": 3.3244, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.599166777496573e-06, + "loss": 3.3411, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.590780829986051e-06, + "loss": 3.3223, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.582411261279264e-06, + "loss": 3.3251, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.574025313768744e-06, + "loss": 3.3256, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.565639366258224e-06, + "loss": 3.3233, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.557253418747704e-06, + "loss": 3.3249, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.548883850040914e-06, + "loss": 3.315, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.540497902530394e-06, + "loss": 3.3231, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.532111955019874e-06, + "loss": 3.3234, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.523726007509354e-06, + "loss": 3.3077, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.515340059998834e-06, + "loss": 3.3277, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.506954112488314e-06, + "loss": 3.3163, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.498568164977794e-06, + "loss": 3.3293, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.490182217467274e-06, + "loss": 3.325, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.481812648760486e-06, + "loss": 3.3126, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.473443080053697e-06, + "loss": 3.3281, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.465057132543176e-06, + "loss": 3.3358, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.456671185032657e-06, + "loss": 3.3115, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.448285237522137e-06, + "loss": 3.3255, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.439899290011615e-06, + "loss": 3.3157, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.431529721304828e-06, + "loss": 3.3158, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.423143773794308e-06, + "loss": 3.3195, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.414757826283786e-06, + "loss": 3.3348, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.406371878773268e-06, + "loss": 3.3297, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.398002310066479e-06, + "loss": 3.3213, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.389616362555959e-06, + "loss": 3.3322, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.381230415045438e-06, + "loss": 3.3218, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.372844467534918e-06, + "loss": 3.3254, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.36447489882813e-06, + "loss": 3.3056, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.356088951317611e-06, + "loss": 3.3217, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.347703003807089e-06, + "loss": 3.3285, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.339317056296569e-06, + "loss": 3.3247, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.330931108786049e-06, + "loss": 3.3214, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.322545161275529e-06, + "loss": 3.3099, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.31417559256874e-06, + "loss": 3.326, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.305789645058221e-06, + "loss": 3.3065, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.297403697547701e-06, + "loss": 3.3379, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.28901775003718e-06, + "loss": 3.3196, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.280648181330392e-06, + "loss": 3.3372, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272262233819872e-06, + "loss": 3.3157, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.26387628630935e-06, + "loss": 3.3159, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.25549033879883e-06, + "loss": 3.3209, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.247104391288312e-06, + "loss": 3.3226, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.238734822581523e-06, + "loss": 3.3173, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.230348875071003e-06, + "loss": 3.3114, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.221962927560483e-06, + "loss": 3.3238, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.213576980049963e-06, + "loss": 3.3175, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.205191032539441e-06, + "loss": 3.3097, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.196821463832653e-06, + "loss": 3.3144, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.188435516322133e-06, + "loss": 3.3136, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.180049568811613e-06, + "loss": 3.328, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.171663621301093e-06, + "loss": 3.3303, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.163277673790573e-06, + "loss": 3.3158, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.154891726280053e-06, + "loss": 3.3159, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.146522157573266e-06, + "loss": 3.3246, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.138136210062744e-06, + "loss": 3.3227, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.129750262552224e-06, + "loss": 3.3234, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.121380693845436e-06, + "loss": 3.3249, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.112994746334915e-06, + "loss": 3.3205, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.104608798824395e-06, + "loss": 3.3271, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.096222851313876e-06, + "loss": 3.3239, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.087836903803356e-06, + "loss": 3.3303, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.079467335096565e-06, + "loss": 3.3258, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.071081387586047e-06, + "loss": 3.3203, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.062695440075527e-06, + "loss": 3.3043, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054309492565005e-06, + "loss": 3.3227, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.045923545054487e-06, + "loss": 3.3202, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.037537597543967e-06, + "loss": 3.3228, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.029168028837177e-06, + "loss": 3.322, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.020782081326657e-06, + "loss": 3.3147, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.012396133816137e-06, + "loss": 3.3201, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.004010186305617e-06, + "loss": 3.3156, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.995624238795096e-06, + "loss": 3.3238, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987254670088308e-06, + "loss": 3.3175, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.978868722577788e-06, + "loss": 3.3204, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.970482775067268e-06, + "loss": 3.3314, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.962096827556748e-06, + "loss": 3.3157, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.953710880046228e-06, + "loss": 3.3025, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.945324932535708e-06, + "loss": 3.3234, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.93695536382892e-06, + "loss": 3.325, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.928569416318399e-06, + "loss": 3.3255, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.920183468807879e-06, + "loss": 3.3205, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.91179752129736e-06, + "loss": 3.3157, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.903411573786839e-06, + "loss": 3.3135, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.89504200508005e-06, + "loss": 3.3276, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.886656057569531e-06, + "loss": 3.3096, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878270110059011e-06, + "loss": 3.3108, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.86988416254849e-06, + "loss": 3.3182, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.861514593841702e-06, + "loss": 3.3251, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.853128646331182e-06, + "loss": 3.3023, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.84474269882066e-06, + "loss": 3.3167, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.836356751310142e-06, + "loss": 3.3062, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.827970803799621e-06, + "loss": 3.3201, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.8195848562891e-06, + "loss": 3.3197, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.811215287582312e-06, + "loss": 3.3106, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.802829340071792e-06, + "loss": 3.3278, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.794443392561272e-06, + "loss": 3.3214, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78605744505075e-06, + "loss": 3.3115, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.777671497540232e-06, + "loss": 3.3194, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.769301928833443e-06, + "loss": 3.3232, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.760915981322923e-06, + "loss": 3.3141, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.752530033812403e-06, + "loss": 3.3026, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.744144086301883e-06, + "loss": 3.3213, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.735758138791363e-06, + "loss": 3.3173, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.727372191280843e-06, + "loss": 3.3218, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.718986243770323e-06, + "loss": 3.3106, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.710616675063533e-06, + "loss": 3.3196, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.702230727553015e-06, + "loss": 3.3172, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.693844780042493e-06, + "loss": 3.3088, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.685458832531973e-06, + "loss": 3.301, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.677072885021453e-06, + "loss": 3.3273, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.668686937510933e-06, + "loss": 3.3283, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.660317368804144e-06, + "loss": 3.3165, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.651931421293624e-06, + "loss": 3.3091, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.643545473783106e-06, + "loss": 3.3238, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.635159526272584e-06, + "loss": 3.3159, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.626789957565795e-06, + "loss": 3.3136, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.618404010055276e-06, + "loss": 3.3163, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.6100180625447545e-06, + "loss": 3.325, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.601632115034235e-06, + "loss": 3.3174, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593246167523715e-06, + "loss": 3.3232, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.584860220013196e-06, + "loss": 3.3128, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.576474272502674e-06, + "loss": 3.3204, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.568104703795886e-06, + "loss": 3.318, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.559718756285367e-06, + "loss": 3.3116, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.551332808774846e-06, + "loss": 3.3316, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.542946861264326e-06, + "loss": 3.3157, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.534560913753806e-06, + "loss": 3.3196, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.526191345047018e-06, + "loss": 3.3169, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.5178053975364965e-06, + "loss": 3.3156, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.931185245513916, + "eval_runtime": 302.3981, + "eval_samples_per_second": 1261.883, + "eval_steps_per_second": 39.435, + "step": 2594868 + }, + { + "epoch": 0.0, + "learning_rate": 7.509435828829708e-06, + "loss": 3.3112, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.501049881319189e-06, + "loss": 3.3209, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.492663933808669e-06, + "loss": 3.3233, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.484277986298148e-06, + "loss": 3.3207, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.475892038787628e-06, + "loss": 3.3278, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.467506091277109e-06, + "loss": 3.3052, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.459120143766588e-06, + "loss": 3.3141, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.4507505750597995e-06, + "loss": 3.3122, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.4423646275492795e-06, + "loss": 3.3241, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.4339786800387594e-06, + "loss": 3.316, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.4255927325282385e-06, + "loss": 3.3223, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.417206785017719e-06, + "loss": 3.3225, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.408837216310931e-06, + "loss": 3.3098, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.400451268800409e-06, + "loss": 3.3138, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.39206532128989e-06, + "loss": 3.3027, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.38367937377937e-06, + "loss": 3.3081, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.375293426268851e-06, + "loss": 3.3081, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.366907478758329e-06, + "loss": 3.3088, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.35852153124781e-06, + "loss": 3.3133, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.3501519625410215e-06, + "loss": 3.332, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.341766015030501e-06, + "loss": 3.3161, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.333396446323712e-06, + "loss": 3.3128, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.325010498813192e-06, + "loss": 3.3189, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.316624551302673e-06, + "loss": 3.3173, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.308238603792151e-06, + "loss": 3.3119, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.299869035085363e-06, + "loss": 3.3039, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.291483087574844e-06, + "loss": 3.3152, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.283097140064324e-06, + "loss": 3.3105, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.274711192553803e-06, + "loss": 3.299, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.266325245043283e-06, + "loss": 3.3193, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.2579392975327635e-06, + "loss": 3.3067, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.249553350022243e-06, + "loss": 3.3226, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.241167402511723e-06, + "loss": 3.3146, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.232797833804934e-06, + "loss": 3.3042, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.224428265098146e-06, + "loss": 3.3165, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.216042317587625e-06, + "loss": 3.3291, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.207656370077105e-06, + "loss": 3.3013, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.199270422566586e-06, + "loss": 3.3184, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.190884475056065e-06, + "loss": 3.3042, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.1825149063492765e-06, + "loss": 3.3078, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.1741289588387564e-06, + "loss": 3.3119, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.165743011328236e-06, + "loss": 3.325, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.1573570638177155e-06, + "loss": 3.318, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.148971116307196e-06, + "loss": 3.3115, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.140585168796676e-06, + "loss": 3.3226, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.132215600089886e-06, + "loss": 3.3099, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.123829652579367e-06, + "loss": 3.3168, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.115443705068847e-06, + "loss": 3.3001, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.107057757558328e-06, + "loss": 3.3064, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.098688188851538e-06, + "loss": 3.3222, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.090302241341018e-06, + "loss": 3.3178, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.0819162938304985e-06, + "loss": 3.3086, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.073530346319978e-06, + "loss": 3.3001, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.0651443988094575e-06, + "loss": 3.3169, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.056774830102669e-06, + "loss": 3.2971, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.04838888259215e-06, + "loss": 3.3256, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.040002935081628e-06, + "loss": 3.3147, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.031616987571109e-06, + "loss": 3.3254, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.023247418864321e-06, + "loss": 3.309, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.014861471353801e-06, + "loss": 3.3043, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.00647552384328e-06, + "loss": 3.3112, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.99808957633276e-06, + "loss": 3.3156, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.989720007625971e-06, + "loss": 3.305, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.9813340601154504e-06, + "loss": 3.3032, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.972948112604931e-06, + "loss": 3.3125, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.964562165094411e-06, + "loss": 3.3081, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.956176217583891e-06, + "loss": 3.2954, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.947806648877102e-06, + "loss": 3.309, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.939420701366582e-06, + "loss": 3.3039, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.931034753856063e-06, + "loss": 3.3141, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.922648806345541e-06, + "loss": 3.3195, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.914262858835022e-06, + "loss": 3.3069, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.905893290128233e-06, + "loss": 3.3112, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.897507342617713e-06, + "loss": 3.312, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.8891213951071925e-06, + "loss": 3.3167, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.880735447596673e-06, + "loss": 3.3135, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.872349500086153e-06, + "loss": 3.3197, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.863979931379365e-06, + "loss": 3.3114, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.855593983868844e-06, + "loss": 3.3164, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.847208036358324e-06, + "loss": 3.3142, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.838822088847805e-06, + "loss": 3.3195, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.830452520141015e-06, + "loss": 3.3156, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.822066572630495e-06, + "loss": 3.3155, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.8136806251199754e-06, + "loss": 3.2967, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.805294677609455e-06, + "loss": 3.3113, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.7969087300989345e-06, + "loss": 3.3109, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.788539161392146e-06, + "loss": 3.314, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.780153213881626e-06, + "loss": 3.313, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.771767266371105e-06, + "loss": 3.3013, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.763381318860586e-06, + "loss": 3.3108, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.754995371350066e-06, + "loss": 3.3061, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.746609423839547e-06, + "loss": 3.3161, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.738239855132757e-06, + "loss": 3.3018, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.729853907622237e-06, + "loss": 3.3129, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.7214679601117175e-06, + "loss": 3.3246, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.713082012601197e-06, + "loss": 3.3069, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.7046960650906765e-06, + "loss": 3.2948, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6963101175801565e-06, + "loss": 3.315, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.687940548873368e-06, + "loss": 3.3158, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.679554601362847e-06, + "loss": 3.3127, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.671168653852328e-06, + "loss": 3.3136, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.662782706341808e-06, + "loss": 3.304, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.654396758831287e-06, + "loss": 3.3029, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.646027190124499e-06, + "loss": 3.3189, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.637641242613979e-06, + "loss": 3.2994, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.6292552951034595e-06, + "loss": 3.3034, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.620869347592938e-06, + "loss": 3.308, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.612499778886149e-06, + "loss": 3.3179, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.60411383137563e-06, + "loss": 3.2921, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.595727883865109e-06, + "loss": 3.3109, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.587341936354589e-06, + "loss": 3.2944, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.57895598884407e-06, + "loss": 3.3107, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.57057004133355e-06, + "loss": 3.3125, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.562184093823029e-06, + "loss": 3.3022, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.553814525116241e-06, + "loss": 3.3176, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.545428577605721e-06, + "loss": 3.3157, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.5370426300952e-06, + "loss": 3.2981, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.52865668258468e-06, + "loss": 3.3132, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.5202871138778914e-06, + "loss": 3.3105, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.511901166367372e-06, + "loss": 3.3083, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.503515218856851e-06, + "loss": 3.2924, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.495129271346331e-06, + "loss": 3.3159, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.486743323835811e-06, + "loss": 3.3052, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.47835737632529e-06, + "loss": 3.3129, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.469971428814771e-06, + "loss": 3.3044, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.461601860107983e-06, + "loss": 3.3107, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.453215912597463e-06, + "loss": 3.3055, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.444829965086942e-06, + "loss": 3.3009, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.436444017576422e-06, + "loss": 3.2936, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.428058070065903e-06, + "loss": 3.3171, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.419672122555382e-06, + "loss": 3.3129, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.411302553848593e-06, + "loss": 3.3109, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.402916606338073e-06, + "loss": 3.3007, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.394530658827553e-06, + "loss": 3.3134, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.386144711317032e-06, + "loss": 3.3104, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.377775142610244e-06, + "loss": 3.3039, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.369389195099725e-06, + "loss": 3.3064, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.361003247589205e-06, + "loss": 3.3132, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.352617300078684e-06, + "loss": 3.3094, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.344231352568164e-06, + "loss": 3.3158, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.335845405057645e-06, + "loss": 3.3027, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.327459457547123e-06, + "loss": 3.3118, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.3190898888403345e-06, + "loss": 3.307, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.310703941329815e-06, + "loss": 3.3013, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.302317993819295e-06, + "loss": 3.3234, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.293932046308774e-06, + "loss": 3.3057, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.285546098798254e-06, + "loss": 3.3134, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.277176530091467e-06, + "loss": 3.3033, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.268790582580945e-06, + "loss": 3.3073, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.931253671646118, + "eval_runtime": 313.4926, + "eval_samples_per_second": 1217.225, + "eval_steps_per_second": 38.039, + "step": 2671188 + }, + { + "epoch": 0.0, + "learning_rate": 6.260421013874157e-06, + "loss": 3.3003, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.2520350663636376e-06, + "loss": 3.312, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.243649118853117e-06, + "loss": 3.3118, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.2352631713425975e-06, + "loss": 3.3133, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.226893602635808e-06, + "loss": 3.3196, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.218507655125288e-06, + "loss": 3.3014, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.210121707614768e-06, + "loss": 3.3044, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.201735760104248e-06, + "loss": 3.2999, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.193349812593728e-06, + "loss": 3.3192, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.184963865083208e-06, + "loss": 3.3053, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.176577917572688e-06, + "loss": 3.3136, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.168191970062168e-06, + "loss": 3.315, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.15982240135538e-06, + "loss": 3.303, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.151436453844859e-06, + "loss": 3.3009, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.143050506334339e-06, + "loss": 3.2988, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.134664558823819e-06, + "loss": 3.2973, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.1262786113132986e-06, + "loss": 3.3041, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.1178926638027785e-06, + "loss": 3.3001, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.1095067162922585e-06, + "loss": 3.3033, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.10113714758547e-06, + "loss": 3.3226, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.09275120007495e-06, + "loss": 3.3091, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.084365252564429e-06, + "loss": 3.3052, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.07597930505391e-06, + "loss": 3.3063, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.067609736347121e-06, + "loss": 3.311, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.059223788836601e-06, + "loss": 3.3007, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.050837841326081e-06, + "loss": 3.2957, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.042451893815561e-06, + "loss": 3.3101, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.034065946305041e-06, + "loss": 3.2944, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.02567999879452e-06, + "loss": 3.2948, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.0172940512840005e-06, + "loss": 3.3071, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.00890810377348e-06, + "loss": 3.2995, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.000538535066691e-06, + "loss": 3.3059, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.992152587556171e-06, + "loss": 3.3072, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.983766640045651e-06, + "loss": 3.2967, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.975380692535131e-06, + "loss": 3.3086, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.966994745024611e-06, + "loss": 3.3178, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.958608797514091e-06, + "loss": 3.2934, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.950239228807302e-06, + "loss": 3.3089, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.941853281296783e-06, + "loss": 3.2911, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.933467333786262e-06, + "loss": 3.3061, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.9250813862757425e-06, + "loss": 3.2993, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.916695438765222e-06, + "loss": 3.3157, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.908309491254702e-06, + "loss": 3.3062, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.899939922547913e-06, + "loss": 3.3049, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.891553975037393e-06, + "loss": 3.3102, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.883168027526873e-06, + "loss": 3.3005, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.874782080016353e-06, + "loss": 3.3103, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.866412511309565e-06, + "loss": 3.2904, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.858026563799044e-06, + "loss": 3.2969, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.849640616288525e-06, + "loss": 3.3105, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.841254668778004e-06, + "loss": 3.3038, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.832885100071215e-06, + "loss": 3.3046, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.824499152560695e-06, + "loss": 3.2912, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.8161132050501745e-06, + "loss": 3.3027, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.807727257539655e-06, + "loss": 3.2886, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.799357688832866e-06, + "loss": 3.3127, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.790971741322347e-06, + "loss": 3.3078, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.782585793811826e-06, + "loss": 3.3131, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.774199846301307e-06, + "loss": 3.3015, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.765813898790786e-06, + "loss": 3.2981, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.757427951280266e-06, + "loss": 3.2987, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.7490583825734775e-06, + "loss": 3.309, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.7406724350629566e-06, + "loss": 3.294, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.732286487552437e-06, + "loss": 3.2945, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.7239005400419165e-06, + "loss": 3.3017, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.715514592531397e-06, + "loss": 3.3029, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.707128645020876e-06, + "loss": 3.2879, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.698759076314088e-06, + "loss": 3.2947, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.690373128803568e-06, + "loss": 3.2964, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.681987181293048e-06, + "loss": 3.3064, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.673601233782528e-06, + "loss": 3.3099, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.665215286272008e-06, + "loss": 3.2977, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.6568457175652195e-06, + "loss": 3.3048, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.648459770054699e-06, + "loss": 3.298, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.6400738225441786e-06, + "loss": 3.3157, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.6316878750336585e-06, + "loss": 3.2983, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.6233019275231385e-06, + "loss": 3.3126, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.61493235881635e-06, + "loss": 3.2984, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.60654641130583e-06, + "loss": 3.3062, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.59816046379531e-06, + "loss": 3.309, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.58977451628479e-06, + "loss": 3.3083, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.581404947578002e-06, + "loss": 3.3077, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.573019000067481e-06, + "loss": 3.3044, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.564633052556961e-06, + "loss": 3.2921, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.556247105046441e-06, + "loss": 3.3009, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.547861157535921e-06, + "loss": 3.3016, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.539491588829132e-06, + "loss": 3.3063, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.531105641318611e-06, + "loss": 3.3026, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.522719693808092e-06, + "loss": 3.2946, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.514333746297571e-06, + "loss": 3.3023, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.505947798787051e-06, + "loss": 3.2962, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.497561851276532e-06, + "loss": 3.3049, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.489192282569743e-06, + "loss": 3.2924, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.480806335059223e-06, + "loss": 3.3081, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.472420387548703e-06, + "loss": 3.3138, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.464034440038183e-06, + "loss": 3.2975, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.455648492527663e-06, + "loss": 3.2853, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.447262545017142e-06, + "loss": 3.304, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.4388765975066225e-06, + "loss": 3.3029, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.430490649996102e-06, + "loss": 3.3083, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.422121081289313e-06, + "loss": 3.3052, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.413751512582525e-06, + "loss": 3.2959, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.405365565072005e-06, + "loss": 3.2983, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.396979617561485e-06, + "loss": 3.3075, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.388593670050965e-06, + "loss": 3.2891, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.380207722540445e-06, + "loss": 3.2983, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.371821775029924e-06, + "loss": 3.2961, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.363435827519405e-06, + "loss": 3.3073, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.355049880008884e-06, + "loss": 3.2786, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.346680311302095e-06, + "loss": 3.3002, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.338294363791575e-06, + "loss": 3.2912, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.329908416281055e-06, + "loss": 3.2961, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.321522468770535e-06, + "loss": 3.3032, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.313152900063747e-06, + "loss": 3.2926, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.304783331356958e-06, + "loss": 3.3127, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.2963973838464385e-06, + "loss": 3.3047, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.288011436335918e-06, + "loss": 3.29, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.2796254888253976e-06, + "loss": 3.3016, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.271255920118609e-06, + "loss": 3.3038, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.262869972608088e-06, + "loss": 3.2996, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.254484025097569e-06, + "loss": 3.2813, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.246098077587048e-06, + "loss": 3.3068, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.237712130076529e-06, + "loss": 3.2961, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.22934256136974e-06, + "loss": 3.3017, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.22095661385922e-06, + "loss": 3.2963, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.2125706663487e-06, + "loss": 3.3039, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.20418471883818e-06, + "loss": 3.2968, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.19579877132766e-06, + "loss": 3.292, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.18742920262087e-06, + "loss": 3.2855, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.179043255110351e-06, + "loss": 3.3076, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.17065730759983e-06, + "loss": 3.3047, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.162271360089311e-06, + "loss": 3.3016, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.153901791382522e-06, + "loss": 3.2916, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.145515843872002e-06, + "loss": 3.301, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.137129896361482e-06, + "loss": 3.3019, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.128743948850962e-06, + "loss": 3.292, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.120358001340442e-06, + "loss": 3.3016, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.1119884326336525e-06, + "loss": 3.2985, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.103602485123133e-06, + "loss": 3.3065, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.0952165376126124e-06, + "loss": 3.3065, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.086830590102092e-06, + "loss": 3.2934, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.078444642591572e-06, + "loss": 3.3017, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.070075073884783e-06, + "loss": 3.2973, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.061689126374264e-06, + "loss": 3.2913, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.053303178863743e-06, + "loss": 3.3148, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.044917231353224e-06, + "loss": 3.2977, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.036531283842704e-06, + "loss": 3.3036, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.0281617151359155e-06, + "loss": 3.2943, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.0197757676253946e-06, + "loss": 3.3017, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.9313158988952637, + "eval_runtime": 306.1066, + "eval_samples_per_second": 1246.595, + "eval_steps_per_second": 38.957, + "step": 2747508 + }, + { + "epoch": 0.0, + "learning_rate": 5.0113898201148745e-06, + "loss": 3.2914, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.003020251408086e-06, + "loss": 3.3039, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.994634303897565e-06, + "loss": 3.3029, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.986248356387046e-06, + "loss": 3.303, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.977862408876525e-06, + "loss": 3.3129, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.969476461366006e-06, + "loss": 3.2908, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.961090513855485e-06, + "loss": 3.2982, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.952720945148697e-06, + "loss": 3.2881, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.944334997638177e-06, + "loss": 3.3094, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.935949050127657e-06, + "loss": 3.2983, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.927563102617137e-06, + "loss": 3.3037, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.9191771551066165e-06, + "loss": 3.3003, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.910807586399828e-06, + "loss": 3.2982, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.902421638889307e-06, + "loss": 3.2876, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.894035691378788e-06, + "loss": 3.2927, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.885649743868267e-06, + "loss": 3.2862, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.877263796357747e-06, + "loss": 3.2951, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.868877848847227e-06, + "loss": 3.2956, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.860491901336707e-06, + "loss": 3.2907, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.852105953826187e-06, + "loss": 3.3137, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.8437527639231295e-06, + "loss": 3.2967, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.83536681641261e-06, + "loss": 3.2983, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.826980868902089e-06, + "loss": 3.3009, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.81859492139157e-06, + "loss": 3.2974, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.810208973881049e-06, + "loss": 3.2928, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.801839405174261e-06, + "loss": 3.2883, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.793453457663741e-06, + "loss": 3.301, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.78506751015322e-06, + "loss": 3.2812, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.776681562642701e-06, + "loss": 3.2871, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.76829561513218e-06, + "loss": 3.2928, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.759909667621661e-06, + "loss": 3.2897, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.7515400989148715e-06, + "loss": 3.3018, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.7431541514043515e-06, + "loss": 3.2965, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.7347682038938314e-06, + "loss": 3.2913, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.726382256383311e-06, + "loss": 3.2993, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.717996308872791e-06, + "loss": 3.3072, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.709610361362271e-06, + "loss": 3.2876, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.701224413851751e-06, + "loss": 3.2978, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.692854845144962e-06, + "loss": 3.2841, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.684468897634443e-06, + "loss": 3.2976, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.676082950123922e-06, + "loss": 3.2883, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.667697002613402e-06, + "loss": 3.3099, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.6593274339066136e-06, + "loss": 3.2979, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.6509414863960935e-06, + "loss": 3.2946, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.6425555388855735e-06, + "loss": 3.3031, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.6341695913750534e-06, + "loss": 3.2916, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.625800022668265e-06, + "loss": 3.299, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.617414075157744e-06, + "loss": 3.2847, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.609028127647225e-06, + "loss": 3.2823, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.600642180136704e-06, + "loss": 3.307, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.592256232626184e-06, + "loss": 3.293, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.583886663919396e-06, + "loss": 3.2972, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.575500716408875e-06, + "loss": 3.284, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.567114768898356e-06, + "loss": 3.2944, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.5587288213878355e-06, + "loss": 3.2822, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.550359252681047e-06, + "loss": 3.301, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.541973305170526e-06, + "loss": 3.2948, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.533587357660007e-06, + "loss": 3.3052, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.525201410149486e-06, + "loss": 3.294, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.516815462638966e-06, + "loss": 3.2872, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.508429515128446e-06, + "loss": 3.2919, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.500059946421657e-06, + "loss": 3.2962, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.491673998911138e-06, + "loss": 3.2867, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.483288051400617e-06, + "loss": 3.2887, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.474902103890097e-06, + "loss": 3.2909, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.466516156379577e-06, + "loss": 3.2985, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.458146587672788e-06, + "loss": 3.2766, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.449760640162268e-06, + "loss": 3.2903, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.441374692651748e-06, + "loss": 3.2847, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.432988745141228e-06, + "loss": 3.2982, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.424602797630708e-06, + "loss": 3.2976, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.41623322892392e-06, + "loss": 3.2906, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.407847281413399e-06, + "loss": 3.2954, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.399461333902879e-06, + "loss": 3.2893, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.391075386392359e-06, + "loss": 3.3084, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3827058176855705e-06, + "loss": 3.2864, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3743198701750504e-06, + "loss": 3.303, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.36593392266453e-06, + "loss": 3.2943, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.35754797515401e-06, + "loss": 3.2952, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.34916202764349e-06, + "loss": 3.3031, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.340792458936702e-06, + "loss": 3.2971, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.332406511426181e-06, + "loss": 3.3001, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.324020563915661e-06, + "loss": 3.295, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.315634616405141e-06, + "loss": 3.281, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307248668894621e-06, + "loss": 3.2964, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.298862721384101e-06, + "loss": 3.2863, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.290476773873581e-06, + "loss": 3.2996, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2821072051667925e-06, + "loss": 3.2951, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.2737212576562716e-06, + "loss": 3.2854, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.2653353101457515e-06, + "loss": 3.2934, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.256949362635232e-06, + "loss": 3.2881, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.2485634151247114e-06, + "loss": 3.2948, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.240193846417923e-06, + "loss": 3.2843, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.231807898907403e-06, + "loss": 3.2995, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.223421951396883e-06, + "loss": 3.3053, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.215036003886363e-06, + "loss": 3.2902, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.206650056375842e-06, + "loss": 3.2747, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.198264108865323e-06, + "loss": 3.2975, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.189878161354802e-06, + "loss": 3.2916, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.181492213844283e-06, + "loss": 3.2984, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.1731226451374936e-06, + "loss": 3.2961, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.164753076430705e-06, + "loss": 3.2899, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.156367128920185e-06, + "loss": 3.2866, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.147981181409665e-06, + "loss": 3.2994, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.139595233899145e-06, + "loss": 3.2807, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.131209286388624e-06, + "loss": 3.2885, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.122823338878105e-06, + "loss": 3.2864, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.114437391367584e-06, + "loss": 3.298, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.106051443857065e-06, + "loss": 3.2728, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.097698253954007e-06, + "loss": 3.2943, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.089312306443487e-06, + "loss": 3.2835, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.080926358932967e-06, + "loss": 3.2896, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.072540411422447e-06, + "loss": 3.291, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.064154463911927e-06, + "loss": 3.2833, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.055784895205139e-06, + "loss": 3.2998, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.047398947694618e-06, + "loss": 3.2971, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.039013000184098e-06, + "loss": 3.2826, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.030627052673578e-06, + "loss": 3.2919, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.022241105163058e-06, + "loss": 3.2941, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.0138715364562694e-06, + "loss": 3.2957, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.0054855889457485e-06, + "loss": 3.2735, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.997099641435229e-06, + "loss": 3.2969, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.9887136939247085e-06, + "loss": 3.2874, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.980327746414188e-06, + "loss": 3.2924, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.971941798903668e-06, + "loss": 3.2828, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.96357223019688e-06, + "loss": 3.2984, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.95518628268636e-06, + "loss": 3.2917, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.94680033517584e-06, + "loss": 3.2818, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.93841438766532e-06, + "loss": 3.2784, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.9300284401548e-06, + "loss": 3.2975, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.921642492644279e-06, + "loss": 3.2908, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.9132729239374906e-06, + "loss": 3.2946, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.9048869764269705e-06, + "loss": 3.2861, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.8965010289164505e-06, + "loss": 3.2914, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.8881150814059304e-06, + "loss": 3.2931, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.879745512699142e-06, + "loss": 3.2835, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.871359565188622e-06, + "loss": 3.292, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.862973617678101e-06, + "loss": 3.2911, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.854587670167582e-06, + "loss": 3.2945, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.846201722657061e-06, + "loss": 3.2995, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.837815775146542e-06, + "loss": 3.2852, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.829429827636021e-06, + "loss": 3.292, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.821060258929233e-06, + "loss": 3.2866, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.8126743114187126e-06, + "loss": 3.2877, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.804288363908192e-06, + "loss": 3.2986, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.7959024163976725e-06, + "loss": 3.2882, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.787516468887152e-06, + "loss": 3.2992, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.7791305213766324e-06, + "loss": 3.2777, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.770760952669843e-06, + "loss": 3.2986, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.9318079948425293, + "eval_runtime": 306.0975, + "eval_samples_per_second": 1246.632, + "eval_steps_per_second": 38.958, + "step": 2823828 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.8316502304083343e+18, + "trial_name": null, + "trial_params": null +}