{ "best_metric": 3.9105277061462402, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/2/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "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": 10.9471, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8172, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1814, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9731, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8113, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7151, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6002, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5309, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4452, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3986, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3468, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.307, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2562, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2055, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1703, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1294, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1003, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0789, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0494, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0175, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0052, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9664, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9506, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9281, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9143, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8875, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8709, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8495, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8307, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.816, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7991, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7944, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.774, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7677, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7598, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7426, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7332, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7062, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7024, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.685, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6831, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6724, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6626, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6418, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6537, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6383, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6311, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6236, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5919, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5914, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5969, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.588, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5718, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5519, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.554, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5415, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5676, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5254, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5373, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5336, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5079, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5149, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5022, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4862, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4863, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5059, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4815, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4729, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4626, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4641, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.477, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940482703000532e-05, "loss": 4.472, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4601, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4654, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4665, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4515, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4397, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4309, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4306, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4249, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4169, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4216, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4222, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4155, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3922, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.3917, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4001, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4025, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3837, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3862, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3901, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.374, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3705, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3739, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3656, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3711, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3617, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3454, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3561, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3562, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3493, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.91533468775121e-05, "loss": 4.3489, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914496093000158e-05, "loss": 4.3447, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913657498249106e-05, "loss": 4.3402, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3379, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911981946627375e-05, "loss": 4.3167, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111449897566966e-05, "loss": 4.3204, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9103063950056446e-05, "loss": 4.3271, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.9094678002545926e-05, "loss": 4.3227, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086292055035406e-05, "loss": 4.3137, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.9077906107524886e-05, "loss": 4.3092, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.9069536538818095e-05, "loss": 4.3071, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061150591307575e-05, "loss": 4.3122, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052764643797055e-05, "loss": 4.3043, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.9044378696286535e-05, "loss": 4.3065, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.9035992748776015e-05, "loss": 4.3003, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027606801265495e-05, "loss": 4.3057, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.3024, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2976, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900246533753767e-05, "loss": 4.3005, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899409576883088e-05, "loss": 4.2983, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898570982132036e-05, "loss": 4.2868, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897732387380984e-05, "loss": 4.2924, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.896893792629932e-05, "loss": 4.2803, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.89605519787888e-05, "loss": 4.2891, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.895216603127827e-05, "loss": 4.2666, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.894378008376775e-05, "loss": 4.2785, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893539413625723e-05, "loss": 4.2635, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892704094635418e-05, "loss": 4.2698, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891865499884366e-05, "loss": 4.2545, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891026905133314e-05, "loss": 4.284, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901883103822624e-05, "loss": 4.2708, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934971563121e-05, "loss": 4.258, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888511120880158e-05, "loss": 4.2591, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887672526129106e-05, "loss": 4.2625, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886833931378054e-05, "loss": 4.2661, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.8859969745073747e-05, "loss": 4.2652, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885160017636696e-05, "loss": 4.251, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884321422885644e-05, "loss": 4.2577, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883482828134592e-05, "loss": 4.2461, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.8826442333835395e-05, "loss": 4.2575, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8818056386324875e-05, "loss": 4.2427, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880967043881436e-05, "loss": 4.2434, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880128449130384e-05, "loss": 4.2415, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879291492259705e-05, "loss": 4.232, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878452897508653e-05, "loss": 4.2377, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877614302757601e-05, "loss": 4.2376, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876775708006549e-05, "loss": 4.2349, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875937113255497e-05, "loss": 4.2362, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875100156384818e-05, "loss": 4.2276, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.193670272827148, "eval_runtime": 303.4498, "eval_samples_per_second": 1257.51, "eval_steps_per_second": 39.298, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874261561633766e-05, "loss": 4.2126, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873422966882714e-05, "loss": 4.209, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872584372131662e-05, "loss": 4.2295, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871747415260983e-05, "loss": 4.2115, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709088205099316e-05, "loss": 4.2307, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700702257588796e-05, "loss": 4.2, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692316310078276e-05, "loss": 4.2087, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683930362567756e-05, "loss": 4.1919, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675560793860965e-05, "loss": 4.2089, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667174846350445e-05, "loss": 4.2003, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658788898839925e-05, "loss": 4.2064, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650402951329405e-05, "loss": 4.203, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642033382622614e-05, "loss": 4.19, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633647435112094e-05, "loss": 4.1892, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625261487601574e-05, "loss": 4.1858, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616875540091054e-05, "loss": 4.1791, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608489592580534e-05, "loss": 4.1878, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.8600103645070014e-05, "loss": 4.1845, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591717697559493e-05, "loss": 4.179, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858334812885271e-05, "loss": 4.1972, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857496218134219e-05, "loss": 4.1731, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856657623383167e-05, "loss": 4.1834, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855819028632115e-05, "loss": 4.1781, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854980433881063e-05, "loss": 4.1866, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854143477010384e-05, "loss": 4.163, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853304882259332e-05, "loss": 4.1714, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.85246628750828e-05, "loss": 4.163, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851627692757228e-05, "loss": 4.1692, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850790735886549e-05, "loss": 4.1524, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849952141135497e-05, "loss": 4.1573, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849113546384445e-05, "loss": 4.1657, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.8482749516333934e-05, "loss": 4.1601, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847436356882341e-05, "loss": 4.1596, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846599400011662e-05, "loss": 4.1638, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.84576080526061e-05, "loss": 4.159, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844922210509558e-05, "loss": 4.1575, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.8440836157585056e-05, "loss": 4.145, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432450210074536e-05, "loss": 4.1527, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842408064136775e-05, "loss": 4.138, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415694693857225e-05, "loss": 4.1467, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.8407308746346705e-05, "loss": 4.1476, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398922798836185e-05, "loss": 4.1447, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.83905532301294e-05, "loss": 4.1338, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838216728261888e-05, "loss": 4.1425, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837378133510836e-05, "loss": 4.1475, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836539538759784e-05, "loss": 4.1403, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8357025818891057e-05, "loss": 4.1417, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834863987138053e-05, "loss": 4.113, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834025392387001e-05, "loss": 4.121, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833186797635949e-05, "loss": 4.138, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.83234984076527e-05, "loss": 4.1294, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831511246014218e-05, "loss": 4.1243, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830672651263166e-05, "loss": 4.1094, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829834056512114e-05, "loss": 4.1135, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289970996414354e-05, "loss": 4.1066, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281585048903834e-05, "loss": 4.1316, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273199101393314e-05, "loss": 4.1078, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264813153882794e-05, "loss": 4.119, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256443585176003e-05, "loss": 4.1214, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248057637665483e-05, "loss": 4.1034, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823967169015496e-05, "loss": 4.1098, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823128574264444e-05, "loss": 4.1011, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822289979513392e-05, "loss": 4.0973, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821453022642713e-05, "loss": 4.098, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820614427891661e-05, "loss": 4.1141, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819775833140609e-05, "loss": 4.1041, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818937238389558e-05, "loss": 4.094, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8181019193992524e-05, "loss": 4.0922, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172633246482004e-05, "loss": 4.0914, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816424729897148e-05, "loss": 4.1089, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815586135146096e-05, "loss": 4.1106, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814747540395044e-05, "loss": 4.1028, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813908945643992e-05, "loss": 4.1123, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81307035089294e-05, "loss": 4.1091, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812231756141888e-05, "loss": 4.1061, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113947992712086e-05, "loss": 4.0954, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105562045201566e-05, "loss": 4.0924, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097176097691046e-05, "loss": 4.0914, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808879015018053e-05, "loss": 4.0896, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808042058147374e-05, "loss": 4.0852, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807203463396322e-05, "loss": 4.0928, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.80636486864527e-05, "loss": 4.0994, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805526273894218e-05, "loss": 4.0884, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804689317023539e-05, "loss": 4.0756, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803850722272487e-05, "loss": 4.0743, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803012127521435e-05, "loss": 4.0816, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802175170650756e-05, "loss": 4.0913, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801336575899704e-05, "loss": 4.0769, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800497981148652e-05, "loss": 4.077, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996593863976e-05, "loss": 4.0834, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988207916465486e-05, "loss": 4.0737, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979821968954966e-05, "loss": 4.0719, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971436021444446e-05, "loss": 4.0733, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963050073933926e-05, "loss": 4.0756, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954680505227135e-05, "loss": 4.077, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946294557716615e-05, "loss": 4.0763, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.7937908610206095e-05, "loss": 4.0604, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.7929522662695575e-05, "loss": 4.0734, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.7921153093988784e-05, "loss": 4.0684, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.7912767146478264e-05, "loss": 4.0771, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.7904381198967744e-05, "loss": 4.0689, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895995251457224e-05, "loss": 4.0686, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788762568275043e-05, "loss": 4.0664, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787923973523992e-05, "loss": 4.0696, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708537877294e-05, "loss": 4.0469, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786246784021888e-05, "loss": 4.0523, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785409827151209e-05, "loss": 4.0611, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784571232400157e-05, "loss": 4.0573, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783732637649105e-05, "loss": 4.0517, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782894042898053e-05, "loss": 4.0499, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782055448147001e-05, "loss": 4.0495, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781216853395948e-05, "loss": 4.0547, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780378258644896e-05, "loss": 4.0499, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779541301774218e-05, "loss": 4.0521, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778702707023166e-05, "loss": 4.0511, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777864112272114e-05, "loss": 4.0573, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777025517521062e-05, "loss": 4.0546, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761885606503834e-05, "loss": 4.0487, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775349965899331e-05, "loss": 4.0574, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774513009028652e-05, "loss": 4.0564, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736744142776e-05, "loss": 4.0412, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772835819526548e-05, "loss": 4.0521, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719972247754956e-05, "loss": 4.0408, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711586300244436e-05, "loss": 4.0533, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703200352733916e-05, "loss": 4.0278, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694814405223396e-05, "loss": 4.0462, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686428457712876e-05, "loss": 4.0303, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767805888900609e-05, "loss": 4.0347, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766967294149557e-05, "loss": 4.0245, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766128699398505e-05, "loss": 4.0552, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765290104647453e-05, "loss": 4.0443, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.7644547856571476e-05, "loss": 4.0357, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636161909060956e-05, "loss": 4.031, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762777596155043e-05, "loss": 4.0399, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761939001403991e-05, "loss": 4.0441, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761100406652939e-05, "loss": 4.0413, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760261811901887e-05, "loss": 4.0345, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759423217150835e-05, "loss": 4.0368, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758584622399783e-05, "loss": 4.0313, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577476655291045e-05, "loss": 4.0453, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569090707780525e-05, "loss": 4.0263, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560704760270005e-05, "loss": 4.0304, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552318812759485e-05, "loss": 4.0278, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543949244052694e-05, "loss": 4.0224, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.75355796753459e-05, "loss": 4.0309, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752719372783538e-05, "loss": 4.0258, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751880778032486e-05, "loss": 4.0306, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751042183281434e-05, "loss": 4.0269, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750205226410755e-05, "loss": 4.0221, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.025816917419434, "eval_runtime": 303.3157, "eval_samples_per_second": 1258.065, "eval_steps_per_second": 39.315, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749366631659703e-05, "loss": 4.0104, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748528036908652e-05, "loss": 4.008, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476894421576e-05, "loss": 4.0255, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746850847406548e-05, "loss": 4.012, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746012252655496e-05, "loss": 4.0361, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745173657904444e-05, "loss": 4.0032, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744335063153392e-05, "loss": 4.0142, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.74349646840234e-05, "loss": 3.9996, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742657873651288e-05, "loss": 4.0168, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741819278900236e-05, "loss": 4.0104, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740980684149184e-05, "loss": 4.0148, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740143727278505e-05, "loss": 4.0112, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7393084082881986e-05, "loss": 4.0006, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738469813537147e-05, "loss": 4.0058, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737631218786095e-05, "loss": 4.0009, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736792624035043e-05, "loss": 3.9962, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735954029283991e-05, "loss": 3.9989, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735115434532939e-05, "loss": 4.0031, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734276839781887e-05, "loss": 3.9956, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733438245030835e-05, "loss": 4.0186, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732601288160156e-05, "loss": 3.9946, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731762693409104e-05, "loss": 4.0023, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730924098658052e-05, "loss": 3.9999, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730085503907e-05, "loss": 4.0071, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729246909155948e-05, "loss": 3.9882, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728409952285269e-05, "loss": 3.9995, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727571357534217e-05, "loss": 3.9898, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726732762783165e-05, "loss": 3.9936, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725894168032114e-05, "loss": 3.9816, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725055573281062e-05, "loss": 3.9846, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724216978530009e-05, "loss": 3.9933, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233800216593306e-05, "loss": 3.9943, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225414269082786e-05, "loss": 3.9929, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7217028321572266e-05, "loss": 3.9954, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720864237406174e-05, "loss": 3.9893, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720025642655122e-05, "loss": 3.993, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191886857844435e-05, "loss": 3.98, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718350091033391e-05, "loss": 3.9924, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717511496282339e-05, "loss": 3.9728, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166729015312875e-05, "loss": 3.9838, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715835944660609e-05, "loss": 3.9814, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149973499095564e-05, "loss": 3.9867, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141587551585044e-05, "loss": 3.981, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133201604074524e-05, "loss": 3.9785, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124815656564004e-05, "loss": 3.988, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711644608785721e-05, "loss": 3.985, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710806014034669e-05, "loss": 3.9824, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709967419283617e-05, "loss": 3.9655, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709128824532565e-05, "loss": 3.9633, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708290229781513e-05, "loss": 3.9786, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707451635030461e-05, "loss": 3.9756, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706614678159783e-05, "loss": 3.9727, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705776083408731e-05, "loss": 3.956, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704937488657679e-05, "loss": 3.9609, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704098893906627e-05, "loss": 3.9608, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703260299155575e-05, "loss": 3.9742, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702421704404523e-05, "loss": 3.9586, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701583109653471e-05, "loss": 3.9708, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700744514902419e-05, "loss": 3.9689, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990755803174e-05, "loss": 3.9576, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990706011610606e-05, "loss": 3.9633, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982320064100086e-05, "loss": 3.9571, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973934116589566e-05, "loss": 3.9494, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965548169079046e-05, "loss": 3.9584, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695717860037226e-05, "loss": 3.9627, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694879265286174e-05, "loss": 3.9677, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694040670535122e-05, "loss": 3.9445, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.69320207578407e-05, "loss": 3.9506, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692363481033018e-05, "loss": 3.9477, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691524886281966e-05, "loss": 3.9745, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690686291530914e-05, "loss": 3.9606, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689849334660235e-05, "loss": 3.9622, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689010739909183e-05, "loss": 3.9749, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688172145158131e-05, "loss": 3.9698, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687333550407079e-05, "loss": 3.9667, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686494955656027e-05, "loss": 3.9577, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685656360904975e-05, "loss": 3.9588, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684817766153923e-05, "loss": 3.9553, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683979171402871e-05, "loss": 3.9529, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831438524125655e-05, "loss": 3.9519, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6823052576615135e-05, "loss": 3.9563, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814666629104615e-05, "loss": 3.9651, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806280681594095e-05, "loss": 3.9529, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679789473408357e-05, "loss": 3.9457, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789525165376784e-05, "loss": 3.939, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781139217866264e-05, "loss": 3.9517, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772753270355744e-05, "loss": 3.9571, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676436732284522e-05, "loss": 3.9479, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755981375334704e-05, "loss": 3.9445, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747595427824184e-05, "loss": 3.9572, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739209480313664e-05, "loss": 3.9357, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673083991160687e-05, "loss": 3.9472, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672245396409635e-05, "loss": 3.9445, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671406801658583e-05, "loss": 3.9524, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670568206907531e-05, "loss": 3.9501, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669731250036852e-05, "loss": 3.9455, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688926552858e-05, "loss": 3.9346, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668054060534748e-05, "loss": 3.9475, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667215465783696e-05, "loss": 3.9398, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666376871032644e-05, "loss": 3.9546, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665539914161966e-05, "loss": 3.9432, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664701319410914e-05, "loss": 3.9447, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663862724659862e-05, "loss": 3.9369, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66302412990881e-05, "loss": 3.9507, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662187173038131e-05, "loss": 3.9221, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661348578287079e-05, "loss": 3.9308, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660509983536027e-05, "loss": 3.938, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659671388784975e-05, "loss": 3.9372, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658832794033923e-05, "loss": 3.9259, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579958371632436e-05, "loss": 3.9309, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571572424121916e-05, "loss": 3.9257, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563186476611396e-05, "loss": 3.935, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554800529100876e-05, "loss": 3.9288, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654643096039409e-05, "loss": 3.9275, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653804501288357e-05, "loss": 3.9368, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652965906537305e-05, "loss": 3.9393, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652127311786253e-05, "loss": 3.9387, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651290354915574e-05, "loss": 3.9294, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650451760164522e-05, "loss": 3.9401, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.64961316541347e-05, "loss": 3.9332, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648774570662418e-05, "loss": 3.9254, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647937613791739e-05, "loss": 3.9401, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647099019040687e-05, "loss": 3.9206, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646260424289635e-05, "loss": 3.9384, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645421829538583e-05, "loss": 3.9168, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445848726679045e-05, "loss": 3.9318, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437462779168525e-05, "loss": 3.9145, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429076831658005e-05, "loss": 3.9194, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420690884147485e-05, "loss": 3.9148, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412321315440694e-05, "loss": 3.9392, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403935367930174e-05, "loss": 3.9302, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395549420419654e-05, "loss": 3.9266, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387163472909134e-05, "loss": 3.9201, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637879390420234e-05, "loss": 3.9247, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637040795669182e-05, "loss": 3.9369, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.63620220091813e-05, "loss": 3.9258, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635363606167078e-05, "loss": 3.9232, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345266492964e-05, "loss": 3.9316, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633688054545348e-05, "loss": 3.9227, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632849459794296e-05, "loss": 3.9296, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632010865043244e-05, "loss": 3.917, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631173908172565e-05, "loss": 3.9222, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630335313421513e-05, "loss": 3.9178, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629496718670461e-05, "loss": 3.9182, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628658123919409e-05, "loss": 3.9178, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.62782116704873e-05, "loss": 3.9237, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626982572297678e-05, "loss": 3.9168, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626143977546626e-05, "loss": 3.9198, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6253053827955737e-05, "loss": 3.917, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9517478942871094, "eval_runtime": 317.1615, "eval_samples_per_second": 1203.144, "eval_steps_per_second": 37.599, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244667880445217e-05, "loss": 3.9094, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623629831173843e-05, "loss": 3.9033, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622791236422791e-05, "loss": 3.9194, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621952641671739e-05, "loss": 3.9056, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621114046920687e-05, "loss": 3.9333, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620277090050008e-05, "loss": 3.899, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619438495298956e-05, "loss": 3.9128, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618599900547904e-05, "loss": 3.8954, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617761305796852e-05, "loss": 3.9121, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6169227110458e-05, "loss": 3.9105, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616085754175121e-05, "loss": 3.9065, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615247159424069e-05, "loss": 3.9097, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144102025533906e-05, "loss": 3.897, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135716078023386e-05, "loss": 3.9065, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127330130512866e-05, "loss": 3.8984, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118944183002346e-05, "loss": 3.8973, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110558235491826e-05, "loss": 3.8978, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.61021722879813e-05, "loss": 3.9016, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609378634047078e-05, "loss": 3.8979, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608540039296026e-05, "loss": 3.9134, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6077030824253475e-05, "loss": 3.897, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606864487674295e-05, "loss": 3.9022, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606025892923243e-05, "loss": 3.9007, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605187298172191e-05, "loss": 3.9105, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043503413015124e-05, "loss": 3.8895, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035117465504604e-05, "loss": 3.9047, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026731517994084e-05, "loss": 3.892, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018345570483564e-05, "loss": 3.8969, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600997600177677e-05, "loss": 3.882, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600159005426625e-05, "loss": 3.8938, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599320410675573e-05, "loss": 3.8946, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598481815924521e-05, "loss": 3.899, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597644859053842e-05, "loss": 3.8971, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.59680626430279e-05, "loss": 3.9012, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595967669551738e-05, "loss": 3.8906, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595129074800686e-05, "loss": 3.8989, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594292117930008e-05, "loss": 3.8885, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593453523178956e-05, "loss": 3.8972, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592614928427904e-05, "loss": 3.8797, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591776333676852e-05, "loss": 3.891, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909393768061727e-05, "loss": 3.8904, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5901007820551206e-05, "loss": 3.8963, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892621873040686e-05, "loss": 3.8877, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884235925530166e-05, "loss": 3.888, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875866356823375e-05, "loss": 3.8949, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867480409312855e-05, "loss": 3.8921, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5859094461802335e-05, "loss": 3.8911, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850708514291815e-05, "loss": 3.8807, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584233894558503e-05, "loss": 3.8652, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583395299807451e-05, "loss": 3.8882, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582556705056399e-05, "loss": 3.8842, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581718110305347e-05, "loss": 3.88, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580881153434668e-05, "loss": 3.874, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580042558683616e-05, "loss": 3.8708, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579203963932564e-05, "loss": 3.8675, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578365369181512e-05, "loss": 3.8844, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577528412310833e-05, "loss": 3.8708, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576689817559781e-05, "loss": 3.8777, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575851222808729e-05, "loss": 3.8851, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575012628057677e-05, "loss": 3.8708, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741756711869985e-05, "loss": 3.8715, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733370764359465e-05, "loss": 3.8756, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724984816848945e-05, "loss": 3.8572, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716598869338425e-05, "loss": 3.8713, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708229300631634e-05, "loss": 3.8795, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699843353121114e-05, "loss": 3.8773, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691457405610594e-05, "loss": 3.8592, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5683071458100074e-05, "loss": 3.8659, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567470188939328e-05, "loss": 3.8622, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566631594188276e-05, "loss": 3.8824, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565792999437224e-05, "loss": 3.8751, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564954404686172e-05, "loss": 3.8773, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564117447815494e-05, "loss": 3.8875, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563278853064442e-05, "loss": 3.886, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.56244025831339e-05, "loss": 3.8868, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561601663562338e-05, "loss": 3.8662, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560764706691659e-05, "loss": 3.8762, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559926111940607e-05, "loss": 3.8741, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559087517189555e-05, "loss": 3.8681, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558248922438503e-05, "loss": 3.8727, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.5574119655678236e-05, "loss": 3.8703, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.5565733708167716e-05, "loss": 3.8788, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557347760657196e-05, "loss": 3.8718, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548961813146676e-05, "loss": 3.8557, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554059224443989e-05, "loss": 3.8592, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553220629692937e-05, "loss": 3.8697, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552382034941885e-05, "loss": 3.8725, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551543440190833e-05, "loss": 3.8639, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550704845439781e-05, "loss": 3.8609, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549867888569102e-05, "loss": 3.8727, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.54902929381805e-05, "loss": 3.8577, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548190699066998e-05, "loss": 3.8614, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547352104315946e-05, "loss": 3.866, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546515147445267e-05, "loss": 3.8717, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545676552694215e-05, "loss": 3.8715, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544837957943163e-05, "loss": 3.8628, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543999363192111e-05, "loss": 3.8499, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431624063214326e-05, "loss": 3.87, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5423238115703806e-05, "loss": 3.8563, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414852168193286e-05, "loss": 3.8767, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406466220682766e-05, "loss": 3.8661, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5398096651975975e-05, "loss": 3.865, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389710704465455e-05, "loss": 3.8568, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381324756954935e-05, "loss": 3.8704, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372938809444415e-05, "loss": 3.8449, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364569240737624e-05, "loss": 3.8539, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5356183293227104e-05, "loss": 3.8533, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347797345716584e-05, "loss": 3.8592, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.53394277770098e-05, "loss": 3.8466, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533104182949928e-05, "loss": 3.8549, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532265588198876e-05, "loss": 3.8519, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531426993447824e-05, "loss": 3.8506, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530590036577145e-05, "loss": 3.8554, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529751441826093e-05, "loss": 3.848, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528912847075041e-05, "loss": 3.8629, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528074252323989e-05, "loss": 3.8611, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.52723729545331e-05, "loss": 3.8609, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526398700702258e-05, "loss": 3.8542, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525560105951206e-05, "loss": 3.8619, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524721511200154e-05, "loss": 3.8614, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523884554329475e-05, "loss": 3.8475, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523045959578423e-05, "loss": 3.8613, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522207364827371e-05, "loss": 3.847, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521368770076319e-05, "loss": 3.8609, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.52053181320564e-05, "loss": 3.8441, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519693218454588e-05, "loss": 3.8547, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518854623703536e-05, "loss": 3.8376, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518016028952484e-05, "loss": 3.8445, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517179072081805e-05, "loss": 3.8419, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516340477330753e-05, "loss": 3.8597, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515501882579701e-05, "loss": 3.8531, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514663287828649e-05, "loss": 3.8566, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513826330957971e-05, "loss": 3.8464, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512987736206919e-05, "loss": 3.8524, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512149141455867e-05, "loss": 3.862, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511310546704815e-05, "loss": 3.8517, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104735898341356e-05, "loss": 3.8503, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096349950830836e-05, "loss": 3.8581, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087964003320316e-05, "loss": 3.8488, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079578055809796e-05, "loss": 3.8587, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5071208487103005e-05, "loss": 3.8409, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062822539592485e-05, "loss": 3.8531, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054436592081965e-05, "loss": 3.8455, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5046050644571445e-05, "loss": 3.8428, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503768107586466e-05, "loss": 3.8487, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502929512835414e-05, "loss": 3.8463, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502090918084362e-05, "loss": 3.8466, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012523233333094e-05, "loss": 3.8443, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500415366462631e-05, "loss": 3.8491, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9105277061462402, "eval_runtime": 316.9798, "eval_samples_per_second": 1203.834, "eval_steps_per_second": 37.621, "step": 305280 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.1231007110383616e+17, "trial_name": null, "trial_params": null }