{ "best_metric": 3.8860065937042236, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/0/checkpoints/checkpoint-381600", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 381600, "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": 10.9724, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8197, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1971, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9867, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8145, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7061, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.602, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5384, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4496, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4067, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3559, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3164, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2621, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2155, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.174, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1412, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1128, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0964, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0555, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0346, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0226, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9766, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9523, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.935, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9275, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8925, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782030879941405e-05, "loss": 4.8725, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773644932430885e-05, "loss": 4.866, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765258984920364e-05, "loss": 4.843, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8167, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8006, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7969, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7839, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7793, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7565, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970659010995419e-05, "loss": 4.74, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7426, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7062, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7007, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6878, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6875, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6647, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6759, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963951890867376e-05, "loss": 4.6454, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 4.6496, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.639, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6313, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6288, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.603, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 4.5906, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.6048, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5908, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5719, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 4.5619, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5677, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5508, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5626, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5345, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5351, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5383, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5198, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5017, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5069, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4903, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4914, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4997, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.496, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4789, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4666, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.461, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4722, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4692, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4595, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4581, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4619, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4532, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4286, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4398, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4356, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4201, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4321, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4225, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4283, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4179, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3931, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4021, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4009, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4022, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3939, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3847, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3882, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.377, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.9228804026303046e-05, "loss": 4.3692, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922041807879253e-05, "loss": 4.3721, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921203213128201e-05, "loss": 4.367, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3785, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3566, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3506, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3508, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3582, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3556, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3411, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3415, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3235, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3386, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3242, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3226, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3261, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3257, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3194, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3175, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3089, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3152, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.303, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3045, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.31, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3061, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.3042, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2941, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2988, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.295, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2806, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2983, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2833, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2914, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2725, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2682, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2657, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.269, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2602, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2767, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2728, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889348077750837e-05, "loss": 4.2573, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2604, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2654, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2618, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885995336627002e-05, "loss": 4.2654, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.8851583797563226e-05, "loss": 4.2617, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.8843197850052706e-05, "loss": 4.2483, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.8834811902542186e-05, "loss": 4.253, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.8826425955031666e-05, "loss": 4.2487, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8818040007521146e-05, "loss": 4.2405, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.252, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2381, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879289854379332e-05, "loss": 4.2283, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87845125962828e-05, "loss": 4.2508, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877612664877228e-05, "loss": 4.2314, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2305, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.232, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875098518504445e-05, "loss": 4.226, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.196994781494141, "eval_runtime": 302.917, "eval_samples_per_second": 1259.721, "eval_steps_per_second": 39.367, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874259923753393e-05, "loss": 4.2093, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873421329002341e-05, "loss": 4.2203, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872582734251289e-05, "loss": 4.2368, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2146, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.228, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2021, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2157, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.1985, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675544415057236e-05, "loss": 4.2096, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667158467546716e-05, "loss": 4.207, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658772520036196e-05, "loss": 4.2098, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650386572525676e-05, "loss": 4.2068, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642017003818885e-05, "loss": 4.1941, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633631056308365e-05, "loss": 4.1845, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625245108797845e-05, "loss": 4.1857, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616859161287324e-05, "loss": 4.1886, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608473213776804e-05, "loss": 4.1981, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.1824, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1919, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.2042, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1811, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1744, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1791, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854978796000689e-05, "loss": 4.1891, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854141839130011e-05, "loss": 4.1677, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853303244378958e-05, "loss": 4.1732, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852464649627906e-05, "loss": 4.1738, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851626054876854e-05, "loss": 4.1692, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.1521, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.1598, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1568, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.84827331375302e-05, "loss": 4.1657, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847434719001968e-05, "loss": 4.1728, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846596124250916e-05, "loss": 4.1563, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.152, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1663, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1395, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.147, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842404788376029e-05, "loss": 4.1375, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.1461, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1359, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.154, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839053685132567e-05, "loss": 4.1396, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838215090381515e-05, "loss": 4.141, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837376495630463e-05, "loss": 4.1374, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836537900879411e-05, "loss": 4.1418, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835699306128359e-05, "loss": 4.1357, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834860711377307e-05, "loss": 4.1263, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1193, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833185159755576e-05, "loss": 4.1403, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832346565004524e-05, "loss": 4.1305, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831507970253472e-05, "loss": 4.1168, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.1176, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1254, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1149, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.1303, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.1121, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1158, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.1273, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1039, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.1011, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231269363840714e-05, "loss": 4.1109, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222883416330194e-05, "loss": 4.0937, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214497468819674e-05, "loss": 4.0992, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206111521309154e-05, "loss": 4.1106, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197725573798634e-05, "loss": 4.1156, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.1018, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.095, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817258411007081e-05, "loss": 4.0873, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816419816256029e-05, "loss": 4.1074, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815581221504977e-05, "loss": 4.1042, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.1011, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.102, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1042, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812228480381141e-05, "loss": 4.1054, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811391523510463e-05, "loss": 4.0832, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810552928759411e-05, "loss": 4.097, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809714334008359e-05, "loss": 4.0956, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808875739257306e-05, "loss": 4.0809, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.1024, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0954, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.0991, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.0967, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0722, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.0854, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0835, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0887, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0834, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0763, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0851, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988158780054285e-05, "loss": 4.079, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.0645, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0736, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0775, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.0875, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0692, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.79378594737949e-05, "loss": 4.0572, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0666, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0753, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0736, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.066, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0626, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.05, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0668, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0523, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0554, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0599, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0607, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837277240079855e-05, "loss": 4.0545, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828891292569335e-05, "loss": 4.0589, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820521723862544e-05, "loss": 4.0476, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812135776352024e-05, "loss": 4.055, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0474, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0475, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778699431262419e-05, "loss": 4.0621, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0589, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777023879640689e-05, "loss": 4.0541, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776185284889637e-05, "loss": 4.0463, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775346690138585e-05, "loss": 4.0527, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774508095387533e-05, "loss": 4.05, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773669500636481e-05, "loss": 4.0386, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772830905885429e-05, "loss": 4.0567, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771992311134377e-05, "loss": 4.0424, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771153716383325e-05, "loss": 4.0522, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770315121632272e-05, "loss": 4.0349, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769478164761594e-05, "loss": 4.0361, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768639570010542e-05, "loss": 4.0329, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76780097525949e-05, "loss": 4.0348, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0329, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.7661254236377586e-05, "loss": 4.0465, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765286828886707e-05, "loss": 4.0493, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764448234135655e-05, "loss": 4.0357, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.0287, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762772682513924e-05, "loss": 4.0413, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761934087762872e-05, "loss": 4.0392, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610954930118195e-05, "loss": 4.0446, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0401, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759419941390089e-05, "loss": 4.0354, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758581346639037e-05, "loss": 4.0269, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577427518879844e-05, "loss": 4.0371, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0276, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756067200266254e-05, "loss": 4.0324, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755228605515202e-05, "loss": 4.0299, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0205, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.0417, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527144591424196e-05, "loss": 4.024, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751875864391367e-05, "loss": 4.0196, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751037269640315e-05, "loss": 4.023, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750198674889263e-05, "loss": 4.0196, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.027214527130127, "eval_runtime": 303.1649, "eval_samples_per_second": 1258.691, "eval_steps_per_second": 39.335, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749360080138211e-05, "loss": 4.0042, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748521485387159e-05, "loss": 4.0197, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747682890636107e-05, "loss": 4.0336, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746844295885055e-05, "loss": 4.0161, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746005701134003e-05, "loss": 4.028, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0074, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744328511631899e-05, "loss": 4.0208, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434899168808475e-05, "loss": 4.0005, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.018, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0151, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0146, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401371757570124e-05, "loss": 4.021, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739300218886333e-05, "loss": 4.0038, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738461624135281e-05, "loss": 3.9984, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737623029384229e-05, "loss": 3.9967, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736784434633177e-05, "loss": 4.007, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735945839882125e-05, "loss": 4.0104, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735107245131073e-05, "loss": 4.0018, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734268650380021e-05, "loss": 4.0057, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733430055628969e-05, "loss": 4.0241, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732591460877917e-05, "loss": 3.9987, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731752866126865e-05, "loss": 3.9953, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730914271375813e-05, "loss": 4.0014, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730075676624761e-05, "loss": 4.0098, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729238719754082e-05, "loss": 3.9925, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.72840012500303e-05, "loss": 3.9959, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727561530251978e-05, "loss": 3.9986, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726722935500926e-05, "loss": 3.9939, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725885978630247e-05, "loss": 3.9803, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725047383879195e-05, "loss": 3.9881, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724208789128143e-05, "loss": 3.9904, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723370194377091e-05, "loss": 3.9926, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225332375064127e-05, "loss": 4.0063, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216946427553606e-05, "loss": 3.9861, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208560480043086e-05, "loss": 3.9857, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200174532532566e-05, "loss": 3.9961, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191804963825775e-05, "loss": 3.9803, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183419016315255e-05, "loss": 3.9794, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.9735, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166663500097945e-05, "loss": 3.9848, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158277552587424e-05, "loss": 3.9726, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149891605076904e-05, "loss": 3.9975, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9762, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133119710055864e-05, "loss": 3.9859, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712475014134908e-05, "loss": 3.9798, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711636419383856e-05, "loss": 3.9775, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.9793, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709959229881752e-05, "loss": 3.9671, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709122273011073e-05, "loss": 3.9628, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708283678260021e-05, "loss": 3.9857, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707445083508969e-05, "loss": 3.975, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.9646, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9687, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9757, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9565, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032553855144554e-05, "loss": 3.9775, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024167907634034e-05, "loss": 3.9635, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9642, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.981, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990264439062e-05, "loss": 3.9576, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699064049639568e-05, "loss": 3.9537, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9664, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697386860137464e-05, "loss": 3.9505, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696549903266785e-05, "loss": 3.9542, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695711308515733e-05, "loss": 3.967, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9693, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694034119013629e-05, "loss": 3.9532, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693197162142951e-05, "loss": 3.9554, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692360205272272e-05, "loss": 3.943, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.69152161052122e-05, "loss": 3.9659, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906830157701677e-05, "loss": 3.9595, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898444210191157e-05, "loss": 3.9637, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890058262680636e-05, "loss": 3.9612, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881672315170116e-05, "loss": 3.9646, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873286367659596e-05, "loss": 3.9702, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864916798952806e-05, "loss": 3.945, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856530851442285e-05, "loss": 3.9567, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848144903931765e-05, "loss": 3.9618, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839758956421245e-05, "loss": 3.9447, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831373008910725e-05, "loss": 3.9652, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822987061400205e-05, "loss": 3.9597, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681460111388969e-05, "loss": 3.9623, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806215166379165e-05, "loss": 3.9621, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679784559767238e-05, "loss": 3.9386, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678945965016186e-05, "loss": 3.9526, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678107370265134e-05, "loss": 3.95, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772687755140814e-05, "loss": 3.9573, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676431818643403e-05, "loss": 3.948, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675593223892351e-05, "loss": 3.9478, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674754629141298e-05, "loss": 3.9526, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673916034390246e-05, "loss": 3.9485, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730807153999415e-05, "loss": 3.9359, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722421206488895e-05, "loss": 3.9448, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6714035258978375e-05, "loss": 3.9502, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705649311467855e-05, "loss": 3.9569, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697263363957335e-05, "loss": 3.9457, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688877416446815e-05, "loss": 3.9271, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668049146893629e-05, "loss": 3.9401, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667210552142577e-05, "loss": 3.9477, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663735952718984e-05, "loss": 3.945, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665535000520846e-05, "loss": 3.9413, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664696405769794e-05, "loss": 3.9372, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663857811018742e-05, "loss": 3.9262, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663020854148063e-05, "loss": 3.9466, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662182259397011e-05, "loss": 3.9217, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661343664645959e-05, "loss": 3.9349, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660506707775281e-05, "loss": 3.9328, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659668113024229e-05, "loss": 3.9447, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658829518273176e-05, "loss": 3.9283, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657990923522124e-05, "loss": 3.9403, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657152328771072e-05, "loss": 3.9289, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.65631373402002e-05, "loss": 3.9298, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655476777149341e-05, "loss": 3.9339, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654638182398289e-05, "loss": 3.9242, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653799587647237e-05, "loss": 3.9428, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652960992896185e-05, "loss": 3.9407, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521240360255066e-05, "loss": 3.9353, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.6512854412744546e-05, "loss": 3.9286, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.6504468465234026e-05, "loss": 3.9327, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.6496082517723506e-05, "loss": 3.9375, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.6487696570212986e-05, "loss": 3.9172, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479310622702466e-05, "loss": 3.9391, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470924675191946e-05, "loss": 3.9274, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462538727681426e-05, "loss": 3.9341, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454169158974635e-05, "loss": 3.9219, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445783211464115e-05, "loss": 3.9249, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437397263953595e-05, "loss": 3.9144, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429011316443075e-05, "loss": 3.9218, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642064174773629e-05, "loss": 3.917, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641225580022577e-05, "loss": 3.9322, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640386985271525e-05, "loss": 3.9367, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639548390520473e-05, "loss": 3.925, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638711433649794e-05, "loss": 3.9161, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637872838898742e-05, "loss": 3.9263, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.63703424414769e-05, "loss": 3.9276, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636195649396638e-05, "loss": 3.9333, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635358692525959e-05, "loss": 3.9284, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634520097774907e-05, "loss": 3.9196, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633681503023855e-05, "loss": 3.9243, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632842908272803e-05, "loss": 3.9288, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320059514021244e-05, "loss": 3.9154, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311673566510724e-05, "loss": 3.9234, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303287619000204e-05, "loss": 3.919, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294901671489684e-05, "loss": 3.9117, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286532102782893e-05, "loss": 3.9328, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278146155272373e-05, "loss": 3.9178, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626976020776185e-05, "loss": 3.9105, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626137426025133e-05, "loss": 3.9151, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625298831274081e-05, "loss": 3.9103, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.95322847366333, "eval_runtime": 303.7283, "eval_samples_per_second": 1256.357, "eval_steps_per_second": 39.262, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624460236523029e-05, "loss": 3.9054, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.62362327965235e-05, "loss": 3.9114, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622784684901298e-05, "loss": 3.9266, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621946090150246e-05, "loss": 3.9126, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621107495399194e-05, "loss": 3.9305, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620268900648142e-05, "loss": 3.8985, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619431943777464e-05, "loss": 3.9179, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618593349026412e-05, "loss": 3.8962, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617754754275359e-05, "loss": 3.9141, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616916159524307e-05, "loss": 3.9144, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616077564773255e-05, "loss": 3.9099, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615240607902577e-05, "loss": 3.916, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144036510318976e-05, "loss": 3.8998, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135650562808456e-05, "loss": 3.8987, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127264615297936e-05, "loss": 3.8957, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118878667787416e-05, "loss": 3.9033, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110492720276896e-05, "loss": 3.9088, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102106772766376e-05, "loss": 3.9014, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093720825255856e-05, "loss": 3.9067, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085334877745336e-05, "loss": 3.9216, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076948930234816e-05, "loss": 3.9017, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068579361528025e-05, "loss": 3.9003, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6060193414017505e-05, "loss": 3.9018, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051807466506985e-05, "loss": 3.9071, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043421518996465e-05, "loss": 3.8924, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035035571485945e-05, "loss": 3.9004, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026649623975425e-05, "loss": 3.9027, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018280055268634e-05, "loss": 3.8931, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009894107758114e-05, "loss": 3.8871, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.60015081602476e-05, "loss": 3.8874, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599312221273708e-05, "loss": 3.898, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598473626522656e-05, "loss": 3.896, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597635031771604e-05, "loss": 3.9106, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596796437020552e-05, "loss": 3.897, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959578422695e-05, "loss": 3.8844, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595120885398821e-05, "loss": 3.8996, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594282290647769e-05, "loss": 3.8894, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593443695896717e-05, "loss": 3.8815, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592605101145665e-05, "loss": 3.8838, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591766506394613e-05, "loss": 3.8875, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.59092791164356e-05, "loss": 3.8818, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590089316892508e-05, "loss": 3.9024, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589250722141457e-05, "loss": 3.8856, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884137652707785e-05, "loss": 3.8921, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875768084000994e-05, "loss": 3.8914, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867382136490474e-05, "loss": 3.8831, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858996188979954e-05, "loss": 3.8891, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585061024146943e-05, "loss": 3.874, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584224067276264e-05, "loss": 3.8638, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583385472525212e-05, "loss": 3.8982, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.58254687777416e-05, "loss": 3.8849, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5817082830231076e-05, "loss": 3.8793, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808696882720556e-05, "loss": 3.8754, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580032731401377e-05, "loss": 3.8822, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579194136650325e-05, "loss": 3.8689, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578355541899273e-05, "loss": 3.8843, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577516947148221e-05, "loss": 3.8787, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576678352397169e-05, "loss": 3.8767, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575839757646117e-05, "loss": 3.8896, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575002800775438e-05, "loss": 3.8681, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574164206024386e-05, "loss": 3.8653, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573325611273334e-05, "loss": 3.883, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572487016522282e-05, "loss": 3.8599, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.57164842177123e-05, "loss": 3.8616, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570811464900551e-05, "loss": 3.882, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569972870149499e-05, "loss": 3.884, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691342753984476e-05, "loss": 3.8626, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682956806473956e-05, "loss": 3.8749, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674570858963436e-05, "loss": 3.8542, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666201290256645e-05, "loss": 3.8797, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657815342746125e-05, "loss": 3.8726, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649429395235605e-05, "loss": 3.8803, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5641043447725085e-05, "loss": 3.8732, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632657500214565e-05, "loss": 3.8789, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624287931507774e-05, "loss": 3.8852, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.5615901983997254e-05, "loss": 3.8585, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.5607516036486734e-05, "loss": 3.8744, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599130088976214e-05, "loss": 3.8767, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590744141465694e-05, "loss": 3.8569, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558237457275891e-05, "loss": 3.8831, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557398862524839e-05, "loss": 3.8772, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556560267773787e-05, "loss": 3.8745, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555721673022735e-05, "loss": 3.8833, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554883078271683e-05, "loss": 3.8601, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554044483520631e-05, "loss": 3.8632, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553207526649952e-05, "loss": 3.8685, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523689318989e-05, "loss": 3.8752, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551530337147848e-05, "loss": 3.8673, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550691742396796e-05, "loss": 3.867, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549854785526117e-05, "loss": 3.866, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549016190775065e-05, "loss": 3.8736, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548177596024013e-05, "loss": 3.8548, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547339001272961e-05, "loss": 3.8621, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546500406521909e-05, "loss": 3.8689, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.54566344965123e-05, "loss": 3.8777, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544824854900178e-05, "loss": 3.8654, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543986260149126e-05, "loss": 3.8482, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431476653980736e-05, "loss": 3.8594, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5423090706470216e-05, "loss": 3.8641, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541472113776343e-05, "loss": 3.866, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540633519025291e-05, "loss": 3.8644, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397949242742385e-05, "loss": 3.858, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389563295231865e-05, "loss": 3.8482, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381177347721345e-05, "loss": 3.864, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537280777901456e-05, "loss": 3.8467, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536442183150404e-05, "loss": 3.8544, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535603588399352e-05, "loss": 3.8523, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347649936483e-05, "loss": 3.8645, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533928036777621e-05, "loss": 3.8513, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533089442026569e-05, "loss": 3.8661, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532250847275517e-05, "loss": 3.8467, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531412252524465e-05, "loss": 3.855, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530573657773413e-05, "loss": 3.8546, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529736700902734e-05, "loss": 3.8521, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528898106151682e-05, "loss": 3.8603, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.52805951140063e-05, "loss": 3.8667, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272209166495786e-05, "loss": 3.858, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5263823218985266e-05, "loss": 3.8513, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255453650278475e-05, "loss": 3.8567, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247067702767955e-05, "loss": 3.8585, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238681755257435e-05, "loss": 3.8418, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230295807746915e-05, "loss": 3.8618, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221926239040124e-05, "loss": 3.8479, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213540291529604e-05, "loss": 3.8615, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.5205154344019084e-05, "loss": 3.8478, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.5196768396508564e-05, "loss": 3.8513, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188382448998044e-05, "loss": 3.8381, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518001288029125e-05, "loss": 3.8516, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517162693278074e-05, "loss": 3.8441, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516324098527022e-05, "loss": 3.8538, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.51548550377597e-05, "loss": 3.8587, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514648546905291e-05, "loss": 3.8549, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513809952154239e-05, "loss": 3.8394, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512971357403187e-05, "loss": 3.8538, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512132762652135e-05, "loss": 3.8557, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511295805781456e-05, "loss": 3.8567, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510457211030404e-05, "loss": 3.8539, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509618616279352e-05, "loss": 3.8475, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087800215283e-05, "loss": 3.8477, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079430646576206e-05, "loss": 3.8575, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507104469906569e-05, "loss": 3.8419, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506265875155517e-05, "loss": 3.8521, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505427280404465e-05, "loss": 3.8436, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504590323533786e-05, "loss": 3.8445, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503751728782734e-05, "loss": 3.8585, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502913134031682e-05, "loss": 3.8467, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.50207453928063e-05, "loss": 3.8373, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501235944529578e-05, "loss": 3.8383, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500398987658899e-05, "loss": 3.842, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9117209911346436, "eval_runtime": 303.9879, "eval_samples_per_second": 1255.284, "eval_steps_per_second": 39.229, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499560392907847e-05, "loss": 3.8267, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498721798156795e-05, "loss": 3.8412, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497883203405743e-05, "loss": 3.8508, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497044608654691e-05, "loss": 3.8429, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496206013903639e-05, "loss": 3.8574, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495367419152587e-05, "loss": 3.8348, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494528824401535e-05, "loss": 3.8422, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493690229650483e-05, "loss": 3.8305, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.4928532727798047e-05, "loss": 3.8405, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492014678028752e-05, "loss": 3.8437, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.4911760832777e-05, "loss": 3.8411, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490337488526648e-05, "loss": 3.8468, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4895021695363425e-05, "loss": 3.8275, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886635747852905e-05, "loss": 3.8304, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878249800342385e-05, "loss": 3.8278, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869863852831864e-05, "loss": 3.8316, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861477905321344e-05, "loss": 3.8412, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853091957810824e-05, "loss": 3.8331, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844706010300304e-05, "loss": 3.8376, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836320062789784e-05, "loss": 3.8552, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827950494082993e-05, "loss": 3.8351, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481956454657247e-05, "loss": 3.8312, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481117859906195e-05, "loss": 3.8318, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480279265155143e-05, "loss": 3.839, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479442308284464e-05, "loss": 3.8248, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478603713533412e-05, "loss": 3.8333, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.47776511878236e-05, "loss": 3.8327, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476926524031308e-05, "loss": 3.8299, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.47608956716063e-05, "loss": 3.8197, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475250972409578e-05, "loss": 3.8243, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474412377658526e-05, "loss": 3.828, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473573782907474e-05, "loss": 3.8319, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472736826036795e-05, "loss": 3.8429, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471898231285743e-05, "loss": 3.829, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471059636534691e-05, "loss": 3.8176, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470221041783639e-05, "loss": 3.8329, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469382447032587e-05, "loss": 3.83, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685454901619076e-05, "loss": 3.8121, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4677068954108556e-05, "loss": 3.8152, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668683006598036e-05, "loss": 3.8238, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.4660297059087516e-05, "loss": 3.8154, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4651911111577e-05, "loss": 3.8376, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464354154287021e-05, "loss": 3.8208, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463515559535969e-05, "loss": 3.8245, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462676964784917e-05, "loss": 3.8253, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461838370033865e-05, "loss": 3.8233, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.461001413163186e-05, "loss": 3.8223, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460162818412134e-05, "loss": 3.8104, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459324223661082e-05, "loss": 3.7966, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.45848562891003e-05, "loss": 3.8383, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457648672039351e-05, "loss": 3.8167, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456810077288299e-05, "loss": 3.8191, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455971482537247e-05, "loss": 3.815, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551328877861956e-05, "loss": 3.8126, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542942930351436e-05, "loss": 3.8073, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534573361644645e-05, "loss": 3.8209, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4526187414134125e-05, "loss": 3.8162, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517801466623605e-05, "loss": 3.8139, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.4509415519113085e-05, "loss": 3.8301, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.4501045950406294e-05, "loss": 3.8023, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.4492660002895774e-05, "loss": 3.8011, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4484274055385254e-05, "loss": 3.826, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475888107874734e-05, "loss": 3.7949, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446751853916794e-05, "loss": 3.8003, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445913259165742e-05, "loss": 3.8203, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445074664414691e-05, "loss": 3.8241, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444236069663639e-05, "loss": 3.8023, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.44339911279296e-05, "loss": 3.8134, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442560518041908e-05, "loss": 3.7948, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441721923290856e-05, "loss": 3.8161, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440883328539804e-05, "loss": 3.8099, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440046371669125e-05, "loss": 3.816, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439207776918073e-05, "loss": 3.8118, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438369182167021e-05, "loss": 3.8183, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437530587415969e-05, "loss": 3.8248, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.43669363054529e-05, "loss": 3.8016, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435855035794238e-05, "loss": 3.8105, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4350164410431864e-05, "loss": 3.8177, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341778462921344e-05, "loss": 3.797, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433340889421455e-05, "loss": 3.8197, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432502294670403e-05, "loss": 3.8198, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431663699919351e-05, "loss": 3.8146, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430825105168299e-05, "loss": 3.8221, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.42998814829762e-05, "loss": 3.8007, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429149553546568e-05, "loss": 3.8008, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.428310958795516e-05, "loss": 3.8083, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427472364044464e-05, "loss": 3.8176, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426635407173785e-05, "loss": 3.8093, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425796812422733e-05, "loss": 3.8046, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424958217671682e-05, "loss": 3.8053, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.42411962292063e-05, "loss": 3.8134, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.4232826660499506e-05, "loss": 3.7996, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.4224440712988986e-05, "loss": 3.8004, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.4216054765478466e-05, "loss": 3.8079, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.4207668817967946e-05, "loss": 3.8194, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.4199299249261155e-05, "loss": 3.8082, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.4190913301750635e-05, "loss": 3.793, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.4182527354240115e-05, "loss": 3.7984, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4174141406729595e-05, "loss": 3.8039, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165771838022804e-05, "loss": 3.8096, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157385890512284e-05, "loss": 3.804, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414899994300177e-05, "loss": 3.803, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140613995491244e-05, "loss": 3.79, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413224442678446e-05, "loss": 3.7998, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.412385847927394e-05, "loss": 3.792, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411547253176342e-05, "loss": 3.8001, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410708658425289e-05, "loss": 3.787, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409871701554611e-05, "loss": 3.8151, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409033106803559e-05, "loss": 3.7943, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408194512052507e-05, "loss": 3.8023, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407355917301454e-05, "loss": 3.7928, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406517322550402e-05, "loss": 3.796, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405680365679724e-05, "loss": 3.798, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404841770928672e-05, "loss": 3.7981, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.40400317617762e-05, "loss": 3.8008, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403164581426568e-05, "loss": 3.8077, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.4023276245558894e-05, "loss": 3.7981, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401489029804837e-05, "loss": 3.7988, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400650435053785e-05, "loss": 3.7988, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399811840302733e-05, "loss": 3.8054, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398974883432054e-05, "loss": 3.7804, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.3981362886810016e-05, "loss": 3.8064, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.3972976939299496e-05, "loss": 3.7899, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.3964590991788976e-05, "loss": 3.8049, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395622142308219e-05, "loss": 3.791, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394783547557167e-05, "loss": 3.7979, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393944952806115e-05, "loss": 3.7849, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393106358055063e-05, "loss": 3.793, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392269401184384e-05, "loss": 3.7935, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391430806433332e-05, "loss": 3.7955, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.39059221168228e-05, "loss": 3.7982, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389753616931228e-05, "loss": 3.8039, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388916660060549e-05, "loss": 3.783, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388078065309497e-05, "loss": 3.7981, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387239470558445e-05, "loss": 3.8029, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386400875807393e-05, "loss": 3.8009, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.3855639189367145e-05, "loss": 3.7967, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3847253241856625e-05, "loss": 3.7975, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.3838867294346105e-05, "loss": 3.79, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.3830481346835585e-05, "loss": 3.8036, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.3822111778128794e-05, "loss": 3.7848, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.3813725830618274e-05, "loss": 3.7985, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.3805339883107754e-05, "loss": 3.7877, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.3796953935597234e-05, "loss": 3.7893, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378858436689044e-05, "loss": 3.8027, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378019841937992e-05, "loss": 3.7943, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.37718124718694e-05, "loss": 3.7863, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376342652435888e-05, "loss": 3.7792, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.37550569556521e-05, "loss": 3.7902, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.8860065937042236, "eval_runtime": 304.0811, "eval_samples_per_second": 1254.899, "eval_steps_per_second": 39.217, "step": 381600 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.6448654467708928e+17, "trial_name": null, "trial_params": null }