{ "best_metric": 3.8451194763183594, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/transformer/3/checkpoints/checkpoint-763200", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 763200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9867, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8188, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1835, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9731, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8049, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.6919, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.5929, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5265, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4448, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3876, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3349, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.2996, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.252, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 5.2013, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 5.169, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 5.1205, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1131, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0688, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0388, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0171, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0046, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9732, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.949, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9289, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9131, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8832, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8692, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8472, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8306, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8169, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.801, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7901, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7837, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.766, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7526, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7394, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.732, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.708, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7085, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6763, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.676, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6717, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6711, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6394, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6469, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6351, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.624, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.631, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5917, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.596, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.6007, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5934, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5741, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5553, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5644, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5456, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5687, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5196, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5405, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5284, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.519, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5238, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5042, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4887, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4921, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5044, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4773, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4797, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4621, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4626, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4778, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4757, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4492, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4624, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.469, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4506, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4324, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4365, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4335, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4242, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4206, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.421, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4231, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.415, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3941, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.3988, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.3989, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3941, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3936, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3833, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3797, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3711, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.9228804026303046e-05, "loss": 4.3805, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922041807879253e-05, "loss": 4.3709, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921203213128201e-05, "loss": 4.3724, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3711, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.356, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.36, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3544, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3531, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3542, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3366, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3458, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3404, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3341, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3239, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3253, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3271, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3202, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3199, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3123, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3048, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3245, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3036, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3089, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3083, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3084, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.2999, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2949, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.3087, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2963, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2821, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.284, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2797, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2796, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2748, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2781, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2666, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2687, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2634, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891025267252941e-05, "loss": 4.282, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890186672501889e-05, "loss": 4.2746, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889348077750837e-05, "loss": 4.2588, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2572, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2601, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2647, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2618, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2571, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2547, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2523, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2486, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2392, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2481, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2378, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2281, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2429, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2358, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2391, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.2288, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.229, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.196639060974121, "eval_runtime": 303.4597, "eval_samples_per_second": 1257.468, "eval_steps_per_second": 39.297, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2195, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.216, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2308, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2157, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.224, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2076, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2151, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.2022, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2087, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.2036, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2122, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.2067, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1908, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.1899, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.1881, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1862, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1898, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1818, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1836, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.198, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.1833, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1834, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.178, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1907, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1615, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1778, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1667, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.1646, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1627, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1577, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1629, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.174, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1604, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1622, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1519, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1588, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1498, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1557, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1361, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1451, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1404, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1549, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1322, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1427, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1423, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1332, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1457, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1181, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1267, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.1391, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1309, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.1236, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.1184, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1233, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828992186000316e-05, "loss": 4.1115, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1297, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1034, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1173, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.1173, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1114, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.12, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.11, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.0959, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.0978, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1209, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.099, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.1004, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.0928, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.0949, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1078, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1109, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.0962, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.1079, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1115, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.1053, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.0862, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.0988, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.0922, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0919, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.0883, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0924, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.0995, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.092, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0732, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803844170750995e-05, "loss": 4.0788, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.082, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0847, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0864, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004930675075325e-05, "loss": 4.0729, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0803, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988158780054285e-05, "loss": 4.0633, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.0786, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0778, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0748, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.0811, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0674, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.79378594737949e-05, "loss": 4.0701, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0743, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.072, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0679, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0625, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789596249384976e-05, "loss": 4.0623, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0683, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.067, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0473, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862451461415144e-05, "loss": 4.0617, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854065513904624e-05, "loss": 4.0629, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845679566394104e-05, "loss": 4.0583, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837293618883584e-05, "loss": 4.0527, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828907671373064e-05, "loss": 4.0534, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820521723862544e-05, "loss": 4.0466, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812135776352024e-05, "loss": 4.0683, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0499, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779538026013471e-05, "loss": 4.0567, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778699431262419e-05, "loss": 4.054, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0641, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777023879640689e-05, "loss": 4.0501, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776185284889637e-05, "loss": 4.0531, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775346690138585e-05, "loss": 4.0605, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774508095387533e-05, "loss": 4.0504, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773669500636481e-05, "loss": 4.0437, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772830905885429e-05, "loss": 4.0455, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771992311134377e-05, "loss": 4.0396, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771153716383325e-05, "loss": 4.0427, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770316759512646e-05, "loss": 4.0438, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769478164761594e-05, "loss": 4.0426, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768639570010542e-05, "loss": 4.0346, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76780097525949e-05, "loss": 4.0375, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.7669640183888106e-05, "loss": 4.0342, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.7661254236377586e-05, "loss": 4.0521, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765286828886707e-05, "loss": 4.0513, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764448234135655e-05, "loss": 4.0381, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763611277264976e-05, "loss": 4.0268, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762772682513924e-05, "loss": 4.0409, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761934087762872e-05, "loss": 4.0408, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610954930118195e-05, "loss": 4.0414, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760258536141141e-05, "loss": 4.0351, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759419941390089e-05, "loss": 4.0395, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758581346639037e-05, "loss": 4.032, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577427518879844e-05, "loss": 4.0345, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756905795017306e-05, "loss": 4.029, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756067200266254e-05, "loss": 4.032, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755228605515202e-05, "loss": 4.0251, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0203, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535530538934716e-05, "loss": 4.0334, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527144591424196e-05, "loss": 4.0297, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751875864391367e-05, "loss": 4.0321, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751037269640315e-05, "loss": 4.0236, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502003127696365e-05, "loss": 4.0225, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.027788162231445, "eval_runtime": 303.457, "eval_samples_per_second": 1257.48, "eval_steps_per_second": 39.297, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493617180185845e-05, "loss": 4.0158, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748523123267532e-05, "loss": 4.0142, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.74768452851648e-05, "loss": 4.028, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746845933765428e-05, "loss": 4.0171, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460073390143764e-05, "loss": 4.0283, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451687442633244e-05, "loss": 4.0091, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.0209, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0089, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0165, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0115, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0191, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0151, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739301856766706e-05, "loss": 4.0006, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738463262015654e-05, "loss": 4.0035, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737624667264602e-05, "loss": 4.0019, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73678607251355e-05, "loss": 4.0036, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 4.0038, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 3.9981, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 4.0003, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733433331389716e-05, "loss": 4.0191, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 4.0057, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 4.0058, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73091754713656e-05, "loss": 4.0033, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730080590265881e-05, "loss": 4.0088, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729241995514829e-05, "loss": 3.9858, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728403400763777e-05, "loss": 4.0007, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727564806012725e-05, "loss": 3.9984, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267278491420456e-05, "loss": 3.9915, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9876, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9854, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.9936, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723375108018211e-05, "loss": 4.0054, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722536513267159e-05, "loss": 3.9925, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721697918516107e-05, "loss": 3.9946, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720859323765055e-05, "loss": 3.9877, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720022366894376e-05, "loss": 3.9898, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719183772143324e-05, "loss": 3.9823, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718345177392272e-05, "loss": 3.9958, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.71750658264122e-05, "loss": 3.9708, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716669625770541e-05, "loss": 3.9843, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715831031019489e-05, "loss": 3.9782, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9956, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9753, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133168846467065e-05, "loss": 3.9809, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124782898956545e-05, "loss": 3.9846, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116396951446025e-05, "loss": 3.9747, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108011003935505e-05, "loss": 3.9841, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099641435228714e-05, "loss": 3.9657, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709127186652192e-05, "loss": 3.9721, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.70828859190114e-05, "loss": 3.9831, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707449997150088e-05, "loss": 3.9738, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706611402399036e-05, "loss": 3.9708, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705772807647984e-05, "loss": 3.967, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704934212896932e-05, "loss": 3.9747, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.70409561814588e-05, "loss": 3.9573, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703257023394828e-05, "loss": 3.9757, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.70242006652415e-05, "loss": 3.9536, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701581471773098e-05, "loss": 3.9702, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700742877022045e-05, "loss": 3.9733, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699904282270993e-05, "loss": 3.9615, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699067325400315e-05, "loss": 3.9682, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698228730649263e-05, "loss": 3.9688, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.69739013589821e-05, "loss": 3.9479, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696551541147158e-05, "loss": 3.9562, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69571458427648e-05, "loss": 3.967, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694875989525428e-05, "loss": 3.9625, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694039032654749e-05, "loss": 3.9604, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693200437903697e-05, "loss": 3.9467, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692361843152645e-05, "loss": 3.9526, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915232484015926e-05, "loss": 3.9672, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906846536505406e-05, "loss": 3.9687, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898460588994886e-05, "loss": 3.9533, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890074641484366e-05, "loss": 3.9694, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881688693973846e-05, "loss": 3.9718, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873319125267055e-05, "loss": 3.9741, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864933177756535e-05, "loss": 3.9432, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856547230246015e-05, "loss": 3.9642, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848161282735495e-05, "loss": 3.9555, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683979171402871e-05, "loss": 3.9522, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831422145321926e-05, "loss": 3.9557, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.68230361978114e-05, "loss": 3.9576, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681465025030088e-05, "loss": 3.9606, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680626430279036e-05, "loss": 3.9599, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679787835527984e-05, "loss": 3.938, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678949240776932e-05, "loss": 3.9465, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.67811064602588e-05, "loss": 3.9476, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677272051274828e-05, "loss": 3.9519, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676435094404149e-05, "loss": 3.9569, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675596499653097e-05, "loss": 3.9406, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674757904902045e-05, "loss": 3.9492, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739193101509935e-05, "loss": 3.9345, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673083991160687e-05, "loss": 3.9477, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672245396409635e-05, "loss": 3.9479, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671406801658583e-05, "loss": 3.9466, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670568206907531e-05, "loss": 3.9512, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669729612156479e-05, "loss": 3.9468, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668891017405427e-05, "loss": 3.9383, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668052422654375e-05, "loss": 3.9494, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667213827903323e-05, "loss": 3.9465, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666376871032644e-05, "loss": 3.9429, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665538276281592e-05, "loss": 3.9334, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.66469968153054e-05, "loss": 3.9384, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663861086779488e-05, "loss": 3.9442, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66302412990881e-05, "loss": 3.9455, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662185535157758e-05, "loss": 3.9211, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661348578287079e-05, "loss": 3.9367, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660509983536027e-05, "loss": 3.9445, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659671388784975e-05, "loss": 3.9365, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658832794033923e-05, "loss": 3.9303, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579941992828707e-05, "loss": 3.9347, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571556045318187e-05, "loss": 3.9274, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563170097807667e-05, "loss": 3.9457, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554800529100876e-05, "loss": 3.9293, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546414581590356e-05, "loss": 3.9391, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6538028634079836e-05, "loss": 3.9374, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652964268656932e-05, "loss": 3.9415, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652127311786253e-05, "loss": 3.9315, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651288717035201e-05, "loss": 3.939, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650450122284149e-05, "loss": 3.9428, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649611527533097e-05, "loss": 3.933, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648772932782045e-05, "loss": 3.9228, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647934338030993e-05, "loss": 3.9287, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470957432799404e-05, "loss": 3.9236, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646258786409262e-05, "loss": 3.9302, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.64542019165821e-05, "loss": 3.9255, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644581596907158e-05, "loss": 3.9292, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643743002156106e-05, "loss": 3.9195, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429060452854276e-05, "loss": 3.9208, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420674505343756e-05, "loss": 3.9211, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412304936636965e-05, "loss": 3.9382, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403918989126445e-05, "loss": 3.9372, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395533041615925e-05, "loss": 3.9282, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387147094105405e-05, "loss": 3.9151, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637876114659488e-05, "loss": 3.9263, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370391577888094e-05, "loss": 3.9312, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6362005630377574e-05, "loss": 3.9278, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353619682867054e-05, "loss": 3.9221, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634523373535653e-05, "loss": 3.9263, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336847787846014e-05, "loss": 3.9224, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328461840335494e-05, "loss": 3.9317, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320075892824974e-05, "loss": 3.9137, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311689945314454e-05, "loss": 3.9265, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630332037660766e-05, "loss": 3.9153, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629493442909714e-05, "loss": 3.91, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628654848158662e-05, "loss": 3.9259, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.62781625340761e-05, "loss": 3.9248, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626977658656558e-05, "loss": 3.9218, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626139063905506e-05, "loss": 3.9176, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625300469154454e-05, "loss": 3.9119, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9528229236602783, "eval_runtime": 303.3267, "eval_samples_per_second": 1258.02, "eval_steps_per_second": 39.314, "step": 228960 }, { "epoch": 0.0, "learning_rate": 4.624461874403402e-05, "loss": 3.9121, "step": 229376 }, { "epoch": 0.0, "learning_rate": 4.62362327965235e-05, "loss": 3.9064, "step": 229888 }, { "epoch": 0.0, "learning_rate": 4.622784684901298e-05, "loss": 3.9211, "step": 230400 }, { "epoch": 0.0, "learning_rate": 4.621946090150246e-05, "loss": 3.9098, "step": 230912 }, { "epoch": 0.0, "learning_rate": 4.621107495399194e-05, "loss": 3.929, "step": 231424 }, { "epoch": 0.0, "learning_rate": 4.620268900648142e-05, "loss": 3.9017, "step": 231936 }, { "epoch": 0.0, "learning_rate": 4.61943030589709e-05, "loss": 3.9199, "step": 232448 }, { "epoch": 0.0, "learning_rate": 4.618591711146038e-05, "loss": 3.9029, "step": 232960 }, { "epoch": 0.0, "learning_rate": 4.617753116394986e-05, "loss": 3.916, "step": 233472 }, { "epoch": 0.0, "learning_rate": 4.616914521643934e-05, "loss": 3.9103, "step": 233984 }, { "epoch": 0.0, "learning_rate": 4.616077564773255e-05, "loss": 3.9088, "step": 234496 }, { "epoch": 0.0, "learning_rate": 4.615238970022203e-05, "loss": 3.9171, "step": 235008 }, { "epoch": 0.0, "learning_rate": 4.614400375271151e-05, "loss": 3.898, "step": 235520 }, { "epoch": 0.0, "learning_rate": 4.613561780520099e-05, "loss": 3.9037, "step": 236032 }, { "epoch": 0.0, "learning_rate": 4.612723185769047e-05, "loss": 3.9007, "step": 236544 }, { "epoch": 0.0, "learning_rate": 4.611884591017995e-05, "loss": 3.9023, "step": 237056 }, { "epoch": 0.0, "learning_rate": 4.611045996266943e-05, "loss": 3.9029, "step": 237568 }, { "epoch": 0.0, "learning_rate": 4.610209039396265e-05, "loss": 3.8981, "step": 238080 }, { "epoch": 0.0, "learning_rate": 4.609370444645213e-05, "loss": 3.9011, "step": 238592 }, { "epoch": 0.0, "learning_rate": 4.6085318498941607e-05, "loss": 3.9191, "step": 239104 }, { "epoch": 0.0, "learning_rate": 4.6076932551431087e-05, "loss": 3.9056, "step": 239616 }, { "epoch": 0.0, "learning_rate": 4.6068546603920566e-05, "loss": 3.9064, "step": 240128 }, { "epoch": 0.0, "learning_rate": 4.6060160656410046e-05, "loss": 3.906, "step": 240640 }, { "epoch": 0.0, "learning_rate": 4.6051774708899526e-05, "loss": 3.9078, "step": 241152 }, { "epoch": 0.0, "learning_rate": 4.6043388761389006e-05, "loss": 3.8897, "step": 241664 }, { "epoch": 0.0, "learning_rate": 4.6035019192682215e-05, "loss": 3.9097, "step": 242176 }, { "epoch": 0.0, "learning_rate": 4.6026633245171695e-05, "loss": 3.8961, "step": 242688 }, { "epoch": 0.0, "learning_rate": 4.6018247297661175e-05, "loss": 3.8933, "step": 243200 }, { "epoch": 0.0, "learning_rate": 4.6009861350150655e-05, "loss": 3.887, "step": 243712 }, { "epoch": 0.01, "learning_rate": 4.6001491781443864e-05, "loss": 3.8944, "step": 244224 }, { "epoch": 0.01, "learning_rate": 4.5993105833933344e-05, "loss": 3.8952, "step": 244736 }, { "epoch": 0.01, "learning_rate": 4.598471988642283e-05, "loss": 3.9108, "step": 245248 }, { "epoch": 0.01, "learning_rate": 4.597633393891231e-05, "loss": 3.9, "step": 245760 }, { "epoch": 0.01, "learning_rate": 4.596796437020552e-05, "loss": 3.899, "step": 246272 }, { "epoch": 0.01, "learning_rate": 4.595959480149873e-05, "loss": 3.8882, "step": 246784 }, { "epoch": 0.01, "learning_rate": 4.595120885398821e-05, "loss": 3.8986, "step": 247296 }, { "epoch": 0.01, "learning_rate": 4.594282290647769e-05, "loss": 3.8851, "step": 247808 }, { "epoch": 0.01, "learning_rate": 4.593443695896717e-05, "loss": 3.9021, "step": 248320 }, { "epoch": 0.01, "learning_rate": 4.592606739026038e-05, "loss": 3.8762, "step": 248832 }, { "epoch": 0.01, "learning_rate": 4.591768144274986e-05, "loss": 3.8888, "step": 249344 }, { "epoch": 0.01, "learning_rate": 4.590929549523934e-05, "loss": 3.8866, "step": 249856 }, { "epoch": 0.01, "learning_rate": 4.590090954772882e-05, "loss": 3.9024, "step": 250368 }, { "epoch": 0.01, "learning_rate": 4.58925236002183e-05, "loss": 3.8849, "step": 250880 }, { "epoch": 0.01, "learning_rate": 4.5884154031511514e-05, "loss": 3.8875, "step": 251392 }, { "epoch": 0.01, "learning_rate": 4.5875768084000994e-05, "loss": 3.8897, "step": 251904 }, { "epoch": 0.01, "learning_rate": 4.5867382136490474e-05, "loss": 3.8865, "step": 252416 }, { "epoch": 0.01, "learning_rate": 4.5858996188979954e-05, "loss": 3.8922, "step": 252928 }, { "epoch": 0.01, "learning_rate": 4.585061024146943e-05, "loss": 3.8788, "step": 253440 }, { "epoch": 0.01, "learning_rate": 4.584224067276264e-05, "loss": 3.8754, "step": 253952 }, { "epoch": 0.01, "learning_rate": 4.583385472525212e-05, "loss": 3.8918, "step": 254464 }, { "epoch": 0.01, "learning_rate": 4.58254687777416e-05, "loss": 3.8824, "step": 254976 }, { "epoch": 0.01, "learning_rate": 4.5817082830231076e-05, "loss": 3.8821, "step": 255488 }, { "epoch": 0.01, "learning_rate": 4.5808696882720556e-05, "loss": 3.8797, "step": 256000 }, { "epoch": 0.01, "learning_rate": 4.5800310935210036e-05, "loss": 3.883, "step": 256512 }, { "epoch": 0.01, "learning_rate": 4.579194136650325e-05, "loss": 3.8671, "step": 257024 }, { "epoch": 0.01, "learning_rate": 4.578355541899273e-05, "loss": 3.8873, "step": 257536 }, { "epoch": 0.01, "learning_rate": 4.577516947148221e-05, "loss": 3.8636, "step": 258048 }, { "epoch": 0.01, "learning_rate": 4.576678352397169e-05, "loss": 3.8828, "step": 258560 }, { "epoch": 0.01, "learning_rate": 4.575839757646117e-05, "loss": 3.8799, "step": 259072 }, { "epoch": 0.01, "learning_rate": 4.575001162895065e-05, "loss": 3.881, "step": 259584 }, { "epoch": 0.01, "learning_rate": 4.574162568144013e-05, "loss": 3.8751, "step": 260096 }, { "epoch": 0.01, "learning_rate": 4.573325611273334e-05, "loss": 3.8828, "step": 260608 }, { "epoch": 0.01, "learning_rate": 4.572487016522282e-05, "loss": 3.8594, "step": 261120 }, { "epoch": 0.01, "learning_rate": 4.57164842177123e-05, "loss": 3.8725, "step": 261632 }, { "epoch": 0.01, "learning_rate": 4.570809827020178e-05, "loss": 3.8805, "step": 262144 }, { "epoch": 0.01, "learning_rate": 4.569972870149499e-05, "loss": 3.8764, "step": 262656 }, { "epoch": 0.01, "learning_rate": 4.5691359132788205e-05, "loss": 3.8666, "step": 263168 }, { "epoch": 0.01, "learning_rate": 4.5682973185277685e-05, "loss": 3.8656, "step": 263680 }, { "epoch": 0.01, "learning_rate": 4.5674587237767165e-05, "loss": 3.8654, "step": 264192 }, { "epoch": 0.01, "learning_rate": 4.5666201290256645e-05, "loss": 3.8762, "step": 264704 }, { "epoch": 0.01, "learning_rate": 4.5657815342746125e-05, "loss": 3.8831, "step": 265216 }, { "epoch": 0.01, "learning_rate": 4.5649445774039334e-05, "loss": 3.869, "step": 265728 }, { "epoch": 0.01, "learning_rate": 4.5641059826528814e-05, "loss": 3.8837, "step": 266240 }, { "epoch": 0.01, "learning_rate": 4.5632673879018294e-05, "loss": 3.8848, "step": 266752 }, { "epoch": 0.01, "learning_rate": 4.5624287931507774e-05, "loss": 3.8914, "step": 267264 }, { "epoch": 0.01, "learning_rate": 4.561591836280098e-05, "loss": 3.856, "step": 267776 }, { "epoch": 0.01, "learning_rate": 4.560753241529046e-05, "loss": 3.8764, "step": 268288 }, { "epoch": 0.01, "learning_rate": 4.559914646777994e-05, "loss": 3.8758, "step": 268800 }, { "epoch": 0.01, "learning_rate": 4.559076052026943e-05, "loss": 3.8643, "step": 269312 }, { "epoch": 0.01, "learning_rate": 4.558237457275891e-05, "loss": 3.8731, "step": 269824 }, { "epoch": 0.01, "learning_rate": 4.557398862524839e-05, "loss": 3.8763, "step": 270336 }, { "epoch": 0.01, "learning_rate": 4.556560267773787e-05, "loss": 3.879, "step": 270848 }, { "epoch": 0.01, "learning_rate": 4.555723310903108e-05, "loss": 3.8683, "step": 271360 }, { "epoch": 0.01, "learning_rate": 4.554884716152056e-05, "loss": 3.8613, "step": 271872 }, { "epoch": 0.01, "learning_rate": 4.554046121401004e-05, "loss": 3.8604, "step": 272384 }, { "epoch": 0.01, "learning_rate": 4.553207526649952e-05, "loss": 3.8648, "step": 272896 }, { "epoch": 0.01, "learning_rate": 4.552370569779273e-05, "loss": 3.8716, "step": 273408 }, { "epoch": 0.01, "learning_rate": 4.551531975028221e-05, "loss": 3.8746, "step": 273920 }, { "epoch": 0.01, "learning_rate": 4.550693380277169e-05, "loss": 3.8591, "step": 274432 }, { "epoch": 0.02, "learning_rate": 4.549854785526117e-05, "loss": 3.8661, "step": 274944 }, { "epoch": 0.02, "learning_rate": 4.549016190775065e-05, "loss": 3.8531, "step": 275456 }, { "epoch": 0.02, "learning_rate": 4.5481792339043864e-05, "loss": 3.8634, "step": 275968 }, { "epoch": 0.02, "learning_rate": 4.5473406391533343e-05, "loss": 3.8678, "step": 276480 }, { "epoch": 0.02, "learning_rate": 4.5465020444022823e-05, "loss": 3.8632, "step": 276992 }, { "epoch": 0.02, "learning_rate": 4.54566344965123e-05, "loss": 3.8727, "step": 277504 }, { "epoch": 0.02, "learning_rate": 4.544826492780551e-05, "loss": 3.866, "step": 278016 }, { "epoch": 0.02, "learning_rate": 4.543987898029499e-05, "loss": 3.8587, "step": 278528 }, { "epoch": 0.02, "learning_rate": 4.543149303278447e-05, "loss": 3.8669, "step": 279040 }, { "epoch": 0.02, "learning_rate": 4.542310708527395e-05, "loss": 3.8673, "step": 279552 }, { "epoch": 0.02, "learning_rate": 4.541472113776343e-05, "loss": 3.8674, "step": 280064 }, { "epoch": 0.02, "learning_rate": 4.540633519025291e-05, "loss": 3.8523, "step": 280576 }, { "epoch": 0.02, "learning_rate": 4.5397949242742385e-05, "loss": 3.8577, "step": 281088 }, { "epoch": 0.02, "learning_rate": 4.5389563295231865e-05, "loss": 3.8636, "step": 281600 }, { "epoch": 0.02, "learning_rate": 4.538119372652508e-05, "loss": 3.8706, "step": 282112 }, { "epoch": 0.02, "learning_rate": 4.53728241578183e-05, "loss": 3.8467, "step": 282624 }, { "epoch": 0.02, "learning_rate": 4.5364454589111506e-05, "loss": 3.8525, "step": 283136 }, { "epoch": 0.02, "learning_rate": 4.5356068641600986e-05, "loss": 3.8669, "step": 283648 }, { "epoch": 0.02, "learning_rate": 4.5347682694090466e-05, "loss": 3.8581, "step": 284160 }, { "epoch": 0.02, "learning_rate": 4.5339296746579946e-05, "loss": 3.8519, "step": 284672 }, { "epoch": 0.02, "learning_rate": 4.5330910799069426e-05, "loss": 3.8527, "step": 285184 }, { "epoch": 0.02, "learning_rate": 4.5322524851558906e-05, "loss": 3.8551, "step": 285696 }, { "epoch": 0.02, "learning_rate": 4.5314138904048386e-05, "loss": 3.8628, "step": 286208 }, { "epoch": 0.02, "learning_rate": 4.530575295653786e-05, "loss": 3.8536, "step": 286720 }, { "epoch": 0.02, "learning_rate": 4.529736700902734e-05, "loss": 3.8552, "step": 287232 }, { "epoch": 0.02, "learning_rate": 4.5288997440320555e-05, "loss": 3.8618, "step": 287744 }, { "epoch": 0.02, "learning_rate": 4.5280611492810035e-05, "loss": 3.8638, "step": 288256 }, { "epoch": 0.02, "learning_rate": 4.5272225545299515e-05, "loss": 3.8633, "step": 288768 }, { "epoch": 0.02, "learning_rate": 4.5263839597788995e-05, "loss": 3.8552, "step": 289280 }, { "epoch": 0.02, "learning_rate": 4.5255453650278475e-05, "loss": 3.8695, "step": 289792 }, { "epoch": 0.02, "learning_rate": 4.5247067702767955e-05, "loss": 3.8579, "step": 290304 }, { "epoch": 0.02, "learning_rate": 4.5238698134061164e-05, "loss": 3.843, "step": 290816 }, { "epoch": 0.02, "learning_rate": 4.5230312186550644e-05, "loss": 3.8537, "step": 291328 }, { "epoch": 0.02, "learning_rate": 4.5221926239040124e-05, "loss": 3.8499, "step": 291840 }, { "epoch": 0.02, "learning_rate": 4.5213540291529604e-05, "loss": 3.8561, "step": 292352 }, { "epoch": 0.02, "learning_rate": 4.520517072282281e-05, "loss": 3.846, "step": 292864 }, { "epoch": 0.02, "learning_rate": 4.519678477531229e-05, "loss": 3.8563, "step": 293376 }, { "epoch": 0.02, "learning_rate": 4.518839882780177e-05, "loss": 3.8442, "step": 293888 }, { "epoch": 0.02, "learning_rate": 4.518001288029125e-05, "loss": 3.8468, "step": 294400 }, { "epoch": 0.02, "learning_rate": 4.517162693278074e-05, "loss": 3.8462, "step": 294912 }, { "epoch": 0.02, "learning_rate": 4.516325736407395e-05, "loss": 3.8659, "step": 295424 }, { "epoch": 0.02, "learning_rate": 4.515487141656343e-05, "loss": 3.8587, "step": 295936 }, { "epoch": 0.02, "learning_rate": 4.514648546905291e-05, "loss": 3.8558, "step": 296448 }, { "epoch": 0.02, "learning_rate": 4.513809952154239e-05, "loss": 3.8407, "step": 296960 }, { "epoch": 0.02, "learning_rate": 4.51297299528356e-05, "loss": 3.8541, "step": 297472 }, { "epoch": 0.02, "learning_rate": 4.512134400532508e-05, "loss": 3.8591, "step": 297984 }, { "epoch": 0.02, "learning_rate": 4.511295805781456e-05, "loss": 3.8507, "step": 298496 }, { "epoch": 0.02, "learning_rate": 4.510457211030404e-05, "loss": 3.8487, "step": 299008 }, { "epoch": 0.02, "learning_rate": 4.5096202541597246e-05, "loss": 3.8558, "step": 299520 }, { "epoch": 0.02, "learning_rate": 4.5087816594086726e-05, "loss": 3.849, "step": 300032 }, { "epoch": 0.02, "learning_rate": 4.5079430646576206e-05, "loss": 3.8594, "step": 300544 }, { "epoch": 0.02, "learning_rate": 4.507104469906569e-05, "loss": 3.8377, "step": 301056 }, { "epoch": 0.02, "learning_rate": 4.506265875155517e-05, "loss": 3.8537, "step": 301568 }, { "epoch": 0.02, "learning_rate": 4.505428918284838e-05, "loss": 3.8419, "step": 302080 }, { "epoch": 0.02, "learning_rate": 4.504590323533786e-05, "loss": 3.8423, "step": 302592 }, { "epoch": 0.02, "learning_rate": 4.503751728782734e-05, "loss": 3.8496, "step": 303104 }, { "epoch": 0.02, "learning_rate": 4.502913134031682e-05, "loss": 3.8553, "step": 303616 }, { "epoch": 0.02, "learning_rate": 4.50207453928063e-05, "loss": 3.8486, "step": 304128 }, { "epoch": 0.02, "learning_rate": 4.501237582409951e-05, "loss": 3.8421, "step": 304640 }, { "epoch": 0.02, "learning_rate": 4.500398987658899e-05, "loss": 3.8437, "step": 305152 }, { "epoch": 0.03, "eval_loss": 3.9119937419891357, "eval_runtime": 303.505, "eval_samples_per_second": 1257.281, "eval_steps_per_second": 39.291, "step": 305280 }, { "epoch": 1.0, "learning_rate": 4.499560392907847e-05, "loss": 3.8453, "step": 305664 }, { "epoch": 1.0, "learning_rate": 4.498721798156795e-05, "loss": 3.8371, "step": 306176 }, { "epoch": 1.0, "learning_rate": 4.497883203405743e-05, "loss": 3.8472, "step": 306688 }, { "epoch": 1.0, "learning_rate": 4.497046246535065e-05, "loss": 3.8403, "step": 307200 }, { "epoch": 1.0, "learning_rate": 4.496207651784013e-05, "loss": 3.8567, "step": 307712 }, { "epoch": 1.0, "learning_rate": 4.495369057032961e-05, "loss": 3.8368, "step": 308224 }, { "epoch": 1.0, "learning_rate": 4.4945304622819087e-05, "loss": 3.8441, "step": 308736 }, { "epoch": 1.0, "learning_rate": 4.4936935054112296e-05, "loss": 3.8328, "step": 309248 }, { "epoch": 1.0, "learning_rate": 4.4928549106601776e-05, "loss": 3.8448, "step": 309760 }, { "epoch": 1.0, "learning_rate": 4.4920163159091256e-05, "loss": 3.8439, "step": 310272 }, { "epoch": 1.0, "learning_rate": 4.4911777211580736e-05, "loss": 3.8382, "step": 310784 }, { "epoch": 1.0, "learning_rate": 4.4903407642873945e-05, "loss": 3.8431, "step": 311296 }, { "epoch": 1.0, "learning_rate": 4.4895021695363425e-05, "loss": 3.8281, "step": 311808 }, { "epoch": 1.0, "learning_rate": 4.4886635747852905e-05, "loss": 3.8336, "step": 312320 }, { "epoch": 1.0, "learning_rate": 4.4878249800342385e-05, "loss": 3.8333, "step": 312832 }, { "epoch": 1.0, "learning_rate": 4.4869863852831864e-05, "loss": 3.8315, "step": 313344 }, { "epoch": 1.0, "learning_rate": 4.486149428412508e-05, "loss": 3.835, "step": 313856 }, { "epoch": 1.0, "learning_rate": 4.485310833661456e-05, "loss": 3.8316, "step": 314368 }, { "epoch": 1.0, "learning_rate": 4.484472238910404e-05, "loss": 3.8339, "step": 314880 }, { "epoch": 1.0, "learning_rate": 4.483633644159352e-05, "loss": 3.8461, "step": 315392 }, { "epoch": 1.0, "learning_rate": 4.482796687288673e-05, "loss": 3.8406, "step": 315904 }, { "epoch": 1.0, "learning_rate": 4.481958092537621e-05, "loss": 3.8381, "step": 316416 }, { "epoch": 1.0, "learning_rate": 4.481119497786569e-05, "loss": 3.8402, "step": 316928 }, { "epoch": 1.0, "learning_rate": 4.480280903035516e-05, "loss": 3.8403, "step": 317440 }, { "epoch": 1.0, "learning_rate": 4.479443946164838e-05, "loss": 3.8218, "step": 317952 }, { "epoch": 1.0, "learning_rate": 4.478605351413786e-05, "loss": 3.8402, "step": 318464 }, { "epoch": 1.0, "learning_rate": 4.477766756662734e-05, "loss": 3.828, "step": 318976 }, { "epoch": 1.0, "learning_rate": 4.476928161911682e-05, "loss": 3.8241, "step": 319488 }, { "epoch": 1.0, "learning_rate": 4.47608956716063e-05, "loss": 3.8204, "step": 320000 }, { "epoch": 1.0, "learning_rate": 4.4752526102899514e-05, "loss": 3.8277, "step": 320512 }, { "epoch": 1.01, "learning_rate": 4.4744140155388994e-05, "loss": 3.8278, "step": 321024 }, { "epoch": 1.01, "learning_rate": 4.473575420787847e-05, "loss": 3.8439, "step": 321536 }, { "epoch": 1.01, "learning_rate": 4.472736826036795e-05, "loss": 3.8348, "step": 322048 }, { "epoch": 1.01, "learning_rate": 4.471898231285743e-05, "loss": 3.8298, "step": 322560 }, { "epoch": 1.01, "learning_rate": 4.4710612744150636e-05, "loss": 3.8221, "step": 323072 }, { "epoch": 1.01, "learning_rate": 4.4702226796640116e-05, "loss": 3.8332, "step": 323584 }, { "epoch": 1.01, "learning_rate": 4.4693840849129596e-05, "loss": 3.8259, "step": 324096 }, { "epoch": 1.01, "learning_rate": 4.4685454901619076e-05, "loss": 3.8312, "step": 324608 }, { "epoch": 1.01, "learning_rate": 4.4677085332912285e-05, "loss": 3.81, "step": 325120 }, { "epoch": 1.01, "learning_rate": 4.466869938540177e-05, "loss": 3.8218, "step": 325632 }, { "epoch": 1.01, "learning_rate": 4.466031343789125e-05, "loss": 3.8223, "step": 326144 }, { "epoch": 1.01, "learning_rate": 4.465192749038073e-05, "loss": 3.8384, "step": 326656 }, { "epoch": 1.01, "learning_rate": 4.464355792167394e-05, "loss": 3.8246, "step": 327168 }, { "epoch": 1.01, "learning_rate": 4.463517197416342e-05, "loss": 3.8221, "step": 327680 }, { "epoch": 1.01, "learning_rate": 4.46267860266529e-05, "loss": 3.826, "step": 328192 }, { "epoch": 1.01, "learning_rate": 4.461840007914238e-05, "loss": 3.821, "step": 328704 }, { "epoch": 1.01, "learning_rate": 4.461003051043559e-05, "loss": 3.8294, "step": 329216 }, { "epoch": 1.01, "learning_rate": 4.460164456292507e-05, "loss": 3.8153, "step": 329728 }, { "epoch": 1.01, "learning_rate": 4.459325861541455e-05, "loss": 3.811, "step": 330240 }, { "epoch": 1.01, "learning_rate": 4.458487266790403e-05, "loss": 3.8283, "step": 330752 }, { "epoch": 1.01, "learning_rate": 4.457648672039351e-05, "loss": 3.8179, "step": 331264 }, { "epoch": 1.01, "learning_rate": 4.4568117151686725e-05, "loss": 3.8188, "step": 331776 }, { "epoch": 1.01, "learning_rate": 4.4559731204176205e-05, "loss": 3.8134, "step": 332288 }, { "epoch": 1.01, "learning_rate": 4.4551345256665685e-05, "loss": 3.8216, "step": 332800 }, { "epoch": 1.01, "learning_rate": 4.4542959309155165e-05, "loss": 3.804, "step": 333312 }, { "epoch": 1.01, "learning_rate": 4.4534589740448374e-05, "loss": 3.819, "step": 333824 }, { "epoch": 1.01, "learning_rate": 4.4526203792937854e-05, "loss": 3.806, "step": 334336 }, { "epoch": 1.01, "learning_rate": 4.4517817845427334e-05, "loss": 3.8164, "step": 334848 }, { "epoch": 1.01, "learning_rate": 4.4509431897916814e-05, "loss": 3.8191, "step": 335360 }, { "epoch": 1.01, "learning_rate": 4.4501045950406294e-05, "loss": 3.816, "step": 335872 }, { "epoch": 1.01, "learning_rate": 4.44926763816995e-05, "loss": 3.8116, "step": 336384 }, { "epoch": 1.01, "learning_rate": 4.448429043418898e-05, "loss": 3.8238, "step": 336896 }, { "epoch": 1.01, "learning_rate": 4.447590448667846e-05, "loss": 3.7989, "step": 337408 }, { "epoch": 1.01, "learning_rate": 4.446751853916794e-05, "loss": 3.8038, "step": 337920 }, { "epoch": 1.01, "learning_rate": 4.445913259165742e-05, "loss": 3.8182, "step": 338432 }, { "epoch": 1.01, "learning_rate": 4.445074664414691e-05, "loss": 3.8133, "step": 338944 }, { "epoch": 1.01, "learning_rate": 4.444236069663639e-05, "loss": 3.8095, "step": 339456 }, { "epoch": 1.01, "learning_rate": 4.44339911279296e-05, "loss": 3.802, "step": 339968 }, { "epoch": 1.01, "learning_rate": 4.442560518041908e-05, "loss": 3.8026, "step": 340480 }, { "epoch": 1.01, "learning_rate": 4.441721923290856e-05, "loss": 3.8127, "step": 340992 }, { "epoch": 1.01, "learning_rate": 4.440883328539804e-05, "loss": 3.8202, "step": 341504 }, { "epoch": 1.01, "learning_rate": 4.440046371669125e-05, "loss": 3.8124, "step": 342016 }, { "epoch": 1.01, "learning_rate": 4.439207776918073e-05, "loss": 3.8209, "step": 342528 }, { "epoch": 1.01, "learning_rate": 4.438369182167021e-05, "loss": 3.8218, "step": 343040 }, { "epoch": 1.01, "learning_rate": 4.437530587415969e-05, "loss": 3.8342, "step": 343552 }, { "epoch": 1.01, "learning_rate": 4.43669363054529e-05, "loss": 3.8007, "step": 344064 }, { "epoch": 1.01, "learning_rate": 4.435855035794238e-05, "loss": 3.8115, "step": 344576 }, { "epoch": 1.01, "learning_rate": 4.4350164410431864e-05, "loss": 3.821, "step": 345088 }, { "epoch": 1.01, "learning_rate": 4.4341778462921344e-05, "loss": 3.8002, "step": 345600 }, { "epoch": 1.01, "learning_rate": 4.4333392515410824e-05, "loss": 3.8149, "step": 346112 }, { "epoch": 1.01, "learning_rate": 4.43250065679003e-05, "loss": 3.8145, "step": 346624 }, { "epoch": 1.01, "learning_rate": 4.431663699919351e-05, "loss": 3.8157, "step": 347136 }, { "epoch": 1.01, "learning_rate": 4.430825105168299e-05, "loss": 3.8111, "step": 347648 }, { "epoch": 1.01, "learning_rate": 4.429986510417247e-05, "loss": 3.801, "step": 348160 }, { "epoch": 1.01, "learning_rate": 4.4291479156661946e-05, "loss": 3.8011, "step": 348672 }, { "epoch": 1.01, "learning_rate": 4.428310958795516e-05, "loss": 3.8038, "step": 349184 }, { "epoch": 1.01, "learning_rate": 4.427472364044464e-05, "loss": 3.8102, "step": 349696 }, { "epoch": 1.01, "learning_rate": 4.426633769293412e-05, "loss": 3.817, "step": 350208 }, { "epoch": 1.01, "learning_rate": 4.42579517454236e-05, "loss": 3.7992, "step": 350720 }, { "epoch": 1.02, "learning_rate": 4.424958217671682e-05, "loss": 3.8065, "step": 351232 }, { "epoch": 1.02, "learning_rate": 4.42411962292063e-05, "loss": 3.7943, "step": 351744 }, { "epoch": 1.02, "learning_rate": 4.423281028169577e-05, "loss": 3.8035, "step": 352256 }, { "epoch": 1.02, "learning_rate": 4.422442433418525e-05, "loss": 3.8083, "step": 352768 }, { "epoch": 1.02, "learning_rate": 4.4216054765478466e-05, "loss": 3.8078, "step": 353280 }, { "epoch": 1.02, "learning_rate": 4.4207668817967946e-05, "loss": 3.815, "step": 353792 }, { "epoch": 1.02, "learning_rate": 4.419928287045742e-05, "loss": 3.8051, "step": 354304 }, { "epoch": 1.02, "learning_rate": 4.41908969229469e-05, "loss": 3.8021, "step": 354816 }, { "epoch": 1.02, "learning_rate": 4.4182527354240115e-05, "loss": 3.8056, "step": 355328 }, { "epoch": 1.02, "learning_rate": 4.4174141406729595e-05, "loss": 3.8052, "step": 355840 }, { "epoch": 1.02, "learning_rate": 4.416575545921907e-05, "loss": 3.811, "step": 356352 }, { "epoch": 1.02, "learning_rate": 4.4157369511708555e-05, "loss": 3.7956, "step": 356864 }, { "epoch": 1.02, "learning_rate": 4.414899994300177e-05, "loss": 3.8019, "step": 357376 }, { "epoch": 1.02, "learning_rate": 4.4140613995491244e-05, "loss": 3.8023, "step": 357888 }, { "epoch": 1.02, "learning_rate": 4.4132228047980724e-05, "loss": 3.8115, "step": 358400 }, { "epoch": 1.02, "learning_rate": 4.4123842100470204e-05, "loss": 3.79, "step": 358912 }, { "epoch": 1.02, "learning_rate": 4.4115456152959684e-05, "loss": 3.7973, "step": 359424 }, { "epoch": 1.02, "learning_rate": 4.410708658425289e-05, "loss": 3.809, "step": 359936 }, { "epoch": 1.02, "learning_rate": 4.409870063674237e-05, "loss": 3.8019, "step": 360448 }, { "epoch": 1.02, "learning_rate": 4.409033106803559e-05, "loss": 3.7907, "step": 360960 }, { "epoch": 1.02, "learning_rate": 4.408194512052507e-05, "loss": 3.8014, "step": 361472 }, { "epoch": 1.02, "learning_rate": 4.407355917301454e-05, "loss": 3.7939, "step": 361984 }, { "epoch": 1.02, "learning_rate": 4.406517322550402e-05, "loss": 3.8103, "step": 362496 }, { "epoch": 1.02, "learning_rate": 4.405678727799351e-05, "loss": 3.795, "step": 363008 }, { "epoch": 1.02, "learning_rate": 4.404840133048299e-05, "loss": 3.7945, "step": 363520 }, { "epoch": 1.02, "learning_rate": 4.404001538297247e-05, "loss": 3.8077, "step": 364032 }, { "epoch": 1.02, "learning_rate": 4.403162943546195e-05, "loss": 3.8119, "step": 364544 }, { "epoch": 1.02, "learning_rate": 4.402325986675516e-05, "loss": 3.803, "step": 365056 }, { "epoch": 1.02, "learning_rate": 4.401487391924464e-05, "loss": 3.8012, "step": 365568 }, { "epoch": 1.02, "learning_rate": 4.400648797173412e-05, "loss": 3.8068, "step": 366080 }, { "epoch": 1.02, "learning_rate": 4.39981020242236e-05, "loss": 3.7988, "step": 366592 }, { "epoch": 1.02, "learning_rate": 4.398973245551681e-05, "loss": 3.7908, "step": 367104 }, { "epoch": 1.02, "learning_rate": 4.3981346508006287e-05, "loss": 3.8025, "step": 367616 }, { "epoch": 1.02, "learning_rate": 4.3972960560495767e-05, "loss": 3.7912, "step": 368128 }, { "epoch": 1.02, "learning_rate": 4.3964574612985247e-05, "loss": 3.8, "step": 368640 }, { "epoch": 1.02, "learning_rate": 4.3956205044278456e-05, "loss": 3.7909, "step": 369152 }, { "epoch": 1.02, "learning_rate": 4.394781909676794e-05, "loss": 3.7982, "step": 369664 }, { "epoch": 1.02, "learning_rate": 4.393943314925742e-05, "loss": 3.7879, "step": 370176 }, { "epoch": 1.02, "learning_rate": 4.39310472017469e-05, "loss": 3.7873, "step": 370688 }, { "epoch": 1.02, "learning_rate": 4.392266125423638e-05, "loss": 3.7947, "step": 371200 }, { "epoch": 1.02, "learning_rate": 4.391429168552959e-05, "loss": 3.8047, "step": 371712 }, { "epoch": 1.02, "learning_rate": 4.390590573801907e-05, "loss": 3.8038, "step": 372224 }, { "epoch": 1.02, "learning_rate": 4.389751979050855e-05, "loss": 3.8035, "step": 372736 }, { "epoch": 1.02, "learning_rate": 4.388913384299803e-05, "loss": 3.7836, "step": 373248 }, { "epoch": 1.02, "learning_rate": 4.388076427429124e-05, "loss": 3.8021, "step": 373760 }, { "epoch": 1.02, "learning_rate": 4.387237832678072e-05, "loss": 3.8014, "step": 374272 }, { "epoch": 1.02, "learning_rate": 4.38639923792702e-05, "loss": 3.7999, "step": 374784 }, { "epoch": 1.02, "learning_rate": 4.385562281056341e-05, "loss": 3.7899, "step": 375296 }, { "epoch": 1.02, "learning_rate": 4.3847236863052896e-05, "loss": 3.8036, "step": 375808 }, { "epoch": 1.02, "learning_rate": 4.3838850915542376e-05, "loss": 3.7903, "step": 376320 }, { "epoch": 1.02, "learning_rate": 4.3830464968031856e-05, "loss": 3.8065, "step": 376832 }, { "epoch": 1.02, "learning_rate": 4.3822079020521336e-05, "loss": 3.7802, "step": 377344 }, { "epoch": 1.02, "learning_rate": 4.3813709451814545e-05, "loss": 3.8048, "step": 377856 }, { "epoch": 1.02, "learning_rate": 4.3805323504304025e-05, "loss": 3.7856, "step": 378368 }, { "epoch": 1.02, "learning_rate": 4.3796937556793505e-05, "loss": 3.7881, "step": 378880 }, { "epoch": 1.02, "learning_rate": 4.3788551609282985e-05, "loss": 3.7985, "step": 379392 }, { "epoch": 1.02, "learning_rate": 4.3780165661772465e-05, "loss": 3.7946, "step": 379904 }, { "epoch": 1.02, "learning_rate": 4.3771796093065674e-05, "loss": 3.798, "step": 380416 }, { "epoch": 1.02, "learning_rate": 4.3763410145555154e-05, "loss": 3.7822, "step": 380928 }, { "epoch": 1.02, "learning_rate": 4.3755024198044634e-05, "loss": 3.7953, "step": 381440 }, { "epoch": 1.03, "eval_loss": 3.887127637863159, "eval_runtime": 303.6757, "eval_samples_per_second": 1256.574, "eval_steps_per_second": 39.269, "step": 381600 }, { "epoch": 0.0, "learning_rate": 4.3746638250534114e-05, "loss": 3.7867, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.3738252303023594e-05, "loss": 3.7837, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.372986635551308e-05, "loss": 3.7945, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.3721480408002554e-05, "loss": 3.7888, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.3713094460492034e-05, "loss": 3.7996, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.3704708512981514e-05, "loss": 3.7841, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.3696322565470993e-05, "loss": 3.7852, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.3687936617960473e-05, "loss": 3.785, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.367956704925368e-05, "loss": 3.7905, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367118110174316e-05, "loss": 3.7909, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.366279515423264e-05, "loss": 3.7843, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365440920672212e-05, "loss": 3.7934, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.364603963801533e-05, "loss": 3.7777, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.363765369050482e-05, "loss": 3.7827, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.36292677429943e-05, "loss": 3.7832, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.362088179548378e-05, "loss": 3.776, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.361251222677699e-05, "loss": 3.7846, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.360412627926647e-05, "loss": 3.7759, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.359574033175595e-05, "loss": 3.7771, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.358735438424543e-05, "loss": 3.7976, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.3578984815538636e-05, "loss": 3.7861, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.3570598868028116e-05, "loss": 3.7937, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.3562212920517596e-05, "loss": 3.7855, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.3553826973007076e-05, "loss": 3.7891, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.3545441025496556e-05, "loss": 3.7707, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.353707145678977e-05, "loss": 3.7914, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.352868550927925e-05, "loss": 3.7794, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.352029956176873e-05, "loss": 3.7694, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.351191361425821e-05, "loss": 3.7711, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.350354404555142e-05, "loss": 3.7751, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.34951580980409e-05, "loss": 3.78, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.348677215053038e-05, "loss": 3.7898, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.347838620301986e-05, "loss": 3.7874, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.347001663431307e-05, "loss": 3.7796, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.346163068680255e-05, "loss": 3.775, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.345324473929203e-05, "loss": 3.7803, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.344485879178151e-05, "loss": 3.775, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.3436489223074726e-05, "loss": 3.7783, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.3428103275564206e-05, "loss": 3.7662, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.3419717328053685e-05, "loss": 3.7686, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.3411331380543165e-05, "loss": 3.7729, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.3402945433032645e-05, "loss": 3.7871, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.3394575864325854e-05, "loss": 3.7768, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.3386189916815334e-05, "loss": 3.7716, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.3377803969304814e-05, "loss": 3.7788, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.3369418021794294e-05, "loss": 3.7687, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.3361048453087503e-05, "loss": 3.7787, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.3352662505576983e-05, "loss": 3.7668, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.334427655806646e-05, "loss": 3.7604, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.333589061055594e-05, "loss": 3.7779, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332752104184916e-05, "loss": 3.7709, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.331913509433864e-05, "loss": 3.77, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331074914682812e-05, "loss": 3.7698, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.33023631993176e-05, "loss": 3.7679, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329397725180708e-05, "loss": 3.7597, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328560768310029e-05, "loss": 3.7677, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327722173558977e-05, "loss": 3.7599, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.326883578807925e-05, "loss": 3.7645, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.326044984056873e-05, "loss": 3.7743, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.325208027186194e-05, "loss": 3.7639, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.324369432435142e-05, "loss": 3.7657, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.32353083768409e-05, "loss": 3.7758, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.322692242933038e-05, "loss": 3.7537, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.321855286062359e-05, "loss": 3.7572, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.321016691311307e-05, "loss": 3.7657, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.320178096560255e-05, "loss": 3.7673, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.319339501809203e-05, "loss": 3.7567, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.318502544938524e-05, "loss": 3.7588, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.317663950187472e-05, "loss": 3.755, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.31682535543642e-05, "loss": 3.7647, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315986760685368e-05, "loss": 3.7718, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.315149803814689e-05, "loss": 3.7666, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.314311209063637e-05, "loss": 3.7737, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313472614312585e-05, "loss": 3.7681, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.312634019561533e-05, "loss": 3.7934, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.3117970626908546e-05, "loss": 3.7543, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.3109584679398026e-05, "loss": 3.7631, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.3101198731887506e-05, "loss": 3.774, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309281278437698e-05, "loss": 3.7507, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.3084443215670195e-05, "loss": 3.7695, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.3076057268159675e-05, "loss": 3.7686, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.3067671320649155e-05, "loss": 3.768, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.305928537313863e-05, "loss": 3.7638, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.3050915804431844e-05, "loss": 3.7511, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042529856921324e-05, "loss": 3.762, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3034143909410804e-05, "loss": 3.7527, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025757961900284e-05, "loss": 3.7645, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.30173883931935e-05, "loss": 3.7718, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.300900244568298e-05, "loss": 3.7502, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.300061649817245e-05, "loss": 3.7598, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.299223055066193e-05, "loss": 3.7526, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.298386098195515e-05, "loss": 3.7542, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297547503444463e-05, "loss": 3.7572, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.29670890869341e-05, "loss": 3.7684, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295870313942358e-05, "loss": 3.77, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.29503335707168e-05, "loss": 3.7545, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294194762320628e-05, "loss": 3.7548, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293356167569576e-05, "loss": 3.7629, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.292517572818524e-05, "loss": 3.7556, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.2916806159478454e-05, "loss": 3.7671, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.290842021196793e-05, "loss": 3.7508, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.290003426445741e-05, "loss": 3.7529, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.289164831694689e-05, "loss": 3.7605, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.288326236943637e-05, "loss": 3.7661, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.2874892800729576e-05, "loss": 3.7448, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.2866506853219056e-05, "loss": 3.7523, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.285813728451227e-05, "loss": 3.7602, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.284975133700175e-05, "loss": 3.7591, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.2841365389491225e-05, "loss": 3.7446, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.283297944198071e-05, "loss": 3.7633, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.282459349447019e-05, "loss": 3.7457, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.281620754695967e-05, "loss": 3.7619, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.280782159944915e-05, "loss": 3.7544, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.279945203074236e-05, "loss": 3.7499, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.279106608323184e-05, "loss": 3.7602, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.278268013572132e-05, "loss": 3.7692, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.27742941882108e-05, "loss": 3.7574, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.276592461950401e-05, "loss": 3.7549, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.275753867199349e-05, "loss": 3.7635, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.274915272448297e-05, "loss": 3.7569, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.274076677697245e-05, "loss": 3.7468, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.273238082946193e-05, "loss": 3.7535, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.2724011260755145e-05, "loss": 3.7484, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.2715625313244625e-05, "loss": 3.7549, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.2707239365734105e-05, "loss": 3.7535, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.2698853418223585e-05, "loss": 3.7509, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.2690483849516794e-05, "loss": 3.7479, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.2682097902006274e-05, "loss": 3.7418, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.2673711954495754e-05, "loss": 3.7533, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.2665326006985234e-05, "loss": 3.7606, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.265695643827844e-05, "loss": 3.7583, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.264857049076792e-05, "loss": 3.7604, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.26401845432574e-05, "loss": 3.7392, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.263179859574688e-05, "loss": 3.7613, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.26234290270401e-05, "loss": 3.7567, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.261504307952958e-05, "loss": 3.755, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.260665713201906e-05, "loss": 3.7508, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.259827118450854e-05, "loss": 3.7568, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.258990161580175e-05, "loss": 3.7463, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.258151566829123e-05, "loss": 3.7681, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.257312972078071e-05, "loss": 3.7357, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.256474377327019e-05, "loss": 3.7585, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.255635782575967e-05, "loss": 3.7423, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.254798825705288e-05, "loss": 3.7472, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.253960230954236e-05, "loss": 3.7552, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.253121636203184e-05, "loss": 3.7501, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.252283041452132e-05, "loss": 3.7601, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.251446084581453e-05, "loss": 3.7358, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.250607489830401e-05, "loss": 3.7538, "step": 457728 }, { "epoch": 0.03, "eval_loss": 3.8698768615722656, "eval_runtime": 302.5882, "eval_samples_per_second": 1261.09, "eval_steps_per_second": 39.41, "step": 457920 }, { "epoch": 1.0, "learning_rate": 4.249768895079349e-05, "loss": 3.7491, "step": 458240 }, { "epoch": 1.0, "learning_rate": 4.248930300328297e-05, "loss": 3.7393, "step": 458752 }, { "epoch": 1.0, "learning_rate": 4.248093343457618e-05, "loss": 3.7532, "step": 459264 }, { "epoch": 1.0, "learning_rate": 4.247254748706566e-05, "loss": 3.7465, "step": 459776 }, { "epoch": 1.0, "learning_rate": 4.246416153955514e-05, "loss": 3.7546, "step": 460288 }, { "epoch": 1.0, "learning_rate": 4.245577559204462e-05, "loss": 3.7427, "step": 460800 }, { "epoch": 1.0, "learning_rate": 4.244740602333783e-05, "loss": 3.7412, "step": 461312 }, { "epoch": 1.0, "learning_rate": 4.243902007582731e-05, "loss": 3.7441, "step": 461824 }, { "epoch": 1.0, "learning_rate": 4.243063412831679e-05, "loss": 3.746, "step": 462336 }, { "epoch": 1.0, "learning_rate": 4.242224818080627e-05, "loss": 3.7484, "step": 462848 }, { "epoch": 1.0, "learning_rate": 4.2413878612099486e-05, "loss": 3.7461, "step": 463360 }, { "epoch": 1.0, "learning_rate": 4.2405492664588966e-05, "loss": 3.7461, "step": 463872 }, { "epoch": 1.0, "learning_rate": 4.2397123095882175e-05, "loss": 3.7396, "step": 464384 }, { "epoch": 1.0, "learning_rate": 4.2388737148371655e-05, "loss": 3.7392, "step": 464896 }, { "epoch": 1.0, "learning_rate": 4.2380351200861135e-05, "loss": 3.7431, "step": 465408 }, { "epoch": 1.0, "learning_rate": 4.2371965253350615e-05, "loss": 3.7344, "step": 465920 }, { "epoch": 1.0, "learning_rate": 4.2363579305840095e-05, "loss": 3.7413, "step": 466432 }, { "epoch": 1.0, "learning_rate": 4.2355193358329575e-05, "loss": 3.7361, "step": 466944 }, { "epoch": 1.0, "learning_rate": 4.2346807410819055e-05, "loss": 3.7366, "step": 467456 }, { "epoch": 1.0, "learning_rate": 4.233842146330853e-05, "loss": 3.7543, "step": 467968 }, { "epoch": 1.0, "learning_rate": 4.2330051894601744e-05, "loss": 3.7463, "step": 468480 }, { "epoch": 1.0, "learning_rate": 4.2321665947091224e-05, "loss": 3.7508, "step": 468992 }, { "epoch": 1.0, "learning_rate": 4.2313279999580704e-05, "loss": 3.7428, "step": 469504 }, { "epoch": 1.0, "learning_rate": 4.2304894052070184e-05, "loss": 3.7472, "step": 470016 }, { "epoch": 1.0, "learning_rate": 4.2296508104559664e-05, "loss": 3.729, "step": 470528 }, { "epoch": 1.0, "learning_rate": 4.228813853585288e-05, "loss": 3.7499, "step": 471040 }, { "epoch": 1.0, "learning_rate": 4.227975258834236e-05, "loss": 3.7363, "step": 471552 }, { "epoch": 1.0, "learning_rate": 4.227136664083183e-05, "loss": 3.7313, "step": 472064 }, { "epoch": 1.0, "learning_rate": 4.226299707212505e-05, "loss": 3.7306, "step": 472576 }, { "epoch": 1.0, "learning_rate": 4.225461112461453e-05, "loss": 3.7349, "step": 473088 }, { "epoch": 1.01, "learning_rate": 4.2246225177104e-05, "loss": 3.7385, "step": 473600 }, { "epoch": 1.01, "learning_rate": 4.223783922959348e-05, "loss": 3.7504, "step": 474112 }, { "epoch": 1.01, "learning_rate": 4.22294696608867e-05, "loss": 3.7458, "step": 474624 }, { "epoch": 1.01, "learning_rate": 4.222108371337618e-05, "loss": 3.7397, "step": 475136 }, { "epoch": 1.01, "learning_rate": 4.221269776586566e-05, "loss": 3.7282, "step": 475648 }, { "epoch": 1.01, "learning_rate": 4.220431181835514e-05, "loss": 3.7418, "step": 476160 }, { "epoch": 1.01, "learning_rate": 4.2195942249648353e-05, "loss": 3.7389, "step": 476672 }, { "epoch": 1.01, "learning_rate": 4.2187556302137833e-05, "loss": 3.7318, "step": 477184 }, { "epoch": 1.01, "learning_rate": 4.217917035462731e-05, "loss": 3.729, "step": 477696 }, { "epoch": 1.01, "learning_rate": 4.2170784407116787e-05, "loss": 3.727, "step": 478208 }, { "epoch": 1.01, "learning_rate": 4.216241483841e-05, "loss": 3.7332, "step": 478720 }, { "epoch": 1.01, "learning_rate": 4.2154028890899476e-05, "loss": 3.7436, "step": 479232 }, { "epoch": 1.01, "learning_rate": 4.2145642943388956e-05, "loss": 3.7402, "step": 479744 }, { "epoch": 1.01, "learning_rate": 4.2137256995878436e-05, "loss": 3.7324, "step": 480256 }, { "epoch": 1.01, "learning_rate": 4.2128871048367915e-05, "loss": 3.7365, "step": 480768 }, { "epoch": 1.01, "learning_rate": 4.212050147966113e-05, "loss": 3.7284, "step": 481280 }, { "epoch": 1.01, "learning_rate": 4.211211553215061e-05, "loss": 3.74, "step": 481792 }, { "epoch": 1.01, "learning_rate": 4.210372958464009e-05, "loss": 3.7267, "step": 482304 }, { "epoch": 1.01, "learning_rate": 4.209534363712957e-05, "loss": 3.7169, "step": 482816 }, { "epoch": 1.01, "learning_rate": 4.208697406842278e-05, "loss": 3.7385, "step": 483328 }, { "epoch": 1.01, "learning_rate": 4.207858812091226e-05, "loss": 3.7331, "step": 483840 }, { "epoch": 1.01, "learning_rate": 4.207020217340174e-05, "loss": 3.7338, "step": 484352 }, { "epoch": 1.01, "learning_rate": 4.206181622589122e-05, "loss": 3.7257, "step": 484864 }, { "epoch": 1.01, "learning_rate": 4.205344665718443e-05, "loss": 3.7261, "step": 485376 }, { "epoch": 1.01, "learning_rate": 4.204506070967391e-05, "loss": 3.7201, "step": 485888 }, { "epoch": 1.01, "learning_rate": 4.203667476216339e-05, "loss": 3.7255, "step": 486400 }, { "epoch": 1.01, "learning_rate": 4.202828881465287e-05, "loss": 3.7212, "step": 486912 }, { "epoch": 1.01, "learning_rate": 4.2019919245946085e-05, "loss": 3.7287, "step": 487424 }, { "epoch": 1.01, "learning_rate": 4.2011533298435565e-05, "loss": 3.7319, "step": 487936 }, { "epoch": 1.01, "learning_rate": 4.2003147350925045e-05, "loss": 3.7251, "step": 488448 }, { "epoch": 1.01, "learning_rate": 4.1994761403414525e-05, "loss": 3.7245, "step": 488960 }, { "epoch": 1.01, "learning_rate": 4.1986391834707734e-05, "loss": 3.7418, "step": 489472 }, { "epoch": 1.01, "learning_rate": 4.1978005887197214e-05, "loss": 3.7117, "step": 489984 }, { "epoch": 1.01, "learning_rate": 4.1969619939686694e-05, "loss": 3.7168, "step": 490496 }, { "epoch": 1.01, "learning_rate": 4.1961233992176174e-05, "loss": 3.7272, "step": 491008 }, { "epoch": 1.01, "learning_rate": 4.195286442346938e-05, "loss": 3.7325, "step": 491520 }, { "epoch": 1.01, "learning_rate": 4.194447847595886e-05, "loss": 3.7159, "step": 492032 }, { "epoch": 1.01, "learning_rate": 4.193609252844834e-05, "loss": 3.7192, "step": 492544 }, { "epoch": 1.01, "learning_rate": 4.192770658093782e-05, "loss": 3.7171, "step": 493056 }, { "epoch": 1.01, "learning_rate": 4.191933701223104e-05, "loss": 3.7227, "step": 493568 }, { "epoch": 1.01, "learning_rate": 4.191095106472052e-05, "loss": 3.735, "step": 494080 }, { "epoch": 1.01, "learning_rate": 4.190256511721e-05, "loss": 3.7254, "step": 494592 }, { "epoch": 1.01, "learning_rate": 4.189417916969948e-05, "loss": 3.7311, "step": 495104 }, { "epoch": 1.01, "learning_rate": 4.188580960099269e-05, "loss": 3.7356, "step": 495616 }, { "epoch": 1.01, "learning_rate": 4.187742365348217e-05, "loss": 3.7487, "step": 496128 }, { "epoch": 1.01, "learning_rate": 4.186903770597165e-05, "loss": 3.7191, "step": 496640 }, { "epoch": 1.01, "learning_rate": 4.186065175846113e-05, "loss": 3.7274, "step": 497152 }, { "epoch": 1.01, "learning_rate": 4.185228218975434e-05, "loss": 3.7323, "step": 497664 }, { "epoch": 1.01, "learning_rate": 4.1843896242243817e-05, "loss": 3.7147, "step": 498176 }, { "epoch": 1.01, "learning_rate": 4.1835510294733297e-05, "loss": 3.7315, "step": 498688 }, { "epoch": 1.01, "learning_rate": 4.1827124347222776e-05, "loss": 3.7294, "step": 499200 }, { "epoch": 1.01, "learning_rate": 4.181875477851599e-05, "loss": 3.7297, "step": 499712 }, { "epoch": 1.01, "learning_rate": 4.181036883100547e-05, "loss": 3.7286, "step": 500224 }, { "epoch": 1.01, "learning_rate": 4.180198288349495e-05, "loss": 3.7131, "step": 500736 }, { "epoch": 1.01, "learning_rate": 4.179359693598443e-05, "loss": 3.7197, "step": 501248 }, { "epoch": 1.01, "learning_rate": 4.178522736727764e-05, "loss": 3.7182, "step": 501760 }, { "epoch": 1.01, "learning_rate": 4.177684141976712e-05, "loss": 3.7246, "step": 502272 }, { "epoch": 1.01, "learning_rate": 4.17684554722566e-05, "loss": 3.7318, "step": 502784 }, { "epoch": 1.01, "learning_rate": 4.176006952474608e-05, "loss": 3.7132, "step": 503296 }, { "epoch": 1.02, "learning_rate": 4.175169995603929e-05, "loss": 3.7229, "step": 503808 }, { "epoch": 1.02, "learning_rate": 4.174331400852877e-05, "loss": 3.7161, "step": 504320 }, { "epoch": 1.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7125, "step": 504832 }, { "epoch": 1.02, "learning_rate": 4.172654211350773e-05, "loss": 3.7245, "step": 505344 }, { "epoch": 1.02, "learning_rate": 4.1718172544800946e-05, "loss": 3.7264, "step": 505856 }, { "epoch": 1.02, "learning_rate": 4.1709786597290426e-05, "loss": 3.7328, "step": 506368 }, { "epoch": 1.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.721, "step": 506880 }, { "epoch": 1.02, "learning_rate": 4.1693014702269386e-05, "loss": 3.7149, "step": 507392 }, { "epoch": 1.02, "learning_rate": 4.1684645133562595e-05, "loss": 3.7241, "step": 507904 }, { "epoch": 1.02, "learning_rate": 4.1676259186052075e-05, "loss": 3.7207, "step": 508416 }, { "epoch": 1.02, "learning_rate": 4.1667873238541555e-05, "loss": 3.7283, "step": 508928 }, { "epoch": 1.02, "learning_rate": 4.1659487291031035e-05, "loss": 3.715, "step": 509440 }, { "epoch": 1.02, "learning_rate": 4.1651117722324244e-05, "loss": 3.7157, "step": 509952 }, { "epoch": 1.02, "learning_rate": 4.1642731774813724e-05, "loss": 3.7205, "step": 510464 }, { "epoch": 1.02, "learning_rate": 4.1634345827303204e-05, "loss": 3.7317, "step": 510976 }, { "epoch": 1.02, "learning_rate": 4.1625959879792684e-05, "loss": 3.7041, "step": 511488 }, { "epoch": 1.02, "learning_rate": 4.16175903110859e-05, "loss": 3.7176, "step": 512000 }, { "epoch": 1.02, "learning_rate": 4.160920436357538e-05, "loss": 3.7201, "step": 512512 }, { "epoch": 1.02, "learning_rate": 4.160081841606486e-05, "loss": 3.724, "step": 513024 }, { "epoch": 1.02, "learning_rate": 4.159244884735807e-05, "loss": 3.7054, "step": 513536 }, { "epoch": 1.02, "learning_rate": 4.158406289984755e-05, "loss": 3.722, "step": 514048 }, { "epoch": 1.02, "learning_rate": 4.157567695233703e-05, "loss": 3.7162, "step": 514560 }, { "epoch": 1.02, "learning_rate": 4.156729100482651e-05, "loss": 3.7202, "step": 515072 }, { "epoch": 1.02, "learning_rate": 4.155890505731599e-05, "loss": 3.7216, "step": 515584 }, { "epoch": 1.02, "learning_rate": 4.155051910980547e-05, "loss": 3.7144, "step": 516096 }, { "epoch": 1.02, "learning_rate": 4.154213316229495e-05, "loss": 3.7178, "step": 516608 }, { "epoch": 1.02, "learning_rate": 4.153374721478443e-05, "loss": 3.7327, "step": 517120 }, { "epoch": 1.02, "learning_rate": 4.152537764607764e-05, "loss": 3.72, "step": 517632 }, { "epoch": 1.02, "learning_rate": 4.151699169856712e-05, "loss": 3.7173, "step": 518144 }, { "epoch": 1.02, "learning_rate": 4.15086057510566e-05, "loss": 3.728, "step": 518656 }, { "epoch": 1.02, "learning_rate": 4.1500219803546084e-05, "loss": 3.7204, "step": 519168 }, { "epoch": 1.02, "learning_rate": 4.149185023483929e-05, "loss": 3.7065, "step": 519680 }, { "epoch": 1.02, "learning_rate": 4.148346428732877e-05, "loss": 3.7221, "step": 520192 }, { "epoch": 1.02, "learning_rate": 4.147507833981825e-05, "loss": 3.7105, "step": 520704 }, { "epoch": 1.02, "learning_rate": 4.146669239230773e-05, "loss": 3.7152, "step": 521216 }, { "epoch": 1.02, "learning_rate": 4.145832282360094e-05, "loss": 3.7161, "step": 521728 }, { "epoch": 1.02, "learning_rate": 4.144993687609042e-05, "loss": 3.716, "step": 522240 }, { "epoch": 1.02, "learning_rate": 4.14415509285799e-05, "loss": 3.7134, "step": 522752 }, { "epoch": 1.02, "learning_rate": 4.143316498106938e-05, "loss": 3.7086, "step": 523264 }, { "epoch": 1.02, "learning_rate": 4.142479541236259e-05, "loss": 3.7117, "step": 523776 }, { "epoch": 1.02, "learning_rate": 4.141640946485207e-05, "loss": 3.7282, "step": 524288 }, { "epoch": 1.02, "learning_rate": 4.140802351734155e-05, "loss": 3.719, "step": 524800 }, { "epoch": 1.02, "learning_rate": 4.139963756983103e-05, "loss": 3.724, "step": 525312 }, { "epoch": 1.02, "learning_rate": 4.139126800112425e-05, "loss": 3.7032, "step": 525824 }, { "epoch": 1.02, "learning_rate": 4.138288205361373e-05, "loss": 3.7292, "step": 526336 }, { "epoch": 1.02, "learning_rate": 4.137449610610321e-05, "loss": 3.7182, "step": 526848 }, { "epoch": 1.02, "learning_rate": 4.136611015859268e-05, "loss": 3.7203, "step": 527360 }, { "epoch": 1.02, "learning_rate": 4.1357740589885896e-05, "loss": 3.7141, "step": 527872 }, { "epoch": 1.02, "learning_rate": 4.1349354642375376e-05, "loss": 3.7196, "step": 528384 }, { "epoch": 1.02, "learning_rate": 4.1340968694864856e-05, "loss": 3.7103, "step": 528896 }, { "epoch": 1.02, "learning_rate": 4.133258274735433e-05, "loss": 3.7347, "step": 529408 }, { "epoch": 1.02, "learning_rate": 4.1324213178647545e-05, "loss": 3.6996, "step": 529920 }, { "epoch": 1.02, "learning_rate": 4.1315827231137025e-05, "loss": 3.7195, "step": 530432 }, { "epoch": 1.02, "learning_rate": 4.1307441283626505e-05, "loss": 3.7097, "step": 530944 }, { "epoch": 1.02, "learning_rate": 4.1299055336115985e-05, "loss": 3.7121, "step": 531456 }, { "epoch": 1.02, "learning_rate": 4.12906857674092e-05, "loss": 3.7142, "step": 531968 }, { "epoch": 1.02, "learning_rate": 4.128229981989868e-05, "loss": 3.7125, "step": 532480 }, { "epoch": 1.02, "learning_rate": 4.1273913872388154e-05, "loss": 3.7269, "step": 532992 }, { "epoch": 1.02, "learning_rate": 4.1265527924877634e-05, "loss": 3.7013, "step": 533504 }, { "epoch": 1.02, "learning_rate": 4.125715835617085e-05, "loss": 3.7193, "step": 534016 }, { "epoch": 1.03, "eval_loss": 3.859912157058716, "eval_runtime": 303.7577, "eval_samples_per_second": 1256.235, "eval_steps_per_second": 39.258, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124877240866032e-05, "loss": 3.7149, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.12403864611498e-05, "loss": 3.7039, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123200051363928e-05, "loss": 3.7154, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.122361456612876e-05, "loss": 3.7128, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121522861861824e-05, "loss": 3.7187, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.120684267110773e-05, "loss": 3.7058, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119845672359721e-05, "loss": 3.7111, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.119007077608669e-05, "loss": 3.7066, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.11817012073799e-05, "loss": 3.7151, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.117331525986938e-05, "loss": 3.7132, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.116492931235886e-05, "loss": 3.7133, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.115654336484834e-05, "loss": 3.7073, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.1148190174945276e-05, "loss": 3.7068, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.1139804227434756e-05, "loss": 3.705, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.1131418279924236e-05, "loss": 3.7099, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.1123032332413716e-05, "loss": 3.6973, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.1114646384903196e-05, "loss": 3.7043, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110626043739268e-05, "loss": 3.6999, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109787448988216e-05, "loss": 3.7037, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108948854237164e-05, "loss": 3.7149, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108111897366485e-05, "loss": 3.7154, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107273302615433e-05, "loss": 3.7158, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.106434707864381e-05, "loss": 3.7094, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105596113113329e-05, "loss": 3.7097, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.10475915624265e-05, "loss": 3.6965, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.103920561491598e-05, "loss": 3.7178, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.103081966740546e-05, "loss": 3.7012, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102243371989494e-05, "loss": 3.6977, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.101406415118815e-05, "loss": 3.6974, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.1005678203677637e-05, "loss": 3.7026, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.0997292256167117e-05, "loss": 3.7027, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.0988906308656597e-05, "loss": 3.7162, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.0980536739949806e-05, "loss": 3.7136, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.0972150792439286e-05, "loss": 3.7026, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.0963764844928766e-05, "loss": 3.6969, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.0955378897418245e-05, "loss": 3.7098, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.0947009328711455e-05, "loss": 3.707, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.0938623381200935e-05, "loss": 3.6975, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.0930237433690414e-05, "loss": 3.6959, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.0921867864983624e-05, "loss": 3.6937, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.0913481917473104e-05, "loss": 3.6969, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.0905095969962583e-05, "loss": 3.7098, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.089671002245207e-05, "loss": 3.706, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.088834045374528e-05, "loss": 3.6977, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.087995450623476e-05, "loss": 3.7043, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.087156855872424e-05, "loss": 3.6946, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.086318261121372e-05, "loss": 3.7057, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.085481304250693e-05, "loss": 3.696, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.084642709499641e-05, "loss": 3.6797, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083804114748589e-05, "loss": 3.7065, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082965519997537e-05, "loss": 3.698, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082128563126858e-05, "loss": 3.7027, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081289968375806e-05, "loss": 3.6931, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080451373624754e-05, "loss": 3.6909, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.0796127788737024e-05, "loss": 3.6887, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078775822003023e-05, "loss": 3.6905, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077937227251971e-05, "loss": 3.6937, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077098632500919e-05, "loss": 3.6941, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076260037749867e-05, "loss": 3.7039, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.075423080879188e-05, "loss": 3.688, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074584486128136e-05, "loss": 3.6939, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.073745891377084e-05, "loss": 3.7063, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072907296626032e-05, "loss": 3.6792, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.072070339755353e-05, "loss": 3.684, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.071231745004301e-05, "loss": 3.6989, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.070393150253249e-05, "loss": 3.6966, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069554555502198e-05, "loss": 3.6843, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068717598631519e-05, "loss": 3.6905, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.0678790038804667e-05, "loss": 3.6827, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.0670404091294147e-05, "loss": 3.6933, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.0662018143783627e-05, "loss": 3.6973, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.0653648575076836e-05, "loss": 3.6955, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.0645262627566316e-05, "loss": 3.6961, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.0636876680055796e-05, "loss": 3.7037, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.0628490732545275e-05, "loss": 3.7149, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.0620121163838485e-05, "loss": 3.688, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.0611735216327965e-05, "loss": 3.6958, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.0603349268817444e-05, "loss": 3.7011, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059496332130693e-05, "loss": 3.6829, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058659375260014e-05, "loss": 3.6947, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.057820780508962e-05, "loss": 3.6983, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.05698218575791e-05, "loss": 3.6975, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056143591006858e-05, "loss": 3.6984, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.055306634136179e-05, "loss": 3.6816, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.054468039385127e-05, "loss": 3.6831, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.053629444634075e-05, "loss": 3.6881, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.052790849883023e-05, "loss": 3.6931, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.051953893012344e-05, "loss": 3.6952, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.051115298261292e-05, "loss": 3.685, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.05027670351024e-05, "loss": 3.6889, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.049438108759188e-05, "loss": 3.6857, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.0486011518885094e-05, "loss": 3.6812, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.0477625571374574e-05, "loss": 3.6913, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0469239623864054e-05, "loss": 3.6951, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.046085367635353e-05, "loss": 3.6993, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.045248410764674e-05, "loss": 3.6911, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044409816013622e-05, "loss": 3.682, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.04357122126257e-05, "loss": 3.6957, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.0427326265115176e-05, "loss": 3.6907, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.041895669640839e-05, "loss": 3.6915, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041057074889787e-05, "loss": 3.6858, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040218480138735e-05, "loss": 3.685, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039379885387683e-05, "loss": 3.6856, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.038542928517005e-05, "loss": 3.7005, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037704333765953e-05, "loss": 3.6755, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.0368657390149e-05, "loss": 3.6874, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.036028782144222e-05, "loss": 3.6849, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.03519018739317e-05, "loss": 3.6929, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.0343532305224906e-05, "loss": 3.6791, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.0335146357714386e-05, "loss": 3.6924, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.0326760410203866e-05, "loss": 3.6799, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.0318374462693346e-05, "loss": 3.6908, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.0309988515182826e-05, "loss": 3.6924, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.0301602567672305e-05, "loss": 3.6806, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.0293216620161785e-05, "loss": 3.6881, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.0284830672651265e-05, "loss": 3.7016, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.0276461103944475e-05, "loss": 3.6908, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.0268075156433954e-05, "loss": 3.687, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.0259689208923434e-05, "loss": 3.6933, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.0251303261412914e-05, "loss": 3.6935, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.0242933692706123e-05, "loss": 3.6772, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.0234547745195603e-05, "loss": 3.6923, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022616179768508e-05, "loss": 3.6767, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021777585017456e-05, "loss": 3.6866, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.020940628146778e-05, "loss": 3.6822, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.020102033395726e-05, "loss": 3.6858, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.019263438644674e-05, "loss": 3.6834, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.018424843893622e-05, "loss": 3.6808, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.017587887022943e-05, "loss": 3.6793, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.016749292271891e-05, "loss": 3.6964, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.015910697520839e-05, "loss": 3.6904, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.015072102769787e-05, "loss": 3.6932, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.014235145899108e-05, "loss": 3.672, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013396551148056e-05, "loss": 3.7021, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012557956397004e-05, "loss": 3.6835, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011719361645952e-05, "loss": 3.6893, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010882404775273e-05, "loss": 3.687, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.010043810024221e-05, "loss": 3.6855, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009205215273169e-05, "loss": 3.6793, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008366620522117e-05, "loss": 3.7021, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007529663651438e-05, "loss": 3.6739, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006691068900386e-05, "loss": 3.6902, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.005852474149334e-05, "loss": 3.6805, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.005013879398282e-05, "loss": 3.6829, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.004176922527603e-05, "loss": 3.6815, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.003338327776551e-05, "loss": 3.6833, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.002499733025499e-05, "loss": 3.694, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.001661138274447e-05, "loss": 3.6777, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.0008241814037687e-05, "loss": 3.6865, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.8532724380493164, "eval_runtime": 311.9124, "eval_samples_per_second": 1223.392, "eval_steps_per_second": 38.232, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.9999855866527166e-05, "loss": 3.6805, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.9991469919016646e-05, "loss": 3.6761, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.9983083971506126e-05, "loss": 3.6823, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.9974714402799336e-05, "loss": 3.6804, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.9966328455288815e-05, "loss": 3.6918, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.9957942507778295e-05, "loss": 3.6751, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.9949556560267775e-05, "loss": 3.6832, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.9941186991560984e-05, "loss": 3.6784, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.9932801044050464e-05, "loss": 3.6791, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.9924415096539944e-05, "loss": 3.6862, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.991604552783316e-05, "loss": 3.679, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990765958032264e-05, "loss": 3.6772, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989929001161585e-05, "loss": 3.6822, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.989090406410533e-05, "loss": 3.669, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.988251811659481e-05, "loss": 3.6781, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.987413216908429e-05, "loss": 3.6706, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.986574622157377e-05, "loss": 3.6781, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.985736027406325e-05, "loss": 3.6719, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.984897432655273e-05, "loss": 3.671, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.984058837904221e-05, "loss": 3.6867, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.983221881033542e-05, "loss": 3.6877, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.982384924162863e-05, "loss": 3.6877, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.981546329411811e-05, "loss": 3.6777, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.9807077346607594e-05, "loss": 3.6774, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.9798691399097074e-05, "loss": 3.6723, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.9790305451586554e-05, "loss": 3.6827, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.9781919504076034e-05, "loss": 3.6748, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.9773533556565514e-05, "loss": 3.6752, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.9765147609054994e-05, "loss": 3.6665, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.97567780403482e-05, "loss": 3.671, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.974839209283768e-05, "loss": 3.6696, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.974000614532716e-05, "loss": 3.6869, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.973162019781664e-05, "loss": 3.6837, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.972325062910985e-05, "loss": 3.674, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.971486468159933e-05, "loss": 3.6693, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.970647873408881e-05, "loss": 3.678, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.969809278657829e-05, "loss": 3.6762, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968972321787151e-05, "loss": 3.6736, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.968133727036099e-05, "loss": 3.668, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967295132285047e-05, "loss": 3.6638, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.966456537533995e-05, "loss": 3.6664, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.9656195806633156e-05, "loss": 3.6839, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.9647809859122636e-05, "loss": 3.6789, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.9639423911612116e-05, "loss": 3.6665, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.9631037964101596e-05, "loss": 3.6752, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.9622668395394805e-05, "loss": 3.6665, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.9614282447884285e-05, "loss": 3.676, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605896500373765e-05, "loss": 3.6678, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.9597510552863245e-05, "loss": 3.6476, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.958914098415646e-05, "loss": 3.6819, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.958075503664594e-05, "loss": 3.6673, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.957236908913542e-05, "loss": 3.6758, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956399952042863e-05, "loss": 3.666, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955561357291811e-05, "loss": 3.663, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954722762540759e-05, "loss": 3.6569, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.953884167789707e-05, "loss": 3.6625, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.953045573038655e-05, "loss": 3.6648, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952206978287602e-05, "loss": 3.6637, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.95136838353655e-05, "loss": 3.6751, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950529788785498e-05, "loss": 3.6595, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.94969283191482e-05, "loss": 3.6666, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948854237163768e-05, "loss": 3.6796, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.948015642412716e-05, "loss": 3.6522, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.947177047661664e-05, "loss": 3.6534, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.946340090790985e-05, "loss": 3.6675, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.945501496039933e-05, "loss": 3.6686, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.944662901288881e-05, "loss": 3.6566, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.9438259444182024e-05, "loss": 3.6605, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.94298734966715e-05, "loss": 3.6579, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.942148754916098e-05, "loss": 3.6626, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.941310160165046e-05, "loss": 3.6689, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.940473203294367e-05, "loss": 3.6657, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.939634608543315e-05, "loss": 3.6733, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.938796013792263e-05, "loss": 3.673, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.937957419041211e-05, "loss": 3.6877, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.937120462170532e-05, "loss": 3.6562, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.93628186741948e-05, "loss": 3.6722, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.935443272668428e-05, "loss": 3.6709, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.934604677917376e-05, "loss": 3.6568, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933767721046697e-05, "loss": 3.6632, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932929126295645e-05, "loss": 3.6752, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932090531544593e-05, "loss": 3.6686, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.931251936793541e-05, "loss": 3.6725, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.9304149799228626e-05, "loss": 3.6524, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.9295763851718106e-05, "loss": 3.6536, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.9287377904207586e-05, "loss": 3.6607, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.9278991956697066e-05, "loss": 3.6678, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.9270622387990275e-05, "loss": 3.6671, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.9262236440479755e-05, "loss": 3.6606, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.9253850492969235e-05, "loss": 3.6547, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.9245464545458715e-05, "loss": 3.662, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.9237094976751924e-05, "loss": 3.6537, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.9228709029241404e-05, "loss": 3.664, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.9220323081730884e-05, "loss": 3.6705, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.9211937134220364e-05, "loss": 3.6696, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.920356756551358e-05, "loss": 3.6627, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.919518161800306e-05, "loss": 3.656, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.918679567049254e-05, "loss": 3.6673, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.917840972298202e-05, "loss": 3.6605, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.917004015427523e-05, "loss": 3.6664, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.916165420676471e-05, "loss": 3.6617, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.915326825925419e-05, "loss": 3.6545, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914488231174367e-05, "loss": 3.6656, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.913651274303688e-05, "loss": 3.668, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912812679552636e-05, "loss": 3.6468, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911974084801584e-05, "loss": 3.6595, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911135490050532e-05, "loss": 3.6535, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.9102985331798534e-05, "loss": 3.6728, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909461576309174e-05, "loss": 3.6466, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908622981558122e-05, "loss": 3.6673, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.90778438680707e-05, "loss": 3.6538, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.906945792056018e-05, "loss": 3.6626, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.906107197304966e-05, "loss": 3.6624, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.905268602553914e-05, "loss": 3.6548, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.904430007802862e-05, "loss": 3.6584, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.90359141305181e-05, "loss": 3.6754, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.902754456181131e-05, "loss": 3.6599, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.901915861430079e-05, "loss": 3.6632, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.901077266679027e-05, "loss": 3.6658, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.900238671927975e-05, "loss": 3.663, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.899401715057297e-05, "loss": 3.6577, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.898563120306245e-05, "loss": 3.6607, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.897724525555193e-05, "loss": 3.6476, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.896885930804141e-05, "loss": 3.6596, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.8960506118138345e-05, "loss": 3.6552, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.8952120170627825e-05, "loss": 3.6582, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.8943734223117305e-05, "loss": 3.6551, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.8935348275606785e-05, "loss": 3.6547, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.8926962328096265e-05, "loss": 3.6517, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.8918576380585745e-05, "loss": 3.6716, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.8910206811878954e-05, "loss": 3.6584, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.890182086436844e-05, "loss": 3.6709, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.889343491685792e-05, "loss": 3.6413, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.88850489693474e-05, "loss": 3.6743, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.887666302183688e-05, "loss": 3.6543, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886827707432636e-05, "loss": 3.6653, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885989112681584e-05, "loss": 3.6612, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885150517930532e-05, "loss": 3.6571, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.884313561059853e-05, "loss": 3.6563, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.883474966308801e-05, "loss": 3.6767, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.882636371557749e-05, "loss": 3.6418, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.881797776806697e-05, "loss": 3.665, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.880960819936018e-05, "loss": 3.6567, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.880122225184966e-05, "loss": 3.6498, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.879283630433914e-05, "loss": 3.6564, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.8784466735632355e-05, "loss": 3.6566, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.8776080788121834e-05, "loss": 3.6676, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.8767694840611314e-05, "loss": 3.6548, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.8759308893100794e-05, "loss": 3.6568, "step": 686592 }, { "epoch": 1.03, "eval_loss": 3.848642587661743, "eval_runtime": 304.6815, "eval_samples_per_second": 1252.426, "eval_steps_per_second": 39.139, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.8750922945590274e-05, "loss": 3.6558, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.8742536998079754e-05, "loss": 3.6476, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873415105056923e-05, "loss": 3.6548, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872576510305871e-05, "loss": 3.6579, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.871737915554819e-05, "loss": 3.669, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.870899320803767e-05, "loss": 3.6462, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.870060726052715e-05, "loss": 3.6572, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.869222131301663e-05, "loss": 3.6512, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.868385174430984e-05, "loss": 3.6557, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.867546579679932e-05, "loss": 3.6614, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.866709622809253e-05, "loss": 3.6512, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.865871028058201e-05, "loss": 3.6518, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.865032433307149e-05, "loss": 3.662, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.864193838556097e-05, "loss": 3.6409, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.863355243805045e-05, "loss": 3.652, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.862516649053993e-05, "loss": 3.6433, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.861678054302941e-05, "loss": 3.652, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.860839459551889e-05, "loss": 3.6469, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.86000250268121e-05, "loss": 3.6456, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.859165545810532e-05, "loss": 3.66, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.85832695105948e-05, "loss": 3.6594, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.857488356308428e-05, "loss": 3.6634, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.856649761557376e-05, "loss": 3.6538, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.855811166806324e-05, "loss": 3.6508, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.854972572055272e-05, "loss": 3.6438, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.8541339773042197e-05, "loss": 3.6581, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.8532953825531677e-05, "loss": 3.6512, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.8524584256824886e-05, "loss": 3.6507, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.8516198309314366e-05, "loss": 3.6419, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.8507812361803846e-05, "loss": 3.6461, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.8499442793097055e-05, "loss": 3.642, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.8491056845586535e-05, "loss": 3.6591, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.8482670898076015e-05, "loss": 3.6614, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.8474284950565495e-05, "loss": 3.6466, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.846591538185871e-05, "loss": 3.6457, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.845752943434819e-05, "loss": 3.6479, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844914348683767e-05, "loss": 3.6527, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.844075753932715e-05, "loss": 3.6469, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843238797062036e-05, "loss": 3.642, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842400202310984e-05, "loss": 3.6369, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.841561607559932e-05, "loss": 3.6441, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840724650689253e-05, "loss": 3.6525, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.839886055938201e-05, "loss": 3.6538, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.839047461187149e-05, "loss": 3.6471, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.838208866436097e-05, "loss": 3.6462, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.837370271685045e-05, "loss": 3.6464, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.8365316769339935e-05, "loss": 3.6478, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.8356930821829415e-05, "loss": 3.6446, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.834854487431889e-05, "loss": 3.6214, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.8340175305612104e-05, "loss": 3.657, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8331789358101584e-05, "loss": 3.6439, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.832340341059106e-05, "loss": 3.6524, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.831503384188427e-05, "loss": 3.6429, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.830664789437375e-05, "loss": 3.6374, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.829826194686323e-05, "loss": 3.6334, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.8289875999352706e-05, "loss": 3.6349, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.828150643064592e-05, "loss": 3.6444, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.82731204831354e-05, "loss": 3.6306, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.826473453562489e-05, "loss": 3.65, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.825634858811436e-05, "loss": 3.6387, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.824797901940758e-05, "loss": 3.6368, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.823959307189706e-05, "loss": 3.6571, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.823120712438653e-05, "loss": 3.6296, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.822282117687601e-05, "loss": 3.6292, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821443522936549e-05, "loss": 3.6435, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820604928185497e-05, "loss": 3.6442, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.819766333434445e-05, "loss": 3.6317, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.818927738683393e-05, "loss": 3.637, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.818090781812714e-05, "loss": 3.6266, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.8172521870616626e-05, "loss": 3.6422, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.8164135923106106e-05, "loss": 3.6446, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.8155749975595586e-05, "loss": 3.6454, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.8147380406888795e-05, "loss": 3.644, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.8139010838182004e-05, "loss": 3.6473, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.8130624890671484e-05, "loss": 3.6612, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.8122238943160964e-05, "loss": 3.6364, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.8113852995650444e-05, "loss": 3.65, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.8105467048139924e-05, "loss": 3.643, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.8097081100629404e-05, "loss": 3.6359, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.8088695153118884e-05, "loss": 3.6355, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.8080309205608364e-05, "loss": 3.6512, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.807193963690158e-05, "loss": 3.6433, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806355368939106e-05, "loss": 3.6473, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.805516774188054e-05, "loss": 3.6299, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.804678179437002e-05, "loss": 3.6305, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.803841222566323e-05, "loss": 3.6366, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.803002627815271e-05, "loss": 3.6425, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.802164033064219e-05, "loss": 3.6433, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801325438313167e-05, "loss": 3.6389, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.800488481442488e-05, "loss": 3.6278, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799649886691436e-05, "loss": 3.64, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.798812929820757e-05, "loss": 3.6304, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.797974335069705e-05, "loss": 3.6389, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.7971357403186534e-05, "loss": 3.6456, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.7962971455676014e-05, "loss": 3.6463, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.7954585508165494e-05, "loss": 3.6395, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.7946199560654974e-05, "loss": 3.6357, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.7937813613144454e-05, "loss": 3.6379, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.7929427665633933e-05, "loss": 3.6362, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.792105809692714e-05, "loss": 3.6447, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.791267214941662e-05, "loss": 3.6349, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.79042862019061e-05, "loss": 3.6339, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789590025439558e-05, "loss": 3.6375, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.788753068568879e-05, "loss": 3.6453, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.787914473817827e-05, "loss": 3.6251, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.787075879066775e-05, "loss": 3.637, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.786237284315723e-05, "loss": 3.6291, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.785400327445045e-05, "loss": 3.646, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.7845633705743656e-05, "loss": 3.6257, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.7837247758233136e-05, "loss": 3.6404, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.7828861810722616e-05, "loss": 3.627, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.7820475863212096e-05, "loss": 3.6437, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.7812089915701576e-05, "loss": 3.6384, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.7803703968191056e-05, "loss": 3.6311, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.7795334399484265e-05, "loss": 3.6354, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.7786948451973745e-05, "loss": 3.6502, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.7778562504463225e-05, "loss": 3.6362, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.7770176556952705e-05, "loss": 3.6424, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.7761790609442185e-05, "loss": 3.637, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.77534210407354e-05, "loss": 3.6378, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.774503509322488e-05, "loss": 3.6388, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773664914571436e-05, "loss": 3.6326, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772826319820384e-05, "loss": 3.6265, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.7719877250693314e-05, "loss": 3.6368, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771150768198653e-05, "loss": 3.6348, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.770312173447601e-05, "loss": 3.6341, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769473578696549e-05, "loss": 3.6325, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.768634983945496e-05, "loss": 3.6326, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.767796389194444e-05, "loss": 3.6284, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.766957794443392e-05, "loss": 3.6464, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.766120837572714e-05, "loss": 3.6377, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.765282242821662e-05, "loss": 3.6461, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.76444364807061e-05, "loss": 3.6183, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.763605053319558e-05, "loss": 3.6469, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.762766458568506e-05, "loss": 3.637, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.761929501697827e-05, "loss": 3.6383, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.761090906946775e-05, "loss": 3.6344, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760252312195723e-05, "loss": 3.6335, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.759413717444671e-05, "loss": 3.6357, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758575122693619e-05, "loss": 3.6502, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757736527942567e-05, "loss": 3.6231, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756897933191515e-05, "loss": 3.6394, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.7560609763208356e-05, "loss": 3.6309, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755222381569784e-05, "loss": 3.6275, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.754383786818732e-05, "loss": 3.6353, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753546829948053e-05, "loss": 3.6327, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.752708235197001e-05, "loss": 3.6416, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751869640445949e-05, "loss": 3.6376, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.751031045694897e-05, "loss": 3.6323, "step": 762880 }, { "epoch": 0.03, "eval_loss": 3.8451194763183594, "eval_runtime": 318.5135, "eval_samples_per_second": 1198.037, "eval_steps_per_second": 37.44, "step": 763200 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 5.3133296366352384e+17, "trial_name": null, "trial_params": null }