{ "best_metric": 3.8442249298095703, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/2/checkpoints/checkpoint-992160", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 2518560, "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 }, { "epoch": 0.0, "learning_rate": 4.499576771711579e-05, "loss": 3.8344, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498738176960527e-05, "loss": 3.832, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497899582209474e-05, "loss": 3.8473, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497060987458422e-05, "loss": 3.8368, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.49622239270737e-05, "loss": 3.8602, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495383797956318e-05, "loss": 3.8354, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494545203205266e-05, "loss": 3.8371, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493706608454214e-05, "loss": 3.824, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492869651583536e-05, "loss": 3.8407, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492031056832484e-05, "loss": 3.8445, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491192462081432e-05, "loss": 3.8347, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.49035386733038e-05, "loss": 3.8368, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489518548340074e-05, "loss": 3.8299, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886799535890216e-05, "loss": 3.8344, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878413588379696e-05, "loss": 3.8323, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4870027640869176e-05, "loss": 3.8266, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861641693358656e-05, "loss": 3.8295, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853255745848136e-05, "loss": 3.836, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844869798337616e-05, "loss": 3.8281, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836483850827096e-05, "loss": 3.8422, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482811428212031e-05, "loss": 3.8319, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481972833460979e-05, "loss": 3.8365, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481134238709927e-05, "loss": 3.831, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480295643958875e-05, "loss": 3.8409, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479458687088196e-05, "loss": 3.8211, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478620092337144e-05, "loss": 3.8342, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477781497586092e-05, "loss": 3.8284, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.47694290283504e-05, "loss": 3.8247, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476105945964361e-05, "loss": 3.8168, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475267351213309e-05, "loss": 3.8242, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474428756462257e-05, "loss": 3.8332, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473590161711205e-05, "loss": 3.8315, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.4727532048405266e-05, "loss": 3.8328, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.4719146100894746e-05, "loss": 3.8325, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710760153384226e-05, "loss": 3.8232, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4702374205873705e-05, "loss": 3.8316, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4694004637166915e-05, "loss": 3.8263, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685618689656395e-05, "loss": 3.8289, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4677232742145874e-05, "loss": 3.8159, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668846794635354e-05, "loss": 3.8254, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.4660477225928564e-05, "loss": 3.8238, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4652091278418043e-05, "loss": 3.831, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.4643705330907523e-05, "loss": 3.8245, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4635319383397003e-05, "loss": 3.8231, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462694981469022e-05, "loss": 3.834, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.46185638671797e-05, "loss": 3.8246, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.461017791966918e-05, "loss": 3.8248, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460179197215866e-05, "loss": 3.8158, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.45934387822556e-05, "loss": 3.801, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458505283474508e-05, "loss": 3.826, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457666688723456e-05, "loss": 3.8209, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456828093972404e-05, "loss": 3.8183, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455989499221352e-05, "loss": 3.8042, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551525423506726e-05, "loss": 3.8101, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4543139475996206e-05, "loss": 3.7992, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453475352848569e-05, "loss": 3.8209, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452636758097517e-05, "loss": 3.809, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451798163346465e-05, "loss": 3.812, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450959568595413e-05, "loss": 3.8241, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450120973844361e-05, "loss": 3.8075, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449284016973682e-05, "loss": 3.8116, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.44844542222263e-05, "loss": 3.8155, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447606827471578e-05, "loss": 3.7964, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446768232720526e-05, "loss": 3.8103, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445929637969474e-05, "loss": 3.8135, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445091043218422e-05, "loss": 3.8168, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.4442524484673695e-05, "loss": 3.7988, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443415491596691e-05, "loss": 3.8048, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442576896845639e-05, "loss": 3.7983, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441738302094588e-05, "loss": 3.8225, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440899707343535e-05, "loss": 3.8147, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440061112592483e-05, "loss": 3.8117, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439222517841431e-05, "loss": 3.8279, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438383923090379e-05, "loss": 3.8198, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437545328339327e-05, "loss": 3.833, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436708371468648e-05, "loss": 3.807, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435869776717596e-05, "loss": 3.8125, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435031181966544e-05, "loss": 3.814, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434192587215492e-05, "loss": 3.8043, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433355630344813e-05, "loss": 3.8145, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4325170355937615e-05, "loss": 3.8091, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316784408427095e-05, "loss": 3.8183, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4308398460916575e-05, "loss": 3.809, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4300028892209784e-05, "loss": 3.7983, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291642944699264e-05, "loss": 3.807, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283256997188744e-05, "loss": 3.8015, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427488742848195e-05, "loss": 3.8146, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426650148097143e-05, "loss": 3.8088, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425811553346091e-05, "loss": 3.8003, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424972958595039e-05, "loss": 3.8135, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424134363843987e-05, "loss": 3.8041, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423295769092935e-05, "loss": 3.7963, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422457174341883e-05, "loss": 3.8053, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421618579590831e-05, "loss": 3.8145, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420781622720153e-05, "loss": 3.8136, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419943027969101e-05, "loss": 3.8075, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419104433218049e-05, "loss": 3.7901, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418265838466997e-05, "loss": 3.8095, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417427243715945e-05, "loss": 3.7998, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416588648964893e-05, "loss": 3.8144, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415750054213841e-05, "loss": 3.811, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414911459462788e-05, "loss": 3.8064, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.41407450259211e-05, "loss": 3.7983, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413235907841058e-05, "loss": 3.8163, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.412397313090006e-05, "loss": 3.7818, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411558718338953e-05, "loss": 3.7993, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4107217614682747e-05, "loss": 3.794, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409883166717223e-05, "loss": 3.8062, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409044571966171e-05, "loss": 3.7865, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4082059772151186e-05, "loss": 3.795, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.40736902034444e-05, "loss": 3.7961, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406530425593388e-05, "loss": 3.7934, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056918308423355e-05, "loss": 3.7966, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404854873971657e-05, "loss": 3.7955, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.404016279220605e-05, "loss": 3.8043, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403177684469553e-05, "loss": 3.8052, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.4023390897185004e-05, "loss": 3.8034, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401502132847822e-05, "loss": 3.796, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.40066353809677e-05, "loss": 3.8067, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399824943345719e-05, "loss": 3.8007, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398986348594666e-05, "loss": 3.7919, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.3981493917239876e-05, "loss": 3.8061, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.3973107969729356e-05, "loss": 3.7887, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396472202221883e-05, "loss": 3.8023, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395633607470831e-05, "loss": 3.789, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.3947966506001525e-05, "loss": 3.8003, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.3939580558491005e-05, "loss": 3.7867, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393119461098048e-05, "loss": 3.7876, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392280866346996e-05, "loss": 3.7902, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3914439094763174e-05, "loss": 3.8029, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3906053147252654e-05, "loss": 3.7965, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389768357854587e-05, "loss": 3.8001, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388929763103535e-05, "loss": 3.7894, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388091168352483e-05, "loss": 3.8008, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.38725257360143e-05, "loss": 3.8067, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386413978850378e-05, "loss": 3.7978, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385575384099326e-05, "loss": 3.7949, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384736789348274e-05, "loss": 3.8019, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383898194597222e-05, "loss": 3.7946, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383061237726543e-05, "loss": 3.8024, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382222642975491e-05, "loss": 3.7881, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381384048224439e-05, "loss": 3.7974, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380545453473388e-05, "loss": 3.7903, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379708496602709e-05, "loss": 3.7916, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378869901851657e-05, "loss": 3.7939, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378031307100605e-05, "loss": 3.7922, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377192712349553e-05, "loss": 3.7945, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763557554788736e-05, "loss": 3.7843, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.3755171607278216e-05, "loss": 3.7965, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.886021614074707, "eval_runtime": 346.7835, "eval_samples_per_second": 1100.372, "eval_steps_per_second": 34.387, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.3746785659767696e-05, "loss": 3.7855, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.3738399712257176e-05, "loss": 3.7774, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.3730030143550385e-05, "loss": 3.7944, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721644196039865e-05, "loss": 3.7849, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.3713258248529345e-05, "loss": 3.8034, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370487230101883e-05, "loss": 3.7858, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369650273231204e-05, "loss": 3.7781, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368811678480152e-05, "loss": 3.7783, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.3679730837291e-05, "loss": 3.783, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367134488978048e-05, "loss": 3.7903, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366297532107369e-05, "loss": 3.7828, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365458937356317e-05, "loss": 3.7847, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364621980485638e-05, "loss": 3.7782, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363783385734586e-05, "loss": 3.7791, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362944790983534e-05, "loss": 3.7835, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362106196232482e-05, "loss": 3.7724, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.36126760148143e-05, "loss": 3.776, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.3604290067303786e-05, "loss": 3.7818, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.3595904119793266e-05, "loss": 3.7787, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.3587518172282746e-05, "loss": 3.7886, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.3579164982379684e-05, "loss": 3.7839, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.3570779034869164e-05, "loss": 3.784, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.3562393087358644e-05, "loss": 3.7829, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.3554007139848124e-05, "loss": 3.785, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.3545621192337604e-05, "loss": 3.7687, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.3537235244827084e-05, "loss": 3.7884, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.3528849297316564e-05, "loss": 3.7718, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.3520463349806044e-05, "loss": 3.7744, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351209378109925e-05, "loss": 3.7686, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350370783358874e-05, "loss": 3.7741, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349532188607822e-05, "loss": 3.7821, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348695231737143e-05, "loss": 3.7776, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347856636986091e-05, "loss": 3.7856, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.347018042235039e-05, "loss": 3.785, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346179447483987e-05, "loss": 3.7716, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345342490613308e-05, "loss": 3.7804, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344503895862256e-05, "loss": 3.7774, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343665301111204e-05, "loss": 3.7766, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342826706360152e-05, "loss": 3.7693, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419897494894726e-05, "loss": 3.7732, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411511547384206e-05, "loss": 3.7785, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340314197867742e-05, "loss": 3.7839, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.33947560311669e-05, "loss": 3.7726, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338637008365638e-05, "loss": 3.7746, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337798413614586e-05, "loss": 3.7812, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336959818863534e-05, "loss": 3.7767, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336121224112482e-05, "loss": 3.7767, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.33528262936143e-05, "loss": 3.7687, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334445672490751e-05, "loss": 3.7472, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333607077739699e-05, "loss": 3.7818, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332768482988647e-05, "loss": 3.7724, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331929888237595e-05, "loss": 3.772, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331092931366916e-05, "loss": 3.7611, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330254336615864e-05, "loss": 3.7555, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329415741864813e-05, "loss": 3.7525, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328577147113761e-05, "loss": 3.7685, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.3277385523627087e-05, "loss": 3.7621, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326899957611656e-05, "loss": 3.7666, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326061362860604e-05, "loss": 3.7727, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.3252244059899256e-05, "loss": 3.7593, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.3243874491192465e-05, "loss": 3.7638, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.3235488543681945e-05, "loss": 3.7693, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.3227102596171425e-05, "loss": 3.7488, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.3218716648660905e-05, "loss": 3.7595, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321033070115038e-05, "loss": 3.7659, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.3201944753639864e-05, "loss": 3.7683, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.3193558806129344e-05, "loss": 3.7482, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318518923742256e-05, "loss": 3.7571, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.3176803289912033e-05, "loss": 3.7502, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.3168417342401513e-05, "loss": 3.7717, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.3160031394890993e-05, "loss": 3.7684, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315164544738047e-05, "loss": 3.7646, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314325949986995e-05, "loss": 3.778, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313487355235943e-05, "loss": 3.7736, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312648760484891e-05, "loss": 3.7852, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311811803614212e-05, "loss": 3.7623, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.31097320886316e-05, "loss": 3.7667, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310134614112108e-05, "loss": 3.7642, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309296019361056e-05, "loss": 3.7553, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308459062490378e-05, "loss": 3.7717, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307620467739326e-05, "loss": 3.7612, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306781872988274e-05, "loss": 3.7715, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305943278237222e-05, "loss": 3.7644, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305106321366543e-05, "loss": 3.7529, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.304267726615491e-05, "loss": 3.7595, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.303429131864439e-05, "loss": 3.7541, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025921749937596e-05, "loss": 3.7702, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3017535802427076e-05, "loss": 3.7645, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3009149854916556e-05, "loss": 3.7477, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000763907406036e-05, "loss": 3.7703, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2992377959895516e-05, "loss": 3.758, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.2983992012385e-05, "loss": 3.7508, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297560606487448e-05, "loss": 3.7572, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296722011736396e-05, "loss": 3.7685, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295885054865717e-05, "loss": 3.7622, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.295046460114665e-05, "loss": 3.7658, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294207865363613e-05, "loss": 3.7466, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293369270612561e-05, "loss": 3.7622, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292530675861509e-05, "loss": 3.7539, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.2916920811104565e-05, "loss": 3.7677, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.2908534863594045e-05, "loss": 3.7665, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.2900148916083525e-05, "loss": 3.7563, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289177934737674e-05, "loss": 3.759, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288339339986622e-05, "loss": 3.7651, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.2875023831159436e-05, "loss": 3.74, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.2866637883648916e-05, "loss": 3.7525, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.2858251936138396e-05, "loss": 3.7477, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284986598862787e-05, "loss": 3.7586, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.2841496419921085e-05, "loss": 3.7456, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.2833110472410565e-05, "loss": 3.7537, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282472452490004e-05, "loss": 3.7493, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.281633857738952e-05, "loss": 3.75, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807952629879e-05, "loss": 3.754, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.279956668236848e-05, "loss": 3.7495, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279118073485796e-05, "loss": 3.7614, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.2782811166151174e-05, "loss": 3.7585, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.2774425218640654e-05, "loss": 3.7607, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.2766039271130134e-05, "loss": 3.7514, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.2757653323619614e-05, "loss": 3.7619, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274928375491282e-05, "loss": 3.7611, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.27408978074023e-05, "loss": 3.7451, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273251185989178e-05, "loss": 3.7644, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272412591238126e-05, "loss": 3.7426, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271573996487074e-05, "loss": 3.7599, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270735401736022e-05, "loss": 3.7424, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.26989680698497e-05, "loss": 3.7592, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269058212233918e-05, "loss": 3.7403, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268221255363239e-05, "loss": 3.7463, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267382660612187e-05, "loss": 3.7418, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266544065861136e-05, "loss": 3.7631, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265705471110084e-05, "loss": 3.7495, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264868514239405e-05, "loss": 3.7589, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.264029919488353e-05, "loss": 3.7444, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263191324737301e-05, "loss": 3.757, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.262352729986249e-05, "loss": 3.7604, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261514135235197e-05, "loss": 3.7555, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260675540484145e-05, "loss": 3.7532, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259836945733093e-05, "loss": 3.7527, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.2589999888624136e-05, "loss": 3.7535, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.2581613941113616e-05, "loss": 3.7605, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.2573227993603096e-05, "loss": 3.7458, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.2564842046092576e-05, "loss": 3.7545, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.2556456098582056e-05, "loss": 3.7464, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2548070151071536e-05, "loss": 3.7515, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539684203561016e-05, "loss": 3.7503, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253131463485423e-05, "loss": 3.7436, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.2522928687343705e-05, "loss": 3.7605, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2514542739833185e-05, "loss": 3.7368, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.2506156792322665e-05, "loss": 3.7573, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.870176315307617, "eval_runtime": 348.6512, "eval_samples_per_second": 1094.478, "eval_steps_per_second": 34.203, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.2497770844812145e-05, "loss": 3.742, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.2489384897301625e-05, "loss": 3.7315, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.2480998949791105e-05, "loss": 3.7492, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.2472613002280585e-05, "loss": 3.7459, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.2464243433573794e-05, "loss": 3.7579, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245585748606328e-05, "loss": 3.7441, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244747153855276e-05, "loss": 3.7374, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243908559104224e-05, "loss": 3.735, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243069964353172e-05, "loss": 3.7424, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242233007482493e-05, "loss": 3.7498, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241394412731441e-05, "loss": 3.741, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240555817980389e-05, "loss": 3.7412, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239717223229337e-05, "loss": 3.7435, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238878628478285e-05, "loss": 3.7356, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.238040033727233e-05, "loss": 3.7394, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237201438976181e-05, "loss": 3.7283, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236362844225129e-05, "loss": 3.7369, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.23552588735445e-05, "loss": 3.7392, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234687292603398e-05, "loss": 3.7387, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233848697852346e-05, "loss": 3.7459, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2330117409816674e-05, "loss": 3.7486, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321731462306154e-05, "loss": 3.7385, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313345514795634e-05, "loss": 3.7401, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304959567285114e-05, "loss": 3.7463, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229657361977459e-05, "loss": 3.7245, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.22882040510678e-05, "loss": 3.7519, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227981810355728e-05, "loss": 3.7312, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.227143215604676e-05, "loss": 3.7316, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.2263046208536236e-05, "loss": 3.7279, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254660261025716e-05, "loss": 3.7351, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246274313515196e-05, "loss": 3.7385, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223788836600468e-05, "loss": 3.7401, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222950241849416e-05, "loss": 3.7436, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222113284978737e-05, "loss": 3.7437, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221274690227685e-05, "loss": 3.7307, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220437733357006e-05, "loss": 3.7421, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219599138605954e-05, "loss": 3.7411, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218760543854902e-05, "loss": 3.7324, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.21792194910385e-05, "loss": 3.7293, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217083354352798e-05, "loss": 3.7343, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216244759601746e-05, "loss": 3.7345, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215407802731067e-05, "loss": 3.742, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214569207980015e-05, "loss": 3.7315, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137306132289637e-05, "loss": 3.7342, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128920184779116e-05, "loss": 3.7443, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120534237268596e-05, "loss": 3.734, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.2112148289758076e-05, "loss": 3.7393, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.2103778721051285e-05, "loss": 3.729, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.2095392773540765e-05, "loss": 3.7025, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.2087006826030245e-05, "loss": 3.7452, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.2078620878519725e-05, "loss": 3.7304, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.2070234931009205e-05, "loss": 3.7345, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061865362302414e-05, "loss": 3.7219, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.2053479414791894e-05, "loss": 3.7123, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2045093467281374e-05, "loss": 3.7179, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036707519770854e-05, "loss": 3.726, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.2028321572260334e-05, "loss": 3.7248, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201993562474982e-05, "loss": 3.7235, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.20115496772393e-05, "loss": 3.7361, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200318010853251e-05, "loss": 3.7185, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.199481053982572e-05, "loss": 3.7201, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.19864245923152e-05, "loss": 3.7351, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197803864480468e-05, "loss": 3.7078, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.196965269729416e-05, "loss": 3.7228, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.196126674978364e-05, "loss": 3.7255, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195288080227312e-05, "loss": 3.734, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.19444948547626e-05, "loss": 3.7074, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193610890725207e-05, "loss": 3.7222, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192773933854529e-05, "loss": 3.7102, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919353391034775e-05, "loss": 3.7334, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191096744352425e-05, "loss": 3.7337, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190258149601373e-05, "loss": 3.7268, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189419554850321e-05, "loss": 3.7337, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188580960099269e-05, "loss": 3.735, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187742365348217e-05, "loss": 3.749, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186905408477538e-05, "loss": 3.7232, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186066813726486e-05, "loss": 3.7288, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185228218975434e-05, "loss": 3.7283, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.1843896242243817e-05, "loss": 3.7161, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.1835526673537026e-05, "loss": 3.7289, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182715710483024e-05, "loss": 3.7265, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181877115731972e-05, "loss": 3.7307, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.18103852098092e-05, "loss": 3.7323, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180199926229868e-05, "loss": 3.7155, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179361331478816e-05, "loss": 3.715, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178522736727764e-05, "loss": 3.7179, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177685779857085e-05, "loss": 3.7332, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.176847185106033e-05, "loss": 3.7238, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.176008590354981e-05, "loss": 3.7172, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175169995603929e-05, "loss": 3.7203, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174331400852877e-05, "loss": 3.7287, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7137, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172654211350773e-05, "loss": 3.718, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.1718172544800946e-05, "loss": 3.7357, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709786597290426e-05, "loss": 3.7247, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.726, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1693014702269386e-05, "loss": 3.7099, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684628754758866e-05, "loss": 3.7251, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.1676242807248346e-05, "loss": 3.7163, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.1667856859737826e-05, "loss": 3.7289, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659470912227306e-05, "loss": 3.7284, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.1651101343520515e-05, "loss": 3.7237, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642715396009995e-05, "loss": 3.7224, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1634329448499475e-05, "loss": 3.7257, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625959879792684e-05, "loss": 3.7047, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1617573932282164e-05, "loss": 3.7174, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.1609187984771644e-05, "loss": 3.7061, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160080203726113e-05, "loss": 3.7251, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159241608975061e-05, "loss": 3.7101, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.1584030142240084e-05, "loss": 3.715, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.15756605735333e-05, "loss": 3.7102, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156727462602278e-05, "loss": 3.7157, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155888867851226e-05, "loss": 3.7174, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.155050273100173e-05, "loss": 3.7116, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154211678349121e-05, "loss": 3.7212, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153374721478443e-05, "loss": 3.7283, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152536126727391e-05, "loss": 3.7191, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151697531976338e-05, "loss": 3.7217, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150858937225287e-05, "loss": 3.7205, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.1500219803546084e-05, "loss": 3.7233, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149183385603556e-05, "loss": 3.7131, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148344790852504e-05, "loss": 3.7227, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147506196101452e-05, "loss": 3.7078, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.1466676013504e-05, "loss": 3.7231, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145829006599348e-05, "loss": 3.7094, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144990411848296e-05, "loss": 3.7155, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144151817097244e-05, "loss": 3.7097, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1433148602265646e-05, "loss": 3.7084, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424762654755126e-05, "loss": 3.7053, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1416393086048335e-05, "loss": 3.7222, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140800713853782e-05, "loss": 3.7159, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.13996211910273e-05, "loss": 3.7241, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139123524351678e-05, "loss": 3.7068, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138286567480999e-05, "loss": 3.7245, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137447972729947e-05, "loss": 3.7226, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136609377978895e-05, "loss": 3.7185, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.135770783227843e-05, "loss": 3.7191, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134932188476791e-05, "loss": 3.7163, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.134093593725739e-05, "loss": 3.7182, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133254998974687e-05, "loss": 3.7274, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132416404223635e-05, "loss": 3.7084, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131579447352956e-05, "loss": 3.7164, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.130740852601904e-05, "loss": 3.7169, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.129902257850852e-05, "loss": 3.7153, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290636630998006e-05, "loss": 3.7082, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282250683487486e-05, "loss": 3.7072, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273864735976966e-05, "loss": 3.7235, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265478788466446e-05, "loss": 3.7042, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125709284095592e-05, "loss": 3.7219, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.860013723373413, "eval_runtime": 310.7249, "eval_samples_per_second": 1228.067, "eval_steps_per_second": 38.378, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248723272249135e-05, "loss": 3.7073, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.1240337324738615e-05, "loss": 3.6964, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.1231951377228095e-05, "loss": 3.7173, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122356542971757e-05, "loss": 3.7067, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.1215212239814513e-05, "loss": 3.7212, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120682629230399e-05, "loss": 3.7124, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119844034479347e-05, "loss": 3.7047, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119005439728296e-05, "loss": 3.7014, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118168482857617e-05, "loss": 3.7075, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117329888106565e-05, "loss": 3.7131, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116491293355513e-05, "loss": 3.7044, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115652698604461e-05, "loss": 3.7066, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114815741733782e-05, "loss": 3.7045, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.11397714698273e-05, "loss": 3.7023, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113138552231678e-05, "loss": 3.7047, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112299957480626e-05, "loss": 3.6956, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.111461362729574e-05, "loss": 3.6999, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110622767978521e-05, "loss": 3.7058, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.10978417322747e-05, "loss": 3.7047, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108947216356791e-05, "loss": 3.7083, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.1081086216057394e-05, "loss": 3.7141, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.107270026854687e-05, "loss": 3.7058, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106431432103635e-05, "loss": 3.7038, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105592837352583e-05, "loss": 3.7071, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104755880481904e-05, "loss": 3.6962, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.1039172857308516e-05, "loss": 3.7147, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.1030786909797996e-05, "loss": 3.6963, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.1022400962287476e-05, "loss": 3.7021, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.1014015014776956e-05, "loss": 3.6965, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005645446070165e-05, "loss": 3.699, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0997259498559645e-05, "loss": 3.7003, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.098887355104913e-05, "loss": 3.7078, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.098048760353861e-05, "loss": 3.7074, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.097210165602809e-05, "loss": 3.7098, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.096371570851757e-05, "loss": 3.6956, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.095534613981078e-05, "loss": 3.7111, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.094696019230026e-05, "loss": 3.7073, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.093857424478974e-05, "loss": 3.696, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.093018829727922e-05, "loss": 3.6998, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.092181872857243e-05, "loss": 3.7002, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.091343278106191e-05, "loss": 3.6984, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.090504683355139e-05, "loss": 3.7073, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.089666088604087e-05, "loss": 3.7013, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088827493853035e-05, "loss": 3.7007, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087988899101983e-05, "loss": 3.7095, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.0871503043509316e-05, "loss": 3.7009, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.0863117095998796e-05, "loss": 3.7035, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.0854747527292005e-05, "loss": 3.6992, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.0846377958585214e-05, "loss": 3.6671, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.0837992011074694e-05, "loss": 3.7128, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.0829606063564174e-05, "loss": 3.6957, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.0821220116053654e-05, "loss": 3.7044, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081285054734686e-05, "loss": 3.6849, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080446459983634e-05, "loss": 3.6828, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079607865232582e-05, "loss": 3.6809, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.07876927048153e-05, "loss": 3.6926, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077930675730478e-05, "loss": 3.6953, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077092080979427e-05, "loss": 3.6876, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076253486228375e-05, "loss": 3.7068, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075414891477323e-05, "loss": 3.6884, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074579572487017e-05, "loss": 3.691, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.073740977735965e-05, "loss": 3.6999, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.072902382984913e-05, "loss": 3.6755, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.072063788233861e-05, "loss": 3.6852, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071225193482809e-05, "loss": 3.6941, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070386598731757e-05, "loss": 3.7006, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069548003980705e-05, "loss": 3.6752, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068709409229652e-05, "loss": 3.6884, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.0678724523589736e-05, "loss": 3.678, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.067033857607922e-05, "loss": 3.7017, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.06619526285687e-05, "loss": 3.6958, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.0653566681058176e-05, "loss": 3.6959, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.0645180733547656e-05, "loss": 3.6998, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.0636794786037136e-05, "loss": 3.7037, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.0628408838526616e-05, "loss": 3.7159, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.0620039269819825e-05, "loss": 3.692, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.0611653322309305e-05, "loss": 3.6961, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0603267374798785e-05, "loss": 3.6977, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.0594881427288265e-05, "loss": 3.6832, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586511858581474e-05, "loss": 3.6935, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.057812591107096e-05, "loss": 3.6957, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.056973996356044e-05, "loss": 3.6999, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056135401604992e-05, "loss": 3.6989, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.05529680685394e-05, "loss": 3.6854, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.054458212102888e-05, "loss": 3.6822, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053619617351836e-05, "loss": 3.6864, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052782660481157e-05, "loss": 3.7018, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.051944065730105e-05, "loss": 3.6917, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051105470979053e-05, "loss": 3.685, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050266876228001e-05, "loss": 3.6877, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049428281476949e-05, "loss": 3.6968, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048589686725897e-05, "loss": 3.6843, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047751091974845e-05, "loss": 3.6874, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046912497223793e-05, "loss": 3.7013, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.046075540353114e-05, "loss": 3.6923, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.0452369456020625e-05, "loss": 3.694, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.0443983508510105e-05, "loss": 3.6819, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.0435597560999585e-05, "loss": 3.6902, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.0427211613489065e-05, "loss": 3.6856, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041882566597854e-05, "loss": 3.6994, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041043971846802e-05, "loss": 3.6933, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.04020537709575e-05, "loss": 3.6969, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039368420225071e-05, "loss": 3.6913, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038529825474019e-05, "loss": 3.6912, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.03769286860334e-05, "loss": 3.6808, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036854273852288e-05, "loss": 3.6808, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036015679101236e-05, "loss": 3.678, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035177084350184e-05, "loss": 3.6953, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034340127479506e-05, "loss": 3.6797, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033501532728454e-05, "loss": 3.6816, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032662937977401e-05, "loss": 3.6766, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031824343226349e-05, "loss": 3.6887, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030985748475297e-05, "loss": 3.6878, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030147153724245e-05, "loss": 3.6783, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.029308558973193e-05, "loss": 3.6941, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.028471602102514e-05, "loss": 3.6925, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.027633007351462e-05, "loss": 3.6868, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.02679441260041e-05, "loss": 3.6936, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.025955817849358e-05, "loss": 3.6898, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.02511886097868e-05, "loss": 3.6892, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.024280266227628e-05, "loss": 3.6868, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.023441671476576e-05, "loss": 3.6896, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.022603076725524e-05, "loss": 3.6791, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.021764481974472e-05, "loss": 3.6919, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209258872234197e-05, "loss": 3.684, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.0200872924723677e-05, "loss": 3.6844, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.0192486977213157e-05, "loss": 3.6775, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.0184117408506366e-05, "loss": 3.6781, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.0175731460995846e-05, "loss": 3.6767, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.0167345513485326e-05, "loss": 3.6904, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.0158959565974805e-05, "loss": 3.6853, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015060637607175e-05, "loss": 3.6935, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014222042856123e-05, "loss": 3.6745, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013383448105071e-05, "loss": 3.6985, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012544853354019e-05, "loss": 3.6876, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011706258602967e-05, "loss": 3.6885, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010867663851915e-05, "loss": 3.6879, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010030706981236e-05, "loss": 3.6822, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009192112230184e-05, "loss": 3.6864, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008353517479132e-05, "loss": 3.6967, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.00751492272808e-05, "loss": 3.6782, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006677965857401e-05, "loss": 3.6879, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005839371106349e-05, "loss": 3.6889, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.005000776355297e-05, "loss": 3.6817, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.0041621816042455e-05, "loss": 3.6792, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.0033235868531935e-05, "loss": 3.6792, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.0024849921021415e-05, "loss": 3.6918, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.0016463973510895e-05, "loss": 3.6766, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000807802600037e-05, "loss": 3.6917, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.8540804386138916, "eval_runtime": 310.113, "eval_samples_per_second": 1230.49, "eval_steps_per_second": 38.454, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.9999708457293584e-05, "loss": 3.6758, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.9991322509783064e-05, "loss": 3.6711, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.9982936562272544e-05, "loss": 3.6807, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997455061476202e-05, "loss": 3.6801, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996618104605523e-05, "loss": 3.6925, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.995779509854471e-05, "loss": 3.6803, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994940915103419e-05, "loss": 3.6759, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994102320352367e-05, "loss": 3.6732, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993263725601315e-05, "loss": 3.6727, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992426768730637e-05, "loss": 3.6859, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991588173979584e-05, "loss": 3.6745, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990749579228532e-05, "loss": 3.6748, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.98991098447748e-05, "loss": 3.6837, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.989072389726428e-05, "loss": 3.6653, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.988233794975376e-05, "loss": 3.673, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.987395200224324e-05, "loss": 3.6686, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.986556605473272e-05, "loss": 3.6687, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.985719648602593e-05, "loss": 3.6766, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.984881053851541e-05, "loss": 3.6751, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840440969808626e-05, "loss": 3.6745, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9832055022298106e-05, "loss": 3.6884, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823669074787586e-05, "loss": 3.6779, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815283127277066e-05, "loss": 3.6778, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9806897179766546e-05, "loss": 3.6733, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.9798511232256026e-05, "loss": 3.6712, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.9790141663549235e-05, "loss": 3.6835, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.9781755716038715e-05, "loss": 3.6678, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.9773369768528195e-05, "loss": 3.6763, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.9764983821017675e-05, "loss": 3.6624, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.9756597873507155e-05, "loss": 3.6722, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.9748211925996635e-05, "loss": 3.6687, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.9739825978486115e-05, "loss": 3.6769, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.9731456409779324e-05, "loss": 3.6815, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972307046226881e-05, "loss": 3.681, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971468451475829e-05, "loss": 3.6705, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970629856724777e-05, "loss": 3.6739, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.969792899854098e-05, "loss": 3.6819, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.968954305103046e-05, "loss": 3.6687, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968115710351994e-05, "loss": 3.6696, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967277115600942e-05, "loss": 3.6696, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.96643852084989e-05, "loss": 3.6744, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965601563979211e-05, "loss": 3.672, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964762969228159e-05, "loss": 3.6778, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963924374477107e-05, "loss": 3.6727, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.963085779726055e-05, "loss": 3.6789, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962247184975003e-05, "loss": 3.6771, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.9614102281043244e-05, "loss": 3.674, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.9605716333532724e-05, "loss": 3.6718, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.9597330386022204e-05, "loss": 3.637, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958894443851168e-05, "loss": 3.6824, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958055849100116e-05, "loss": 3.6645, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957217254349064e-05, "loss": 3.6767, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956380297478385e-05, "loss": 3.6616, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.9555417027273326e-05, "loss": 3.6553, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.9547031079762806e-05, "loss": 3.6488, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.9538645132252286e-05, "loss": 3.6627, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.9530259184741766e-05, "loss": 3.6682, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9521873237231246e-05, "loss": 3.6615, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.951350366852446e-05, "loss": 3.6747, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950511772101394e-05, "loss": 3.6612, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949673177350342e-05, "loss": 3.6613, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.94883458259929e-05, "loss": 3.671, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.947995987848238e-05, "loss": 3.6486, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.947157393097186e-05, "loss": 3.6566, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946320436226507e-05, "loss": 3.6675, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945481841475455e-05, "loss": 3.6698, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944643246724403e-05, "loss": 3.6509, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943804651973351e-05, "loss": 3.6602, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.942966057222299e-05, "loss": 3.6503, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942127462471247e-05, "loss": 3.6731, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.941288867720195e-05, "loss": 3.6703, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.940451910849517e-05, "loss": 3.6674, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939613316098465e-05, "loss": 3.6717, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.9387747213474127e-05, "loss": 3.6746, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.9379361265963607e-05, "loss": 3.6887, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.9370975318453086e-05, "loss": 3.6656, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.9362589370942566e-05, "loss": 3.6681, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935420342343204e-05, "loss": 3.6637, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934581747592152e-05, "loss": 3.6599, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.9337447907214735e-05, "loss": 3.6644, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.9329061959704215e-05, "loss": 3.6696, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932067601219369e-05, "loss": 3.6692, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931229006468317e-05, "loss": 3.674, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930390411717265e-05, "loss": 3.655, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295518169662135e-05, "loss": 3.6541, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287132222151615e-05, "loss": 3.6586, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.9278762653444824e-05, "loss": 3.6756, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.9270376705934304e-05, "loss": 3.6661, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.9261990758423784e-05, "loss": 3.655, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.9253604810913264e-05, "loss": 3.6609, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.9245218863402744e-05, "loss": 3.6666, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9236832915892224e-05, "loss": 3.6591, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.9228446968381704e-05, "loss": 3.6585, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922007739967491e-05, "loss": 3.6736, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921169145216439e-05, "loss": 3.6671, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920330550465387e-05, "loss": 3.6661, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919491955714335e-05, "loss": 3.6562, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918653360963283e-05, "loss": 3.66, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917814766212232e-05, "loss": 3.66, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916977809341553e-05, "loss": 3.6703, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.916139214590501e-05, "loss": 3.6675, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.915300619839449e-05, "loss": 3.6657, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.914462025088397e-05, "loss": 3.6675, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.913623430337345e-05, "loss": 3.66, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.912786473466666e-05, "loss": 3.6589, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911947878715614e-05, "loss": 3.652, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.911109283964562e-05, "loss": 3.6479, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.91027068921351e-05, "loss": 3.6695, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909432094462458e-05, "loss": 3.656, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.908593499711406e-05, "loss": 3.651, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907756542840727e-05, "loss": 3.6508, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906917948089675e-05, "loss": 3.6538, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.9060793533386226e-05, "loss": 3.6646, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.9052407585875706e-05, "loss": 3.6519, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.9044021638365186e-05, "loss": 3.6644, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.90356520696584e-05, "loss": 3.6659, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9027266122147875e-05, "loss": 3.6622, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.9018880174637355e-05, "loss": 3.6659, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.9010494227126835e-05, "loss": 3.6619, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900212465842005e-05, "loss": 3.6614, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.8993738710909524e-05, "loss": 3.6604, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898535276339901e-05, "loss": 3.6603, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897696681588849e-05, "loss": 3.6563, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.896858086837797e-05, "loss": 3.6634, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.896019492086745e-05, "loss": 3.6583, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.895180897335693e-05, "loss": 3.657, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.894342302584641e-05, "loss": 3.6509, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893505345713962e-05, "loss": 3.6511, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892668388843283e-05, "loss": 3.6503, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891829794092231e-05, "loss": 3.6626, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.890991199341179e-05, "loss": 3.6565, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.890152604590127e-05, "loss": 3.6705, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889315647719448e-05, "loss": 3.6484, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.8884770529683965e-05, "loss": 3.6687, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.8876384582173445e-05, "loss": 3.6619, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.8867998634662925e-05, "loss": 3.6635, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859629065956134e-05, "loss": 3.6623, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8851243118445614e-05, "loss": 3.6557, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.8842857170935094e-05, "loss": 3.6628, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.8834471223424574e-05, "loss": 3.6695, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.8826085275914054e-05, "loss": 3.6511, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881771570720726e-05, "loss": 3.6625, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880932975969674e-05, "loss": 3.6584, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880094381218622e-05, "loss": 3.6543, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.87925578646757e-05, "loss": 3.6572, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878417191716518e-05, "loss": 3.6495, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877578596965466e-05, "loss": 3.6652, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876740002214414e-05, "loss": 3.6529, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875901407463363e-05, "loss": 3.6619, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.849538803100586, "eval_runtime": 307.5313, "eval_samples_per_second": 1240.82, "eval_steps_per_second": 38.777, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875064450592684e-05, "loss": 3.6499, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874225855841632e-05, "loss": 3.6451, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873388898970953e-05, "loss": 3.652, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872550304219901e-05, "loss": 3.6533, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871711709468849e-05, "loss": 3.6674, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870873114717797e-05, "loss": 3.6533, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.8700361578471176e-05, "loss": 3.6515, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.8691975630960656e-05, "loss": 3.6499, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.8683589683450136e-05, "loss": 3.645, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.8675203735939616e-05, "loss": 3.6604, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.8666817788429096e-05, "loss": 3.6478, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865844821972231e-05, "loss": 3.6497, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.865006227221179e-05, "loss": 3.6582, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864167632470127e-05, "loss": 3.6407, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.863329037719075e-05, "loss": 3.646, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.862492080848396e-05, "loss": 3.6418, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861653486097344e-05, "loss": 3.6454, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860814891346292e-05, "loss": 3.6439, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.85997629659524e-05, "loss": 3.6533, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859139339724561e-05, "loss": 3.6512, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858300744973509e-05, "loss": 3.6613, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.857462150222457e-05, "loss": 3.6497, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.856623555471405e-05, "loss": 3.6526, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.8557849607203537e-05, "loss": 3.6447, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.854946365969301e-05, "loss": 3.6493, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.8541094090986226e-05, "loss": 3.6556, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.8532708143475706e-05, "loss": 3.642, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.8524322195965185e-05, "loss": 3.6531, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.851593624845466e-05, "loss": 3.636, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.850755030094414e-05, "loss": 3.6446, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.849916435343362e-05, "loss": 3.6453, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849079478472683e-05, "loss": 3.65, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.848240883721631e-05, "loss": 3.6591, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.847402288970579e-05, "loss": 3.6555, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.8465636942195274e-05, "loss": 3.6463, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.8457250994684754e-05, "loss": 3.6424, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.844888142597796e-05, "loss": 3.659, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.844049547846744e-05, "loss": 3.6447, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843210953095692e-05, "loss": 3.6444, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.84237235834464e-05, "loss": 3.6437, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841535401473961e-05, "loss": 3.6491, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840696806722909e-05, "loss": 3.6477, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839858211971857e-05, "loss": 3.65, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.839019617220805e-05, "loss": 3.65, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.838181022469753e-05, "loss": 3.649, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837342427718701e-05, "loss": 3.653, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836505470848023e-05, "loss": 3.6481, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835666876096971e-05, "loss": 3.6478, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834828281345919e-05, "loss": 3.6143, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.833989686594867e-05, "loss": 3.6543, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.833151091843815e-05, "loss": 3.6397, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832312497092763e-05, "loss": 3.6544, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831475540222084e-05, "loss": 3.6359, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.830636945471032e-05, "loss": 3.6296, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.82979835071998e-05, "loss": 3.6244, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.828959755968928e-05, "loss": 3.6362, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.8281227990982486e-05, "loss": 3.6487, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.8272842043471966e-05, "loss": 3.6308, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.8264456095961446e-05, "loss": 3.6528, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.8256070148450926e-05, "loss": 3.6413, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824770057974414e-05, "loss": 3.6305, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.823931463223362e-05, "loss": 3.6465, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.82309286847231e-05, "loss": 3.6302, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822254273721258e-05, "loss": 3.6293, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821417316850579e-05, "loss": 3.6443, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.820578722099527e-05, "loss": 3.6461, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.819740127348475e-05, "loss": 3.6274, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.818901532597423e-05, "loss": 3.6338, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.818062937846371e-05, "loss": 3.6248, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.817224343095319e-05, "loss": 3.647, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.8163857483442663e-05, "loss": 3.6459, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.815548791473588e-05, "loss": 3.6413, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.814710196722536e-05, "loss": 3.6476, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.8138716019714846e-05, "loss": 3.6502, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.813033007220432e-05, "loss": 3.6645, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.81219441246938e-05, "loss": 3.6424, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.811355817718328e-05, "loss": 3.6449, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810517222967276e-05, "loss": 3.6393, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.809678628216224e-05, "loss": 3.6368, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808841671345545e-05, "loss": 3.6385, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808003076594493e-05, "loss": 3.6462, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807164481843441e-05, "loss": 3.6434, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.806325887092389e-05, "loss": 3.6527, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.805487292341337e-05, "loss": 3.6296, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804648697590285e-05, "loss": 3.63, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.803810102839233e-05, "loss": 3.6367, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.8029731459685544e-05, "loss": 3.6457, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.8021345512175024e-05, "loss": 3.6434, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8012959564664504e-05, "loss": 3.6348, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.8004573617153984e-05, "loss": 3.6362, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.7996187669643464e-05, "loss": 3.6435, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.798781810093667e-05, "loss": 3.6345, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797943215342615e-05, "loss": 3.632, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.797104620591563e-05, "loss": 3.6481, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.796266025840511e-05, "loss": 3.6413, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795427431089459e-05, "loss": 3.645, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.79459047421878e-05, "loss": 3.6309, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793751879467728e-05, "loss": 3.6364, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792913284716677e-05, "loss": 3.6345, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792074689965625e-05, "loss": 3.649, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791236095214573e-05, "loss": 3.6456, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790399138343894e-05, "loss": 3.6384, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789560543592842e-05, "loss": 3.6424, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.78872194884179e-05, "loss": 3.636, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.787883354090738e-05, "loss": 3.64, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.7870463972200586e-05, "loss": 3.6268, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.7862078024690066e-05, "loss": 3.6278, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7853692077179546e-05, "loss": 3.6404, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.7845306129669026e-05, "loss": 3.6367, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.7836936560962235e-05, "loss": 3.6228, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.782855061345172e-05, "loss": 3.6286, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.78201646659412e-05, "loss": 3.6306, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.781177871843068e-05, "loss": 3.6389, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.7803392770920155e-05, "loss": 3.6283, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.7795006823409635e-05, "loss": 3.6427, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778663725470285e-05, "loss": 3.6436, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.7778251307192324e-05, "loss": 3.6391, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.7769865359681804e-05, "loss": 3.6369, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.7761479412171284e-05, "loss": 3.6435, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.77531098434645e-05, "loss": 3.6374, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.774472389595397e-05, "loss": 3.64, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.773633794844346e-05, "loss": 3.636, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.772795200093294e-05, "loss": 3.6295, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771956605342242e-05, "loss": 3.6389, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.77111801059119e-05, "loss": 3.6397, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770279415840138e-05, "loss": 3.6308, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769440821089086e-05, "loss": 3.6317, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768603864218407e-05, "loss": 3.6275, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767766907347728e-05, "loss": 3.6221, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.766928312596676e-05, "loss": 3.6414, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766089717845624e-05, "loss": 3.6316, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765251123094572e-05, "loss": 3.6465, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764414166223893e-05, "loss": 3.6247, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.7635755714728413e-05, "loss": 3.6441, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.762736976721789e-05, "loss": 3.6411, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.761898381970737e-05, "loss": 3.6405, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.761061425100058e-05, "loss": 3.637, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760222830349006e-05, "loss": 3.6294, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759384235597954e-05, "loss": 3.6423, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.758545640846902e-05, "loss": 3.6434, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.75770704609585e-05, "loss": 3.6296, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.756870089225171e-05, "loss": 3.6391, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.756031494474119e-05, "loss": 3.637, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755192899723067e-05, "loss": 3.6323, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.754354304972015e-05, "loss": 3.6319, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.753515710220963e-05, "loss": 3.6278, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.752677115469911e-05, "loss": 3.6411, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.751838520718859e-05, "loss": 3.6339, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.750999925967808e-05, "loss": 3.6396, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.846451759338379, "eval_runtime": 304.7916, "eval_samples_per_second": 1251.974, "eval_steps_per_second": 39.125, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.750162969097129e-05, "loss": 3.6263, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.749324374346077e-05, "loss": 3.6228, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.748485779595025e-05, "loss": 3.629, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.747647184843973e-05, "loss": 3.6308, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.7468102279732936e-05, "loss": 3.6445, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.7459716332222416e-05, "loss": 3.6329, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.7451330384711896e-05, "loss": 3.626, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.7442944437201376e-05, "loss": 3.6276, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.7434558489690856e-05, "loss": 3.6224, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.7426188920984065e-05, "loss": 3.6326, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.7417802973473545e-05, "loss": 3.6271, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.740941702596303e-05, "loss": 3.6318, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.740103107845251e-05, "loss": 3.6352, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.7392645130941985e-05, "loss": 3.6138, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.73842755622352e-05, "loss": 3.6252, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.737588961472468e-05, "loss": 3.6144, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736750366721416e-05, "loss": 3.6283, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.7359117719703634e-05, "loss": 3.6251, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.7350731772193114e-05, "loss": 3.6281, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.734236220348633e-05, "loss": 3.6261, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.733397625597581e-05, "loss": 3.6386, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732559030846528e-05, "loss": 3.6261, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731720436095477e-05, "loss": 3.6317, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.730881841344425e-05, "loss": 3.6258, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.730044884473746e-05, "loss": 3.6269, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729206289722694e-05, "loss": 3.632, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728367694971642e-05, "loss": 3.6162, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.72752910022059e-05, "loss": 3.6284, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726690505469538e-05, "loss": 3.6162, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725851910718486e-05, "loss": 3.6212, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.725013315967434e-05, "loss": 3.6261, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.724174721216382e-05, "loss": 3.6287, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.723337764345703e-05, "loss": 3.6273, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.722499169594651e-05, "loss": 3.639, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.721660574843599e-05, "loss": 3.6205, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720821980092547e-05, "loss": 3.6213, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.719985023221868e-05, "loss": 3.6393, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.719146428470816e-05, "loss": 3.6221, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718307833719764e-05, "loss": 3.6222, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.717469238968712e-05, "loss": 3.6228, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.716632282098033e-05, "loss": 3.621, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.715793687346981e-05, "loss": 3.6258, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.714955092595929e-05, "loss": 3.6257, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.714116497844877e-05, "loss": 3.6303, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.713277903093825e-05, "loss": 3.6243, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.712439308342773e-05, "loss": 3.6328, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711602351472094e-05, "loss": 3.6242, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.710763756721042e-05, "loss": 3.6286, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709925161969991e-05, "loss": 3.5931, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709086567218939e-05, "loss": 3.6316, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.708247972467887e-05, "loss": 3.6142, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.7074110155972076e-05, "loss": 3.6306, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.7065724208461556e-05, "loss": 3.6134, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.7057338260951036e-05, "loss": 3.6096, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.7048952313440516e-05, "loss": 3.6026, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.7040582744733725e-05, "loss": 3.6152, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.7032196797223205e-05, "loss": 3.6269, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.7023810849712685e-05, "loss": 3.6084, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.7015424902202165e-05, "loss": 3.6296, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.7007038954691645e-05, "loss": 3.6215, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.699866938598486e-05, "loss": 3.6061, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.699028343847434e-05, "loss": 3.6242, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.698189749096382e-05, "loss": 3.6073, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6973511543453294e-05, "loss": 3.6093, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.6965125595942774e-05, "loss": 3.6216, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.695675602723599e-05, "loss": 3.6235, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.694837007972547e-05, "loss": 3.6027, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.693998413221494e-05, "loss": 3.6162, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693159818470442e-05, "loss": 3.605, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.69232122371939e-05, "loss": 3.6182, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691482628968338e-05, "loss": 3.6259, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.69064567209766e-05, "loss": 3.6206, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689807077346608e-05, "loss": 3.6286, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.688968482595556e-05, "loss": 3.626, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688129887844504e-05, "loss": 3.6419, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687291293093452e-05, "loss": 3.6225, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686454336222773e-05, "loss": 3.6268, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685615741471721e-05, "loss": 3.6125, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684777146720669e-05, "loss": 3.6144, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.683938551969617e-05, "loss": 3.6176, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.683101595098938e-05, "loss": 3.6219, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.682263000347886e-05, "loss": 3.6248, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.6814244055968337e-05, "loss": 3.6285, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.6805858108457817e-05, "loss": 3.6073, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.6797472160947297e-05, "loss": 3.6106, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.6789086213436776e-05, "loss": 3.6121, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.678071664472999e-05, "loss": 3.6266, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.677233069721947e-05, "loss": 3.6186, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676394474970895e-05, "loss": 3.6144, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675555880219843e-05, "loss": 3.6185, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.674717285468791e-05, "loss": 3.6198, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.673880328598112e-05, "loss": 3.6102, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.67304173384706e-05, "loss": 3.6125, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672203139096008e-05, "loss": 3.6254, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.671364544344956e-05, "loss": 3.625, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670525949593904e-05, "loss": 3.6222, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669688992723225e-05, "loss": 3.6078, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668850397972173e-05, "loss": 3.6142, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.668011803221122e-05, "loss": 3.6146, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.66717320847007e-05, "loss": 3.6205, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666334613719018e-05, "loss": 3.6277, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.6654976568483386e-05, "loss": 3.6144, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.6646590620972866e-05, "loss": 3.6216, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.6638204673462346e-05, "loss": 3.6179, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.6629818725951826e-05, "loss": 3.615, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.6621449157245035e-05, "loss": 3.6075, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.6613063209734515e-05, "loss": 3.6062, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.6604677262223995e-05, "loss": 3.6179, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.6596291314713475e-05, "loss": 3.6135, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.6587905367202955e-05, "loss": 3.6042, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.657953579849617e-05, "loss": 3.6092, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.657114985098565e-05, "loss": 3.6028, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.656276390347513e-05, "loss": 3.6185, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.6554377955964604e-05, "loss": 3.6108, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654600838725782e-05, "loss": 3.6181, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.65376224397473e-05, "loss": 3.6218, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.652923649223678e-05, "loss": 3.6182, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.652085054472625e-05, "loss": 3.616, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.651248097601947e-05, "loss": 3.626, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.650409502850895e-05, "loss": 3.6165, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.649570908099842e-05, "loss": 3.6186, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.648732313348791e-05, "loss": 3.6122, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.647893718597739e-05, "loss": 3.6117, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.647055123846687e-05, "loss": 3.6157, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646218166976008e-05, "loss": 3.6162, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645379572224956e-05, "loss": 3.6073, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644540977473904e-05, "loss": 3.6115, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.643702382722852e-05, "loss": 3.6032, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.6428654258521726e-05, "loss": 3.6015, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.6420268311011206e-05, "loss": 3.6196, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.6411882363500686e-05, "loss": 3.6128, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.6403496415990166e-05, "loss": 3.6234, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.6395126847283375e-05, "loss": 3.6065, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.638674089977286e-05, "loss": 3.6211, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637835495226234e-05, "loss": 3.6197, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.636996900475182e-05, "loss": 3.6167, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.636159943604503e-05, "loss": 3.6165, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635321348853451e-05, "loss": 3.6089, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.634482754102399e-05, "loss": 3.6259, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.633644159351347e-05, "loss": 3.6246, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.632805564600295e-05, "loss": 3.608, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.631968607729616e-05, "loss": 3.6157, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631130012978564e-05, "loss": 3.6161, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.630291418227512e-05, "loss": 3.6107, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.62945282347646e-05, "loss": 3.6089, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.628614228725408e-05, "loss": 3.6112, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.627775633974356e-05, "loss": 3.6157, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.6269386771036776e-05, "loss": 3.6161, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.6261000823526256e-05, "loss": 3.6165, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.845015525817871, "eval_runtime": 304.9308, "eval_samples_per_second": 1251.402, "eval_steps_per_second": 39.107, "step": 839520 }, { "epoch": 1.0, "learning_rate": 3.6252614876015735e-05, "loss": 3.6053, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.6244228928505215e-05, "loss": 3.6004, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.6235859359798425e-05, "loss": 3.6084, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.6227473412287904e-05, "loss": 3.6126, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.6219087464777384e-05, "loss": 3.6228, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.6210701517266864e-05, "loss": 3.6125, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.6202315569756344e-05, "loss": 3.6094, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.6193946001049553e-05, "loss": 3.6072, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.6185560053539033e-05, "loss": 3.5983, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617717410602851e-05, "loss": 3.6086, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.616878815851799e-05, "loss": 3.6126, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.616041858981121e-05, "loss": 3.6082, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.615204902110442e-05, "loss": 3.6127, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.61436630735939e-05, "loss": 3.5962, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.613527712608338e-05, "loss": 3.6031, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.612689117857286e-05, "loss": 3.5916, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.611850523106234e-05, "loss": 3.6078, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.611011928355182e-05, "loss": 3.6038, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.61017333360413e-05, "loss": 3.606, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.609334738853078e-05, "loss": 3.605, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.608497781982399e-05, "loss": 3.6193, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.607659187231347e-05, "loss": 3.6044, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.606820592480295e-05, "loss": 3.6118, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.6059819977292434e-05, "loss": 3.603, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.605145040858564e-05, "loss": 3.6089, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604306446107512e-05, "loss": 3.6138, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.60346785135646e-05, "loss": 3.595, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602629256605408e-05, "loss": 3.607, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.6017906618543556e-05, "loss": 3.598, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.600953704983677e-05, "loss": 3.6014, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.600115110232625e-05, "loss": 3.6065, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599276515481573e-05, "loss": 3.6097, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.5984379207305205e-05, "loss": 3.6022, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.597600963859842e-05, "loss": 3.6216, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.59676236910879e-05, "loss": 3.6027, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.595923774357739e-05, "loss": 3.5997, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.595085179606686e-05, "loss": 3.616, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.5942482227360076e-05, "loss": 3.5991, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.5934096279849556e-05, "loss": 3.6019, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.592571033233903e-05, "loss": 3.6064, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.591732438482851e-05, "loss": 3.6005, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.590893843731799e-05, "loss": 3.6064, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.5900568868611205e-05, "loss": 3.612, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.589218292110068e-05, "loss": 3.6059, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.588379697359016e-05, "loss": 3.6076, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.587541102607964e-05, "loss": 3.608, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.5867041457372854e-05, "loss": 3.6051, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.5858655509862334e-05, "loss": 3.6083, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.5850269562351814e-05, "loss": 3.5758, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.5841883614841294e-05, "loss": 3.6079, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.5833497667330774e-05, "loss": 3.5972, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.5825111719820254e-05, "loss": 3.6095, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.581674215111346e-05, "loss": 3.5964, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.580835620360294e-05, "loss": 3.5851, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.579997025609242e-05, "loss": 3.5856, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.57915843085819e-05, "loss": 3.5921, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.578321473987511e-05, "loss": 3.6073, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.577482879236459e-05, "loss": 3.5842, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.576644284485408e-05, "loss": 3.6128, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.575805689734356e-05, "loss": 3.6043, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.574968732863677e-05, "loss": 3.583, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.574130138112625e-05, "loss": 3.6056, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.573291543361573e-05, "loss": 3.5867, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.572452948610521e-05, "loss": 3.5865, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.571614353859469e-05, "loss": 3.5954, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.57077739698879e-05, "loss": 3.6068, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.569938802237738e-05, "loss": 3.5815, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.569100207486686e-05, "loss": 3.5998, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.568261612735634e-05, "loss": 3.5809, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.5674246558649546e-05, "loss": 3.5998, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.566586061113903e-05, "loss": 3.6044, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.565747466362851e-05, "loss": 3.6039, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.564908871611799e-05, "loss": 3.6042, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.56407191474112e-05, "loss": 3.606, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.563233319990068e-05, "loss": 3.6228, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.562394725239016e-05, "loss": 3.6048, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.561556130487964e-05, "loss": 3.6081, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.560717535736912e-05, "loss": 3.5917, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.55987894098586e-05, "loss": 3.5953, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.559040346234808e-05, "loss": 3.5968, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.558203389364129e-05, "loss": 3.6016, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557364794613077e-05, "loss": 3.6061, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.556526199862025e-05, "loss": 3.6085, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555687605110973e-05, "loss": 3.591, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.5548506482402946e-05, "loss": 3.5917, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.5540120534892426e-05, "loss": 3.5871, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.5531734587381906e-05, "loss": 3.6089, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.5523348639871386e-05, "loss": 3.5992, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.5514962692360866e-05, "loss": 3.5923, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.550657674485034e-05, "loss": 3.6025, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.5498207176143555e-05, "loss": 3.5962, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.5489821228633035e-05, "loss": 3.5921, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.5481435281122515e-05, "loss": 3.5934, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.547304933361199e-05, "loss": 3.6059, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.5464679764905204e-05, "loss": 3.603, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.5456293817394684e-05, "loss": 3.6047, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.5447907869884164e-05, "loss": 3.5889, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.5439521922373644e-05, "loss": 3.5963, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543115235366686e-05, "loss": 3.5956, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.542276640615634e-05, "loss": 3.6037, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.541438045864581e-05, "loss": 3.6051, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.540599451113529e-05, "loss": 3.6008, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.539760856362477e-05, "loss": 3.6009, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.538922261611425e-05, "loss": 3.6, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.538085304740746e-05, "loss": 3.5977, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.537246709989694e-05, "loss": 3.5859, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.536408115238642e-05, "loss": 3.5898, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.53556952048759e-05, "loss": 3.5948, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.534732563616912e-05, "loss": 3.5942, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.53389396886586e-05, "loss": 3.5839, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.533055374114808e-05, "loss": 3.5863, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.532216779363756e-05, "loss": 3.5866, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.5313798224930766e-05, "loss": 3.5952, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.5305412277420246e-05, "loss": 3.5948, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.5297026329909726e-05, "loss": 3.5962, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.5288640382399206e-05, "loss": 3.6028, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.5280270813692415e-05, "loss": 3.6013, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.5271884866181895e-05, "loss": 3.5941, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.5263498918671375e-05, "loss": 3.6051, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.5255112971160855e-05, "loss": 3.597, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.524672702365034e-05, "loss": 3.6001, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.523835745494355e-05, "loss": 3.5941, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.522997150743303e-05, "loss": 3.5947, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522158555992251e-05, "loss": 3.5958, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521319961241199e-05, "loss": 3.5991, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.520481366490147e-05, "loss": 3.5898, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.519644409619468e-05, "loss": 3.5925, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.518805814868416e-05, "loss": 3.581, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.517967220117364e-05, "loss": 3.5877, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.517128625366312e-05, "loss": 3.597, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.516291668495633e-05, "loss": 3.5931, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.515453073744581e-05, "loss": 3.6046, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.5146144789935296e-05, "loss": 3.5826, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.5137758842424776e-05, "loss": 3.6043, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.5129372894914256e-05, "loss": 3.6014, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.5120986947403736e-05, "loss": 3.6009, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.5112617378696945e-05, "loss": 3.588, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.5104231431186425e-05, "loss": 3.5919, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.5095845483675905e-05, "loss": 3.6071, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.5087459536165385e-05, "loss": 3.6028, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.5079073588654864e-05, "loss": 3.5913, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.5070704019948074e-05, "loss": 3.5926, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.5062318072437554e-05, "loss": 3.5951, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.5053932124927034e-05, "loss": 3.5978, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.5045546177416513e-05, "loss": 3.5869, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.503717660870973e-05, "loss": 3.5971, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502879066119921e-05, "loss": 3.5925, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.502040471368869e-05, "loss": 3.5947, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.501201876617817e-05, "loss": 3.5984, "step": 915456 }, { "epoch": 1.03, "eval_loss": 3.8442368507385254, "eval_runtime": 305.2159, "eval_samples_per_second": 1250.233, "eval_steps_per_second": 39.071, "step": 915840 }, { "epoch": 0.0, "learning_rate": 3.500363281866765e-05, "loss": 3.5936, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.499524687115712e-05, "loss": 3.577, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.49868609236466e-05, "loss": 3.5914, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.497847497613608e-05, "loss": 3.5951, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.497010540742929e-05, "loss": 3.5953, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.496171945991877e-05, "loss": 3.5978, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.495333351240825e-05, "loss": 3.5922, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.494494756489773e-05, "loss": 3.5873, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.493656161738722e-05, "loss": 3.578, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.492819204868043e-05, "loss": 3.591, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.491980610116991e-05, "loss": 3.5935, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.491142015365939e-05, "loss": 3.5894, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.4903050584952596e-05, "loss": 3.5988, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.4894664637442076e-05, "loss": 3.5726, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.4886278689931556e-05, "loss": 3.5834, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.4877892742421036e-05, "loss": 3.5761, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.4869506794910516e-05, "loss": 3.5872, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.4861120847399996e-05, "loss": 3.5855, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.4852734899889476e-05, "loss": 3.5867, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.4844348952378956e-05, "loss": 3.5816, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.4835979383672165e-05, "loss": 3.6035, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.482759343616165e-05, "loss": 3.587, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.481920748865113e-05, "loss": 3.5925, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481082154114061e-05, "loss": 3.5851, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.480245197243382e-05, "loss": 3.5942, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.47940660249233e-05, "loss": 3.5916, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.478568007741278e-05, "loss": 3.5768, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.477729412990226e-05, "loss": 3.5883, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.476890818239174e-05, "loss": 3.5778, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.476053861368495e-05, "loss": 3.5809, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.475215266617443e-05, "loss": 3.5918, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474376671866391e-05, "loss": 3.5879, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.473538077115339e-05, "loss": 3.5848, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.472699482364287e-05, "loss": 3.601, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.4718625254936085e-05, "loss": 3.5844, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.4710239307425565e-05, "loss": 3.5841, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.4701853359915045e-05, "loss": 3.5969, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.4693467412404525e-05, "loss": 3.578, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.4685097843697734e-05, "loss": 3.5848, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.4676711896187214e-05, "loss": 3.5853, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.4668325948676694e-05, "loss": 3.5808, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.4659940001166174e-05, "loss": 3.5898, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.4651554053655654e-05, "loss": 3.5944, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.464318448494886e-05, "loss": 3.5845, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.463479853743834e-05, "loss": 3.5901, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.462641258992782e-05, "loss": 3.5911, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.46180266424173e-05, "loss": 3.5849, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.460965707371052e-05, "loss": 3.5895, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.46012711262e-05, "loss": 3.5586, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.459288517868948e-05, "loss": 3.5851, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.458449923117895e-05, "loss": 3.582, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.457612966247217e-05, "loss": 3.591, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.456774371496165e-05, "loss": 3.579, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455935776745113e-05, "loss": 3.5691, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.45509718199406e-05, "loss": 3.5671, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.454260225123382e-05, "loss": 3.5714, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.45342163037233e-05, "loss": 3.5905, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.452583035621278e-05, "loss": 3.5644, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.4517444408702257e-05, "loss": 3.5936, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.450907483999547e-05, "loss": 3.5849, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.450068889248495e-05, "loss": 3.5695, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.4492302944974426e-05, "loss": 3.5868, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.4483916997463906e-05, "loss": 3.5692, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447554742875712e-05, "loss": 3.5714, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.44671614812466e-05, "loss": 3.574, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.4458775533736075e-05, "loss": 3.5881, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.4450389586225555e-05, "loss": 3.5697, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.4442003638715034e-05, "loss": 3.5807, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.443363407000825e-05, "loss": 3.5604, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.442524812249773e-05, "loss": 3.5811, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.441686217498721e-05, "loss": 3.5861, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.440847622747669e-05, "loss": 3.5868, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.44001066587699e-05, "loss": 3.5862, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.439172071125938e-05, "loss": 3.5883, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.438333476374886e-05, "loss": 3.6023, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.437494881623834e-05, "loss": 3.5874, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.436657924753155e-05, "loss": 3.591, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.435819330002103e-05, "loss": 3.5743, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.434980735251051e-05, "loss": 3.5767, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.434142140499999e-05, "loss": 3.5789, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.433303545748947e-05, "loss": 3.5812, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.4324665888782684e-05, "loss": 3.5875, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.4316279941272164e-05, "loss": 3.5913, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.4307893993761644e-05, "loss": 3.5764, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.4299508046251124e-05, "loss": 3.5709, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.429113847754433e-05, "loss": 3.57, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.428275253003381e-05, "loss": 3.5902, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.427436658252329e-05, "loss": 3.5797, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.426598063501277e-05, "loss": 3.5753, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.425759468750225e-05, "loss": 3.5838, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.424920873999173e-05, "loss": 3.5803, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.424083917128494e-05, "loss": 3.5732, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.423245322377442e-05, "loss": 3.5729, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.42240672762639e-05, "loss": 3.5874, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.421568132875338e-05, "loss": 3.5887, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.42073117600466e-05, "loss": 3.5848, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.419892581253608e-05, "loss": 3.5687, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.419053986502556e-05, "loss": 3.5787, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.418215391751504e-05, "loss": 3.5792, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.417376797000452e-05, "loss": 3.5821, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.4165398401297726e-05, "loss": 3.5896, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.4157012453787206e-05, "loss": 3.5805, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.4148626506276686e-05, "loss": 3.5808, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.4140240558766166e-05, "loss": 3.5815, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.4131870990059375e-05, "loss": 3.581, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.4123485042548855e-05, "loss": 3.5697, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.4115099095038335e-05, "loss": 3.5731, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.410671314752782e-05, "loss": 3.5787, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.409834357882103e-05, "loss": 3.5772, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.408995763131051e-05, "loss": 3.5617, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.408157168379999e-05, "loss": 3.5726, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.407318573628947e-05, "loss": 3.5616, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.406481616758268e-05, "loss": 3.5819, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.405643022007216e-05, "loss": 3.5758, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.404804427256164e-05, "loss": 3.5785, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.403965832505112e-05, "loss": 3.5782, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.403128875634433e-05, "loss": 3.5848, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.402290280883381e-05, "loss": 3.5787, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.401451686132329e-05, "loss": 3.5811, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.4006130913812776e-05, "loss": 3.5835, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.3997761345105985e-05, "loss": 3.5806, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.3989375397595465e-05, "loss": 3.576, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.3980989450084945e-05, "loss": 3.5784, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.3972603502574425e-05, "loss": 3.5786, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.3964233933867634e-05, "loss": 3.5783, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.3955847986357114e-05, "loss": 3.5726, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.3947462038846594e-05, "loss": 3.5753, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.3939076091336074e-05, "loss": 3.5631, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.3930690143825554e-05, "loss": 3.5715, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.392232057511876e-05, "loss": 3.5781, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.391393462760824e-05, "loss": 3.5785, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.390554868009773e-05, "loss": 3.5848, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.389716273258721e-05, "loss": 3.5717, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.388879316388042e-05, "loss": 3.5847, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.38804072163699e-05, "loss": 3.5845, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.387202126885938e-05, "loss": 3.5777, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386363532134886e-05, "loss": 3.5752, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.385526575264207e-05, "loss": 3.5759, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.384687980513155e-05, "loss": 3.5902, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.383849385762103e-05, "loss": 3.5833, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.38301079101105e-05, "loss": 3.5762, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.3821738341403716e-05, "loss": 3.5766, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.3813352393893196e-05, "loss": 3.5768, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.380496644638268e-05, "loss": 3.5764, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.3796580498872156e-05, "loss": 3.5718, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.3788194551361636e-05, "loss": 3.5768, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.377982498265485e-05, "loss": 3.5741, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.377143903514433e-05, "loss": 3.5798, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.3763053087633805e-05, "loss": 3.5791, "step": 991744 }, { "epoch": 0.03, "eval_loss": 3.8442249298095703, "eval_runtime": 302.6004, "eval_samples_per_second": 1261.039, "eval_steps_per_second": 39.408, "step": 992160 }, { "epoch": 1.0, "learning_rate": 3.3754667140123285e-05, "loss": 3.5751, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.3746281192612765e-05, "loss": 3.5613, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.3737911623905974e-05, "loss": 3.5697, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.3729525676395454e-05, "loss": 3.5817, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.3721139728884934e-05, "loss": 3.5788, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371275378137442e-05, "loss": 3.5814, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.370438421266763e-05, "loss": 3.5703, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.369599826515711e-05, "loss": 3.5711, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.368761231764659e-05, "loss": 3.5607, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.367922637013607e-05, "loss": 3.5766, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.367084042262555e-05, "loss": 3.5721, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366247085391876e-05, "loss": 3.5743, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.3654101285211975e-05, "loss": 3.5801, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.364571533770145e-05, "loss": 3.558, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.363732939019093e-05, "loss": 3.5684, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.362894344268041e-05, "loss": 3.5544, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.362055749516989e-05, "loss": 3.5724, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.3612171547659375e-05, "loss": 3.5653, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.3603785600148854e-05, "loss": 3.5735, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.3595399652638334e-05, "loss": 3.5633, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.3587030083931544e-05, "loss": 3.5854, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.3578644136421024e-05, "loss": 3.5718, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.3570258188910503e-05, "loss": 3.5744, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.3561872241399983e-05, "loss": 3.5698, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.355350267269319e-05, "loss": 3.578, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.354511672518267e-05, "loss": 3.5736, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.353673077767215e-05, "loss": 3.5626, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.352834483016163e-05, "loss": 3.5723, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.351995888265111e-05, "loss": 3.5586, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.351158931394433e-05, "loss": 3.5626, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.350320336643381e-05, "loss": 3.5707, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.349481741892329e-05, "loss": 3.5679, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.348643147141277e-05, "loss": 3.5688, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.347806190270598e-05, "loss": 3.582, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.346967595519546e-05, "loss": 3.566, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.346129000768494e-05, "loss": 3.5719, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.345290406017442e-05, "loss": 3.5739, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.3444534491467626e-05, "loss": 3.5624, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.3436148543957106e-05, "loss": 3.5717, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.3427762596446586e-05, "loss": 3.5647, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.3419376648936066e-05, "loss": 3.5626, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.3410990701425546e-05, "loss": 3.5716, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.340262113271876e-05, "loss": 3.5799, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.339423518520824e-05, "loss": 3.5647, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.338584923769772e-05, "loss": 3.5726, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.33774632901872e-05, "loss": 3.5748, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.336909372148041e-05, "loss": 3.5685, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.336070777396989e-05, "loss": 3.5731, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.335232182645937e-05, "loss": 3.5391, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.334393587894885e-05, "loss": 3.5695, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.333556631024206e-05, "loss": 3.5643, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.332718036273154e-05, "loss": 3.5755, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.331879441522102e-05, "loss": 3.5622, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.33104084677105e-05, "loss": 3.5522, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.3302038899003715e-05, "loss": 3.5472, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.3293652951493195e-05, "loss": 3.5509, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.3285267003982675e-05, "loss": 3.5763, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.3276881056472155e-05, "loss": 3.5503, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.3268511487765364e-05, "loss": 3.574, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.3260125540254844e-05, "loss": 3.5658, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.3251739592744324e-05, "loss": 3.5561, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.3243353645233804e-05, "loss": 3.5687, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.3234984076527013e-05, "loss": 3.5482, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.322659812901649e-05, "loss": 3.5545, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.321821218150597e-05, "loss": 3.5566, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.320982623399545e-05, "loss": 3.5727, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.320144028648493e-05, "loss": 3.5536, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.319307071777815e-05, "loss": 3.5595, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.318468477026763e-05, "loss": 3.5489, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.317629882275711e-05, "loss": 3.5612, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.316791287524658e-05, "loss": 3.5706, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.31595433065398e-05, "loss": 3.5682, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.315115735902928e-05, "loss": 3.5722, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.314277141151876e-05, "loss": 3.5707, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.313438546400823e-05, "loss": 3.5845, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.312601589530145e-05, "loss": 3.5695, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.311762994779093e-05, "loss": 3.5738, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.310924400028041e-05, "loss": 3.56, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.310085805276989e-05, "loss": 3.5616, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.30924884840631e-05, "loss": 3.5632, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.308410253655258e-05, "loss": 3.5609, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.3075716589042056e-05, "loss": 3.5694, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.3067330641531536e-05, "loss": 3.5731, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.305896107282475e-05, "loss": 3.5677, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.305057512531423e-05, "loss": 3.5484, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.3042189177803705e-05, "loss": 3.5544, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.3033803230293185e-05, "loss": 3.57, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.3025417282782665e-05, "loss": 3.5662, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.3017031335272145e-05, "loss": 3.5596, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.300866176656536e-05, "loss": 3.5663, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.300027581905484e-05, "loss": 3.5652, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.299188987154432e-05, "loss": 3.5561, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.29835039240338e-05, "loss": 3.5603, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.297513435532701e-05, "loss": 3.5681, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.296674840781649e-05, "loss": 3.5708, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.295836246030597e-05, "loss": 3.5694, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.294997651279545e-05, "loss": 3.5517, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.294160694408866e-05, "loss": 3.5598, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.293322099657814e-05, "loss": 3.5649, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.292483504906762e-05, "loss": 3.5681, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.29164491015571e-05, "loss": 3.5701, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.2908079532850314e-05, "loss": 3.5651, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.2899693585339794e-05, "loss": 3.5628, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.2891307637829274e-05, "loss": 3.5628, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.2882921690318754e-05, "loss": 3.5656, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.2874535742808234e-05, "loss": 3.5533, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.286616617410144e-05, "loss": 3.5519, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285778022659092e-05, "loss": 3.5632, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.28493942790804e-05, "loss": 3.5627, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284100833156988e-05, "loss": 3.5472, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.283263876286309e-05, "loss": 3.5548, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.282425281535257e-05, "loss": 3.5496, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.281586686784205e-05, "loss": 3.5606, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.280748092033153e-05, "loss": 3.5598, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.279911135162475e-05, "loss": 3.5592, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.279072540411423e-05, "loss": 3.5638, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.278233945660371e-05, "loss": 3.5703, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.277395350909319e-05, "loss": 3.5617, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.27655839403864e-05, "loss": 3.5647, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.275719799287588e-05, "loss": 3.5693, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.274881204536536e-05, "loss": 3.5619, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.274042609785484e-05, "loss": 3.5575, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.2732056529148046e-05, "loss": 3.5642, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.2723670581637526e-05, "loss": 3.5617, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.2715284634127006e-05, "loss": 3.5593, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.2706898686616486e-05, "loss": 3.554, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.26985291179097e-05, "loss": 3.5606, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.269014317039918e-05, "loss": 3.5525, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.268175722288866e-05, "loss": 3.5539, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.267337127537814e-05, "loss": 3.5546, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.266500170667135e-05, "loss": 3.563, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.265661575916083e-05, "loss": 3.5648, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.264822981165031e-05, "loss": 3.5556, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.263984386413979e-05, "loss": 3.5685, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.2631474295433e-05, "loss": 3.5695, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.262308834792248e-05, "loss": 3.5669, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.261470240041196e-05, "loss": 3.5605, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.260631645290144e-05, "loss": 3.5566, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.2597946884194655e-05, "loss": 3.5744, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.2589560936684135e-05, "loss": 3.5579, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.2581174989173615e-05, "loss": 3.5666, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.2572789041663095e-05, "loss": 3.5597, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.2564419472956304e-05, "loss": 3.5612, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.2556033525445784e-05, "loss": 3.5584, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.2547647577935264e-05, "loss": 3.5564, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.2539261630424744e-05, "loss": 3.5642, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.253089206171795e-05, "loss": 3.5575, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.252250611420743e-05, "loss": 3.5634, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.251412016669691e-05, "loss": 3.5605, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 3.845308303833008, "eval_runtime": 308.404, "eval_samples_per_second": 1237.309, "eval_steps_per_second": 38.667, "step": 1068480 }, { "epoch": 0.0, "learning_rate": 3.250573421918639e-05, "loss": 3.5535, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.249734827167587e-05, "loss": 3.547, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.248896232416535e-05, "loss": 3.5514, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.248057637665484e-05, "loss": 3.5664, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.247220680794805e-05, "loss": 3.5596, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.246382086043753e-05, "loss": 3.5663, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.245543491292701e-05, "loss": 3.5521, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.244704896541649e-05, "loss": 3.5548, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.24386793967097e-05, "loss": 3.545, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.243029344919918e-05, "loss": 3.5572, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.242190750168866e-05, "loss": 3.5584, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.241352155417813e-05, "loss": 3.5596, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.2405168364275076e-05, "loss": 3.5639, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.239678241676456e-05, "loss": 3.5458, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.238839646925404e-05, "loss": 3.5457, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.238001052174352e-05, "loss": 3.5437, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.2371624574233e-05, "loss": 3.5528, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.236323862672248e-05, "loss": 3.5487, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.235485267921196e-05, "loss": 3.5585, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.2346466731701436e-05, "loss": 3.5478, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.233809716299465e-05, "loss": 3.5679, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.232971121548413e-05, "loss": 3.5554, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.2321325267973605e-05, "loss": 3.553, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.2312939320463085e-05, "loss": 3.5561, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.23045697517563e-05, "loss": 3.5658, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.229618380424578e-05, "loss": 3.5541, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.228779785673526e-05, "loss": 3.5475, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.227941190922474e-05, "loss": 3.5551, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.227102596171422e-05, "loss": 3.541, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.2262656393007436e-05, "loss": 3.546, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.225427044549691e-05, "loss": 3.5528, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.224588449798639e-05, "loss": 3.5531, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.223749855047587e-05, "loss": 3.5563, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.222912898176908e-05, "loss": 3.5627, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.222074303425856e-05, "loss": 3.5546, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.221235708674804e-05, "loss": 3.5548, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.220397113923752e-05, "loss": 3.557, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.2195601570530734e-05, "loss": 3.5474, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.2187215623020214e-05, "loss": 3.5579, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.2178829675509694e-05, "loss": 3.5479, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.2170443727999174e-05, "loss": 3.5479, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.216207415929238e-05, "loss": 3.5531, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.215368821178186e-05, "loss": 3.5647, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.214530226427134e-05, "loss": 3.547, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.213691631676082e-05, "loss": 3.5627, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212854674805403e-05, "loss": 3.5559, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.212016080054351e-05, "loss": 3.5548, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.211177485303299e-05, "loss": 3.5557, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.210338890552247e-05, "loss": 3.5243, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.209500295801195e-05, "loss": 3.5504, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.208663338930517e-05, "loss": 3.5552, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.207824744179465e-05, "loss": 3.5546, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.206986149428413e-05, "loss": 3.5458, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.206147554677361e-05, "loss": 3.5394, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.2053105978066817e-05, "loss": 3.5311, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.2044720030556297e-05, "loss": 3.5363, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.2036334083045776e-05, "loss": 3.5631, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.2027948135535256e-05, "loss": 3.533, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.2019578566828466e-05, "loss": 3.5567, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.2011192619317946e-05, "loss": 3.549, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.2002806671807425e-05, "loss": 3.5378, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.1994420724296905e-05, "loss": 3.5525, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198605115559012e-05, "loss": 3.5377, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.19776652080796e-05, "loss": 3.5417, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.196927926056908e-05, "loss": 3.5376, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.196089331305856e-05, "loss": 3.5558, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.195252374435177e-05, "loss": 3.5424, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.194413779684125e-05, "loss": 3.5421, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.193575184933073e-05, "loss": 3.5351, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.192736590182021e-05, "loss": 3.5449, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.191899633311342e-05, "loss": 3.5538, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.19106103856029e-05, "loss": 3.5511, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.190222443809238e-05, "loss": 3.5526, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.189383849058186e-05, "loss": 3.5574, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.1885452543071346e-05, "loss": 3.5681, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.1877082974364555e-05, "loss": 3.5545, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.1868697026854035e-05, "loss": 3.5573, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.1860311079343515e-05, "loss": 3.5463, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.1851925131832995e-05, "loss": 3.5463, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.1843555563126204e-05, "loss": 3.5446, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.1835169615615684e-05, "loss": 3.5428, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.1826783668105164e-05, "loss": 3.556, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.1818397720594644e-05, "loss": 3.5592, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.181002815188785e-05, "loss": 3.5525, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.180164220437733e-05, "loss": 3.5291, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.179325625686681e-05, "loss": 3.5406, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.178487030935629e-05, "loss": 3.5523, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.177648436184578e-05, "loss": 3.5515, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.176809841433526e-05, "loss": 3.5408, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.175972884562847e-05, "loss": 3.5525, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.175134289811795e-05, "loss": 3.5462, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.174295695060743e-05, "loss": 3.5396, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.173457100309691e-05, "loss": 3.5428, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.172620143439012e-05, "loss": 3.5552, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.17178154868796e-05, "loss": 3.5469, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.170942953936908e-05, "loss": 3.5566, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.170104359185856e-05, "loss": 3.5362, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.169265764434804e-05, "loss": 3.5435, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.1684288075641246e-05, "loss": 3.5519, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.167590212813073e-05, "loss": 3.5505, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.166751618062021e-05, "loss": 3.5551, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.1659130233109686e-05, "loss": 3.5495, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.16507606644029e-05, "loss": 3.5474, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.164237471689238e-05, "loss": 3.5473, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.163398876938186e-05, "loss": 3.5534, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.1625602821871335e-05, "loss": 3.5333, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.161723325316455e-05, "loss": 3.5409, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.160884730565403e-05, "loss": 3.5432, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.160046135814351e-05, "loss": 3.5448, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.1592075410632984e-05, "loss": 3.5362, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.15837058419262e-05, "loss": 3.5379, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.157531989441569e-05, "loss": 3.5302, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.156693394690516e-05, "loss": 3.5496, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.155854799939464e-05, "loss": 3.5428, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.1550178430687856e-05, "loss": 3.5442, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.1541792483177336e-05, "loss": 3.548, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.153340653566681e-05, "loss": 3.5526, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.152502058815629e-05, "loss": 3.5469, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.1516651019449505e-05, "loss": 3.5458, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.1508265071938985e-05, "loss": 3.5561, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.149987912442846e-05, "loss": 3.5459, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.149149317691794e-05, "loss": 3.5396, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.1483107229407425e-05, "loss": 3.5476, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.1474737660700634e-05, "loss": 3.5452, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.1466351713190114e-05, "loss": 3.5474, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.1457965765679594e-05, "loss": 3.5366, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.1449579818169074e-05, "loss": 3.5472, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.144121024946228e-05, "loss": 3.5373, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143282430195176e-05, "loss": 3.5408, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.142443835444124e-05, "loss": 3.5332, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.141605240693072e-05, "loss": 3.553, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140768283822393e-05, "loss": 3.5498, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.139929689071341e-05, "loss": 3.5342, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.139091094320289e-05, "loss": 3.5535, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.138252499569238e-05, "loss": 3.5511, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.137415542698559e-05, "loss": 3.5511, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.136576947947507e-05, "loss": 3.5428, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.135738353196455e-05, "loss": 3.5449, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.134899758445403e-05, "loss": 3.5598, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.134061163694351e-05, "loss": 3.5426, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.1332242068236716e-05, "loss": 3.5512, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.1323856120726196e-05, "loss": 3.5428, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.1315470173215676e-05, "loss": 3.5462, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.1307084225705156e-05, "loss": 3.5412, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.1298714656998365e-05, "loss": 3.5385, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.1290328709487845e-05, "loss": 3.5467, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.128194276197733e-05, "loss": 3.5434, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.127355681446681e-05, "loss": 3.5505, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.126518724576002e-05, "loss": 3.5437, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 3.845208168029785, "eval_runtime": 303.7344, "eval_samples_per_second": 1256.331, "eval_steps_per_second": 39.261, "step": 1144800 }, { "epoch": 1.0, "learning_rate": 3.12568012982495e-05, "loss": 3.5408, "step": 1144832 }, { "epoch": 1.0, "learning_rate": 3.124841535073898e-05, "loss": 3.5375, "step": 1145344 }, { "epoch": 1.0, "learning_rate": 3.124002940322846e-05, "loss": 3.536, "step": 1145856 }, { "epoch": 1.0, "learning_rate": 3.123164345571794e-05, "loss": 3.5467, "step": 1146368 }, { "epoch": 1.0, "learning_rate": 3.122327388701115e-05, "loss": 3.5448, "step": 1146880 }, { "epoch": 1.0, "learning_rate": 3.121488793950063e-05, "loss": 3.5543, "step": 1147392 }, { "epoch": 1.0, "learning_rate": 3.120650199199011e-05, "loss": 3.5358, "step": 1147904 }, { "epoch": 1.0, "learning_rate": 3.119811604447959e-05, "loss": 3.5399, "step": 1148416 }, { "epoch": 1.0, "learning_rate": 3.11897464757728e-05, "loss": 3.5277, "step": 1148928 }, { "epoch": 1.0, "learning_rate": 3.1181360528262286e-05, "loss": 3.5432, "step": 1149440 }, { "epoch": 1.0, "learning_rate": 3.1172974580751766e-05, "loss": 3.5378, "step": 1149952 }, { "epoch": 1.0, "learning_rate": 3.1164588633241245e-05, "loss": 3.5473, "step": 1150464 }, { "epoch": 1.0, "learning_rate": 3.1156235443338184e-05, "loss": 3.5472, "step": 1150976 }, { "epoch": 1.0, "learning_rate": 3.1147849495827664e-05, "loss": 3.532, "step": 1151488 }, { "epoch": 1.0, "learning_rate": 3.1139463548317144e-05, "loss": 3.5283, "step": 1152000 }, { "epoch": 1.0, "learning_rate": 3.1131077600806624e-05, "loss": 3.5318, "step": 1152512 }, { "epoch": 1.0, "learning_rate": 3.1122691653296104e-05, "loss": 3.5355, "step": 1153024 }, { "epoch": 1.0, "learning_rate": 3.1114305705785583e-05, "loss": 3.5345, "step": 1153536 }, { "epoch": 1.0, "learning_rate": 3.1105919758275063e-05, "loss": 3.5435, "step": 1154048 }, { "epoch": 1.0, "learning_rate": 3.1097533810764543e-05, "loss": 3.5321, "step": 1154560 }, { "epoch": 1.0, "learning_rate": 3.108916424205775e-05, "loss": 3.5506, "step": 1155072 }, { "epoch": 1.0, "learning_rate": 3.108077829454724e-05, "loss": 3.5372, "step": 1155584 }, { "epoch": 1.0, "learning_rate": 3.107239234703672e-05, "loss": 3.541, "step": 1156096 }, { "epoch": 1.0, "learning_rate": 3.10640063995262e-05, "loss": 3.5404, "step": 1156608 }, { "epoch": 1.0, "learning_rate": 3.105563683081941e-05, "loss": 3.5492, "step": 1157120 }, { "epoch": 1.0, "learning_rate": 3.104725088330889e-05, "loss": 3.5401, "step": 1157632 }, { "epoch": 1.0, "learning_rate": 3.103886493579837e-05, "loss": 3.5347, "step": 1158144 }, { "epoch": 1.0, "learning_rate": 3.103047898828785e-05, "loss": 3.5383, "step": 1158656 }, { "epoch": 1.0, "learning_rate": 3.102209304077733e-05, "loss": 3.5259, "step": 1159168 }, { "epoch": 1.0, "learning_rate": 3.101372347207054e-05, "loss": 3.5351, "step": 1159680 }, { "epoch": 1.01, "learning_rate": 3.100533752456002e-05, "loss": 3.5347, "step": 1160192 }, { "epoch": 1.01, "learning_rate": 3.09969515770495e-05, "loss": 3.542, "step": 1160704 }, { "epoch": 1.01, "learning_rate": 3.098856562953898e-05, "loss": 3.5369, "step": 1161216 }, { "epoch": 1.01, "learning_rate": 3.0980196060832186e-05, "loss": 3.5459, "step": 1161728 }, { "epoch": 1.01, "learning_rate": 3.097181011332167e-05, "loss": 3.5413, "step": 1162240 }, { "epoch": 1.01, "learning_rate": 3.096342416581115e-05, "loss": 3.5398, "step": 1162752 }, { "epoch": 1.01, "learning_rate": 3.095503821830063e-05, "loss": 3.5435, "step": 1163264 }, { "epoch": 1.01, "learning_rate": 3.094666864959384e-05, "loss": 3.5305, "step": 1163776 }, { "epoch": 1.01, "learning_rate": 3.093828270208332e-05, "loss": 3.543, "step": 1164288 }, { "epoch": 1.01, "learning_rate": 3.09298967545728e-05, "loss": 3.5317, "step": 1164800 }, { "epoch": 1.01, "learning_rate": 3.092151080706228e-05, "loss": 3.5334, "step": 1165312 }, { "epoch": 1.01, "learning_rate": 3.091312485955176e-05, "loss": 3.5407, "step": 1165824 }, { "epoch": 1.01, "learning_rate": 3.090475529084497e-05, "loss": 3.5469, "step": 1166336 }, { "epoch": 1.01, "learning_rate": 3.089636934333445e-05, "loss": 3.5355, "step": 1166848 }, { "epoch": 1.01, "learning_rate": 3.088798339582393e-05, "loss": 3.5426, "step": 1167360 }, { "epoch": 1.01, "learning_rate": 3.087959744831341e-05, "loss": 3.541, "step": 1167872 }, { "epoch": 1.01, "learning_rate": 3.0871227879606627e-05, "loss": 3.5401, "step": 1168384 }, { "epoch": 1.01, "learning_rate": 3.0862841932096106e-05, "loss": 3.5393, "step": 1168896 }, { "epoch": 1.01, "learning_rate": 3.0854455984585586e-05, "loss": 3.513, "step": 1169408 }, { "epoch": 1.01, "learning_rate": 3.0846070037075066e-05, "loss": 3.5313, "step": 1169920 }, { "epoch": 1.01, "learning_rate": 3.0837700468368275e-05, "loss": 3.543, "step": 1170432 }, { "epoch": 1.01, "learning_rate": 3.0829314520857755e-05, "loss": 3.5401, "step": 1170944 }, { "epoch": 1.01, "learning_rate": 3.0820928573347235e-05, "loss": 3.5309, "step": 1171456 }, { "epoch": 1.01, "learning_rate": 3.081254262583671e-05, "loss": 3.5194, "step": 1171968 }, { "epoch": 1.01, "learning_rate": 3.0804173057129924e-05, "loss": 3.5245, "step": 1172480 }, { "epoch": 1.01, "learning_rate": 3.0795787109619404e-05, "loss": 3.5151, "step": 1172992 }, { "epoch": 1.01, "learning_rate": 3.0787401162108884e-05, "loss": 3.5511, "step": 1173504 }, { "epoch": 1.01, "learning_rate": 3.0779015214598364e-05, "loss": 3.5179, "step": 1174016 }, { "epoch": 1.01, "learning_rate": 3.0770629267087844e-05, "loss": 3.5396, "step": 1174528 }, { "epoch": 1.01, "learning_rate": 3.076225969838106e-05, "loss": 3.5338, "step": 1175040 }, { "epoch": 1.01, "learning_rate": 3.075387375087053e-05, "loss": 3.5248, "step": 1175552 }, { "epoch": 1.01, "learning_rate": 3.074548780336001e-05, "loss": 3.5346, "step": 1176064 }, { "epoch": 1.01, "learning_rate": 3.073710185584949e-05, "loss": 3.5235, "step": 1176576 }, { "epoch": 1.01, "learning_rate": 3.072873228714271e-05, "loss": 3.5259, "step": 1177088 }, { "epoch": 1.01, "learning_rate": 3.072034633963218e-05, "loss": 3.5209, "step": 1177600 }, { "epoch": 1.01, "learning_rate": 3.071196039212166e-05, "loss": 3.5425, "step": 1178112 }, { "epoch": 1.01, "learning_rate": 3.070357444461114e-05, "loss": 3.527, "step": 1178624 }, { "epoch": 1.01, "learning_rate": 3.069520487590436e-05, "loss": 3.525, "step": 1179136 }, { "epoch": 1.01, "learning_rate": 3.068681892839383e-05, "loss": 3.5204, "step": 1179648 }, { "epoch": 1.01, "learning_rate": 3.067843298088332e-05, "loss": 3.5301, "step": 1180160 }, { "epoch": 1.01, "learning_rate": 3.06700470333728e-05, "loss": 3.5395, "step": 1180672 }, { "epoch": 1.01, "learning_rate": 3.066166108586228e-05, "loss": 3.5384, "step": 1181184 }, { "epoch": 1.01, "learning_rate": 3.065329151715549e-05, "loss": 3.5389, "step": 1181696 }, { "epoch": 1.01, "learning_rate": 3.064490556964497e-05, "loss": 3.54, "step": 1182208 }, { "epoch": 1.01, "learning_rate": 3.063651962213445e-05, "loss": 3.5505, "step": 1182720 }, { "epoch": 1.01, "learning_rate": 3.062813367462393e-05, "loss": 3.5421, "step": 1183232 }, { "epoch": 1.01, "learning_rate": 3.0619764105917136e-05, "loss": 3.5393, "step": 1183744 }, { "epoch": 1.01, "learning_rate": 3.0611378158406616e-05, "loss": 3.5298, "step": 1184256 }, { "epoch": 1.01, "learning_rate": 3.0602992210896096e-05, "loss": 3.5347, "step": 1184768 }, { "epoch": 1.01, "learning_rate": 3.0594606263385576e-05, "loss": 3.5293, "step": 1185280 }, { "epoch": 1.01, "learning_rate": 3.0586236694678785e-05, "loss": 3.5313, "step": 1185792 }, { "epoch": 1.01, "learning_rate": 3.057785074716827e-05, "loss": 3.5405, "step": 1186304 }, { "epoch": 1.01, "learning_rate": 3.056946479965775e-05, "loss": 3.5461, "step": 1186816 }, { "epoch": 1.01, "learning_rate": 3.056107885214723e-05, "loss": 3.5361, "step": 1187328 }, { "epoch": 1.01, "learning_rate": 3.055270928344044e-05, "loss": 3.52, "step": 1187840 }, { "epoch": 1.01, "learning_rate": 3.054432333592992e-05, "loss": 3.5228, "step": 1188352 }, { "epoch": 1.01, "learning_rate": 3.05359373884194e-05, "loss": 3.5333, "step": 1188864 }, { "epoch": 1.01, "learning_rate": 3.052755144090888e-05, "loss": 3.5422, "step": 1189376 }, { "epoch": 1.01, "learning_rate": 3.051918187220209e-05, "loss": 3.5253, "step": 1189888 }, { "epoch": 1.01, "learning_rate": 3.051079592469157e-05, "loss": 3.5382, "step": 1190400 }, { "epoch": 1.02, "learning_rate": 3.050240997718105e-05, "loss": 3.5361, "step": 1190912 }, { "epoch": 1.02, "learning_rate": 3.0494024029670533e-05, "loss": 3.5231, "step": 1191424 }, { "epoch": 1.02, "learning_rate": 3.0485638082160013e-05, "loss": 3.5265, "step": 1191936 }, { "epoch": 1.02, "learning_rate": 3.0477268513453222e-05, "loss": 3.5379, "step": 1192448 }, { "epoch": 1.02, "learning_rate": 3.0468882565942702e-05, "loss": 3.5316, "step": 1192960 }, { "epoch": 1.02, "learning_rate": 3.0460496618432182e-05, "loss": 3.54, "step": 1193472 }, { "epoch": 1.02, "learning_rate": 3.0452110670921662e-05, "loss": 3.5258, "step": 1193984 }, { "epoch": 1.02, "learning_rate": 3.0443741102214874e-05, "loss": 3.5279, "step": 1194496 }, { "epoch": 1.02, "learning_rate": 3.0435355154704354e-05, "loss": 3.5326, "step": 1195008 }, { "epoch": 1.02, "learning_rate": 3.0426969207193834e-05, "loss": 3.5383, "step": 1195520 }, { "epoch": 1.02, "learning_rate": 3.0418583259683314e-05, "loss": 3.5359, "step": 1196032 }, { "epoch": 1.02, "learning_rate": 3.0410213690976523e-05, "loss": 3.5361, "step": 1196544 }, { "epoch": 1.02, "learning_rate": 3.0401827743466003e-05, "loss": 3.5342, "step": 1197056 }, { "epoch": 1.02, "learning_rate": 3.0393441795955487e-05, "loss": 3.5337, "step": 1197568 }, { "epoch": 1.02, "learning_rate": 3.0385055848444966e-05, "loss": 3.5361, "step": 1198080 }, { "epoch": 1.02, "learning_rate": 3.0376669900934446e-05, "loss": 3.517, "step": 1198592 }, { "epoch": 1.02, "learning_rate": 3.0368300332227656e-05, "loss": 3.5249, "step": 1199104 }, { "epoch": 1.02, "learning_rate": 3.0359914384717136e-05, "loss": 3.5335, "step": 1199616 }, { "epoch": 1.02, "learning_rate": 3.0351528437206615e-05, "loss": 3.5297, "step": 1200128 }, { "epoch": 1.02, "learning_rate": 3.0343142489696095e-05, "loss": 3.52, "step": 1200640 }, { "epoch": 1.02, "learning_rate": 3.0334772920989308e-05, "loss": 3.525, "step": 1201152 }, { "epoch": 1.02, "learning_rate": 3.0326386973478788e-05, "loss": 3.5151, "step": 1201664 }, { "epoch": 1.02, "learning_rate": 3.0318001025968268e-05, "loss": 3.5329, "step": 1202176 }, { "epoch": 1.02, "learning_rate": 3.0309615078457748e-05, "loss": 3.5243, "step": 1202688 }, { "epoch": 1.02, "learning_rate": 3.0301245509750957e-05, "loss": 3.536, "step": 1203200 }, { "epoch": 1.02, "learning_rate": 3.029285956224044e-05, "loss": 3.5297, "step": 1203712 }, { "epoch": 1.02, "learning_rate": 3.028447361472992e-05, "loss": 3.5396, "step": 1204224 }, { "epoch": 1.02, "learning_rate": 3.02760876672194e-05, "loss": 3.532, "step": 1204736 }, { "epoch": 1.02, "learning_rate": 3.026771809851261e-05, "loss": 3.5348, "step": 1205248 }, { "epoch": 1.02, "learning_rate": 3.025933215100209e-05, "loss": 3.5389, "step": 1205760 }, { "epoch": 1.02, "learning_rate": 3.025094620349157e-05, "loss": 3.5291, "step": 1206272 }, { "epoch": 1.02, "learning_rate": 3.024256025598105e-05, "loss": 3.5292, "step": 1206784 }, { "epoch": 1.02, "learning_rate": 3.023419068727426e-05, "loss": 3.5335, "step": 1207296 }, { "epoch": 1.02, "learning_rate": 3.022580473976374e-05, "loss": 3.5314, "step": 1207808 }, { "epoch": 1.02, "learning_rate": 3.021741879225322e-05, "loss": 3.5335, "step": 1208320 }, { "epoch": 1.02, "learning_rate": 3.02090328447427e-05, "loss": 3.5242, "step": 1208832 }, { "epoch": 1.02, "learning_rate": 3.020066327603591e-05, "loss": 3.527, "step": 1209344 }, { "epoch": 1.02, "learning_rate": 3.0192277328525394e-05, "loss": 3.5246, "step": 1209856 }, { "epoch": 1.02, "learning_rate": 3.0183891381014874e-05, "loss": 3.5217, "step": 1210368 }, { "epoch": 1.02, "learning_rate": 3.0175505433504354e-05, "loss": 3.5174, "step": 1210880 }, { "epoch": 1.02, "learning_rate": 3.0167135864797563e-05, "loss": 3.5426, "step": 1211392 }, { "epoch": 1.02, "learning_rate": 3.0158749917287043e-05, "loss": 3.5366, "step": 1211904 }, { "epoch": 1.02, "learning_rate": 3.0150363969776523e-05, "loss": 3.5273, "step": 1212416 }, { "epoch": 1.02, "learning_rate": 3.0141978022266003e-05, "loss": 3.53, "step": 1212928 }, { "epoch": 1.02, "learning_rate": 3.0133592074755486e-05, "loss": 3.5336, "step": 1213440 }, { "epoch": 1.02, "learning_rate": 3.0125222506048695e-05, "loss": 3.5392, "step": 1213952 }, { "epoch": 1.02, "learning_rate": 3.0116836558538175e-05, "loss": 3.5311, "step": 1214464 }, { "epoch": 1.02, "learning_rate": 3.0108450611027655e-05, "loss": 3.5296, "step": 1214976 }, { "epoch": 1.02, "learning_rate": 3.0100064663517135e-05, "loss": 3.5413, "step": 1215488 }, { "epoch": 1.02, "learning_rate": 3.009167871600661e-05, "loss": 3.5237, "step": 1216000 }, { "epoch": 1.02, "learning_rate": 3.0083309147299827e-05, "loss": 3.5383, "step": 1216512 }, { "epoch": 1.02, "learning_rate": 3.0074923199789307e-05, "loss": 3.5303, "step": 1217024 }, { "epoch": 1.02, "learning_rate": 3.0066537252278787e-05, "loss": 3.5344, "step": 1217536 }, { "epoch": 1.02, "learning_rate": 3.005815130476826e-05, "loss": 3.5293, "step": 1218048 }, { "epoch": 1.02, "learning_rate": 3.0049781736061476e-05, "loss": 3.519, "step": 1218560 }, { "epoch": 1.02, "learning_rate": 3.0041395788550956e-05, "loss": 3.5367, "step": 1219072 }, { "epoch": 1.02, "learning_rate": 3.003300984104044e-05, "loss": 3.5298, "step": 1219584 }, { "epoch": 1.02, "learning_rate": 3.0024623893529913e-05, "loss": 3.5334, "step": 1220096 }, { "epoch": 1.02, "learning_rate": 3.001625432482313e-05, "loss": 3.5265, "step": 1220608 }, { "epoch": 1.03, "learning_rate": 3.000786837731261e-05, "loss": 3.531, "step": 1221120 }, { "epoch": 1.03, "eval_loss": 3.8468105792999268, "eval_runtime": 303.2508, "eval_samples_per_second": 1258.335, "eval_steps_per_second": 39.324, "step": 1221120 }, { "epoch": 0.0, "learning_rate": 2.9999482429802085e-05, "loss": 3.5201, "step": 1221632 }, { "epoch": 0.0, "learning_rate": 2.9991096482291565e-05, "loss": 3.5182, "step": 1222144 }, { "epoch": 0.0, "learning_rate": 2.9982710534781045e-05, "loss": 3.5349, "step": 1222656 }, { "epoch": 0.0, "learning_rate": 2.997434096607426e-05, "loss": 3.5321, "step": 1223168 }, { "epoch": 0.0, "learning_rate": 2.9965955018563734e-05, "loss": 3.5397, "step": 1223680 }, { "epoch": 0.0, "learning_rate": 2.9957569071053214e-05, "loss": 3.5209, "step": 1224192 }, { "epoch": 0.0, "learning_rate": 2.9949183123542694e-05, "loss": 3.5235, "step": 1224704 }, { "epoch": 0.0, "learning_rate": 2.994081355483591e-05, "loss": 3.5124, "step": 1225216 }, { "epoch": 0.0, "learning_rate": 2.9932427607325387e-05, "loss": 3.5308, "step": 1225728 }, { "epoch": 0.0, "learning_rate": 2.9924041659814867e-05, "loss": 3.5229, "step": 1226240 }, { "epoch": 0.0, "learning_rate": 2.9915655712304347e-05, "loss": 3.532, "step": 1226752 }, { "epoch": 0.0, "learning_rate": 2.9907286143597556e-05, "loss": 3.529, "step": 1227264 }, { "epoch": 0.0, "learning_rate": 2.989891657489077e-05, "loss": 3.5239, "step": 1227776 }, { "epoch": 0.0, "learning_rate": 2.9890530627380255e-05, "loss": 3.5139, "step": 1228288 }, { "epoch": 0.0, "learning_rate": 2.9882144679869735e-05, "loss": 3.518, "step": 1228800 }, { "epoch": 0.0, "learning_rate": 2.9873758732359208e-05, "loss": 3.514, "step": 1229312 }, { "epoch": 0.0, "learning_rate": 2.9865372784848688e-05, "loss": 3.5228, "step": 1229824 }, { "epoch": 0.0, "learning_rate": 2.9856986837338168e-05, "loss": 3.5266, "step": 1230336 }, { "epoch": 0.0, "learning_rate": 2.9848600889827648e-05, "loss": 3.5169, "step": 1230848 }, { "epoch": 0.0, "learning_rate": 2.984023132112086e-05, "loss": 3.5421, "step": 1231360 }, { "epoch": 0.0, "learning_rate": 2.983184537361034e-05, "loss": 3.5218, "step": 1231872 }, { "epoch": 0.0, "learning_rate": 2.982345942609982e-05, "loss": 3.5273, "step": 1232384 }, { "epoch": 0.0, "learning_rate": 2.98150734785893e-05, "loss": 3.5261, "step": 1232896 }, { "epoch": 0.0, "learning_rate": 2.980668753107878e-05, "loss": 3.5324, "step": 1233408 }, { "epoch": 0.0, "learning_rate": 2.9798317962371993e-05, "loss": 3.5219, "step": 1233920 }, { "epoch": 0.0, "learning_rate": 2.9789932014861473e-05, "loss": 3.5239, "step": 1234432 }, { "epoch": 0.0, "learning_rate": 2.9781546067350953e-05, "loss": 3.522, "step": 1234944 }, { "epoch": 0.0, "learning_rate": 2.9773160119840433e-05, "loss": 3.5194, "step": 1235456 }, { "epoch": 0.0, "learning_rate": 2.976479055113364e-05, "loss": 3.5155, "step": 1235968 }, { "epoch": 0.01, "learning_rate": 2.975640460362312e-05, "loss": 3.5183, "step": 1236480 }, { "epoch": 0.01, "learning_rate": 2.97480186561126e-05, "loss": 3.5306, "step": 1236992 }, { "epoch": 0.01, "learning_rate": 2.973963270860208e-05, "loss": 3.5254, "step": 1237504 }, { "epoch": 0.01, "learning_rate": 2.9731263139895294e-05, "loss": 3.5273, "step": 1238016 }, { "epoch": 0.01, "learning_rate": 2.9722877192384774e-05, "loss": 3.5298, "step": 1238528 }, { "epoch": 0.01, "learning_rate": 2.9714491244874254e-05, "loss": 3.5245, "step": 1239040 }, { "epoch": 0.01, "learning_rate": 2.9706105297363734e-05, "loss": 3.5287, "step": 1239552 }, { "epoch": 0.01, "learning_rate": 2.9697735728656946e-05, "loss": 3.5189, "step": 1240064 }, { "epoch": 0.01, "learning_rate": 2.9689349781146426e-05, "loss": 3.524, "step": 1240576 }, { "epoch": 0.01, "learning_rate": 2.9680963833635906e-05, "loss": 3.5181, "step": 1241088 }, { "epoch": 0.01, "learning_rate": 2.9672577886125386e-05, "loss": 3.5223, "step": 1241600 }, { "epoch": 0.01, "learning_rate": 2.9664191938614866e-05, "loss": 3.524, "step": 1242112 }, { "epoch": 0.01, "learning_rate": 2.9655805991104346e-05, "loss": 3.5324, "step": 1242624 }, { "epoch": 0.01, "learning_rate": 2.9647436422397555e-05, "loss": 3.5197, "step": 1243136 }, { "epoch": 0.01, "learning_rate": 2.9639050474887035e-05, "loss": 3.5276, "step": 1243648 }, { "epoch": 0.01, "learning_rate": 2.963066452737652e-05, "loss": 3.5297, "step": 1244160 }, { "epoch": 0.01, "learning_rate": 2.9622278579866e-05, "loss": 3.5277, "step": 1244672 }, { "epoch": 0.01, "learning_rate": 2.9613909011159208e-05, "loss": 3.5238, "step": 1245184 }, { "epoch": 0.01, "learning_rate": 2.9605523063648688e-05, "loss": 3.4988, "step": 1245696 }, { "epoch": 0.01, "learning_rate": 2.9597137116138167e-05, "loss": 3.5178, "step": 1246208 }, { "epoch": 0.01, "learning_rate": 2.9588751168627647e-05, "loss": 3.5237, "step": 1246720 }, { "epoch": 0.01, "learning_rate": 2.958038159992086e-05, "loss": 3.5294, "step": 1247232 }, { "epoch": 0.01, "learning_rate": 2.957199565241034e-05, "loss": 3.5164, "step": 1247744 }, { "epoch": 0.01, "learning_rate": 2.956360970489982e-05, "loss": 3.5012, "step": 1248256 }, { "epoch": 0.01, "learning_rate": 2.95552237573893e-05, "loss": 3.5099, "step": 1248768 }, { "epoch": 0.01, "learning_rate": 2.954683780987878e-05, "loss": 3.5024, "step": 1249280 }, { "epoch": 0.01, "learning_rate": 2.953846824117199e-05, "loss": 3.5334, "step": 1249792 }, { "epoch": 0.01, "learning_rate": 2.9530082293661472e-05, "loss": 3.5077, "step": 1250304 }, { "epoch": 0.01, "learning_rate": 2.9521696346150952e-05, "loss": 3.5238, "step": 1250816 }, { "epoch": 0.01, "learning_rate": 2.9513310398640432e-05, "loss": 3.5223, "step": 1251328 }, { "epoch": 0.01, "learning_rate": 2.950494082993364e-05, "loss": 3.5074, "step": 1251840 }, { "epoch": 0.01, "learning_rate": 2.949655488242312e-05, "loss": 3.5224, "step": 1252352 }, { "epoch": 0.01, "learning_rate": 2.94881689349126e-05, "loss": 3.5131, "step": 1252864 }, { "epoch": 0.01, "learning_rate": 2.947978298740208e-05, "loss": 3.5062, "step": 1253376 }, { "epoch": 0.01, "learning_rate": 2.9471397039891564e-05, "loss": 3.5046, "step": 1253888 }, { "epoch": 0.01, "learning_rate": 2.9463027471184773e-05, "loss": 3.5321, "step": 1254400 }, { "epoch": 0.01, "learning_rate": 2.9454641523674253e-05, "loss": 3.5162, "step": 1254912 }, { "epoch": 0.01, "learning_rate": 2.9446255576163733e-05, "loss": 3.5084, "step": 1255424 }, { "epoch": 0.01, "learning_rate": 2.9437869628653213e-05, "loss": 3.506, "step": 1255936 }, { "epoch": 0.01, "learning_rate": 2.9429500059946426e-05, "loss": 3.5144, "step": 1256448 }, { "epoch": 0.01, "learning_rate": 2.9421114112435906e-05, "loss": 3.5252, "step": 1256960 }, { "epoch": 0.01, "learning_rate": 2.9412728164925386e-05, "loss": 3.5239, "step": 1257472 }, { "epoch": 0.01, "learning_rate": 2.9404342217414866e-05, "loss": 3.5242, "step": 1257984 }, { "epoch": 0.01, "learning_rate": 2.9395972648708075e-05, "loss": 3.5288, "step": 1258496 }, { "epoch": 0.01, "learning_rate": 2.9387586701197555e-05, "loss": 3.5326, "step": 1259008 }, { "epoch": 0.01, "learning_rate": 2.9379200753687035e-05, "loss": 3.5272, "step": 1259520 }, { "epoch": 0.01, "learning_rate": 2.9370814806176518e-05, "loss": 3.5248, "step": 1260032 }, { "epoch": 0.01, "learning_rate": 2.9362445237469727e-05, "loss": 3.5156, "step": 1260544 }, { "epoch": 0.01, "learning_rate": 2.9354059289959207e-05, "loss": 3.5214, "step": 1261056 }, { "epoch": 0.01, "learning_rate": 2.9345673342448687e-05, "loss": 3.5189, "step": 1261568 }, { "epoch": 0.01, "learning_rate": 2.9337287394938164e-05, "loss": 3.517, "step": 1262080 }, { "epoch": 0.01, "learning_rate": 2.932891782623138e-05, "loss": 3.5219, "step": 1262592 }, { "epoch": 0.01, "learning_rate": 2.932053187872086e-05, "loss": 3.5275, "step": 1263104 }, { "epoch": 0.01, "learning_rate": 2.931214593121034e-05, "loss": 3.5248, "step": 1263616 }, { "epoch": 0.01, "learning_rate": 2.9303759983699813e-05, "loss": 3.5041, "step": 1264128 }, { "epoch": 0.01, "learning_rate": 2.929539041499303e-05, "loss": 3.5076, "step": 1264640 }, { "epoch": 0.01, "learning_rate": 2.928700446748251e-05, "loss": 3.5223, "step": 1265152 }, { "epoch": 0.01, "learning_rate": 2.927861851997199e-05, "loss": 3.5283, "step": 1265664 }, { "epoch": 0.01, "learning_rate": 2.9270232572461465e-05, "loss": 3.5121, "step": 1266176 }, { "epoch": 0.01, "learning_rate": 2.926186300375468e-05, "loss": 3.5233, "step": 1266688 }, { "epoch": 0.02, "learning_rate": 2.925347705624416e-05, "loss": 3.5245, "step": 1267200 }, { "epoch": 0.02, "learning_rate": 2.9245091108733634e-05, "loss": 3.5071, "step": 1267712 }, { "epoch": 0.02, "learning_rate": 2.9236705161223117e-05, "loss": 3.512, "step": 1268224 }, { "epoch": 0.02, "learning_rate": 2.9228335592516333e-05, "loss": 3.52, "step": 1268736 }, { "epoch": 0.02, "learning_rate": 2.9219949645005813e-05, "loss": 3.5203, "step": 1269248 }, { "epoch": 0.02, "learning_rate": 2.9211563697495286e-05, "loss": 3.5233, "step": 1269760 }, { "epoch": 0.02, "learning_rate": 2.9203177749984766e-05, "loss": 3.5194, "step": 1270272 }, { "epoch": 0.02, "learning_rate": 2.9194791802474246e-05, "loss": 3.5084, "step": 1270784 }, { "epoch": 0.02, "learning_rate": 2.9186422233767462e-05, "loss": 3.5243, "step": 1271296 }, { "epoch": 0.02, "learning_rate": 2.917803628625694e-05, "loss": 3.5244, "step": 1271808 }, { "epoch": 0.02, "learning_rate": 2.916965033874642e-05, "loss": 3.5198, "step": 1272320 }, { "epoch": 0.02, "learning_rate": 2.9161280770039634e-05, "loss": 3.5256, "step": 1272832 }, { "epoch": 0.02, "learning_rate": 2.9152894822529108e-05, "loss": 3.517, "step": 1273344 }, { "epoch": 0.02, "learning_rate": 2.9144508875018588e-05, "loss": 3.5215, "step": 1273856 }, { "epoch": 0.02, "learning_rate": 2.913612292750807e-05, "loss": 3.5262, "step": 1274368 }, { "epoch": 0.02, "learning_rate": 2.912773697999755e-05, "loss": 3.5034, "step": 1274880 }, { "epoch": 0.02, "learning_rate": 2.911936741129076e-05, "loss": 3.5089, "step": 1275392 }, { "epoch": 0.02, "learning_rate": 2.911098146378024e-05, "loss": 3.5206, "step": 1275904 }, { "epoch": 0.02, "learning_rate": 2.910259551626972e-05, "loss": 3.5189, "step": 1276416 }, { "epoch": 0.02, "learning_rate": 2.90942095687592e-05, "loss": 3.5011, "step": 1276928 }, { "epoch": 0.02, "learning_rate": 2.9085840000052412e-05, "loss": 3.5129, "step": 1277440 }, { "epoch": 0.02, "learning_rate": 2.9077454052541892e-05, "loss": 3.5054, "step": 1277952 }, { "epoch": 0.02, "learning_rate": 2.9069068105031372e-05, "loss": 3.5173, "step": 1278464 }, { "epoch": 0.02, "learning_rate": 2.9060682157520852e-05, "loss": 3.5135, "step": 1278976 }, { "epoch": 0.02, "learning_rate": 2.905231258881406e-05, "loss": 3.5174, "step": 1279488 }, { "epoch": 0.02, "learning_rate": 2.904392664130354e-05, "loss": 3.515, "step": 1280000 }, { "epoch": 0.02, "learning_rate": 2.9035540693793025e-05, "loss": 3.5256, "step": 1280512 }, { "epoch": 0.02, "learning_rate": 2.9027154746282505e-05, "loss": 3.5207, "step": 1281024 }, { "epoch": 0.02, "learning_rate": 2.9018785177575714e-05, "loss": 3.5238, "step": 1281536 }, { "epoch": 0.02, "learning_rate": 2.9010399230065194e-05, "loss": 3.5245, "step": 1282048 }, { "epoch": 0.02, "learning_rate": 2.9002013282554674e-05, "loss": 3.5204, "step": 1282560 }, { "epoch": 0.02, "learning_rate": 2.8993627335044154e-05, "loss": 3.5076, "step": 1283072 }, { "epoch": 0.02, "learning_rate": 2.8985257766337366e-05, "loss": 3.5189, "step": 1283584 }, { "epoch": 0.02, "learning_rate": 2.8976871818826846e-05, "loss": 3.5151, "step": 1284096 }, { "epoch": 0.02, "learning_rate": 2.8968485871316326e-05, "loss": 3.5258, "step": 1284608 }, { "epoch": 0.02, "learning_rate": 2.8960099923805806e-05, "loss": 3.5062, "step": 1285120 }, { "epoch": 0.02, "learning_rate": 2.8951730355099015e-05, "loss": 3.5179, "step": 1285632 }, { "epoch": 0.02, "learning_rate": 2.8943344407588495e-05, "loss": 3.5054, "step": 1286144 }, { "epoch": 0.02, "learning_rate": 2.893495846007798e-05, "loss": 3.507, "step": 1286656 }, { "epoch": 0.02, "learning_rate": 2.8926572512567458e-05, "loss": 3.5041, "step": 1287168 }, { "epoch": 0.02, "learning_rate": 2.8918202943860667e-05, "loss": 3.529, "step": 1287680 }, { "epoch": 0.02, "learning_rate": 2.8909816996350147e-05, "loss": 3.5257, "step": 1288192 }, { "epoch": 0.02, "learning_rate": 2.8901431048839627e-05, "loss": 3.5104, "step": 1288704 }, { "epoch": 0.02, "learning_rate": 2.8893045101329107e-05, "loss": 3.5158, "step": 1289216 }, { "epoch": 0.02, "learning_rate": 2.888467553262232e-05, "loss": 3.5183, "step": 1289728 }, { "epoch": 0.02, "learning_rate": 2.88762895851118e-05, "loss": 3.5249, "step": 1290240 }, { "epoch": 0.02, "learning_rate": 2.886790363760128e-05, "loss": 3.5232, "step": 1290752 }, { "epoch": 0.02, "learning_rate": 2.885951769009076e-05, "loss": 3.5131, "step": 1291264 }, { "epoch": 0.02, "learning_rate": 2.885114812138397e-05, "loss": 3.5264, "step": 1291776 }, { "epoch": 0.02, "learning_rate": 2.884276217387345e-05, "loss": 3.5084, "step": 1292288 }, { "epoch": 0.02, "learning_rate": 2.883437622636293e-05, "loss": 3.5276, "step": 1292800 }, { "epoch": 0.02, "learning_rate": 2.8825990278852412e-05, "loss": 3.5182, "step": 1293312 }, { "epoch": 0.02, "learning_rate": 2.881762071014562e-05, "loss": 3.5168, "step": 1293824 }, { "epoch": 0.02, "learning_rate": 2.88092347626351e-05, "loss": 3.5175, "step": 1294336 }, { "epoch": 0.02, "learning_rate": 2.880084881512458e-05, "loss": 3.5087, "step": 1294848 }, { "epoch": 0.02, "learning_rate": 2.879246286761406e-05, "loss": 3.5203, "step": 1295360 }, { "epoch": 0.02, "learning_rate": 2.8784093298907273e-05, "loss": 3.5196, "step": 1295872 }, { "epoch": 0.02, "learning_rate": 2.8775707351396753e-05, "loss": 3.5195, "step": 1296384 }, { "epoch": 0.02, "learning_rate": 2.8767321403886233e-05, "loss": 3.5149, "step": 1296896 }, { "epoch": 0.02, "learning_rate": 2.8758935456375713e-05, "loss": 3.5134, "step": 1297408 }, { "epoch": 0.03, "eval_loss": 3.847564935684204, "eval_runtime": 302.8108, "eval_samples_per_second": 1260.163, "eval_steps_per_second": 39.381, "step": 1297440 }, { "epoch": 1.0, "learning_rate": 2.8750565887668922e-05, "loss": 3.5064, "step": 1297920 }, { "epoch": 1.0, "learning_rate": 2.8742179940158402e-05, "loss": 3.5062, "step": 1298432 }, { "epoch": 1.0, "learning_rate": 2.8733793992647882e-05, "loss": 3.5218, "step": 1298944 }, { "epoch": 1.0, "learning_rate": 2.8725408045137366e-05, "loss": 3.5118, "step": 1299456 }, { "epoch": 1.0, "learning_rate": 2.8717038476430575e-05, "loss": 3.5296, "step": 1299968 }, { "epoch": 1.0, "learning_rate": 2.8708652528920055e-05, "loss": 3.505, "step": 1300480 }, { "epoch": 1.0, "learning_rate": 2.8700266581409535e-05, "loss": 3.5146, "step": 1300992 }, { "epoch": 1.0, "learning_rate": 2.8691880633899015e-05, "loss": 3.5008, "step": 1301504 }, { "epoch": 1.0, "learning_rate": 2.8683511065192227e-05, "loss": 3.5166, "step": 1302016 }, { "epoch": 1.0, "learning_rate": 2.8675125117681707e-05, "loss": 3.5121, "step": 1302528 }, { "epoch": 1.0, "learning_rate": 2.8666739170171187e-05, "loss": 3.5149, "step": 1303040 }, { "epoch": 1.0, "learning_rate": 2.8658353222660667e-05, "loss": 3.5145, "step": 1303552 }, { "epoch": 1.0, "learning_rate": 2.8649983653953876e-05, "loss": 3.5072, "step": 1304064 }, { "epoch": 1.0, "learning_rate": 2.8641597706443356e-05, "loss": 3.5043, "step": 1304576 }, { "epoch": 1.0, "learning_rate": 2.8633211758932836e-05, "loss": 3.5066, "step": 1305088 }, { "epoch": 1.0, "learning_rate": 2.862482581142232e-05, "loss": 3.4986, "step": 1305600 }, { "epoch": 1.0, "learning_rate": 2.86164398639118e-05, "loss": 3.5105, "step": 1306112 }, { "epoch": 1.0, "learning_rate": 2.860805391640128e-05, "loss": 3.5098, "step": 1306624 }, { "epoch": 1.0, "learning_rate": 2.859966796889076e-05, "loss": 3.5062, "step": 1307136 }, { "epoch": 1.0, "learning_rate": 2.8591298400183968e-05, "loss": 3.5271, "step": 1307648 }, { "epoch": 1.0, "learning_rate": 2.8582912452673448e-05, "loss": 3.5073, "step": 1308160 }, { "epoch": 1.0, "learning_rate": 2.8574526505162928e-05, "loss": 3.515, "step": 1308672 }, { "epoch": 1.0, "learning_rate": 2.856614055765241e-05, "loss": 3.5128, "step": 1309184 }, { "epoch": 1.0, "learning_rate": 2.855775461014189e-05, "loss": 3.5206, "step": 1309696 }, { "epoch": 1.0, "learning_rate": 2.85493850414351e-05, "loss": 3.5026, "step": 1310208 }, { "epoch": 1.0, "learning_rate": 2.854099909392458e-05, "loss": 3.5125, "step": 1310720 }, { "epoch": 1.0, "learning_rate": 2.853261314641406e-05, "loss": 3.5043, "step": 1311232 }, { "epoch": 1.0, "learning_rate": 2.852422719890354e-05, "loss": 3.513, "step": 1311744 }, { "epoch": 1.0, "learning_rate": 2.8515857630196753e-05, "loss": 3.4974, "step": 1312256 }, { "epoch": 1.01, "learning_rate": 2.8507471682686233e-05, "loss": 3.5029, "step": 1312768 }, { "epoch": 1.01, "learning_rate": 2.8499085735175713e-05, "loss": 3.5176, "step": 1313280 }, { "epoch": 1.01, "learning_rate": 2.8490699787665186e-05, "loss": 3.512, "step": 1313792 }, { "epoch": 1.01, "learning_rate": 2.8482330218958402e-05, "loss": 3.5124, "step": 1314304 }, { "epoch": 1.01, "learning_rate": 2.8473944271447882e-05, "loss": 3.5168, "step": 1314816 }, { "epoch": 1.01, "learning_rate": 2.8465558323937365e-05, "loss": 3.511, "step": 1315328 }, { "epoch": 1.01, "learning_rate": 2.845717237642684e-05, "loss": 3.5117, "step": 1315840 }, { "epoch": 1.01, "learning_rate": 2.8448802807720054e-05, "loss": 3.5069, "step": 1316352 }, { "epoch": 1.01, "learning_rate": 2.8440416860209534e-05, "loss": 3.5156, "step": 1316864 }, { "epoch": 1.01, "learning_rate": 2.8432030912699014e-05, "loss": 3.5019, "step": 1317376 }, { "epoch": 1.01, "learning_rate": 2.842364496518849e-05, "loss": 3.51, "step": 1317888 }, { "epoch": 1.01, "learning_rate": 2.841525901767797e-05, "loss": 3.5104, "step": 1318400 }, { "epoch": 1.01, "learning_rate": 2.8406889448971187e-05, "loss": 3.5179, "step": 1318912 }, { "epoch": 1.01, "learning_rate": 2.839850350146066e-05, "loss": 3.5051, "step": 1319424 }, { "epoch": 1.01, "learning_rate": 2.839011755395014e-05, "loss": 3.5123, "step": 1319936 }, { "epoch": 1.01, "learning_rate": 2.838173160643962e-05, "loss": 3.5184, "step": 1320448 }, { "epoch": 1.01, "learning_rate": 2.8373362037732835e-05, "loss": 3.5138, "step": 1320960 }, { "epoch": 1.01, "learning_rate": 2.8364976090222312e-05, "loss": 3.5116, "step": 1321472 }, { "epoch": 1.01, "learning_rate": 2.8356590142711792e-05, "loss": 3.4859, "step": 1321984 }, { "epoch": 1.01, "learning_rate": 2.8348204195201272e-05, "loss": 3.5013, "step": 1322496 }, { "epoch": 1.01, "learning_rate": 2.8339834626494488e-05, "loss": 3.5147, "step": 1323008 }, { "epoch": 1.01, "learning_rate": 2.8331448678983964e-05, "loss": 3.5106, "step": 1323520 }, { "epoch": 1.01, "learning_rate": 2.8323062731473444e-05, "loss": 3.5063, "step": 1324032 }, { "epoch": 1.01, "learning_rate": 2.8314676783962924e-05, "loss": 3.4886, "step": 1324544 }, { "epoch": 1.01, "learning_rate": 2.8306307215256133e-05, "loss": 3.497, "step": 1325056 }, { "epoch": 1.01, "learning_rate": 2.8297921267745613e-05, "loss": 3.4884, "step": 1325568 }, { "epoch": 1.01, "learning_rate": 2.8289535320235093e-05, "loss": 3.5163, "step": 1326080 }, { "epoch": 1.01, "learning_rate": 2.8281149372724573e-05, "loss": 3.4966, "step": 1326592 }, { "epoch": 1.01, "learning_rate": 2.8272779804017786e-05, "loss": 3.5091, "step": 1327104 }, { "epoch": 1.01, "learning_rate": 2.8264393856507266e-05, "loss": 3.5093, "step": 1327616 }, { "epoch": 1.01, "learning_rate": 2.8256007908996746e-05, "loss": 3.4959, "step": 1328128 }, { "epoch": 1.01, "learning_rate": 2.8247621961486226e-05, "loss": 3.5066, "step": 1328640 }, { "epoch": 1.01, "learning_rate": 2.8239252392779435e-05, "loss": 3.4972, "step": 1329152 }, { "epoch": 1.01, "learning_rate": 2.8230866445268918e-05, "loss": 3.497, "step": 1329664 }, { "epoch": 1.01, "learning_rate": 2.8222480497758398e-05, "loss": 3.4935, "step": 1330176 }, { "epoch": 1.01, "learning_rate": 2.8214094550247878e-05, "loss": 3.5125, "step": 1330688 }, { "epoch": 1.01, "learning_rate": 2.8205724981541087e-05, "loss": 3.504, "step": 1331200 }, { "epoch": 1.01, "learning_rate": 2.8197339034030567e-05, "loss": 3.4935, "step": 1331712 }, { "epoch": 1.01, "learning_rate": 2.8188953086520047e-05, "loss": 3.4951, "step": 1332224 }, { "epoch": 1.01, "learning_rate": 2.8180567139009527e-05, "loss": 3.4982, "step": 1332736 }, { "epoch": 1.01, "learning_rate": 2.817219757030274e-05, "loss": 3.5116, "step": 1333248 }, { "epoch": 1.01, "learning_rate": 2.816381162279222e-05, "loss": 3.5088, "step": 1333760 }, { "epoch": 1.01, "learning_rate": 2.81554256752817e-05, "loss": 3.5108, "step": 1334272 }, { "epoch": 1.01, "learning_rate": 2.814703972777118e-05, "loss": 3.5209, "step": 1334784 }, { "epoch": 1.01, "learning_rate": 2.813867015906439e-05, "loss": 3.5154, "step": 1335296 }, { "epoch": 1.01, "learning_rate": 2.8130284211553872e-05, "loss": 3.518, "step": 1335808 }, { "epoch": 1.01, "learning_rate": 2.812189826404335e-05, "loss": 3.5093, "step": 1336320 }, { "epoch": 1.01, "learning_rate": 2.811351231653283e-05, "loss": 3.5041, "step": 1336832 }, { "epoch": 1.01, "learning_rate": 2.810514274782604e-05, "loss": 3.5093, "step": 1337344 }, { "epoch": 1.01, "learning_rate": 2.809675680031552e-05, "loss": 3.5041, "step": 1337856 }, { "epoch": 1.01, "learning_rate": 2.8088370852805e-05, "loss": 3.5033, "step": 1338368 }, { "epoch": 1.01, "learning_rate": 2.807998490529448e-05, "loss": 3.5093, "step": 1338880 }, { "epoch": 1.01, "learning_rate": 2.8071615336587693e-05, "loss": 3.5168, "step": 1339392 }, { "epoch": 1.01, "learning_rate": 2.8063229389077173e-05, "loss": 3.5067, "step": 1339904 }, { "epoch": 1.01, "learning_rate": 2.8054843441566653e-05, "loss": 3.4952, "step": 1340416 }, { "epoch": 1.01, "learning_rate": 2.8046457494056133e-05, "loss": 3.4927, "step": 1340928 }, { "epoch": 1.01, "learning_rate": 2.8038071546545613e-05, "loss": 3.5054, "step": 1341440 }, { "epoch": 1.01, "learning_rate": 2.8029701977838822e-05, "loss": 3.5155, "step": 1341952 }, { "epoch": 1.01, "learning_rate": 2.8021316030328305e-05, "loss": 3.4997, "step": 1342464 }, { "epoch": 1.01, "learning_rate": 2.8012930082817785e-05, "loss": 3.5071, "step": 1342976 }, { "epoch": 1.02, "learning_rate": 2.8004544135307265e-05, "loss": 3.5109, "step": 1343488 }, { "epoch": 1.02, "learning_rate": 2.7996174566600474e-05, "loss": 3.4978, "step": 1344000 }, { "epoch": 1.02, "learning_rate": 2.7987788619089954e-05, "loss": 3.5001, "step": 1344512 }, { "epoch": 1.02, "learning_rate": 2.7979402671579434e-05, "loss": 3.5019, "step": 1345024 }, { "epoch": 1.02, "learning_rate": 2.7971016724068914e-05, "loss": 3.5085, "step": 1345536 }, { "epoch": 1.02, "learning_rate": 2.7962630776558398e-05, "loss": 3.5096, "step": 1346048 }, { "epoch": 1.02, "learning_rate": 2.7954261207851607e-05, "loss": 3.5101, "step": 1346560 }, { "epoch": 1.02, "learning_rate": 2.7945875260341087e-05, "loss": 3.495, "step": 1347072 }, { "epoch": 1.02, "learning_rate": 2.7937489312830567e-05, "loss": 3.5112, "step": 1347584 }, { "epoch": 1.02, "learning_rate": 2.7929103365320047e-05, "loss": 3.5057, "step": 1348096 }, { "epoch": 1.02, "learning_rate": 2.792073379661326e-05, "loss": 3.5124, "step": 1348608 }, { "epoch": 1.02, "learning_rate": 2.791234784910274e-05, "loss": 3.5072, "step": 1349120 }, { "epoch": 1.02, "learning_rate": 2.790396190159222e-05, "loss": 3.508, "step": 1349632 }, { "epoch": 1.02, "learning_rate": 2.78955759540817e-05, "loss": 3.5076, "step": 1350144 }, { "epoch": 1.02, "learning_rate": 2.7887206385374908e-05, "loss": 3.513, "step": 1350656 }, { "epoch": 1.02, "learning_rate": 2.7878820437864388e-05, "loss": 3.4892, "step": 1351168 }, { "epoch": 1.02, "learning_rate": 2.7870434490353868e-05, "loss": 3.4986, "step": 1351680 }, { "epoch": 1.02, "learning_rate": 2.786204854284335e-05, "loss": 3.5043, "step": 1352192 }, { "epoch": 1.02, "learning_rate": 2.785367897413656e-05, "loss": 3.5041, "step": 1352704 }, { "epoch": 1.02, "learning_rate": 2.784529302662604e-05, "loss": 3.4902, "step": 1353216 }, { "epoch": 1.02, "learning_rate": 2.783690707911552e-05, "loss": 3.4983, "step": 1353728 }, { "epoch": 1.02, "learning_rate": 2.7828521131605e-05, "loss": 3.4927, "step": 1354240 }, { "epoch": 1.02, "learning_rate": 2.7820151562898213e-05, "loss": 3.5028, "step": 1354752 }, { "epoch": 1.02, "learning_rate": 2.7811765615387693e-05, "loss": 3.4965, "step": 1355264 }, { "epoch": 1.02, "learning_rate": 2.7803379667877173e-05, "loss": 3.5028, "step": 1355776 }, { "epoch": 1.02, "learning_rate": 2.7794993720366653e-05, "loss": 3.5039, "step": 1356288 }, { "epoch": 1.02, "learning_rate": 2.778662415165986e-05, "loss": 3.5125, "step": 1356800 }, { "epoch": 1.02, "learning_rate": 2.777823820414934e-05, "loss": 3.5075, "step": 1357312 }, { "epoch": 1.02, "learning_rate": 2.776985225663882e-05, "loss": 3.5051, "step": 1357824 }, { "epoch": 1.02, "learning_rate": 2.7761466309128305e-05, "loss": 3.5145, "step": 1358336 }, { "epoch": 1.02, "learning_rate": 2.7753096740421514e-05, "loss": 3.5068, "step": 1358848 }, { "epoch": 1.02, "learning_rate": 2.7744710792910994e-05, "loss": 3.495, "step": 1359360 }, { "epoch": 1.02, "learning_rate": 2.7736324845400474e-05, "loss": 3.5093, "step": 1359872 }, { "epoch": 1.02, "learning_rate": 2.7727938897889954e-05, "loss": 3.5004, "step": 1360384 }, { "epoch": 1.02, "learning_rate": 2.7719552950379434e-05, "loss": 3.511, "step": 1360896 }, { "epoch": 1.02, "learning_rate": 2.7711183381672646e-05, "loss": 3.491, "step": 1361408 }, { "epoch": 1.02, "learning_rate": 2.7702797434162126e-05, "loss": 3.5075, "step": 1361920 }, { "epoch": 1.02, "learning_rate": 2.7694411486651606e-05, "loss": 3.4911, "step": 1362432 }, { "epoch": 1.02, "learning_rate": 2.7686025539141086e-05, "loss": 3.4933, "step": 1362944 }, { "epoch": 1.02, "learning_rate": 2.7677655970434295e-05, "loss": 3.4918, "step": 1363456 }, { "epoch": 1.02, "learning_rate": 2.7669270022923775e-05, "loss": 3.5149, "step": 1363968 }, { "epoch": 1.02, "learning_rate": 2.766088407541326e-05, "loss": 3.5117, "step": 1364480 }, { "epoch": 1.02, "learning_rate": 2.765249812790274e-05, "loss": 3.5012, "step": 1364992 }, { "epoch": 1.02, "learning_rate": 2.7644128559195948e-05, "loss": 3.4982, "step": 1365504 }, { "epoch": 1.02, "learning_rate": 2.7635742611685428e-05, "loss": 3.507, "step": 1366016 }, { "epoch": 1.02, "learning_rate": 2.7627356664174908e-05, "loss": 3.5106, "step": 1366528 }, { "epoch": 1.02, "learning_rate": 2.7618970716664387e-05, "loss": 3.5055, "step": 1367040 }, { "epoch": 1.02, "learning_rate": 2.76106011479576e-05, "loss": 3.5028, "step": 1367552 }, { "epoch": 1.02, "learning_rate": 2.760221520044708e-05, "loss": 3.5102, "step": 1368064 }, { "epoch": 1.02, "learning_rate": 2.759382925293656e-05, "loss": 3.5007, "step": 1368576 }, { "epoch": 1.02, "learning_rate": 2.7585443305426033e-05, "loss": 3.5149, "step": 1369088 }, { "epoch": 1.02, "learning_rate": 2.757707373671925e-05, "loss": 3.5024, "step": 1369600 }, { "epoch": 1.02, "learning_rate": 2.756868778920873e-05, "loss": 3.5036, "step": 1370112 }, { "epoch": 1.02, "learning_rate": 2.7560301841698212e-05, "loss": 3.5016, "step": 1370624 }, { "epoch": 1.02, "learning_rate": 2.7551915894187685e-05, "loss": 3.4963, "step": 1371136 }, { "epoch": 1.02, "learning_rate": 2.7543529946677165e-05, "loss": 3.5078, "step": 1371648 }, { "epoch": 1.02, "learning_rate": 2.753516037797038e-05, "loss": 3.5033, "step": 1372160 }, { "epoch": 1.02, "learning_rate": 2.752677443045986e-05, "loss": 3.5077, "step": 1372672 }, { "epoch": 1.02, "learning_rate": 2.7518388482949338e-05, "loss": 3.4999, "step": 1373184 }, { "epoch": 1.02, "learning_rate": 2.7510002535438818e-05, "loss": 3.5002, "step": 1373696 }, { "epoch": 1.03, "eval_loss": 3.849041223526001, "eval_runtime": 301.6776, "eval_samples_per_second": 1264.897, "eval_steps_per_second": 39.529, "step": 1373760 }, { "epoch": 0.0, "learning_rate": 2.7501616587928298e-05, "loss": 3.4943, "step": 1374208 }, { "epoch": 0.0, "learning_rate": 2.7493230640417778e-05, "loss": 3.4936, "step": 1374720 }, { "epoch": 0.0, "learning_rate": 2.7484844692907258e-05, "loss": 3.506, "step": 1375232 }, { "epoch": 0.0, "learning_rate": 2.7476458745396738e-05, "loss": 3.4962, "step": 1375744 }, { "epoch": 0.0, "learning_rate": 2.746808917668995e-05, "loss": 3.5186, "step": 1376256 }, { "epoch": 0.0, "learning_rate": 2.745970322917943e-05, "loss": 3.4926, "step": 1376768 }, { "epoch": 0.0, "learning_rate": 2.745131728166891e-05, "loss": 3.4999, "step": 1377280 }, { "epoch": 0.0, "learning_rate": 2.744293133415839e-05, "loss": 3.4869, "step": 1377792 }, { "epoch": 0.0, "learning_rate": 2.74345617654516e-05, "loss": 3.5035, "step": 1378304 }, { "epoch": 0.0, "learning_rate": 2.742617581794108e-05, "loss": 3.4991, "step": 1378816 }, { "epoch": 0.0, "learning_rate": 2.741778987043056e-05, "loss": 3.5003, "step": 1379328 }, { "epoch": 0.0, "learning_rate": 2.7409403922920042e-05, "loss": 3.4984, "step": 1379840 }, { "epoch": 0.0, "learning_rate": 2.740105073301698e-05, "loss": 3.4935, "step": 1380352 }, { "epoch": 0.0, "learning_rate": 2.739266478550646e-05, "loss": 3.4931, "step": 1380864 }, { "epoch": 0.0, "learning_rate": 2.738427883799594e-05, "loss": 3.495, "step": 1381376 }, { "epoch": 0.0, "learning_rate": 2.737589289048542e-05, "loss": 3.4892, "step": 1381888 }, { "epoch": 0.0, "learning_rate": 2.7367506942974904e-05, "loss": 3.494, "step": 1382400 }, { "epoch": 0.0, "learning_rate": 2.7359120995464384e-05, "loss": 3.4992, "step": 1382912 }, { "epoch": 0.0, "learning_rate": 2.7350735047953864e-05, "loss": 3.4934, "step": 1383424 }, { "epoch": 0.0, "learning_rate": 2.7342365479247073e-05, "loss": 3.5143, "step": 1383936 }, { "epoch": 0.0, "learning_rate": 2.7333979531736553e-05, "loss": 3.4959, "step": 1384448 }, { "epoch": 0.0, "learning_rate": 2.7325593584226033e-05, "loss": 3.4993, "step": 1384960 }, { "epoch": 0.0, "learning_rate": 2.7317207636715513e-05, "loss": 3.4996, "step": 1385472 }, { "epoch": 0.0, "learning_rate": 2.7308821689204993e-05, "loss": 3.5075, "step": 1385984 }, { "epoch": 0.0, "learning_rate": 2.7300452120498205e-05, "loss": 3.4916, "step": 1386496 }, { "epoch": 0.0, "learning_rate": 2.7292066172987685e-05, "loss": 3.5001, "step": 1387008 }, { "epoch": 0.0, "learning_rate": 2.7283680225477165e-05, "loss": 3.4919, "step": 1387520 }, { "epoch": 0.0, "learning_rate": 2.7275294277966645e-05, "loss": 3.5004, "step": 1388032 }, { "epoch": 0.0, "learning_rate": 2.7266924709259854e-05, "loss": 3.4836, "step": 1388544 }, { "epoch": 0.01, "learning_rate": 2.7258538761749337e-05, "loss": 3.4878, "step": 1389056 }, { "epoch": 0.01, "learning_rate": 2.7250152814238817e-05, "loss": 3.5035, "step": 1389568 }, { "epoch": 0.01, "learning_rate": 2.7241766866728297e-05, "loss": 3.4999, "step": 1390080 }, { "epoch": 0.01, "learning_rate": 2.7233397298021506e-05, "loss": 3.5002, "step": 1390592 }, { "epoch": 0.01, "learning_rate": 2.7225011350510986e-05, "loss": 3.5049, "step": 1391104 }, { "epoch": 0.01, "learning_rate": 2.7216625403000466e-05, "loss": 3.4965, "step": 1391616 }, { "epoch": 0.01, "learning_rate": 2.7208239455489946e-05, "loss": 3.5008, "step": 1392128 }, { "epoch": 0.01, "learning_rate": 2.719986988678316e-05, "loss": 3.4911, "step": 1392640 }, { "epoch": 0.01, "learning_rate": 2.719148393927264e-05, "loss": 3.5057, "step": 1393152 }, { "epoch": 0.01, "learning_rate": 2.718309799176212e-05, "loss": 3.4895, "step": 1393664 }, { "epoch": 0.01, "learning_rate": 2.71747120442516e-05, "loss": 3.4951, "step": 1394176 }, { "epoch": 0.01, "learning_rate": 2.716632609674108e-05, "loss": 3.4948, "step": 1394688 }, { "epoch": 0.01, "learning_rate": 2.715795652803429e-05, "loss": 3.5059, "step": 1395200 }, { "epoch": 0.01, "learning_rate": 2.714957058052377e-05, "loss": 3.4976, "step": 1395712 }, { "epoch": 0.01, "learning_rate": 2.714118463301325e-05, "loss": 3.4939, "step": 1396224 }, { "epoch": 0.01, "learning_rate": 2.713279868550273e-05, "loss": 3.5036, "step": 1396736 }, { "epoch": 0.01, "learning_rate": 2.712442911679594e-05, "loss": 3.5022, "step": 1397248 }, { "epoch": 0.01, "learning_rate": 2.711604316928542e-05, "loss": 3.4972, "step": 1397760 }, { "epoch": 0.01, "learning_rate": 2.71076572217749e-05, "loss": 3.4817, "step": 1398272 }, { "epoch": 0.01, "learning_rate": 2.7099271274264383e-05, "loss": 3.4823, "step": 1398784 }, { "epoch": 0.01, "learning_rate": 2.7090885326753863e-05, "loss": 3.4973, "step": 1399296 }, { "epoch": 0.01, "learning_rate": 2.7082515758047072e-05, "loss": 3.4979, "step": 1399808 }, { "epoch": 0.01, "learning_rate": 2.7074129810536552e-05, "loss": 3.4954, "step": 1400320 }, { "epoch": 0.01, "learning_rate": 2.7065743863026032e-05, "loss": 3.4759, "step": 1400832 }, { "epoch": 0.01, "learning_rate": 2.7057357915515512e-05, "loss": 3.4836, "step": 1401344 }, { "epoch": 0.01, "learning_rate": 2.7048988346808725e-05, "loss": 3.481, "step": 1401856 }, { "epoch": 0.01, "learning_rate": 2.7040602399298205e-05, "loss": 3.4948, "step": 1402368 }, { "epoch": 0.01, "learning_rate": 2.7032216451787685e-05, "loss": 3.4848, "step": 1402880 }, { "epoch": 0.01, "learning_rate": 2.7023830504277164e-05, "loss": 3.497, "step": 1403392 }, { "epoch": 0.01, "learning_rate": 2.7015460935570374e-05, "loss": 3.4933, "step": 1403904 }, { "epoch": 0.01, "learning_rate": 2.7007074988059854e-05, "loss": 3.4863, "step": 1404416 }, { "epoch": 0.01, "learning_rate": 2.6998689040549337e-05, "loss": 3.4922, "step": 1404928 }, { "epoch": 0.01, "learning_rate": 2.6990303093038817e-05, "loss": 3.4874, "step": 1405440 }, { "epoch": 0.01, "learning_rate": 2.6981933524332026e-05, "loss": 3.479, "step": 1405952 }, { "epoch": 0.01, "learning_rate": 2.6973547576821506e-05, "loss": 3.4884, "step": 1406464 }, { "epoch": 0.01, "learning_rate": 2.6965161629310986e-05, "loss": 3.494, "step": 1406976 }, { "epoch": 0.01, "learning_rate": 2.6956775681800466e-05, "loss": 3.4996, "step": 1407488 }, { "epoch": 0.01, "learning_rate": 2.6948389734289942e-05, "loss": 3.4758, "step": 1408000 }, { "epoch": 0.01, "learning_rate": 2.6940020165583158e-05, "loss": 3.4839, "step": 1408512 }, { "epoch": 0.01, "learning_rate": 2.6931634218072638e-05, "loss": 3.4799, "step": 1409024 }, { "epoch": 0.01, "learning_rate": 2.692324827056211e-05, "loss": 3.5052, "step": 1409536 }, { "epoch": 0.01, "learning_rate": 2.691486232305159e-05, "loss": 3.493, "step": 1410048 }, { "epoch": 0.01, "learning_rate": 2.6906492754344807e-05, "loss": 3.4956, "step": 1410560 }, { "epoch": 0.01, "learning_rate": 2.689810680683429e-05, "loss": 3.5091, "step": 1411072 }, { "epoch": 0.01, "learning_rate": 2.6889720859323764e-05, "loss": 3.5038, "step": 1411584 }, { "epoch": 0.01, "learning_rate": 2.6881334911813244e-05, "loss": 3.5061, "step": 1412096 }, { "epoch": 0.01, "learning_rate": 2.687296534310646e-05, "loss": 3.4951, "step": 1412608 }, { "epoch": 0.01, "learning_rate": 2.686457939559594e-05, "loss": 3.4941, "step": 1413120 }, { "epoch": 0.01, "learning_rate": 2.6856193448085416e-05, "loss": 3.4954, "step": 1413632 }, { "epoch": 0.01, "learning_rate": 2.6847807500574896e-05, "loss": 3.4901, "step": 1414144 }, { "epoch": 0.01, "learning_rate": 2.6839437931868112e-05, "loss": 3.4935, "step": 1414656 }, { "epoch": 0.01, "learning_rate": 2.6831051984357585e-05, "loss": 3.4939, "step": 1415168 }, { "epoch": 0.01, "learning_rate": 2.6822666036847065e-05, "loss": 3.5026, "step": 1415680 }, { "epoch": 0.01, "learning_rate": 2.6814280089336545e-05, "loss": 3.4915, "step": 1416192 }, { "epoch": 0.01, "learning_rate": 2.680591052062976e-05, "loss": 3.4868, "step": 1416704 }, { "epoch": 0.01, "learning_rate": 2.6797524573119237e-05, "loss": 3.4784, "step": 1417216 }, { "epoch": 0.01, "learning_rate": 2.6789138625608717e-05, "loss": 3.4945, "step": 1417728 }, { "epoch": 0.01, "learning_rate": 2.6780752678098197e-05, "loss": 3.5006, "step": 1418240 }, { "epoch": 0.01, "learning_rate": 2.6772383109391413e-05, "loss": 3.4898, "step": 1418752 }, { "epoch": 0.01, "learning_rate": 2.676399716188089e-05, "loss": 3.4927, "step": 1419264 }, { "epoch": 0.02, "learning_rate": 2.675561121437037e-05, "loss": 3.5016, "step": 1419776 }, { "epoch": 0.02, "learning_rate": 2.674722526685985e-05, "loss": 3.4794, "step": 1420288 }, { "epoch": 0.02, "learning_rate": 2.673885569815306e-05, "loss": 3.4905, "step": 1420800 }, { "epoch": 0.02, "learning_rate": 2.673046975064254e-05, "loss": 3.4875, "step": 1421312 }, { "epoch": 0.02, "learning_rate": 2.672208380313202e-05, "loss": 3.4975, "step": 1421824 }, { "epoch": 0.02, "learning_rate": 2.67136978556215e-05, "loss": 3.4981, "step": 1422336 }, { "epoch": 0.02, "learning_rate": 2.670532828691471e-05, "loss": 3.4949, "step": 1422848 }, { "epoch": 0.02, "learning_rate": 2.669694233940419e-05, "loss": 3.483, "step": 1423360 }, { "epoch": 0.02, "learning_rate": 2.668855639189367e-05, "loss": 3.4996, "step": 1423872 }, { "epoch": 0.02, "learning_rate": 2.668017044438315e-05, "loss": 3.489, "step": 1424384 }, { "epoch": 0.02, "learning_rate": 2.667180087567636e-05, "loss": 3.5075, "step": 1424896 }, { "epoch": 0.02, "learning_rate": 2.6663414928165843e-05, "loss": 3.495, "step": 1425408 }, { "epoch": 0.02, "learning_rate": 2.6655028980655323e-05, "loss": 3.4968, "step": 1425920 }, { "epoch": 0.02, "learning_rate": 2.6646643033144803e-05, "loss": 3.491, "step": 1426432 }, { "epoch": 0.02, "learning_rate": 2.6638273464438012e-05, "loss": 3.5038, "step": 1426944 }, { "epoch": 0.02, "learning_rate": 2.6629887516927492e-05, "loss": 3.475, "step": 1427456 }, { "epoch": 0.02, "learning_rate": 2.6621501569416972e-05, "loss": 3.4864, "step": 1427968 }, { "epoch": 0.02, "learning_rate": 2.6613115621906452e-05, "loss": 3.4898, "step": 1428480 }, { "epoch": 0.02, "learning_rate": 2.6604746053199665e-05, "loss": 3.4914, "step": 1428992 }, { "epoch": 0.02, "learning_rate": 2.6596360105689145e-05, "loss": 3.4771, "step": 1429504 }, { "epoch": 0.02, "learning_rate": 2.6587974158178625e-05, "loss": 3.4855, "step": 1430016 }, { "epoch": 0.02, "learning_rate": 2.6579588210668105e-05, "loss": 3.4786, "step": 1430528 }, { "epoch": 0.02, "learning_rate": 2.6571218641961314e-05, "loss": 3.4908, "step": 1431040 }, { "epoch": 0.02, "learning_rate": 2.6562832694450797e-05, "loss": 3.4855, "step": 1431552 }, { "epoch": 0.02, "learning_rate": 2.6554446746940277e-05, "loss": 3.4853, "step": 1432064 }, { "epoch": 0.02, "learning_rate": 2.6546060799429757e-05, "loss": 3.4964, "step": 1432576 }, { "epoch": 0.02, "learning_rate": 2.6537691230722966e-05, "loss": 3.5019, "step": 1433088 }, { "epoch": 0.02, "learning_rate": 2.6529305283212446e-05, "loss": 3.4954, "step": 1433600 }, { "epoch": 0.02, "learning_rate": 2.6520919335701926e-05, "loss": 3.4901, "step": 1434112 }, { "epoch": 0.02, "learning_rate": 2.6512533388191406e-05, "loss": 3.5028, "step": 1434624 }, { "epoch": 0.02, "learning_rate": 2.6504147440680886e-05, "loss": 3.4913, "step": 1435136 }, { "epoch": 0.02, "learning_rate": 2.64957778719741e-05, "loss": 3.4842, "step": 1435648 }, { "epoch": 0.02, "learning_rate": 2.648739192446358e-05, "loss": 3.4998, "step": 1436160 }, { "epoch": 0.02, "learning_rate": 2.647900597695306e-05, "loss": 3.4843, "step": 1436672 }, { "epoch": 0.02, "learning_rate": 2.6470636408246267e-05, "loss": 3.4986, "step": 1437184 }, { "epoch": 0.02, "learning_rate": 2.646225046073575e-05, "loss": 3.4807, "step": 1437696 }, { "epoch": 0.02, "learning_rate": 2.645386451322523e-05, "loss": 3.4945, "step": 1438208 }, { "epoch": 0.02, "learning_rate": 2.644547856571471e-05, "loss": 3.4789, "step": 1438720 }, { "epoch": 0.02, "learning_rate": 2.643710899700792e-05, "loss": 3.4817, "step": 1439232 }, { "epoch": 0.02, "learning_rate": 2.64287230494974e-05, "loss": 3.4825, "step": 1439744 }, { "epoch": 0.02, "learning_rate": 2.642033710198688e-05, "loss": 3.4997, "step": 1440256 }, { "epoch": 0.02, "learning_rate": 2.641195115447636e-05, "loss": 3.4959, "step": 1440768 }, { "epoch": 0.02, "learning_rate": 2.6403581585769572e-05, "loss": 3.4899, "step": 1441280 }, { "epoch": 0.02, "learning_rate": 2.6395195638259052e-05, "loss": 3.4872, "step": 1441792 }, { "epoch": 0.02, "learning_rate": 2.6386809690748532e-05, "loss": 3.4926, "step": 1442304 }, { "epoch": 0.02, "learning_rate": 2.6378423743238012e-05, "loss": 3.5044, "step": 1442816 }, { "epoch": 0.02, "learning_rate": 2.637005417453122e-05, "loss": 3.4894, "step": 1443328 }, { "epoch": 0.02, "learning_rate": 2.63616682270207e-05, "loss": 3.4895, "step": 1443840 }, { "epoch": 0.02, "learning_rate": 2.6353282279510184e-05, "loss": 3.4986, "step": 1444352 }, { "epoch": 0.02, "learning_rate": 2.6344896331999664e-05, "loss": 3.489, "step": 1444864 }, { "epoch": 0.02, "learning_rate": 2.6336526763292873e-05, "loss": 3.4987, "step": 1445376 }, { "epoch": 0.02, "learning_rate": 2.6328140815782353e-05, "loss": 3.4892, "step": 1445888 }, { "epoch": 0.02, "learning_rate": 2.6319754868271833e-05, "loss": 3.4916, "step": 1446400 }, { "epoch": 0.02, "learning_rate": 2.6311368920761313e-05, "loss": 3.4892, "step": 1446912 }, { "epoch": 0.02, "learning_rate": 2.6302999352054526e-05, "loss": 3.4871, "step": 1447424 }, { "epoch": 0.02, "learning_rate": 2.6294613404544006e-05, "loss": 3.487, "step": 1447936 }, { "epoch": 0.02, "learning_rate": 2.6286227457033486e-05, "loss": 3.4958, "step": 1448448 }, { "epoch": 0.02, "learning_rate": 2.6277841509522966e-05, "loss": 3.4905, "step": 1448960 }, { "epoch": 0.02, "learning_rate": 2.6269471940816175e-05, "loss": 3.4884, "step": 1449472 }, { "epoch": 0.02, "learning_rate": 2.6261085993305655e-05, "loss": 3.488, "step": 1449984 }, { "epoch": 0.03, "eval_loss": 3.8497912883758545, "eval_runtime": 303.1278, "eval_samples_per_second": 1258.845, "eval_steps_per_second": 39.34, "step": 1450080 }, { "epoch": 1.0, "learning_rate": 2.6252700045795138e-05, "loss": 3.4859, "step": 1450496 }, { "epoch": 1.0, "learning_rate": 2.6244314098284618e-05, "loss": 3.4832, "step": 1451008 }, { "epoch": 1.0, "learning_rate": 2.6235944529577827e-05, "loss": 3.492, "step": 1451520 }, { "epoch": 1.0, "learning_rate": 2.6227558582067307e-05, "loss": 3.482, "step": 1452032 }, { "epoch": 1.0, "learning_rate": 2.6219172634556787e-05, "loss": 3.5089, "step": 1452544 }, { "epoch": 1.0, "learning_rate": 2.6210786687046267e-05, "loss": 3.4774, "step": 1453056 }, { "epoch": 1.0, "learning_rate": 2.6202400739535747e-05, "loss": 3.4892, "step": 1453568 }, { "epoch": 1.0, "learning_rate": 2.619403117082896e-05, "loss": 3.4739, "step": 1454080 }, { "epoch": 1.0, "learning_rate": 2.618564522331844e-05, "loss": 3.4894, "step": 1454592 }, { "epoch": 1.0, "learning_rate": 2.617725927580792e-05, "loss": 3.4902, "step": 1455104 }, { "epoch": 1.0, "learning_rate": 2.61688733282974e-05, "loss": 3.4829, "step": 1455616 }, { "epoch": 1.0, "learning_rate": 2.616050375959061e-05, "loss": 3.4875, "step": 1456128 }, { "epoch": 1.0, "learning_rate": 2.615213419088382e-05, "loss": 3.4804, "step": 1456640 }, { "epoch": 1.0, "learning_rate": 2.61437482433733e-05, "loss": 3.4815, "step": 1457152 }, { "epoch": 1.0, "learning_rate": 2.613536229586278e-05, "loss": 3.4796, "step": 1457664 }, { "epoch": 1.0, "learning_rate": 2.612697634835226e-05, "loss": 3.4791, "step": 1458176 }, { "epoch": 1.0, "learning_rate": 2.611859040084174e-05, "loss": 3.4788, "step": 1458688 }, { "epoch": 1.0, "learning_rate": 2.611020445333122e-05, "loss": 3.4835, "step": 1459200 }, { "epoch": 1.0, "learning_rate": 2.61018185058207e-05, "loss": 3.4832, "step": 1459712 }, { "epoch": 1.0, "learning_rate": 2.6093432558310184e-05, "loss": 3.4979, "step": 1460224 }, { "epoch": 1.0, "learning_rate": 2.6085062989603393e-05, "loss": 3.4838, "step": 1460736 }, { "epoch": 1.0, "learning_rate": 2.6076677042092873e-05, "loss": 3.4852, "step": 1461248 }, { "epoch": 1.0, "learning_rate": 2.6068291094582353e-05, "loss": 3.4868, "step": 1461760 }, { "epoch": 1.0, "learning_rate": 2.6059905147071833e-05, "loss": 3.4946, "step": 1462272 }, { "epoch": 1.0, "learning_rate": 2.6051535578365045e-05, "loss": 3.4782, "step": 1462784 }, { "epoch": 1.0, "learning_rate": 2.6043149630854525e-05, "loss": 3.4911, "step": 1463296 }, { "epoch": 1.0, "learning_rate": 2.6034763683344005e-05, "loss": 3.4782, "step": 1463808 }, { "epoch": 1.0, "learning_rate": 2.6026377735833485e-05, "loss": 3.4839, "step": 1464320 }, { "epoch": 1.0, "learning_rate": 2.6018008167126694e-05, "loss": 3.4709, "step": 1464832 }, { "epoch": 1.01, "learning_rate": 2.6009622219616174e-05, "loss": 3.4822, "step": 1465344 }, { "epoch": 1.01, "learning_rate": 2.6001236272105654e-05, "loss": 3.4856, "step": 1465856 }, { "epoch": 1.01, "learning_rate": 2.5992850324595138e-05, "loss": 3.4879, "step": 1466368 }, { "epoch": 1.01, "learning_rate": 2.5984480755888347e-05, "loss": 3.4878, "step": 1466880 }, { "epoch": 1.01, "learning_rate": 2.5976094808377827e-05, "loss": 3.4921, "step": 1467392 }, { "epoch": 1.01, "learning_rate": 2.5967708860867307e-05, "loss": 3.481, "step": 1467904 }, { "epoch": 1.01, "learning_rate": 2.5959322913356787e-05, "loss": 3.4891, "step": 1468416 }, { "epoch": 1.01, "learning_rate": 2.595095334465e-05, "loss": 3.4819, "step": 1468928 }, { "epoch": 1.01, "learning_rate": 2.594256739713948e-05, "loss": 3.4911, "step": 1469440 }, { "epoch": 1.01, "learning_rate": 2.593418144962896e-05, "loss": 3.4749, "step": 1469952 }, { "epoch": 1.01, "learning_rate": 2.592579550211844e-05, "loss": 3.4834, "step": 1470464 }, { "epoch": 1.01, "learning_rate": 2.5917409554607912e-05, "loss": 3.4823, "step": 1470976 }, { "epoch": 1.01, "learning_rate": 2.5909023607097392e-05, "loss": 3.4939, "step": 1471488 }, { "epoch": 1.01, "learning_rate": 2.5900654038390608e-05, "loss": 3.4847, "step": 1472000 }, { "epoch": 1.01, "learning_rate": 2.5892268090880085e-05, "loss": 3.4843, "step": 1472512 }, { "epoch": 1.01, "learning_rate": 2.5883882143369564e-05, "loss": 3.4911, "step": 1473024 }, { "epoch": 1.01, "learning_rate": 2.5875496195859044e-05, "loss": 3.4889, "step": 1473536 }, { "epoch": 1.01, "learning_rate": 2.586712662715226e-05, "loss": 3.4831, "step": 1474048 }, { "epoch": 1.01, "learning_rate": 2.5858740679641737e-05, "loss": 3.4767, "step": 1474560 }, { "epoch": 1.01, "learning_rate": 2.5850354732131217e-05, "loss": 3.4615, "step": 1475072 }, { "epoch": 1.01, "learning_rate": 2.5841968784620697e-05, "loss": 3.4862, "step": 1475584 }, { "epoch": 1.01, "learning_rate": 2.5833599215913913e-05, "loss": 3.4844, "step": 1476096 }, { "epoch": 1.01, "learning_rate": 2.5825213268403386e-05, "loss": 3.4783, "step": 1476608 }, { "epoch": 1.01, "learning_rate": 2.5816827320892866e-05, "loss": 3.4698, "step": 1477120 }, { "epoch": 1.01, "learning_rate": 2.5808441373382346e-05, "loss": 3.4694, "step": 1477632 }, { "epoch": 1.01, "learning_rate": 2.5800071804675558e-05, "loss": 3.465, "step": 1478144 }, { "epoch": 1.01, "learning_rate": 2.5791685857165038e-05, "loss": 3.4844, "step": 1478656 }, { "epoch": 1.01, "learning_rate": 2.5783299909654518e-05, "loss": 3.4757, "step": 1479168 }, { "epoch": 1.01, "learning_rate": 2.5774913962143998e-05, "loss": 3.4784, "step": 1479680 }, { "epoch": 1.01, "learning_rate": 2.5766544393437207e-05, "loss": 3.4843, "step": 1480192 }, { "epoch": 1.01, "learning_rate": 2.575815844592669e-05, "loss": 3.4747, "step": 1480704 }, { "epoch": 1.01, "learning_rate": 2.574977249841617e-05, "loss": 3.4773, "step": 1481216 }, { "epoch": 1.01, "learning_rate": 2.574138655090565e-05, "loss": 3.4791, "step": 1481728 }, { "epoch": 1.01, "learning_rate": 2.573301698219886e-05, "loss": 3.4631, "step": 1482240 }, { "epoch": 1.01, "learning_rate": 2.572463103468834e-05, "loss": 3.4762, "step": 1482752 }, { "epoch": 1.01, "learning_rate": 2.571624508717782e-05, "loss": 3.4849, "step": 1483264 }, { "epoch": 1.01, "learning_rate": 2.57078591396673e-05, "loss": 3.4814, "step": 1483776 }, { "epoch": 1.01, "learning_rate": 2.5699473192156783e-05, "loss": 3.4642, "step": 1484288 }, { "epoch": 1.01, "learning_rate": 2.5691103623449992e-05, "loss": 3.4718, "step": 1484800 }, { "epoch": 1.01, "learning_rate": 2.5682717675939472e-05, "loss": 3.4685, "step": 1485312 }, { "epoch": 1.01, "learning_rate": 2.5674331728428952e-05, "loss": 3.4875, "step": 1485824 }, { "epoch": 1.01, "learning_rate": 2.5665945780918432e-05, "loss": 3.4802, "step": 1486336 }, { "epoch": 1.01, "learning_rate": 2.5657576212211644e-05, "loss": 3.4828, "step": 1486848 }, { "epoch": 1.01, "learning_rate": 2.5649190264701124e-05, "loss": 3.4938, "step": 1487360 }, { "epoch": 1.01, "learning_rate": 2.5640804317190604e-05, "loss": 3.4909, "step": 1487872 }, { "epoch": 1.01, "learning_rate": 2.5632418369680084e-05, "loss": 3.4972, "step": 1488384 }, { "epoch": 1.01, "learning_rate": 2.5624048800973293e-05, "loss": 3.4755, "step": 1488896 }, { "epoch": 1.01, "learning_rate": 2.5615662853462773e-05, "loss": 3.4834, "step": 1489408 }, { "epoch": 1.01, "learning_rate": 2.5607276905952253e-05, "loss": 3.4835, "step": 1489920 }, { "epoch": 1.01, "learning_rate": 2.5598890958441733e-05, "loss": 3.4782, "step": 1490432 }, { "epoch": 1.01, "learning_rate": 2.5590521389734946e-05, "loss": 3.4857, "step": 1490944 }, { "epoch": 1.01, "learning_rate": 2.5582135442224425e-05, "loss": 3.4813, "step": 1491456 }, { "epoch": 1.01, "learning_rate": 2.5573749494713905e-05, "loss": 3.4904, "step": 1491968 }, { "epoch": 1.01, "learning_rate": 2.5565363547203385e-05, "loss": 3.4817, "step": 1492480 }, { "epoch": 1.01, "learning_rate": 2.5556993978496594e-05, "loss": 3.4681, "step": 1492992 }, { "epoch": 1.01, "learning_rate": 2.5548608030986078e-05, "loss": 3.4695, "step": 1493504 }, { "epoch": 1.01, "learning_rate": 2.5540222083475558e-05, "loss": 3.4831, "step": 1494016 }, { "epoch": 1.01, "learning_rate": 2.5531836135965038e-05, "loss": 3.4882, "step": 1494528 }, { "epoch": 1.01, "learning_rate": 2.5523466567258247e-05, "loss": 3.4776, "step": 1495040 }, { "epoch": 1.01, "learning_rate": 2.5515080619747727e-05, "loss": 3.4775, "step": 1495552 }, { "epoch": 1.02, "learning_rate": 2.5506694672237207e-05, "loss": 3.4871, "step": 1496064 }, { "epoch": 1.02, "learning_rate": 2.5498308724726687e-05, "loss": 3.4718, "step": 1496576 }, { "epoch": 1.02, "learning_rate": 2.54899391560199e-05, "loss": 3.4733, "step": 1497088 }, { "epoch": 1.02, "learning_rate": 2.548155320850938e-05, "loss": 3.4776, "step": 1497600 }, { "epoch": 1.02, "learning_rate": 2.547316726099886e-05, "loss": 3.4849, "step": 1498112 }, { "epoch": 1.02, "learning_rate": 2.546478131348834e-05, "loss": 3.4891, "step": 1498624 }, { "epoch": 1.02, "learning_rate": 2.5456411744781548e-05, "loss": 3.481, "step": 1499136 }, { "epoch": 1.02, "learning_rate": 2.544802579727103e-05, "loss": 3.4678, "step": 1499648 }, { "epoch": 1.02, "learning_rate": 2.543963984976051e-05, "loss": 3.4899, "step": 1500160 }, { "epoch": 1.02, "learning_rate": 2.543125390224999e-05, "loss": 3.4729, "step": 1500672 }, { "epoch": 1.02, "learning_rate": 2.54228843335432e-05, "loss": 3.496, "step": 1501184 }, { "epoch": 1.02, "learning_rate": 2.541449838603268e-05, "loss": 3.4855, "step": 1501696 }, { "epoch": 1.02, "learning_rate": 2.540611243852216e-05, "loss": 3.4831, "step": 1502208 }, { "epoch": 1.02, "learning_rate": 2.539772649101164e-05, "loss": 3.4775, "step": 1502720 }, { "epoch": 1.02, "learning_rate": 2.5389356922304853e-05, "loss": 3.489, "step": 1503232 }, { "epoch": 1.02, "learning_rate": 2.5380970974794333e-05, "loss": 3.4668, "step": 1503744 }, { "epoch": 1.02, "learning_rate": 2.5372585027283813e-05, "loss": 3.4762, "step": 1504256 }, { "epoch": 1.02, "learning_rate": 2.5364199079773293e-05, "loss": 3.4721, "step": 1504768 }, { "epoch": 1.02, "learning_rate": 2.5355829511066502e-05, "loss": 3.48, "step": 1505280 }, { "epoch": 1.02, "learning_rate": 2.5347443563555985e-05, "loss": 3.465, "step": 1505792 }, { "epoch": 1.02, "learning_rate": 2.5339057616045465e-05, "loss": 3.4749, "step": 1506304 }, { "epoch": 1.02, "learning_rate": 2.5330671668534945e-05, "loss": 3.4714, "step": 1506816 }, { "epoch": 1.02, "learning_rate": 2.5322302099828154e-05, "loss": 3.4711, "step": 1507328 }, { "epoch": 1.02, "learning_rate": 2.5313916152317634e-05, "loss": 3.4757, "step": 1507840 }, { "epoch": 1.02, "learning_rate": 2.5305530204807114e-05, "loss": 3.4706, "step": 1508352 }, { "epoch": 1.02, "learning_rate": 2.5297144257296594e-05, "loss": 3.485, "step": 1508864 }, { "epoch": 1.02, "learning_rate": 2.5288774688589807e-05, "loss": 3.4894, "step": 1509376 }, { "epoch": 1.02, "learning_rate": 2.5280388741079286e-05, "loss": 3.4847, "step": 1509888 }, { "epoch": 1.02, "learning_rate": 2.5272002793568766e-05, "loss": 3.4755, "step": 1510400 }, { "epoch": 1.02, "learning_rate": 2.5263616846058246e-05, "loss": 3.4874, "step": 1510912 }, { "epoch": 1.02, "learning_rate": 2.5255247277351455e-05, "loss": 3.4822, "step": 1511424 }, { "epoch": 1.02, "learning_rate": 2.524686132984094e-05, "loss": 3.47, "step": 1511936 }, { "epoch": 1.02, "learning_rate": 2.523847538233042e-05, "loss": 3.4847, "step": 1512448 }, { "epoch": 1.02, "learning_rate": 2.52300894348199e-05, "loss": 3.4756, "step": 1512960 }, { "epoch": 1.02, "learning_rate": 2.522170348730938e-05, "loss": 3.4848, "step": 1513472 }, { "epoch": 1.02, "learning_rate": 2.5213333918602588e-05, "loss": 3.4718, "step": 1513984 }, { "epoch": 1.02, "learning_rate": 2.5204947971092068e-05, "loss": 3.4813, "step": 1514496 }, { "epoch": 1.02, "learning_rate": 2.5196562023581548e-05, "loss": 3.4653, "step": 1515008 }, { "epoch": 1.02, "learning_rate": 2.518817607607103e-05, "loss": 3.4707, "step": 1515520 }, { "epoch": 1.02, "learning_rate": 2.517980650736424e-05, "loss": 3.4707, "step": 1516032 }, { "epoch": 1.02, "learning_rate": 2.517142055985372e-05, "loss": 3.4809, "step": 1516544 }, { "epoch": 1.02, "learning_rate": 2.51630346123432e-05, "loss": 3.4781, "step": 1517056 }, { "epoch": 1.02, "learning_rate": 2.515464866483268e-05, "loss": 3.4848, "step": 1517568 }, { "epoch": 1.02, "learning_rate": 2.5146279096125892e-05, "loss": 3.475, "step": 1518080 }, { "epoch": 1.02, "learning_rate": 2.5137893148615372e-05, "loss": 3.4824, "step": 1518592 }, { "epoch": 1.02, "learning_rate": 2.5129507201104852e-05, "loss": 3.4881, "step": 1519104 }, { "epoch": 1.02, "learning_rate": 2.5121121253594332e-05, "loss": 3.4785, "step": 1519616 }, { "epoch": 1.02, "learning_rate": 2.511275168488754e-05, "loss": 3.4766, "step": 1520128 }, { "epoch": 1.02, "learning_rate": 2.510436573737702e-05, "loss": 3.4876, "step": 1520640 }, { "epoch": 1.02, "learning_rate": 2.50959797898665e-05, "loss": 3.4757, "step": 1521152 }, { "epoch": 1.02, "learning_rate": 2.5087593842355985e-05, "loss": 3.4879, "step": 1521664 }, { "epoch": 1.02, "learning_rate": 2.5079224273649194e-05, "loss": 3.4715, "step": 1522176 }, { "epoch": 1.02, "learning_rate": 2.5070838326138674e-05, "loss": 3.4835, "step": 1522688 }, { "epoch": 1.02, "learning_rate": 2.5062452378628154e-05, "loss": 3.4761, "step": 1523200 }, { "epoch": 1.02, "learning_rate": 2.5054066431117634e-05, "loss": 3.4749, "step": 1523712 }, { "epoch": 1.02, "learning_rate": 2.5045696862410846e-05, "loss": 3.4796, "step": 1524224 }, { "epoch": 1.02, "learning_rate": 2.5037310914900326e-05, "loss": 3.48, "step": 1524736 }, { "epoch": 1.02, "learning_rate": 2.5028924967389806e-05, "loss": 3.4797, "step": 1525248 }, { "epoch": 1.02, "learning_rate": 2.5020539019879286e-05, "loss": 3.4723, "step": 1525760 }, { "epoch": 1.02, "learning_rate": 2.5012169451172495e-05, "loss": 3.4789, "step": 1526272 }, { "epoch": 1.03, "eval_loss": 3.8522579669952393, "eval_runtime": 302.7288, "eval_samples_per_second": 1260.504, "eval_steps_per_second": 39.392, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5003783503661975e-05, "loss": 3.4704, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4995397556151455e-05, "loss": 3.4696, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4987011608640935e-05, "loss": 3.4798, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4978625661130415e-05, "loss": 3.4706, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4970256092423624e-05, "loss": 3.4949, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4961870144913104e-05, "loss": 3.4739, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4953484197402584e-05, "loss": 3.4734, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.4945098249892064e-05, "loss": 3.4603, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.4936728681185276e-05, "loss": 3.4772, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.4928342733674756e-05, "loss": 3.484, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4919956786164236e-05, "loss": 3.4707, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4911570838653716e-05, "loss": 3.4733, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.490321764875066e-05, "loss": 3.4692, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.489483170124014e-05, "loss": 3.4703, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.4886445753729618e-05, "loss": 3.4688, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.4878059806219098e-05, "loss": 3.4657, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.4869673858708578e-05, "loss": 3.4664, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.4861287911198058e-05, "loss": 3.4747, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.4852901963687538e-05, "loss": 3.4723, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4844516016177018e-05, "loss": 3.4823, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.483614644747023e-05, "loss": 3.475, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.482776049995971e-05, "loss": 3.4768, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.481937455244919e-05, "loss": 3.4734, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.481098860493867e-05, "loss": 3.4838, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.480261903623188e-05, "loss": 3.4677, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.4794233088721362e-05, "loss": 3.476, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.4785847141210842e-05, "loss": 3.472, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.4777461193700322e-05, "loss": 3.4681, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.476909162499353e-05, "loss": 3.4608, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.476070567748301e-05, "loss": 3.4673, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.475231972997249e-05, "loss": 3.479, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.474393378246197e-05, "loss": 3.4764, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4735564213755184e-05, "loss": 3.4796, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4727178266244664e-05, "loss": 3.4776, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4718792318734144e-05, "loss": 3.469, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.471040637122362e-05, "loss": 3.476, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.4702036802516833e-05, "loss": 3.4714, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.4693650855006316e-05, "loss": 3.4763, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4685264907495796e-05, "loss": 3.4633, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4676878959985273e-05, "loss": 3.4739, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4668509391278485e-05, "loss": 3.4705, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4660123443767965e-05, "loss": 3.4807, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.465173749625744e-05, "loss": 3.4738, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.4643351548746925e-05, "loss": 3.4735, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.4634981980040137e-05, "loss": 3.4823, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.4626596032529617e-05, "loss": 3.4734, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4618210085019094e-05, "loss": 3.4726, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4609824137508574e-05, "loss": 3.4623, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4601454568801786e-05, "loss": 3.4494, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.459306862129127e-05, "loss": 3.4771, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.4584682673780746e-05, "loss": 3.4738, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.4576296726270226e-05, "loss": 3.4697, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.4567910778759706e-05, "loss": 3.4528, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4559541210052915e-05, "loss": 3.4615, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.4551155262542395e-05, "loss": 3.4523, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.454276931503188e-05, "loss": 3.4737, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.453438336752136e-05, "loss": 3.4638, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.4526013798814568e-05, "loss": 3.4636, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.4517627851304048e-05, "loss": 3.4749, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.4509241903793528e-05, "loss": 3.4606, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.4500855956283007e-05, "loss": 3.4657, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.449248638757622e-05, "loss": 3.4707, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.44841004400657e-05, "loss": 3.4497, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.447571449255518e-05, "loss": 3.4667, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.446732854504466e-05, "loss": 3.4678, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.445895897633787e-05, "loss": 3.4726, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.445057302882735e-05, "loss": 3.4539, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.4442187081316832e-05, "loss": 3.4621, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.4433801133806312e-05, "loss": 3.4532, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.442543156509952e-05, "loss": 3.4774, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4417045617589e-05, "loss": 3.4688, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.440865967007848e-05, "loss": 3.4684, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.4400290101371694e-05, "loss": 3.4851, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.4391904153861174e-05, "loss": 3.4737, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4383518206350654e-05, "loss": 3.4926, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4375132258840134e-05, "loss": 3.466, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.4366746311329614e-05, "loss": 3.4695, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4358376742622823e-05, "loss": 3.4708, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.4349990795112303e-05, "loss": 3.4618, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.4341604847601786e-05, "loss": 3.4751, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.4333218900091266e-05, "loss": 3.465, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.4324849331384475e-05, "loss": 3.476, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.4316463383873955e-05, "loss": 3.4679, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4308077436363435e-05, "loss": 3.4588, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.4299691488852915e-05, "loss": 3.465, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.4291321920146127e-05, "loss": 3.4631, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.4282935972635607e-05, "loss": 3.4773, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4274550025125087e-05, "loss": 3.4697, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.4266164077614567e-05, "loss": 3.4638, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.4257794508907776e-05, "loss": 3.4746, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.4249408561397256e-05, "loss": 3.464, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.424102261388674e-05, "loss": 3.4576, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.423263666637622e-05, "loss": 3.4652, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.422426709766943e-05, "loss": 3.4754, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.421588115015891e-05, "loss": 3.4775, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.420749520264839e-05, "loss": 3.4703, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.4199109255137865e-05, "loss": 3.4549, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.419073968643108e-05, "loss": 3.4753, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.418235373892056e-05, "loss": 3.4628, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.417396779141004e-05, "loss": 3.4815, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.4165581843899517e-05, "loss": 3.4757, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.415721227519273e-05, "loss": 3.4713, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.414882632768221e-05, "loss": 3.4643, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4140440380171693e-05, "loss": 3.48, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.413205443266117e-05, "loss": 3.452, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.4123684863954382e-05, "loss": 3.4656, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.4115298916443862e-05, "loss": 3.4563, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.410691296893334e-05, "loss": 3.4735, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.409852702142282e-05, "loss": 3.4517, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4090157452716035e-05, "loss": 3.4618, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4081771505205515e-05, "loss": 3.4614, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.407338555769499e-05, "loss": 3.4624, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.406499961018447e-05, "loss": 3.4625, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4056630041477684e-05, "loss": 3.4634, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4048244093967164e-05, "loss": 3.4717, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4039858146456644e-05, "loss": 3.4757, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4031472198946123e-05, "loss": 3.4699, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4023102630239336e-05, "loss": 3.4639, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4014716682728813e-05, "loss": 3.4778, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4006330735218292e-05, "loss": 3.4669, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.3997944787707772e-05, "loss": 3.4595, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.398957521900099e-05, "loss": 3.4746, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3981189271490465e-05, "loss": 3.462, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.3972803323979945e-05, "loss": 3.4715, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3964417376469425e-05, "loss": 3.4604, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.3956047807762637e-05, "loss": 3.4683, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.3947661860252117e-05, "loss": 3.4562, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.3939275912741597e-05, "loss": 3.4579, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.3930889965231077e-05, "loss": 3.4617, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.3922520396524286e-05, "loss": 3.4683, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.3914134449013766e-05, "loss": 3.467, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3905748501503246e-05, "loss": 3.4717, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.3897362553992726e-05, "loss": 3.4636, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.388899298528594e-05, "loss": 3.4726, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.388060703777542e-05, "loss": 3.4747, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.38722210902649e-05, "loss": 3.467, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.386383514275438e-05, "loss": 3.4657, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.3855465574047588e-05, "loss": 3.4734, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.384707962653707e-05, "loss": 3.4661, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.383869367902655e-05, "loss": 3.4758, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.383030773151603e-05, "loss": 3.4621, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.382193816280924e-05, "loss": 3.4704, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.381355221529872e-05, "loss": 3.4644, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.38051662677882e-05, "loss": 3.465, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.379678032027768e-05, "loss": 3.4651, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.3788410751570892e-05, "loss": 3.466, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.3780024804060372e-05, "loss": 3.4703, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.3771638856549852e-05, "loss": 3.4564, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.3763252909039332e-05, "loss": 3.4715, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 3.8532488346099854, "eval_runtime": 308.4759, "eval_samples_per_second": 1237.02, "eval_steps_per_second": 38.658, "step": 1602720 }, { "epoch": 1.0, "learning_rate": 2.375488334033254e-05, "loss": 3.4626, "step": 1603072 }, { "epoch": 1.0, "learning_rate": 2.3746497392822025e-05, "loss": 3.4579, "step": 1603584 }, { "epoch": 1.0, "learning_rate": 2.3738111445311505e-05, "loss": 3.4696, "step": 1604096 }, { "epoch": 1.0, "learning_rate": 2.3729725497800984e-05, "loss": 3.4617, "step": 1604608 }, { "epoch": 1.0, "learning_rate": 2.3721355929094194e-05, "loss": 3.4791, "step": 1605120 }, { "epoch": 1.0, "learning_rate": 2.3712969981583674e-05, "loss": 3.4641, "step": 1605632 }, { "epoch": 1.0, "learning_rate": 2.3704584034073153e-05, "loss": 3.4564, "step": 1606144 }, { "epoch": 1.0, "learning_rate": 2.3696198086562633e-05, "loss": 3.4552, "step": 1606656 }, { "epoch": 1.0, "learning_rate": 2.3687828517855846e-05, "loss": 3.4595, "step": 1607168 }, { "epoch": 1.0, "learning_rate": 2.3679442570345326e-05, "loss": 3.4686, "step": 1607680 }, { "epoch": 1.0, "learning_rate": 2.3671056622834806e-05, "loss": 3.4579, "step": 1608192 }, { "epoch": 1.0, "learning_rate": 2.3662670675324286e-05, "loss": 3.4644, "step": 1608704 }, { "epoch": 1.0, "learning_rate": 2.3654301106617495e-05, "loss": 3.4602, "step": 1609216 }, { "epoch": 1.0, "learning_rate": 2.3645915159106978e-05, "loss": 3.4532, "step": 1609728 }, { "epoch": 1.0, "learning_rate": 2.3637529211596458e-05, "loss": 3.4616, "step": 1610240 }, { "epoch": 1.0, "learning_rate": 2.3629143264085938e-05, "loss": 3.4503, "step": 1610752 }, { "epoch": 1.0, "learning_rate": 2.3620757316575415e-05, "loss": 3.4534, "step": 1611264 }, { "epoch": 1.0, "learning_rate": 2.3612371369064895e-05, "loss": 3.4613, "step": 1611776 }, { "epoch": 1.0, "learning_rate": 2.3603985421554375e-05, "loss": 3.462, "step": 1612288 }, { "epoch": 1.0, "learning_rate": 2.3595599474043855e-05, "loss": 3.4691, "step": 1612800 }, { "epoch": 1.0, "learning_rate": 2.3587229905337067e-05, "loss": 3.4648, "step": 1613312 }, { "epoch": 1.0, "learning_rate": 2.3578843957826547e-05, "loss": 3.4649, "step": 1613824 }, { "epoch": 1.0, "learning_rate": 2.3570458010316027e-05, "loss": 3.4646, "step": 1614336 }, { "epoch": 1.0, "learning_rate": 2.3562072062805507e-05, "loss": 3.4678, "step": 1614848 }, { "epoch": 1.0, "learning_rate": 2.3553702494098716e-05, "loss": 3.4531, "step": 1615360 }, { "epoch": 1.0, "learning_rate": 2.3545316546588196e-05, "loss": 3.4699, "step": 1615872 }, { "epoch": 1.0, "learning_rate": 2.353693059907768e-05, "loss": 3.4552, "step": 1616384 }, { "epoch": 1.0, "learning_rate": 2.352854465156716e-05, "loss": 3.4578, "step": 1616896 }, { "epoch": 1.0, "learning_rate": 2.352017508286037e-05, "loss": 3.4532, "step": 1617408 }, { "epoch": 1.0, "learning_rate": 2.351178913534985e-05, "loss": 3.4569, "step": 1617920 }, { "epoch": 1.01, "learning_rate": 2.3503403187839328e-05, "loss": 3.4674, "step": 1618432 }, { "epoch": 1.01, "learning_rate": 2.3495017240328808e-05, "loss": 3.4602, "step": 1618944 }, { "epoch": 1.01, "learning_rate": 2.348664767162202e-05, "loss": 3.4697, "step": 1619456 }, { "epoch": 1.01, "learning_rate": 2.34782617241115e-05, "loss": 3.4689, "step": 1619968 }, { "epoch": 1.01, "learning_rate": 2.346987577660098e-05, "loss": 3.4562, "step": 1620480 }, { "epoch": 1.01, "learning_rate": 2.346148982909046e-05, "loss": 3.4625, "step": 1620992 }, { "epoch": 1.01, "learning_rate": 2.345312026038367e-05, "loss": 3.4608, "step": 1621504 }, { "epoch": 1.01, "learning_rate": 2.344473431287315e-05, "loss": 3.4629, "step": 1622016 }, { "epoch": 1.01, "learning_rate": 2.3436348365362633e-05, "loss": 3.4547, "step": 1622528 }, { "epoch": 1.01, "learning_rate": 2.3427962417852113e-05, "loss": 3.4572, "step": 1623040 }, { "epoch": 1.01, "learning_rate": 2.3419592849145322e-05, "loss": 3.4616, "step": 1623552 }, { "epoch": 1.01, "learning_rate": 2.3411206901634802e-05, "loss": 3.4683, "step": 1624064 }, { "epoch": 1.01, "learning_rate": 2.3402820954124282e-05, "loss": 3.4603, "step": 1624576 }, { "epoch": 1.01, "learning_rate": 2.3394435006613762e-05, "loss": 3.4617, "step": 1625088 }, { "epoch": 1.01, "learning_rate": 2.3386065437906974e-05, "loss": 3.4684, "step": 1625600 }, { "epoch": 1.01, "learning_rate": 2.3377679490396454e-05, "loss": 3.4635, "step": 1626112 }, { "epoch": 1.01, "learning_rate": 2.3369293542885934e-05, "loss": 3.4578, "step": 1626624 }, { "epoch": 1.01, "learning_rate": 2.3360907595375414e-05, "loss": 3.4533, "step": 1627136 }, { "epoch": 1.01, "learning_rate": 2.3352538026668623e-05, "loss": 3.434, "step": 1627648 }, { "epoch": 1.01, "learning_rate": 2.3344152079158103e-05, "loss": 3.4686, "step": 1628160 }, { "epoch": 1.01, "learning_rate": 2.3335766131647587e-05, "loss": 3.4606, "step": 1628672 }, { "epoch": 1.01, "learning_rate": 2.3327380184137067e-05, "loss": 3.4605, "step": 1629184 }, { "epoch": 1.01, "learning_rate": 2.3319010615430276e-05, "loss": 3.447, "step": 1629696 }, { "epoch": 1.01, "learning_rate": 2.3310624667919756e-05, "loss": 3.4431, "step": 1630208 }, { "epoch": 1.01, "learning_rate": 2.3302238720409236e-05, "loss": 3.4422, "step": 1630720 }, { "epoch": 1.01, "learning_rate": 2.3293852772898716e-05, "loss": 3.4598, "step": 1631232 }, { "epoch": 1.01, "learning_rate": 2.3285466825388196e-05, "loss": 3.4523, "step": 1631744 }, { "epoch": 1.01, "learning_rate": 2.3277097256681408e-05, "loss": 3.4533, "step": 1632256 }, { "epoch": 1.01, "learning_rate": 2.3268711309170888e-05, "loss": 3.4611, "step": 1632768 }, { "epoch": 1.01, "learning_rate": 2.3260325361660365e-05, "loss": 3.4492, "step": 1633280 }, { "epoch": 1.01, "learning_rate": 2.3251939414149844e-05, "loss": 3.4565, "step": 1633792 }, { "epoch": 1.01, "learning_rate": 2.3243569845443057e-05, "loss": 3.4614, "step": 1634304 }, { "epoch": 1.01, "learning_rate": 2.323518389793254e-05, "loss": 3.4406, "step": 1634816 }, { "epoch": 1.01, "learning_rate": 2.3226797950422017e-05, "loss": 3.452, "step": 1635328 }, { "epoch": 1.01, "learning_rate": 2.3218412002911497e-05, "loss": 3.4576, "step": 1635840 }, { "epoch": 1.01, "learning_rate": 2.321004243420471e-05, "loss": 3.4605, "step": 1636352 }, { "epoch": 1.01, "learning_rate": 2.320165648669419e-05, "loss": 3.4403, "step": 1636864 }, { "epoch": 1.01, "learning_rate": 2.3193270539183666e-05, "loss": 3.452, "step": 1637376 }, { "epoch": 1.01, "learning_rate": 2.318488459167315e-05, "loss": 3.4427, "step": 1637888 }, { "epoch": 1.01, "learning_rate": 2.317651502296636e-05, "loss": 3.4641, "step": 1638400 }, { "epoch": 1.01, "learning_rate": 2.3168129075455838e-05, "loss": 3.4608, "step": 1638912 }, { "epoch": 1.01, "learning_rate": 2.3159743127945318e-05, "loss": 3.455, "step": 1639424 }, { "epoch": 1.01, "learning_rate": 2.3151357180434798e-05, "loss": 3.4719, "step": 1639936 }, { "epoch": 1.01, "learning_rate": 2.314298761172801e-05, "loss": 3.4628, "step": 1640448 }, { "epoch": 1.01, "learning_rate": 2.313460166421749e-05, "loss": 3.4817, "step": 1640960 }, { "epoch": 1.01, "learning_rate": 2.312621571670697e-05, "loss": 3.4566, "step": 1641472 }, { "epoch": 1.01, "learning_rate": 2.311782976919645e-05, "loss": 3.4596, "step": 1641984 }, { "epoch": 1.01, "learning_rate": 2.3109460200489663e-05, "loss": 3.4579, "step": 1642496 }, { "epoch": 1.01, "learning_rate": 2.310107425297914e-05, "loss": 3.4497, "step": 1643008 }, { "epoch": 1.01, "learning_rate": 2.309268830546862e-05, "loss": 3.466, "step": 1643520 }, { "epoch": 1.01, "learning_rate": 2.3084318736761835e-05, "loss": 3.4524, "step": 1644032 }, { "epoch": 1.01, "learning_rate": 2.3075932789251312e-05, "loss": 3.4655, "step": 1644544 }, { "epoch": 1.01, "learning_rate": 2.3067546841740792e-05, "loss": 3.4571, "step": 1645056 }, { "epoch": 1.01, "learning_rate": 2.3059160894230272e-05, "loss": 3.4455, "step": 1645568 }, { "epoch": 1.01, "learning_rate": 2.3050791325523484e-05, "loss": 3.4539, "step": 1646080 }, { "epoch": 1.01, "learning_rate": 2.3042405378012964e-05, "loss": 3.4476, "step": 1646592 }, { "epoch": 1.01, "learning_rate": 2.3034019430502444e-05, "loss": 3.4673, "step": 1647104 }, { "epoch": 1.01, "learning_rate": 2.3025633482991924e-05, "loss": 3.4607, "step": 1647616 }, { "epoch": 1.01, "learning_rate": 2.3017247535481404e-05, "loss": 3.4478, "step": 1648128 }, { "epoch": 1.02, "learning_rate": 2.3008877966774613e-05, "loss": 3.4664, "step": 1648640 }, { "epoch": 1.02, "learning_rate": 2.3000492019264093e-05, "loss": 3.453, "step": 1649152 }, { "epoch": 1.02, "learning_rate": 2.2992106071753573e-05, "loss": 3.448, "step": 1649664 }, { "epoch": 1.02, "learning_rate": 2.2983720124243057e-05, "loss": 3.4515, "step": 1650176 }, { "epoch": 1.02, "learning_rate": 2.2975350555536266e-05, "loss": 3.4628, "step": 1650688 }, { "epoch": 1.02, "learning_rate": 2.2966964608025746e-05, "loss": 3.4606, "step": 1651200 }, { "epoch": 1.02, "learning_rate": 2.2958578660515226e-05, "loss": 3.4632, "step": 1651712 }, { "epoch": 1.02, "learning_rate": 2.2950192713004705e-05, "loss": 3.4448, "step": 1652224 }, { "epoch": 1.02, "learning_rate": 2.2941823144297918e-05, "loss": 3.4621, "step": 1652736 }, { "epoch": 1.02, "learning_rate": 2.2933437196787398e-05, "loss": 3.4518, "step": 1653248 }, { "epoch": 1.02, "learning_rate": 2.2925051249276878e-05, "loss": 3.4681, "step": 1653760 }, { "epoch": 1.02, "learning_rate": 2.2916665301766358e-05, "loss": 3.4653, "step": 1654272 }, { "epoch": 1.02, "learning_rate": 2.2908295733059567e-05, "loss": 3.4562, "step": 1654784 }, { "epoch": 1.02, "learning_rate": 2.2899909785549047e-05, "loss": 3.4558, "step": 1655296 }, { "epoch": 1.02, "learning_rate": 2.2891523838038527e-05, "loss": 3.4654, "step": 1655808 }, { "epoch": 1.02, "learning_rate": 2.288313789052801e-05, "loss": 3.4439, "step": 1656320 }, { "epoch": 1.02, "learning_rate": 2.287476832182122e-05, "loss": 3.4523, "step": 1656832 }, { "epoch": 1.02, "learning_rate": 2.28663823743107e-05, "loss": 3.4424, "step": 1657344 }, { "epoch": 1.02, "learning_rate": 2.285799642680018e-05, "loss": 3.4589, "step": 1657856 }, { "epoch": 1.02, "learning_rate": 2.284961047928966e-05, "loss": 3.4425, "step": 1658368 }, { "epoch": 1.02, "learning_rate": 2.284124091058287e-05, "loss": 3.4543, "step": 1658880 }, { "epoch": 1.02, "learning_rate": 2.283285496307235e-05, "loss": 3.4474, "step": 1659392 }, { "epoch": 1.02, "learning_rate": 2.282446901556183e-05, "loss": 3.4507, "step": 1659904 }, { "epoch": 1.02, "learning_rate": 2.281608306805131e-05, "loss": 3.4539, "step": 1660416 }, { "epoch": 1.02, "learning_rate": 2.280771349934452e-05, "loss": 3.45, "step": 1660928 }, { "epoch": 1.02, "learning_rate": 2.2799327551834e-05, "loss": 3.4614, "step": 1661440 }, { "epoch": 1.02, "learning_rate": 2.279094160432348e-05, "loss": 3.4646, "step": 1661952 }, { "epoch": 1.02, "learning_rate": 2.2782555656812964e-05, "loss": 3.4614, "step": 1662464 }, { "epoch": 1.02, "learning_rate": 2.2774186088106173e-05, "loss": 3.4499, "step": 1662976 }, { "epoch": 1.02, "learning_rate": 2.2765800140595653e-05, "loss": 3.4649, "step": 1663488 }, { "epoch": 1.02, "learning_rate": 2.2757414193085133e-05, "loss": 3.4618, "step": 1664000 }, { "epoch": 1.02, "learning_rate": 2.2749028245574613e-05, "loss": 3.444, "step": 1664512 }, { "epoch": 1.02, "learning_rate": 2.2740658676867825e-05, "loss": 3.4661, "step": 1665024 }, { "epoch": 1.02, "learning_rate": 2.2732272729357305e-05, "loss": 3.4462, "step": 1665536 }, { "epoch": 1.02, "learning_rate": 2.2723886781846785e-05, "loss": 3.4612, "step": 1666048 }, { "epoch": 1.02, "learning_rate": 2.2715500834336262e-05, "loss": 3.4461, "step": 1666560 }, { "epoch": 1.02, "learning_rate": 2.2707131265629474e-05, "loss": 3.4599, "step": 1667072 }, { "epoch": 1.02, "learning_rate": 2.2698745318118954e-05, "loss": 3.4451, "step": 1667584 }, { "epoch": 1.02, "learning_rate": 2.2690359370608434e-05, "loss": 3.4458, "step": 1668096 }, { "epoch": 1.02, "learning_rate": 2.2681973423097914e-05, "loss": 3.4443, "step": 1668608 }, { "epoch": 1.02, "learning_rate": 2.2673603854391127e-05, "loss": 3.4627, "step": 1669120 }, { "epoch": 1.02, "learning_rate": 2.2665217906880607e-05, "loss": 3.4532, "step": 1669632 }, { "epoch": 1.02, "learning_rate": 2.2656831959370087e-05, "loss": 3.4615, "step": 1670144 }, { "epoch": 1.02, "learning_rate": 2.2648446011859563e-05, "loss": 3.4504, "step": 1670656 }, { "epoch": 1.02, "learning_rate": 2.264007644315278e-05, "loss": 3.4615, "step": 1671168 }, { "epoch": 1.02, "learning_rate": 2.263169049564226e-05, "loss": 3.4627, "step": 1671680 }, { "epoch": 1.02, "learning_rate": 2.2623304548131736e-05, "loss": 3.4579, "step": 1672192 }, { "epoch": 1.02, "learning_rate": 2.2614918600621215e-05, "loss": 3.4574, "step": 1672704 }, { "epoch": 1.02, "learning_rate": 2.2606549031914428e-05, "loss": 3.4545, "step": 1673216 }, { "epoch": 1.02, "learning_rate": 2.2598163084403908e-05, "loss": 3.4531, "step": 1673728 }, { "epoch": 1.02, "learning_rate": 2.2589777136893388e-05, "loss": 3.465, "step": 1674240 }, { "epoch": 1.02, "learning_rate": 2.2581391189382868e-05, "loss": 3.4512, "step": 1674752 }, { "epoch": 1.02, "learning_rate": 2.257302162067608e-05, "loss": 3.4591, "step": 1675264 }, { "epoch": 1.02, "learning_rate": 2.256463567316556e-05, "loss": 3.4522, "step": 1675776 }, { "epoch": 1.02, "learning_rate": 2.2556249725655037e-05, "loss": 3.4543, "step": 1676288 }, { "epoch": 1.02, "learning_rate": 2.2547863778144517e-05, "loss": 3.4538, "step": 1676800 }, { "epoch": 1.02, "learning_rate": 2.253949420943773e-05, "loss": 3.4506, "step": 1677312 }, { "epoch": 1.02, "learning_rate": 2.253110826192721e-05, "loss": 3.4648, "step": 1677824 }, { "epoch": 1.02, "learning_rate": 2.252272231441669e-05, "loss": 3.4398, "step": 1678336 }, { "epoch": 1.02, "learning_rate": 2.251433636690617e-05, "loss": 3.4617, "step": 1678848 }, { "epoch": 1.03, "eval_loss": 3.854151487350464, "eval_runtime": 325.3875, "eval_samples_per_second": 1172.728, "eval_steps_per_second": 36.649, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.250596679819938e-05, "loss": 3.4522, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.2497580850688858e-05, "loss": 3.4436, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.248919490317834e-05, "loss": 3.4558, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.248080895566782e-05, "loss": 3.4508, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.2472439386961034e-05, "loss": 3.4647, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.246405343945051e-05, "loss": 3.4521, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.245566749193999e-05, "loss": 3.4474, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.244728154442947e-05, "loss": 3.442, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.2438911975722683e-05, "loss": 3.4506, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.2430526028212163e-05, "loss": 3.4572, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.2422140080701643e-05, "loss": 3.4479, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.2413754133191123e-05, "loss": 3.4501, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.2405384564484332e-05, "loss": 3.4532, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.2396998616973812e-05, "loss": 3.4413, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.2388612669463295e-05, "loss": 3.4484, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.2380226721952775e-05, "loss": 3.4384, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.2371840774442255e-05, "loss": 3.4437, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.2363454826931735e-05, "loss": 3.4484, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.235506887942121e-05, "loss": 3.4506, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.234668293191069e-05, "loss": 3.4572, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.2338313363203904e-05, "loss": 3.4588, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.2329927415693387e-05, "loss": 3.4495, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.2321541468182864e-05, "loss": 3.4524, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.2313155520672344e-05, "loss": 3.4573, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.2304785951965556e-05, "loss": 3.4394, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.2296400004455036e-05, "loss": 3.4628, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.2288014056944513e-05, "loss": 3.443, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.2279628109433996e-05, "loss": 3.4445, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.227125854072721e-05, "loss": 3.4399, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.2262872593216685e-05, "loss": 3.4497, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.2254486645706165e-05, "loss": 3.4516, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2246100698195645e-05, "loss": 3.4536, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.2237731129488858e-05, "loss": 3.4557, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.2229345181978338e-05, "loss": 3.4556, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.2220959234467818e-05, "loss": 3.4456, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.2212573286957298e-05, "loss": 3.4528, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.220420371825051e-05, "loss": 3.4527, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.2195817770739987e-05, "loss": 3.447, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.2187431823229467e-05, "loss": 3.4442, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.217904587571895e-05, "loss": 3.4477, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.217067630701216e-05, "loss": 3.4478, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.216229035950164e-05, "loss": 3.4594, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.215390441199112e-05, "loss": 3.4488, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.21455184644806e-05, "loss": 3.4482, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.213714889577381e-05, "loss": 3.4593, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.212876294826329e-05, "loss": 3.4489, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.212037700075277e-05, "loss": 3.4525, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.211199105324225e-05, "loss": 3.4436, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.210362148453546e-05, "loss": 3.4181, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.209523553702494e-05, "loss": 3.4603, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.208684958951442e-05, "loss": 3.4482, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.2078463642003904e-05, "loss": 3.4511, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.2070094073297113e-05, "loss": 3.4366, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.2061708125786593e-05, "loss": 3.43, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2053322178276073e-05, "loss": 3.4328, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.2044936230765553e-05, "loss": 3.4432, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.2036566662058765e-05, "loss": 3.4436, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.2028180714548245e-05, "loss": 3.4414, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.2019794767037725e-05, "loss": 3.4523, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.2011408819527205e-05, "loss": 3.4365, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.2003039250820414e-05, "loss": 3.4416, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.1994653303309894e-05, "loss": 3.4533, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.1986267355799374e-05, "loss": 3.4254, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.1977881408288857e-05, "loss": 3.4392, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.1969511839582066e-05, "loss": 3.4456, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.1961125892071546e-05, "loss": 3.4523, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.1952739944561026e-05, "loss": 3.4277, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1944353997050506e-05, "loss": 3.4407, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.193598442834372e-05, "loss": 3.4279, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.19275984808332e-05, "loss": 3.4529, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.191921253332268e-05, "loss": 3.4513, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.191082658581216e-05, "loss": 3.4457, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.1902457017105368e-05, "loss": 3.455, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.1894071069594848e-05, "loss": 3.4529, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.1885685122084328e-05, "loss": 3.4706, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.187729917457381e-05, "loss": 3.444, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.186892960586702e-05, "loss": 3.449, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.18605436583565e-05, "loss": 3.4473, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.185215771084598e-05, "loss": 3.4378, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.184377176333546e-05, "loss": 3.4506, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.1835402194628672e-05, "loss": 3.4478, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.1827016247118152e-05, "loss": 3.4526, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.1818630299607632e-05, "loss": 3.4546, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.1810244352097112e-05, "loss": 3.4353, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.180187478339032e-05, "loss": 3.4361, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.17934888358798e-05, "loss": 3.4388, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.178510288836928e-05, "loss": 3.4567, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.177671694085876e-05, "loss": 3.4474, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.1768347372151974e-05, "loss": 3.44, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.1759961424641454e-05, "loss": 3.4432, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1751575477130934e-05, "loss": 3.4479, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.174318952962041e-05, "loss": 3.4366, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.1734819960913626e-05, "loss": 3.4398, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.1726434013403106e-05, "loss": 3.4563, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.1718048065892583e-05, "loss": 3.4481, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1709662118382063e-05, "loss": 3.4503, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.1701292549675275e-05, "loss": 3.4365, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.1692906602164755e-05, "loss": 3.4506, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.1684520654654235e-05, "loss": 3.441, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.1676134707143715e-05, "loss": 3.4562, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.1667765138436927e-05, "loss": 3.4524, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.1659379190926407e-05, "loss": 3.4504, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.1650993243415884e-05, "loss": 3.4467, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.1642607295905364e-05, "loss": 3.4513, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.1634221348394844e-05, "loss": 3.4321, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.1625851779688056e-05, "loss": 3.4439, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.1617465832177536e-05, "loss": 3.4313, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.1609079884667016e-05, "loss": 3.451, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.1600693937156496e-05, "loss": 3.4344, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.1592324368449705e-05, "loss": 3.4398, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.158393842093919e-05, "loss": 3.4319, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.157555247342867e-05, "loss": 3.4412, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.156716652591815e-05, "loss": 3.4424, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.1558796957211358e-05, "loss": 3.4377, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.1550411009700838e-05, "loss": 3.4455, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.1542025062190318e-05, "loss": 3.4561, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.1533639114679797e-05, "loss": 3.4457, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.152526954597301e-05, "loss": 3.4461, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.151688359846249e-05, "loss": 3.4488, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.150849765095197e-05, "loss": 3.4495, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.150011170344145e-05, "loss": 3.4386, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.149174213473466e-05, "loss": 3.4497, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.1483356187224142e-05, "loss": 3.437, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.1474970239713622e-05, "loss": 3.45, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1466584292203102e-05, "loss": 3.4397, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.145821472349631e-05, "loss": 3.4421, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.144982877598579e-05, "loss": 3.439, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.144144282847527e-05, "loss": 3.4339, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.143305688096475e-05, "loss": 3.4363, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1424687312257964e-05, "loss": 3.4474, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1416301364747444e-05, "loss": 3.4442, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.1407915417236924e-05, "loss": 3.4503, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.1399529469726404e-05, "loss": 3.437, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.1391159901019613e-05, "loss": 3.4531, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.1382773953509096e-05, "loss": 3.4495, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.1374388005998576e-05, "loss": 3.4465, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.1366002058488056e-05, "loss": 3.4462, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.1357632489781265e-05, "loss": 3.4434, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.1349246542270745e-05, "loss": 3.4457, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.1340860594760225e-05, "loss": 3.4575, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.1332474647249705e-05, "loss": 3.4385, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.1324105078542917e-05, "loss": 3.4469, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.1315719131032397e-05, "loss": 3.4469, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.1307333183521877e-05, "loss": 3.4468, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1298947236011357e-05, "loss": 3.4359, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.1290577667304566e-05, "loss": 3.4406, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.1282191719794046e-05, "loss": 3.4547, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.127380577228353e-05, "loss": 3.4332, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.126541982477301e-05, "loss": 3.4509, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.8559629917144775, "eval_runtime": 345.1912, "eval_samples_per_second": 1105.448, "eval_steps_per_second": 34.546, "step": 1755360 }, { "epoch": 1.0, "learning_rate": 2.125705025606622e-05, "loss": 3.4406, "step": 1755648 }, { "epoch": 1.0, "learning_rate": 2.12486643085557e-05, "loss": 3.4325, "step": 1756160 }, { "epoch": 1.0, "learning_rate": 2.124027836104518e-05, "loss": 3.4456, "step": 1756672 }, { "epoch": 1.0, "learning_rate": 2.123189241353466e-05, "loss": 3.4346, "step": 1757184 }, { "epoch": 1.0, "learning_rate": 2.122352284482787e-05, "loss": 3.4517, "step": 1757696 }, { "epoch": 1.0, "learning_rate": 2.121513689731735e-05, "loss": 3.443, "step": 1758208 }, { "epoch": 1.0, "learning_rate": 2.120675094980683e-05, "loss": 3.4374, "step": 1758720 }, { "epoch": 1.0, "learning_rate": 2.1198365002296307e-05, "loss": 3.4325, "step": 1759232 }, { "epoch": 1.0, "learning_rate": 2.118999543358952e-05, "loss": 3.4387, "step": 1759744 }, { "epoch": 1.0, "learning_rate": 2.1181609486079e-05, "loss": 3.4449, "step": 1760256 }, { "epoch": 1.0, "learning_rate": 2.1173223538568483e-05, "loss": 3.4357, "step": 1760768 }, { "epoch": 1.0, "learning_rate": 2.116483759105796e-05, "loss": 3.4375, "step": 1761280 }, { "epoch": 1.0, "learning_rate": 2.11564844011549e-05, "loss": 3.441, "step": 1761792 }, { "epoch": 1.0, "learning_rate": 2.114809845364438e-05, "loss": 3.4307, "step": 1762304 }, { "epoch": 1.0, "learning_rate": 2.113971250613386e-05, "loss": 3.4384, "step": 1762816 }, { "epoch": 1.0, "learning_rate": 2.1131326558623345e-05, "loss": 3.4287, "step": 1763328 }, { "epoch": 1.0, "learning_rate": 2.1122940611112825e-05, "loss": 3.4297, "step": 1763840 }, { "epoch": 1.0, "learning_rate": 2.1114554663602305e-05, "loss": 3.4388, "step": 1764352 }, { "epoch": 1.0, "learning_rate": 2.110616871609178e-05, "loss": 3.4394, "step": 1764864 }, { "epoch": 1.0, "learning_rate": 2.109778276858126e-05, "loss": 3.4436, "step": 1765376 }, { "epoch": 1.0, "learning_rate": 2.1089413199874474e-05, "loss": 3.4481, "step": 1765888 }, { "epoch": 1.0, "learning_rate": 2.1081027252363954e-05, "loss": 3.442, "step": 1766400 }, { "epoch": 1.0, "learning_rate": 2.1072641304853434e-05, "loss": 3.4392, "step": 1766912 }, { "epoch": 1.0, "learning_rate": 2.1064255357342913e-05, "loss": 3.4437, "step": 1767424 }, { "epoch": 1.0, "learning_rate": 2.1055885788636126e-05, "loss": 3.4347, "step": 1767936 }, { "epoch": 1.0, "learning_rate": 2.1047499841125603e-05, "loss": 3.4507, "step": 1768448 }, { "epoch": 1.0, "learning_rate": 2.1039113893615082e-05, "loss": 3.4312, "step": 1768960 }, { "epoch": 1.0, "learning_rate": 2.1030727946104566e-05, "loss": 3.4379, "step": 1769472 }, { "epoch": 1.0, "learning_rate": 2.102235837739778e-05, "loss": 3.4304, "step": 1769984 }, { "epoch": 1.0, "learning_rate": 2.1013972429887255e-05, "loss": 3.4345, "step": 1770496 }, { "epoch": 1.01, "learning_rate": 2.1005586482376735e-05, "loss": 3.4375, "step": 1771008 }, { "epoch": 1.01, "learning_rate": 2.0997200534866215e-05, "loss": 3.4434, "step": 1771520 }, { "epoch": 1.01, "learning_rate": 2.0988830966159427e-05, "loss": 3.4423, "step": 1772032 }, { "epoch": 1.01, "learning_rate": 2.0980445018648907e-05, "loss": 3.4447, "step": 1772544 }, { "epoch": 1.01, "learning_rate": 2.0972059071138387e-05, "loss": 3.4319, "step": 1773056 }, { "epoch": 1.01, "learning_rate": 2.0963673123627867e-05, "loss": 3.4458, "step": 1773568 }, { "epoch": 1.01, "learning_rate": 2.0955303554921076e-05, "loss": 3.4414, "step": 1774080 }, { "epoch": 1.01, "learning_rate": 2.0946917607410556e-05, "loss": 3.4348, "step": 1774592 }, { "epoch": 1.01, "learning_rate": 2.0938531659900036e-05, "loss": 3.4376, "step": 1775104 }, { "epoch": 1.01, "learning_rate": 2.093014571238952e-05, "loss": 3.4352, "step": 1775616 }, { "epoch": 1.01, "learning_rate": 2.092177614368273e-05, "loss": 3.4366, "step": 1776128 }, { "epoch": 1.01, "learning_rate": 2.091339019617221e-05, "loss": 3.4467, "step": 1776640 }, { "epoch": 1.01, "learning_rate": 2.090500424866169e-05, "loss": 3.4392, "step": 1777152 }, { "epoch": 1.01, "learning_rate": 2.089661830115117e-05, "loss": 3.4393, "step": 1777664 }, { "epoch": 1.01, "learning_rate": 2.088824873244438e-05, "loss": 3.4464, "step": 1778176 }, { "epoch": 1.01, "learning_rate": 2.087986278493386e-05, "loss": 3.4395, "step": 1778688 }, { "epoch": 1.01, "learning_rate": 2.087147683742334e-05, "loss": 3.4364, "step": 1779200 }, { "epoch": 1.01, "learning_rate": 2.086309088991282e-05, "loss": 3.4345, "step": 1779712 }, { "epoch": 1.01, "learning_rate": 2.085472132120603e-05, "loss": 3.406, "step": 1780224 }, { "epoch": 1.01, "learning_rate": 2.084633537369551e-05, "loss": 3.4488, "step": 1780736 }, { "epoch": 1.01, "learning_rate": 2.083794942618499e-05, "loss": 3.4348, "step": 1781248 }, { "epoch": 1.01, "learning_rate": 2.082956347867447e-05, "loss": 3.4441, "step": 1781760 }, { "epoch": 1.01, "learning_rate": 2.0821193909967682e-05, "loss": 3.4216, "step": 1782272 }, { "epoch": 1.01, "learning_rate": 2.0812807962457162e-05, "loss": 3.4217, "step": 1782784 }, { "epoch": 1.01, "learning_rate": 2.0804422014946642e-05, "loss": 3.419, "step": 1783296 }, { "epoch": 1.01, "learning_rate": 2.0796036067436122e-05, "loss": 3.4314, "step": 1783808 }, { "epoch": 1.01, "learning_rate": 2.0787666498729335e-05, "loss": 3.4341, "step": 1784320 }, { "epoch": 1.01, "learning_rate": 2.0779280551218815e-05, "loss": 3.4257, "step": 1784832 }, { "epoch": 1.01, "learning_rate": 2.0770894603708295e-05, "loss": 3.4448, "step": 1785344 }, { "epoch": 1.01, "learning_rate": 2.0762508656197774e-05, "loss": 3.4275, "step": 1785856 }, { "epoch": 1.01, "learning_rate": 2.0754139087490984e-05, "loss": 3.4311, "step": 1786368 }, { "epoch": 1.01, "learning_rate": 2.0745753139980464e-05, "loss": 3.4429, "step": 1786880 }, { "epoch": 1.01, "learning_rate": 2.0737367192469943e-05, "loss": 3.4154, "step": 1787392 }, { "epoch": 1.01, "learning_rate": 2.0728981244959423e-05, "loss": 3.4257, "step": 1787904 }, { "epoch": 1.01, "learning_rate": 2.0720611676252636e-05, "loss": 3.4345, "step": 1788416 }, { "epoch": 1.01, "learning_rate": 2.0712225728742116e-05, "loss": 3.4407, "step": 1788928 }, { "epoch": 1.01, "learning_rate": 2.0703839781231596e-05, "loss": 3.4166, "step": 1789440 }, { "epoch": 1.01, "learning_rate": 2.0695453833721076e-05, "loss": 3.4308, "step": 1789952 }, { "epoch": 1.01, "learning_rate": 2.0687084265014285e-05, "loss": 3.4198, "step": 1790464 }, { "epoch": 1.01, "learning_rate": 2.0678698317503768e-05, "loss": 3.4397, "step": 1790976 }, { "epoch": 1.01, "learning_rate": 2.0670312369993248e-05, "loss": 3.4377, "step": 1791488 }, { "epoch": 1.01, "learning_rate": 2.0661926422482728e-05, "loss": 3.4345, "step": 1792000 }, { "epoch": 1.01, "learning_rate": 2.0653556853775937e-05, "loss": 3.4442, "step": 1792512 }, { "epoch": 1.01, "learning_rate": 2.0645170906265417e-05, "loss": 3.4438, "step": 1793024 }, { "epoch": 1.01, "learning_rate": 2.0636784958754897e-05, "loss": 3.4582, "step": 1793536 }, { "epoch": 1.01, "learning_rate": 2.0628399011244377e-05, "loss": 3.4357, "step": 1794048 }, { "epoch": 1.01, "learning_rate": 2.062002944253759e-05, "loss": 3.4376, "step": 1794560 }, { "epoch": 1.01, "learning_rate": 2.061164349502707e-05, "loss": 3.4397, "step": 1795072 }, { "epoch": 1.01, "learning_rate": 2.060325754751655e-05, "loss": 3.4243, "step": 1795584 }, { "epoch": 1.01, "learning_rate": 2.0594871600006026e-05, "loss": 3.4371, "step": 1796096 }, { "epoch": 1.01, "learning_rate": 2.058650203129924e-05, "loss": 3.4371, "step": 1796608 }, { "epoch": 1.01, "learning_rate": 2.0578116083788722e-05, "loss": 3.4422, "step": 1797120 }, { "epoch": 1.01, "learning_rate": 2.0569730136278202e-05, "loss": 3.4407, "step": 1797632 }, { "epoch": 1.01, "learning_rate": 2.056134418876768e-05, "loss": 3.4277, "step": 1798144 }, { "epoch": 1.01, "learning_rate": 2.055297462006089e-05, "loss": 3.4237, "step": 1798656 }, { "epoch": 1.01, "learning_rate": 2.054458867255037e-05, "loss": 3.4269, "step": 1799168 }, { "epoch": 1.01, "learning_rate": 2.053620272503985e-05, "loss": 3.4448, "step": 1799680 }, { "epoch": 1.01, "learning_rate": 2.052781677752933e-05, "loss": 3.4373, "step": 1800192 }, { "epoch": 1.01, "learning_rate": 2.0519447208822543e-05, "loss": 3.429, "step": 1800704 }, { "epoch": 1.02, "learning_rate": 2.0511061261312023e-05, "loss": 3.4306, "step": 1801216 }, { "epoch": 1.02, "learning_rate": 2.05026753138015e-05, "loss": 3.4381, "step": 1801728 }, { "epoch": 1.02, "learning_rate": 2.049428936629098e-05, "loss": 3.4271, "step": 1802240 }, { "epoch": 1.02, "learning_rate": 2.0485919797584192e-05, "loss": 3.4288, "step": 1802752 }, { "epoch": 1.02, "learning_rate": 2.0477533850073676e-05, "loss": 3.4441, "step": 1803264 }, { "epoch": 1.02, "learning_rate": 2.0469147902563152e-05, "loss": 3.4364, "step": 1803776 }, { "epoch": 1.02, "learning_rate": 2.0460761955052632e-05, "loss": 3.4374, "step": 1804288 }, { "epoch": 1.02, "learning_rate": 2.0452392386345845e-05, "loss": 3.4283, "step": 1804800 }, { "epoch": 1.02, "learning_rate": 2.044400643883532e-05, "loss": 3.4369, "step": 1805312 }, { "epoch": 1.02, "learning_rate": 2.0435620491324804e-05, "loss": 3.4278, "step": 1805824 }, { "epoch": 1.02, "learning_rate": 2.0427234543814284e-05, "loss": 3.4454, "step": 1806336 }, { "epoch": 1.02, "learning_rate": 2.0418864975107497e-05, "loss": 3.4384, "step": 1806848 }, { "epoch": 1.02, "learning_rate": 2.0410479027596973e-05, "loss": 3.4422, "step": 1807360 }, { "epoch": 1.02, "learning_rate": 2.0402093080086453e-05, "loss": 3.435, "step": 1807872 }, { "epoch": 1.02, "learning_rate": 2.0393707132575933e-05, "loss": 3.4362, "step": 1808384 }, { "epoch": 1.02, "learning_rate": 2.0385321185065413e-05, "loss": 3.4255, "step": 1808896 }, { "epoch": 1.02, "learning_rate": 2.0376951616358626e-05, "loss": 3.4283, "step": 1809408 }, { "epoch": 1.02, "learning_rate": 2.0368565668848106e-05, "loss": 3.4213, "step": 1809920 }, { "epoch": 1.02, "learning_rate": 2.0360179721337586e-05, "loss": 3.4394, "step": 1810432 }, { "epoch": 1.02, "learning_rate": 2.0351793773827066e-05, "loss": 3.4218, "step": 1810944 }, { "epoch": 1.02, "learning_rate": 2.0343424205120275e-05, "loss": 3.4275, "step": 1811456 }, { "epoch": 1.02, "learning_rate": 2.0335038257609755e-05, "loss": 3.4223, "step": 1811968 }, { "epoch": 1.02, "learning_rate": 2.0326652310099238e-05, "loss": 3.4341, "step": 1812480 }, { "epoch": 1.02, "learning_rate": 2.0318266362588718e-05, "loss": 3.4321, "step": 1812992 }, { "epoch": 1.02, "learning_rate": 2.0309896793881927e-05, "loss": 3.4232, "step": 1813504 }, { "epoch": 1.02, "learning_rate": 2.0301510846371407e-05, "loss": 3.438, "step": 1814016 }, { "epoch": 1.02, "learning_rate": 2.0293124898860887e-05, "loss": 3.4411, "step": 1814528 }, { "epoch": 1.02, "learning_rate": 2.0284738951350367e-05, "loss": 3.4351, "step": 1815040 }, { "epoch": 1.02, "learning_rate": 2.027636938264358e-05, "loss": 3.4387, "step": 1815552 }, { "epoch": 1.02, "learning_rate": 2.026798343513306e-05, "loss": 3.4378, "step": 1816064 }, { "epoch": 1.02, "learning_rate": 2.025959748762254e-05, "loss": 3.4356, "step": 1816576 }, { "epoch": 1.02, "learning_rate": 2.025121154011202e-05, "loss": 3.4308, "step": 1817088 }, { "epoch": 1.02, "learning_rate": 2.024284197140523e-05, "loss": 3.4372, "step": 1817600 }, { "epoch": 1.02, "learning_rate": 2.023445602389471e-05, "loss": 3.427, "step": 1818112 }, { "epoch": 1.02, "learning_rate": 2.0226070076384192e-05, "loss": 3.4378, "step": 1818624 }, { "epoch": 1.02, "learning_rate": 2.0217684128873672e-05, "loss": 3.4302, "step": 1819136 }, { "epoch": 1.02, "learning_rate": 2.020931456016688e-05, "loss": 3.4323, "step": 1819648 }, { "epoch": 1.02, "learning_rate": 2.020092861265636e-05, "loss": 3.4256, "step": 1820160 }, { "epoch": 1.02, "learning_rate": 2.019254266514584e-05, "loss": 3.4228, "step": 1820672 }, { "epoch": 1.02, "learning_rate": 2.018415671763532e-05, "loss": 3.4256, "step": 1821184 }, { "epoch": 1.02, "learning_rate": 2.0175787148928533e-05, "loss": 3.4364, "step": 1821696 }, { "epoch": 1.02, "learning_rate": 2.0167401201418013e-05, "loss": 3.4335, "step": 1822208 }, { "epoch": 1.02, "learning_rate": 2.0159015253907493e-05, "loss": 3.4407, "step": 1822720 }, { "epoch": 1.02, "learning_rate": 2.0150629306396973e-05, "loss": 3.4237, "step": 1823232 }, { "epoch": 1.02, "learning_rate": 2.0142259737690182e-05, "loss": 3.4459, "step": 1823744 }, { "epoch": 1.02, "learning_rate": 2.0133873790179662e-05, "loss": 3.4345, "step": 1824256 }, { "epoch": 1.02, "learning_rate": 2.0125487842669145e-05, "loss": 3.4351, "step": 1824768 }, { "epoch": 1.02, "learning_rate": 2.0117101895158625e-05, "loss": 3.435, "step": 1825280 }, { "epoch": 1.02, "learning_rate": 2.0108732326451834e-05, "loss": 3.4304, "step": 1825792 }, { "epoch": 1.02, "learning_rate": 2.0100346378941314e-05, "loss": 3.4337, "step": 1826304 }, { "epoch": 1.02, "learning_rate": 2.0091960431430794e-05, "loss": 3.4443, "step": 1826816 }, { "epoch": 1.02, "learning_rate": 2.0083574483920274e-05, "loss": 3.4284, "step": 1827328 }, { "epoch": 1.02, "learning_rate": 2.0075204915213487e-05, "loss": 3.4383, "step": 1827840 }, { "epoch": 1.02, "learning_rate": 2.0066818967702967e-05, "loss": 3.4355, "step": 1828352 }, { "epoch": 1.02, "learning_rate": 2.0058433020192447e-05, "loss": 3.4314, "step": 1828864 }, { "epoch": 1.02, "learning_rate": 2.0050047072681923e-05, "loss": 3.4256, "step": 1829376 }, { "epoch": 1.02, "learning_rate": 2.0041677503975136e-05, "loss": 3.4289, "step": 1829888 }, { "epoch": 1.02, "learning_rate": 2.0033291556464616e-05, "loss": 3.4403, "step": 1830400 }, { "epoch": 1.02, "learning_rate": 2.00249056089541e-05, "loss": 3.4264, "step": 1830912 }, { "epoch": 1.02, "learning_rate": 2.0016519661443576e-05, "loss": 3.438, "step": 1831424 }, { "epoch": 1.03, "eval_loss": 3.8573296070098877, "eval_runtime": 336.877, "eval_samples_per_second": 1132.731, "eval_steps_per_second": 35.399, "step": 1831680 }, { "epoch": 0.0, "learning_rate": 2.0008150092736788e-05, "loss": 3.4245, "step": 1831936 }, { "epoch": 0.0, "learning_rate": 1.9999764145226268e-05, "loss": 3.4247, "step": 1832448 }, { "epoch": 0.0, "learning_rate": 1.9991378197715748e-05, "loss": 3.4285, "step": 1832960 }, { "epoch": 0.0, "learning_rate": 1.9982992250205228e-05, "loss": 3.4301, "step": 1833472 }, { "epoch": 0.0, "learning_rate": 1.997462268149844e-05, "loss": 3.4425, "step": 1833984 }, { "epoch": 0.0, "learning_rate": 1.996623673398792e-05, "loss": 3.4301, "step": 1834496 }, { "epoch": 0.0, "learning_rate": 1.9957850786477397e-05, "loss": 3.4284, "step": 1835008 }, { "epoch": 0.0, "learning_rate": 1.9949464838966877e-05, "loss": 3.4254, "step": 1835520 }, { "epoch": 0.0, "learning_rate": 1.994109527026009e-05, "loss": 3.4251, "step": 1836032 }, { "epoch": 0.0, "learning_rate": 1.993270932274957e-05, "loss": 3.4358, "step": 1836544 }, { "epoch": 0.0, "learning_rate": 1.992432337523905e-05, "loss": 3.4233, "step": 1837056 }, { "epoch": 0.0, "learning_rate": 1.991593742772853e-05, "loss": 3.4246, "step": 1837568 }, { "epoch": 0.0, "learning_rate": 1.990758423782547e-05, "loss": 3.439, "step": 1838080 }, { "epoch": 0.0, "learning_rate": 1.989919829031495e-05, "loss": 3.4147, "step": 1838592 }, { "epoch": 0.0, "learning_rate": 1.989081234280443e-05, "loss": 3.4232, "step": 1839104 }, { "epoch": 0.0, "learning_rate": 1.9882426395293914e-05, "loss": 3.42, "step": 1839616 }, { "epoch": 0.0, "learning_rate": 1.9874040447783394e-05, "loss": 3.4204, "step": 1840128 }, { "epoch": 0.0, "learning_rate": 1.986565450027287e-05, "loss": 3.4289, "step": 1840640 }, { "epoch": 0.0, "learning_rate": 1.985726855276235e-05, "loss": 3.43, "step": 1841152 }, { "epoch": 0.0, "learning_rate": 1.984888260525183e-05, "loss": 3.429, "step": 1841664 }, { "epoch": 0.0, "learning_rate": 1.9840513036545043e-05, "loss": 3.4407, "step": 1842176 }, { "epoch": 0.0, "learning_rate": 1.9832127089034523e-05, "loss": 3.4308, "step": 1842688 }, { "epoch": 0.0, "learning_rate": 1.9823741141524003e-05, "loss": 3.4312, "step": 1843200 }, { "epoch": 0.0, "learning_rate": 1.9815355194013483e-05, "loss": 3.4274, "step": 1843712 }, { "epoch": 0.0, "learning_rate": 1.9806985625306695e-05, "loss": 3.4268, "step": 1844224 }, { "epoch": 0.0, "learning_rate": 1.9798599677796172e-05, "loss": 3.4365, "step": 1844736 }, { "epoch": 0.0, "learning_rate": 1.9790213730285652e-05, "loss": 3.4217, "step": 1845248 }, { "epoch": 0.0, "learning_rate": 1.9781827782775132e-05, "loss": 3.4277, "step": 1845760 }, { "epoch": 0.0, "learning_rate": 1.9773458214068344e-05, "loss": 3.418, "step": 1846272 }, { "epoch": 0.0, "learning_rate": 1.9765072266557824e-05, "loss": 3.4261, "step": 1846784 }, { "epoch": 0.01, "learning_rate": 1.9756686319047304e-05, "loss": 3.4244, "step": 1847296 }, { "epoch": 0.01, "learning_rate": 1.9748300371536784e-05, "loss": 3.4323, "step": 1847808 }, { "epoch": 0.01, "learning_rate": 1.9739930802829993e-05, "loss": 3.4351, "step": 1848320 }, { "epoch": 0.01, "learning_rate": 1.9731544855319477e-05, "loss": 3.4375, "step": 1848832 }, { "epoch": 0.01, "learning_rate": 1.9723158907808957e-05, "loss": 3.4234, "step": 1849344 }, { "epoch": 0.01, "learning_rate": 1.9714772960298437e-05, "loss": 3.4277, "step": 1849856 }, { "epoch": 0.01, "learning_rate": 1.9706403391591646e-05, "loss": 3.4326, "step": 1850368 }, { "epoch": 0.01, "learning_rate": 1.9698017444081126e-05, "loss": 3.4251, "step": 1850880 }, { "epoch": 0.01, "learning_rate": 1.9689631496570606e-05, "loss": 3.4257, "step": 1851392 }, { "epoch": 0.01, "learning_rate": 1.9681245549060086e-05, "loss": 3.423, "step": 1851904 }, { "epoch": 0.01, "learning_rate": 1.9672875980353298e-05, "loss": 3.4278, "step": 1852416 }, { "epoch": 0.01, "learning_rate": 1.9664490032842778e-05, "loss": 3.427, "step": 1852928 }, { "epoch": 0.01, "learning_rate": 1.9656104085332258e-05, "loss": 3.4337, "step": 1853440 }, { "epoch": 0.01, "learning_rate": 1.9647718137821738e-05, "loss": 3.4286, "step": 1853952 }, { "epoch": 0.01, "learning_rate": 1.9639348569114947e-05, "loss": 3.4335, "step": 1854464 }, { "epoch": 0.01, "learning_rate": 1.963096262160443e-05, "loss": 3.4312, "step": 1854976 }, { "epoch": 0.01, "learning_rate": 1.962257667409391e-05, "loss": 3.4259, "step": 1855488 }, { "epoch": 0.01, "learning_rate": 1.961419072658339e-05, "loss": 3.4255, "step": 1856000 }, { "epoch": 0.01, "learning_rate": 1.96058211578766e-05, "loss": 3.3923, "step": 1856512 }, { "epoch": 0.01, "learning_rate": 1.959743521036608e-05, "loss": 3.4398, "step": 1857024 }, { "epoch": 0.01, "learning_rate": 1.958904926285556e-05, "loss": 3.4222, "step": 1857536 }, { "epoch": 0.01, "learning_rate": 1.958066331534504e-05, "loss": 3.4348, "step": 1858048 }, { "epoch": 0.01, "learning_rate": 1.9572293746638252e-05, "loss": 3.4171, "step": 1858560 }, { "epoch": 0.01, "learning_rate": 1.9563907799127732e-05, "loss": 3.4115, "step": 1859072 }, { "epoch": 0.01, "learning_rate": 1.9555521851617212e-05, "loss": 3.4065, "step": 1859584 }, { "epoch": 0.01, "learning_rate": 1.954713590410669e-05, "loss": 3.4181, "step": 1860096 }, { "epoch": 0.01, "learning_rate": 1.95387663353999e-05, "loss": 3.4249, "step": 1860608 }, { "epoch": 0.01, "learning_rate": 1.9530380387889384e-05, "loss": 3.4175, "step": 1861120 }, { "epoch": 0.01, "learning_rate": 1.9521994440378864e-05, "loss": 3.4308, "step": 1861632 }, { "epoch": 0.01, "learning_rate": 1.9513608492868344e-05, "loss": 3.4184, "step": 1862144 }, { "epoch": 0.01, "learning_rate": 1.9505238924161553e-05, "loss": 3.4186, "step": 1862656 }, { "epoch": 0.01, "learning_rate": 1.9496852976651033e-05, "loss": 3.4282, "step": 1863168 }, { "epoch": 0.01, "learning_rate": 1.9488467029140513e-05, "loss": 3.4084, "step": 1863680 }, { "epoch": 0.01, "learning_rate": 1.9480081081629993e-05, "loss": 3.4149, "step": 1864192 }, { "epoch": 0.01, "learning_rate": 1.9471711512923205e-05, "loss": 3.4249, "step": 1864704 }, { "epoch": 0.01, "learning_rate": 1.9463325565412685e-05, "loss": 3.4268, "step": 1865216 }, { "epoch": 0.01, "learning_rate": 1.9454939617902165e-05, "loss": 3.4103, "step": 1865728 }, { "epoch": 0.01, "learning_rate": 1.9446553670391645e-05, "loss": 3.4166, "step": 1866240 }, { "epoch": 0.01, "learning_rate": 1.9438184101684854e-05, "loss": 3.4085, "step": 1866752 }, { "epoch": 0.01, "learning_rate": 1.9429798154174338e-05, "loss": 3.4296, "step": 1867264 }, { "epoch": 0.01, "learning_rate": 1.9421412206663818e-05, "loss": 3.4301, "step": 1867776 }, { "epoch": 0.01, "learning_rate": 1.9413026259153294e-05, "loss": 3.4237, "step": 1868288 }, { "epoch": 0.01, "learning_rate": 1.9404656690446507e-05, "loss": 3.4322, "step": 1868800 }, { "epoch": 0.01, "learning_rate": 1.9396270742935987e-05, "loss": 3.432, "step": 1869312 }, { "epoch": 0.01, "learning_rate": 1.9387884795425467e-05, "loss": 3.4487, "step": 1869824 }, { "epoch": 0.01, "learning_rate": 1.9379498847914947e-05, "loss": 3.4256, "step": 1870336 }, { "epoch": 0.01, "learning_rate": 1.9371112900404427e-05, "loss": 3.4269, "step": 1870848 }, { "epoch": 0.01, "learning_rate": 1.936274333169764e-05, "loss": 3.4232, "step": 1871360 }, { "epoch": 0.01, "learning_rate": 1.935435738418712e-05, "loss": 3.4189, "step": 1871872 }, { "epoch": 0.01, "learning_rate": 1.9345971436676596e-05, "loss": 3.4263, "step": 1872384 }, { "epoch": 0.01, "learning_rate": 1.9337585489166076e-05, "loss": 3.4273, "step": 1872896 }, { "epoch": 0.01, "learning_rate": 1.932921592045929e-05, "loss": 3.429, "step": 1873408 }, { "epoch": 0.01, "learning_rate": 1.9320829972948768e-05, "loss": 3.4327, "step": 1873920 }, { "epoch": 0.01, "learning_rate": 1.9312444025438248e-05, "loss": 3.4143, "step": 1874432 }, { "epoch": 0.01, "learning_rate": 1.9304058077927728e-05, "loss": 3.413, "step": 1874944 }, { "epoch": 0.01, "learning_rate": 1.929568850922094e-05, "loss": 3.4177, "step": 1875456 }, { "epoch": 0.01, "learning_rate": 1.9287302561710417e-05, "loss": 3.4357, "step": 1875968 }, { "epoch": 0.01, "learning_rate": 1.92789166141999e-05, "loss": 3.428, "step": 1876480 }, { "epoch": 0.01, "learning_rate": 1.927053066668938e-05, "loss": 3.4163, "step": 1876992 }, { "epoch": 0.02, "learning_rate": 1.9262161097982593e-05, "loss": 3.4216, "step": 1877504 }, { "epoch": 0.02, "learning_rate": 1.925377515047207e-05, "loss": 3.4266, "step": 1878016 }, { "epoch": 0.02, "learning_rate": 1.924538920296155e-05, "loss": 3.42, "step": 1878528 }, { "epoch": 0.02, "learning_rate": 1.923700325545103e-05, "loss": 3.4156, "step": 1879040 }, { "epoch": 0.02, "learning_rate": 1.9228633686744242e-05, "loss": 3.433, "step": 1879552 }, { "epoch": 0.02, "learning_rate": 1.922024773923372e-05, "loss": 3.4297, "step": 1880064 }, { "epoch": 0.02, "learning_rate": 1.92118617917232e-05, "loss": 3.4261, "step": 1880576 }, { "epoch": 0.02, "learning_rate": 1.920347584421268e-05, "loss": 3.4164, "step": 1881088 }, { "epoch": 0.02, "learning_rate": 1.919510627550589e-05, "loss": 3.4221, "step": 1881600 }, { "epoch": 0.02, "learning_rate": 1.918672032799537e-05, "loss": 3.4208, "step": 1882112 }, { "epoch": 0.02, "learning_rate": 1.9178334380484854e-05, "loss": 3.4337, "step": 1882624 }, { "epoch": 0.02, "learning_rate": 1.9169948432974334e-05, "loss": 3.4259, "step": 1883136 }, { "epoch": 0.02, "learning_rate": 1.9161578864267543e-05, "loss": 3.4278, "step": 1883648 }, { "epoch": 0.02, "learning_rate": 1.9153192916757023e-05, "loss": 3.4292, "step": 1884160 }, { "epoch": 0.02, "learning_rate": 1.9144806969246503e-05, "loss": 3.4225, "step": 1884672 }, { "epoch": 0.02, "learning_rate": 1.9136421021735983e-05, "loss": 3.4225, "step": 1885184 }, { "epoch": 0.02, "learning_rate": 1.9128051453029195e-05, "loss": 3.4145, "step": 1885696 }, { "epoch": 0.02, "learning_rate": 1.9119665505518675e-05, "loss": 3.4087, "step": 1886208 }, { "epoch": 0.02, "learning_rate": 1.9111279558008155e-05, "loss": 3.4312, "step": 1886720 }, { "epoch": 0.02, "learning_rate": 1.9102893610497635e-05, "loss": 3.4143, "step": 1887232 }, { "epoch": 0.02, "learning_rate": 1.9094524041790844e-05, "loss": 3.4116, "step": 1887744 }, { "epoch": 0.02, "learning_rate": 1.9086138094280324e-05, "loss": 3.4126, "step": 1888256 }, { "epoch": 0.02, "learning_rate": 1.9077752146769808e-05, "loss": 3.4146, "step": 1888768 }, { "epoch": 0.02, "learning_rate": 1.9069366199259288e-05, "loss": 3.4269, "step": 1889280 }, { "epoch": 0.02, "learning_rate": 1.9060996630552497e-05, "loss": 3.4178, "step": 1889792 }, { "epoch": 0.02, "learning_rate": 1.9052610683041977e-05, "loss": 3.4261, "step": 1890304 }, { "epoch": 0.02, "learning_rate": 1.9044224735531457e-05, "loss": 3.4317, "step": 1890816 }, { "epoch": 0.02, "learning_rate": 1.9035838788020937e-05, "loss": 3.4283, "step": 1891328 }, { "epoch": 0.02, "learning_rate": 1.902746921931415e-05, "loss": 3.4258, "step": 1891840 }, { "epoch": 0.02, "learning_rate": 1.901908327180363e-05, "loss": 3.4258, "step": 1892352 }, { "epoch": 0.02, "learning_rate": 1.901069732429311e-05, "loss": 3.4256, "step": 1892864 }, { "epoch": 0.02, "learning_rate": 1.900231137678259e-05, "loss": 3.4206, "step": 1893376 }, { "epoch": 0.02, "learning_rate": 1.8993941808075798e-05, "loss": 3.4252, "step": 1893888 }, { "epoch": 0.02, "learning_rate": 1.8985555860565278e-05, "loss": 3.4215, "step": 1894400 }, { "epoch": 0.02, "learning_rate": 1.897716991305476e-05, "loss": 3.4277, "step": 1894912 }, { "epoch": 0.02, "learning_rate": 1.896878396554424e-05, "loss": 3.4215, "step": 1895424 }, { "epoch": 0.02, "learning_rate": 1.896041439683745e-05, "loss": 3.4188, "step": 1895936 }, { "epoch": 0.02, "learning_rate": 1.895202844932693e-05, "loss": 3.4151, "step": 1896448 }, { "epoch": 0.02, "learning_rate": 1.894364250181641e-05, "loss": 3.4131, "step": 1896960 }, { "epoch": 0.02, "learning_rate": 1.893525655430589e-05, "loss": 3.4146, "step": 1897472 }, { "epoch": 0.02, "learning_rate": 1.8926886985599103e-05, "loss": 3.4246, "step": 1897984 }, { "epoch": 0.02, "learning_rate": 1.8918501038088583e-05, "loss": 3.4184, "step": 1898496 }, { "epoch": 0.02, "learning_rate": 1.8910115090578063e-05, "loss": 3.4327, "step": 1899008 }, { "epoch": 0.02, "learning_rate": 1.8901729143067543e-05, "loss": 3.4146, "step": 1899520 }, { "epoch": 0.02, "learning_rate": 1.889335957436075e-05, "loss": 3.4318, "step": 1900032 }, { "epoch": 0.02, "learning_rate": 1.888497362685023e-05, "loss": 3.4249, "step": 1900544 }, { "epoch": 0.02, "learning_rate": 1.8876587679339715e-05, "loss": 3.4253, "step": 1901056 }, { "epoch": 0.02, "learning_rate": 1.886820173182919e-05, "loss": 3.4258, "step": 1901568 }, { "epoch": 0.02, "learning_rate": 1.8859832163122404e-05, "loss": 3.4197, "step": 1902080 }, { "epoch": 0.02, "learning_rate": 1.8851446215611884e-05, "loss": 3.4263, "step": 1902592 }, { "epoch": 0.02, "learning_rate": 1.8843060268101364e-05, "loss": 3.4344, "step": 1903104 }, { "epoch": 0.02, "learning_rate": 1.883467432059084e-05, "loss": 3.4149, "step": 1903616 }, { "epoch": 0.02, "learning_rate": 1.8826304751884056e-05, "loss": 3.4277, "step": 1904128 }, { "epoch": 0.02, "learning_rate": 1.8817918804373536e-05, "loss": 3.4223, "step": 1904640 }, { "epoch": 0.02, "learning_rate": 1.8809532856863016e-05, "loss": 3.4196, "step": 1905152 }, { "epoch": 0.02, "learning_rate": 1.8801146909352493e-05, "loss": 3.4193, "step": 1905664 }, { "epoch": 0.02, "learning_rate": 1.8792777340645705e-05, "loss": 3.4172, "step": 1906176 }, { "epoch": 0.02, "learning_rate": 1.8784391393135185e-05, "loss": 3.4304, "step": 1906688 }, { "epoch": 0.02, "learning_rate": 1.8776005445624665e-05, "loss": 3.4188, "step": 1907200 }, { "epoch": 0.02, "learning_rate": 1.8767619498114145e-05, "loss": 3.4261, "step": 1907712 }, { "epoch": 0.03, "eval_loss": 3.858802318572998, "eval_runtime": 303.6604, "eval_samples_per_second": 1256.637, "eval_steps_per_second": 39.271, "step": 1908000 }, { "epoch": 1.0, "learning_rate": 1.8759249929407358e-05, "loss": 3.4137, "step": 1908224 }, { "epoch": 1.0, "learning_rate": 1.8750863981896838e-05, "loss": 3.4136, "step": 1908736 }, { "epoch": 1.0, "learning_rate": 1.8742478034386314e-05, "loss": 3.4177, "step": 1909248 }, { "epoch": 1.0, "learning_rate": 1.8734092086875794e-05, "loss": 3.421, "step": 1909760 }, { "epoch": 1.0, "learning_rate": 1.872572251816901e-05, "loss": 3.4338, "step": 1910272 }, { "epoch": 1.0, "learning_rate": 1.871733657065849e-05, "loss": 3.4184, "step": 1910784 }, { "epoch": 1.0, "learning_rate": 1.8708950623147967e-05, "loss": 3.4173, "step": 1911296 }, { "epoch": 1.0, "learning_rate": 1.8700564675637447e-05, "loss": 3.4172, "step": 1911808 }, { "epoch": 1.0, "learning_rate": 1.869219510693066e-05, "loss": 3.4127, "step": 1912320 }, { "epoch": 1.0, "learning_rate": 1.868380915942014e-05, "loss": 3.4262, "step": 1912832 }, { "epoch": 1.0, "learning_rate": 1.867542321190962e-05, "loss": 3.4138, "step": 1913344 }, { "epoch": 1.0, "learning_rate": 1.86670372643991e-05, "loss": 3.4163, "step": 1913856 }, { "epoch": 1.0, "learning_rate": 1.865868407449604e-05, "loss": 3.4288, "step": 1914368 }, { "epoch": 1.0, "learning_rate": 1.865029812698552e-05, "loss": 3.4045, "step": 1914880 }, { "epoch": 1.0, "learning_rate": 1.8641912179475e-05, "loss": 3.4113, "step": 1915392 }, { "epoch": 1.0, "learning_rate": 1.8633526231964484e-05, "loss": 3.408, "step": 1915904 }, { "epoch": 1.0, "learning_rate": 1.8625140284453964e-05, "loss": 3.4122, "step": 1916416 }, { "epoch": 1.0, "learning_rate": 1.861675433694344e-05, "loss": 3.4114, "step": 1916928 }, { "epoch": 1.0, "learning_rate": 1.860836838943292e-05, "loss": 3.4227, "step": 1917440 }, { "epoch": 1.0, "learning_rate": 1.85999824419224e-05, "loss": 3.4192, "step": 1917952 }, { "epoch": 1.0, "learning_rate": 1.859161287321561e-05, "loss": 3.4293, "step": 1918464 }, { "epoch": 1.0, "learning_rate": 1.8583226925705093e-05, "loss": 3.4186, "step": 1918976 }, { "epoch": 1.0, "learning_rate": 1.8574840978194573e-05, "loss": 3.4212, "step": 1919488 }, { "epoch": 1.0, "learning_rate": 1.8566455030684053e-05, "loss": 3.4169, "step": 1920000 }, { "epoch": 1.0, "learning_rate": 1.855808546197726e-05, "loss": 3.4183, "step": 1920512 }, { "epoch": 1.0, "learning_rate": 1.854969951446674e-05, "loss": 3.426, "step": 1921024 }, { "epoch": 1.0, "learning_rate": 1.854131356695622e-05, "loss": 3.4101, "step": 1921536 }, { "epoch": 1.0, "learning_rate": 1.85329276194457e-05, "loss": 3.4212, "step": 1922048 }, { "epoch": 1.0, "learning_rate": 1.8524558050738914e-05, "loss": 3.403, "step": 1922560 }, { "epoch": 1.0, "learning_rate": 1.8516172103228394e-05, "loss": 3.4141, "step": 1923072 }, { "epoch": 1.01, "learning_rate": 1.8507786155717874e-05, "loss": 3.4162, "step": 1923584 }, { "epoch": 1.01, "learning_rate": 1.8499400208207354e-05, "loss": 3.4175, "step": 1924096 }, { "epoch": 1.01, "learning_rate": 1.8491030639500563e-05, "loss": 3.4263, "step": 1924608 }, { "epoch": 1.01, "learning_rate": 1.8482644691990046e-05, "loss": 3.425, "step": 1925120 }, { "epoch": 1.01, "learning_rate": 1.8474258744479526e-05, "loss": 3.414, "step": 1925632 }, { "epoch": 1.01, "learning_rate": 1.8465872796969006e-05, "loss": 3.4111, "step": 1926144 }, { "epoch": 1.01, "learning_rate": 1.8457503228262215e-05, "loss": 3.4272, "step": 1926656 }, { "epoch": 1.01, "learning_rate": 1.8449117280751695e-05, "loss": 3.4165, "step": 1927168 }, { "epoch": 1.01, "learning_rate": 1.8440731333241175e-05, "loss": 3.4147, "step": 1927680 }, { "epoch": 1.01, "learning_rate": 1.8432345385730655e-05, "loss": 3.4114, "step": 1928192 }, { "epoch": 1.01, "learning_rate": 1.8423975817023868e-05, "loss": 3.4203, "step": 1928704 }, { "epoch": 1.01, "learning_rate": 1.8415589869513348e-05, "loss": 3.4163, "step": 1929216 }, { "epoch": 1.01, "learning_rate": 1.8407203922002828e-05, "loss": 3.4201, "step": 1929728 }, { "epoch": 1.01, "learning_rate": 1.8398817974492308e-05, "loss": 3.4196, "step": 1930240 }, { "epoch": 1.01, "learning_rate": 1.8390448405785517e-05, "loss": 3.4193, "step": 1930752 }, { "epoch": 1.01, "learning_rate": 1.8382062458275e-05, "loss": 3.4222, "step": 1931264 }, { "epoch": 1.01, "learning_rate": 1.837367651076448e-05, "loss": 3.416, "step": 1931776 }, { "epoch": 1.01, "learning_rate": 1.836529056325396e-05, "loss": 3.4169, "step": 1932288 }, { "epoch": 1.01, "learning_rate": 1.835692099454717e-05, "loss": 3.3831, "step": 1932800 }, { "epoch": 1.01, "learning_rate": 1.834853504703665e-05, "loss": 3.4262, "step": 1933312 }, { "epoch": 1.01, "learning_rate": 1.834014909952613e-05, "loss": 3.411, "step": 1933824 }, { "epoch": 1.01, "learning_rate": 1.833176315201561e-05, "loss": 3.4265, "step": 1934336 }, { "epoch": 1.01, "learning_rate": 1.832339358330882e-05, "loss": 3.4046, "step": 1934848 }, { "epoch": 1.01, "learning_rate": 1.83150076357983e-05, "loss": 3.3996, "step": 1935360 }, { "epoch": 1.01, "learning_rate": 1.830662168828778e-05, "loss": 3.3957, "step": 1935872 }, { "epoch": 1.01, "learning_rate": 1.829823574077726e-05, "loss": 3.4097, "step": 1936384 }, { "epoch": 1.01, "learning_rate": 1.828986617207047e-05, "loss": 3.4223, "step": 1936896 }, { "epoch": 1.01, "learning_rate": 1.8281480224559954e-05, "loss": 3.4022, "step": 1937408 }, { "epoch": 1.01, "learning_rate": 1.8273094277049434e-05, "loss": 3.4224, "step": 1937920 }, { "epoch": 1.01, "learning_rate": 1.8264708329538914e-05, "loss": 3.4117, "step": 1938432 }, { "epoch": 1.01, "learning_rate": 1.8256338760832123e-05, "loss": 3.4007, "step": 1938944 }, { "epoch": 1.01, "learning_rate": 1.8247952813321603e-05, "loss": 3.4191, "step": 1939456 }, { "epoch": 1.01, "learning_rate": 1.8239566865811083e-05, "loss": 3.4028, "step": 1939968 }, { "epoch": 1.01, "learning_rate": 1.8231180918300563e-05, "loss": 3.4002, "step": 1940480 }, { "epoch": 1.01, "learning_rate": 1.8222811349593775e-05, "loss": 3.4147, "step": 1940992 }, { "epoch": 1.01, "learning_rate": 1.8214425402083255e-05, "loss": 3.4187, "step": 1941504 }, { "epoch": 1.01, "learning_rate": 1.8206039454572735e-05, "loss": 3.4017, "step": 1942016 }, { "epoch": 1.01, "learning_rate": 1.819765350706221e-05, "loss": 3.4059, "step": 1942528 }, { "epoch": 1.01, "learning_rate": 1.8189283938355424e-05, "loss": 3.3983, "step": 1943040 }, { "epoch": 1.01, "learning_rate": 1.8180897990844907e-05, "loss": 3.4158, "step": 1943552 }, { "epoch": 1.01, "learning_rate": 1.8172512043334387e-05, "loss": 3.4209, "step": 1944064 }, { "epoch": 1.01, "learning_rate": 1.8164126095823864e-05, "loss": 3.4131, "step": 1944576 }, { "epoch": 1.01, "learning_rate": 1.8155756527117076e-05, "loss": 3.4196, "step": 1945088 }, { "epoch": 1.01, "learning_rate": 1.8147370579606556e-05, "loss": 3.4205, "step": 1945600 }, { "epoch": 1.01, "learning_rate": 1.8138984632096033e-05, "loss": 3.4352, "step": 1946112 }, { "epoch": 1.01, "learning_rate": 1.8130598684585516e-05, "loss": 3.4151, "step": 1946624 }, { "epoch": 1.01, "learning_rate": 1.812222911587873e-05, "loss": 3.4201, "step": 1947136 }, { "epoch": 1.01, "learning_rate": 1.811384316836821e-05, "loss": 3.4114, "step": 1947648 }, { "epoch": 1.01, "learning_rate": 1.8105457220857685e-05, "loss": 3.4095, "step": 1948160 }, { "epoch": 1.01, "learning_rate": 1.8097071273347165e-05, "loss": 3.4143, "step": 1948672 }, { "epoch": 1.01, "learning_rate": 1.8088701704640378e-05, "loss": 3.4211, "step": 1949184 }, { "epoch": 1.01, "learning_rate": 1.8080315757129858e-05, "loss": 3.4135, "step": 1949696 }, { "epoch": 1.01, "learning_rate": 1.8071929809619338e-05, "loss": 3.4253, "step": 1950208 }, { "epoch": 1.01, "learning_rate": 1.8063543862108817e-05, "loss": 3.4007, "step": 1950720 }, { "epoch": 1.01, "learning_rate": 1.805517429340203e-05, "loss": 3.4019, "step": 1951232 }, { "epoch": 1.01, "learning_rate": 1.8046788345891507e-05, "loss": 3.4093, "step": 1951744 }, { "epoch": 1.01, "learning_rate": 1.8038402398380986e-05, "loss": 3.4182, "step": 1952256 }, { "epoch": 1.01, "learning_rate": 1.803001645087047e-05, "loss": 3.4186, "step": 1952768 }, { "epoch": 1.01, "learning_rate": 1.8021646882163682e-05, "loss": 3.4079, "step": 1953280 }, { "epoch": 1.02, "learning_rate": 1.801326093465316e-05, "loss": 3.4105, "step": 1953792 }, { "epoch": 1.02, "learning_rate": 1.800487498714264e-05, "loss": 3.4161, "step": 1954304 }, { "epoch": 1.02, "learning_rate": 1.799648903963212e-05, "loss": 3.4082, "step": 1954816 }, { "epoch": 1.02, "learning_rate": 1.798811947092533e-05, "loss": 3.4038, "step": 1955328 }, { "epoch": 1.02, "learning_rate": 1.797973352341481e-05, "loss": 3.4227, "step": 1955840 }, { "epoch": 1.02, "learning_rate": 1.797134757590429e-05, "loss": 3.4183, "step": 1956352 }, { "epoch": 1.02, "learning_rate": 1.796296162839377e-05, "loss": 3.4182, "step": 1956864 }, { "epoch": 1.02, "learning_rate": 1.795459205968698e-05, "loss": 3.4069, "step": 1957376 }, { "epoch": 1.02, "learning_rate": 1.794620611217646e-05, "loss": 3.4134, "step": 1957888 }, { "epoch": 1.02, "learning_rate": 1.793782016466594e-05, "loss": 3.4076, "step": 1958400 }, { "epoch": 1.02, "learning_rate": 1.7929434217155424e-05, "loss": 3.421, "step": 1958912 }, { "epoch": 1.02, "learning_rate": 1.7921064648448633e-05, "loss": 3.4206, "step": 1959424 }, { "epoch": 1.02, "learning_rate": 1.7912678700938113e-05, "loss": 3.4158, "step": 1959936 }, { "epoch": 1.02, "learning_rate": 1.7904292753427593e-05, "loss": 3.4161, "step": 1960448 }, { "epoch": 1.02, "learning_rate": 1.7895906805917072e-05, "loss": 3.4124, "step": 1960960 }, { "epoch": 1.02, "learning_rate": 1.7887537237210285e-05, "loss": 3.4148, "step": 1961472 }, { "epoch": 1.02, "learning_rate": 1.7879151289699765e-05, "loss": 3.4019, "step": 1961984 }, { "epoch": 1.02, "learning_rate": 1.7870765342189245e-05, "loss": 3.4012, "step": 1962496 }, { "epoch": 1.02, "learning_rate": 1.7862379394678725e-05, "loss": 3.4154, "step": 1963008 }, { "epoch": 1.02, "learning_rate": 1.7854009825971934e-05, "loss": 3.4109, "step": 1963520 }, { "epoch": 1.02, "learning_rate": 1.7845623878461414e-05, "loss": 3.3992, "step": 1964032 }, { "epoch": 1.02, "learning_rate": 1.7837237930950894e-05, "loss": 3.4034, "step": 1964544 }, { "epoch": 1.02, "learning_rate": 1.7828851983440377e-05, "loss": 3.4037, "step": 1965056 }, { "epoch": 1.02, "learning_rate": 1.7820482414733586e-05, "loss": 3.4139, "step": 1965568 }, { "epoch": 1.02, "learning_rate": 1.7812096467223066e-05, "loss": 3.4045, "step": 1966080 }, { "epoch": 1.02, "learning_rate": 1.7803710519712546e-05, "loss": 3.4167, "step": 1966592 }, { "epoch": 1.02, "learning_rate": 1.7795324572202026e-05, "loss": 3.4213, "step": 1967104 }, { "epoch": 1.02, "learning_rate": 1.778695500349524e-05, "loss": 3.4156, "step": 1967616 }, { "epoch": 1.02, "learning_rate": 1.777856905598472e-05, "loss": 3.4132, "step": 1968128 }, { "epoch": 1.02, "learning_rate": 1.77701831084742e-05, "loss": 3.4172, "step": 1968640 }, { "epoch": 1.02, "learning_rate": 1.776179716096368e-05, "loss": 3.415, "step": 1969152 }, { "epoch": 1.02, "learning_rate": 1.7753427592256888e-05, "loss": 3.4122, "step": 1969664 }, { "epoch": 1.02, "learning_rate": 1.7745041644746368e-05, "loss": 3.4148, "step": 1970176 }, { "epoch": 1.02, "learning_rate": 1.7736655697235847e-05, "loss": 3.4075, "step": 1970688 }, { "epoch": 1.02, "learning_rate": 1.772826974972533e-05, "loss": 3.4148, "step": 1971200 }, { "epoch": 1.02, "learning_rate": 1.771990018101854e-05, "loss": 3.4148, "step": 1971712 }, { "epoch": 1.02, "learning_rate": 1.771151423350802e-05, "loss": 3.4054, "step": 1972224 }, { "epoch": 1.02, "learning_rate": 1.77031282859975e-05, "loss": 3.4091, "step": 1972736 }, { "epoch": 1.02, "learning_rate": 1.769474233848698e-05, "loss": 3.4026, "step": 1973248 }, { "epoch": 1.02, "learning_rate": 1.7686372769780192e-05, "loss": 3.4005, "step": 1973760 }, { "epoch": 1.02, "learning_rate": 1.7677986822269672e-05, "loss": 3.4186, "step": 1974272 }, { "epoch": 1.02, "learning_rate": 1.7669600874759152e-05, "loss": 3.4086, "step": 1974784 }, { "epoch": 1.02, "learning_rate": 1.7661214927248632e-05, "loss": 3.4235, "step": 1975296 }, { "epoch": 1.02, "learning_rate": 1.765284535854184e-05, "loss": 3.4017, "step": 1975808 }, { "epoch": 1.02, "learning_rate": 1.764445941103132e-05, "loss": 3.4202, "step": 1976320 }, { "epoch": 1.02, "learning_rate": 1.76360734635208e-05, "loss": 3.4168, "step": 1976832 }, { "epoch": 1.02, "learning_rate": 1.762768751601028e-05, "loss": 3.4175, "step": 1977344 }, { "epoch": 1.02, "learning_rate": 1.7619317947303494e-05, "loss": 3.4137, "step": 1977856 }, { "epoch": 1.02, "learning_rate": 1.7610931999792974e-05, "loss": 3.4064, "step": 1978368 }, { "epoch": 1.02, "learning_rate": 1.7602546052282454e-05, "loss": 3.4199, "step": 1978880 }, { "epoch": 1.02, "learning_rate": 1.7594176483575663e-05, "loss": 3.4197, "step": 1979392 }, { "epoch": 1.02, "learning_rate": 1.7585790536065143e-05, "loss": 3.4086, "step": 1979904 }, { "epoch": 1.02, "learning_rate": 1.7577404588554626e-05, "loss": 3.4155, "step": 1980416 }, { "epoch": 1.02, "learning_rate": 1.7569018641044106e-05, "loss": 3.4124, "step": 1980928 }, { "epoch": 1.02, "learning_rate": 1.7560649072337315e-05, "loss": 3.4086, "step": 1981440 }, { "epoch": 1.02, "learning_rate": 1.7552263124826795e-05, "loss": 3.4089, "step": 1981952 }, { "epoch": 1.02, "learning_rate": 1.7543877177316275e-05, "loss": 3.4072, "step": 1982464 }, { "epoch": 1.02, "learning_rate": 1.7535491229805755e-05, "loss": 3.4177, "step": 1982976 }, { "epoch": 1.02, "learning_rate": 1.7527105282295235e-05, "loss": 3.4115, "step": 1983488 }, { "epoch": 1.02, "learning_rate": 1.7518735713588447e-05, "loss": 3.4151, "step": 1984000 }, { "epoch": 1.03, "eval_loss": 3.8601832389831543, "eval_runtime": 304.2015, "eval_samples_per_second": 1254.402, "eval_steps_per_second": 39.201, "step": 1984320 }, { "epoch": 0.0, "learning_rate": 1.7510349766077927e-05, "loss": 3.3985, "step": 1984512 }, { "epoch": 0.0, "learning_rate": 1.7501963818567404e-05, "loss": 3.4024, "step": 1985024 }, { "epoch": 0.0, "learning_rate": 1.7493577871056884e-05, "loss": 3.4064, "step": 1985536 }, { "epoch": 0.0, "learning_rate": 1.7485191923546364e-05, "loss": 3.4095, "step": 1986048 }, { "epoch": 0.0, "learning_rate": 1.747682235483958e-05, "loss": 3.4233, "step": 1986560 }, { "epoch": 0.0, "learning_rate": 1.7468436407329056e-05, "loss": 3.4095, "step": 1987072 }, { "epoch": 0.0, "learning_rate": 1.7460050459818536e-05, "loss": 3.4056, "step": 1987584 }, { "epoch": 0.0, "learning_rate": 1.7451664512308016e-05, "loss": 3.4076, "step": 1988096 }, { "epoch": 0.0, "learning_rate": 1.744329494360123e-05, "loss": 3.4018, "step": 1988608 }, { "epoch": 0.0, "learning_rate": 1.743490899609071e-05, "loss": 3.411, "step": 1989120 }, { "epoch": 0.0, "learning_rate": 1.742652304858019e-05, "loss": 3.4055, "step": 1989632 }, { "epoch": 0.0, "learning_rate": 1.741813710106967e-05, "loss": 3.4081, "step": 1990144 }, { "epoch": 0.0, "learning_rate": 1.740978391116661e-05, "loss": 3.418, "step": 1990656 }, { "epoch": 0.0, "learning_rate": 1.740139796365609e-05, "loss": 3.3941, "step": 1991168 }, { "epoch": 0.0, "learning_rate": 1.739301201614557e-05, "loss": 3.4018, "step": 1991680 }, { "epoch": 0.0, "learning_rate": 1.738462606863505e-05, "loss": 3.3949, "step": 1992192 }, { "epoch": 0.0, "learning_rate": 1.737624012112453e-05, "loss": 3.406, "step": 1992704 }, { "epoch": 0.0, "learning_rate": 1.736785417361401e-05, "loss": 3.4044, "step": 1993216 }, { "epoch": 0.0, "learning_rate": 1.735946822610349e-05, "loss": 3.4088, "step": 1993728 }, { "epoch": 0.0, "learning_rate": 1.735108227859297e-05, "loss": 3.4074, "step": 1994240 }, { "epoch": 0.0, "learning_rate": 1.734271270988618e-05, "loss": 3.4183, "step": 1994752 }, { "epoch": 0.0, "learning_rate": 1.7334326762375662e-05, "loss": 3.4073, "step": 1995264 }, { "epoch": 0.0, "learning_rate": 1.7325940814865142e-05, "loss": 3.4135, "step": 1995776 }, { "epoch": 0.0, "learning_rate": 1.7317554867354622e-05, "loss": 3.4095, "step": 1996288 }, { "epoch": 0.0, "learning_rate": 1.730918529864783e-05, "loss": 3.4081, "step": 1996800 }, { "epoch": 0.0, "learning_rate": 1.730079935113731e-05, "loss": 3.414, "step": 1997312 }, { "epoch": 0.0, "learning_rate": 1.729241340362679e-05, "loss": 3.3982, "step": 1997824 }, { "epoch": 0.0, "learning_rate": 1.728402745611627e-05, "loss": 3.4073, "step": 1998336 }, { "epoch": 0.0, "learning_rate": 1.7275657887409484e-05, "loss": 3.3978, "step": 1998848 }, { "epoch": 0.0, "learning_rate": 1.7267271939898963e-05, "loss": 3.4001, "step": 1999360 }, { "epoch": 0.01, "learning_rate": 1.7258885992388443e-05, "loss": 3.4086, "step": 1999872 }, { "epoch": 0.01, "learning_rate": 1.7250500044877923e-05, "loss": 3.4101, "step": 2000384 }, { "epoch": 0.01, "learning_rate": 1.7242130476171132e-05, "loss": 3.4078, "step": 2000896 }, { "epoch": 0.01, "learning_rate": 1.7233744528660616e-05, "loss": 3.4193, "step": 2001408 }, { "epoch": 0.01, "learning_rate": 1.7225358581150096e-05, "loss": 3.4032, "step": 2001920 }, { "epoch": 0.01, "learning_rate": 1.7216972633639576e-05, "loss": 3.4024, "step": 2002432 }, { "epoch": 0.01, "learning_rate": 1.7208603064932785e-05, "loss": 3.4163, "step": 2002944 }, { "epoch": 0.01, "learning_rate": 1.7200217117422265e-05, "loss": 3.4041, "step": 2003456 }, { "epoch": 0.01, "learning_rate": 1.7191831169911745e-05, "loss": 3.4042, "step": 2003968 }, { "epoch": 0.01, "learning_rate": 1.7183445222401225e-05, "loss": 3.4056, "step": 2004480 }, { "epoch": 0.01, "learning_rate": 1.7175075653694437e-05, "loss": 3.4035, "step": 2004992 }, { "epoch": 0.01, "learning_rate": 1.7166689706183917e-05, "loss": 3.4061, "step": 2005504 }, { "epoch": 0.01, "learning_rate": 1.7158303758673397e-05, "loss": 3.4111, "step": 2006016 }, { "epoch": 0.01, "learning_rate": 1.7149917811162877e-05, "loss": 3.4121, "step": 2006528 }, { "epoch": 0.01, "learning_rate": 1.7141548242456086e-05, "loss": 3.4083, "step": 2007040 }, { "epoch": 0.01, "learning_rate": 1.7133162294945566e-05, "loss": 3.413, "step": 2007552 }, { "epoch": 0.01, "learning_rate": 1.712477634743505e-05, "loss": 3.4044, "step": 2008064 }, { "epoch": 0.01, "learning_rate": 1.711639039992453e-05, "loss": 3.4107, "step": 2008576 }, { "epoch": 0.01, "learning_rate": 1.710802083121774e-05, "loss": 3.3749, "step": 2009088 }, { "epoch": 0.01, "learning_rate": 1.709963488370722e-05, "loss": 3.4157, "step": 2009600 }, { "epoch": 0.01, "learning_rate": 1.70912489361967e-05, "loss": 3.3995, "step": 2010112 }, { "epoch": 0.01, "learning_rate": 1.708286298868618e-05, "loss": 3.414, "step": 2010624 }, { "epoch": 0.01, "learning_rate": 1.707449341997939e-05, "loss": 3.397, "step": 2011136 }, { "epoch": 0.01, "learning_rate": 1.706610747246887e-05, "loss": 3.3914, "step": 2011648 }, { "epoch": 0.01, "learning_rate": 1.705772152495835e-05, "loss": 3.3852, "step": 2012160 }, { "epoch": 0.01, "learning_rate": 1.7049335577447827e-05, "loss": 3.3967, "step": 2012672 }, { "epoch": 0.01, "learning_rate": 1.704096600874104e-05, "loss": 3.4094, "step": 2013184 }, { "epoch": 0.01, "learning_rate": 1.703258006123052e-05, "loss": 3.3892, "step": 2013696 }, { "epoch": 0.01, "learning_rate": 1.7024194113720003e-05, "loss": 3.4119, "step": 2014208 }, { "epoch": 0.01, "learning_rate": 1.701580816620948e-05, "loss": 3.4047, "step": 2014720 }, { "epoch": 0.01, "learning_rate": 1.7007438597502692e-05, "loss": 3.3882, "step": 2015232 }, { "epoch": 0.01, "learning_rate": 1.6999052649992172e-05, "loss": 3.409, "step": 2015744 }, { "epoch": 0.01, "learning_rate": 1.6990666702481652e-05, "loss": 3.391, "step": 2016256 }, { "epoch": 0.01, "learning_rate": 1.6982280754971132e-05, "loss": 3.3916, "step": 2016768 }, { "epoch": 0.01, "learning_rate": 1.6973911186264345e-05, "loss": 3.4048, "step": 2017280 }, { "epoch": 0.01, "learning_rate": 1.6965525238753824e-05, "loss": 3.4059, "step": 2017792 }, { "epoch": 0.01, "learning_rate": 1.69571392912433e-05, "loss": 3.3879, "step": 2018304 }, { "epoch": 0.01, "learning_rate": 1.694875334373278e-05, "loss": 3.4004, "step": 2018816 }, { "epoch": 0.01, "learning_rate": 1.6940383775025993e-05, "loss": 3.39, "step": 2019328 }, { "epoch": 0.01, "learning_rate": 1.6931997827515473e-05, "loss": 3.4009, "step": 2019840 }, { "epoch": 0.01, "learning_rate": 1.6923611880004953e-05, "loss": 3.4087, "step": 2020352 }, { "epoch": 0.01, "learning_rate": 1.6915225932494433e-05, "loss": 3.4038, "step": 2020864 }, { "epoch": 0.01, "learning_rate": 1.6906856363787646e-05, "loss": 3.4105, "step": 2021376 }, { "epoch": 0.01, "learning_rate": 1.6898470416277126e-05, "loss": 3.4106, "step": 2021888 }, { "epoch": 0.01, "learning_rate": 1.6890084468766602e-05, "loss": 3.4249, "step": 2022400 }, { "epoch": 0.01, "learning_rate": 1.6881698521256086e-05, "loss": 3.4093, "step": 2022912 }, { "epoch": 0.01, "learning_rate": 1.6873328952549298e-05, "loss": 3.4116, "step": 2023424 }, { "epoch": 0.01, "learning_rate": 1.6864943005038775e-05, "loss": 3.3973, "step": 2023936 }, { "epoch": 0.01, "learning_rate": 1.6856557057528255e-05, "loss": 3.3994, "step": 2024448 }, { "epoch": 0.01, "learning_rate": 1.6848171110017735e-05, "loss": 3.4046, "step": 2024960 }, { "epoch": 0.01, "learning_rate": 1.6839801541310947e-05, "loss": 3.4069, "step": 2025472 }, { "epoch": 0.01, "learning_rate": 1.6831415593800427e-05, "loss": 3.4096, "step": 2025984 }, { "epoch": 0.01, "learning_rate": 1.6823029646289907e-05, "loss": 3.4139, "step": 2026496 }, { "epoch": 0.01, "learning_rate": 1.6814643698779387e-05, "loss": 3.3917, "step": 2027008 }, { "epoch": 0.01, "learning_rate": 1.68062741300726e-05, "loss": 3.3951, "step": 2027520 }, { "epoch": 0.01, "learning_rate": 1.6797888182562076e-05, "loss": 3.3957, "step": 2028032 }, { "epoch": 0.01, "learning_rate": 1.6789502235051556e-05, "loss": 3.4123, "step": 2028544 }, { "epoch": 0.01, "learning_rate": 1.678111628754104e-05, "loss": 3.4061, "step": 2029056 }, { "epoch": 0.01, "learning_rate": 1.677274671883425e-05, "loss": 3.3994, "step": 2029568 }, { "epoch": 0.01, "learning_rate": 1.676436077132373e-05, "loss": 3.4034, "step": 2030080 }, { "epoch": 0.02, "learning_rate": 1.675597482381321e-05, "loss": 3.4026, "step": 2030592 }, { "epoch": 0.02, "learning_rate": 1.674758887630269e-05, "loss": 3.397, "step": 2031104 }, { "epoch": 0.02, "learning_rate": 1.67392193075959e-05, "loss": 3.3976, "step": 2031616 }, { "epoch": 0.02, "learning_rate": 1.673083336008538e-05, "loss": 3.4114, "step": 2032128 }, { "epoch": 0.02, "learning_rate": 1.672244741257486e-05, "loss": 3.4124, "step": 2032640 }, { "epoch": 0.02, "learning_rate": 1.671406146506434e-05, "loss": 3.4065, "step": 2033152 }, { "epoch": 0.02, "learning_rate": 1.670569189635755e-05, "loss": 3.3937, "step": 2033664 }, { "epoch": 0.02, "learning_rate": 1.669730594884703e-05, "loss": 3.4014, "step": 2034176 }, { "epoch": 0.02, "learning_rate": 1.668892000133651e-05, "loss": 3.4032, "step": 2034688 }, { "epoch": 0.02, "learning_rate": 1.668053405382599e-05, "loss": 3.4087, "step": 2035200 }, { "epoch": 0.02, "learning_rate": 1.6672148106315473e-05, "loss": 3.4104, "step": 2035712 }, { "epoch": 0.02, "learning_rate": 1.6663778537608682e-05, "loss": 3.4007, "step": 2036224 }, { "epoch": 0.02, "learning_rate": 1.6655392590098162e-05, "loss": 3.4078, "step": 2036736 }, { "epoch": 0.02, "learning_rate": 1.6647006642587642e-05, "loss": 3.4026, "step": 2037248 }, { "epoch": 0.02, "learning_rate": 1.6638620695077122e-05, "loss": 3.4063, "step": 2037760 }, { "epoch": 0.02, "learning_rate": 1.6630251126370334e-05, "loss": 3.3932, "step": 2038272 }, { "epoch": 0.02, "learning_rate": 1.6621865178859814e-05, "loss": 3.393, "step": 2038784 }, { "epoch": 0.02, "learning_rate": 1.6613479231349294e-05, "loss": 3.4018, "step": 2039296 }, { "epoch": 0.02, "learning_rate": 1.6605093283838774e-05, "loss": 3.4007, "step": 2039808 }, { "epoch": 0.02, "learning_rate": 1.6596723715131983e-05, "loss": 3.3891, "step": 2040320 }, { "epoch": 0.02, "learning_rate": 1.6588337767621463e-05, "loss": 3.3929, "step": 2040832 }, { "epoch": 0.02, "learning_rate": 1.6579951820110943e-05, "loss": 3.3883, "step": 2041344 }, { "epoch": 0.02, "learning_rate": 1.6571565872600427e-05, "loss": 3.4059, "step": 2041856 }, { "epoch": 0.02, "learning_rate": 1.6563196303893636e-05, "loss": 3.3989, "step": 2042368 }, { "epoch": 0.02, "learning_rate": 1.6554810356383116e-05, "loss": 3.403, "step": 2042880 }, { "epoch": 0.02, "learning_rate": 1.6546424408872596e-05, "loss": 3.4102, "step": 2043392 }, { "epoch": 0.02, "learning_rate": 1.6538038461362076e-05, "loss": 3.4076, "step": 2043904 }, { "epoch": 0.02, "learning_rate": 1.6529668892655288e-05, "loss": 3.4018, "step": 2044416 }, { "epoch": 0.02, "learning_rate": 1.6521282945144768e-05, "loss": 3.411, "step": 2044928 }, { "epoch": 0.02, "learning_rate": 1.6512896997634248e-05, "loss": 3.405, "step": 2045440 }, { "epoch": 0.02, "learning_rate": 1.6504511050123725e-05, "loss": 3.403, "step": 2045952 }, { "epoch": 0.02, "learning_rate": 1.6496141481416937e-05, "loss": 3.4013, "step": 2046464 }, { "epoch": 0.02, "learning_rate": 1.6487755533906417e-05, "loss": 3.4023, "step": 2046976 }, { "epoch": 0.02, "learning_rate": 1.6479369586395897e-05, "loss": 3.4051, "step": 2047488 }, { "epoch": 0.02, "learning_rate": 1.6470983638885377e-05, "loss": 3.4046, "step": 2048000 }, { "epoch": 0.02, "learning_rate": 1.646261407017859e-05, "loss": 3.3964, "step": 2048512 }, { "epoch": 0.02, "learning_rate": 1.645422812266807e-05, "loss": 3.398, "step": 2049024 }, { "epoch": 0.02, "learning_rate": 1.644584217515755e-05, "loss": 3.3911, "step": 2049536 }, { "epoch": 0.02, "learning_rate": 1.6437456227647026e-05, "loss": 3.3908, "step": 2050048 }, { "epoch": 0.02, "learning_rate": 1.6429086658940242e-05, "loss": 3.4076, "step": 2050560 }, { "epoch": 0.02, "learning_rate": 1.6420700711429722e-05, "loss": 3.3982, "step": 2051072 }, { "epoch": 0.02, "learning_rate": 1.6412314763919198e-05, "loss": 3.4095, "step": 2051584 }, { "epoch": 0.02, "learning_rate": 1.6403928816408678e-05, "loss": 3.395, "step": 2052096 }, { "epoch": 0.02, "learning_rate": 1.639555924770189e-05, "loss": 3.4099, "step": 2052608 }, { "epoch": 0.02, "learning_rate": 1.638717330019137e-05, "loss": 3.405, "step": 2053120 }, { "epoch": 0.02, "learning_rate": 1.637878735268085e-05, "loss": 3.4025, "step": 2053632 }, { "epoch": 0.02, "learning_rate": 1.637040140517033e-05, "loss": 3.4046, "step": 2054144 }, { "epoch": 0.02, "learning_rate": 1.6362031836463543e-05, "loss": 3.3962, "step": 2054656 }, { "epoch": 0.02, "learning_rate": 1.6353645888953023e-05, "loss": 3.4105, "step": 2055168 }, { "epoch": 0.02, "learning_rate": 1.63452599414425e-05, "loss": 3.4101, "step": 2055680 }, { "epoch": 0.02, "learning_rate": 1.633687399393198e-05, "loss": 3.3962, "step": 2056192 }, { "epoch": 0.02, "learning_rate": 1.6328504425225195e-05, "loss": 3.4054, "step": 2056704 }, { "epoch": 0.02, "learning_rate": 1.6320118477714672e-05, "loss": 3.4035, "step": 2057216 }, { "epoch": 0.02, "learning_rate": 1.6311732530204152e-05, "loss": 3.3956, "step": 2057728 }, { "epoch": 0.02, "learning_rate": 1.6303346582693632e-05, "loss": 3.3942, "step": 2058240 }, { "epoch": 0.02, "learning_rate": 1.6294977013986844e-05, "loss": 3.4001, "step": 2058752 }, { "epoch": 0.02, "learning_rate": 1.6286591066476324e-05, "loss": 3.4048, "step": 2059264 }, { "epoch": 0.02, "learning_rate": 1.6278205118965804e-05, "loss": 3.4044, "step": 2059776 }, { "epoch": 0.02, "learning_rate": 1.6269819171455284e-05, "loss": 3.4028, "step": 2060288 }, { "epoch": 0.03, "eval_loss": 3.8614466190338135, "eval_runtime": 338.7155, "eval_samples_per_second": 1126.583, "eval_steps_per_second": 35.207, "step": 2060640 }, { "epoch": 1.0, "learning_rate": 1.6261449602748497e-05, "loss": 3.3928, "step": 2060800 }, { "epoch": 1.0, "learning_rate": 1.6253063655237973e-05, "loss": 3.3918, "step": 2061312 }, { "epoch": 1.0, "learning_rate": 1.6244677707727453e-05, "loss": 3.397, "step": 2061824 }, { "epoch": 1.0, "learning_rate": 1.6236291760216933e-05, "loss": 3.4001, "step": 2062336 }, { "epoch": 1.0, "learning_rate": 1.6227922191510146e-05, "loss": 3.4105, "step": 2062848 }, { "epoch": 1.0, "learning_rate": 1.6219536243999626e-05, "loss": 3.4005, "step": 2063360 }, { "epoch": 1.0, "learning_rate": 1.6211150296489106e-05, "loss": 3.3996, "step": 2063872 }, { "epoch": 1.0, "learning_rate": 1.6202764348978586e-05, "loss": 3.3983, "step": 2064384 }, { "epoch": 1.0, "learning_rate": 1.6194394780271795e-05, "loss": 3.3894, "step": 2064896 }, { "epoch": 1.0, "learning_rate": 1.6186008832761275e-05, "loss": 3.3978, "step": 2065408 }, { "epoch": 1.0, "learning_rate": 1.6177622885250758e-05, "loss": 3.4016, "step": 2065920 }, { "epoch": 1.0, "learning_rate": 1.6169236937740238e-05, "loss": 3.3965, "step": 2066432 }, { "epoch": 1.0, "learning_rate": 1.616088374783718e-05, "loss": 3.4031, "step": 2066944 }, { "epoch": 1.0, "learning_rate": 1.615249780032666e-05, "loss": 3.3849, "step": 2067456 }, { "epoch": 1.0, "learning_rate": 1.614411185281614e-05, "loss": 3.3922, "step": 2067968 }, { "epoch": 1.0, "learning_rate": 1.613572590530562e-05, "loss": 3.3826, "step": 2068480 }, { "epoch": 1.0, "learning_rate": 1.61273399577951e-05, "loss": 3.3954, "step": 2068992 }, { "epoch": 1.0, "learning_rate": 1.611895401028458e-05, "loss": 3.3949, "step": 2069504 }, { "epoch": 1.0, "learning_rate": 1.611056806277406e-05, "loss": 3.397, "step": 2070016 }, { "epoch": 1.0, "learning_rate": 1.610218211526354e-05, "loss": 3.3982, "step": 2070528 }, { "epoch": 1.0, "learning_rate": 1.609381254655675e-05, "loss": 3.4123, "step": 2071040 }, { "epoch": 1.0, "learning_rate": 1.608542659904623e-05, "loss": 3.396, "step": 2071552 }, { "epoch": 1.0, "learning_rate": 1.607704065153571e-05, "loss": 3.4036, "step": 2072064 }, { "epoch": 1.0, "learning_rate": 1.606865470402519e-05, "loss": 3.3952, "step": 2072576 }, { "epoch": 1.0, "learning_rate": 1.60602851353184e-05, "loss": 3.4002, "step": 2073088 }, { "epoch": 1.0, "learning_rate": 1.605189918780788e-05, "loss": 3.4051, "step": 2073600 }, { "epoch": 1.0, "learning_rate": 1.604351324029736e-05, "loss": 3.3874, "step": 2074112 }, { "epoch": 1.0, "learning_rate": 1.603512729278684e-05, "loss": 3.3974, "step": 2074624 }, { "epoch": 1.0, "learning_rate": 1.6026757724080053e-05, "loss": 3.3884, "step": 2075136 }, { "epoch": 1.0, "learning_rate": 1.6018371776569533e-05, "loss": 3.3912, "step": 2075648 }, { "epoch": 1.01, "learning_rate": 1.6009985829059013e-05, "loss": 3.3996, "step": 2076160 }, { "epoch": 1.01, "learning_rate": 1.6001599881548493e-05, "loss": 3.3998, "step": 2076672 }, { "epoch": 1.01, "learning_rate": 1.5993230312841702e-05, "loss": 3.3923, "step": 2077184 }, { "epoch": 1.01, "learning_rate": 1.5984844365331182e-05, "loss": 3.4136, "step": 2077696 }, { "epoch": 1.01, "learning_rate": 1.5976458417820665e-05, "loss": 3.3963, "step": 2078208 }, { "epoch": 1.01, "learning_rate": 1.5968072470310145e-05, "loss": 3.392, "step": 2078720 }, { "epoch": 1.01, "learning_rate": 1.5959702901603354e-05, "loss": 3.4057, "step": 2079232 }, { "epoch": 1.01, "learning_rate": 1.5951316954092834e-05, "loss": 3.3918, "step": 2079744 }, { "epoch": 1.01, "learning_rate": 1.5942931006582314e-05, "loss": 3.3957, "step": 2080256 }, { "epoch": 1.01, "learning_rate": 1.5934545059071794e-05, "loss": 3.3964, "step": 2080768 }, { "epoch": 1.01, "learning_rate": 1.5926175490365007e-05, "loss": 3.3925, "step": 2081280 }, { "epoch": 1.01, "learning_rate": 1.5917789542854487e-05, "loss": 3.3948, "step": 2081792 }, { "epoch": 1.01, "learning_rate": 1.5909403595343967e-05, "loss": 3.403, "step": 2082304 }, { "epoch": 1.01, "learning_rate": 1.5901017647833447e-05, "loss": 3.3992, "step": 2082816 }, { "epoch": 1.01, "learning_rate": 1.5892648079126656e-05, "loss": 3.4003, "step": 2083328 }, { "epoch": 1.01, "learning_rate": 1.5884262131616136e-05, "loss": 3.3996, "step": 2083840 }, { "epoch": 1.01, "learning_rate": 1.587587618410562e-05, "loss": 3.3934, "step": 2084352 }, { "epoch": 1.01, "learning_rate": 1.5867490236595096e-05, "loss": 3.4004, "step": 2084864 }, { "epoch": 1.01, "learning_rate": 1.5859120667888308e-05, "loss": 3.367, "step": 2085376 }, { "epoch": 1.01, "learning_rate": 1.5850734720377788e-05, "loss": 3.4006, "step": 2085888 }, { "epoch": 1.01, "learning_rate": 1.5842348772867268e-05, "loss": 3.3922, "step": 2086400 }, { "epoch": 1.01, "learning_rate": 1.5833962825356748e-05, "loss": 3.4037, "step": 2086912 }, { "epoch": 1.01, "learning_rate": 1.582559325664996e-05, "loss": 3.3865, "step": 2087424 }, { "epoch": 1.01, "learning_rate": 1.581720730913944e-05, "loss": 3.3776, "step": 2087936 }, { "epoch": 1.01, "learning_rate": 1.580882136162892e-05, "loss": 3.3792, "step": 2088448 }, { "epoch": 1.01, "learning_rate": 1.5800435414118397e-05, "loss": 3.385, "step": 2088960 }, { "epoch": 1.01, "learning_rate": 1.579206584541161e-05, "loss": 3.3999, "step": 2089472 }, { "epoch": 1.01, "learning_rate": 1.578367989790109e-05, "loss": 3.378, "step": 2089984 }, { "epoch": 1.01, "learning_rate": 1.577529395039057e-05, "loss": 3.4037, "step": 2090496 }, { "epoch": 1.01, "learning_rate": 1.576690800288005e-05, "loss": 3.3954, "step": 2091008 }, { "epoch": 1.01, "learning_rate": 1.5758538434173262e-05, "loss": 3.3752, "step": 2091520 }, { "epoch": 1.01, "learning_rate": 1.575015248666274e-05, "loss": 3.4001, "step": 2092032 }, { "epoch": 1.01, "learning_rate": 1.5741766539152218e-05, "loss": 3.3811, "step": 2092544 }, { "epoch": 1.01, "learning_rate": 1.5733380591641698e-05, "loss": 3.381, "step": 2093056 }, { "epoch": 1.01, "learning_rate": 1.5725011022934914e-05, "loss": 3.3889, "step": 2093568 }, { "epoch": 1.01, "learning_rate": 1.5716625075424394e-05, "loss": 3.3997, "step": 2094080 }, { "epoch": 1.01, "learning_rate": 1.570823912791387e-05, "loss": 3.3772, "step": 2094592 }, { "epoch": 1.01, "learning_rate": 1.569985318040335e-05, "loss": 3.3925, "step": 2095104 }, { "epoch": 1.01, "learning_rate": 1.5691483611696563e-05, "loss": 3.3761, "step": 2095616 }, { "epoch": 1.01, "learning_rate": 1.5683097664186043e-05, "loss": 3.3911, "step": 2096128 }, { "epoch": 1.01, "learning_rate": 1.5674711716675523e-05, "loss": 3.3974, "step": 2096640 }, { "epoch": 1.01, "learning_rate": 1.5666325769165003e-05, "loss": 3.3984, "step": 2097152 }, { "epoch": 1.01, "learning_rate": 1.5657956200458215e-05, "loss": 3.3991, "step": 2097664 }, { "epoch": 1.01, "learning_rate": 1.5649570252947692e-05, "loss": 3.4017, "step": 2098176 }, { "epoch": 1.01, "learning_rate": 1.5641184305437172e-05, "loss": 3.4179, "step": 2098688 }, { "epoch": 1.01, "learning_rate": 1.5632798357926652e-05, "loss": 3.3978, "step": 2099200 }, { "epoch": 1.01, "learning_rate": 1.5624428789219868e-05, "loss": 3.4021, "step": 2099712 }, { "epoch": 1.01, "learning_rate": 1.5616042841709344e-05, "loss": 3.3852, "step": 2100224 }, { "epoch": 1.01, "learning_rate": 1.5607656894198824e-05, "loss": 3.3906, "step": 2100736 }, { "epoch": 1.01, "learning_rate": 1.5599270946688304e-05, "loss": 3.3915, "step": 2101248 }, { "epoch": 1.01, "learning_rate": 1.5590901377981513e-05, "loss": 3.3962, "step": 2101760 }, { "epoch": 1.01, "learning_rate": 1.5582515430470997e-05, "loss": 3.4017, "step": 2102272 }, { "epoch": 1.01, "learning_rate": 1.5574129482960477e-05, "loss": 3.4018, "step": 2102784 }, { "epoch": 1.01, "learning_rate": 1.5565743535449957e-05, "loss": 3.386, "step": 2103296 }, { "epoch": 1.01, "learning_rate": 1.5557373966743166e-05, "loss": 3.384, "step": 2103808 }, { "epoch": 1.01, "learning_rate": 1.5548988019232646e-05, "loss": 3.3812, "step": 2104320 }, { "epoch": 1.01, "learning_rate": 1.5540602071722126e-05, "loss": 3.404, "step": 2104832 }, { "epoch": 1.01, "learning_rate": 1.5532216124211606e-05, "loss": 3.3941, "step": 2105344 }, { "epoch": 1.01, "learning_rate": 1.5523846555504818e-05, "loss": 3.3884, "step": 2105856 }, { "epoch": 1.01, "learning_rate": 1.5515460607994298e-05, "loss": 3.3989, "step": 2106368 }, { "epoch": 1.02, "learning_rate": 1.5507074660483778e-05, "loss": 3.3892, "step": 2106880 }, { "epoch": 1.02, "learning_rate": 1.5498688712973258e-05, "loss": 3.3864, "step": 2107392 }, { "epoch": 1.02, "learning_rate": 1.5490319144266467e-05, "loss": 3.3871, "step": 2107904 }, { "epoch": 1.02, "learning_rate": 1.548193319675595e-05, "loss": 3.399, "step": 2108416 }, { "epoch": 1.02, "learning_rate": 1.547354724924543e-05, "loss": 3.3988, "step": 2108928 }, { "epoch": 1.02, "learning_rate": 1.546516130173491e-05, "loss": 3.3997, "step": 2109440 }, { "epoch": 1.02, "learning_rate": 1.545679173302812e-05, "loss": 3.3847, "step": 2109952 }, { "epoch": 1.02, "learning_rate": 1.54484057855176e-05, "loss": 3.3929, "step": 2110464 }, { "epoch": 1.02, "learning_rate": 1.544001983800708e-05, "loss": 3.3933, "step": 2110976 }, { "epoch": 1.02, "learning_rate": 1.543163389049656e-05, "loss": 3.3996, "step": 2111488 }, { "epoch": 1.02, "learning_rate": 1.542326432178977e-05, "loss": 3.3988, "step": 2112000 }, { "epoch": 1.02, "learning_rate": 1.541487837427925e-05, "loss": 3.3973, "step": 2112512 }, { "epoch": 1.02, "learning_rate": 1.540649242676873e-05, "loss": 3.395, "step": 2113024 }, { "epoch": 1.02, "learning_rate": 1.539810647925821e-05, "loss": 3.3953, "step": 2113536 }, { "epoch": 1.02, "learning_rate": 1.538973691055142e-05, "loss": 3.3941, "step": 2114048 }, { "epoch": 1.02, "learning_rate": 1.5381350963040904e-05, "loss": 3.3843, "step": 2114560 }, { "epoch": 1.02, "learning_rate": 1.5372965015530384e-05, "loss": 3.385, "step": 2115072 }, { "epoch": 1.02, "learning_rate": 1.5364579068019864e-05, "loss": 3.3886, "step": 2115584 }, { "epoch": 1.02, "learning_rate": 1.5356209499313073e-05, "loss": 3.3914, "step": 2116096 }, { "epoch": 1.02, "learning_rate": 1.5347823551802553e-05, "loss": 3.3781, "step": 2116608 }, { "epoch": 1.02, "learning_rate": 1.5339437604292033e-05, "loss": 3.3823, "step": 2117120 }, { "epoch": 1.02, "learning_rate": 1.5331068035585245e-05, "loss": 3.3831, "step": 2117632 }, { "epoch": 1.02, "learning_rate": 1.5322682088074725e-05, "loss": 3.3899, "step": 2118144 }, { "epoch": 1.02, "learning_rate": 1.5314296140564205e-05, "loss": 3.3914, "step": 2118656 }, { "epoch": 1.02, "learning_rate": 1.5305910193053685e-05, "loss": 3.3912, "step": 2119168 }, { "epoch": 1.02, "learning_rate": 1.5297540624346894e-05, "loss": 3.3972, "step": 2119680 }, { "epoch": 1.02, "learning_rate": 1.5289154676836374e-05, "loss": 3.3999, "step": 2120192 }, { "epoch": 1.02, "learning_rate": 1.5280768729325858e-05, "loss": 3.3903, "step": 2120704 }, { "epoch": 1.02, "learning_rate": 1.5272382781815338e-05, "loss": 3.4021, "step": 2121216 }, { "epoch": 1.02, "learning_rate": 1.5264013213108547e-05, "loss": 3.3948, "step": 2121728 }, { "epoch": 1.02, "learning_rate": 1.5255627265598027e-05, "loss": 3.394, "step": 2122240 }, { "epoch": 1.02, "learning_rate": 1.5247241318087507e-05, "loss": 3.3905, "step": 2122752 }, { "epoch": 1.02, "learning_rate": 1.5238855370576988e-05, "loss": 3.3915, "step": 2123264 }, { "epoch": 1.02, "learning_rate": 1.5230485801870197e-05, "loss": 3.392, "step": 2123776 }, { "epoch": 1.02, "learning_rate": 1.5222099854359679e-05, "loss": 3.3952, "step": 2124288 }, { "epoch": 1.02, "learning_rate": 1.5213713906849159e-05, "loss": 3.3861, "step": 2124800 }, { "epoch": 1.02, "learning_rate": 1.5205327959338639e-05, "loss": 3.3873, "step": 2125312 }, { "epoch": 1.02, "learning_rate": 1.519695839063185e-05, "loss": 3.3769, "step": 2125824 }, { "epoch": 1.02, "learning_rate": 1.518857244312133e-05, "loss": 3.3863, "step": 2126336 }, { "epoch": 1.02, "learning_rate": 1.518018649561081e-05, "loss": 3.3968, "step": 2126848 }, { "epoch": 1.02, "learning_rate": 1.517180054810029e-05, "loss": 3.3898, "step": 2127360 }, { "epoch": 1.02, "learning_rate": 1.51634309793935e-05, "loss": 3.4012, "step": 2127872 }, { "epoch": 1.02, "learning_rate": 1.515504503188298e-05, "loss": 3.3802, "step": 2128384 }, { "epoch": 1.02, "learning_rate": 1.514665908437246e-05, "loss": 3.4021, "step": 2128896 }, { "epoch": 1.02, "learning_rate": 1.5138273136861939e-05, "loss": 3.397, "step": 2129408 }, { "epoch": 1.02, "learning_rate": 1.5129903568155151e-05, "loss": 3.3974, "step": 2129920 }, { "epoch": 1.02, "learning_rate": 1.5121517620644633e-05, "loss": 3.384, "step": 2130432 }, { "epoch": 1.02, "learning_rate": 1.5113131673134113e-05, "loss": 3.3896, "step": 2130944 }, { "epoch": 1.02, "learning_rate": 1.510474572562359e-05, "loss": 3.4038, "step": 2131456 }, { "epoch": 1.02, "learning_rate": 1.5096376156916803e-05, "loss": 3.3998, "step": 2131968 }, { "epoch": 1.02, "learning_rate": 1.5087990209406283e-05, "loss": 3.3884, "step": 2132480 }, { "epoch": 1.02, "learning_rate": 1.5079604261895763e-05, "loss": 3.3914, "step": 2132992 }, { "epoch": 1.02, "learning_rate": 1.5071218314385242e-05, "loss": 3.3911, "step": 2133504 }, { "epoch": 1.02, "learning_rate": 1.5062848745678454e-05, "loss": 3.3934, "step": 2134016 }, { "epoch": 1.02, "learning_rate": 1.5054462798167934e-05, "loss": 3.384, "step": 2134528 }, { "epoch": 1.02, "learning_rate": 1.5046076850657412e-05, "loss": 3.3935, "step": 2135040 }, { "epoch": 1.02, "learning_rate": 1.5037690903146892e-05, "loss": 3.3888, "step": 2135552 }, { "epoch": 1.02, "learning_rate": 1.5029321334440105e-05, "loss": 3.3909, "step": 2136064 }, { "epoch": 1.02, "learning_rate": 1.5020935386929585e-05, "loss": 3.394, "step": 2136576 }, { "epoch": 1.03, "eval_loss": 3.8629493713378906, "eval_runtime": 338.8063, "eval_samples_per_second": 1126.281, "eval_steps_per_second": 35.197, "step": 2136960 }, { "epoch": 0.0, "learning_rate": 1.5012549439419063e-05, "loss": 3.3922, "step": 2137088 }, { "epoch": 0.0, "learning_rate": 1.5004163491908543e-05, "loss": 3.3773, "step": 2137600 }, { "epoch": 0.0, "learning_rate": 1.4995777544398023e-05, "loss": 3.3869, "step": 2138112 }, { "epoch": 0.0, "learning_rate": 1.4987391596887504e-05, "loss": 3.394, "step": 2138624 }, { "epoch": 0.0, "learning_rate": 1.4979022028180714e-05, "loss": 3.3931, "step": 2139136 }, { "epoch": 0.0, "learning_rate": 1.4970636080670195e-05, "loss": 3.3971, "step": 2139648 }, { "epoch": 0.0, "learning_rate": 1.4962250133159675e-05, "loss": 3.3898, "step": 2140160 }, { "epoch": 0.0, "learning_rate": 1.4953864185649155e-05, "loss": 3.3871, "step": 2140672 }, { "epoch": 0.0, "learning_rate": 1.4945494616942366e-05, "loss": 3.3763, "step": 2141184 }, { "epoch": 0.0, "learning_rate": 1.4937108669431846e-05, "loss": 3.3886, "step": 2141696 }, { "epoch": 0.0, "learning_rate": 1.4928722721921326e-05, "loss": 3.3909, "step": 2142208 }, { "epoch": 0.0, "learning_rate": 1.4920336774410806e-05, "loss": 3.3884, "step": 2142720 }, { "epoch": 0.0, "learning_rate": 1.4911983584507749e-05, "loss": 3.3973, "step": 2143232 }, { "epoch": 0.0, "learning_rate": 1.4903597636997229e-05, "loss": 3.3719, "step": 2143744 }, { "epoch": 0.0, "learning_rate": 1.489521168948671e-05, "loss": 3.3811, "step": 2144256 }, { "epoch": 0.0, "learning_rate": 1.4886825741976187e-05, "loss": 3.3759, "step": 2144768 }, { "epoch": 0.0, "learning_rate": 1.4878439794465667e-05, "loss": 3.3839, "step": 2145280 }, { "epoch": 0.0, "learning_rate": 1.4870053846955149e-05, "loss": 3.3835, "step": 2145792 }, { "epoch": 0.0, "learning_rate": 1.4861667899444629e-05, "loss": 3.3866, "step": 2146304 }, { "epoch": 0.0, "learning_rate": 1.4853281951934109e-05, "loss": 3.384, "step": 2146816 }, { "epoch": 0.0, "learning_rate": 1.484491238322732e-05, "loss": 3.4031, "step": 2147328 }, { "epoch": 0.0, "learning_rate": 1.48365264357168e-05, "loss": 3.3868, "step": 2147840 }, { "epoch": 0.0, "learning_rate": 1.482814048820628e-05, "loss": 3.3921, "step": 2148352 }, { "epoch": 0.0, "learning_rate": 1.481975454069576e-05, "loss": 3.385, "step": 2148864 }, { "epoch": 0.0, "learning_rate": 1.481138497198897e-05, "loss": 3.3926, "step": 2149376 }, { "epoch": 0.0, "learning_rate": 1.480299902447845e-05, "loss": 3.393, "step": 2149888 }, { "epoch": 0.0, "learning_rate": 1.479461307696793e-05, "loss": 3.3774, "step": 2150400 }, { "epoch": 0.0, "learning_rate": 1.4786227129457412e-05, "loss": 3.3867, "step": 2150912 }, { "epoch": 0.0, "learning_rate": 1.4777857560750621e-05, "loss": 3.3771, "step": 2151424 }, { "epoch": 0.0, "learning_rate": 1.4769471613240103e-05, "loss": 3.379, "step": 2151936 }, { "epoch": 0.01, "learning_rate": 1.4761085665729583e-05, "loss": 3.3915, "step": 2152448 }, { "epoch": 0.01, "learning_rate": 1.4752699718219062e-05, "loss": 3.387, "step": 2152960 }, { "epoch": 0.01, "learning_rate": 1.4744330149512273e-05, "loss": 3.3842, "step": 2153472 }, { "epoch": 0.01, "learning_rate": 1.4735944202001753e-05, "loss": 3.4016, "step": 2153984 }, { "epoch": 0.01, "learning_rate": 1.4727558254491233e-05, "loss": 3.3853, "step": 2154496 }, { "epoch": 0.01, "learning_rate": 1.4719172306980713e-05, "loss": 3.3857, "step": 2155008 }, { "epoch": 0.01, "learning_rate": 1.4710802738273924e-05, "loss": 3.3951, "step": 2155520 }, { "epoch": 0.01, "learning_rate": 1.4702416790763404e-05, "loss": 3.3788, "step": 2156032 }, { "epoch": 0.01, "learning_rate": 1.4694030843252884e-05, "loss": 3.3855, "step": 2156544 }, { "epoch": 0.01, "learning_rate": 1.4685644895742365e-05, "loss": 3.3842, "step": 2157056 }, { "epoch": 0.01, "learning_rate": 1.4677275327035575e-05, "loss": 3.3837, "step": 2157568 }, { "epoch": 0.01, "learning_rate": 1.4668889379525056e-05, "loss": 3.3882, "step": 2158080 }, { "epoch": 0.01, "learning_rate": 1.4660503432014536e-05, "loss": 3.3981, "step": 2158592 }, { "epoch": 0.01, "learning_rate": 1.4652117484504013e-05, "loss": 3.3859, "step": 2159104 }, { "epoch": 0.01, "learning_rate": 1.4643747915797227e-05, "loss": 3.3908, "step": 2159616 }, { "epoch": 0.01, "learning_rate": 1.4635361968286707e-05, "loss": 3.3904, "step": 2160128 }, { "epoch": 0.01, "learning_rate": 1.4626976020776187e-05, "loss": 3.3846, "step": 2160640 }, { "epoch": 0.01, "learning_rate": 1.4618590073265665e-05, "loss": 3.3887, "step": 2161152 }, { "epoch": 0.01, "learning_rate": 1.4610220504558878e-05, "loss": 3.3583, "step": 2161664 }, { "epoch": 0.01, "learning_rate": 1.4601834557048358e-05, "loss": 3.3872, "step": 2162176 }, { "epoch": 0.01, "learning_rate": 1.4593448609537837e-05, "loss": 3.3847, "step": 2162688 }, { "epoch": 0.01, "learning_rate": 1.4585062662027316e-05, "loss": 3.3908, "step": 2163200 }, { "epoch": 0.01, "learning_rate": 1.4576693093320528e-05, "loss": 3.3789, "step": 2163712 }, { "epoch": 0.01, "learning_rate": 1.4568307145810008e-05, "loss": 3.3681, "step": 2164224 }, { "epoch": 0.01, "learning_rate": 1.4559921198299486e-05, "loss": 3.3693, "step": 2164736 }, { "epoch": 0.01, "learning_rate": 1.4551535250788966e-05, "loss": 3.3726, "step": 2165248 }, { "epoch": 0.01, "learning_rate": 1.454316568208218e-05, "loss": 3.3932, "step": 2165760 }, { "epoch": 0.01, "learning_rate": 1.453477973457166e-05, "loss": 3.3666, "step": 2166272 }, { "epoch": 0.01, "learning_rate": 1.4526393787061137e-05, "loss": 3.3932, "step": 2166784 }, { "epoch": 0.01, "learning_rate": 1.4518007839550619e-05, "loss": 3.3837, "step": 2167296 }, { "epoch": 0.01, "learning_rate": 1.4509638270843831e-05, "loss": 3.371, "step": 2167808 }, { "epoch": 0.01, "learning_rate": 1.4501252323333308e-05, "loss": 3.3882, "step": 2168320 }, { "epoch": 0.01, "learning_rate": 1.449286637582279e-05, "loss": 3.3707, "step": 2168832 }, { "epoch": 0.01, "learning_rate": 1.448448042831227e-05, "loss": 3.3735, "step": 2169344 }, { "epoch": 0.01, "learning_rate": 1.4476110859605482e-05, "loss": 3.3757, "step": 2169856 }, { "epoch": 0.01, "learning_rate": 1.446772491209496e-05, "loss": 3.3878, "step": 2170368 }, { "epoch": 0.01, "learning_rate": 1.445933896458444e-05, "loss": 3.3715, "step": 2170880 }, { "epoch": 0.01, "learning_rate": 1.445095301707392e-05, "loss": 3.3831, "step": 2171392 }, { "epoch": 0.01, "learning_rate": 1.4442583448367134e-05, "loss": 3.3645, "step": 2171904 }, { "epoch": 0.01, "learning_rate": 1.443419750085661e-05, "loss": 3.3809, "step": 2172416 }, { "epoch": 0.01, "learning_rate": 1.442581155334609e-05, "loss": 3.3875, "step": 2172928 }, { "epoch": 0.01, "learning_rate": 1.4417425605835572e-05, "loss": 3.3877, "step": 2173440 }, { "epoch": 0.01, "learning_rate": 1.4409056037128782e-05, "loss": 3.3883, "step": 2173952 }, { "epoch": 0.01, "learning_rate": 1.4400670089618261e-05, "loss": 3.39, "step": 2174464 }, { "epoch": 0.01, "learning_rate": 1.4392284142107743e-05, "loss": 3.4026, "step": 2174976 }, { "epoch": 0.01, "learning_rate": 1.4383898194597223e-05, "loss": 3.3897, "step": 2175488 }, { "epoch": 0.01, "learning_rate": 1.4375528625890434e-05, "loss": 3.3939, "step": 2176000 }, { "epoch": 0.01, "learning_rate": 1.4367142678379914e-05, "loss": 3.3744, "step": 2176512 }, { "epoch": 0.01, "learning_rate": 1.4358756730869394e-05, "loss": 3.3788, "step": 2177024 }, { "epoch": 0.01, "learning_rate": 1.4350370783358874e-05, "loss": 3.3826, "step": 2177536 }, { "epoch": 0.01, "learning_rate": 1.4342001214652085e-05, "loss": 3.3855, "step": 2178048 }, { "epoch": 0.01, "learning_rate": 1.4333615267141564e-05, "loss": 3.3907, "step": 2178560 }, { "epoch": 0.01, "learning_rate": 1.4325229319631044e-05, "loss": 3.3938, "step": 2179072 }, { "epoch": 0.01, "learning_rate": 1.4316843372120526e-05, "loss": 3.3791, "step": 2179584 }, { "epoch": 0.01, "learning_rate": 1.4308473803413735e-05, "loss": 3.3721, "step": 2180096 }, { "epoch": 0.01, "learning_rate": 1.4300087855903215e-05, "loss": 3.3726, "step": 2180608 }, { "epoch": 0.01, "learning_rate": 1.4291701908392697e-05, "loss": 3.3911, "step": 2181120 }, { "epoch": 0.01, "learning_rate": 1.4283315960882177e-05, "loss": 3.385, "step": 2181632 }, { "epoch": 0.01, "learning_rate": 1.4274946392175388e-05, "loss": 3.3789, "step": 2182144 }, { "epoch": 0.01, "learning_rate": 1.4266560444664867e-05, "loss": 3.3873, "step": 2182656 }, { "epoch": 0.02, "learning_rate": 1.4258174497154347e-05, "loss": 3.3824, "step": 2183168 }, { "epoch": 0.02, "learning_rate": 1.4249788549643827e-05, "loss": 3.3735, "step": 2183680 }, { "epoch": 0.02, "learning_rate": 1.4241418980937038e-05, "loss": 3.3778, "step": 2184192 }, { "epoch": 0.02, "learning_rate": 1.4233033033426518e-05, "loss": 3.3879, "step": 2184704 }, { "epoch": 0.02, "learning_rate": 1.4224647085915998e-05, "loss": 3.3929, "step": 2185216 }, { "epoch": 0.02, "learning_rate": 1.4216261138405478e-05, "loss": 3.3895, "step": 2185728 }, { "epoch": 0.02, "learning_rate": 1.4207891569698689e-05, "loss": 3.3729, "step": 2186240 }, { "epoch": 0.02, "learning_rate": 1.4199505622188169e-05, "loss": 3.3834, "step": 2186752 }, { "epoch": 0.02, "learning_rate": 1.419111967467765e-05, "loss": 3.385, "step": 2187264 }, { "epoch": 0.02, "learning_rate": 1.418273372716713e-05, "loss": 3.3867, "step": 2187776 }, { "epoch": 0.02, "learning_rate": 1.4174364158460341e-05, "loss": 3.3932, "step": 2188288 }, { "epoch": 0.02, "learning_rate": 1.4165978210949821e-05, "loss": 3.3849, "step": 2188800 }, { "epoch": 0.02, "learning_rate": 1.4157592263439301e-05, "loss": 3.3848, "step": 2189312 }, { "epoch": 0.02, "learning_rate": 1.4149206315928781e-05, "loss": 3.3852, "step": 2189824 }, { "epoch": 0.02, "learning_rate": 1.4140836747221992e-05, "loss": 3.3841, "step": 2190336 }, { "epoch": 0.02, "learning_rate": 1.4132450799711472e-05, "loss": 3.3753, "step": 2190848 }, { "epoch": 0.02, "learning_rate": 1.4124064852200952e-05, "loss": 3.3748, "step": 2191360 }, { "epoch": 0.02, "learning_rate": 1.4115678904690432e-05, "loss": 3.3788, "step": 2191872 }, { "epoch": 0.02, "learning_rate": 1.4107309335983643e-05, "loss": 3.3816, "step": 2192384 }, { "epoch": 0.02, "learning_rate": 1.4098923388473122e-05, "loss": 3.363, "step": 2192896 }, { "epoch": 0.02, "learning_rate": 1.4090537440962604e-05, "loss": 3.3775, "step": 2193408 }, { "epoch": 0.02, "learning_rate": 1.4082151493452084e-05, "loss": 3.3648, "step": 2193920 }, { "epoch": 0.02, "learning_rate": 1.4073781924745293e-05, "loss": 3.3866, "step": 2194432 }, { "epoch": 0.02, "learning_rate": 1.4065395977234775e-05, "loss": 3.3794, "step": 2194944 }, { "epoch": 0.02, "learning_rate": 1.4057010029724255e-05, "loss": 3.3824, "step": 2195456 }, { "epoch": 0.02, "learning_rate": 1.4048624082213735e-05, "loss": 3.3855, "step": 2195968 }, { "epoch": 0.02, "learning_rate": 1.4040254513506946e-05, "loss": 3.3896, "step": 2196480 }, { "epoch": 0.02, "learning_rate": 1.4031868565996425e-05, "loss": 3.3844, "step": 2196992 }, { "epoch": 0.02, "learning_rate": 1.4023482618485905e-05, "loss": 3.3864, "step": 2197504 }, { "epoch": 0.02, "learning_rate": 1.4015113049779116e-05, "loss": 3.3858, "step": 2198016 }, { "epoch": 0.02, "learning_rate": 1.4006727102268596e-05, "loss": 3.3824, "step": 2198528 }, { "epoch": 0.02, "learning_rate": 1.3998341154758076e-05, "loss": 3.3804, "step": 2199040 }, { "epoch": 0.02, "learning_rate": 1.3989955207247558e-05, "loss": 3.3828, "step": 2199552 }, { "epoch": 0.02, "learning_rate": 1.3981585638540767e-05, "loss": 3.3818, "step": 2200064 }, { "epoch": 0.02, "learning_rate": 1.3973199691030247e-05, "loss": 3.3824, "step": 2200576 }, { "epoch": 0.02, "learning_rate": 1.3964813743519728e-05, "loss": 3.3756, "step": 2201088 }, { "epoch": 0.02, "learning_rate": 1.3956427796009208e-05, "loss": 3.3772, "step": 2201600 }, { "epoch": 0.02, "learning_rate": 1.394805822730242e-05, "loss": 3.3662, "step": 2202112 }, { "epoch": 0.02, "learning_rate": 1.39396722797919e-05, "loss": 3.3766, "step": 2202624 }, { "epoch": 0.02, "learning_rate": 1.393128633228138e-05, "loss": 3.382, "step": 2203136 }, { "epoch": 0.02, "learning_rate": 1.3922900384770857e-05, "loss": 3.3823, "step": 2203648 }, { "epoch": 0.02, "learning_rate": 1.391453081606407e-05, "loss": 3.3875, "step": 2204160 }, { "epoch": 0.02, "learning_rate": 1.390614486855355e-05, "loss": 3.3749, "step": 2204672 }, { "epoch": 0.02, "learning_rate": 1.389775892104303e-05, "loss": 3.3909, "step": 2205184 }, { "epoch": 0.02, "learning_rate": 1.3889372973532508e-05, "loss": 3.3866, "step": 2205696 }, { "epoch": 0.02, "learning_rate": 1.3880987026021988e-05, "loss": 3.3817, "step": 2206208 }, { "epoch": 0.02, "learning_rate": 1.38726174573152e-05, "loss": 3.3787, "step": 2206720 }, { "epoch": 0.02, "learning_rate": 1.3864231509804679e-05, "loss": 3.3798, "step": 2207232 }, { "epoch": 0.02, "learning_rate": 1.3855845562294159e-05, "loss": 3.3943, "step": 2207744 }, { "epoch": 0.02, "learning_rate": 1.3847475993587373e-05, "loss": 3.3854, "step": 2208256 }, { "epoch": 0.02, "learning_rate": 1.3839090046076853e-05, "loss": 3.3803, "step": 2208768 }, { "epoch": 0.02, "learning_rate": 1.383070409856633e-05, "loss": 3.3825, "step": 2209280 }, { "epoch": 0.02, "learning_rate": 1.3822318151055811e-05, "loss": 3.3826, "step": 2209792 }, { "epoch": 0.02, "learning_rate": 1.3813948582349024e-05, "loss": 3.3814, "step": 2210304 }, { "epoch": 0.02, "learning_rate": 1.3805562634838504e-05, "loss": 3.3755, "step": 2210816 }, { "epoch": 0.02, "learning_rate": 1.3797176687327982e-05, "loss": 3.3833, "step": 2211328 }, { "epoch": 0.02, "learning_rate": 1.3788790739817462e-05, "loss": 3.3791, "step": 2211840 }, { "epoch": 0.02, "learning_rate": 1.3780421171110674e-05, "loss": 3.3832, "step": 2212352 }, { "epoch": 0.02, "learning_rate": 1.3772035223600152e-05, "loss": 3.3829, "step": 2212864 }, { "epoch": 0.03, "eval_loss": 3.864792585372925, "eval_runtime": 304.4412, "eval_samples_per_second": 1253.415, "eval_steps_per_second": 39.17, "step": 2213280 }, { "epoch": 1.0, "learning_rate": 1.3763649276089632e-05, "loss": 3.3792, "step": 2213376 }, { "epoch": 1.0, "learning_rate": 1.3755263328579112e-05, "loss": 3.3708, "step": 2213888 }, { "epoch": 1.0, "learning_rate": 1.3746893759872327e-05, "loss": 3.3743, "step": 2214400 }, { "epoch": 1.0, "learning_rate": 1.3738507812361803e-05, "loss": 3.3856, "step": 2214912 }, { "epoch": 1.0, "learning_rate": 1.3730121864851283e-05, "loss": 3.3835, "step": 2215424 }, { "epoch": 1.0, "learning_rate": 1.3721735917340765e-05, "loss": 3.3879, "step": 2215936 }, { "epoch": 1.0, "learning_rate": 1.3713366348633977e-05, "loss": 3.3754, "step": 2216448 }, { "epoch": 1.0, "learning_rate": 1.3704980401123454e-05, "loss": 3.3766, "step": 2216960 }, { "epoch": 1.0, "learning_rate": 1.3696594453612935e-05, "loss": 3.3677, "step": 2217472 }, { "epoch": 1.0, "learning_rate": 1.3688208506102415e-05, "loss": 3.3818, "step": 2217984 }, { "epoch": 1.0, "learning_rate": 1.3679838937395626e-05, "loss": 3.3759, "step": 2218496 }, { "epoch": 1.0, "learning_rate": 1.3671452989885106e-05, "loss": 3.3789, "step": 2219008 }, { "epoch": 1.0, "learning_rate": 1.3663083421178319e-05, "loss": 3.3896, "step": 2219520 }, { "epoch": 1.0, "learning_rate": 1.3654697473667799e-05, "loss": 3.3617, "step": 2220032 }, { "epoch": 1.0, "learning_rate": 1.3646311526157277e-05, "loss": 3.3728, "step": 2220544 }, { "epoch": 1.0, "learning_rate": 1.3637925578646757e-05, "loss": 3.3626, "step": 2221056 }, { "epoch": 1.0, "learning_rate": 1.3629539631136237e-05, "loss": 3.3775, "step": 2221568 }, { "epoch": 1.0, "learning_rate": 1.3621153683625717e-05, "loss": 3.3708, "step": 2222080 }, { "epoch": 1.0, "learning_rate": 1.3612767736115198e-05, "loss": 3.3815, "step": 2222592 }, { "epoch": 1.0, "learning_rate": 1.3604381788604678e-05, "loss": 3.3714, "step": 2223104 }, { "epoch": 1.0, "learning_rate": 1.3596012219897889e-05, "loss": 3.3933, "step": 2223616 }, { "epoch": 1.0, "learning_rate": 1.3587626272387369e-05, "loss": 3.3788, "step": 2224128 }, { "epoch": 1.0, "learning_rate": 1.3579240324876849e-05, "loss": 3.3818, "step": 2224640 }, { "epoch": 1.0, "learning_rate": 1.3570854377366329e-05, "loss": 3.3779, "step": 2225152 }, { "epoch": 1.0, "learning_rate": 1.356248480865954e-05, "loss": 3.3855, "step": 2225664 }, { "epoch": 1.0, "learning_rate": 1.355409886114902e-05, "loss": 3.3784, "step": 2226176 }, { "epoch": 1.0, "learning_rate": 1.35457129136385e-05, "loss": 3.3689, "step": 2226688 }, { "epoch": 1.0, "learning_rate": 1.3537326966127981e-05, "loss": 3.3805, "step": 2227200 }, { "epoch": 1.0, "learning_rate": 1.352895739742119e-05, "loss": 3.3658, "step": 2227712 }, { "epoch": 1.0, "learning_rate": 1.352057144991067e-05, "loss": 3.3698, "step": 2228224 }, { "epoch": 1.01, "learning_rate": 1.3512185502400152e-05, "loss": 3.3802, "step": 2228736 }, { "epoch": 1.01, "learning_rate": 1.3503799554889632e-05, "loss": 3.3751, "step": 2229248 }, { "epoch": 1.01, "learning_rate": 1.3495429986182843e-05, "loss": 3.3777, "step": 2229760 }, { "epoch": 1.01, "learning_rate": 1.3487044038672323e-05, "loss": 3.3875, "step": 2230272 }, { "epoch": 1.01, "learning_rate": 1.3478658091161803e-05, "loss": 3.3759, "step": 2230784 }, { "epoch": 1.01, "learning_rate": 1.3470272143651281e-05, "loss": 3.3784, "step": 2231296 }, { "epoch": 1.01, "learning_rate": 1.3461902574944493e-05, "loss": 3.3795, "step": 2231808 }, { "epoch": 1.01, "learning_rate": 1.3453516627433973e-05, "loss": 3.3717, "step": 2232320 }, { "epoch": 1.01, "learning_rate": 1.3445130679923453e-05, "loss": 3.3786, "step": 2232832 }, { "epoch": 1.01, "learning_rate": 1.3436744732412932e-05, "loss": 3.3728, "step": 2233344 }, { "epoch": 1.01, "learning_rate": 1.3428375163706144e-05, "loss": 3.3716, "step": 2233856 }, { "epoch": 1.01, "learning_rate": 1.3419989216195624e-05, "loss": 3.3791, "step": 2234368 }, { "epoch": 1.01, "learning_rate": 1.3411603268685106e-05, "loss": 3.3888, "step": 2234880 }, { "epoch": 1.01, "learning_rate": 1.3403217321174582e-05, "loss": 3.3747, "step": 2235392 }, { "epoch": 1.01, "learning_rate": 1.3394847752467796e-05, "loss": 3.3802, "step": 2235904 }, { "epoch": 1.01, "learning_rate": 1.3386461804957276e-05, "loss": 3.3838, "step": 2236416 }, { "epoch": 1.01, "learning_rate": 1.3378075857446753e-05, "loss": 3.3755, "step": 2236928 }, { "epoch": 1.01, "learning_rate": 1.3369689909936235e-05, "loss": 3.3797, "step": 2237440 }, { "epoch": 1.01, "learning_rate": 1.3361320341229447e-05, "loss": 3.347, "step": 2237952 }, { "epoch": 1.01, "learning_rate": 1.3352934393718927e-05, "loss": 3.3788, "step": 2238464 }, { "epoch": 1.01, "learning_rate": 1.3344548446208405e-05, "loss": 3.3744, "step": 2238976 }, { "epoch": 1.01, "learning_rate": 1.3336162498697885e-05, "loss": 3.3828, "step": 2239488 }, { "epoch": 1.01, "learning_rate": 1.3327792929991098e-05, "loss": 3.3699, "step": 2240000 }, { "epoch": 1.01, "learning_rate": 1.3319406982480578e-05, "loss": 3.3605, "step": 2240512 }, { "epoch": 1.01, "learning_rate": 1.3311021034970056e-05, "loss": 3.3567, "step": 2241024 }, { "epoch": 1.01, "learning_rate": 1.3302635087459536e-05, "loss": 3.3589, "step": 2241536 }, { "epoch": 1.01, "learning_rate": 1.329426551875275e-05, "loss": 3.3853, "step": 2242048 }, { "epoch": 1.01, "learning_rate": 1.3285879571242227e-05, "loss": 3.3604, "step": 2242560 }, { "epoch": 1.01, "learning_rate": 1.3277493623731707e-05, "loss": 3.3807, "step": 2243072 }, { "epoch": 1.01, "learning_rate": 1.3269107676221187e-05, "loss": 3.3725, "step": 2243584 }, { "epoch": 1.01, "learning_rate": 1.32607381075144e-05, "loss": 3.3656, "step": 2244096 }, { "epoch": 1.01, "learning_rate": 1.3252352160003877e-05, "loss": 3.3773, "step": 2244608 }, { "epoch": 1.01, "learning_rate": 1.3243966212493359e-05, "loss": 3.3589, "step": 2245120 }, { "epoch": 1.01, "learning_rate": 1.3235580264982839e-05, "loss": 3.3638, "step": 2245632 }, { "epoch": 1.01, "learning_rate": 1.322721069627605e-05, "loss": 3.3668, "step": 2246144 }, { "epoch": 1.01, "learning_rate": 1.321882474876553e-05, "loss": 3.3802, "step": 2246656 }, { "epoch": 1.01, "learning_rate": 1.321043880125501e-05, "loss": 3.3622, "step": 2247168 }, { "epoch": 1.01, "learning_rate": 1.320205285374449e-05, "loss": 3.3669, "step": 2247680 }, { "epoch": 1.01, "learning_rate": 1.31936832850377e-05, "loss": 3.3582, "step": 2248192 }, { "epoch": 1.01, "learning_rate": 1.318529733752718e-05, "loss": 3.3708, "step": 2248704 }, { "epoch": 1.01, "learning_rate": 1.317691139001666e-05, "loss": 3.3789, "step": 2249216 }, { "epoch": 1.01, "learning_rate": 1.316852544250614e-05, "loss": 3.3778, "step": 2249728 }, { "epoch": 1.01, "learning_rate": 1.3160155873799351e-05, "loss": 3.382, "step": 2250240 }, { "epoch": 1.01, "learning_rate": 1.3151769926288831e-05, "loss": 3.3804, "step": 2250752 }, { "epoch": 1.01, "learning_rate": 1.3143383978778313e-05, "loss": 3.3938, "step": 2251264 }, { "epoch": 1.01, "learning_rate": 1.3134998031267793e-05, "loss": 3.3785, "step": 2251776 }, { "epoch": 1.01, "learning_rate": 1.3126628462561002e-05, "loss": 3.385, "step": 2252288 }, { "epoch": 1.01, "learning_rate": 1.3118242515050483e-05, "loss": 3.369, "step": 2252800 }, { "epoch": 1.01, "learning_rate": 1.3109856567539963e-05, "loss": 3.3713, "step": 2253312 }, { "epoch": 1.01, "learning_rate": 1.3101470620029443e-05, "loss": 3.3724, "step": 2253824 }, { "epoch": 1.01, "learning_rate": 1.3093101051322654e-05, "loss": 3.3711, "step": 2254336 }, { "epoch": 1.01, "learning_rate": 1.3084715103812134e-05, "loss": 3.3795, "step": 2254848 }, { "epoch": 1.01, "learning_rate": 1.3076329156301614e-05, "loss": 3.3822, "step": 2255360 }, { "epoch": 1.01, "learning_rate": 1.3067943208791094e-05, "loss": 3.377, "step": 2255872 }, { "epoch": 1.01, "learning_rate": 1.3059573640084305e-05, "loss": 3.359, "step": 2256384 }, { "epoch": 1.01, "learning_rate": 1.3051187692573785e-05, "loss": 3.3615, "step": 2256896 }, { "epoch": 1.01, "learning_rate": 1.3042801745063266e-05, "loss": 3.3794, "step": 2257408 }, { "epoch": 1.01, "learning_rate": 1.3034415797552746e-05, "loss": 3.3763, "step": 2257920 }, { "epoch": 1.01, "learning_rate": 1.3026046228845955e-05, "loss": 3.3678, "step": 2258432 }, { "epoch": 1.01, "learning_rate": 1.3017660281335437e-05, "loss": 3.3748, "step": 2258944 }, { "epoch": 1.02, "learning_rate": 1.3009274333824917e-05, "loss": 3.3734, "step": 2259456 }, { "epoch": 1.02, "learning_rate": 1.3000888386314397e-05, "loss": 3.3661, "step": 2259968 }, { "epoch": 1.02, "learning_rate": 1.2992518817607608e-05, "loss": 3.3698, "step": 2260480 }, { "epoch": 1.02, "learning_rate": 1.2984132870097088e-05, "loss": 3.3775, "step": 2260992 }, { "epoch": 1.02, "learning_rate": 1.2975746922586568e-05, "loss": 3.3809, "step": 2261504 }, { "epoch": 1.02, "learning_rate": 1.2967360975076048e-05, "loss": 3.3783, "step": 2262016 }, { "epoch": 1.02, "learning_rate": 1.2958991406369258e-05, "loss": 3.3619, "step": 2262528 }, { "epoch": 1.02, "learning_rate": 1.2950605458858738e-05, "loss": 3.3702, "step": 2263040 }, { "epoch": 1.02, "learning_rate": 1.294221951134822e-05, "loss": 3.3775, "step": 2263552 }, { "epoch": 1.02, "learning_rate": 1.29338335638377e-05, "loss": 3.3787, "step": 2264064 }, { "epoch": 1.02, "learning_rate": 1.2925463995130909e-05, "loss": 3.3797, "step": 2264576 }, { "epoch": 1.02, "learning_rate": 1.291707804762039e-05, "loss": 3.3755, "step": 2265088 }, { "epoch": 1.02, "learning_rate": 1.290869210010987e-05, "loss": 3.3739, "step": 2265600 }, { "epoch": 1.02, "learning_rate": 1.290030615259935e-05, "loss": 3.3729, "step": 2266112 }, { "epoch": 1.02, "learning_rate": 1.2891936583892561e-05, "loss": 3.3742, "step": 2266624 }, { "epoch": 1.02, "learning_rate": 1.2883550636382041e-05, "loss": 3.3656, "step": 2267136 }, { "epoch": 1.02, "learning_rate": 1.2875164688871521e-05, "loss": 3.3639, "step": 2267648 }, { "epoch": 1.02, "learning_rate": 1.2866778741361001e-05, "loss": 3.3716, "step": 2268160 }, { "epoch": 1.02, "learning_rate": 1.2858409172654212e-05, "loss": 3.374, "step": 2268672 }, { "epoch": 1.02, "learning_rate": 1.2850023225143692e-05, "loss": 3.3563, "step": 2269184 }, { "epoch": 1.02, "learning_rate": 1.2841637277633172e-05, "loss": 3.3654, "step": 2269696 }, { "epoch": 1.02, "learning_rate": 1.283325133012265e-05, "loss": 3.3583, "step": 2270208 }, { "epoch": 1.02, "learning_rate": 1.2824881761415863e-05, "loss": 3.3707, "step": 2270720 }, { "epoch": 1.02, "learning_rate": 1.2816495813905344e-05, "loss": 3.3706, "step": 2271232 }, { "epoch": 1.02, "learning_rate": 1.2808109866394824e-05, "loss": 3.3699, "step": 2271744 }, { "epoch": 1.02, "learning_rate": 1.2799723918884301e-05, "loss": 3.3752, "step": 2272256 }, { "epoch": 1.02, "learning_rate": 1.2791354350177515e-05, "loss": 3.3848, "step": 2272768 }, { "epoch": 1.02, "learning_rate": 1.2782968402666995e-05, "loss": 3.374, "step": 2273280 }, { "epoch": 1.02, "learning_rate": 1.2774582455156475e-05, "loss": 3.3763, "step": 2273792 }, { "epoch": 1.02, "learning_rate": 1.2766196507645953e-05, "loss": 3.3813, "step": 2274304 }, { "epoch": 1.02, "learning_rate": 1.2757826938939166e-05, "loss": 3.3706, "step": 2274816 }, { "epoch": 1.02, "learning_rate": 1.2749440991428646e-05, "loss": 3.3707, "step": 2275328 }, { "epoch": 1.02, "learning_rate": 1.2741055043918124e-05, "loss": 3.3743, "step": 2275840 }, { "epoch": 1.02, "learning_rate": 1.2732685475211336e-05, "loss": 3.3712, "step": 2276352 }, { "epoch": 1.02, "learning_rate": 1.2724299527700816e-05, "loss": 3.3716, "step": 2276864 }, { "epoch": 1.02, "learning_rate": 1.2715913580190298e-05, "loss": 3.3644, "step": 2277376 }, { "epoch": 1.02, "learning_rate": 1.2707527632679775e-05, "loss": 3.3722, "step": 2277888 }, { "epoch": 1.02, "learning_rate": 1.2699158063972987e-05, "loss": 3.3655, "step": 2278400 }, { "epoch": 1.02, "learning_rate": 1.2690772116462469e-05, "loss": 3.3681, "step": 2278912 }, { "epoch": 1.02, "learning_rate": 1.2682386168951949e-05, "loss": 3.367, "step": 2279424 }, { "epoch": 1.02, "learning_rate": 1.2674000221441425e-05, "loss": 3.3756, "step": 2279936 }, { "epoch": 1.02, "learning_rate": 1.2665614273930907e-05, "loss": 3.3787, "step": 2280448 }, { "epoch": 1.02, "learning_rate": 1.265724470522412e-05, "loss": 3.3656, "step": 2280960 }, { "epoch": 1.02, "learning_rate": 1.2648858757713598e-05, "loss": 3.3791, "step": 2281472 }, { "epoch": 1.02, "learning_rate": 1.2640472810203078e-05, "loss": 3.3776, "step": 2281984 }, { "epoch": 1.02, "learning_rate": 1.263210324149629e-05, "loss": 3.3772, "step": 2282496 }, { "epoch": 1.02, "learning_rate": 1.262371729398577e-05, "loss": 3.3707, "step": 2283008 }, { "epoch": 1.02, "learning_rate": 1.2615331346475248e-05, "loss": 3.3676, "step": 2283520 }, { "epoch": 1.02, "learning_rate": 1.2606945398964728e-05, "loss": 3.3848, "step": 2284032 }, { "epoch": 1.02, "learning_rate": 1.259857583025794e-05, "loss": 3.3678, "step": 2284544 }, { "epoch": 1.02, "learning_rate": 1.2590189882747419e-05, "loss": 3.3761, "step": 2285056 }, { "epoch": 1.02, "learning_rate": 1.2581803935236899e-05, "loss": 3.372, "step": 2285568 }, { "epoch": 1.02, "learning_rate": 1.2573417987726379e-05, "loss": 3.3722, "step": 2286080 }, { "epoch": 1.02, "learning_rate": 1.2565048419019593e-05, "loss": 3.3686, "step": 2286592 }, { "epoch": 1.02, "learning_rate": 1.255666247150907e-05, "loss": 3.3667, "step": 2287104 }, { "epoch": 1.02, "learning_rate": 1.2548276523998551e-05, "loss": 3.3738, "step": 2287616 }, { "epoch": 1.02, "learning_rate": 1.2539890576488031e-05, "loss": 3.3698, "step": 2288128 }, { "epoch": 1.02, "learning_rate": 1.2531521007781244e-05, "loss": 3.375, "step": 2288640 }, { "epoch": 1.02, "learning_rate": 1.2523135060270722e-05, "loss": 3.3686, "step": 2289152 }, { "epoch": 1.03, "eval_loss": 3.866483688354492, "eval_runtime": 304.5624, "eval_samples_per_second": 1252.915, "eval_steps_per_second": 39.155, "step": 2289600 }, { "epoch": 0.0, "learning_rate": 1.2514749112760202e-05, "loss": 3.369, "step": 2289664 }, { "epoch": 0.0, "learning_rate": 1.2506363165249682e-05, "loss": 3.3632, "step": 2290176 }, { "epoch": 0.0, "learning_rate": 1.2497977217739162e-05, "loss": 3.3625, "step": 2290688 }, { "epoch": 0.0, "learning_rate": 1.2489591270228644e-05, "loss": 3.3772, "step": 2291200 }, { "epoch": 0.0, "learning_rate": 1.2481221701521853e-05, "loss": 3.374, "step": 2291712 }, { "epoch": 0.0, "learning_rate": 1.2472835754011333e-05, "loss": 3.3783, "step": 2292224 }, { "epoch": 0.0, "learning_rate": 1.2464449806500814e-05, "loss": 3.365, "step": 2292736 }, { "epoch": 0.0, "learning_rate": 1.2456063858990293e-05, "loss": 3.3669, "step": 2293248 }, { "epoch": 0.0, "learning_rate": 1.2447694290283505e-05, "loss": 3.3591, "step": 2293760 }, { "epoch": 0.0, "learning_rate": 1.2439308342772985e-05, "loss": 3.3725, "step": 2294272 }, { "epoch": 0.0, "learning_rate": 1.2430922395262465e-05, "loss": 3.3693, "step": 2294784 }, { "epoch": 0.0, "learning_rate": 1.2422536447751943e-05, "loss": 3.368, "step": 2295296 }, { "epoch": 0.0, "learning_rate": 1.2414183257848886e-05, "loss": 3.3775, "step": 2295808 }, { "epoch": 0.0, "learning_rate": 1.2405797310338366e-05, "loss": 3.3575, "step": 2296320 }, { "epoch": 0.0, "learning_rate": 1.2397411362827848e-05, "loss": 3.359, "step": 2296832 }, { "epoch": 0.0, "learning_rate": 1.2389025415317326e-05, "loss": 3.3569, "step": 2297344 }, { "epoch": 0.0, "learning_rate": 1.2380639467806806e-05, "loss": 3.3643, "step": 2297856 }, { "epoch": 0.0, "learning_rate": 1.2372253520296286e-05, "loss": 3.3597, "step": 2298368 }, { "epoch": 0.0, "learning_rate": 1.2363867572785766e-05, "loss": 3.3726, "step": 2298880 }, { "epoch": 0.0, "learning_rate": 1.2355481625275246e-05, "loss": 3.3625, "step": 2299392 }, { "epoch": 0.0, "learning_rate": 1.2347112056568459e-05, "loss": 3.381, "step": 2299904 }, { "epoch": 0.0, "learning_rate": 1.2338726109057939e-05, "loss": 3.3699, "step": 2300416 }, { "epoch": 0.0, "learning_rate": 1.2330340161547417e-05, "loss": 3.3674, "step": 2300928 }, { "epoch": 0.0, "learning_rate": 1.2321954214036897e-05, "loss": 3.3701, "step": 2301440 }, { "epoch": 0.0, "learning_rate": 1.231358464533011e-05, "loss": 3.3794, "step": 2301952 }, { "epoch": 0.0, "learning_rate": 1.230519869781959e-05, "loss": 3.3687, "step": 2302464 }, { "epoch": 0.0, "learning_rate": 1.2296812750309068e-05, "loss": 3.3625, "step": 2302976 }, { "epoch": 0.0, "learning_rate": 1.228842680279855e-05, "loss": 3.3698, "step": 2303488 }, { "epoch": 0.0, "learning_rate": 1.228005723409176e-05, "loss": 3.3553, "step": 2304000 }, { "epoch": 0.0, "learning_rate": 1.227167128658124e-05, "loss": 3.3599, "step": 2304512 }, { "epoch": 0.01, "learning_rate": 1.226328533907072e-05, "loss": 3.3685, "step": 2305024 }, { "epoch": 0.01, "learning_rate": 1.22548993915602e-05, "loss": 3.3669, "step": 2305536 }, { "epoch": 0.01, "learning_rate": 1.224652982285341e-05, "loss": 3.3692, "step": 2306048 }, { "epoch": 0.01, "learning_rate": 1.223814387534289e-05, "loss": 3.3766, "step": 2306560 }, { "epoch": 0.01, "learning_rate": 1.222975792783237e-05, "loss": 3.3658, "step": 2307072 }, { "epoch": 0.01, "learning_rate": 1.222137198032185e-05, "loss": 3.3708, "step": 2307584 }, { "epoch": 0.01, "learning_rate": 1.2213002411615063e-05, "loss": 3.3701, "step": 2308096 }, { "epoch": 0.01, "learning_rate": 1.2204616464104541e-05, "loss": 3.3612, "step": 2308608 }, { "epoch": 0.01, "learning_rate": 1.2196230516594021e-05, "loss": 3.3723, "step": 2309120 }, { "epoch": 0.01, "learning_rate": 1.2187844569083503e-05, "loss": 3.362, "step": 2309632 }, { "epoch": 0.01, "learning_rate": 1.2179475000376712e-05, "loss": 3.3643, "step": 2310144 }, { "epoch": 0.01, "learning_rate": 1.2171089052866194e-05, "loss": 3.3658, "step": 2310656 }, { "epoch": 0.01, "learning_rate": 1.2162703105355674e-05, "loss": 3.3804, "step": 2311168 }, { "epoch": 0.01, "learning_rate": 1.2154317157845154e-05, "loss": 3.3631, "step": 2311680 }, { "epoch": 0.01, "learning_rate": 1.2145947589138364e-05, "loss": 3.3756, "step": 2312192 }, { "epoch": 0.01, "learning_rate": 1.2137561641627844e-05, "loss": 3.3687, "step": 2312704 }, { "epoch": 0.01, "learning_rate": 1.2129175694117324e-05, "loss": 3.3687, "step": 2313216 }, { "epoch": 0.01, "learning_rate": 1.2120789746606802e-05, "loss": 3.3681, "step": 2313728 }, { "epoch": 0.01, "learning_rate": 1.2112420177900015e-05, "loss": 3.3374, "step": 2314240 }, { "epoch": 0.01, "learning_rate": 1.2104034230389495e-05, "loss": 3.3644, "step": 2314752 }, { "epoch": 0.01, "learning_rate": 1.2095648282878975e-05, "loss": 3.3713, "step": 2315264 }, { "epoch": 0.01, "learning_rate": 1.2087262335368455e-05, "loss": 3.3697, "step": 2315776 }, { "epoch": 0.01, "learning_rate": 1.2078892766661666e-05, "loss": 3.3591, "step": 2316288 }, { "epoch": 0.01, "learning_rate": 1.2070506819151146e-05, "loss": 3.3521, "step": 2316800 }, { "epoch": 0.01, "learning_rate": 1.2062120871640627e-05, "loss": 3.3463, "step": 2317312 }, { "epoch": 0.01, "learning_rate": 1.2053734924130105e-05, "loss": 3.3514, "step": 2317824 }, { "epoch": 0.01, "learning_rate": 1.2045365355423318e-05, "loss": 3.3785, "step": 2318336 }, { "epoch": 0.01, "learning_rate": 1.2036979407912798e-05, "loss": 3.3483, "step": 2318848 }, { "epoch": 0.01, "learning_rate": 1.2028593460402276e-05, "loss": 3.3686, "step": 2319360 }, { "epoch": 0.01, "learning_rate": 1.2020207512891756e-05, "loss": 3.362, "step": 2319872 }, { "epoch": 0.01, "learning_rate": 1.2011837944184969e-05, "loss": 3.3522, "step": 2320384 }, { "epoch": 0.01, "learning_rate": 1.2003451996674449e-05, "loss": 3.3672, "step": 2320896 }, { "epoch": 0.01, "learning_rate": 1.1995066049163929e-05, "loss": 3.3534, "step": 2321408 }, { "epoch": 0.01, "learning_rate": 1.1986680101653408e-05, "loss": 3.3557, "step": 2321920 }, { "epoch": 0.01, "learning_rate": 1.197831053294662e-05, "loss": 3.3529, "step": 2322432 }, { "epoch": 0.01, "learning_rate": 1.19699245854361e-05, "loss": 3.3712, "step": 2322944 }, { "epoch": 0.01, "learning_rate": 1.196153863792558e-05, "loss": 3.3563, "step": 2323456 }, { "epoch": 0.01, "learning_rate": 1.1953152690415059e-05, "loss": 3.3563, "step": 2323968 }, { "epoch": 0.01, "learning_rate": 1.1944783121708272e-05, "loss": 3.3507, "step": 2324480 }, { "epoch": 0.01, "learning_rate": 1.193639717419775e-05, "loss": 3.3584, "step": 2324992 }, { "epoch": 0.01, "learning_rate": 1.192801122668723e-05, "loss": 3.3696, "step": 2325504 }, { "epoch": 0.01, "learning_rate": 1.191962527917671e-05, "loss": 3.369, "step": 2326016 }, { "epoch": 0.01, "learning_rate": 1.1911255710469922e-05, "loss": 3.3676, "step": 2326528 }, { "epoch": 0.01, "learning_rate": 1.19028697629594e-05, "loss": 3.3716, "step": 2327040 }, { "epoch": 0.01, "learning_rate": 1.189448381544888e-05, "loss": 3.3835, "step": 2327552 }, { "epoch": 0.01, "learning_rate": 1.1886097867938362e-05, "loss": 3.3715, "step": 2328064 }, { "epoch": 0.01, "learning_rate": 1.1877728299231571e-05, "loss": 3.3733, "step": 2328576 }, { "epoch": 0.01, "learning_rate": 1.1869342351721053e-05, "loss": 3.361, "step": 2329088 }, { "epoch": 0.01, "learning_rate": 1.1860956404210533e-05, "loss": 3.3619, "step": 2329600 }, { "epoch": 0.01, "learning_rate": 1.1852570456700013e-05, "loss": 3.3624, "step": 2330112 }, { "epoch": 0.01, "learning_rate": 1.1844200887993224e-05, "loss": 3.3591, "step": 2330624 }, { "epoch": 0.01, "learning_rate": 1.1835814940482704e-05, "loss": 3.3714, "step": 2331136 }, { "epoch": 0.01, "learning_rate": 1.1827428992972184e-05, "loss": 3.3747, "step": 2331648 }, { "epoch": 0.01, "learning_rate": 1.1819043045461663e-05, "loss": 3.369, "step": 2332160 }, { "epoch": 0.01, "learning_rate": 1.1810673476754874e-05, "loss": 3.346, "step": 2332672 }, { "epoch": 0.01, "learning_rate": 1.1802287529244354e-05, "loss": 3.3565, "step": 2333184 }, { "epoch": 0.01, "learning_rate": 1.1793901581733834e-05, "loss": 3.3659, "step": 2333696 }, { "epoch": 0.01, "learning_rate": 1.1785515634223314e-05, "loss": 3.3697, "step": 2334208 }, { "epoch": 0.01, "learning_rate": 1.1777146065516525e-05, "loss": 3.3578, "step": 2334720 }, { "epoch": 0.01, "learning_rate": 1.1768760118006007e-05, "loss": 3.37, "step": 2335232 }, { "epoch": 0.02, "learning_rate": 1.1760374170495487e-05, "loss": 3.3621, "step": 2335744 }, { "epoch": 0.02, "learning_rate": 1.1751988222984965e-05, "loss": 3.3525, "step": 2336256 }, { "epoch": 0.02, "learning_rate": 1.1743618654278177e-05, "loss": 3.3596, "step": 2336768 }, { "epoch": 0.02, "learning_rate": 1.1735232706767657e-05, "loss": 3.3699, "step": 2337280 }, { "epoch": 0.02, "learning_rate": 1.1726846759257135e-05, "loss": 3.3661, "step": 2337792 }, { "epoch": 0.02, "learning_rate": 1.1718460811746617e-05, "loss": 3.3724, "step": 2338304 }, { "epoch": 0.02, "learning_rate": 1.1710091243039828e-05, "loss": 3.3535, "step": 2338816 }, { "epoch": 0.02, "learning_rate": 1.1701705295529308e-05, "loss": 3.3607, "step": 2339328 }, { "epoch": 0.02, "learning_rate": 1.1693319348018788e-05, "loss": 3.3703, "step": 2339840 }, { "epoch": 0.02, "learning_rate": 1.1684933400508268e-05, "loss": 3.3676, "step": 2340352 }, { "epoch": 0.02, "learning_rate": 1.1676563831801479e-05, "loss": 3.3722, "step": 2340864 }, { "epoch": 0.02, "learning_rate": 1.166817788429096e-05, "loss": 3.3671, "step": 2341376 }, { "epoch": 0.02, "learning_rate": 1.1659791936780438e-05, "loss": 3.3646, "step": 2341888 }, { "epoch": 0.02, "learning_rate": 1.1651405989269918e-05, "loss": 3.3656, "step": 2342400 }, { "epoch": 0.02, "learning_rate": 1.1643036420563131e-05, "loss": 3.3695, "step": 2342912 }, { "epoch": 0.02, "learning_rate": 1.163465047305261e-05, "loss": 3.3507, "step": 2343424 }, { "epoch": 0.02, "learning_rate": 1.162626452554209e-05, "loss": 3.3586, "step": 2343936 }, { "epoch": 0.02, "learning_rate": 1.1617878578031569e-05, "loss": 3.3585, "step": 2344448 }, { "epoch": 0.02, "learning_rate": 1.1609509009324782e-05, "loss": 3.3638, "step": 2344960 }, { "epoch": 0.02, "learning_rate": 1.160112306181426e-05, "loss": 3.3512, "step": 2345472 }, { "epoch": 0.02, "learning_rate": 1.1592737114303742e-05, "loss": 3.3551, "step": 2345984 }, { "epoch": 0.02, "learning_rate": 1.1584351166793221e-05, "loss": 3.3473, "step": 2346496 }, { "epoch": 0.02, "learning_rate": 1.1575981598086432e-05, "loss": 3.3664, "step": 2347008 }, { "epoch": 0.02, "learning_rate": 1.1567595650575912e-05, "loss": 3.3607, "step": 2347520 }, { "epoch": 0.02, "learning_rate": 1.1559209703065392e-05, "loss": 3.3607, "step": 2348032 }, { "epoch": 0.02, "learning_rate": 1.1550823755554872e-05, "loss": 3.3645, "step": 2348544 }, { "epoch": 0.02, "learning_rate": 1.1542454186848083e-05, "loss": 3.373, "step": 2349056 }, { "epoch": 0.02, "learning_rate": 1.1534068239337563e-05, "loss": 3.3648, "step": 2349568 }, { "epoch": 0.02, "learning_rate": 1.1525682291827043e-05, "loss": 3.3639, "step": 2350080 }, { "epoch": 0.02, "learning_rate": 1.1517296344316523e-05, "loss": 3.374, "step": 2350592 }, { "epoch": 0.02, "learning_rate": 1.1508926775609734e-05, "loss": 3.3612, "step": 2351104 }, { "epoch": 0.02, "learning_rate": 1.1500540828099214e-05, "loss": 3.3581, "step": 2351616 }, { "epoch": 0.02, "learning_rate": 1.1492154880588695e-05, "loss": 3.3666, "step": 2352128 }, { "epoch": 0.02, "learning_rate": 1.1483768933078173e-05, "loss": 3.3651, "step": 2352640 }, { "epoch": 0.02, "learning_rate": 1.1475399364371384e-05, "loss": 3.3645, "step": 2353152 }, { "epoch": 0.02, "learning_rate": 1.1467013416860866e-05, "loss": 3.3531, "step": 2353664 }, { "epoch": 0.02, "learning_rate": 1.1458627469350346e-05, "loss": 3.3637, "step": 2354176 }, { "epoch": 0.02, "learning_rate": 1.1450241521839824e-05, "loss": 3.3543, "step": 2354688 }, { "epoch": 0.02, "learning_rate": 1.1441871953133037e-05, "loss": 3.3597, "step": 2355200 }, { "epoch": 0.02, "learning_rate": 1.1433486005622517e-05, "loss": 3.3509, "step": 2355712 }, { "epoch": 0.02, "learning_rate": 1.1425100058111996e-05, "loss": 3.3705, "step": 2356224 }, { "epoch": 0.02, "learning_rate": 1.1416714110601476e-05, "loss": 3.3707, "step": 2356736 }, { "epoch": 0.02, "learning_rate": 1.1408344541894687e-05, "loss": 3.3517, "step": 2357248 }, { "epoch": 0.02, "learning_rate": 1.1399958594384167e-05, "loss": 3.3718, "step": 2357760 }, { "epoch": 0.02, "learning_rate": 1.1391572646873647e-05, "loss": 3.3672, "step": 2358272 }, { "epoch": 0.02, "learning_rate": 1.1383186699363127e-05, "loss": 3.3689, "step": 2358784 }, { "epoch": 0.02, "learning_rate": 1.1374817130656338e-05, "loss": 3.3601, "step": 2359296 }, { "epoch": 0.02, "learning_rate": 1.136643118314582e-05, "loss": 3.3618, "step": 2359808 }, { "epoch": 0.02, "learning_rate": 1.1358045235635298e-05, "loss": 3.3728, "step": 2360320 }, { "epoch": 0.02, "learning_rate": 1.1349659288124778e-05, "loss": 3.3581, "step": 2360832 }, { "epoch": 0.02, "learning_rate": 1.134128971941799e-05, "loss": 3.3679, "step": 2361344 }, { "epoch": 0.02, "learning_rate": 1.133290377190747e-05, "loss": 3.3616, "step": 2361856 }, { "epoch": 0.02, "learning_rate": 1.1324517824396948e-05, "loss": 3.3634, "step": 2362368 }, { "epoch": 0.02, "learning_rate": 1.131613187688643e-05, "loss": 3.3578, "step": 2362880 }, { "epoch": 0.02, "learning_rate": 1.1307762308179641e-05, "loss": 3.357, "step": 2363392 }, { "epoch": 0.02, "learning_rate": 1.129937636066912e-05, "loss": 3.3633, "step": 2363904 }, { "epoch": 0.02, "learning_rate": 1.12909904131586e-05, "loss": 3.3591, "step": 2364416 }, { "epoch": 0.02, "learning_rate": 1.128260446564808e-05, "loss": 3.3702, "step": 2364928 }, { "epoch": 0.02, "learning_rate": 1.1274234896941292e-05, "loss": 3.3607, "step": 2365440 }, { "epoch": 0.03, "eval_loss": 3.867492437362671, "eval_runtime": 303.6273, "eval_samples_per_second": 1256.774, "eval_steps_per_second": 39.275, "step": 2365920 }, { "epoch": 1.0, "learning_rate": 1.1265848949430772e-05, "loss": 3.3579, "step": 2365952 }, { "epoch": 1.0, "learning_rate": 1.1257463001920251e-05, "loss": 3.3559, "step": 2366464 }, { "epoch": 1.0, "learning_rate": 1.1249077054409731e-05, "loss": 3.3536, "step": 2366976 }, { "epoch": 1.0, "learning_rate": 1.1240707485702942e-05, "loss": 3.365, "step": 2367488 }, { "epoch": 1.0, "learning_rate": 1.1232321538192422e-05, "loss": 3.3624, "step": 2368000 }, { "epoch": 1.0, "learning_rate": 1.1223935590681902e-05, "loss": 3.3724, "step": 2368512 }, { "epoch": 1.0, "learning_rate": 1.1215566021975115e-05, "loss": 3.3544, "step": 2369024 }, { "epoch": 1.0, "learning_rate": 1.1207180074464593e-05, "loss": 3.3592, "step": 2369536 }, { "epoch": 1.0, "learning_rate": 1.1198794126954073e-05, "loss": 3.3501, "step": 2370048 }, { "epoch": 1.0, "learning_rate": 1.1190408179443554e-05, "loss": 3.3636, "step": 2370560 }, { "epoch": 1.0, "learning_rate": 1.1182038610736765e-05, "loss": 3.3556, "step": 2371072 }, { "epoch": 1.0, "learning_rate": 1.1173652663226245e-05, "loss": 3.3646, "step": 2371584 }, { "epoch": 1.0, "learning_rate": 1.1165283094519456e-05, "loss": 3.3662, "step": 2372096 }, { "epoch": 1.0, "learning_rate": 1.1156897147008936e-05, "loss": 3.3477, "step": 2372608 }, { "epoch": 1.0, "learning_rate": 1.1148511199498416e-05, "loss": 3.3457, "step": 2373120 }, { "epoch": 1.0, "learning_rate": 1.1140125251987896e-05, "loss": 3.3511, "step": 2373632 }, { "epoch": 1.0, "learning_rate": 1.1131739304477376e-05, "loss": 3.354, "step": 2374144 }, { "epoch": 1.0, "learning_rate": 1.1123353356966856e-05, "loss": 3.3544, "step": 2374656 }, { "epoch": 1.0, "learning_rate": 1.1114967409456336e-05, "loss": 3.3616, "step": 2375168 }, { "epoch": 1.0, "learning_rate": 1.1106581461945816e-05, "loss": 3.3528, "step": 2375680 }, { "epoch": 1.0, "learning_rate": 1.1098211893239026e-05, "loss": 3.3715, "step": 2376192 }, { "epoch": 1.0, "learning_rate": 1.1089825945728506e-05, "loss": 3.3583, "step": 2376704 }, { "epoch": 1.0, "learning_rate": 1.1081439998217986e-05, "loss": 3.3611, "step": 2377216 }, { "epoch": 1.0, "learning_rate": 1.1073054050707466e-05, "loss": 3.3612, "step": 2377728 }, { "epoch": 1.0, "learning_rate": 1.1064684482000679e-05, "loss": 3.3693, "step": 2378240 }, { "epoch": 1.0, "learning_rate": 1.1056298534490157e-05, "loss": 3.3594, "step": 2378752 }, { "epoch": 1.0, "learning_rate": 1.1047912586979637e-05, "loss": 3.3542, "step": 2379264 }, { "epoch": 1.0, "learning_rate": 1.1039526639469119e-05, "loss": 3.3596, "step": 2379776 }, { "epoch": 1.0, "learning_rate": 1.103115707076233e-05, "loss": 3.3468, "step": 2380288 }, { "epoch": 1.0, "learning_rate": 1.1022771123251808e-05, "loss": 3.3526, "step": 2380800 }, { "epoch": 1.01, "learning_rate": 1.101438517574129e-05, "loss": 3.3547, "step": 2381312 }, { "epoch": 1.01, "learning_rate": 1.100599922823077e-05, "loss": 3.362, "step": 2381824 }, { "epoch": 1.01, "learning_rate": 1.099762965952398e-05, "loss": 3.357, "step": 2382336 }, { "epoch": 1.01, "learning_rate": 1.098924371201346e-05, "loss": 3.3656, "step": 2382848 }, { "epoch": 1.01, "learning_rate": 1.098085776450294e-05, "loss": 3.3616, "step": 2383360 }, { "epoch": 1.01, "learning_rate": 1.097247181699242e-05, "loss": 3.3586, "step": 2383872 }, { "epoch": 1.01, "learning_rate": 1.096410224828563e-05, "loss": 3.3617, "step": 2384384 }, { "epoch": 1.01, "learning_rate": 1.095571630077511e-05, "loss": 3.3498, "step": 2384896 }, { "epoch": 1.01, "learning_rate": 1.094733035326459e-05, "loss": 3.3657, "step": 2385408 }, { "epoch": 1.01, "learning_rate": 1.093894440575407e-05, "loss": 3.3511, "step": 2385920 }, { "epoch": 1.01, "learning_rate": 1.0930574837047281e-05, "loss": 3.355, "step": 2386432 }, { "epoch": 1.01, "learning_rate": 1.0922188889536761e-05, "loss": 3.3564, "step": 2386944 }, { "epoch": 1.01, "learning_rate": 1.0913802942026243e-05, "loss": 3.3667, "step": 2387456 }, { "epoch": 1.01, "learning_rate": 1.0905416994515721e-05, "loss": 3.3558, "step": 2387968 }, { "epoch": 1.01, "learning_rate": 1.0897047425808934e-05, "loss": 3.3618, "step": 2388480 }, { "epoch": 1.01, "learning_rate": 1.0888661478298414e-05, "loss": 3.3609, "step": 2388992 }, { "epoch": 1.01, "learning_rate": 1.0880275530787894e-05, "loss": 3.3598, "step": 2389504 }, { "epoch": 1.01, "learning_rate": 1.0871889583277372e-05, "loss": 3.3614, "step": 2390016 }, { "epoch": 1.01, "learning_rate": 1.0863520014570584e-05, "loss": 3.33, "step": 2390528 }, { "epoch": 1.01, "learning_rate": 1.0855134067060064e-05, "loss": 3.3503, "step": 2391040 }, { "epoch": 1.01, "learning_rate": 1.0846748119549543e-05, "loss": 3.3636, "step": 2391552 }, { "epoch": 1.01, "learning_rate": 1.0838362172039024e-05, "loss": 3.3615, "step": 2392064 }, { "epoch": 1.01, "learning_rate": 1.0829992603332235e-05, "loss": 3.3494, "step": 2392576 }, { "epoch": 1.01, "learning_rate": 1.0821606655821715e-05, "loss": 3.338, "step": 2393088 }, { "epoch": 1.01, "learning_rate": 1.0813220708311195e-05, "loss": 3.3423, "step": 2393600 }, { "epoch": 1.01, "learning_rate": 1.0804834760800675e-05, "loss": 3.3353, "step": 2394112 }, { "epoch": 1.01, "learning_rate": 1.0796465192093887e-05, "loss": 3.3709, "step": 2394624 }, { "epoch": 1.01, "learning_rate": 1.0788079244583367e-05, "loss": 3.3398, "step": 2395136 }, { "epoch": 1.01, "learning_rate": 1.0779693297072846e-05, "loss": 3.3583, "step": 2395648 }, { "epoch": 1.01, "learning_rate": 1.0771307349562326e-05, "loss": 3.3528, "step": 2396160 }, { "epoch": 1.01, "learning_rate": 1.0762937780855538e-05, "loss": 3.344, "step": 2396672 }, { "epoch": 1.01, "learning_rate": 1.0754551833345016e-05, "loss": 3.3565, "step": 2397184 }, { "epoch": 1.01, "learning_rate": 1.0746165885834496e-05, "loss": 3.3474, "step": 2397696 }, { "epoch": 1.01, "learning_rate": 1.0737779938323978e-05, "loss": 3.345, "step": 2398208 }, { "epoch": 1.01, "learning_rate": 1.0729410369617189e-05, "loss": 3.3411, "step": 2398720 }, { "epoch": 1.01, "learning_rate": 1.0721024422106669e-05, "loss": 3.3644, "step": 2399232 }, { "epoch": 1.01, "learning_rate": 1.0712638474596149e-05, "loss": 3.3453, "step": 2399744 }, { "epoch": 1.01, "learning_rate": 1.0704252527085629e-05, "loss": 3.3442, "step": 2400256 }, { "epoch": 1.01, "learning_rate": 1.069588295837884e-05, "loss": 3.3408, "step": 2400768 }, { "epoch": 1.01, "learning_rate": 1.068749701086832e-05, "loss": 3.3502, "step": 2401280 }, { "epoch": 1.01, "learning_rate": 1.06791110633578e-05, "loss": 3.36, "step": 2401792 }, { "epoch": 1.01, "learning_rate": 1.067072511584728e-05, "loss": 3.3613, "step": 2402304 }, { "epoch": 1.01, "learning_rate": 1.066235554714049e-05, "loss": 3.3601, "step": 2402816 }, { "epoch": 1.01, "learning_rate": 1.065396959962997e-05, "loss": 3.3624, "step": 2403328 }, { "epoch": 1.01, "learning_rate": 1.064558365211945e-05, "loss": 3.3699, "step": 2403840 }, { "epoch": 1.01, "learning_rate": 1.0637197704608932e-05, "loss": 3.3661, "step": 2404352 }, { "epoch": 1.01, "learning_rate": 1.062882813590214e-05, "loss": 3.3627, "step": 2404864 }, { "epoch": 1.01, "learning_rate": 1.0620442188391622e-05, "loss": 3.3499, "step": 2405376 }, { "epoch": 1.01, "learning_rate": 1.0612056240881102e-05, "loss": 3.3554, "step": 2405888 }, { "epoch": 1.01, "learning_rate": 1.060367029337058e-05, "loss": 3.3513, "step": 2406400 }, { "epoch": 1.01, "learning_rate": 1.0595300724663793e-05, "loss": 3.354, "step": 2406912 }, { "epoch": 1.01, "learning_rate": 1.0586914777153273e-05, "loss": 3.3624, "step": 2407424 }, { "epoch": 1.01, "learning_rate": 1.0578528829642753e-05, "loss": 3.3664, "step": 2407936 }, { "epoch": 1.01, "learning_rate": 1.0570142882132231e-05, "loss": 3.3556, "step": 2408448 }, { "epoch": 1.01, "learning_rate": 1.0561773313425444e-05, "loss": 3.3398, "step": 2408960 }, { "epoch": 1.01, "learning_rate": 1.0553387365914924e-05, "loss": 3.344, "step": 2409472 }, { "epoch": 1.01, "learning_rate": 1.0545001418404404e-05, "loss": 3.3539, "step": 2409984 }, { "epoch": 1.01, "learning_rate": 1.0536615470893884e-05, "loss": 3.3652, "step": 2410496 }, { "epoch": 1.01, "learning_rate": 1.0528245902187094e-05, "loss": 3.3449, "step": 2411008 }, { "epoch": 1.01, "learning_rate": 1.0519859954676576e-05, "loss": 3.3599, "step": 2411520 }, { "epoch": 1.02, "learning_rate": 1.0511474007166054e-05, "loss": 3.3559, "step": 2412032 }, { "epoch": 1.02, "learning_rate": 1.0503088059655534e-05, "loss": 3.3434, "step": 2412544 }, { "epoch": 1.02, "learning_rate": 1.0494718490948747e-05, "loss": 3.3489, "step": 2413056 }, { "epoch": 1.02, "learning_rate": 1.0486332543438227e-05, "loss": 3.3595, "step": 2413568 }, { "epoch": 1.02, "learning_rate": 1.0477946595927705e-05, "loss": 3.3529, "step": 2414080 }, { "epoch": 1.02, "learning_rate": 1.0469560648417185e-05, "loss": 3.3631, "step": 2414592 }, { "epoch": 1.02, "learning_rate": 1.0461191079710397e-05, "loss": 3.3485, "step": 2415104 }, { "epoch": 1.02, "learning_rate": 1.0452805132199876e-05, "loss": 3.3497, "step": 2415616 }, { "epoch": 1.02, "learning_rate": 1.0444419184689357e-05, "loss": 3.3563, "step": 2416128 }, { "epoch": 1.02, "learning_rate": 1.0436033237178837e-05, "loss": 3.362, "step": 2416640 }, { "epoch": 1.02, "learning_rate": 1.0427663668472048e-05, "loss": 3.3581, "step": 2417152 }, { "epoch": 1.02, "learning_rate": 1.0419277720961528e-05, "loss": 3.3586, "step": 2417664 }, { "epoch": 1.02, "learning_rate": 1.0410891773451008e-05, "loss": 3.3552, "step": 2418176 }, { "epoch": 1.02, "learning_rate": 1.0402505825940488e-05, "loss": 3.3582, "step": 2418688 }, { "epoch": 1.02, "learning_rate": 1.03941362572337e-05, "loss": 3.3575, "step": 2419200 }, { "epoch": 1.02, "learning_rate": 1.0385750309723179e-05, "loss": 3.3384, "step": 2419712 }, { "epoch": 1.02, "learning_rate": 1.0377364362212659e-05, "loss": 3.3472, "step": 2420224 }, { "epoch": 1.02, "learning_rate": 1.0368978414702139e-05, "loss": 3.3529, "step": 2420736 }, { "epoch": 1.02, "learning_rate": 1.036060884599535e-05, "loss": 3.3532, "step": 2421248 }, { "epoch": 1.02, "learning_rate": 1.035222289848483e-05, "loss": 3.3429, "step": 2421760 }, { "epoch": 1.02, "learning_rate": 1.0343836950974311e-05, "loss": 3.3461, "step": 2422272 }, { "epoch": 1.02, "learning_rate": 1.0335451003463791e-05, "loss": 3.3375, "step": 2422784 }, { "epoch": 1.02, "learning_rate": 1.0327081434757e-05, "loss": 3.355, "step": 2423296 }, { "epoch": 1.02, "learning_rate": 1.0318695487246482e-05, "loss": 3.3468, "step": 2423808 }, { "epoch": 1.02, "learning_rate": 1.0310309539735962e-05, "loss": 3.3572, "step": 2424320 }, { "epoch": 1.02, "learning_rate": 1.030192359222544e-05, "loss": 3.3518, "step": 2424832 }, { "epoch": 1.02, "learning_rate": 1.0293554023518652e-05, "loss": 3.3653, "step": 2425344 }, { "epoch": 1.02, "learning_rate": 1.0285168076008132e-05, "loss": 3.3553, "step": 2425856 }, { "epoch": 1.02, "learning_rate": 1.0276782128497612e-05, "loss": 3.3551, "step": 2426368 }, { "epoch": 1.02, "learning_rate": 1.0268396180987092e-05, "loss": 3.3618, "step": 2426880 }, { "epoch": 1.02, "learning_rate": 1.0260026612280303e-05, "loss": 3.3532, "step": 2427392 }, { "epoch": 1.02, "learning_rate": 1.0251640664769783e-05, "loss": 3.3506, "step": 2427904 }, { "epoch": 1.02, "learning_rate": 1.0243254717259263e-05, "loss": 3.3544, "step": 2428416 }, { "epoch": 1.02, "learning_rate": 1.0234868769748743e-05, "loss": 3.3535, "step": 2428928 }, { "epoch": 1.02, "learning_rate": 1.0226499201041954e-05, "loss": 3.3564, "step": 2429440 }, { "epoch": 1.02, "learning_rate": 1.0218113253531435e-05, "loss": 3.3474, "step": 2429952 }, { "epoch": 1.02, "learning_rate": 1.0209727306020914e-05, "loss": 3.3478, "step": 2430464 }, { "epoch": 1.02, "learning_rate": 1.0201341358510394e-05, "loss": 3.3445, "step": 2430976 }, { "epoch": 1.02, "learning_rate": 1.0192971789803606e-05, "loss": 3.3459, "step": 2431488 }, { "epoch": 1.02, "learning_rate": 1.0184585842293086e-05, "loss": 3.3416, "step": 2432000 }, { "epoch": 1.02, "learning_rate": 1.0176199894782564e-05, "loss": 3.3654, "step": 2432512 }, { "epoch": 1.02, "learning_rate": 1.0167813947272046e-05, "loss": 3.3579, "step": 2433024 }, { "epoch": 1.02, "learning_rate": 1.0159444378565257e-05, "loss": 3.3503, "step": 2433536 }, { "epoch": 1.02, "learning_rate": 1.0151058431054737e-05, "loss": 3.3543, "step": 2434048 }, { "epoch": 1.02, "learning_rate": 1.0142672483544217e-05, "loss": 3.3553, "step": 2434560 }, { "epoch": 1.02, "learning_rate": 1.0134286536033697e-05, "loss": 3.3607, "step": 2435072 }, { "epoch": 1.02, "learning_rate": 1.0125916967326907e-05, "loss": 3.3543, "step": 2435584 }, { "epoch": 1.02, "learning_rate": 1.0117531019816387e-05, "loss": 3.3525, "step": 2436096 }, { "epoch": 1.02, "learning_rate": 1.0109145072305867e-05, "loss": 3.3647, "step": 2436608 }, { "epoch": 1.02, "learning_rate": 1.0100759124795347e-05, "loss": 3.3474, "step": 2437120 }, { "epoch": 1.02, "learning_rate": 1.009238955608856e-05, "loss": 3.358, "step": 2437632 }, { "epoch": 1.02, "learning_rate": 1.0084003608578038e-05, "loss": 3.3533, "step": 2438144 }, { "epoch": 1.02, "learning_rate": 1.0075617661067518e-05, "loss": 3.3578, "step": 2438656 }, { "epoch": 1.02, "learning_rate": 1.0067231713556998e-05, "loss": 3.3507, "step": 2439168 }, { "epoch": 1.02, "learning_rate": 1.005886214485021e-05, "loss": 3.3405, "step": 2439680 }, { "epoch": 1.02, "learning_rate": 1.0050476197339689e-05, "loss": 3.3563, "step": 2440192 }, { "epoch": 1.02, "learning_rate": 1.004209024982917e-05, "loss": 3.3524, "step": 2440704 }, { "epoch": 1.02, "learning_rate": 1.003370430231865e-05, "loss": 3.3587, "step": 2441216 }, { "epoch": 1.02, "learning_rate": 1.0025334733611861e-05, "loss": 3.3482, "step": 2441728 }, { "epoch": 1.03, "learning_rate": 1.0016948786101341e-05, "loss": 3.354, "step": 2442240 }, { "epoch": 1.03, "eval_loss": 3.8665201663970947, "eval_runtime": 304.234, "eval_samples_per_second": 1254.268, "eval_steps_per_second": 39.197, "step": 2442240 }, { "epoch": 0.0, "learning_rate": 1.0008562838590821e-05, "loss": 3.3456, "step": 2442752 }, { "epoch": 0.0, "learning_rate": 1.0000176891080301e-05, "loss": 3.3417, "step": 2443264 }, { "epoch": 0.0, "learning_rate": 9.991790943569781e-06, "loss": 3.3588, "step": 2443776 }, { "epoch": 0.0, "learning_rate": 9.983421374862992e-06, "loss": 3.3544, "step": 2444288 }, { "epoch": 0.0, "learning_rate": 9.975035427352472e-06, "loss": 3.3622, "step": 2444800 }, { "epoch": 0.0, "learning_rate": 9.966649479841952e-06, "loss": 3.3445, "step": 2445312 }, { "epoch": 0.0, "learning_rate": 9.958263532331432e-06, "loss": 3.3488, "step": 2445824 }, { "epoch": 0.0, "learning_rate": 9.949893963624642e-06, "loss": 3.3379, "step": 2446336 }, { "epoch": 0.0, "learning_rate": 9.941508016114124e-06, "loss": 3.3563, "step": 2446848 }, { "epoch": 0.0, "learning_rate": 9.933122068603602e-06, "loss": 3.344, "step": 2447360 }, { "epoch": 0.0, "learning_rate": 9.924736121093082e-06, "loss": 3.3541, "step": 2447872 }, { "epoch": 0.0, "learning_rate": 9.916366552386295e-06, "loss": 3.3519, "step": 2448384 }, { "epoch": 0.0, "learning_rate": 9.907996983679506e-06, "loss": 3.3479, "step": 2448896 }, { "epoch": 0.0, "learning_rate": 9.899611036168985e-06, "loss": 3.3375, "step": 2449408 }, { "epoch": 0.0, "learning_rate": 9.891225088658465e-06, "loss": 3.3415, "step": 2449920 }, { "epoch": 0.0, "learning_rate": 9.882839141147945e-06, "loss": 3.3385, "step": 2450432 }, { "epoch": 0.0, "learning_rate": 9.874453193637424e-06, "loss": 3.3468, "step": 2450944 }, { "epoch": 0.0, "learning_rate": 9.866067246126905e-06, "loss": 3.351, "step": 2451456 }, { "epoch": 0.0, "learning_rate": 9.857681298616385e-06, "loss": 3.3414, "step": 2451968 }, { "epoch": 0.0, "learning_rate": 9.849311729909596e-06, "loss": 3.3666, "step": 2452480 }, { "epoch": 0.0, "learning_rate": 9.840925782399076e-06, "loss": 3.3469, "step": 2452992 }, { "epoch": 0.0, "learning_rate": 9.832539834888556e-06, "loss": 3.3518, "step": 2453504 }, { "epoch": 0.0, "learning_rate": 9.824153887378036e-06, "loss": 3.3512, "step": 2454016 }, { "epoch": 0.0, "learning_rate": 9.815784318671247e-06, "loss": 3.3586, "step": 2454528 }, { "epoch": 0.0, "learning_rate": 9.807398371160727e-06, "loss": 3.3458, "step": 2455040 }, { "epoch": 0.0, "learning_rate": 9.799012423650207e-06, "loss": 3.3492, "step": 2455552 }, { "epoch": 0.0, "learning_rate": 9.790626476139687e-06, "loss": 3.3448, "step": 2456064 }, { "epoch": 0.0, "learning_rate": 9.782256907432897e-06, "loss": 3.345, "step": 2456576 }, { "epoch": 0.0, "learning_rate": 9.773870959922377e-06, "loss": 3.3389, "step": 2457088 }, { "epoch": 0.01, "learning_rate": 9.765485012411859e-06, "loss": 3.3437, "step": 2457600 }, { "epoch": 0.01, "learning_rate": 9.757099064901337e-06, "loss": 3.3548, "step": 2458112 }, { "epoch": 0.01, "learning_rate": 9.748729496194548e-06, "loss": 3.3488, "step": 2458624 }, { "epoch": 0.01, "learning_rate": 9.74034354868403e-06, "loss": 3.3534, "step": 2459136 }, { "epoch": 0.01, "learning_rate": 9.73195760117351e-06, "loss": 3.3527, "step": 2459648 }, { "epoch": 0.01, "learning_rate": 9.723571653662988e-06, "loss": 3.3514, "step": 2460160 }, { "epoch": 0.01, "learning_rate": 9.7152020849562e-06, "loss": 3.3504, "step": 2460672 }, { "epoch": 0.01, "learning_rate": 9.70681613744568e-06, "loss": 3.3449, "step": 2461184 }, { "epoch": 0.01, "learning_rate": 9.69843018993516e-06, "loss": 3.3487, "step": 2461696 }, { "epoch": 0.01, "learning_rate": 9.69004424242464e-06, "loss": 3.342, "step": 2462208 }, { "epoch": 0.01, "learning_rate": 9.681674673717851e-06, "loss": 3.3495, "step": 2462720 }, { "epoch": 0.01, "learning_rate": 9.673288726207331e-06, "loss": 3.3479, "step": 2463232 }, { "epoch": 0.01, "learning_rate": 9.664902778696811e-06, "loss": 3.3575, "step": 2463744 }, { "epoch": 0.01, "learning_rate": 9.656516831186291e-06, "loss": 3.3447, "step": 2464256 }, { "epoch": 0.01, "learning_rate": 9.648147262479502e-06, "loss": 3.3513, "step": 2464768 }, { "epoch": 0.01, "learning_rate": 9.639761314968983e-06, "loss": 3.3535, "step": 2465280 }, { "epoch": 0.01, "learning_rate": 9.631375367458462e-06, "loss": 3.3515, "step": 2465792 }, { "epoch": 0.01, "learning_rate": 9.622989419947942e-06, "loss": 3.3474, "step": 2466304 }, { "epoch": 0.01, "learning_rate": 9.614619851241154e-06, "loss": 3.3222, "step": 2466816 }, { "epoch": 0.01, "learning_rate": 9.606233903730634e-06, "loss": 3.3442, "step": 2467328 }, { "epoch": 0.01, "learning_rate": 9.597847956220112e-06, "loss": 3.35, "step": 2467840 }, { "epoch": 0.01, "learning_rate": 9.589462008709594e-06, "loss": 3.354, "step": 2468352 }, { "epoch": 0.01, "learning_rate": 9.581092440002805e-06, "loss": 3.3409, "step": 2468864 }, { "epoch": 0.01, "learning_rate": 9.572706492492285e-06, "loss": 3.3279, "step": 2469376 }, { "epoch": 0.01, "learning_rate": 9.564320544981765e-06, "loss": 3.3359, "step": 2469888 }, { "epoch": 0.01, "learning_rate": 9.555934597471245e-06, "loss": 3.3277, "step": 2470400 }, { "epoch": 0.01, "learning_rate": 9.547565028764455e-06, "loss": 3.3596, "step": 2470912 }, { "epoch": 0.01, "learning_rate": 9.539179081253935e-06, "loss": 3.3327, "step": 2471424 }, { "epoch": 0.01, "learning_rate": 9.530793133743415e-06, "loss": 3.3508, "step": 2471936 }, { "epoch": 0.01, "learning_rate": 9.522407186232895e-06, "loss": 3.3449, "step": 2472448 }, { "epoch": 0.01, "learning_rate": 9.514037617526108e-06, "loss": 3.3323, "step": 2472960 }, { "epoch": 0.01, "learning_rate": 9.505651670015586e-06, "loss": 3.3475, "step": 2473472 }, { "epoch": 0.01, "learning_rate": 9.497265722505066e-06, "loss": 3.3388, "step": 2473984 }, { "epoch": 0.01, "learning_rate": 9.488879774994548e-06, "loss": 3.3337, "step": 2474496 }, { "epoch": 0.01, "learning_rate": 9.480510206287757e-06, "loss": 3.3295, "step": 2475008 }, { "epoch": 0.01, "learning_rate": 9.472124258777237e-06, "loss": 3.3595, "step": 2475520 }, { "epoch": 0.01, "learning_rate": 9.463738311266718e-06, "loss": 3.3407, "step": 2476032 }, { "epoch": 0.01, "learning_rate": 9.455352363756198e-06, "loss": 3.3341, "step": 2476544 }, { "epoch": 0.01, "learning_rate": 9.446982795049409e-06, "loss": 3.3328, "step": 2477056 }, { "epoch": 0.01, "learning_rate": 9.438596847538889e-06, "loss": 3.3401, "step": 2477568 }, { "epoch": 0.01, "learning_rate": 9.430210900028369e-06, "loss": 3.3494, "step": 2478080 }, { "epoch": 0.01, "learning_rate": 9.421824952517847e-06, "loss": 3.3505, "step": 2478592 }, { "epoch": 0.01, "learning_rate": 9.41345538381106e-06, "loss": 3.3501, "step": 2479104 }, { "epoch": 0.01, "learning_rate": 9.40506943630054e-06, "loss": 3.3547, "step": 2479616 }, { "epoch": 0.01, "learning_rate": 9.39668348879002e-06, "loss": 3.3591, "step": 2480128 }, { "epoch": 0.01, "learning_rate": 9.3882975412795e-06, "loss": 3.3554, "step": 2480640 }, { "epoch": 0.01, "learning_rate": 9.37992797257271e-06, "loss": 3.351, "step": 2481152 }, { "epoch": 0.01, "learning_rate": 9.37154202506219e-06, "loss": 3.3415, "step": 2481664 }, { "epoch": 0.01, "learning_rate": 9.363156077551672e-06, "loss": 3.3473, "step": 2482176 }, { "epoch": 0.01, "learning_rate": 9.35477013004115e-06, "loss": 3.3448, "step": 2482688 }, { "epoch": 0.01, "learning_rate": 9.346400561334363e-06, "loss": 3.3429, "step": 2483200 }, { "epoch": 0.01, "learning_rate": 9.338014613823843e-06, "loss": 3.3471, "step": 2483712 }, { "epoch": 0.01, "learning_rate": 9.329628666313321e-06, "loss": 3.3509, "step": 2484224 }, { "epoch": 0.01, "learning_rate": 9.3212427188028e-06, "loss": 3.3502, "step": 2484736 }, { "epoch": 0.01, "learning_rate": 9.312873150096013e-06, "loss": 3.3316, "step": 2485248 }, { "epoch": 0.01, "learning_rate": 9.304487202585493e-06, "loss": 3.3343, "step": 2485760 }, { "epoch": 0.01, "learning_rate": 9.296101255074972e-06, "loss": 3.3469, "step": 2486272 }, { "epoch": 0.01, "learning_rate": 9.287715307564453e-06, "loss": 3.3542, "step": 2486784 }, { "epoch": 0.01, "learning_rate": 9.279345738857664e-06, "loss": 3.339, "step": 2487296 }, { "epoch": 0.01, "learning_rate": 9.270959791347144e-06, "loss": 3.3515, "step": 2487808 }, { "epoch": 0.02, "learning_rate": 9.262573843836624e-06, "loss": 3.3495, "step": 2488320 }, { "epoch": 0.02, "learning_rate": 9.254187896326104e-06, "loss": 3.3342, "step": 2488832 }, { "epoch": 0.02, "learning_rate": 9.245818327619316e-06, "loss": 3.3394, "step": 2489344 }, { "epoch": 0.02, "learning_rate": 9.237432380108795e-06, "loss": 3.3477, "step": 2489856 }, { "epoch": 0.02, "learning_rate": 9.229046432598275e-06, "loss": 3.3459, "step": 2490368 }, { "epoch": 0.02, "learning_rate": 9.220660485087755e-06, "loss": 3.3509, "step": 2490880 }, { "epoch": 0.02, "learning_rate": 9.212290916380967e-06, "loss": 3.3464, "step": 2491392 }, { "epoch": 0.02, "learning_rate": 9.203904968870445e-06, "loss": 3.3348, "step": 2491904 }, { "epoch": 0.02, "learning_rate": 9.195519021359925e-06, "loss": 3.3523, "step": 2492416 }, { "epoch": 0.02, "learning_rate": 9.187133073849407e-06, "loss": 3.349, "step": 2492928 }, { "epoch": 0.02, "learning_rate": 9.178763505142616e-06, "loss": 3.3476, "step": 2493440 }, { "epoch": 0.02, "learning_rate": 9.170377557632098e-06, "loss": 3.3538, "step": 2493952 }, { "epoch": 0.02, "learning_rate": 9.161991610121578e-06, "loss": 3.3437, "step": 2494464 }, { "epoch": 0.02, "learning_rate": 9.153605662611058e-06, "loss": 3.347, "step": 2494976 }, { "epoch": 0.02, "learning_rate": 9.145236093904268e-06, "loss": 3.3526, "step": 2495488 }, { "epoch": 0.02, "learning_rate": 9.136850146393748e-06, "loss": 3.3305, "step": 2496000 }, { "epoch": 0.02, "learning_rate": 9.128464198883228e-06, "loss": 3.3358, "step": 2496512 }, { "epoch": 0.02, "learning_rate": 9.120078251372706e-06, "loss": 3.3453, "step": 2497024 }, { "epoch": 0.02, "learning_rate": 9.111708682665919e-06, "loss": 3.3457, "step": 2497536 }, { "epoch": 0.02, "learning_rate": 9.103322735155399e-06, "loss": 3.3289, "step": 2498048 }, { "epoch": 0.02, "learning_rate": 9.094936787644879e-06, "loss": 3.3377, "step": 2498560 }, { "epoch": 0.02, "learning_rate": 9.086550840134359e-06, "loss": 3.3321, "step": 2499072 }, { "epoch": 0.02, "learning_rate": 9.07818127142757e-06, "loss": 3.3428, "step": 2499584 }, { "epoch": 0.02, "learning_rate": 9.069795323917051e-06, "loss": 3.3416, "step": 2500096 }, { "epoch": 0.02, "learning_rate": 9.061409376406531e-06, "loss": 3.3439, "step": 2500608 }, { "epoch": 0.02, "learning_rate": 9.05302342889601e-06, "loss": 3.343, "step": 2501120 }, { "epoch": 0.02, "learning_rate": 9.044653860189222e-06, "loss": 3.3544, "step": 2501632 }, { "epoch": 0.02, "learning_rate": 9.036267912678702e-06, "loss": 3.3474, "step": 2502144 }, { "epoch": 0.02, "learning_rate": 9.02788196516818e-06, "loss": 3.3483, "step": 2502656 }, { "epoch": 0.02, "learning_rate": 9.019512396461393e-06, "loss": 3.3524, "step": 2503168 }, { "epoch": 0.02, "learning_rate": 9.011126448950873e-06, "loss": 3.3478, "step": 2503680 }, { "epoch": 0.02, "learning_rate": 9.002740501440353e-06, "loss": 3.3366, "step": 2504192 }, { "epoch": 0.02, "learning_rate": 8.994354553929833e-06, "loss": 3.3457, "step": 2504704 }, { "epoch": 0.02, "learning_rate": 8.985968606419313e-06, "loss": 3.3421, "step": 2505216 }, { "epoch": 0.02, "learning_rate": 8.977582658908792e-06, "loss": 3.3523, "step": 2505728 }, { "epoch": 0.02, "learning_rate": 8.96919671139827e-06, "loss": 3.3314, "step": 2506240 }, { "epoch": 0.02, "learning_rate": 8.960810763887752e-06, "loss": 3.3448, "step": 2506752 }, { "epoch": 0.02, "learning_rate": 8.952441195180963e-06, "loss": 3.3317, "step": 2507264 }, { "epoch": 0.02, "learning_rate": 8.944055247670443e-06, "loss": 3.3361, "step": 2507776 }, { "epoch": 0.02, "learning_rate": 8.935669300159923e-06, "loss": 3.3328, "step": 2508288 }, { "epoch": 0.02, "learning_rate": 8.927283352649403e-06, "loss": 3.3549, "step": 2508800 }, { "epoch": 0.02, "learning_rate": 8.918913783942614e-06, "loss": 3.3535, "step": 2509312 }, { "epoch": 0.02, "learning_rate": 8.910527836432095e-06, "loss": 3.3373, "step": 2509824 }, { "epoch": 0.02, "learning_rate": 8.902141888921574e-06, "loss": 3.3428, "step": 2510336 }, { "epoch": 0.02, "learning_rate": 8.893755941411054e-06, "loss": 3.3464, "step": 2510848 }, { "epoch": 0.02, "learning_rate": 8.885386372704266e-06, "loss": 3.3505, "step": 2511360 }, { "epoch": 0.02, "learning_rate": 8.877000425193744e-06, "loss": 3.3474, "step": 2511872 }, { "epoch": 0.02, "learning_rate": 8.868614477683224e-06, "loss": 3.3397, "step": 2512384 }, { "epoch": 0.02, "learning_rate": 8.860228530172706e-06, "loss": 3.3545, "step": 2512896 }, { "epoch": 0.02, "learning_rate": 8.851858961465917e-06, "loss": 3.3362, "step": 2513408 }, { "epoch": 0.02, "learning_rate": 8.843473013955395e-06, "loss": 3.3525, "step": 2513920 }, { "epoch": 0.02, "learning_rate": 8.835087066444877e-06, "loss": 3.3449, "step": 2514432 }, { "epoch": 0.02, "learning_rate": 8.826701118934357e-06, "loss": 3.345, "step": 2514944 }, { "epoch": 0.02, "learning_rate": 8.818331550227567e-06, "loss": 3.344, "step": 2515456 }, { "epoch": 0.02, "learning_rate": 8.809945602717047e-06, "loss": 3.3353, "step": 2515968 }, { "epoch": 0.02, "learning_rate": 8.801559655206527e-06, "loss": 3.3457, "step": 2516480 }, { "epoch": 0.02, "learning_rate": 8.793173707696007e-06, "loss": 3.3449, "step": 2516992 }, { "epoch": 0.02, "learning_rate": 8.784804138989218e-06, "loss": 3.3486, "step": 2517504 }, { "epoch": 0.02, "learning_rate": 8.776418191478698e-06, "loss": 3.3409, "step": 2518016 }, { "epoch": 0.02, "learning_rate": 8.768032243968178e-06, "loss": 3.3404, "step": 2518528 }, { "epoch": 0.03, "eval_loss": 3.8688809871673584, "eval_runtime": 305.4511, "eval_samples_per_second": 1249.27, "eval_steps_per_second": 39.041, "step": 2518560 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.7515580866066483e+18, "trial_name": null, "trial_params": null }