{ "best_metric": 3.8423147201538086, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/4/checkpoints/checkpoint-992160", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 1755360, "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": 10.954, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8135, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1863, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9774, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8154, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7126, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6054, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5353, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4565, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.409, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3484, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3284, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2759, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.211, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1854, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1418, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1252, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0828, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0543, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0297, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0107, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9891, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9677, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.949, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9265, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.9062, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8783, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8621, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8399, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8335, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8171, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8003, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7901, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7706, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7669, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7601, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7427, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7085, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7172, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.688, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.685, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6815, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6749, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6574, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6574, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6492, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6397, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6312, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6081, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.6041, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.608, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5928, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5781, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5659, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5701, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5539, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5696, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5412, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5465, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5399, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5155, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5244, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5112, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5019, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4974, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5142, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4917, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4813, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4674, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4671, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4847, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4823, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4561, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4724, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4656, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.453, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4386, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4445, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4329, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4273, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4281, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4223, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4262, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4228, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.4031, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4078, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4083, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3999, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3952, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.392, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.394, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3814, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3828, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3758, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3802, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3745, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3695, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3501, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3575, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3598, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916173282502262e-05, "loss": 4.3667, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.91533468775121e-05, "loss": 4.3515, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914497730880531e-05, "loss": 4.3417, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913659136129479e-05, "loss": 4.3388, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912820541378427e-05, "loss": 4.3464, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911981946627375e-05, "loss": 4.3161, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111449897566966e-05, "loss": 4.3251, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9103063950056446e-05, "loss": 4.3258, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.9094678002545926e-05, "loss": 4.3255, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086292055035406e-05, "loss": 4.3172, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.9077906107524886e-05, "loss": 4.3256, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.9069520160014366e-05, "loss": 4.3064, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061134212503846e-05, "loss": 4.3326, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052764643797055e-05, "loss": 4.3113, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.9044378696286535e-05, "loss": 4.314, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.9035992748776015e-05, "loss": 4.3181, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027606801265495e-05, "loss": 4.3266, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019237232558704e-05, "loss": 4.3048, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010851285048184e-05, "loss": 4.2975, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900246533753767e-05, "loss": 4.3044, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899407939002715e-05, "loss": 4.2907, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2989, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2939, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2848, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.89605519787888e-05, "loss": 4.3015, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.895216603127827e-05, "loss": 4.2818, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.894378008376775e-05, "loss": 4.2788, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893539413625723e-05, "loss": 4.277, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892702456755045e-05, "loss": 4.2807, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891863862003992e-05, "loss": 4.2686, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891025267252941e-05, "loss": 4.2858, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890186672501889e-05, "loss": 4.2781, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889348077750837e-05, "loss": 4.2664, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2615, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2674, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2645, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885995336627002e-05, "loss": 4.2686, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.8851583797563226e-05, "loss": 4.2635, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.8843197850052706e-05, "loss": 4.2664, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.8834811902542186e-05, "loss": 4.2612, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.8826425955031666e-05, "loss": 4.2549, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8818040007521146e-05, "loss": 4.2455, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2453, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2517, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879289854379332e-05, "loss": 4.2313, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87845125962828e-05, "loss": 4.2511, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877612664877228e-05, "loss": 4.2455, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2365, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.2396, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875098518504445e-05, "loss": 4.2392, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.199338912963867, "eval_runtime": 304.8042, "eval_samples_per_second": 1251.922, "eval_steps_per_second": 39.123, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874259923753393e-05, "loss": 4.2148, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873421329002341e-05, "loss": 4.2244, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872582734251289e-05, "loss": 4.233, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2212, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2247, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2149, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2139, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.2065, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2145, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.2032, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2226, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650386572525676e-05, "loss": 4.216, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642033382622614e-05, "loss": 4.1988, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633647435112094e-05, "loss": 4.1938, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625261487601574e-05, "loss": 4.194, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616875540091054e-05, "loss": 4.1932, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608489592580534e-05, "loss": 4.1878, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.8600103645070014e-05, "loss": 4.1909, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591717697559493e-05, "loss": 4.1864, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858333175004898e-05, "loss": 4.1976, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857494580253846e-05, "loss": 4.1913, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856657623383167e-05, "loss": 4.1919, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855819028632115e-05, "loss": 4.1874, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854980433881063e-05, "loss": 4.1962, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854141839130011e-05, "loss": 4.1712, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853303244378958e-05, "loss": 4.1753, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852464649627906e-05, "loss": 4.1711, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851627692757228e-05, "loss": 4.1703, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850789098006175e-05, "loss": 4.171, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849950503255123e-05, "loss": 4.167, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849111908504072e-05, "loss": 4.1719, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.84827331375302e-05, "loss": 4.1707, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847436356882341e-05, "loss": 4.158, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846597762131289e-05, "loss": 4.1668, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845759167380237e-05, "loss": 4.1733, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844920572629185e-05, "loss": 4.1607, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.8440836157585056e-05, "loss": 4.1455, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432450210074536e-05, "loss": 4.1562, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8424064262564016e-05, "loss": 4.1393, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415678315053496e-05, "loss": 4.1474, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.8407308746346705e-05, "loss": 4.1482, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398922798836185e-05, "loss": 4.1559, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839053685132567e-05, "loss": 4.144, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838215090381515e-05, "loss": 4.1486, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837378133510836e-05, "loss": 4.1515, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836539538759784e-05, "loss": 4.145, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835700944008732e-05, "loss": 4.1461, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.83486234925768e-05, "loss": 4.1276, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834025392387001e-05, "loss": 4.1363, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833186797635949e-05, "loss": 4.1423, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832348202884897e-05, "loss": 4.134, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831509608133845e-05, "loss": 4.1285, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830671013382793e-05, "loss": 4.1158, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1279, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1185, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281568670100105e-05, "loss": 4.1337, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273182722589585e-05, "loss": 4.1182, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264796775079065e-05, "loss": 4.1278, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256410827568545e-05, "loss": 4.1282, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248024880058025e-05, "loss": 4.1043, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239655311351234e-05, "loss": 4.1189, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231269363840714e-05, "loss": 4.1165, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222883416330194e-05, "loss": 4.1061, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214497468819674e-05, "loss": 4.1059, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820612790011288e-05, "loss": 4.1244, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819774195260236e-05, "loss": 4.1126, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818935600509184e-05, "loss": 4.1003, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818097005758132e-05, "loss": 4.092, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817260048887454e-05, "loss": 4.1007, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816421454136402e-05, "loss": 4.114, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.81558285938535e-05, "loss": 4.1189, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814744264634298e-05, "loss": 4.103, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813907307763619e-05, "loss": 4.1158, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813068713012567e-05, "loss": 4.1106, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812230118261515e-05, "loss": 4.1049, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811391523510463e-05, "loss": 4.0905, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810554566639784e-05, "loss": 4.1068, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809715971888732e-05, "loss": 4.0955, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887737713768e-05, "loss": 4.0908, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808038782386628e-05, "loss": 4.0937, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807201825515949e-05, "loss": 4.0906, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806363230764897e-05, "loss": 4.105, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805524636013845e-05, "loss": 4.0927, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804686041262793e-05, "loss": 4.0854, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803849084392114e-05, "loss": 4.0891, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803010489641062e-05, "loss": 4.0915, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.80217189489001e-05, "loss": 4.0878, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801333300138958e-05, "loss": 4.0845, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800496343268279e-05, "loss": 4.0785, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799657748517227e-05, "loss": 4.0933, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798819153766175e-05, "loss": 4.0778, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797980559015123e-05, "loss": 4.0805, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971436021444446e-05, "loss": 4.076, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963050073933926e-05, "loss": 4.0869, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954664126423406e-05, "loss": 4.0846, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946278178912886e-05, "loss": 4.078, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.7937908610206095e-05, "loss": 4.0647, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.7929522662695575e-05, "loss": 4.0748, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.7921136715185055e-05, "loss": 4.0745, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.7912750767674535e-05, "loss": 4.0843, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.7904381198967744e-05, "loss": 4.076, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895995251457224e-05, "loss": 4.0665, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887609303946704e-05, "loss": 4.0611, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879223356436184e-05, "loss": 4.0745, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708537877294e-05, "loss": 4.0447, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786248421902261e-05, "loss": 4.0592, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785409827151209e-05, "loss": 4.0615, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784571232400157e-05, "loss": 4.062, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783732637649105e-05, "loss": 4.0512, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782894042898053e-05, "loss": 4.0613, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782055448147001e-05, "loss": 4.053, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781216853395948e-05, "loss": 4.072, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780378258644896e-05, "loss": 4.0562, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779541301774218e-05, "loss": 4.056, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778702707023166e-05, "loss": 4.0712, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777864112272114e-05, "loss": 4.0746, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770271554014354e-05, "loss": 4.0547, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761885606503834e-05, "loss": 4.0493, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775349965899331e-05, "loss": 4.0607, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774511371148279e-05, "loss": 4.0479, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773672776397227e-05, "loss": 4.0509, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728341816461747e-05, "loss": 4.0573, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719955868951227e-05, "loss": 4.0446, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711569921440707e-05, "loss": 4.0632, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703200352733916e-05, "loss": 4.0448, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694814405223396e-05, "loss": 4.0475, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686428457712876e-05, "loss": 4.0411, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678042510202355e-05, "loss": 4.0481, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766967294149557e-05, "loss": 4.0409, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766128699398505e-05, "loss": 4.0551, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765290104647453e-05, "loss": 4.0514, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764451509896401e-05, "loss": 4.0428, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763614553025722e-05, "loss": 4.0263, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.76277595827467e-05, "loss": 4.0486, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761937363523618e-05, "loss": 4.0396, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761098768772566e-05, "loss": 4.0474, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760261811901887e-05, "loss": 4.0435, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759423217150835e-05, "loss": 4.0436, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758584622399783e-05, "loss": 4.0426, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757746027648731e-05, "loss": 4.0453, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569090707780525e-05, "loss": 4.0298, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560704760270005e-05, "loss": 4.0289, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552318812759485e-05, "loss": 4.0396, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543932865248965e-05, "loss": 4.023, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535563296542174e-05, "loss": 4.0376, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527177349031654e-05, "loss": 4.0427, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518791401521134e-05, "loss": 4.0292, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510405454010614e-05, "loss": 4.0295, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750203588530382e-05, "loss": 4.0323, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.029595851898193, "eval_runtime": 317.0735, "eval_samples_per_second": 1203.478, "eval_steps_per_second": 37.61, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.74936499377933e-05, "loss": 4.0124, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748526399028278e-05, "loss": 4.0207, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747687804277226e-05, "loss": 4.0311, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746849209526175e-05, "loss": 4.0236, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746010614775123e-05, "loss": 4.0286, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745172020024071e-05, "loss": 4.0122, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744333425273019e-05, "loss": 4.0243, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743494830521967e-05, "loss": 4.0076, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742656235770914e-05, "loss": 4.0196, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741817641019862e-05, "loss": 4.0156, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.74097904626881e-05, "loss": 4.0235, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740142089398132e-05, "loss": 4.0283, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7393067704078257e-05, "loss": 4.0084, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384681756567737e-05, "loss": 4.01, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376295809057216e-05, "loss": 4.0078, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73679098615467e-05, "loss": 4.0055, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735952391403618e-05, "loss": 4.003, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735113796652566e-05, "loss": 4.0063, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734275201901514e-05, "loss": 4.0026, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.7334366071504616e-05, "loss": 4.024, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325980123994096e-05, "loss": 4.0041, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317594176483576e-05, "loss": 4.0168, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309208228973056e-05, "loss": 4.0096, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300822281462536e-05, "loss": 4.0166, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292452712755745e-05, "loss": 3.9906, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7284066765245225e-05, "loss": 4.0033, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275680817734705e-05, "loss": 3.9935, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726731124902792e-05, "loss": 4.0, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.72589253015174e-05, "loss": 3.9939, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725053935400688e-05, "loss": 3.9942, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724215340649636e-05, "loss": 4.0044, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723378383778957e-05, "loss": 4.0029, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722539789027905e-05, "loss": 3.9876, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721701194276853e-05, "loss": 4.0023, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720862599525801e-05, "loss": 3.9981, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720025642655122e-05, "loss": 3.9954, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.71918704790407e-05, "loss": 3.9835, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718348453153018e-05, "loss": 3.9912, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717509858401966e-05, "loss": 3.9735, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716671263650914e-05, "loss": 3.9881, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715832668899862e-05, "loss": 3.9831, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149940741488105e-05, "loss": 3.9928, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141554793977585e-05, "loss": 3.9861, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133185225270794e-05, "loss": 3.988, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124799277760274e-05, "loss": 3.9923, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116413330249754e-05, "loss": 3.9873, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108027382739234e-05, "loss": 3.9868, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099657814032443e-05, "loss": 3.9711, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709127186652192e-05, "loss": 3.9786, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.70828859190114e-05, "loss": 3.9881, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707449997150088e-05, "loss": 3.9789, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706613040279409e-05, "loss": 3.9746, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705774445528357e-05, "loss": 3.9661, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704935850777306e-05, "loss": 3.9777, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704097256026254e-05, "loss": 3.9632, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703260299155575e-05, "loss": 3.9799, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702421704404523e-05, "loss": 3.9658, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701583109653471e-05, "loss": 3.981, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700744514902419e-05, "loss": 3.977, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990755803174e-05, "loss": 3.9592, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699068963280688e-05, "loss": 3.969, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698230368529636e-05, "loss": 3.9678, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697391773778584e-05, "loss": 3.9596, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965548169079046e-05, "loss": 3.9658, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.6957162221568526e-05, "loss": 3.9745, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694877627405801e-05, "loss": 3.9697, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694039032654749e-05, "loss": 3.9582, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.69320207578407e-05, "loss": 3.9489, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692363481033018e-05, "loss": 3.9564, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691524886281966e-05, "loss": 3.9712, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690686291530914e-05, "loss": 3.9776, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689849334660235e-05, "loss": 3.9615, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689012377789556e-05, "loss": 3.9746, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688173783038504e-05, "loss": 3.9699, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687335188287452e-05, "loss": 3.9706, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864965935364e-05, "loss": 3.9462, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685657998785348e-05, "loss": 3.9691, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848194040342966e-05, "loss": 3.9616, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839808092832446e-05, "loss": 3.9527, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831422145321926e-05, "loss": 3.9614, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6823052576615135e-05, "loss": 3.9568, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814666629104615e-05, "loss": 3.9683, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806280681594095e-05, "loss": 3.9601, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679789473408357e-05, "loss": 3.9492, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789525165376784e-05, "loss": 3.9543, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781139217866264e-05, "loss": 3.9555, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772753270355744e-05, "loss": 3.9562, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676436732284522e-05, "loss": 3.9508, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675599775413843e-05, "loss": 3.9483, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674761180662792e-05, "loss": 3.9592, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67392258591174e-05, "loss": 3.9489, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673083991160687e-05, "loss": 3.9509, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672247034290009e-05, "loss": 3.9458, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671408439538957e-05, "loss": 3.959, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670569844787904e-05, "loss": 3.9553, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669731250036852e-05, "loss": 3.9482, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668894293166174e-05, "loss": 3.9406, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668055698415122e-05, "loss": 3.9504, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667217103664069e-05, "loss": 3.9417, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666378508913017e-05, "loss": 3.9611, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665541552042339e-05, "loss": 3.9467, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6647029572912874e-05, "loss": 3.9423, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663864362540235e-05, "loss": 3.9344, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663025767789183e-05, "loss": 3.9475, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662188810918504e-05, "loss": 3.9242, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661351854047825e-05, "loss": 3.9378, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660513259296773e-05, "loss": 3.9384, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659674664545721e-05, "loss": 3.9397, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658836069794669e-05, "loss": 3.9262, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579974750436165e-05, "loss": 3.9446, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657160518172938e-05, "loss": 3.9299, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656321923421886e-05, "loss": 3.9517, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655483328670834e-05, "loss": 3.9372, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654644733919782e-05, "loss": 3.9345, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65380613916873e-05, "loss": 3.9526, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652967544417678e-05, "loss": 3.9565, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652130587546999e-05, "loss": 3.9375, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651291992795947e-05, "loss": 3.931, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650453398044895e-05, "loss": 3.9399, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649614803293843e-05, "loss": 3.9316, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648776208542791e-05, "loss": 3.9306, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647937613791739e-05, "loss": 3.9422, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647099019040687e-05, "loss": 3.9257, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646260424289635e-05, "loss": 3.9471, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645423467418956e-05, "loss": 3.9311, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445848726679045e-05, "loss": 3.9335, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437462779168525e-05, "loss": 3.9241, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429093210461734e-05, "loss": 3.9352, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420707262951214e-05, "loss": 3.9231, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412321315440694e-05, "loss": 3.9431, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403935367930174e-05, "loss": 3.9342, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639556579922338e-05, "loss": 3.9295, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638717985171286e-05, "loss": 3.9144, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637879390420234e-05, "loss": 3.9379, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637040795669182e-05, "loss": 3.9306, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636203838798503e-05, "loss": 3.9311, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635365244047451e-05, "loss": 3.9279, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345266492964e-05, "loss": 3.935, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633689692425721e-05, "loss": 3.9331, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632851097674669e-05, "loss": 3.9378, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632012502923617e-05, "loss": 3.9176, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631173908172565e-05, "loss": 3.9208, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630335313421513e-05, "loss": 3.9294, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629496718670461e-05, "loss": 3.9118, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628659761799782e-05, "loss": 3.9264, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.62782116704873e-05, "loss": 3.9362, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626982572297678e-05, "loss": 3.9223, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626143977546626e-05, "loss": 3.9183, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6253070206759466e-05, "loss": 3.9279, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9548325538635254, "eval_runtime": 312.8434, "eval_samples_per_second": 1219.751, "eval_steps_per_second": 38.118, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624468425924895e-05, "loss": 3.9142, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623629831173843e-05, "loss": 3.9136, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622791236422791e-05, "loss": 3.9247, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621952641671739e-05, "loss": 3.9143, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.62111568480106e-05, "loss": 3.9258, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620277090050008e-05, "loss": 3.9065, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619438495298956e-05, "loss": 3.9202, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618599900547904e-05, "loss": 3.9011, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617761305796852e-05, "loss": 3.9148, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6169227110458e-05, "loss": 3.9116, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616085754175121e-05, "loss": 3.9199, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615247159424069e-05, "loss": 3.9224, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144102025533906e-05, "loss": 3.9063, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135716078023386e-05, "loss": 3.909, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127330130512866e-05, "loss": 3.9059, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118944183002346e-05, "loss": 3.906, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110558235491826e-05, "loss": 3.8997, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.61021722879813e-05, "loss": 3.905, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609378634047078e-05, "loss": 3.9011, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608540039296026e-05, "loss": 3.9265, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6077030824253475e-05, "loss": 3.9045, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606864487674295e-05, "loss": 3.9103, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606025892923243e-05, "loss": 3.9148, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605187298172191e-05, "loss": 3.9165, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604348703421139e-05, "loss": 3.8936, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035101086700875e-05, "loss": 3.9046, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026715139190355e-05, "loss": 3.8963, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018345570483564e-05, "loss": 3.9027, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009959622973044e-05, "loss": 3.8954, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001573675462524e-05, "loss": 3.8953, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5993187727952004e-05, "loss": 3.9063, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.5984801780441484e-05, "loss": 3.9056, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976415832930964e-05, "loss": 3.8978, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5968029885420443e-05, "loss": 3.9033, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595966031671365e-05, "loss": 3.9029, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595129074800686e-05, "loss": 3.8987, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594290480049634e-05, "loss": 3.8876, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593451885298583e-05, "loss": 3.9004, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592613290547531e-05, "loss": 3.8761, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591776333676852e-05, "loss": 3.8944, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909377389258e-05, "loss": 3.8872, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590099144174748e-05, "loss": 3.9021, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589260549423696e-05, "loss": 3.8985, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588421954672644e-05, "loss": 3.8915, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587583359921592e-05, "loss": 3.9004, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867464030509126e-05, "loss": 3.8978, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5859078082998606e-05, "loss": 3.8936, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850692135488086e-05, "loss": 3.8806, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842306187977566e-05, "loss": 3.8836, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833920240467046e-05, "loss": 3.8988, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582555067176026e-05, "loss": 3.8838, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581716472424974e-05, "loss": 3.8806, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580877877673922e-05, "loss": 3.88, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.58003928292287e-05, "loss": 3.8888, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579200688171818e-05, "loss": 3.8737, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578362093420766e-05, "loss": 3.8882, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5775234986697135e-05, "loss": 3.8808, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576686541799035e-05, "loss": 3.8877, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575847947047983e-05, "loss": 3.8876, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575009352296931e-05, "loss": 3.8744, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741707575458784e-05, "loss": 3.8757, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733321627948264e-05, "loss": 3.886, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724935680437744e-05, "loss": 3.8698, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571656611173096e-05, "loss": 3.8765, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570818016422044e-05, "loss": 3.8868, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569979421670992e-05, "loss": 3.8867, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.56914082691994e-05, "loss": 3.8699, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568302232168888e-05, "loss": 3.8633, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567463637417836e-05, "loss": 3.8683, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566625042666784e-05, "loss": 3.8813, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565786447915732e-05, "loss": 3.8892, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564949491045053e-05, "loss": 3.8774, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564110896294001e-05, "loss": 3.8878, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563272301542949e-05, "loss": 3.8861, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562433706791897e-05, "loss": 3.8838, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.5615967499212184e-05, "loss": 3.8655, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.5607581551701664e-05, "loss": 3.8829, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599195604191144e-05, "loss": 3.877, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590809656680624e-05, "loss": 3.8696, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582423709170104e-05, "loss": 3.8758, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.5574037761659584e-05, "loss": 3.8758, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.5565651814149064e-05, "loss": 3.8795, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555728224544227e-05, "loss": 3.8777, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554889629793175e-05, "loss": 3.8677, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554051035042123e-05, "loss": 3.8734, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553212440291071e-05, "loss": 3.8709, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552373845540019e-05, "loss": 3.8736, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515352507889666e-05, "loss": 3.8698, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550696656037915e-05, "loss": 3.8643, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549859699167237e-05, "loss": 3.8802, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549021104416185e-05, "loss": 3.8701, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548184147545506e-05, "loss": 3.8644, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547345552794454e-05, "loss": 3.8652, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546506958043402e-05, "loss": 3.8813, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.54566836329235e-05, "loss": 3.8758, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544831406421671e-05, "loss": 3.8666, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543992811670619e-05, "loss": 3.8583, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431542169195667e-05, "loss": 3.8677, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542315622168514e-05, "loss": 3.8605, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414786652978356e-05, "loss": 3.8823, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406400705467836e-05, "loss": 3.8674, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539801475795732e-05, "loss": 3.8633, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389628810446796e-05, "loss": 3.8573, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538125924174001e-05, "loss": 3.8697, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537287329422949e-05, "loss": 3.8424, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536448734671897e-05, "loss": 3.8587, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5356101399208444e-05, "loss": 3.8598, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347715451697924e-05, "loss": 3.8628, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533934588299114e-05, "loss": 3.8478, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330959935480613e-05, "loss": 3.8668, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322573987970093e-05, "loss": 3.8528, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314188040459573e-05, "loss": 3.8711, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530581847175279e-05, "loss": 3.8622, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529743252424227e-05, "loss": 3.8557, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528904657673175e-05, "loss": 3.8738, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528066062922123e-05, "loss": 3.8785, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272291060514445e-05, "loss": 3.8629, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526390511300392e-05, "loss": 3.856, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.52555191654934e-05, "loss": 3.8622, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524713321798288e-05, "loss": 3.852, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523874727047236e-05, "loss": 3.8533, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523036132296184e-05, "loss": 3.8686, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522197537545132e-05, "loss": 3.8523, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.52135894279408e-05, "loss": 3.8703, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520523623803774e-05, "loss": 3.8577, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519685029052722e-05, "loss": 3.8612, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.51884643430167e-05, "loss": 3.8448, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518007839550618e-05, "loss": 3.8628, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517170882679939e-05, "loss": 3.8478, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516332287928887e-05, "loss": 3.8667, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515493693177835e-05, "loss": 3.8581, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514655098426783e-05, "loss": 3.8602, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513816503675731e-05, "loss": 3.8396, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512979546805052e-05, "loss": 3.8663, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512140952054e-05, "loss": 3.8533, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511302357302948e-05, "loss": 3.8564, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510463762551896e-05, "loss": 3.8536, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096268056812177e-05, "loss": 3.8628, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087882109301657e-05, "loss": 3.8598, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079496161791136e-05, "loss": 3.8622, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5071110214280616e-05, "loss": 3.8452, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062740645573826e-05, "loss": 3.8499, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054354698063305e-05, "loss": 3.852, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045968750552785e-05, "loss": 3.8432, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037582803042265e-05, "loss": 3.8541, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5029196855531745e-05, "loss": 3.8623, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020827286824954e-05, "loss": 3.8516, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012441339314434e-05, "loss": 3.8444, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5004055391803914e-05, "loss": 3.8561, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.913831949234009, "eval_runtime": 307.2402, "eval_samples_per_second": 1241.996, "eval_steps_per_second": 38.813, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.49956694442934e-05, "loss": 3.8348, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498728349678288e-05, "loss": 3.8415, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497889754927236e-05, "loss": 3.8513, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497051160176184e-05, "loss": 3.8474, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496212565425132e-05, "loss": 3.8564, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.49537397067408e-05, "loss": 3.8368, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945353759230274e-05, "loss": 3.8473, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.4936967811719754e-05, "loss": 3.8311, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492859824301297e-05, "loss": 3.8487, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492021229550245e-05, "loss": 3.8431, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491182634799192e-05, "loss": 3.8461, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.49034404004814e-05, "loss": 3.8536, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4895087210578355e-05, "loss": 3.8333, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886701263067835e-05, "loss": 3.8445, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878315315557315e-05, "loss": 3.8355, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869929368046795e-05, "loss": 3.8369, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861543420536275e-05, "loss": 3.8294, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485315747302575e-05, "loss": 3.8384, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484477152551523e-05, "loss": 3.8349, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483638557800471e-05, "loss": 3.856, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4828016009297924e-05, "loss": 3.836, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.48196300617874e-05, "loss": 3.8417, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481124411427688e-05, "loss": 3.8478, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480285816676636e-05, "loss": 3.8506, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.4794472219255837e-05, "loss": 3.8259, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478610265054905e-05, "loss": 3.8405, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477771670303853e-05, "loss": 3.8286, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476933075552801e-05, "loss": 3.8362, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476094480801749e-05, "loss": 3.8239, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.47525752393107e-05, "loss": 3.8308, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474418929180018e-05, "loss": 3.8384, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473580334428966e-05, "loss": 3.8389, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472741739677914e-05, "loss": 3.8291, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471903144926862e-05, "loss": 3.8417, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471066188056183e-05, "loss": 3.8309, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470227593305131e-05, "loss": 3.8391, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469388998554079e-05, "loss": 3.821, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468550403803028e-05, "loss": 3.8332, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4677134469323486e-05, "loss": 3.8159, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668748521812966e-05, "loss": 3.8262, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.4660362574302446e-05, "loss": 3.8216, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4651976626791926e-05, "loss": 3.8371, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.4643590679281406e-05, "loss": 3.8311, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4635221110574615e-05, "loss": 3.8305, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.4626835163064095e-05, "loss": 3.8337, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.4618449215553575e-05, "loss": 3.833, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.4610063268043055e-05, "loss": 3.8274, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.4601693699336264e-05, "loss": 3.8212, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4593307751825744e-05, "loss": 3.8109, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584921804315224e-05, "loss": 3.8353, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457653585680471e-05, "loss": 3.8232, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456816628809792e-05, "loss": 3.8155, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.45597803405874e-05, "loss": 3.8191, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455139439307688e-05, "loss": 3.8246, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.454300844556636e-05, "loss": 3.812, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453463887685957e-05, "loss": 3.8195, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452625292934905e-05, "loss": 3.8185, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451786698183853e-05, "loss": 3.8204, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450948103432801e-05, "loss": 3.8298, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450109508681749e-05, "loss": 3.8118, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.44927255181107e-05, "loss": 3.8126, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448433957060018e-05, "loss": 3.823, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475953623089664e-05, "loss": 3.8107, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.4467567675579144e-05, "loss": 3.8142, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445919810687235e-05, "loss": 3.8243, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445081215936183e-05, "loss": 3.8219, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444242621185131e-05, "loss": 3.8085, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443404026434079e-05, "loss": 3.8023, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442565431683027e-05, "loss": 3.8035, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441728474812348e-05, "loss": 3.817, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440889880061296e-05, "loss": 3.8305, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440051285310244e-05, "loss": 3.8135, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439212690559192e-05, "loss": 3.8277, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438375733688513e-05, "loss": 3.8236, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437537138937462e-05, "loss": 3.8283, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.43669854418641e-05, "loss": 3.8046, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435859949435358e-05, "loss": 3.8202, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435022992564679e-05, "loss": 3.8148, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434184397813627e-05, "loss": 3.8063, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433345803062575e-05, "loss": 3.8205, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432507208311523e-05, "loss": 3.8148, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431668613560471e-05, "loss": 3.8153, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4308316566897916e-05, "loss": 3.8171, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4299930619387396e-05, "loss": 3.8113, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291544671876876e-05, "loss": 3.8145, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283158724366356e-05, "loss": 3.8095, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274772776855836e-05, "loss": 3.8151, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426640320814905e-05, "loss": 3.807, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425801726063853e-05, "loss": 3.8079, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249631313128005e-05, "loss": 3.8161, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.4241245365617485e-05, "loss": 3.8144, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.42328757969107e-05, "loss": 3.8033, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422448984940018e-05, "loss": 3.8068, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.4216103901889654e-05, "loss": 3.8221, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.4207717954379134e-05, "loss": 3.8174, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419934838567235e-05, "loss": 3.81, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419096243816182e-05, "loss": 3.8002, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418257649065131e-05, "loss": 3.8084, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417419054314079e-05, "loss": 3.8023, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165820974434005e-05, "loss": 3.8181, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415743502692348e-05, "loss": 3.8162, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414904907941296e-05, "loss": 3.8052, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414066313190244e-05, "loss": 3.7985, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132293563195654e-05, "loss": 3.8131, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.412390761568513e-05, "loss": 3.7842, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411552166817461e-05, "loss": 3.8062, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410713572066409e-05, "loss": 3.7978, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098766151957296e-05, "loss": 3.8057, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090380204446776e-05, "loss": 3.7919, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408199425693626e-05, "loss": 3.8079, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407360830942574e-05, "loss": 3.8006, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406522236191522e-05, "loss": 3.806, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405685279320843e-05, "loss": 3.8102, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404846684569791e-05, "loss": 3.7977, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.404008089818739e-05, "loss": 3.8167, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403169495067687e-05, "loss": 3.8244, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402332538197008e-05, "loss": 3.8063, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401493943445956e-05, "loss": 3.7964, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400655348694904e-05, "loss": 3.8071, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399816753943852e-05, "loss": 3.7996, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398979797073173e-05, "loss": 3.7926, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398141202322122e-05, "loss": 3.8136, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.39730260757107e-05, "loss": 3.7938, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396464012820018e-05, "loss": 3.8113, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956270559493386e-05, "loss": 3.8033, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.3947884611982866e-05, "loss": 3.8048, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.3939498664472346e-05, "loss": 3.7962, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.3931112716961826e-05, "loss": 3.801, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.3922743148255035e-05, "loss": 3.7982, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3914357200744515e-05, "loss": 3.8108, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905971253233995e-05, "loss": 3.8005, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897585305723475e-05, "loss": 3.8041, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3889215737016684e-05, "loss": 3.787, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388082978950617e-05, "loss": 3.8101, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387244384199565e-05, "loss": 3.7981, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386405789448513e-05, "loss": 3.8049, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385568832577834e-05, "loss": 3.7962, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384730237826782e-05, "loss": 3.8079, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.38389164307573e-05, "loss": 3.8032, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383053048324678e-05, "loss": 3.8122, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382216091453999e-05, "loss": 3.787, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381377496702947e-05, "loss": 3.7984, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380538901951895e-05, "loss": 3.7955, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379700307200843e-05, "loss": 3.7905, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378863350330164e-05, "loss": 3.8037, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3780247555791124e-05, "loss": 3.8034, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771861608280604e-05, "loss": 3.8033, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763475660770084e-05, "loss": 3.7836, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.3755089713259564e-05, "loss": 3.8036, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.888087749481201, "eval_runtime": 307.4628, "eval_samples_per_second": 1241.096, "eval_steps_per_second": 38.785, "step": 381600 }, { "epoch": 0.0, "learning_rate": 4.374672014455277e-05, "loss": 3.7839, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.373833419704225e-05, "loss": 3.7855, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.372994824953173e-05, "loss": 3.8009, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.372156230202121e-05, "loss": 3.7964, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.371317635451069e-05, "loss": 3.797, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.370479040700017e-05, "loss": 3.7881, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.369640445948965e-05, "loss": 3.7915, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.368801851197913e-05, "loss": 3.7791, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.367964894327234e-05, "loss": 3.7934, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367126299576182e-05, "loss": 3.7912, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.36628770482513e-05, "loss": 3.7918, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365449110074079e-05, "loss": 3.7999, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.364613791083773e-05, "loss": 3.7845, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.363775196332721e-05, "loss": 3.7936, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.3629366015816687e-05, "loss": 3.7856, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.3620980068306167e-05, "loss": 3.7838, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.3612594120795647e-05, "loss": 3.7779, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.3604208173285126e-05, "loss": 3.787, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.3595822225774606e-05, "loss": 3.7811, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.358743627826408e-05, "loss": 3.8012, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.3579066709557295e-05, "loss": 3.7891, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.3570680762046775e-05, "loss": 3.79, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.3562294814536255e-05, "loss": 3.7967, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.3553908867025735e-05, "loss": 3.7972, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.3545522919515215e-05, "loss": 3.7735, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.353715335080843e-05, "loss": 3.7872, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.3528767403297904e-05, "loss": 3.7811, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.3520381455787384e-05, "loss": 3.7832, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.3511995508276864e-05, "loss": 3.7747, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.350362593957008e-05, "loss": 3.7784, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.349523999205955e-05, "loss": 3.7911, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.348685404454903e-05, "loss": 3.7857, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.347846809703851e-05, "loss": 3.7826, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.347008214952799e-05, "loss": 3.7882, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.346171258082121e-05, "loss": 3.7838, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.345332663331069e-05, "loss": 3.7875, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.344494068580017e-05, "loss": 3.7746, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.343655473828965e-05, "loss": 3.7745, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.342818516958286e-05, "loss": 3.7713, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.341979922207234e-05, "loss": 3.7731, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.341141327456182e-05, "loss": 3.7726, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.34030273270513e-05, "loss": 3.7864, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.339465775834451e-05, "loss": 3.7833, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.338627181083399e-05, "loss": 3.7818, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.337788586332347e-05, "loss": 3.7898, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.336949991581295e-05, "loss": 3.7792, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.336113034710616e-05, "loss": 3.7803, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.335274439959564e-05, "loss": 3.7698, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.334435845208512e-05, "loss": 3.7587, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.33359725045746e-05, "loss": 3.787, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332760293586781e-05, "loss": 3.7741, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.331921698835729e-05, "loss": 3.7707, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331083104084677e-05, "loss": 3.7706, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.330244509333625e-05, "loss": 3.7731, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329407552462946e-05, "loss": 3.762, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328568957711894e-05, "loss": 3.7704, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327730362960842e-05, "loss": 3.7717, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.32689176820979e-05, "loss": 3.7708, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.3260548113391116e-05, "loss": 3.7805, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.3252162165880596e-05, "loss": 3.7628, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.3243776218370076e-05, "loss": 3.7651, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.3235390270859556e-05, "loss": 3.7785, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.3227020702152765e-05, "loss": 3.7616, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.3218634754642245e-05, "loss": 3.7627, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.3210248807131725e-05, "loss": 3.7725, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.3201862859621205e-05, "loss": 3.7764, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.3193493290914414e-05, "loss": 3.76, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.3185107343403894e-05, "loss": 3.7594, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.3176721395893374e-05, "loss": 3.7503, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.3168335448382854e-05, "loss": 3.7713, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315994950087234e-05, "loss": 3.7822, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.315157993216555e-05, "loss": 3.7678, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.314319398465503e-05, "loss": 3.7751, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313480803714451e-05, "loss": 3.7741, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.312643846843772e-05, "loss": 3.7838, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.31180525209272e-05, "loss": 3.7588, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.310966657341668e-05, "loss": 3.7717, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.310128062590616e-05, "loss": 3.768, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309291105719937e-05, "loss": 3.7577, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.308452510968885e-05, "loss": 3.7728, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.307613916217833e-05, "loss": 3.7725, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.306775321466781e-05, "loss": 3.7687, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.3059383645961024e-05, "loss": 3.7729, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.3050997698450504e-05, "loss": 3.7653, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042611750939984e-05, "loss": 3.761, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3034225803429464e-05, "loss": 3.7643, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025839855918944e-05, "loss": 3.77, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.301747028721215e-05, "loss": 3.7576, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.300908433970163e-05, "loss": 3.7628, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.300069839219111e-05, "loss": 3.7713, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.299231244468059e-05, "loss": 3.768, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.29839428759738e-05, "loss": 3.7567, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297555692846328e-05, "loss": 3.7605, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.296717098095276e-05, "loss": 3.778, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295878503344224e-05, "loss": 3.7708, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.295041546473546e-05, "loss": 3.7683, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294202951722494e-05, "loss": 3.7514, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293364356971442e-05, "loss": 3.7635, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.29252576222039e-05, "loss": 3.7602, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.2916888053497106e-05, "loss": 3.7692, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.2908502105986586e-05, "loss": 3.7722, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.2900116158476066e-05, "loss": 3.7607, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.2891730210965546e-05, "loss": 3.7535, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.2883360642258755e-05, "loss": 3.7682, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.2874974694748235e-05, "loss": 3.7412, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.2866588747237715e-05, "loss": 3.7581, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.2858202799727195e-05, "loss": 3.7496, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.284983323102041e-05, "loss": 3.7646, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.284144728350989e-05, "loss": 3.7463, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.283306133599937e-05, "loss": 3.7627, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.282467538848885e-05, "loss": 3.7538, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.281630581978206e-05, "loss": 3.7628, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.280791987227154e-05, "loss": 3.7648, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.279953392476102e-05, "loss": 3.7578, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.27911479772505e-05, "loss": 3.7701, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.278277840854371e-05, "loss": 3.7773, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.277439246103319e-05, "loss": 3.7625, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.276600651352267e-05, "loss": 3.7548, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.275762056601215e-05, "loss": 3.7597, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.2749250997305365e-05, "loss": 3.7587, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.2740865049794845e-05, "loss": 3.7452, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.2732479102284325e-05, "loss": 3.7744, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.2724093154773805e-05, "loss": 3.746, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.2715723586067014e-05, "loss": 3.7691, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.2707337638556494e-05, "loss": 3.758, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.2698951691045974e-05, "loss": 3.7594, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.2690565743535454e-05, "loss": 3.7528, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.268219617482866e-05, "loss": 3.7587, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.267381022731814e-05, "loss": 3.7537, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.266542427980762e-05, "loss": 3.7668, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.26570383322971e-05, "loss": 3.7574, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.264865238478658e-05, "loss": 3.7624, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.26402828160798e-05, "loss": 3.7426, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.263189686856928e-05, "loss": 3.7668, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.262351092105876e-05, "loss": 3.7534, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.261512497354823e-05, "loss": 3.7597, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.260675540484145e-05, "loss": 3.7566, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.259836945733093e-05, "loss": 3.7627, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.25899835098204e-05, "loss": 3.7575, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.258159756230988e-05, "loss": 3.7732, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.2573227993603096e-05, "loss": 3.7412, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.2564842046092576e-05, "loss": 3.7549, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.2556456098582056e-05, "loss": 3.7522, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.2548070151071536e-05, "loss": 3.7509, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.253970058236475e-05, "loss": 3.7521, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.253131463485423e-05, "loss": 3.761, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.2522928687343705e-05, "loss": 3.7612, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.2514542739833185e-05, "loss": 3.7438, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.25061731711264e-05, "loss": 3.7625, "step": 457728 }, { "epoch": 0.03, "eval_loss": 3.8709728717803955, "eval_runtime": 305.1574, "eval_samples_per_second": 1250.473, "eval_steps_per_second": 39.078, "step": 457920 }, { "epoch": 1.0, "learning_rate": 4.2497787223615874e-05, "loss": 3.75, "step": 458240 }, { "epoch": 1.0, "learning_rate": 4.2489401276105354e-05, "loss": 3.7395, "step": 458752 }, { "epoch": 1.0, "learning_rate": 4.2481015328594834e-05, "loss": 3.7605, "step": 459264 }, { "epoch": 1.0, "learning_rate": 4.247264575988805e-05, "loss": 3.7528, "step": 459776 }, { "epoch": 1.0, "learning_rate": 4.246425981237753e-05, "loss": 3.7563, "step": 460288 }, { "epoch": 1.0, "learning_rate": 4.245587386486701e-05, "loss": 3.7455, "step": 460800 }, { "epoch": 1.0, "learning_rate": 4.244748791735649e-05, "loss": 3.7443, "step": 461312 }, { "epoch": 1.0, "learning_rate": 4.24391183486497e-05, "loss": 3.7421, "step": 461824 }, { "epoch": 1.0, "learning_rate": 4.243073240113918e-05, "loss": 3.752, "step": 462336 }, { "epoch": 1.0, "learning_rate": 4.242234645362866e-05, "loss": 3.7464, "step": 462848 }, { "epoch": 1.0, "learning_rate": 4.241396050611814e-05, "loss": 3.7527, "step": 463360 }, { "epoch": 1.0, "learning_rate": 4.240559093741135e-05, "loss": 3.756, "step": 463872 }, { "epoch": 1.0, "learning_rate": 4.2397221368704564e-05, "loss": 3.7444, "step": 464384 }, { "epoch": 1.0, "learning_rate": 4.2388835421194044e-05, "loss": 3.7463, "step": 464896 }, { "epoch": 1.0, "learning_rate": 4.2380449473683524e-05, "loss": 3.747, "step": 465408 }, { "epoch": 1.0, "learning_rate": 4.2372063526173004e-05, "loss": 3.7391, "step": 465920 }, { "epoch": 1.0, "learning_rate": 4.2363677578662484e-05, "loss": 3.7352, "step": 466432 }, { "epoch": 1.0, "learning_rate": 4.2355291631151963e-05, "loss": 3.7437, "step": 466944 }, { "epoch": 1.0, "learning_rate": 4.2346905683641443e-05, "loss": 3.7414, "step": 467456 }, { "epoch": 1.0, "learning_rate": 4.233851973613092e-05, "loss": 3.7569, "step": 467968 }, { "epoch": 1.0, "learning_rate": 4.233015016742413e-05, "loss": 3.748, "step": 468480 }, { "epoch": 1.0, "learning_rate": 4.232176421991361e-05, "loss": 3.7504, "step": 468992 }, { "epoch": 1.0, "learning_rate": 4.231337827240309e-05, "loss": 3.7542, "step": 469504 }, { "epoch": 1.0, "learning_rate": 4.230499232489257e-05, "loss": 3.7545, "step": 470016 }, { "epoch": 1.0, "learning_rate": 4.229662275618578e-05, "loss": 3.7345, "step": 470528 }, { "epoch": 1.0, "learning_rate": 4.228823680867526e-05, "loss": 3.7491, "step": 471040 }, { "epoch": 1.0, "learning_rate": 4.227985086116474e-05, "loss": 3.7348, "step": 471552 }, { "epoch": 1.0, "learning_rate": 4.227146491365422e-05, "loss": 3.7416, "step": 472064 }, { "epoch": 1.0, "learning_rate": 4.226309534494744e-05, "loss": 3.7395, "step": 472576 }, { "epoch": 1.0, "learning_rate": 4.225470939743692e-05, "loss": 3.7366, "step": 473088 }, { "epoch": 1.01, "learning_rate": 4.22463234499264e-05, "loss": 3.7494, "step": 473600 }, { "epoch": 1.01, "learning_rate": 4.223793750241588e-05, "loss": 3.7453, "step": 474112 }, { "epoch": 1.01, "learning_rate": 4.2229567933709086e-05, "loss": 3.7418, "step": 474624 }, { "epoch": 1.01, "learning_rate": 4.2221181986198566e-05, "loss": 3.7451, "step": 475136 }, { "epoch": 1.01, "learning_rate": 4.2212796038688046e-05, "loss": 3.7409, "step": 475648 }, { "epoch": 1.01, "learning_rate": 4.2204410091177526e-05, "loss": 3.749, "step": 476160 }, { "epoch": 1.01, "learning_rate": 4.2196040522470735e-05, "loss": 3.7368, "step": 476672 }, { "epoch": 1.01, "learning_rate": 4.2187654574960215e-05, "loss": 3.7351, "step": 477184 }, { "epoch": 1.01, "learning_rate": 4.2179268627449695e-05, "loss": 3.7282, "step": 477696 }, { "epoch": 1.01, "learning_rate": 4.2170882679939175e-05, "loss": 3.7331, "step": 478208 }, { "epoch": 1.01, "learning_rate": 4.216251311123239e-05, "loss": 3.7346, "step": 478720 }, { "epoch": 1.01, "learning_rate": 4.215412716372187e-05, "loss": 3.7463, "step": 479232 }, { "epoch": 1.01, "learning_rate": 4.214574121621135e-05, "loss": 3.7418, "step": 479744 }, { "epoch": 1.01, "learning_rate": 4.213735526870083e-05, "loss": 3.7419, "step": 480256 }, { "epoch": 1.01, "learning_rate": 4.212898569999404e-05, "loss": 3.7481, "step": 480768 }, { "epoch": 1.01, "learning_rate": 4.212059975248352e-05, "loss": 3.7412, "step": 481280 }, { "epoch": 1.01, "learning_rate": 4.2112213804973e-05, "loss": 3.7422, "step": 481792 }, { "epoch": 1.01, "learning_rate": 4.210382785746248e-05, "loss": 3.7283, "step": 482304 }, { "epoch": 1.01, "learning_rate": 4.209545828875569e-05, "loss": 3.7181, "step": 482816 }, { "epoch": 1.01, "learning_rate": 4.208707234124517e-05, "loss": 3.749, "step": 483328 }, { "epoch": 1.01, "learning_rate": 4.207868639373465e-05, "loss": 3.7361, "step": 483840 }, { "epoch": 1.01, "learning_rate": 4.207030044622413e-05, "loss": 3.7269, "step": 484352 }, { "epoch": 1.01, "learning_rate": 4.2061930877517345e-05, "loss": 3.736, "step": 484864 }, { "epoch": 1.01, "learning_rate": 4.2053544930006824e-05, "loss": 3.7299, "step": 485376 }, { "epoch": 1.01, "learning_rate": 4.2045158982496304e-05, "loss": 3.7267, "step": 485888 }, { "epoch": 1.01, "learning_rate": 4.2036773034985784e-05, "loss": 3.7273, "step": 486400 }, { "epoch": 1.01, "learning_rate": 4.2028403466278993e-05, "loss": 3.7323, "step": 486912 }, { "epoch": 1.01, "learning_rate": 4.2020017518768473e-05, "loss": 3.7312, "step": 487424 }, { "epoch": 1.01, "learning_rate": 4.2011631571257953e-05, "loss": 3.7447, "step": 487936 }, { "epoch": 1.01, "learning_rate": 4.200324562374743e-05, "loss": 3.7243, "step": 488448 }, { "epoch": 1.01, "learning_rate": 4.199487605504064e-05, "loss": 3.7223, "step": 488960 }, { "epoch": 1.01, "learning_rate": 4.198649010753012e-05, "loss": 3.7448, "step": 489472 }, { "epoch": 1.01, "learning_rate": 4.19781041600196e-05, "loss": 3.7171, "step": 489984 }, { "epoch": 1.01, "learning_rate": 4.196971821250908e-05, "loss": 3.7257, "step": 490496 }, { "epoch": 1.01, "learning_rate": 4.19613486438023e-05, "loss": 3.7367, "step": 491008 }, { "epoch": 1.01, "learning_rate": 4.195296269629178e-05, "loss": 3.7406, "step": 491520 }, { "epoch": 1.01, "learning_rate": 4.194457674878126e-05, "loss": 3.7206, "step": 492032 }, { "epoch": 1.01, "learning_rate": 4.193619080127074e-05, "loss": 3.7209, "step": 492544 }, { "epoch": 1.01, "learning_rate": 4.192782123256395e-05, "loss": 3.7127, "step": 493056 }, { "epoch": 1.01, "learning_rate": 4.191943528505343e-05, "loss": 3.73, "step": 493568 }, { "epoch": 1.01, "learning_rate": 4.191104933754291e-05, "loss": 3.7439, "step": 494080 }, { "epoch": 1.01, "learning_rate": 4.190266339003239e-05, "loss": 3.7293, "step": 494592 }, { "epoch": 1.01, "learning_rate": 4.1894293821325596e-05, "loss": 3.7332, "step": 495104 }, { "epoch": 1.01, "learning_rate": 4.1885907873815076e-05, "loss": 3.7378, "step": 495616 }, { "epoch": 1.01, "learning_rate": 4.1877521926304556e-05, "loss": 3.7433, "step": 496128 }, { "epoch": 1.01, "learning_rate": 4.1869135978794036e-05, "loss": 3.7225, "step": 496640 }, { "epoch": 1.01, "learning_rate": 4.186076641008725e-05, "loss": 3.7352, "step": 497152 }, { "epoch": 1.01, "learning_rate": 4.185238046257673e-05, "loss": 3.7283, "step": 497664 }, { "epoch": 1.01, "learning_rate": 4.184399451506621e-05, "loss": 3.7188, "step": 498176 }, { "epoch": 1.01, "learning_rate": 4.183560856755569e-05, "loss": 3.7342, "step": 498688 }, { "epoch": 1.01, "learning_rate": 4.18272389988489e-05, "loss": 3.7336, "step": 499200 }, { "epoch": 1.01, "learning_rate": 4.181885305133838e-05, "loss": 3.7326, "step": 499712 }, { "epoch": 1.01, "learning_rate": 4.181046710382786e-05, "loss": 3.731, "step": 500224 }, { "epoch": 1.01, "learning_rate": 4.180208115631734e-05, "loss": 3.7305, "step": 500736 }, { "epoch": 1.01, "learning_rate": 4.179371158761055e-05, "loss": 3.7202, "step": 501248 }, { "epoch": 1.01, "learning_rate": 4.178532564010003e-05, "loss": 3.7295, "step": 501760 }, { "epoch": 1.01, "learning_rate": 4.177693969258951e-05, "loss": 3.7294, "step": 502272 }, { "epoch": 1.01, "learning_rate": 4.176855374507899e-05, "loss": 3.7213, "step": 502784 }, { "epoch": 1.01, "learning_rate": 4.1760184176372206e-05, "loss": 3.7248, "step": 503296 }, { "epoch": 1.02, "learning_rate": 4.1751798228861685e-05, "loss": 3.7274, "step": 503808 }, { "epoch": 1.02, "learning_rate": 4.1743412281351165e-05, "loss": 3.7344, "step": 504320 }, { "epoch": 1.02, "learning_rate": 4.1735026333840645e-05, "loss": 3.7219, "step": 504832 }, { "epoch": 1.02, "learning_rate": 4.1726656765133854e-05, "loss": 3.7205, "step": 505344 }, { "epoch": 1.02, "learning_rate": 4.1718270817623334e-05, "loss": 3.7404, "step": 505856 }, { "epoch": 1.02, "learning_rate": 4.1709884870112814e-05, "loss": 3.7316, "step": 506368 }, { "epoch": 1.02, "learning_rate": 4.1701498922602294e-05, "loss": 3.7315, "step": 506880 }, { "epoch": 1.02, "learning_rate": 4.1693129353895503e-05, "loss": 3.7141, "step": 507392 }, { "epoch": 1.02, "learning_rate": 4.1684743406384983e-05, "loss": 3.73, "step": 507904 }, { "epoch": 1.02, "learning_rate": 4.167635745887446e-05, "loss": 3.721, "step": 508416 }, { "epoch": 1.02, "learning_rate": 4.166797151136394e-05, "loss": 3.7298, "step": 508928 }, { "epoch": 1.02, "learning_rate": 4.165960194265716e-05, "loss": 3.7377, "step": 509440 }, { "epoch": 1.02, "learning_rate": 4.165121599514664e-05, "loss": 3.7205, "step": 509952 }, { "epoch": 1.02, "learning_rate": 4.164283004763612e-05, "loss": 3.7189, "step": 510464 }, { "epoch": 1.02, "learning_rate": 4.16344441001256e-05, "loss": 3.7281, "step": 510976 }, { "epoch": 1.02, "learning_rate": 4.162607453141881e-05, "loss": 3.7039, "step": 511488 }, { "epoch": 1.02, "learning_rate": 4.161768858390829e-05, "loss": 3.7262, "step": 512000 }, { "epoch": 1.02, "learning_rate": 4.160930263639777e-05, "loss": 3.7079, "step": 512512 }, { "epoch": 1.02, "learning_rate": 4.160091668888725e-05, "loss": 3.7271, "step": 513024 }, { "epoch": 1.02, "learning_rate": 4.159254712018046e-05, "loss": 3.7117, "step": 513536 }, { "epoch": 1.02, "learning_rate": 4.158416117266994e-05, "loss": 3.7255, "step": 514048 }, { "epoch": 1.02, "learning_rate": 4.157577522515942e-05, "loss": 3.7189, "step": 514560 }, { "epoch": 1.02, "learning_rate": 4.15673892776489e-05, "loss": 3.7224, "step": 515072 }, { "epoch": 1.02, "learning_rate": 4.155901970894211e-05, "loss": 3.7338, "step": 515584 }, { "epoch": 1.02, "learning_rate": 4.155063376143159e-05, "loss": 3.7186, "step": 516096 }, { "epoch": 1.02, "learning_rate": 4.154224781392107e-05, "loss": 3.7335, "step": 516608 }, { "epoch": 1.02, "learning_rate": 4.153386186641055e-05, "loss": 3.7386, "step": 517120 }, { "epoch": 1.02, "learning_rate": 4.152549229770376e-05, "loss": 3.7245, "step": 517632 }, { "epoch": 1.02, "learning_rate": 4.151710635019324e-05, "loss": 3.724, "step": 518144 }, { "epoch": 1.02, "learning_rate": 4.150872040268272e-05, "loss": 3.7185, "step": 518656 }, { "epoch": 1.02, "learning_rate": 4.1500334455172195e-05, "loss": 3.723, "step": 519168 }, { "epoch": 1.02, "learning_rate": 4.149196488646541e-05, "loss": 3.7151, "step": 519680 }, { "epoch": 1.02, "learning_rate": 4.148357893895489e-05, "loss": 3.733, "step": 520192 }, { "epoch": 1.02, "learning_rate": 4.147519299144437e-05, "loss": 3.7057, "step": 520704 }, { "epoch": 1.02, "learning_rate": 4.146680704393385e-05, "loss": 3.731, "step": 521216 }, { "epoch": 1.02, "learning_rate": 4.1458437475227067e-05, "loss": 3.7255, "step": 521728 }, { "epoch": 1.02, "learning_rate": 4.1450051527716546e-05, "loss": 3.723, "step": 522240 }, { "epoch": 1.02, "learning_rate": 4.1441665580206026e-05, "loss": 3.7149, "step": 522752 }, { "epoch": 1.02, "learning_rate": 4.14332796326955e-05, "loss": 3.7255, "step": 523264 }, { "epoch": 1.02, "learning_rate": 4.1424910063988715e-05, "loss": 3.7126, "step": 523776 }, { "epoch": 1.02, "learning_rate": 4.1416524116478195e-05, "loss": 3.7342, "step": 524288 }, { "epoch": 1.02, "learning_rate": 4.140813816896767e-05, "loss": 3.7171, "step": 524800 }, { "epoch": 1.02, "learning_rate": 4.139975222145715e-05, "loss": 3.7289, "step": 525312 }, { "epoch": 1.02, "learning_rate": 4.1391382652750364e-05, "loss": 3.7054, "step": 525824 }, { "epoch": 1.02, "learning_rate": 4.1382996705239844e-05, "loss": 3.7335, "step": 526336 }, { "epoch": 1.02, "learning_rate": 4.137461075772932e-05, "loss": 3.72, "step": 526848 }, { "epoch": 1.02, "learning_rate": 4.1366241189022533e-05, "loss": 3.7237, "step": 527360 }, { "epoch": 1.02, "learning_rate": 4.135785524151202e-05, "loss": 3.7205, "step": 527872 }, { "epoch": 1.02, "learning_rate": 4.13494692940015e-05, "loss": 3.7198, "step": 528384 }, { "epoch": 1.02, "learning_rate": 4.134108334649097e-05, "loss": 3.7269, "step": 528896 }, { "epoch": 1.02, "learning_rate": 4.133271377778419e-05, "loss": 3.7398, "step": 529408 }, { "epoch": 1.02, "learning_rate": 4.132432783027367e-05, "loss": 3.7061, "step": 529920 }, { "epoch": 1.02, "learning_rate": 4.131594188276314e-05, "loss": 3.7201, "step": 530432 }, { "epoch": 1.02, "learning_rate": 4.130755593525262e-05, "loss": 3.7149, "step": 530944 }, { "epoch": 1.02, "learning_rate": 4.129918636654584e-05, "loss": 3.7186, "step": 531456 }, { "epoch": 1.02, "learning_rate": 4.129080041903532e-05, "loss": 3.7143, "step": 531968 }, { "epoch": 1.02, "learning_rate": 4.128241447152479e-05, "loss": 3.7232, "step": 532480 }, { "epoch": 1.02, "learning_rate": 4.127402852401427e-05, "loss": 3.7232, "step": 532992 }, { "epoch": 1.02, "learning_rate": 4.126565895530749e-05, "loss": 3.7116, "step": 533504 }, { "epoch": 1.02, "learning_rate": 4.125727300779697e-05, "loss": 3.7285, "step": 534016 }, { "epoch": 1.03, "eval_loss": 3.8605904579162598, "eval_runtime": 304.7052, "eval_samples_per_second": 1252.328, "eval_steps_per_second": 39.136, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124888706028645e-05, "loss": 3.7103, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.124050111277593e-05, "loss": 3.7069, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123211516526541e-05, "loss": 3.7237, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.122372921775489e-05, "loss": 3.7147, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121534327024437e-05, "loss": 3.722, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.120695732273385e-05, "loss": 3.7092, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119857137522333e-05, "loss": 3.712, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.119018542771281e-05, "loss": 3.7057, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.1181815859006016e-05, "loss": 3.7174, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.1173429911495496e-05, "loss": 3.7102, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.1165043963984976e-05, "loss": 3.7187, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.1156658016474456e-05, "loss": 3.7209, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.11483048265714e-05, "loss": 3.7156, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.113991887906088e-05, "loss": 3.7104, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.113153293155036e-05, "loss": 3.7106, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.112314698403984e-05, "loss": 3.7025, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111476103652932e-05, "loss": 3.7028, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.11063750890188e-05, "loss": 3.7107, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109798914150828e-05, "loss": 3.7096, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108960319399776e-05, "loss": 3.7171, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108123362529097e-05, "loss": 3.7198, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107284767778045e-05, "loss": 3.7118, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.106446173026993e-05, "loss": 3.7196, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105607578275941e-05, "loss": 3.7197, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.1047706214052625e-05, "loss": 3.6979, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.1039320266542105e-05, "loss": 3.7157, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.1030934319031585e-05, "loss": 3.7036, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.1022548371521065e-05, "loss": 3.7054, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.1014178802814274e-05, "loss": 3.702, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.1005792855303754e-05, "loss": 3.7061, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.0997406907793234e-05, "loss": 3.7104, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.0989020960282714e-05, "loss": 3.7151, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.098065139157592e-05, "loss": 3.7093, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.09722654440654e-05, "loss": 3.7134, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096387949655488e-05, "loss": 3.7025, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095549354904436e-05, "loss": 3.7137, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094712398033758e-05, "loss": 3.7093, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.093873803282706e-05, "loss": 3.6953, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.093035208531654e-05, "loss": 3.6954, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.092198251660975e-05, "loss": 3.7, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.091359656909923e-05, "loss": 3.7064, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.090521062158871e-05, "loss": 3.7083, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.089682467407819e-05, "loss": 3.7109, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.08884551053714e-05, "loss": 3.7038, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.088006915786088e-05, "loss": 3.719, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.087168321035036e-05, "loss": 3.706, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.086329726283984e-05, "loss": 3.7103, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.085492769413305e-05, "loss": 3.6978, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.084654174662253e-05, "loss": 3.678, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083815579911201e-05, "loss": 3.7169, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082976985160149e-05, "loss": 3.7036, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.08214002828947e-05, "loss": 3.6995, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081301433538418e-05, "loss": 3.7004, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080462838787366e-05, "loss": 3.6981, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.079624244036314e-05, "loss": 3.6935, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078787287165635e-05, "loss": 3.692, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077948692414583e-05, "loss": 3.7, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077110097663531e-05, "loss": 3.696, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076271502912479e-05, "loss": 3.7122, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.0754345460418006e-05, "loss": 3.6921, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.0745959512907486e-05, "loss": 3.6901, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.0737573565396966e-05, "loss": 3.7102, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.0729187617886446e-05, "loss": 3.6837, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.0720818049179655e-05, "loss": 3.691, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.0712432101669135e-05, "loss": 3.7055, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.0704046154158615e-05, "loss": 3.708, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.0695660206648095e-05, "loss": 3.6883, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.0687290637941304e-05, "loss": 3.6875, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.0678904690430784e-05, "loss": 3.6812, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.0670518742920264e-05, "loss": 3.6954, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.0662132795409744e-05, "loss": 3.7114, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065376322670296e-05, "loss": 3.6956, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064537727919244e-05, "loss": 3.7019, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063699133168192e-05, "loss": 3.7058, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.06286053841714e-05, "loss": 3.7113, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.062023581546461e-05, "loss": 3.6882, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061184986795409e-05, "loss": 3.7074, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060346392044357e-05, "loss": 3.6919, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059507797293305e-05, "loss": 3.6923, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058670840422626e-05, "loss": 3.6979, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.057832245671574e-05, "loss": 3.7067, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056993650920522e-05, "loss": 3.6982, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.05615505616947e-05, "loss": 3.704, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.0553180992987914e-05, "loss": 3.6952, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.0544795045477394e-05, "loss": 3.6861, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.0536409097966874e-05, "loss": 3.6982, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.052802315045635e-05, "loss": 3.6974, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.051965358174956e-05, "loss": 3.69, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.051126763423904e-05, "loss": 3.6936, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.0502881686728516e-05, "loss": 3.6964, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.0494495739217996e-05, "loss": 3.7033, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.048612617051121e-05, "loss": 3.6893, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.047774022300069e-05, "loss": 3.6887, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0469354275490165e-05, "loss": 3.7055, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.046096832797965e-05, "loss": 3.7028, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.045259875927287e-05, "loss": 3.6971, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044421281176235e-05, "loss": 3.6869, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.043582686425182e-05, "loss": 3.6948, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.0427457295545036e-05, "loss": 3.6887, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.0419071348034516e-05, "loss": 3.6983, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041068540052399e-05, "loss": 3.7045, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040229945301347e-05, "loss": 3.6933, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.0393929884306685e-05, "loss": 3.6891, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.0385543936796165e-05, "loss": 3.6913, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037715798928564e-05, "loss": 3.6787, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036877204177512e-05, "loss": 3.69, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.0360402473068334e-05, "loss": 3.6818, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.0352016525557814e-05, "loss": 3.6992, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.0343630578047294e-05, "loss": 3.6792, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.0335244630536774e-05, "loss": 3.6911, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.032687506182999e-05, "loss": 3.6858, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.031848911431946e-05, "loss": 3.6966, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.031010316680894e-05, "loss": 3.6984, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030171721929842e-05, "loss": 3.6865, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.029334765059164e-05, "loss": 3.7017, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028496170308111e-05, "loss": 3.7034, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.027657575557059e-05, "loss": 3.6935, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.026818980806007e-05, "loss": 3.6962, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.025982023935329e-05, "loss": 3.685, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.025143429184277e-05, "loss": 3.6903, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.024304834433225e-05, "loss": 3.6883, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.023466239682173e-05, "loss": 3.6959, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022629282811494e-05, "loss": 3.6773, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021790688060442e-05, "loss": 3.7008, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.02095209330939e-05, "loss": 3.6949, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.020113498558338e-05, "loss": 3.6918, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.0192765416876586e-05, "loss": 3.6832, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.0184379469366066e-05, "loss": 3.6953, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.0175993521855546e-05, "loss": 3.6839, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.0167607574345026e-05, "loss": 3.6996, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.015923800563824e-05, "loss": 3.6916, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.015085205812772e-05, "loss": 3.6948, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.01424661106172e-05, "loss": 3.673, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013408016310668e-05, "loss": 3.7053, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012571059439989e-05, "loss": 3.686, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011732464688937e-05, "loss": 3.6932, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010893869937885e-05, "loss": 3.6908, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.010055275186833e-05, "loss": 3.6867, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009218318316154e-05, "loss": 3.696, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008379723565102e-05, "loss": 3.708, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.00754112881405e-05, "loss": 3.6779, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006702534062998e-05, "loss": 3.6924, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.0058655771923195e-05, "loss": 3.6863, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.0050269824412675e-05, "loss": 3.6878, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.0041883876902155e-05, "loss": 3.6841, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.0033497929391635e-05, "loss": 3.6922, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0025128360684844e-05, "loss": 3.6959, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0016742413174324e-05, "loss": 3.6806, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.0008356465663804e-05, "loss": 3.6956, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.853287935256958, "eval_runtime": 307.5847, "eval_samples_per_second": 1240.605, "eval_steps_per_second": 38.77, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.9999970518153284e-05, "loss": 3.6835, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.999160094944649e-05, "loss": 3.6798, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.998321500193597e-05, "loss": 3.6902, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997482905442545e-05, "loss": 3.6834, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.996644310691493e-05, "loss": 3.6921, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.995807353820815e-05, "loss": 3.6758, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.994968759069763e-05, "loss": 3.6891, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994130164318711e-05, "loss": 3.6752, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993293207448032e-05, "loss": 3.6856, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.99245461269698e-05, "loss": 3.6821, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.991616017945928e-05, "loss": 3.6866, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990777423194876e-05, "loss": 3.6911, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989940466324197e-05, "loss": 3.6831, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.989101871573145e-05, "loss": 3.6814, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.988263276822093e-05, "loss": 3.6836, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.987424682071041e-05, "loss": 3.6696, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.986586087319989e-05, "loss": 3.6723, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.985747492568937e-05, "loss": 3.6834, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.984908897817885e-05, "loss": 3.6808, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.984070303066833e-05, "loss": 3.6827, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.983233346196154e-05, "loss": 3.6892, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.982394751445102e-05, "loss": 3.6853, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.98155615669405e-05, "loss": 3.69, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.980717561942998e-05, "loss": 3.6871, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.979880605072319e-05, "loss": 3.6722, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.979042010321267e-05, "loss": 3.6854, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.978203415570215e-05, "loss": 3.6731, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.977364820819163e-05, "loss": 3.6809, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.976527863948484e-05, "loss": 3.6762, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.975689269197432e-05, "loss": 3.674, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.974850674446381e-05, "loss": 3.68, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.974012079695329e-05, "loss": 3.6867, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.9731751228246496e-05, "loss": 3.68, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.9723365280735976e-05, "loss": 3.6826, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.9714979333225456e-05, "loss": 3.6723, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.9706609764518665e-05, "loss": 3.686, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.9698223817008145e-05, "loss": 3.6795, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.9689837869497625e-05, "loss": 3.6666, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.9681451921987105e-05, "loss": 3.6688, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.9673082353280314e-05, "loss": 3.6685, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.9664696405769794e-05, "loss": 3.6782, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.9656310458259274e-05, "loss": 3.679, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.964792451074876e-05, "loss": 3.6793, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.963955494204197e-05, "loss": 3.6783, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.963116899453145e-05, "loss": 3.6865, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.962278304702093e-05, "loss": 3.6804, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.961439709951041e-05, "loss": 3.6818, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.960602753080362e-05, "loss": 3.6721, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.95976415832931e-05, "loss": 3.647, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.958925563578258e-05, "loss": 3.6942, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.958086968827206e-05, "loss": 3.6719, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.957250011956527e-05, "loss": 3.6723, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956411417205475e-05, "loss": 3.6727, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955572822454423e-05, "loss": 3.6689, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.9547342277033714e-05, "loss": 3.6619, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.9538972708326923e-05, "loss": 3.6639, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.9530586760816403e-05, "loss": 3.6739, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952220081330588e-05, "loss": 3.6676, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.951381486579536e-05, "loss": 3.6851, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950544529708857e-05, "loss": 3.6673, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949705934957805e-05, "loss": 3.6604, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948867340206753e-05, "loss": 3.6801, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.948028745455701e-05, "loss": 3.6593, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.947191788585022e-05, "loss": 3.6615, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.94635319383397e-05, "loss": 3.6782, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.945514599082918e-05, "loss": 3.6771, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.944676004331866e-05, "loss": 3.6624, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.943839047461188e-05, "loss": 3.6587, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.943000452710136e-05, "loss": 3.6516, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.942161857959084e-05, "loss": 3.6686, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.941323263208032e-05, "loss": 3.682, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.9404863063373526e-05, "loss": 3.6694, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.9396477115863006e-05, "loss": 3.6751, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.9388091168352486e-05, "loss": 3.6754, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.937970522084196e-05, "loss": 3.6832, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.9371335652135175e-05, "loss": 3.6633, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.936296608342839e-05, "loss": 3.6776, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.935458013591787e-05, "loss": 3.6625, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.934619418840735e-05, "loss": 3.6655, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933780824089683e-05, "loss": 3.6694, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932942229338631e-05, "loss": 3.6772, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932103634587579e-05, "loss": 3.6703, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.9312650398365264e-05, "loss": 3.6803, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.9304264450854744e-05, "loss": 3.663, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.929589488214796e-05, "loss": 3.6627, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.928750893463743e-05, "loss": 3.6721, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.927913936593065e-05, "loss": 3.6693, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.927075341842013e-05, "loss": 3.6584, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926236747090961e-05, "loss": 3.668, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925398152339909e-05, "loss": 3.6719, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.924559557588857e-05, "loss": 3.6754, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.9237226007181784e-05, "loss": 3.6623, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.922884005967126e-05, "loss": 3.6597, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.922045411216074e-05, "loss": 3.6801, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.921206816465022e-05, "loss": 3.6718, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.92036822171397e-05, "loss": 3.6706, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.919529626962918e-05, "loss": 3.6604, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.918691032211866e-05, "loss": 3.665, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.917852437460814e-05, "loss": 3.6607, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.9170154805901346e-05, "loss": 3.6719, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.9161768858390826e-05, "loss": 3.677, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.9153382910880306e-05, "loss": 3.6674, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914499696336979e-05, "loss": 3.6621, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.9136627394663e-05, "loss": 3.6577, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912824144715248e-05, "loss": 3.6594, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911985549964196e-05, "loss": 3.6585, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911146955213144e-05, "loss": 3.654, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.910309998342465e-05, "loss": 3.6706, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909471403591413e-05, "loss": 3.6545, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908632808840361e-05, "loss": 3.662, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.907794214089309e-05, "loss": 3.656, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.90695725721863e-05, "loss": 3.6692, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.906118662467578e-05, "loss": 3.6718, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.905280067716526e-05, "loss": 3.6602, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.904441472965475e-05, "loss": 3.6775, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.9036045160947956e-05, "loss": 3.6791, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.9027659213437436e-05, "loss": 3.6678, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.9019289644730645e-05, "loss": 3.6677, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.9010903697220125e-05, "loss": 3.6594, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.9002517749709605e-05, "loss": 3.6577, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.8994131802199085e-05, "loss": 3.6674, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.8985745854688565e-05, "loss": 3.6671, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.8977359907178045e-05, "loss": 3.6529, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.8968973959667525e-05, "loss": 3.6732, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.8960588012157005e-05, "loss": 3.6702, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.895223482225395e-05, "loss": 3.6665, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.894384887474343e-05, "loss": 3.6581, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893546292723291e-05, "loss": 3.6642, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.892707697972239e-05, "loss": 3.6587, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.891869103221187e-05, "loss": 3.6738, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.891030508470135e-05, "loss": 3.6637, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.890191913719083e-05, "loss": 3.6717, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.889353318968031e-05, "loss": 3.6474, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.888517999977725e-05, "loss": 3.6776, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.887679405226673e-05, "loss": 3.6561, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886840810475621e-05, "loss": 3.6691, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.886002215724569e-05, "loss": 3.6663, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885163620973517e-05, "loss": 3.6554, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.8843250262224654e-05, "loss": 3.6699, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.8834864314714134e-05, "loss": 3.6825, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.8826478367203614e-05, "loss": 3.6495, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.881810879849682e-05, "loss": 3.669, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.88097228509863e-05, "loss": 3.6594, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.880135328227951e-05, "loss": 3.6579, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.879296733476899e-05, "loss": 3.6594, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.878458138725847e-05, "loss": 3.6659, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.877619543974795e-05, "loss": 3.6678, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.876782587104116e-05, "loss": 3.6599, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.875943992353064e-05, "loss": 3.6668, "step": 686592 }, { "epoch": 1.03, "eval_loss": 3.8490421772003174, "eval_runtime": 308.4359, "eval_samples_per_second": 1237.181, "eval_steps_per_second": 38.663, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.875105397602012e-05, "loss": 3.6496, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.874266802850961e-05, "loss": 3.6522, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873428208099909e-05, "loss": 3.6635, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872589613348857e-05, "loss": 3.6591, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.871751018597804e-05, "loss": 3.6657, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.870912423846752e-05, "loss": 3.6505, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.8700738290957e-05, "loss": 3.6616, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.869235234344648e-05, "loss": 3.6518, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.868398277473969e-05, "loss": 3.656, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.867559682722917e-05, "loss": 3.6591, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.866721087971865e-05, "loss": 3.6572, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.865882493220813e-05, "loss": 3.6624, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.8650471742305075e-05, "loss": 3.667, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.8642085794794555e-05, "loss": 3.6499, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.863369984728404e-05, "loss": 3.6541, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.8625313899773515e-05, "loss": 3.6476, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.8616927952262995e-05, "loss": 3.644, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.8608542004752474e-05, "loss": 3.6595, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.8600156057241954e-05, "loss": 3.6492, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.8591770109731434e-05, "loss": 3.6577, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.8583400541024643e-05, "loss": 3.6663, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.8575014593514123e-05, "loss": 3.6629, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.8566628646003603e-05, "loss": 3.6649, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.855824269849308e-05, "loss": 3.6603, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.854987312978629e-05, "loss": 3.6461, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.854148718227578e-05, "loss": 3.6588, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.853310123476526e-05, "loss": 3.6494, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.852471528725474e-05, "loss": 3.6575, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.851634571854795e-05, "loss": 3.6471, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.8507976149841164e-05, "loss": 3.6507, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.849959020233064e-05, "loss": 3.6522, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.849120425482012e-05, "loss": 3.6602, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.84828183073096e-05, "loss": 3.6562, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.847443235979908e-05, "loss": 3.6542, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.846604641228856e-05, "loss": 3.6484, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.845766046477804e-05, "loss": 3.658, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844927451726752e-05, "loss": 3.6581, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.844090494856073e-05, "loss": 3.6449, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843251900105021e-05, "loss": 3.6443, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842413305353969e-05, "loss": 3.6426, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.841574710602917e-05, "loss": 3.6463, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840737753732238e-05, "loss": 3.652, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.839899158981186e-05, "loss": 3.6567, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.839060564230134e-05, "loss": 3.6526, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.838221969479082e-05, "loss": 3.658, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.837385012608403e-05, "loss": 3.6583, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.836546417857351e-05, "loss": 3.6544, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.835707823106299e-05, "loss": 3.6456, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.834869228355247e-05, "loss": 3.6255, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.8340322714845687e-05, "loss": 3.6655, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8331936767335166e-05, "loss": 3.645, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.8323550819824646e-05, "loss": 3.6479, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.8315164872314126e-05, "loss": 3.6517, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.8306795303607335e-05, "loss": 3.6428, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.8298409356096815e-05, "loss": 3.6384, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.8290039787390025e-05, "loss": 3.6402, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.8281653839879504e-05, "loss": 3.6489, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.8273267892368984e-05, "loss": 3.6402, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.8264881944858464e-05, "loss": 3.6597, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.8256495997347944e-05, "loss": 3.6449, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.8248110049837424e-05, "loss": 3.6315, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.8239724102326904e-05, "loss": 3.657, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.8231338154816384e-05, "loss": 3.6377, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.82229685861096e-05, "loss": 3.6361, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821458263859908e-05, "loss": 3.6539, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820619669108856e-05, "loss": 3.6544, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.819781074357804e-05, "loss": 3.6362, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.818942479606752e-05, "loss": 3.634, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.8181038848557e-05, "loss": 3.6284, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.817265290104647e-05, "loss": 3.6443, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.816428333233969e-05, "loss": 3.6552, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.815589738482917e-05, "loss": 3.6465, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.814751143731864e-05, "loss": 3.6491, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.813914186861186e-05, "loss": 3.6489, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.813075592110134e-05, "loss": 3.6554, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.8122369973590825e-05, "loss": 3.6427, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.81139840260803e-05, "loss": 3.6554, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810559807856978e-05, "loss": 3.634, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.8097228509862994e-05, "loss": 3.641, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.8088842562352474e-05, "loss": 3.6441, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.808045661484195e-05, "loss": 3.6483, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.807207066733143e-05, "loss": 3.6503, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806368471982091e-05, "loss": 3.6539, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.8055315151114116e-05, "loss": 3.6363, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.8046929203603596e-05, "loss": 3.6376, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.8038543256093076e-05, "loss": 3.6468, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.803015730858256e-05, "loss": 3.6489, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.802177136107204e-05, "loss": 3.6342, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801340179236525e-05, "loss": 3.6407, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.800501584485473e-05, "loss": 3.6483, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799662989734421e-05, "loss": 3.6457, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.798824394983369e-05, "loss": 3.6417, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.797985800232317e-05, "loss": 3.6358, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.797147205481265e-05, "loss": 3.6511, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.796308610730213e-05, "loss": 3.6505, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.795471653859534e-05, "loss": 3.6467, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.794633059108482e-05, "loss": 3.6368, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.79379446435743e-05, "loss": 3.6428, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.792955869606378e-05, "loss": 3.6345, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.792117274855326e-05, "loss": 3.6493, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.7912803179846476e-05, "loss": 3.6512, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.7904417232335956e-05, "loss": 3.6413, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.7896031284825436e-05, "loss": 3.6424, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.7887645337314916e-05, "loss": 3.6325, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.7879259389804396e-05, "loss": 3.6366, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.7870873442293876e-05, "loss": 3.6324, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.7862487494783356e-05, "loss": 3.6322, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.785410154727283e-05, "loss": 3.6444, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.7845731978566045e-05, "loss": 3.6317, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.7837346031055525e-05, "loss": 3.6361, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.7828960083545005e-05, "loss": 3.6347, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.7820590514838214e-05, "loss": 3.6396, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.7812204567327694e-05, "loss": 3.6497, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.780381861981718e-05, "loss": 3.638, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.779543267230666e-05, "loss": 3.6515, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.7787046724796134e-05, "loss": 3.6558, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.777867715608935e-05, "loss": 3.6446, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.777029120857883e-05, "loss": 3.6392, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.77619052610683e-05, "loss": 3.6383, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.775351931355778e-05, "loss": 3.6374, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.7745149744851e-05, "loss": 3.6436, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773676379734048e-05, "loss": 3.6416, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772837784982995e-05, "loss": 3.629, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.771999190231943e-05, "loss": 3.6501, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771160595480892e-05, "loss": 3.6493, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.7703236386102134e-05, "loss": 3.6357, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769485043859161e-05, "loss": 3.6363, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.768646449108109e-05, "loss": 3.6442, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.767807854357057e-05, "loss": 3.6316, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.766969259606005e-05, "loss": 3.652, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.766130664854953e-05, "loss": 3.6375, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.765292070103901e-05, "loss": 3.6487, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.7644551132332216e-05, "loss": 3.6248, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.7636165184821696e-05, "loss": 3.6484, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.7627779237311176e-05, "loss": 3.6409, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.7619393289800656e-05, "loss": 3.6398, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.7611007342290136e-05, "loss": 3.6423, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760263777358335e-05, "loss": 3.6336, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.759425182607283e-05, "loss": 3.6441, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758586587856231e-05, "loss": 3.6646, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757747993105179e-05, "loss": 3.6255, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756909398354127e-05, "loss": 3.6439, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.756072441483448e-05, "loss": 3.6365, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755233846732396e-05, "loss": 3.6332, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.754395251981344e-05, "loss": 3.6381, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753556657230292e-05, "loss": 3.6403, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.75271806247924e-05, "loss": 3.6432, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751881105608561e-05, "loss": 3.6397, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.751042510857509e-05, "loss": 3.6419, "step": 762880 }, { "epoch": 0.03, "eval_loss": 3.8457443714141846, "eval_runtime": 304.9597, "eval_samples_per_second": 1251.284, "eval_steps_per_second": 39.104, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.750203916106457e-05, "loss": 3.6311, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.7493653213554056e-05, "loss": 3.629, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.7485283644847265e-05, "loss": 3.6393, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.7476897697336745e-05, "loss": 3.6368, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.7468511749826225e-05, "loss": 3.6448, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.7460125802315705e-05, "loss": 3.6273, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.7451756233608914e-05, "loss": 3.6372, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.7443370286098394e-05, "loss": 3.6254, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.7434984338587874e-05, "loss": 3.6361, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.7426598391077354e-05, "loss": 3.6356, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.7418212443566834e-05, "loss": 3.6305, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.7409826496056314e-05, "loss": 3.6418, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.740147330615326e-05, "loss": 3.6472, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.739308735864274e-05, "loss": 3.6254, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.738470141113222e-05, "loss": 3.6358, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.73763154636217e-05, "loss": 3.6201, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.736792951611118e-05, "loss": 3.6229, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.735954356860066e-05, "loss": 3.6345, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.735115762109014e-05, "loss": 3.6274, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.734277167357961e-05, "loss": 3.6365, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.733438572606909e-05, "loss": 3.6423, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.732599977855857e-05, "loss": 3.6376, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.731761383104805e-05, "loss": 3.6411, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.730922788353753e-05, "loss": 3.6356, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.730087469363448e-05, "loss": 3.6283, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.729248874612396e-05, "loss": 3.6339, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.728410279861344e-05, "loss": 3.6284, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.727571685110292e-05, "loss": 3.636, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.72673309035924e-05, "loss": 3.6225, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.725896133488561e-05, "loss": 3.6282, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.7250575387375086e-05, "loss": 3.6297, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.7242189439864566e-05, "loss": 3.637, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.7233803492354046e-05, "loss": 3.6357, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.7225417544843526e-05, "loss": 3.63, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.7217031597333006e-05, "loss": 3.6283, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.7208662028626215e-05, "loss": 3.6308, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.7200276081115695e-05, "loss": 3.6366, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.719189013360518e-05, "loss": 3.6209, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.718350418609466e-05, "loss": 3.6216, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.717511823858414e-05, "loss": 3.6207, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.716673229107362e-05, "loss": 3.6248, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.71583463435631e-05, "loss": 3.6277, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.714996039605258e-05, "loss": 3.6357, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.714160720614952e-05, "loss": 3.6308, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.7133221258639e-05, "loss": 3.6342, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.712483531112848e-05, "loss": 3.6349, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.711644936361796e-05, "loss": 3.6335, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.710807979491117e-05, "loss": 3.6253, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709969384740065e-05, "loss": 3.6017, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.7091307899890135e-05, "loss": 3.6406, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.7082921952379615e-05, "loss": 3.6225, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.7074536004869095e-05, "loss": 3.6276, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.7066150057358575e-05, "loss": 3.6288, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.7057764109848055e-05, "loss": 3.6174, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.7049378162337535e-05, "loss": 3.6185, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.704102497243447e-05, "loss": 3.6166, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.703263902492395e-05, "loss": 3.6291, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702425307741343e-05, "loss": 3.616, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.701586712990291e-05, "loss": 3.6376, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700748118239239e-05, "loss": 3.6227, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.699909523488187e-05, "loss": 3.6069, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.699070928737135e-05, "loss": 3.6389, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.698232333986083e-05, "loss": 3.6143, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.697395377115405e-05, "loss": 3.613, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.696556782364353e-05, "loss": 3.6313, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.695718187613301e-05, "loss": 3.634, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.694879592862249e-05, "loss": 3.6124, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.694040998111197e-05, "loss": 3.6128, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.693202403360145e-05, "loss": 3.6077, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.692365446489466e-05, "loss": 3.6196, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.691526851738414e-05, "loss": 3.632, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.690688256987362e-05, "loss": 3.6256, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.68984966223631e-05, "loss": 3.6278, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.6890127053656307e-05, "loss": 3.6244, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.6881741106145787e-05, "loss": 3.6322, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687335515863527e-05, "loss": 3.624, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.6864969211124746e-05, "loss": 3.632, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.6856583263614226e-05, "loss": 3.6123, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.6848197316103706e-05, "loss": 3.6186, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.683982774739692e-05, "loss": 3.6261, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.6831441799886395e-05, "loss": 3.6261, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.6823055852375875e-05, "loss": 3.6293, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.6814669904865355e-05, "loss": 3.6319, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.6806283957354835e-05, "loss": 3.6183, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.6797914388648044e-05, "loss": 3.614, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.6789528441137524e-05, "loss": 3.623, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.678114249362701e-05, "loss": 3.6283, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.677275654611649e-05, "loss": 3.6122, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.67643869774097e-05, "loss": 3.6198, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.675600102989918e-05, "loss": 3.6307, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.674761508238866e-05, "loss": 3.6216, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.673922913487814e-05, "loss": 3.6196, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.673084318736762e-05, "loss": 3.6154, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.672247361866083e-05, "loss": 3.6273, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.671408767115031e-05, "loss": 3.6316, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.670570172363979e-05, "loss": 3.6244, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.669731577612927e-05, "loss": 3.6153, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.668892982861875e-05, "loss": 3.6193, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.6680560259911965e-05, "loss": 3.6145, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.6672174312401445e-05, "loss": 3.6285, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.6663788364890925e-05, "loss": 3.6296, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.6655402417380405e-05, "loss": 3.617, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.6647032848673614e-05, "loss": 3.62, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.6638646901163094e-05, "loss": 3.6168, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.6630260953652574e-05, "loss": 3.6119, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.6621875006142054e-05, "loss": 3.6133, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.6613489058631533e-05, "loss": 3.6121, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.6605103111121013e-05, "loss": 3.6171, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.659673354241422e-05, "loss": 3.6141, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.65883475949037e-05, "loss": 3.6124, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.657996164739318e-05, "loss": 3.6179, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.657157569988266e-05, "loss": 3.6158, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.656318975237214e-05, "loss": 3.6278, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.655480380486163e-05, "loss": 3.6132, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.654641785735111e-05, "loss": 3.6327, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.653803190984058e-05, "loss": 3.6339, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.652967871993753e-05, "loss": 3.6256, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.652129277242701e-05, "loss": 3.6173, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.651290682491649e-05, "loss": 3.6177, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.650452087740597e-05, "loss": 3.6155, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.6496151308699176e-05, "loss": 3.6255, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.6487765361188656e-05, "loss": 3.6187, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.6479379413678136e-05, "loss": 3.6097, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.6470993466167616e-05, "loss": 3.6253, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.6462607518657096e-05, "loss": 3.6297, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.645423794995031e-05, "loss": 3.6124, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.644585200243979e-05, "loss": 3.6165, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.643746605492927e-05, "loss": 3.6217, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.642908010741875e-05, "loss": 3.6071, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.642071053871196e-05, "loss": 3.633, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.641232459120144e-05, "loss": 3.6145, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.640393864369092e-05, "loss": 3.6298, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.63955526961804e-05, "loss": 3.6035, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.6387166748669874e-05, "loss": 3.6245, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.637879717996309e-05, "loss": 3.6174, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.637041123245257e-05, "loss": 3.6196, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.636202528494205e-05, "loss": 3.6211, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635363933743153e-05, "loss": 3.6124, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.6345269768724746e-05, "loss": 3.6242, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.6336883821214225e-05, "loss": 3.6399, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.6328497873703705e-05, "loss": 3.6066, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.632011192619318e-05, "loss": 3.6175, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.6311742357486394e-05, "loss": 3.6189, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.6303356409975874e-05, "loss": 3.6145, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.629497046246535e-05, "loss": 3.6176, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.628658451495483e-05, "loss": 3.6194, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.627819856744431e-05, "loss": 3.6201, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.6269828998737523e-05, "loss": 3.6191, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.6261443051227e-05, "loss": 3.6185, "step": 839168 }, { "epoch": 1.03, "eval_loss": 3.8445825576782227, "eval_runtime": 308.3389, "eval_samples_per_second": 1237.57, "eval_steps_per_second": 38.675, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.625305710371648e-05, "loss": 3.6004, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.624467115620596e-05, "loss": 3.6065, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.623628520869544e-05, "loss": 3.6195, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.622789926118492e-05, "loss": 3.6122, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.62195133136744e-05, "loss": 3.626, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.621112736616388e-05, "loss": 3.6082, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.620275779745709e-05, "loss": 3.6153, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.619437184994657e-05, "loss": 3.6094, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.618598590243605e-05, "loss": 3.6156, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.617759995492553e-05, "loss": 3.6088, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.616921400741501e-05, "loss": 3.6119, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.616084443870823e-05, "loss": 3.6264, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.615247487000144e-05, "loss": 3.6199, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.614408892249092e-05, "loss": 3.6038, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.61357029749804e-05, "loss": 3.6143, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.612731702746988e-05, "loss": 3.598, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.611893107995936e-05, "loss": 3.6047, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.611054513244884e-05, "loss": 3.6183, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.610215918493832e-05, "loss": 3.6048, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.60937732374278e-05, "loss": 3.6133, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.6085403668721006e-05, "loss": 3.6181, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.6077017721210486e-05, "loss": 3.6173, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.6068631773699966e-05, "loss": 3.6218, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.6060245826189446e-05, "loss": 3.6183, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.6051859878678926e-05, "loss": 3.6062, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.604349030997214e-05, "loss": 3.6114, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603510436246162e-05, "loss": 3.6055, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.60267184149511e-05, "loss": 3.6144, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.601833246744058e-05, "loss": 3.6047, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.600996289873379e-05, "loss": 3.6086, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.600157695122327e-05, "loss": 3.611, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.599319100371275e-05, "loss": 3.6133, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.598480505620223e-05, "loss": 3.6129, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.597641910869171e-05, "loss": 3.6133, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.5968033161181183e-05, "loss": 3.6058, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.59596635924744e-05, "loss": 3.6123, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.595127764496388e-05, "loss": 3.6178, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.594289169745336e-05, "loss": 3.6006, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.593450574994284e-05, "loss": 3.5998, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.592611980243232e-05, "loss": 3.6023, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.5917750233725535e-05, "loss": 3.6008, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.590936428621501e-05, "loss": 3.6079, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.590097833870449e-05, "loss": 3.6119, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.589259239119397e-05, "loss": 3.6158, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.588420644368345e-05, "loss": 3.6103, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.587583687497666e-05, "loss": 3.6131, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.586745092746614e-05, "loss": 3.6134, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.585906497995562e-05, "loss": 3.6078, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.58506790324451e-05, "loss": 3.5837, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.5842293084934584e-05, "loss": 3.6193, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.583392351622779e-05, "loss": 3.6005, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.582553756871727e-05, "loss": 3.6089, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.581715162120675e-05, "loss": 3.6022, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.580876567369623e-05, "loss": 3.5991, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.580039610498944e-05, "loss": 3.6, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.579201015747892e-05, "loss": 3.5989, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.57836242099684e-05, "loss": 3.6087, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.577523826245788e-05, "loss": 3.5925, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.576685231494736e-05, "loss": 3.6187, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.575848274624057e-05, "loss": 3.6063, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.575009679873005e-05, "loss": 3.5829, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.574171085121954e-05, "loss": 3.6181, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.573332490370902e-05, "loss": 3.5929, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.5724955335002226e-05, "loss": 3.5949, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.5716569387491706e-05, "loss": 3.6057, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.5708183439981186e-05, "loss": 3.6139, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.5699797492470666e-05, "loss": 3.5938, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.5691411544960146e-05, "loss": 3.5993, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.5683041976253355e-05, "loss": 3.5854, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.5674656028742835e-05, "loss": 3.5976, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.5666270081232315e-05, "loss": 3.6136, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.5657884133721795e-05, "loss": 3.6041, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.5649514565015004e-05, "loss": 3.6081, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.564112861750449e-05, "loss": 3.6067, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.563274266999397e-05, "loss": 3.6149, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.562435672248345e-05, "loss": 3.604, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.561598715377666e-05, "loss": 3.6124, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.560760120626614e-05, "loss": 3.5939, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.559921525875562e-05, "loss": 3.5979, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.55908293112451e-05, "loss": 3.6037, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.558245974253831e-05, "loss": 3.604, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.557407379502779e-05, "loss": 3.6067, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.556568784751727e-05, "loss": 3.6132, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.555730190000675e-05, "loss": 3.6036, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.554891595249623e-05, "loss": 3.5918, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.5540546383789445e-05, "loss": 3.6036, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.5532160436278925e-05, "loss": 3.6061, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.5523774488768405e-05, "loss": 3.5918, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.5515388541257885e-05, "loss": 3.5987, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.5507002593747365e-05, "loss": 3.6117, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.5498616646236845e-05, "loss": 3.5997, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.549023069872632e-05, "loss": 3.603, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.5481861130019534e-05, "loss": 3.5937, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.5473475182509014e-05, "loss": 3.6089, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.5465089234998493e-05, "loss": 3.6089, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.545670328748797e-05, "loss": 3.6099, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.544833371878118e-05, "loss": 3.5894, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.543994777127066e-05, "loss": 3.6043, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.543156182376014e-05, "loss": 3.5921, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.542317587624962e-05, "loss": 3.6063, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.541480630754284e-05, "loss": 3.6132, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.540642036003232e-05, "loss": 3.5959, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.539803441252179e-05, "loss": 3.601, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.538964846501127e-05, "loss": 3.5935, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.538126251750075e-05, "loss": 3.5945, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.537289294879397e-05, "loss": 3.594, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.536450700128344e-05, "loss": 3.5952, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.535612105377292e-05, "loss": 3.5979, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.53477351062624e-05, "loss": 3.5951, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.533934915875188e-05, "loss": 3.5906, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.5330979590045096e-05, "loss": 3.5918, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.5322593642534576e-05, "loss": 3.5969, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.5314207695024056e-05, "loss": 3.613, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.5305821747513536e-05, "loss": 3.5964, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.5297452178806745e-05, "loss": 3.609, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.5289066231296225e-05, "loss": 3.6107, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.5280680283785705e-05, "loss": 3.6123, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.5272294336275185e-05, "loss": 3.5957, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.5263924767568394e-05, "loss": 3.5992, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.5255538820057874e-05, "loss": 3.5973, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.5247152872547354e-05, "loss": 3.6035, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.5238766925036834e-05, "loss": 3.6019, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.5230380977526314e-05, "loss": 3.5928, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.522201140881953e-05, "loss": 3.5991, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521362546130901e-05, "loss": 3.6098, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.520523951379849e-05, "loss": 3.6012, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.519685356628797e-05, "loss": 3.5938, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.518848399758118e-05, "loss": 3.6023, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.518009805007066e-05, "loss": 3.5883, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.517171210256014e-05, "loss": 3.6109, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.516332615504962e-05, "loss": 3.5972, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.515495658634283e-05, "loss": 3.6094, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514657063883231e-05, "loss": 3.5853, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.513818469132179e-05, "loss": 3.6043, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.512979874381127e-05, "loss": 3.6007, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.5121429175104483e-05, "loss": 3.599, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.511304322759396e-05, "loss": 3.6027, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.510465728008344e-05, "loss": 3.5926, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.509627133257292e-05, "loss": 3.6075, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.50878853850624e-05, "loss": 3.6206, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.507951581635561e-05, "loss": 3.5878, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.507112986884509e-05, "loss": 3.5976, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.506274392133457e-05, "loss": 3.5996, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.505435797382405e-05, "loss": 3.598, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.504598840511726e-05, "loss": 3.5938, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.503760245760674e-05, "loss": 3.6042, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.502921651009622e-05, "loss": 3.597, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.502083056258571e-05, "loss": 3.5988, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.501246099387892e-05, "loss": 3.6021, "step": 915456 }, { "epoch": 0.03, "eval_loss": 3.8437600135803223, "eval_runtime": 307.9573, "eval_samples_per_second": 1239.103, "eval_steps_per_second": 38.723, "step": 915840 }, { "epoch": 1.0, "learning_rate": 3.50040750463684e-05, "loss": 3.5943, "step": 915968 }, { "epoch": 1.0, "learning_rate": 3.499568909885788e-05, "loss": 3.5833, "step": 916480 }, { "epoch": 1.0, "learning_rate": 3.498730315134736e-05, "loss": 3.6015, "step": 916992 }, { "epoch": 1.0, "learning_rate": 3.4978933582640566e-05, "loss": 3.5958, "step": 917504 }, { "epoch": 1.0, "learning_rate": 3.4970547635130046e-05, "loss": 3.6009, "step": 918016 }, { "epoch": 1.0, "learning_rate": 3.4962161687619526e-05, "loss": 3.5904, "step": 918528 }, { "epoch": 1.0, "learning_rate": 3.4953775740109006e-05, "loss": 3.601, "step": 919040 }, { "epoch": 1.0, "learning_rate": 3.4945406171402215e-05, "loss": 3.5883, "step": 919552 }, { "epoch": 1.0, "learning_rate": 3.4937020223891695e-05, "loss": 3.5938, "step": 920064 }, { "epoch": 1.0, "learning_rate": 3.4928634276381175e-05, "loss": 3.5888, "step": 920576 }, { "epoch": 1.0, "learning_rate": 3.492024832887066e-05, "loss": 3.595, "step": 921088 }, { "epoch": 1.0, "learning_rate": 3.491187876016387e-05, "loss": 3.6051, "step": 921600 }, { "epoch": 1.0, "learning_rate": 3.490350919145708e-05, "loss": 3.605, "step": 922112 }, { "epoch": 1.0, "learning_rate": 3.489512324394656e-05, "loss": 3.5861, "step": 922624 }, { "epoch": 1.0, "learning_rate": 3.488673729643604e-05, "loss": 3.5952, "step": 923136 }, { "epoch": 1.0, "learning_rate": 3.487835134892552e-05, "loss": 3.5799, "step": 923648 }, { "epoch": 1.0, "learning_rate": 3.4869965401415e-05, "loss": 3.5892, "step": 924160 }, { "epoch": 1.0, "learning_rate": 3.486157945390448e-05, "loss": 3.5933, "step": 924672 }, { "epoch": 1.0, "learning_rate": 3.485319350639396e-05, "loss": 3.5856, "step": 925184 }, { "epoch": 1.0, "learning_rate": 3.484480755888344e-05, "loss": 3.5962, "step": 925696 }, { "epoch": 1.0, "learning_rate": 3.483643799017665e-05, "loss": 3.5991, "step": 926208 }, { "epoch": 1.0, "learning_rate": 3.482805204266613e-05, "loss": 3.5959, "step": 926720 }, { "epoch": 1.0, "learning_rate": 3.4819666095155615e-05, "loss": 3.6048, "step": 927232 }, { "epoch": 1.0, "learning_rate": 3.4811280147645095e-05, "loss": 3.6001, "step": 927744 }, { "epoch": 1.0, "learning_rate": 3.4802894200134575e-05, "loss": 3.588, "step": 928256 }, { "epoch": 1.0, "learning_rate": 3.4794524631427784e-05, "loss": 3.5957, "step": 928768 }, { "epoch": 1.0, "learning_rate": 3.4786138683917264e-05, "loss": 3.5857, "step": 929280 }, { "epoch": 1.0, "learning_rate": 3.4777752736406744e-05, "loss": 3.5946, "step": 929792 }, { "epoch": 1.0, "learning_rate": 3.476936678889622e-05, "loss": 3.5853, "step": 930304 }, { "epoch": 1.0, "learning_rate": 3.476099722018943e-05, "loss": 3.5886, "step": 930816 }, { "epoch": 1.01, "learning_rate": 3.475261127267891e-05, "loss": 3.5939, "step": 931328 }, { "epoch": 1.01, "learning_rate": 3.474422532516839e-05, "loss": 3.5909, "step": 931840 }, { "epoch": 1.01, "learning_rate": 3.4735839377657866e-05, "loss": 3.5916, "step": 932352 }, { "epoch": 1.01, "learning_rate": 3.472745343014735e-05, "loss": 3.5971, "step": 932864 }, { "epoch": 1.01, "learning_rate": 3.471906748263683e-05, "loss": 3.5882, "step": 933376 }, { "epoch": 1.01, "learning_rate": 3.471069791393005e-05, "loss": 3.5904, "step": 933888 }, { "epoch": 1.01, "learning_rate": 3.470231196641952e-05, "loss": 3.6009, "step": 934400 }, { "epoch": 1.01, "learning_rate": 3.4693926018909e-05, "loss": 3.5767, "step": 934912 }, { "epoch": 1.01, "learning_rate": 3.468554007139848e-05, "loss": 3.587, "step": 935424 }, { "epoch": 1.01, "learning_rate": 3.467715412388796e-05, "loss": 3.5844, "step": 935936 }, { "epoch": 1.01, "learning_rate": 3.466878455518117e-05, "loss": 3.5842, "step": 936448 }, { "epoch": 1.01, "learning_rate": 3.466039860767065e-05, "loss": 3.5865, "step": 936960 }, { "epoch": 1.01, "learning_rate": 3.465201266016013e-05, "loss": 3.5926, "step": 937472 }, { "epoch": 1.01, "learning_rate": 3.464362671264961e-05, "loss": 3.5971, "step": 937984 }, { "epoch": 1.01, "learning_rate": 3.463524076513909e-05, "loss": 3.5923, "step": 938496 }, { "epoch": 1.01, "learning_rate": 3.462687119643231e-05, "loss": 3.5958, "step": 939008 }, { "epoch": 1.01, "learning_rate": 3.461848524892179e-05, "loss": 3.5959, "step": 939520 }, { "epoch": 1.01, "learning_rate": 3.461009930141127e-05, "loss": 3.5882, "step": 940032 }, { "epoch": 1.01, "learning_rate": 3.4601713353900747e-05, "loss": 3.5686, "step": 940544 }, { "epoch": 1.01, "learning_rate": 3.4593343785193956e-05, "loss": 3.595, "step": 941056 }, { "epoch": 1.01, "learning_rate": 3.4584957837683436e-05, "loss": 3.5845, "step": 941568 }, { "epoch": 1.01, "learning_rate": 3.4576571890172916e-05, "loss": 3.5871, "step": 942080 }, { "epoch": 1.01, "learning_rate": 3.4568185942662396e-05, "loss": 3.5839, "step": 942592 }, { "epoch": 1.01, "learning_rate": 3.4559816373955605e-05, "loss": 3.5806, "step": 943104 }, { "epoch": 1.01, "learning_rate": 3.4551430426445085e-05, "loss": 3.5827, "step": 943616 }, { "epoch": 1.01, "learning_rate": 3.4543044478934565e-05, "loss": 3.5793, "step": 944128 }, { "epoch": 1.01, "learning_rate": 3.4534658531424045e-05, "loss": 3.5927, "step": 944640 }, { "epoch": 1.01, "learning_rate": 3.452628896271726e-05, "loss": 3.5702, "step": 945152 }, { "epoch": 1.01, "learning_rate": 3.451790301520674e-05, "loss": 3.6018, "step": 945664 }, { "epoch": 1.01, "learning_rate": 3.450951706769622e-05, "loss": 3.5893, "step": 946176 }, { "epoch": 1.01, "learning_rate": 3.45011311201857e-05, "loss": 3.5682, "step": 946688 }, { "epoch": 1.01, "learning_rate": 3.449274517267518e-05, "loss": 3.5986, "step": 947200 }, { "epoch": 1.01, "learning_rate": 3.448437560396839e-05, "loss": 3.5732, "step": 947712 }, { "epoch": 1.01, "learning_rate": 3.447598965645787e-05, "loss": 3.5809, "step": 948224 }, { "epoch": 1.01, "learning_rate": 3.446760370894735e-05, "loss": 3.5837, "step": 948736 }, { "epoch": 1.01, "learning_rate": 3.445921776143683e-05, "loss": 3.5946, "step": 949248 }, { "epoch": 1.01, "learning_rate": 3.445084819273004e-05, "loss": 3.5771, "step": 949760 }, { "epoch": 1.01, "learning_rate": 3.444246224521952e-05, "loss": 3.5789, "step": 950272 }, { "epoch": 1.01, "learning_rate": 3.4434076297709e-05, "loss": 3.5643, "step": 950784 }, { "epoch": 1.01, "learning_rate": 3.442569035019848e-05, "loss": 3.5838, "step": 951296 }, { "epoch": 1.01, "learning_rate": 3.441730440268796e-05, "loss": 3.5911, "step": 951808 }, { "epoch": 1.01, "learning_rate": 3.440891845517744e-05, "loss": 3.5884, "step": 952320 }, { "epoch": 1.01, "learning_rate": 3.4400532507666925e-05, "loss": 3.5892, "step": 952832 }, { "epoch": 1.01, "learning_rate": 3.4392162938960134e-05, "loss": 3.5889, "step": 953344 }, { "epoch": 1.01, "learning_rate": 3.4383776991449614e-05, "loss": 3.5982, "step": 953856 }, { "epoch": 1.01, "learning_rate": 3.4375391043939094e-05, "loss": 3.5823, "step": 954368 }, { "epoch": 1.01, "learning_rate": 3.4367005096428574e-05, "loss": 3.5929, "step": 954880 }, { "epoch": 1.01, "learning_rate": 3.435863552772178e-05, "loss": 3.579, "step": 955392 }, { "epoch": 1.01, "learning_rate": 3.435024958021126e-05, "loss": 3.5832, "step": 955904 }, { "epoch": 1.01, "learning_rate": 3.434186363270074e-05, "loss": 3.5846, "step": 956416 }, { "epoch": 1.01, "learning_rate": 3.433347768519022e-05, "loss": 3.5835, "step": 956928 }, { "epoch": 1.01, "learning_rate": 3.432510811648343e-05, "loss": 3.5923, "step": 957440 }, { "epoch": 1.01, "learning_rate": 3.431672216897291e-05, "loss": 3.5903, "step": 957952 }, { "epoch": 1.01, "learning_rate": 3.430833622146239e-05, "loss": 3.5928, "step": 958464 }, { "epoch": 1.01, "learning_rate": 3.429995027395188e-05, "loss": 3.5735, "step": 958976 }, { "epoch": 1.01, "learning_rate": 3.429156432644136e-05, "loss": 3.5833, "step": 959488 }, { "epoch": 1.01, "learning_rate": 3.428319475773457e-05, "loss": 3.5889, "step": 960000 }, { "epoch": 1.01, "learning_rate": 3.427480881022405e-05, "loss": 3.5764, "step": 960512 }, { "epoch": 1.01, "learning_rate": 3.426642286271353e-05, "loss": 3.5773, "step": 961024 }, { "epoch": 1.01, "learning_rate": 3.4258036915203e-05, "loss": 3.5895, "step": 961536 }, { "epoch": 1.02, "learning_rate": 3.424965096769248e-05, "loss": 3.5864, "step": 962048 }, { "epoch": 1.02, "learning_rate": 3.4241281398985696e-05, "loss": 3.581, "step": 962560 }, { "epoch": 1.02, "learning_rate": 3.4232895451475176e-05, "loss": 3.5782, "step": 963072 }, { "epoch": 1.02, "learning_rate": 3.422450950396465e-05, "loss": 3.5881, "step": 963584 }, { "epoch": 1.02, "learning_rate": 3.421612355645413e-05, "loss": 3.594, "step": 964096 }, { "epoch": 1.02, "learning_rate": 3.4207737608943616e-05, "loss": 3.5891, "step": 964608 }, { "epoch": 1.02, "learning_rate": 3.4199368040236825e-05, "loss": 3.5721, "step": 965120 }, { "epoch": 1.02, "learning_rate": 3.4190982092726305e-05, "loss": 3.5859, "step": 965632 }, { "epoch": 1.02, "learning_rate": 3.4182596145215785e-05, "loss": 3.5751, "step": 966144 }, { "epoch": 1.02, "learning_rate": 3.4174210197705265e-05, "loss": 3.5864, "step": 966656 }, { "epoch": 1.02, "learning_rate": 3.4165840628998474e-05, "loss": 3.5969, "step": 967168 }, { "epoch": 1.02, "learning_rate": 3.4157454681487954e-05, "loss": 3.5793, "step": 967680 }, { "epoch": 1.02, "learning_rate": 3.4149068733977434e-05, "loss": 3.5777, "step": 968192 }, { "epoch": 1.02, "learning_rate": 3.4140682786466914e-05, "loss": 3.5803, "step": 968704 }, { "epoch": 1.02, "learning_rate": 3.4132296838956394e-05, "loss": 3.5788, "step": 969216 }, { "epoch": 1.02, "learning_rate": 3.41239272702496e-05, "loss": 3.5716, "step": 969728 }, { "epoch": 1.02, "learning_rate": 3.411554132273908e-05, "loss": 3.5815, "step": 970240 }, { "epoch": 1.02, "learning_rate": 3.410715537522857e-05, "loss": 3.5784, "step": 970752 }, { "epoch": 1.02, "learning_rate": 3.409876942771805e-05, "loss": 3.5787, "step": 971264 }, { "epoch": 1.02, "learning_rate": 3.409038348020753e-05, "loss": 3.5715, "step": 971776 }, { "epoch": 1.02, "learning_rate": 3.408201391150074e-05, "loss": 3.5755, "step": 972288 }, { "epoch": 1.02, "learning_rate": 3.407362796399022e-05, "loss": 3.5757, "step": 972800 }, { "epoch": 1.02, "learning_rate": 3.40652420164797e-05, "loss": 3.5948, "step": 973312 }, { "epoch": 1.02, "learning_rate": 3.405685606896918e-05, "loss": 3.5774, "step": 973824 }, { "epoch": 1.02, "learning_rate": 3.404848650026239e-05, "loss": 3.59, "step": 974336 }, { "epoch": 1.02, "learning_rate": 3.404010055275187e-05, "loss": 3.5889, "step": 974848 }, { "epoch": 1.02, "learning_rate": 3.403171460524135e-05, "loss": 3.5992, "step": 975360 }, { "epoch": 1.02, "learning_rate": 3.402332865773083e-05, "loss": 3.5809, "step": 975872 }, { "epoch": 1.02, "learning_rate": 3.401495908902404e-05, "loss": 3.5796, "step": 976384 }, { "epoch": 1.02, "learning_rate": 3.4006573141513524e-05, "loss": 3.5815, "step": 976896 }, { "epoch": 1.02, "learning_rate": 3.3998187194003004e-05, "loss": 3.5842, "step": 977408 }, { "epoch": 1.02, "learning_rate": 3.3989801246492483e-05, "loss": 3.5799, "step": 977920 }, { "epoch": 1.02, "learning_rate": 3.398143167778569e-05, "loss": 3.5812, "step": 978432 }, { "epoch": 1.02, "learning_rate": 3.397304573027517e-05, "loss": 3.5797, "step": 978944 }, { "epoch": 1.02, "learning_rate": 3.396465978276465e-05, "loss": 3.5914, "step": 979456 }, { "epoch": 1.02, "learning_rate": 3.395627383525413e-05, "loss": 3.579, "step": 979968 }, { "epoch": 1.02, "learning_rate": 3.394788788774361e-05, "loss": 3.5772, "step": 980480 }, { "epoch": 1.02, "learning_rate": 3.393951831903682e-05, "loss": 3.582, "step": 980992 }, { "epoch": 1.02, "learning_rate": 3.39311323715263e-05, "loss": 3.5767, "step": 981504 }, { "epoch": 1.02, "learning_rate": 3.392274642401578e-05, "loss": 3.5935, "step": 982016 }, { "epoch": 1.02, "learning_rate": 3.391436047650526e-05, "loss": 3.5774, "step": 982528 }, { "epoch": 1.02, "learning_rate": 3.390599090779848e-05, "loss": 3.5924, "step": 983040 }, { "epoch": 1.02, "learning_rate": 3.389760496028796e-05, "loss": 3.5722, "step": 983552 }, { "epoch": 1.02, "learning_rate": 3.388921901277744e-05, "loss": 3.5828, "step": 984064 }, { "epoch": 1.02, "learning_rate": 3.388083306526692e-05, "loss": 3.5838, "step": 984576 }, { "epoch": 1.02, "learning_rate": 3.3872463496560126e-05, "loss": 3.5797, "step": 985088 }, { "epoch": 1.02, "learning_rate": 3.3864077549049606e-05, "loss": 3.5767, "step": 985600 }, { "epoch": 1.02, "learning_rate": 3.3855691601539086e-05, "loss": 3.5814, "step": 986112 }, { "epoch": 1.02, "learning_rate": 3.3847305654028566e-05, "loss": 3.5882, "step": 986624 }, { "epoch": 1.02, "learning_rate": 3.3838919706518046e-05, "loss": 3.6004, "step": 987136 }, { "epoch": 1.02, "learning_rate": 3.3830550137811255e-05, "loss": 3.5736, "step": 987648 }, { "epoch": 1.02, "learning_rate": 3.3822164190300735e-05, "loss": 3.578, "step": 988160 }, { "epoch": 1.02, "learning_rate": 3.3813778242790215e-05, "loss": 3.5819, "step": 988672 }, { "epoch": 1.02, "learning_rate": 3.3805392295279695e-05, "loss": 3.58, "step": 989184 }, { "epoch": 1.02, "learning_rate": 3.379702272657291e-05, "loss": 3.5742, "step": 989696 }, { "epoch": 1.02, "learning_rate": 3.378863677906239e-05, "loss": 3.5885, "step": 990208 }, { "epoch": 1.02, "learning_rate": 3.378025083155187e-05, "loss": 3.5764, "step": 990720 }, { "epoch": 1.02, "learning_rate": 3.377186488404135e-05, "loss": 3.5869, "step": 991232 }, { "epoch": 1.02, "learning_rate": 3.376349531533456e-05, "loss": 3.5781, "step": 991744 }, { "epoch": 1.03, "eval_loss": 3.8423147201538086, "eval_runtime": 307.9958, "eval_samples_per_second": 1238.949, "eval_steps_per_second": 38.718, "step": 992160 }, { "epoch": 0.0, "learning_rate": 3.375510936782404e-05, "loss": 3.5785, "step": 992256 }, { "epoch": 0.0, "learning_rate": 3.374672342031352e-05, "loss": 3.5644, "step": 992768 }, { "epoch": 0.0, "learning_rate": 3.3738337472803e-05, "loss": 3.582, "step": 993280 }, { "epoch": 0.0, "learning_rate": 3.372995152529248e-05, "loss": 3.5831, "step": 993792 }, { "epoch": 0.0, "learning_rate": 3.372158195658569e-05, "loss": 3.5824, "step": 994304 }, { "epoch": 0.0, "learning_rate": 3.371319600907517e-05, "loss": 3.5747, "step": 994816 }, { "epoch": 0.0, "learning_rate": 3.370481006156465e-05, "loss": 3.5787, "step": 995328 }, { "epoch": 0.0, "learning_rate": 3.369642411405413e-05, "loss": 3.5738, "step": 995840 }, { "epoch": 0.0, "learning_rate": 3.368803816654361e-05, "loss": 3.5724, "step": 996352 }, { "epoch": 0.0, "learning_rate": 3.3679668597836824e-05, "loss": 3.5767, "step": 996864 }, { "epoch": 0.0, "learning_rate": 3.3671282650326304e-05, "loss": 3.5752, "step": 997376 }, { "epoch": 0.0, "learning_rate": 3.3662896702815784e-05, "loss": 3.5851, "step": 997888 }, { "epoch": 0.0, "learning_rate": 3.3654527134108993e-05, "loss": 3.5917, "step": 998400 }, { "epoch": 0.0, "learning_rate": 3.3646141186598473e-05, "loss": 3.5671, "step": 998912 }, { "epoch": 0.0, "learning_rate": 3.363775523908795e-05, "loss": 3.5708, "step": 999424 }, { "epoch": 0.0, "learning_rate": 3.3629369291577427e-05, "loss": 3.5647, "step": 999936 }, { "epoch": 0.0, "learning_rate": 3.3620983344066906e-05, "loss": 3.5703, "step": 1000448 }, { "epoch": 0.0, "learning_rate": 3.3612597396556386e-05, "loss": 3.5763, "step": 1000960 }, { "epoch": 0.0, "learning_rate": 3.3604211449045866e-05, "loss": 3.568, "step": 1001472 }, { "epoch": 0.0, "learning_rate": 3.3595825501535346e-05, "loss": 3.5735, "step": 1001984 }, { "epoch": 0.0, "learning_rate": 3.358745593282856e-05, "loss": 3.5881, "step": 1002496 }, { "epoch": 0.0, "learning_rate": 3.357906998531804e-05, "loss": 3.5777, "step": 1003008 }, { "epoch": 0.0, "learning_rate": 3.357068403780752e-05, "loss": 3.5856, "step": 1003520 }, { "epoch": 0.0, "learning_rate": 3.3562298090297e-05, "loss": 3.5846, "step": 1004032 }, { "epoch": 0.0, "learning_rate": 3.355391214278648e-05, "loss": 3.5733, "step": 1004544 }, { "epoch": 0.0, "learning_rate": 3.354554257407969e-05, "loss": 3.5781, "step": 1005056 }, { "epoch": 0.0, "learning_rate": 3.353715662656917e-05, "loss": 3.5674, "step": 1005568 }, { "epoch": 0.0, "learning_rate": 3.352877067905865e-05, "loss": 3.5778, "step": 1006080 }, { "epoch": 0.0, "learning_rate": 3.352038473154813e-05, "loss": 3.5679, "step": 1006592 }, { "epoch": 0.0, "learning_rate": 3.351201516284134e-05, "loss": 3.5704, "step": 1007104 }, { "epoch": 0.01, "learning_rate": 3.350362921533082e-05, "loss": 3.5776, "step": 1007616 }, { "epoch": 0.01, "learning_rate": 3.34952432678203e-05, "loss": 3.5747, "step": 1008128 }, { "epoch": 0.01, "learning_rate": 3.348685732030979e-05, "loss": 3.5797, "step": 1008640 }, { "epoch": 0.01, "learning_rate": 3.347847137279927e-05, "loss": 3.5737, "step": 1009152 }, { "epoch": 0.01, "learning_rate": 3.347008542528875e-05, "loss": 3.5718, "step": 1009664 }, { "epoch": 0.01, "learning_rate": 3.346169947777823e-05, "loss": 3.5763, "step": 1010176 }, { "epoch": 0.01, "learning_rate": 3.3453329909071436e-05, "loss": 3.5855, "step": 1010688 }, { "epoch": 0.01, "learning_rate": 3.3444943961560916e-05, "loss": 3.557, "step": 1011200 }, { "epoch": 0.01, "learning_rate": 3.3436558014050396e-05, "loss": 3.5727, "step": 1011712 }, { "epoch": 0.01, "learning_rate": 3.3428172066539876e-05, "loss": 3.5687, "step": 1012224 }, { "epoch": 0.01, "learning_rate": 3.3419786119029356e-05, "loss": 3.5628, "step": 1012736 }, { "epoch": 0.01, "learning_rate": 3.3411416550322565e-05, "loss": 3.5657, "step": 1013248 }, { "epoch": 0.01, "learning_rate": 3.3403030602812045e-05, "loss": 3.5817, "step": 1013760 }, { "epoch": 0.01, "learning_rate": 3.3394644655301525e-05, "loss": 3.5776, "step": 1014272 }, { "epoch": 0.01, "learning_rate": 3.3386258707791004e-05, "loss": 3.5756, "step": 1014784 }, { "epoch": 0.01, "learning_rate": 3.337788913908422e-05, "loss": 3.5791, "step": 1015296 }, { "epoch": 0.01, "learning_rate": 3.33695031915737e-05, "loss": 3.5761, "step": 1015808 }, { "epoch": 0.01, "learning_rate": 3.336111724406318e-05, "loss": 3.5696, "step": 1016320 }, { "epoch": 0.01, "learning_rate": 3.335273129655266e-05, "loss": 3.5533, "step": 1016832 }, { "epoch": 0.01, "learning_rate": 3.334436172784587e-05, "loss": 3.5792, "step": 1017344 }, { "epoch": 0.01, "learning_rate": 3.333597578033535e-05, "loss": 3.5678, "step": 1017856 }, { "epoch": 0.01, "learning_rate": 3.332758983282483e-05, "loss": 3.5725, "step": 1018368 }, { "epoch": 0.01, "learning_rate": 3.331920388531431e-05, "loss": 3.5664, "step": 1018880 }, { "epoch": 0.01, "learning_rate": 3.331083431660752e-05, "loss": 3.5634, "step": 1019392 }, { "epoch": 0.01, "learning_rate": 3.3302448369097e-05, "loss": 3.5625, "step": 1019904 }, { "epoch": 0.01, "learning_rate": 3.329406242158648e-05, "loss": 3.5604, "step": 1020416 }, { "epoch": 0.01, "learning_rate": 3.328567647407596e-05, "loss": 3.5773, "step": 1020928 }, { "epoch": 0.01, "learning_rate": 3.3277306905369174e-05, "loss": 3.5593, "step": 1021440 }, { "epoch": 0.01, "learning_rate": 3.3268920957858654e-05, "loss": 3.5768, "step": 1021952 }, { "epoch": 0.01, "learning_rate": 3.3260535010348134e-05, "loss": 3.5745, "step": 1022464 }, { "epoch": 0.01, "learning_rate": 3.3252149062837614e-05, "loss": 3.5539, "step": 1022976 }, { "epoch": 0.01, "learning_rate": 3.3243763115327094e-05, "loss": 3.5792, "step": 1023488 }, { "epoch": 0.01, "learning_rate": 3.32353935466203e-05, "loss": 3.5555, "step": 1024000 }, { "epoch": 0.01, "learning_rate": 3.322700759910978e-05, "loss": 3.5651, "step": 1024512 }, { "epoch": 0.01, "learning_rate": 3.321862165159926e-05, "loss": 3.562, "step": 1025024 }, { "epoch": 0.01, "learning_rate": 3.3210235704088736e-05, "loss": 3.5801, "step": 1025536 }, { "epoch": 0.01, "learning_rate": 3.320186613538195e-05, "loss": 3.5622, "step": 1026048 }, { "epoch": 0.01, "learning_rate": 3.319348018787143e-05, "loss": 3.5603, "step": 1026560 }, { "epoch": 0.01, "learning_rate": 3.318509424036091e-05, "loss": 3.5473, "step": 1027072 }, { "epoch": 0.01, "learning_rate": 3.317670829285039e-05, "loss": 3.5632, "step": 1027584 }, { "epoch": 0.01, "learning_rate": 3.316833872414361e-05, "loss": 3.5768, "step": 1028096 }, { "epoch": 0.01, "learning_rate": 3.315995277663309e-05, "loss": 3.5769, "step": 1028608 }, { "epoch": 0.01, "learning_rate": 3.315156682912257e-05, "loss": 3.5689, "step": 1029120 }, { "epoch": 0.01, "learning_rate": 3.314318088161204e-05, "loss": 3.5747, "step": 1029632 }, { "epoch": 0.01, "learning_rate": 3.313481131290526e-05, "loss": 3.5812, "step": 1030144 }, { "epoch": 0.01, "learning_rate": 3.3126425365394737e-05, "loss": 3.565, "step": 1030656 }, { "epoch": 0.01, "learning_rate": 3.311803941788421e-05, "loss": 3.5734, "step": 1031168 }, { "epoch": 0.01, "learning_rate": 3.310965347037369e-05, "loss": 3.5677, "step": 1031680 }, { "epoch": 0.01, "learning_rate": 3.3101283901666906e-05, "loss": 3.5629, "step": 1032192 }, { "epoch": 0.01, "learning_rate": 3.3092897954156386e-05, "loss": 3.5651, "step": 1032704 }, { "epoch": 0.01, "learning_rate": 3.3084512006645866e-05, "loss": 3.5683, "step": 1033216 }, { "epoch": 0.01, "learning_rate": 3.3076126059135345e-05, "loss": 3.5761, "step": 1033728 }, { "epoch": 0.01, "learning_rate": 3.306775649042856e-05, "loss": 3.5764, "step": 1034240 }, { "epoch": 0.01, "learning_rate": 3.305937054291804e-05, "loss": 3.574, "step": 1034752 }, { "epoch": 0.01, "learning_rate": 3.3050984595407514e-05, "loss": 3.5575, "step": 1035264 }, { "epoch": 0.01, "learning_rate": 3.3042598647896994e-05, "loss": 3.5696, "step": 1035776 }, { "epoch": 0.01, "learning_rate": 3.3034212700386474e-05, "loss": 3.5698, "step": 1036288 }, { "epoch": 0.01, "learning_rate": 3.3025843131679683e-05, "loss": 3.5609, "step": 1036800 }, { "epoch": 0.01, "learning_rate": 3.3017457184169163e-05, "loss": 3.562, "step": 1037312 }, { "epoch": 0.01, "learning_rate": 3.300907123665864e-05, "loss": 3.5717, "step": 1037824 }, { "epoch": 0.02, "learning_rate": 3.300068528914812e-05, "loss": 3.5667, "step": 1038336 }, { "epoch": 0.02, "learning_rate": 3.29922993416376e-05, "loss": 3.5665, "step": 1038848 }, { "epoch": 0.02, "learning_rate": 3.298392977293082e-05, "loss": 3.5626, "step": 1039360 }, { "epoch": 0.02, "learning_rate": 3.29755438254203e-05, "loss": 3.5744, "step": 1039872 }, { "epoch": 0.02, "learning_rate": 3.296715787790978e-05, "loss": 3.5744, "step": 1040384 }, { "epoch": 0.02, "learning_rate": 3.295877193039926e-05, "loss": 3.5717, "step": 1040896 }, { "epoch": 0.02, "learning_rate": 3.295040236169247e-05, "loss": 3.5529, "step": 1041408 }, { "epoch": 0.02, "learning_rate": 3.294201641418195e-05, "loss": 3.5702, "step": 1041920 }, { "epoch": 0.02, "learning_rate": 3.293363046667143e-05, "loss": 3.5623, "step": 1042432 }, { "epoch": 0.02, "learning_rate": 3.292524451916091e-05, "loss": 3.5684, "step": 1042944 }, { "epoch": 0.02, "learning_rate": 3.291685857165039e-05, "loss": 3.581, "step": 1043456 }, { "epoch": 0.02, "learning_rate": 3.29084890029436e-05, "loss": 3.5605, "step": 1043968 }, { "epoch": 0.02, "learning_rate": 3.290010305543308e-05, "loss": 3.5622, "step": 1044480 }, { "epoch": 0.02, "learning_rate": 3.289171710792256e-05, "loss": 3.5608, "step": 1044992 }, { "epoch": 0.02, "learning_rate": 3.288333116041204e-05, "loss": 3.5651, "step": 1045504 }, { "epoch": 0.02, "learning_rate": 3.287496159170525e-05, "loss": 3.5537, "step": 1046016 }, { "epoch": 0.02, "learning_rate": 3.286657564419473e-05, "loss": 3.5609, "step": 1046528 }, { "epoch": 0.02, "learning_rate": 3.285818969668421e-05, "loss": 3.562, "step": 1047040 }, { "epoch": 0.02, "learning_rate": 3.284980374917369e-05, "loss": 3.5623, "step": 1047552 }, { "epoch": 0.02, "learning_rate": 3.284141780166317e-05, "loss": 3.5574, "step": 1048064 }, { "epoch": 0.02, "learning_rate": 3.283304823295638e-05, "loss": 3.5599, "step": 1048576 }, { "epoch": 0.02, "learning_rate": 3.282466228544586e-05, "loss": 3.557, "step": 1049088 }, { "epoch": 0.02, "learning_rate": 3.281627633793534e-05, "loss": 3.5786, "step": 1049600 }, { "epoch": 0.02, "learning_rate": 3.280789039042482e-05, "loss": 3.5622, "step": 1050112 }, { "epoch": 0.02, "learning_rate": 3.279952082171803e-05, "loss": 3.5706, "step": 1050624 }, { "epoch": 0.02, "learning_rate": 3.279113487420751e-05, "loss": 3.5734, "step": 1051136 }, { "epoch": 0.02, "learning_rate": 3.278274892669699e-05, "loss": 3.5824, "step": 1051648 }, { "epoch": 0.02, "learning_rate": 3.277436297918647e-05, "loss": 3.564, "step": 1052160 }, { "epoch": 0.02, "learning_rate": 3.2765993410479686e-05, "loss": 3.5643, "step": 1052672 }, { "epoch": 0.02, "learning_rate": 3.2757607462969166e-05, "loss": 3.5654, "step": 1053184 }, { "epoch": 0.02, "learning_rate": 3.2749221515458646e-05, "loss": 3.5648, "step": 1053696 }, { "epoch": 0.02, "learning_rate": 3.2740835567948126e-05, "loss": 3.561, "step": 1054208 }, { "epoch": 0.02, "learning_rate": 3.2732465999241335e-05, "loss": 3.5653, "step": 1054720 }, { "epoch": 0.02, "learning_rate": 3.2724080051730815e-05, "loss": 3.564, "step": 1055232 }, { "epoch": 0.02, "learning_rate": 3.2715694104220295e-05, "loss": 3.5728, "step": 1055744 }, { "epoch": 0.02, "learning_rate": 3.2707308156709775e-05, "loss": 3.5633, "step": 1056256 }, { "epoch": 0.02, "learning_rate": 3.2698922209199255e-05, "loss": 3.5607, "step": 1056768 }, { "epoch": 0.02, "learning_rate": 3.2690552640492464e-05, "loss": 3.5671, "step": 1057280 }, { "epoch": 0.02, "learning_rate": 3.2682166692981944e-05, "loss": 3.5617, "step": 1057792 }, { "epoch": 0.02, "learning_rate": 3.2673780745471424e-05, "loss": 3.5698, "step": 1058304 }, { "epoch": 0.02, "learning_rate": 3.266539479796091e-05, "loss": 3.5642, "step": 1058816 }, { "epoch": 0.02, "learning_rate": 3.265702522925412e-05, "loss": 3.5725, "step": 1059328 }, { "epoch": 0.02, "learning_rate": 3.26486392817436e-05, "loss": 3.5601, "step": 1059840 }, { "epoch": 0.02, "learning_rate": 3.264025333423308e-05, "loss": 3.5634, "step": 1060352 }, { "epoch": 0.02, "learning_rate": 3.263186738672256e-05, "loss": 3.5694, "step": 1060864 }, { "epoch": 0.02, "learning_rate": 3.262349781801577e-05, "loss": 3.5631, "step": 1061376 }, { "epoch": 0.02, "learning_rate": 3.261511187050525e-05, "loss": 3.5635, "step": 1061888 }, { "epoch": 0.02, "learning_rate": 3.260672592299473e-05, "loss": 3.5635, "step": 1062400 }, { "epoch": 0.02, "learning_rate": 3.259833997548421e-05, "loss": 3.5723, "step": 1062912 }, { "epoch": 0.02, "learning_rate": 3.258997040677742e-05, "loss": 3.5832, "step": 1063424 }, { "epoch": 0.02, "learning_rate": 3.25815844592669e-05, "loss": 3.5598, "step": 1063936 }, { "epoch": 0.02, "learning_rate": 3.257319851175638e-05, "loss": 3.5581, "step": 1064448 }, { "epoch": 0.02, "learning_rate": 3.2564812564245865e-05, "loss": 3.5615, "step": 1064960 }, { "epoch": 0.02, "learning_rate": 3.2556442995539074e-05, "loss": 3.5643, "step": 1065472 }, { "epoch": 0.02, "learning_rate": 3.2548057048028554e-05, "loss": 3.5565, "step": 1065984 }, { "epoch": 0.02, "learning_rate": 3.2539671100518034e-05, "loss": 3.5735, "step": 1066496 }, { "epoch": 0.02, "learning_rate": 3.2531285153007514e-05, "loss": 3.5629, "step": 1067008 }, { "epoch": 0.02, "learning_rate": 3.252291558430072e-05, "loss": 3.5706, "step": 1067520 }, { "epoch": 0.02, "learning_rate": 3.25145296367902e-05, "loss": 3.5567, "step": 1068032 }, { "epoch": 0.03, "eval_loss": 3.8440983295440674, "eval_runtime": 310.468, "eval_samples_per_second": 1229.083, "eval_steps_per_second": 38.41, "step": 1068480 }, { "epoch": 1.0, "learning_rate": 3.250614368927968e-05, "loss": 3.565, "step": 1068544 }, { "epoch": 1.0, "learning_rate": 3.249775774176916e-05, "loss": 3.5524, "step": 1069056 }, { "epoch": 1.0, "learning_rate": 3.248938817306237e-05, "loss": 3.5633, "step": 1069568 }, { "epoch": 1.0, "learning_rate": 3.248100222555185e-05, "loss": 3.5651, "step": 1070080 }, { "epoch": 1.0, "learning_rate": 3.247261627804133e-05, "loss": 3.568, "step": 1070592 }, { "epoch": 1.0, "learning_rate": 3.246423033053081e-05, "loss": 3.5599, "step": 1071104 }, { "epoch": 1.0, "learning_rate": 3.245586076182403e-05, "loss": 3.5586, "step": 1071616 }, { "epoch": 1.0, "learning_rate": 3.244747481431351e-05, "loss": 3.5568, "step": 1072128 }, { "epoch": 1.0, "learning_rate": 3.243908886680299e-05, "loss": 3.5566, "step": 1072640 }, { "epoch": 1.0, "learning_rate": 3.243070291929247e-05, "loss": 3.5619, "step": 1073152 }, { "epoch": 1.0, "learning_rate": 3.2422333350585676e-05, "loss": 3.5584, "step": 1073664 }, { "epoch": 1.0, "learning_rate": 3.2413947403075156e-05, "loss": 3.5707, "step": 1074176 }, { "epoch": 1.0, "learning_rate": 3.2405577834368365e-05, "loss": 3.5753, "step": 1074688 }, { "epoch": 1.0, "learning_rate": 3.2397191886857845e-05, "loss": 3.5514, "step": 1075200 }, { "epoch": 1.0, "learning_rate": 3.2388805939347325e-05, "loss": 3.5591, "step": 1075712 }, { "epoch": 1.0, "learning_rate": 3.2380419991836805e-05, "loss": 3.544, "step": 1076224 }, { "epoch": 1.0, "learning_rate": 3.2372034044326285e-05, "loss": 3.5561, "step": 1076736 }, { "epoch": 1.0, "learning_rate": 3.2363648096815765e-05, "loss": 3.5567, "step": 1077248 }, { "epoch": 1.0, "learning_rate": 3.2355262149305245e-05, "loss": 3.5563, "step": 1077760 }, { "epoch": 1.0, "learning_rate": 3.2346876201794725e-05, "loss": 3.5542, "step": 1078272 }, { "epoch": 1.0, "learning_rate": 3.233850663308794e-05, "loss": 3.5742, "step": 1078784 }, { "epoch": 1.0, "learning_rate": 3.2330120685577414e-05, "loss": 3.5608, "step": 1079296 }, { "epoch": 1.0, "learning_rate": 3.2321734738066894e-05, "loss": 3.567, "step": 1079808 }, { "epoch": 1.0, "learning_rate": 3.2313348790556374e-05, "loss": 3.5666, "step": 1080320 }, { "epoch": 1.0, "learning_rate": 3.2304962843045854e-05, "loss": 3.5633, "step": 1080832 }, { "epoch": 1.0, "learning_rate": 3.229659327433906e-05, "loss": 3.5562, "step": 1081344 }, { "epoch": 1.0, "learning_rate": 3.228820732682854e-05, "loss": 3.5545, "step": 1081856 }, { "epoch": 1.0, "learning_rate": 3.227982137931802e-05, "loss": 3.5612, "step": 1082368 }, { "epoch": 1.0, "learning_rate": 3.227145181061124e-05, "loss": 3.5516, "step": 1082880 }, { "epoch": 1.0, "learning_rate": 3.226306586310072e-05, "loss": 3.554, "step": 1083392 }, { "epoch": 1.01, "learning_rate": 3.22546799155902e-05, "loss": 3.5613, "step": 1083904 }, { "epoch": 1.01, "learning_rate": 3.224629396807968e-05, "loss": 3.5536, "step": 1084416 }, { "epoch": 1.01, "learning_rate": 3.223792439937289e-05, "loss": 3.566, "step": 1084928 }, { "epoch": 1.01, "learning_rate": 3.222953845186237e-05, "loss": 3.5551, "step": 1085440 }, { "epoch": 1.01, "learning_rate": 3.222115250435185e-05, "loss": 3.5572, "step": 1085952 }, { "epoch": 1.01, "learning_rate": 3.221276655684133e-05, "loss": 3.566, "step": 1086464 }, { "epoch": 1.01, "learning_rate": 3.220439698813454e-05, "loss": 3.5638, "step": 1086976 }, { "epoch": 1.01, "learning_rate": 3.219601104062402e-05, "loss": 3.542, "step": 1087488 }, { "epoch": 1.01, "learning_rate": 3.21876250931135e-05, "loss": 3.5559, "step": 1088000 }, { "epoch": 1.01, "learning_rate": 3.217923914560298e-05, "loss": 3.5525, "step": 1088512 }, { "epoch": 1.01, "learning_rate": 3.217085319809246e-05, "loss": 3.5429, "step": 1089024 }, { "epoch": 1.01, "learning_rate": 3.216248362938567e-05, "loss": 3.5555, "step": 1089536 }, { "epoch": 1.01, "learning_rate": 3.215409768187515e-05, "loss": 3.5682, "step": 1090048 }, { "epoch": 1.01, "learning_rate": 3.214571173436463e-05, "loss": 3.5584, "step": 1090560 }, { "epoch": 1.01, "learning_rate": 3.213732578685411e-05, "loss": 3.5615, "step": 1091072 }, { "epoch": 1.01, "learning_rate": 3.212895621814732e-05, "loss": 3.5625, "step": 1091584 }, { "epoch": 1.01, "learning_rate": 3.21205702706368e-05, "loss": 3.5608, "step": 1092096 }, { "epoch": 1.01, "learning_rate": 3.211218432312628e-05, "loss": 3.5537, "step": 1092608 }, { "epoch": 1.01, "learning_rate": 3.210379837561576e-05, "loss": 3.5404, "step": 1093120 }, { "epoch": 1.01, "learning_rate": 3.209542880690897e-05, "loss": 3.559, "step": 1093632 }, { "epoch": 1.01, "learning_rate": 3.208704285939845e-05, "loss": 3.5555, "step": 1094144 }, { "epoch": 1.01, "learning_rate": 3.207865691188793e-05, "loss": 3.5566, "step": 1094656 }, { "epoch": 1.01, "learning_rate": 3.207027096437741e-05, "loss": 3.5508, "step": 1095168 }, { "epoch": 1.01, "learning_rate": 3.2061901395670626e-05, "loss": 3.5492, "step": 1095680 }, { "epoch": 1.01, "learning_rate": 3.2053515448160106e-05, "loss": 3.5429, "step": 1096192 }, { "epoch": 1.01, "learning_rate": 3.2045129500649586e-05, "loss": 3.5473, "step": 1096704 }, { "epoch": 1.01, "learning_rate": 3.2036743553139066e-05, "loss": 3.565, "step": 1097216 }, { "epoch": 1.01, "learning_rate": 3.2028373984432275e-05, "loss": 3.541, "step": 1097728 }, { "epoch": 1.01, "learning_rate": 3.2019988036921755e-05, "loss": 3.5607, "step": 1098240 }, { "epoch": 1.01, "learning_rate": 3.2011602089411235e-05, "loss": 3.5551, "step": 1098752 }, { "epoch": 1.01, "learning_rate": 3.2003216141900715e-05, "loss": 3.5417, "step": 1099264 }, { "epoch": 1.01, "learning_rate": 3.1994846573193924e-05, "loss": 3.5564, "step": 1099776 }, { "epoch": 1.01, "learning_rate": 3.1986460625683404e-05, "loss": 3.5451, "step": 1100288 }, { "epoch": 1.01, "learning_rate": 3.1978074678172884e-05, "loss": 3.5507, "step": 1100800 }, { "epoch": 1.01, "learning_rate": 3.1969688730662364e-05, "loss": 3.5423, "step": 1101312 }, { "epoch": 1.01, "learning_rate": 3.196131916195558e-05, "loss": 3.5652, "step": 1101824 }, { "epoch": 1.01, "learning_rate": 3.195293321444506e-05, "loss": 3.5512, "step": 1102336 }, { "epoch": 1.01, "learning_rate": 3.194454726693454e-05, "loss": 3.5368, "step": 1102848 }, { "epoch": 1.01, "learning_rate": 3.193616131942402e-05, "loss": 3.5335, "step": 1103360 }, { "epoch": 1.01, "learning_rate": 3.192779175071723e-05, "loss": 3.5467, "step": 1103872 }, { "epoch": 1.01, "learning_rate": 3.191940580320671e-05, "loss": 3.5558, "step": 1104384 }, { "epoch": 1.01, "learning_rate": 3.191101985569619e-05, "loss": 3.5645, "step": 1104896 }, { "epoch": 1.01, "learning_rate": 3.190263390818567e-05, "loss": 3.5515, "step": 1105408 }, { "epoch": 1.01, "learning_rate": 3.189426433947888e-05, "loss": 3.5597, "step": 1105920 }, { "epoch": 1.01, "learning_rate": 3.188587839196836e-05, "loss": 3.5604, "step": 1106432 }, { "epoch": 1.01, "learning_rate": 3.187749244445784e-05, "loss": 3.5523, "step": 1106944 }, { "epoch": 1.01, "learning_rate": 3.186910649694732e-05, "loss": 3.5538, "step": 1107456 }, { "epoch": 1.01, "learning_rate": 3.1860736928240533e-05, "loss": 3.5523, "step": 1107968 }, { "epoch": 1.01, "learning_rate": 3.1852350980730013e-05, "loss": 3.5508, "step": 1108480 }, { "epoch": 1.01, "learning_rate": 3.1843965033219493e-05, "loss": 3.5478, "step": 1108992 }, { "epoch": 1.01, "learning_rate": 3.183557908570897e-05, "loss": 3.5525, "step": 1109504 }, { "epoch": 1.01, "learning_rate": 3.182719313819845e-05, "loss": 3.562, "step": 1110016 }, { "epoch": 1.01, "learning_rate": 3.181882356949166e-05, "loss": 3.5635, "step": 1110528 }, { "epoch": 1.01, "learning_rate": 3.181043762198114e-05, "loss": 3.5552, "step": 1111040 }, { "epoch": 1.01, "learning_rate": 3.180205167447062e-05, "loss": 3.5399, "step": 1111552 }, { "epoch": 1.01, "learning_rate": 3.17936657269601e-05, "loss": 3.5531, "step": 1112064 }, { "epoch": 1.01, "learning_rate": 3.178529615825331e-05, "loss": 3.5526, "step": 1112576 }, { "epoch": 1.01, "learning_rate": 3.177691021074279e-05, "loss": 3.5493, "step": 1113088 }, { "epoch": 1.01, "learning_rate": 3.176852426323227e-05, "loss": 3.5464, "step": 1113600 }, { "epoch": 1.01, "learning_rate": 3.176013831572176e-05, "loss": 3.5558, "step": 1114112 }, { "epoch": 1.02, "learning_rate": 3.175176874701497e-05, "loss": 3.5551, "step": 1114624 }, { "epoch": 1.02, "learning_rate": 3.174338279950445e-05, "loss": 3.5443, "step": 1115136 }, { "epoch": 1.02, "learning_rate": 3.173499685199393e-05, "loss": 3.5506, "step": 1115648 }, { "epoch": 1.02, "learning_rate": 3.172661090448341e-05, "loss": 3.5555, "step": 1116160 }, { "epoch": 1.02, "learning_rate": 3.1718241335776616e-05, "loss": 3.5556, "step": 1116672 }, { "epoch": 1.02, "learning_rate": 3.1709855388266096e-05, "loss": 3.5613, "step": 1117184 }, { "epoch": 1.02, "learning_rate": 3.1701469440755576e-05, "loss": 3.5376, "step": 1117696 }, { "epoch": 1.02, "learning_rate": 3.1693083493245056e-05, "loss": 3.5547, "step": 1118208 }, { "epoch": 1.02, "learning_rate": 3.1684697545734536e-05, "loss": 3.5524, "step": 1118720 }, { "epoch": 1.02, "learning_rate": 3.1676327977027745e-05, "loss": 3.5474, "step": 1119232 }, { "epoch": 1.02, "learning_rate": 3.1667942029517225e-05, "loss": 3.5683, "step": 1119744 }, { "epoch": 1.02, "learning_rate": 3.165955608200671e-05, "loss": 3.5487, "step": 1120256 }, { "epoch": 1.02, "learning_rate": 3.165117013449619e-05, "loss": 3.5429, "step": 1120768 }, { "epoch": 1.02, "learning_rate": 3.16428005657894e-05, "loss": 3.5507, "step": 1121280 }, { "epoch": 1.02, "learning_rate": 3.163441461827888e-05, "loss": 3.5501, "step": 1121792 }, { "epoch": 1.02, "learning_rate": 3.162602867076836e-05, "loss": 3.5362, "step": 1122304 }, { "epoch": 1.02, "learning_rate": 3.161764272325784e-05, "loss": 3.5467, "step": 1122816 }, { "epoch": 1.02, "learning_rate": 3.1609256775747314e-05, "loss": 3.547, "step": 1123328 }, { "epoch": 1.02, "learning_rate": 3.160088720704053e-05, "loss": 3.5432, "step": 1123840 }, { "epoch": 1.02, "learning_rate": 3.159250125953001e-05, "loss": 3.5392, "step": 1124352 }, { "epoch": 1.02, "learning_rate": 3.158411531201949e-05, "loss": 3.5497, "step": 1124864 }, { "epoch": 1.02, "learning_rate": 3.157572936450896e-05, "loss": 3.5384, "step": 1125376 }, { "epoch": 1.02, "learning_rate": 3.156735979580218e-05, "loss": 3.5625, "step": 1125888 }, { "epoch": 1.02, "learning_rate": 3.155897384829166e-05, "loss": 3.5468, "step": 1126400 }, { "epoch": 1.02, "learning_rate": 3.155058790078114e-05, "loss": 3.5544, "step": 1126912 }, { "epoch": 1.02, "learning_rate": 3.154220195327062e-05, "loss": 3.5565, "step": 1127424 }, { "epoch": 1.02, "learning_rate": 3.1533832384563834e-05, "loss": 3.5722, "step": 1127936 }, { "epoch": 1.02, "learning_rate": 3.1525446437053314e-05, "loss": 3.5481, "step": 1128448 }, { "epoch": 1.02, "learning_rate": 3.151706048954279e-05, "loss": 3.5471, "step": 1128960 }, { "epoch": 1.02, "learning_rate": 3.150867454203227e-05, "loss": 3.5523, "step": 1129472 }, { "epoch": 1.02, "learning_rate": 3.150030497332548e-05, "loss": 3.5465, "step": 1129984 }, { "epoch": 1.02, "learning_rate": 3.149191902581496e-05, "loss": 3.5492, "step": 1130496 }, { "epoch": 1.02, "learning_rate": 3.1483533078304436e-05, "loss": 3.5498, "step": 1131008 }, { "epoch": 1.02, "learning_rate": 3.1475147130793916e-05, "loss": 3.5491, "step": 1131520 }, { "epoch": 1.02, "learning_rate": 3.146677756208713e-05, "loss": 3.559, "step": 1132032 }, { "epoch": 1.02, "learning_rate": 3.145839161457661e-05, "loss": 3.5491, "step": 1132544 }, { "epoch": 1.02, "learning_rate": 3.145000566706609e-05, "loss": 3.5463, "step": 1133056 }, { "epoch": 1.02, "learning_rate": 3.144161971955557e-05, "loss": 3.5496, "step": 1133568 }, { "epoch": 1.02, "learning_rate": 3.143325015084879e-05, "loss": 3.5535, "step": 1134080 }, { "epoch": 1.02, "learning_rate": 3.142486420333826e-05, "loss": 3.5489, "step": 1134592 }, { "epoch": 1.02, "learning_rate": 3.141647825582774e-05, "loss": 3.5515, "step": 1135104 }, { "epoch": 1.02, "learning_rate": 3.140809230831722e-05, "loss": 3.5561, "step": 1135616 }, { "epoch": 1.02, "learning_rate": 3.139972273961044e-05, "loss": 3.5429, "step": 1136128 }, { "epoch": 1.02, "learning_rate": 3.139133679209991e-05, "loss": 3.5457, "step": 1136640 }, { "epoch": 1.02, "learning_rate": 3.138295084458939e-05, "loss": 3.5522, "step": 1137152 }, { "epoch": 1.02, "learning_rate": 3.137456489707887e-05, "loss": 3.5527, "step": 1137664 }, { "epoch": 1.02, "learning_rate": 3.1366195328372086e-05, "loss": 3.5441, "step": 1138176 }, { "epoch": 1.02, "learning_rate": 3.1357809380861566e-05, "loss": 3.5512, "step": 1138688 }, { "epoch": 1.02, "learning_rate": 3.1349423433351046e-05, "loss": 3.5567, "step": 1139200 }, { "epoch": 1.02, "learning_rate": 3.1341037485840526e-05, "loss": 3.561, "step": 1139712 }, { "epoch": 1.02, "learning_rate": 3.1332667917133735e-05, "loss": 3.5494, "step": 1140224 }, { "epoch": 1.02, "learning_rate": 3.1324281969623215e-05, "loss": 3.548, "step": 1140736 }, { "epoch": 1.02, "learning_rate": 3.1315896022112695e-05, "loss": 3.5433, "step": 1141248 }, { "epoch": 1.02, "learning_rate": 3.1307510074602175e-05, "loss": 3.5529, "step": 1141760 }, { "epoch": 1.02, "learning_rate": 3.1299140505895384e-05, "loss": 3.5399, "step": 1142272 }, { "epoch": 1.02, "learning_rate": 3.1290754558384864e-05, "loss": 3.5594, "step": 1142784 }, { "epoch": 1.02, "learning_rate": 3.1282368610874344e-05, "loss": 3.5459, "step": 1143296 }, { "epoch": 1.02, "learning_rate": 3.1273982663363824e-05, "loss": 3.5535, "step": 1143808 }, { "epoch": 1.02, "learning_rate": 3.126561309465704e-05, "loss": 3.5429, "step": 1144320 }, { "epoch": 1.03, "eval_loss": 3.8441402912139893, "eval_runtime": 307.0374, "eval_samples_per_second": 1242.816, "eval_steps_per_second": 38.839, "step": 1144800 }, { "epoch": 0.0, "learning_rate": 3.125722714714652e-05, "loss": 3.4977, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.1248841199636e-05, "loss": 3.5387, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.124045525212548e-05, "loss": 3.5483, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.123206930461496e-05, "loss": 3.5514, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.122368335710444e-05, "loss": 3.5484, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.121531378839765e-05, "loss": 3.5498, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.120692784088713e-05, "loss": 3.5415, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.119854189337661e-05, "loss": 3.5426, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.119017232466982e-05, "loss": 3.5433, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.11817863771593e-05, "loss": 3.5464, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.117340042964878e-05, "loss": 3.5432, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.116501448213826e-05, "loss": 3.5557, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.115664491343147e-05, "loss": 3.5573, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.114825896592095e-05, "loss": 3.535, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.113987301841043e-05, "loss": 3.5448, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.113148707089991e-05, "loss": 3.5309, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.112310112338939e-05, "loss": 3.5459, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.11147315546826e-05, "loss": 3.5362, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.110634560717208e-05, "loss": 3.5434, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.109795965966156e-05, "loss": 3.5419, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.108957371215104e-05, "loss": 3.5526, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.108120414344425e-05, "loss": 3.5474, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.107281819593373e-05, "loss": 3.5495, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.106443224842321e-05, "loss": 3.5528, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.10560463009127e-05, "loss": 3.5498, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104767673220591e-05, "loss": 3.5413, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.103929078469539e-05, "loss": 3.5372, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.103090483718487e-05, "loss": 3.5451, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102251888967435e-05, "loss": 3.535, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.1014149320967556e-05, "loss": 3.5408, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.1005763373457036e-05, "loss": 3.5449, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.0997377425946516e-05, "loss": 3.541, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.0988991478435996e-05, "loss": 3.5519, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.0980605530925476e-05, "loss": 3.5413, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.0972235962218685e-05, "loss": 3.543, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.0963850014708165e-05, "loss": 3.552, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.095546406719765e-05, "loss": 3.5461, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.094707811968713e-05, "loss": 3.5254, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.093870855098034e-05, "loss": 3.5485, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.093032260346982e-05, "loss": 3.5336, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.09219366559593e-05, "loss": 3.5285, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.091355070844878e-05, "loss": 3.5414, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.090518113974199e-05, "loss": 3.553, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.089679519223147e-05, "loss": 3.5414, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.088840924472095e-05, "loss": 3.5439, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.088002329721043e-05, "loss": 3.5506, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.087165372850364e-05, "loss": 3.5457, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.086326778099312e-05, "loss": 3.5406, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.0854881833482605e-05, "loss": 3.5254, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.0846495885972085e-05, "loss": 3.543, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.0838126317265294e-05, "loss": 3.5446, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.0829740369754774e-05, "loss": 3.5399, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.0821354422244254e-05, "loss": 3.5351, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.0812968474733734e-05, "loss": 3.5325, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080459890602694e-05, "loss": 3.5343, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.079621295851642e-05, "loss": 3.5279, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.07878270110059e-05, "loss": 3.5507, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077944106349538e-05, "loss": 3.5264, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.077107149478859e-05, "loss": 3.545, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076268554727807e-05, "loss": 3.5399, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075429959976755e-05, "loss": 3.5272, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.074591365225704e-05, "loss": 3.5407, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.073754408355025e-05, "loss": 3.5325, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.072915813603973e-05, "loss": 3.532, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.072077218852921e-05, "loss": 3.5247, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071238624101869e-05, "loss": 3.5552, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.07040166723119e-05, "loss": 3.5333, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.069563072480138e-05, "loss": 3.5267, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.068724477729086e-05, "loss": 3.5198, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.0678875208584066e-05, "loss": 3.532, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.0670489261073546e-05, "loss": 3.5429, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.0662103313563026e-05, "loss": 3.5477, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0653717366052506e-05, "loss": 3.5353, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.064534779734572e-05, "loss": 3.5466, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.06369618498352e-05, "loss": 3.5461, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.062857590232468e-05, "loss": 3.5386, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.062018995481416e-05, "loss": 3.539, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.061182038610737e-05, "loss": 3.539, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.060343443859685e-05, "loss": 3.5361, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.059504849108633e-05, "loss": 3.5357, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.058666254357581e-05, "loss": 3.5372, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.0578276596065284e-05, "loss": 3.5472, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.05699070273585e-05, "loss": 3.5445, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.056152107984798e-05, "loss": 3.5415, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.055313513233746e-05, "loss": 3.5267, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.054474918482694e-05, "loss": 3.5364, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.0536379616120155e-05, "loss": 3.5427, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.0527993668609635e-05, "loss": 3.5377, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.051960772109911e-05, "loss": 3.5315, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.0511221773588588e-05, "loss": 3.5365, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.0502852204881804e-05, "loss": 3.544, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.0494466257371284e-05, "loss": 3.528, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.048608030986076e-05, "loss": 3.5344, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.047769436235024e-05, "loss": 3.5399, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.0469324793643456e-05, "loss": 3.5392, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.0460938846132936e-05, "loss": 3.5452, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.045255289862241e-05, "loss": 3.5298, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.044416695111189e-05, "loss": 3.5338, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.0435781003601373e-05, "loss": 3.5367, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.0427411434894582e-05, "loss": 3.5372, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.0419025487384062e-05, "loss": 3.5462, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.0410639539873542e-05, "loss": 3.5376, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0402253592363022e-05, "loss": 3.5262, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0393884023656234e-05, "loss": 3.5309, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.0385498076145714e-05, "loss": 3.5417, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.0377112128635194e-05, "loss": 3.5133, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.0368726181124674e-05, "loss": 3.5335, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.0360356612417883e-05, "loss": 3.5361, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0351970664907363e-05, "loss": 3.5256, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.0343584717396843e-05, "loss": 3.5252, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.0335198769886327e-05, "loss": 3.5376, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.0326829201179536e-05, "loss": 3.5237, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.0318443253669016e-05, "loss": 3.5472, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.0310057306158496e-05, "loss": 3.5328, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.0301671358647976e-05, "loss": 3.5382, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.0293285411137455e-05, "loss": 3.5424, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.0284915842430668e-05, "loss": 3.5565, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.0276529894920148e-05, "loss": 3.5335, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.0268143947409628e-05, "loss": 3.5302, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.0259757999899108e-05, "loss": 3.5397, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0251388431192317e-05, "loss": 3.5316, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.0243002483681797e-05, "loss": 3.5323, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.0234616536171277e-05, "loss": 3.5357, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.022623058866076e-05, "loss": 3.5348, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.021786101995397e-05, "loss": 3.5449, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.020947507244345e-05, "loss": 3.5355, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.020108912493293e-05, "loss": 3.5309, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.019270317742241e-05, "loss": 3.5352, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.018433360871562e-05, "loss": 3.535, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.01759476612051e-05, "loss": 3.5311, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.016756171369458e-05, "loss": 3.5367, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.015917576618406e-05, "loss": 3.5451, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.015080619747727e-05, "loss": 3.5348, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.014242024996675e-05, "loss": 3.5224, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.013403430245623e-05, "loss": 3.5375, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.0125648354945714e-05, "loss": 3.5347, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0117278786238923e-05, "loss": 3.5339, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0108892838728403e-05, "loss": 3.5373, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0100506891217883e-05, "loss": 3.5443, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0092120943707363e-05, "loss": 3.5417, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.0083751375000575e-05, "loss": 3.5358, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.0075365427490055e-05, "loss": 3.5307, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.0066979479979535e-05, "loss": 3.5294, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.0058593532469015e-05, "loss": 3.5383, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.0050223963762224e-05, "loss": 3.521, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.0041838016251704e-05, "loss": 3.546, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.0033452068741184e-05, "loss": 3.5394, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.0025066121230668e-05, "loss": 3.5358, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.0016696552523877e-05, "loss": 3.5281, "step": 1220608 }, { "epoch": 0.03, "learning_rate": 3.0008310605013357e-05, "loss": 3.5382, "step": 1221120 }, { "epoch": 0.03, "eval_loss": 3.844632387161255, "eval_runtime": 310.3735, "eval_samples_per_second": 1229.457, "eval_steps_per_second": 38.421, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.9999924657502837e-05, "loss": 3.5205, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.9991538709992316e-05, "loss": 3.5313, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.998316914128553e-05, "loss": 3.5381, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.997478319377501e-05, "loss": 3.5378, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.996639724626449e-05, "loss": 3.5382, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.995801129875397e-05, "loss": 3.5241, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.9949641730047178e-05, "loss": 3.5276, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.9941255782536658e-05, "loss": 3.5232, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.9932869835026138e-05, "loss": 3.5377, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.992448388751562e-05, "loss": 3.5239, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.991611431880883e-05, "loss": 3.5431, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.990774475010204e-05, "loss": 3.5453, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.989935880259152e-05, "loss": 3.521, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.9890972855081e-05, "loss": 3.5272, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.9882586907570483e-05, "loss": 3.5179, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.9874200960059963e-05, "loss": 3.5285, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.9865815012549443e-05, "loss": 3.5262, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.9857429065038923e-05, "loss": 3.5289, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.9849043117528402e-05, "loss": 3.528, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.9840657170017882e-05, "loss": 3.5368, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.983228760131109e-05, "loss": 3.5325, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.9823901653800575e-05, "loss": 3.5349, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.9815515706290055e-05, "loss": 3.5367, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.9807129758779535e-05, "loss": 3.5387, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.9798760190072744e-05, "loss": 3.5258, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.9790374242562224e-05, "loss": 3.5239, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.9781988295051704e-05, "loss": 3.5313, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9773602347541184e-05, "loss": 3.5217, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.9765232778834396e-05, "loss": 3.525, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.9756846831323876e-05, "loss": 3.526, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.9748460883813356e-05, "loss": 3.533, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9740074936302836e-05, "loss": 3.5376, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.9731705367596045e-05, "loss": 3.5239, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.972331942008553e-05, "loss": 3.5319, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.971493347257501e-05, "loss": 3.5374, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.970654752506448e-05, "loss": 3.5317, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.9698177956357698e-05, "loss": 3.5157, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.9689792008847177e-05, "loss": 3.5325, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.9681406061336657e-05, "loss": 3.5141, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.9673020113826134e-05, "loss": 3.5212, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.966465054511935e-05, "loss": 3.5225, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.965626459760883e-05, "loss": 3.5376, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.964787865009831e-05, "loss": 3.5301, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.9639492702587783e-05, "loss": 3.5313, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.9631123133881e-05, "loss": 3.5355, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.9622737186370482e-05, "loss": 3.5324, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.9614351238859955e-05, "loss": 3.5273, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.9605965291349435e-05, "loss": 3.5118, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.959759572264265e-05, "loss": 3.5264, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.958920977513213e-05, "loss": 3.5314, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.9580823827621608e-05, "loss": 3.5256, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.9572437880111088e-05, "loss": 3.5182, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.9564068311404304e-05, "loss": 3.5176, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.9555682363893784e-05, "loss": 3.5216, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.9547296416383257e-05, "loss": 3.5111, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.9538910468872737e-05, "loss": 3.5337, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.9530540900165953e-05, "loss": 3.5149, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.952215495265543e-05, "loss": 3.5324, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.951376900514491e-05, "loss": 3.5258, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.950538305763439e-05, "loss": 3.5116, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.9497013488927605e-05, "loss": 3.5293, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.948862754141708e-05, "loss": 3.5211, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.948024159390656e-05, "loss": 3.5177, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.947185564639604e-05, "loss": 3.5117, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.9463486077689257e-05, "loss": 3.5368, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.945510013017873e-05, "loss": 3.5217, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.944671418266821e-05, "loss": 3.5121, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.943832823515769e-05, "loss": 3.506, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.9429958666450903e-05, "loss": 3.5154, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.9421572718940383e-05, "loss": 3.5269, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.9413186771429863e-05, "loss": 3.5344, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.9404800823919343e-05, "loss": 3.5226, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9396431255212552e-05, "loss": 3.5347, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9388045307702035e-05, "loss": 3.532, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9379659360191515e-05, "loss": 3.5249, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.9371273412680995e-05, "loss": 3.5211, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.9362903843974204e-05, "loss": 3.5269, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.9354517896463684e-05, "loss": 3.5226, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.9346131948953164e-05, "loss": 3.5206, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9337746001442644e-05, "loss": 3.5251, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9329376432735856e-05, "loss": 3.5275, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9320990485225336e-05, "loss": 3.5305, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9312604537714816e-05, "loss": 3.5284, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9304218590204296e-05, "loss": 3.5184, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.9295849021497505e-05, "loss": 3.519, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.9287463073986985e-05, "loss": 3.529, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.927907712647647e-05, "loss": 3.5207, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.927069117896595e-05, "loss": 3.5204, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.9262321610259158e-05, "loss": 3.5215, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.9253935662748638e-05, "loss": 3.5311, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.9245549715238118e-05, "loss": 3.5153, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.9237163767727598e-05, "loss": 3.5204, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.922879419902081e-05, "loss": 3.5221, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.922040825151029e-05, "loss": 3.5317, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.921202230399977e-05, "loss": 3.5248, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.920363635648925e-05, "loss": 3.5253, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.919526678778246e-05, "loss": 3.5142, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.918688084027194e-05, "loss": 3.5228, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.9178494892761422e-05, "loss": 3.5237, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.9170108945250902e-05, "loss": 3.5342, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.916173937654411e-05, "loss": 3.5243, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.915335342903359e-05, "loss": 3.5154, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.914496748152307e-05, "loss": 3.5158, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.913658153401255e-05, "loss": 3.5293, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.9128211965305764e-05, "loss": 3.5021, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.9119826017795244e-05, "loss": 3.5156, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9111440070284724e-05, "loss": 3.5208, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9103054122774204e-05, "loss": 3.5186, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9094684554067413e-05, "loss": 3.5076, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.9086298606556893e-05, "loss": 3.5261, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.9077912659046376e-05, "loss": 3.5088, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.9069526711535856e-05, "loss": 3.5333, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.9061157142829065e-05, "loss": 3.5172, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9052771195318545e-05, "loss": 3.5252, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.9044385247808025e-05, "loss": 3.5289, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.9035999300297505e-05, "loss": 3.5444, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.9027629731590717e-05, "loss": 3.5173, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.9019243784080197e-05, "loss": 3.521, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.9010857836569677e-05, "loss": 3.5229, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.9002471889059157e-05, "loss": 3.5135, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.8994102320352366e-05, "loss": 3.5225, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.8985716372841846e-05, "loss": 3.5208, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.897733042533133e-05, "loss": 3.5174, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.896894447782081e-05, "loss": 3.5362, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.896055853031029e-05, "loss": 3.519, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.89521889616035e-05, "loss": 3.5184, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.894380301409298e-05, "loss": 3.5187, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.893541706658246e-05, "loss": 3.5227, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.892703111907194e-05, "loss": 3.5165, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.891866155036515e-05, "loss": 3.529, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.891027560285463e-05, "loss": 3.5325, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.890188965534411e-05, "loss": 3.5197, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.889350370783359e-05, "loss": 3.5093, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.88851341391268e-05, "loss": 3.5234, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.8876748191616283e-05, "loss": 3.5212, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.8868362244105763e-05, "loss": 3.5234, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.8859976296595243e-05, "loss": 3.5229, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.8851606727888452e-05, "loss": 3.5313, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.8843220780377932e-05, "loss": 3.5243, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8834834832867412e-05, "loss": 3.5255, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8826448885356892e-05, "loss": 3.519, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.8818079316650105e-05, "loss": 3.515, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.8809693369139585e-05, "loss": 3.5286, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.8801307421629065e-05, "loss": 3.5061, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.8792921474118545e-05, "loss": 3.5324, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8784551905411754e-05, "loss": 3.5274, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8776165957901237e-05, "loss": 3.5235, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8767780010390717e-05, "loss": 3.5161, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.8759394062880197e-05, "loss": 3.5224, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 3.84559965133667, "eval_runtime": 309.9922, "eval_samples_per_second": 1230.97, "eval_steps_per_second": 38.469, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.8751008115369677e-05, "loss": 3.5057, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.8742622167859157e-05, "loss": 3.5185, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.873423622034863e-05, "loss": 3.5261, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.8725850272838113e-05, "loss": 3.5175, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.871748070413133e-05, "loss": 3.5246, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.870909475662081e-05, "loss": 3.5124, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8700708809110282e-05, "loss": 3.5143, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.8692322861599762e-05, "loss": 3.5114, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.8683953292892978e-05, "loss": 3.5229, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.8675567345382455e-05, "loss": 3.5098, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.8667181397871935e-05, "loss": 3.5297, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.8658795450361415e-05, "loss": 3.5277, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.865042588165463e-05, "loss": 3.515, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.8642039934144104e-05, "loss": 3.5091, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8633653986633584e-05, "loss": 3.5112, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.8625268039123067e-05, "loss": 3.5109, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.861689847041628e-05, "loss": 3.511, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.8608512522905756e-05, "loss": 3.5169, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.8600126575395236e-05, "loss": 3.5115, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.8591740627884716e-05, "loss": 3.5265, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.858337105917793e-05, "loss": 3.5189, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.857498511166741e-05, "loss": 3.5229, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.856659916415689e-05, "loss": 3.524, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.855821321664637e-05, "loss": 3.5293, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.854982726913585e-05, "loss": 3.5055, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8541457700429057e-05, "loss": 3.5158, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8533071752918537e-05, "loss": 3.5136, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8524685805408017e-05, "loss": 3.5104, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.85162998578975e-05, "loss": 3.5114, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.850793028919071e-05, "loss": 3.5114, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.849954434168019e-05, "loss": 3.5223, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.849115839416967e-05, "loss": 3.5208, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.848277244665915e-05, "loss": 3.5078, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.8474402877952362e-05, "loss": 3.5211, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8466016930441842e-05, "loss": 3.525, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.8457630982931322e-05, "loss": 3.5146, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.8449245035420802e-05, "loss": 3.5036, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.844087546671401e-05, "loss": 3.5183, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.843248951920349e-05, "loss": 3.501, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.842410357169297e-05, "loss": 3.5104, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.8415717624182454e-05, "loss": 3.5096, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.8407348055475663e-05, "loss": 3.5264, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.8398962107965143e-05, "loss": 3.5116, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.8390576160454623e-05, "loss": 3.5168, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8382190212944103e-05, "loss": 3.5244, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8373820644237316e-05, "loss": 3.5153, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8365434696726796e-05, "loss": 3.5152, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8357048749216276e-05, "loss": 3.4978, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8348662801705756e-05, "loss": 3.5133, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.8340293232998965e-05, "loss": 3.5178, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.8331907285488445e-05, "loss": 3.5131, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8323521337977925e-05, "loss": 3.5095, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8315135390467408e-05, "loss": 3.501, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8306765821760617e-05, "loss": 3.5119, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8298379874250097e-05, "loss": 3.498, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8289993926739577e-05, "loss": 3.5162, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8281607979229057e-05, "loss": 3.5024, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.827323841052227e-05, "loss": 3.5183, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.826485246301175e-05, "loss": 3.5149, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.825646651550123e-05, "loss": 3.4984, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.824808056799071e-05, "loss": 3.5115, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.823971099928392e-05, "loss": 3.5111, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.82313250517734e-05, "loss": 3.5014, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.822293910426288e-05, "loss": 3.4997, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.8214553156752362e-05, "loss": 3.5208, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.820618358804557e-05, "loss": 3.5117, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.819779764053505e-05, "loss": 3.4966, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.818941169302453e-05, "loss": 3.492, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.818102574551401e-05, "loss": 3.5048, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.8172656176807223e-05, "loss": 3.5154, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.8164270229296703e-05, "loss": 3.52, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.8155884281786183e-05, "loss": 3.5107, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.8147498334275663e-05, "loss": 3.5223, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8139128765568872e-05, "loss": 3.5168, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.8130742818058352e-05, "loss": 3.5172, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.8122356870547832e-05, "loss": 3.5031, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.8113970923037315e-05, "loss": 3.5172, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.8105601354330524e-05, "loss": 3.5086, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.8097215406820004e-05, "loss": 3.5103, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.8088829459309484e-05, "loss": 3.5113, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.8080443511798964e-05, "loss": 3.5106, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8072073943092177e-05, "loss": 3.5226, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8063687995581657e-05, "loss": 3.5093, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8055302048071137e-05, "loss": 3.5053, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.8046916100560617e-05, "loss": 3.5069, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.8038546531853826e-05, "loss": 3.5151, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.8030160584343306e-05, "loss": 3.5098, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.8021774636832786e-05, "loss": 3.5081, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.801338868932227e-05, "loss": 3.5019, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8005019120615478e-05, "loss": 3.5206, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7996633173104958e-05, "loss": 3.5022, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7988247225594438e-05, "loss": 3.5065, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7979861278083918e-05, "loss": 3.5037, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.797149170937713e-05, "loss": 3.5159, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.796310576186661e-05, "loss": 3.5129, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.795471981435609e-05, "loss": 3.5129, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.794633386684557e-05, "loss": 3.5017, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.793796429813878e-05, "loss": 3.5125, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.792957835062826e-05, "loss": 3.5089, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.792119240311774e-05, "loss": 3.5202, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7912806455607223e-05, "loss": 3.5129, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.7904436886900432e-05, "loss": 3.5062, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.7896050939389912e-05, "loss": 3.5008, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.7887664991879392e-05, "loss": 3.5147, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.787927904436887e-05, "loss": 3.4864, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7870909475662084e-05, "loss": 3.5055, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7862523528151564e-05, "loss": 3.5071, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7854137580641044e-05, "loss": 3.5048, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7845751633130524e-05, "loss": 3.4929, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.7837382064423733e-05, "loss": 3.5094, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7828996116913213e-05, "loss": 3.501, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.7820610169402693e-05, "loss": 3.5177, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7812224221892176e-05, "loss": 3.508, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7803854653185385e-05, "loss": 3.5063, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7795468705674865e-05, "loss": 3.5193, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7787082758164345e-05, "loss": 3.5294, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.7778696810653825e-05, "loss": 3.5037, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.7770327241947038e-05, "loss": 3.5056, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.7761941294436518e-05, "loss": 3.515, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.7753555346925998e-05, "loss": 3.5018, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.7745169399415478e-05, "loss": 3.5062, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.7736799830708687e-05, "loss": 3.5114, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.7728413883198167e-05, "loss": 3.5039, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.7720027935687647e-05, "loss": 3.5225, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.7711641988177127e-05, "loss": 3.506, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.7703256040666603e-05, "loss": 3.5086, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.769488647195982e-05, "loss": 3.5035, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.76865005244493e-05, "loss": 3.5103, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.7678114576938776e-05, "loss": 3.5026, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.7669728629428256e-05, "loss": 3.5157, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.766135906072147e-05, "loss": 3.519, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.765297311321095e-05, "loss": 3.5077, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7644587165700425e-05, "loss": 3.4928, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7636201218189905e-05, "loss": 3.5145, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.762783164948312e-05, "loss": 3.5048, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.76194457019726e-05, "loss": 3.5108, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.7611059754462077e-05, "loss": 3.5088, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.7602673806951557e-05, "loss": 3.5146, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.7594304238244773e-05, "loss": 3.5109, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.7585918290734246e-05, "loss": 3.5182, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7577532343223726e-05, "loss": 3.5032, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.756914639571321e-05, "loss": 3.5022, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.7560776827006425e-05, "loss": 3.5159, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.7552390879495898e-05, "loss": 3.4969, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7544004931985378e-05, "loss": 3.5142, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7535618984474858e-05, "loss": 3.5205, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7527249415768074e-05, "loss": 3.5081, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.751886346825755e-05, "loss": 3.4998, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.751047752074703e-05, "loss": 3.5064, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 3.8477485179901123, "eval_runtime": 302.5188, "eval_samples_per_second": 1261.379, "eval_steps_per_second": 39.419, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.750209157323651e-05, "loss": 3.4971, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.749372200452972e-05, "loss": 3.5043, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.74853360570192e-05, "loss": 3.5123, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.747695010950868e-05, "loss": 3.5076, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7468564161998163e-05, "loss": 3.5145, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7460194593291372e-05, "loss": 3.4948, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7451808645780852e-05, "loss": 3.5057, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.7443422698270332e-05, "loss": 3.4934, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7435036750759812e-05, "loss": 3.509, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7426667182053024e-05, "loss": 3.5039, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.7418281234542504e-05, "loss": 3.509, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.7409895287031984e-05, "loss": 3.5144, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.7401525718325193e-05, "loss": 3.5031, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.7393139770814673e-05, "loss": 3.4993, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.7384753823304153e-05, "loss": 3.4987, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.7376367875793633e-05, "loss": 3.496, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.7367981928283117e-05, "loss": 3.4962, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.7359595980772597e-05, "loss": 3.5035, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.7351210033262076e-05, "loss": 3.4967, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.7342840464555286e-05, "loss": 3.5191, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7334454517044766e-05, "loss": 3.502, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7326068569534245e-05, "loss": 3.513, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.7317682622023725e-05, "loss": 3.5111, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.7309313053316938e-05, "loss": 3.5138, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.7300927105806418e-05, "loss": 3.4899, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.7292541158295898e-05, "loss": 3.5044, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.7284155210785378e-05, "loss": 3.4963, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7275785642078587e-05, "loss": 3.5008, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.726739969456807e-05, "loss": 3.4967, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.725901374705755e-05, "loss": 3.4983, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.725062779954703e-05, "loss": 3.5106, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.724225823084024e-05, "loss": 3.5083, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.723387228332972e-05, "loss": 3.4929, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.72254863358192e-05, "loss": 3.5122, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.721710038830868e-05, "loss": 3.5061, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.7208714440798162e-05, "loss": 3.5033, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.720034487209137e-05, "loss": 3.4937, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.719195892458085e-05, "loss": 3.5067, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.718357297707033e-05, "loss": 3.4866, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.717518702955981e-05, "loss": 3.5006, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.7166817460853024e-05, "loss": 3.4953, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7158431513342504e-05, "loss": 3.5109, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7150045565831984e-05, "loss": 3.502, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.7141659618321464e-05, "loss": 3.5035, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.7133290049614673e-05, "loss": 3.5121, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.7124904102104153e-05, "loss": 3.5051, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.7116518154593633e-05, "loss": 3.5042, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.7108132207083116e-05, "loss": 3.4874, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7099762638376325e-05, "loss": 3.4968, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7091376690865805e-05, "loss": 3.5062, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.7082990743355285e-05, "loss": 3.4993, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7074604795844765e-05, "loss": 3.4941, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7066235227137978e-05, "loss": 3.4905, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.7057849279627458e-05, "loss": 3.4976, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7049463332116937e-05, "loss": 3.4832, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7041077384606417e-05, "loss": 3.5035, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7032707815899627e-05, "loss": 3.4928, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.7024321868389106e-05, "loss": 3.5074, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7015935920878586e-05, "loss": 3.4997, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.700754997336807e-05, "loss": 3.4878, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.699918040466128e-05, "loss": 3.4976, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.699079445715076e-05, "loss": 3.4961, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.698240850964024e-05, "loss": 3.4895, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.697402256212972e-05, "loss": 3.4956, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.696565299342293e-05, "loss": 3.5032, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.695726704591241e-05, "loss": 3.5012, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.694888109840189e-05, "loss": 3.4855, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.694049515089137e-05, "loss": 3.4777, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.693212558218458e-05, "loss": 3.4891, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.692373963467406e-05, "loss": 3.5013, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.691535368716354e-05, "loss": 3.5066, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.690696773965302e-05, "loss": 3.4951, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.6898598170946233e-05, "loss": 3.5096, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.6890212223435713e-05, "loss": 3.5037, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.6881826275925192e-05, "loss": 3.5072, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.6873440328414672e-05, "loss": 3.4851, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.6865070759707885e-05, "loss": 3.5056, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.6856684812197365e-05, "loss": 3.4991, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6848298864686845e-05, "loss": 3.4954, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6839912917176325e-05, "loss": 3.5016, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.6831543348469534e-05, "loss": 3.497, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.6823157400959014e-05, "loss": 3.5084, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6814771453448494e-05, "loss": 3.499, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6806385505937974e-05, "loss": 3.4905, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6798015937231186e-05, "loss": 3.4955, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6789629989720666e-05, "loss": 3.4992, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.6781244042210146e-05, "loss": 3.4982, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.6772858094699626e-05, "loss": 3.493, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6764488525992835e-05, "loss": 3.4933, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.675610257848232e-05, "loss": 3.5035, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.67477166309718e-05, "loss": 3.4922, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.673933068346127e-05, "loss": 3.496, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6730961114754488e-05, "loss": 3.491, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.6722575167243967e-05, "loss": 3.5083, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.6714189219733447e-05, "loss": 3.5018, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.6705803272222924e-05, "loss": 3.4995, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669743370351614e-05, "loss": 3.4915, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668904775600562e-05, "loss": 3.5012, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.66806618084951e-05, "loss": 3.4899, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.6672275860984573e-05, "loss": 3.5094, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.666390629227779e-05, "loss": 3.4975, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.6655520344767272e-05, "loss": 3.4932, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.6647134397256745e-05, "loss": 3.4899, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6638748449746225e-05, "loss": 3.5014, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.663037888103944e-05, "loss": 3.4774, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.662199293352892e-05, "loss": 3.494, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6613606986018398e-05, "loss": 3.4926, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6605221038507878e-05, "loss": 3.4919, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6596851469801094e-05, "loss": 3.4782, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6588465522290574e-05, "loss": 3.5008, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6580079574780047e-05, "loss": 3.4868, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6571693627269527e-05, "loss": 3.5054, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.656330767975901e-05, "loss": 3.4941, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.655493811105222e-05, "loss": 3.4923, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.65465521635417e-05, "loss": 3.5085, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.653816621603118e-05, "loss": 3.5184, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.652978026852066e-05, "loss": 3.4923, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.652141069981387e-05, "loss": 3.492, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.651302475230335e-05, "loss": 3.4996, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.650463880479283e-05, "loss": 3.4907, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.649625285728231e-05, "loss": 3.4922, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.648788328857552e-05, "loss": 3.5043, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.6479497341065e-05, "loss": 3.4891, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.647111139355448e-05, "loss": 3.5067, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.6462725446043964e-05, "loss": 3.4947, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.6454355877337173e-05, "loss": 3.4978, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.6445969929826653e-05, "loss": 3.4889, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.6437583982316133e-05, "loss": 3.4977, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.6429198034805613e-05, "loss": 3.4873, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.6420828466098825e-05, "loss": 3.505, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.6412442518588305e-05, "loss": 3.5026, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.6404056571077785e-05, "loss": 3.4979, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.6395670623567265e-05, "loss": 3.482, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.6387301054860474e-05, "loss": 3.5031, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.6378915107349954e-05, "loss": 3.4955, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6370529159839434e-05, "loss": 3.4966, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6362159591132646e-05, "loss": 3.4946, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.6353773643622126e-05, "loss": 3.5042, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.6345387696111606e-05, "loss": 3.5002, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.6337001748601086e-05, "loss": 3.5069, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.6328615801090566e-05, "loss": 3.49, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.632024623238378e-05, "loss": 3.4889, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.631186028487326e-05, "loss": 3.5006, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.630347433736274e-05, "loss": 3.4834, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.629508838985222e-05, "loss": 3.4996, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.6286718821145428e-05, "loss": 3.5094, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.6278332873634908e-05, "loss": 3.4964, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.6269946926124388e-05, "loss": 3.4871, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.626156097861387e-05, "loss": 3.4963, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 3.8498504161834717, "eval_runtime": 307.3594, "eval_samples_per_second": 1241.514, "eval_steps_per_second": 38.798, "step": 1450080 }, { "epoch": 0.0, "learning_rate": 2.625317503110335e-05, "loss": 3.4826, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.624478908359283e-05, "loss": 3.4921, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.623640313608231e-05, "loss": 3.4994, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.622801718857179e-05, "loss": 3.4907, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.6219647619865e-05, "loss": 3.5049, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.621126167235448e-05, "loss": 3.4832, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.6202875724843963e-05, "loss": 3.4951, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.6194489777333443e-05, "loss": 3.481, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.6186120208626652e-05, "loss": 3.4963, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.6177734261116132e-05, "loss": 3.4884, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.6169348313605612e-05, "loss": 3.4967, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.6160962366095092e-05, "loss": 3.5012, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.6152592797388305e-05, "loss": 3.4905, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.6144206849877785e-05, "loss": 3.4902, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.6135820902367265e-05, "loss": 3.4855, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.6127434954856744e-05, "loss": 3.4874, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.6119065386149954e-05, "loss": 3.4826, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.6110679438639434e-05, "loss": 3.4894, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.6102293491128917e-05, "loss": 3.4824, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.6093907543618397e-05, "loss": 3.5092, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6085537974911606e-05, "loss": 3.4901, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6077152027401086e-05, "loss": 3.4948, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6068766079890566e-05, "loss": 3.5036, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6060380132380046e-05, "loss": 3.501, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.6052010563673258e-05, "loss": 3.4806, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.6043624616162738e-05, "loss": 3.4911, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.6035238668652218e-05, "loss": 3.4846, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.6026852721141698e-05, "loss": 3.4912, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.6018483152434907e-05, "loss": 3.4805, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.6010097204924387e-05, "loss": 3.4851, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.6001711257413867e-05, "loss": 3.4963, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.599332530990335e-05, "loss": 3.4965, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.5984939362392824e-05, "loss": 3.4886, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.597656979368604e-05, "loss": 3.497, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.596818384617552e-05, "loss": 3.4933, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.5959797898665e-05, "loss": 3.49, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.5951411951154476e-05, "loss": 3.4801, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.5943042382447692e-05, "loss": 3.4949, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.5934656434937172e-05, "loss": 3.4732, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.5926270487426652e-05, "loss": 3.4882, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.5917884539916125e-05, "loss": 3.4819, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.590951497120934e-05, "loss": 3.4992, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.590112902369882e-05, "loss": 3.4948, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.5892743076188297e-05, "loss": 3.4876, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.5884357128677777e-05, "loss": 3.4981, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.5875987559970993e-05, "loss": 3.4954, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.5867601612460473e-05, "loss": 3.4914, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.585921566494995e-05, "loss": 3.4767, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.585082971743943e-05, "loss": 3.481, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.5842460148732646e-05, "loss": 3.4975, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.583407420122212e-05, "loss": 3.4848, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.58256882537116e-05, "loss": 3.478, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.581730230620108e-05, "loss": 3.4814, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.5808932737494295e-05, "loss": 3.4863, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.580054678998377e-05, "loss": 3.4745, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.579216084247325e-05, "loss": 3.4875, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.578377489496273e-05, "loss": 3.4823, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.5775405326255947e-05, "loss": 3.4905, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.576701937874542e-05, "loss": 3.4863, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.5758633431234903e-05, "loss": 3.4782, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.5750247483724383e-05, "loss": 3.481, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.5741877915017592e-05, "loss": 3.491, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5733491967507072e-05, "loss": 3.4737, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.5725106019996552e-05, "loss": 3.4805, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.5716720072486032e-05, "loss": 3.4924, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.5708350503779245e-05, "loss": 3.4911, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.5699964556268725e-05, "loss": 3.4725, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.5691578608758205e-05, "loss": 3.4693, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.5683192661247685e-05, "loss": 3.4758, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.5674823092540894e-05, "loss": 3.4874, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.5666437145030374e-05, "loss": 3.4923, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.5658051197519857e-05, "loss": 3.4845, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.5649665250009337e-05, "loss": 3.4957, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.5641295681302546e-05, "loss": 3.4928, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.5632909733792026e-05, "loss": 3.4954, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5624523786281506e-05, "loss": 3.4759, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.5616137838770986e-05, "loss": 3.4932, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.56077682700642e-05, "loss": 3.488, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.559938232255368e-05, "loss": 3.4806, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.559099637504316e-05, "loss": 3.488, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.558261042753264e-05, "loss": 3.4872, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5574240858825847e-05, "loss": 3.4921, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5565854911315327e-05, "loss": 3.4877, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.555746896380481e-05, "loss": 3.4792, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.554908301629429e-05, "loss": 3.4864, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.55407134475875e-05, "loss": 3.4827, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.553232750007698e-05, "loss": 3.4864, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.552394155256646e-05, "loss": 3.4819, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.551555560505594e-05, "loss": 3.4795, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.5507186036349152e-05, "loss": 3.4915, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.5498800088838632e-05, "loss": 3.4836, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.5490414141328112e-05, "loss": 3.4808, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.5482028193817592e-05, "loss": 3.4795, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.54736586251108e-05, "loss": 3.4974, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.546527267760028e-05, "loss": 3.4902, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.5456886730089764e-05, "loss": 3.4853, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.5448500782579244e-05, "loss": 3.4782, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.5440131213872453e-05, "loss": 3.4898, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.5431745266361933e-05, "loss": 3.4775, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.5423359318851413e-05, "loss": 3.5011, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.5414973371340893e-05, "loss": 3.4838, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.5406603802634106e-05, "loss": 3.4823, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.5398217855123586e-05, "loss": 3.4786, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.5389831907613066e-05, "loss": 3.488, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.5381445960102546e-05, "loss": 3.4628, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.5373076391395755e-05, "loss": 3.482, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.5364690443885235e-05, "loss": 3.4812, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.5356304496374718e-05, "loss": 3.4807, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.5347918548864198e-05, "loss": 3.4669, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.5339548980157407e-05, "loss": 3.4887, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5331163032646887e-05, "loss": 3.4728, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5322777085136367e-05, "loss": 3.489, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.5314391137625847e-05, "loss": 3.4849, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.530602156891906e-05, "loss": 3.4782, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.529763562140854e-05, "loss": 3.4942, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.528924967389802e-05, "loss": 3.5048, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.52808637263875e-05, "loss": 3.4868, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.527247777887698e-05, "loss": 3.4799, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.526410821017019e-05, "loss": 3.4867, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.5255722262659672e-05, "loss": 3.4759, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5247336315149152e-05, "loss": 3.4802, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.523896674644236e-05, "loss": 3.4912, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.523058079893184e-05, "loss": 3.4795, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.522219485142132e-05, "loss": 3.4928, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.52138089039108e-05, "loss": 3.4833, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.520542295640028e-05, "loss": 3.4893, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5197053387693493e-05, "loss": 3.4723, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.5188667440182973e-05, "loss": 3.4876, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.5180281492672453e-05, "loss": 3.4754, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.5171895545161933e-05, "loss": 3.4908, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.5163525976455142e-05, "loss": 3.4896, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.5155140028944625e-05, "loss": 3.49, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.5146754081434105e-05, "loss": 3.4684, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.5138368133923585e-05, "loss": 3.495, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.5129998565216794e-05, "loss": 3.4809, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.5121612617706274e-05, "loss": 3.4828, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.5113226670195754e-05, "loss": 3.4831, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.5104840722685234e-05, "loss": 3.4929, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.5096471153978447e-05, "loss": 3.4888, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.5088085206467927e-05, "loss": 3.4924, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.5079699258957407e-05, "loss": 3.4759, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.5071313311446887e-05, "loss": 3.4824, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.5062943742740096e-05, "loss": 3.4845, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.5054557795229576e-05, "loss": 3.4757, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.504617184771906e-05, "loss": 3.4864, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.503778590020854e-05, "loss": 3.4957, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.5029416331501748e-05, "loss": 3.4866, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.5021030383991228e-05, "loss": 3.474, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.5012644436480708e-05, "loss": 3.4863, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 3.850329637527466, "eval_runtime": 308.0017, "eval_samples_per_second": 1238.925, "eval_steps_per_second": 38.717, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5004258488970188e-05, "loss": 3.4693, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4995872541459668e-05, "loss": 3.4797, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4987486593949148e-05, "loss": 3.4859, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4979100646438628e-05, "loss": 3.483, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4970731077731837e-05, "loss": 3.4926, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4962345130221317e-05, "loss": 3.4714, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4953959182710797e-05, "loss": 3.4803, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.494557323520028e-05, "loss": 3.466, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.493720366649349e-05, "loss": 3.4878, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.492881771898297e-05, "loss": 3.4769, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.492043177147245e-05, "loss": 3.4806, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.491204582396193e-05, "loss": 3.4907, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.490367625525514e-05, "loss": 3.4755, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.489529030774462e-05, "loss": 3.4811, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.48869043602341e-05, "loss": 3.4733, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.487851841272358e-05, "loss": 3.4767, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.487014884401679e-05, "loss": 3.4691, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.486176289650627e-05, "loss": 3.4779, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.485337694899575e-05, "loss": 3.4753, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4844991001485234e-05, "loss": 3.4932, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4836621432778443e-05, "loss": 3.4792, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.4828235485267923e-05, "loss": 3.4833, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.4819849537757403e-05, "loss": 3.4923, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.4811463590246883e-05, "loss": 3.4902, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.4803094021540095e-05, "loss": 3.4685, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.4794708074029575e-05, "loss": 3.4818, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.4786322126519055e-05, "loss": 3.4702, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.4777936179008535e-05, "loss": 3.4812, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.4769566610301744e-05, "loss": 3.4661, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.4761180662791224e-05, "loss": 3.4745, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.4752794715280704e-05, "loss": 3.486, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.4744408767770184e-05, "loss": 3.4835, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4736039199063397e-05, "loss": 3.4752, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4727653251552877e-05, "loss": 3.4891, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4719267304042357e-05, "loss": 3.4758, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.4710881356531833e-05, "loss": 3.4838, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.470251178782505e-05, "loss": 3.4666, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.469412584031453e-05, "loss": 3.4821, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.468573989280401e-05, "loss": 3.4658, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4677353945293485e-05, "loss": 3.473, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4668984376586698e-05, "loss": 3.4721, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4660598429076178e-05, "loss": 3.4872, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.4652212481565658e-05, "loss": 3.481, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.4643826534055138e-05, "loss": 3.4791, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.463545696534835e-05, "loss": 3.4841, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.462707101783783e-05, "loss": 3.4828, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4618685070327307e-05, "loss": 3.4779, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4610299122816787e-05, "loss": 3.4688, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.460192955411e-05, "loss": 3.4638, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.459354360659948e-05, "loss": 3.4852, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.458515765908896e-05, "loss": 3.4753, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.457677171157844e-05, "loss": 3.4657, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.456840214287165e-05, "loss": 3.4721, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4560016195361128e-05, "loss": 3.4741, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.455163024785061e-05, "loss": 3.4616, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.454324430034009e-05, "loss": 3.4695, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.453485835282957e-05, "loss": 3.4719, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.452648878412278e-05, "loss": 3.4759, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.451810283661226e-05, "loss": 3.4817, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.450971688910174e-05, "loss": 3.4664, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.450133094159122e-05, "loss": 3.4684, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.4492961372884433e-05, "loss": 3.4773, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.4484575425373913e-05, "loss": 3.4657, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.4476189477863393e-05, "loss": 3.4679, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.4467803530352873e-05, "loss": 3.4792, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.4459433961646082e-05, "loss": 3.4781, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.4451048014135565e-05, "loss": 3.4627, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.4442662066625045e-05, "loss": 3.4552, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.4434276119114525e-05, "loss": 3.4612, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.4425906550407734e-05, "loss": 3.4748, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4417520602897214e-05, "loss": 3.4844, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.4409134655386694e-05, "loss": 3.4723, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.4400748707876174e-05, "loss": 3.4848, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.4392379139169387e-05, "loss": 3.481, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4383993191658866e-05, "loss": 3.4851, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4375607244148346e-05, "loss": 3.465, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.4367237675441556e-05, "loss": 3.4801, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4358851727931035e-05, "loss": 3.4742, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.435046578042052e-05, "loss": 3.4684, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.434207983291e-05, "loss": 3.4808, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.433369388539948e-05, "loss": 3.4757, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.4325324316692688e-05, "loss": 3.4758, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.4316938369182168e-05, "loss": 3.4749, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4308552421671648e-05, "loss": 3.4725, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.4300166474161128e-05, "loss": 3.4759, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.429179690545434e-05, "loss": 3.4691, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.428341095794382e-05, "loss": 3.4753, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.42750250104333e-05, "loss": 3.4674, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.426663906292278e-05, "loss": 3.4716, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.425826949421599e-05, "loss": 3.4762, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.424988354670547e-05, "loss": 3.4729, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.4241497599194952e-05, "loss": 3.4641, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.4233111651684432e-05, "loss": 3.4678, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.422474208297764e-05, "loss": 3.4838, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.421635613546712e-05, "loss": 3.4786, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.42079701879566e-05, "loss": 3.4757, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.419958424044608e-05, "loss": 3.4684, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.4191214671739294e-05, "loss": 3.4755, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.4182828724228774e-05, "loss": 3.4658, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.4174442776718254e-05, "loss": 3.4832, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.416605682920773e-05, "loss": 3.4778, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.4157687260500943e-05, "loss": 3.4699, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.4149301312990423e-05, "loss": 3.466, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4140915365479906e-05, "loss": 3.4793, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.4132529417969383e-05, "loss": 3.4488, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.4124159849262595e-05, "loss": 3.4754, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.4115773901752075e-05, "loss": 3.464, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.410738795424155e-05, "loss": 3.4694, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.4099002006731035e-05, "loss": 3.4562, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4090632438024248e-05, "loss": 3.4763, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4082246490513727e-05, "loss": 3.4683, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4073860543003204e-05, "loss": 3.4723, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4065474595492684e-05, "loss": 3.4761, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4057105026785896e-05, "loss": 3.4654, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4048719079275376e-05, "loss": 3.4846, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4040333131764856e-05, "loss": 3.4945, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4031947184254336e-05, "loss": 3.4739, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.402357761554755e-05, "loss": 3.4656, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4015191668037025e-05, "loss": 3.4779, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4006805720526505e-05, "loss": 3.469, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.399841977301599e-05, "loss": 3.4628, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.39900502043092e-05, "loss": 3.4824, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3981664256798678e-05, "loss": 3.4653, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.3973278309288158e-05, "loss": 3.4794, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3964892361777638e-05, "loss": 3.4717, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.395652279307085e-05, "loss": 3.4772, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.394813684556033e-05, "loss": 3.4686, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.393975089804981e-05, "loss": 3.4731, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.393136495053929e-05, "loss": 3.4695, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.39229953818325e-05, "loss": 3.4776, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.391460943432198e-05, "loss": 3.4741, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.390622348681146e-05, "loss": 3.478, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.3897837539300942e-05, "loss": 3.4599, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.388946797059415e-05, "loss": 3.4808, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.388108202308363e-05, "loss": 3.469, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.387269607557311e-05, "loss": 3.4747, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.386431012806259e-05, "loss": 3.4705, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.3855940559355804e-05, "loss": 3.4802, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.3847554611845284e-05, "loss": 3.4762, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3839168664334764e-05, "loss": 3.4852, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3830782716824244e-05, "loss": 3.4613, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.3822413148117453e-05, "loss": 3.4722, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.3814027200606933e-05, "loss": 3.4697, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.3805641253096413e-05, "loss": 3.4652, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.3797255305585893e-05, "loss": 3.4772, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.3788885736879105e-05, "loss": 3.4802, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.3780499789368585e-05, "loss": 3.4796, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.3772113841858065e-05, "loss": 3.4581, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.3763727894347545e-05, "loss": 3.4768, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 3.851027727127075, "eval_runtime": 304.3929, "eval_samples_per_second": 1253.614, "eval_steps_per_second": 39.176, "step": 1602720 }, { "epoch": 1.0, "learning_rate": 2.3755358325640757e-05, "loss": 3.4649, "step": 1603072 }, { "epoch": 1.0, "learning_rate": 2.3746972378130237e-05, "loss": 3.4661, "step": 1603584 }, { "epoch": 1.0, "learning_rate": 2.3738586430619717e-05, "loss": 3.4777, "step": 1604096 }, { "epoch": 1.0, "learning_rate": 2.3730200483109197e-05, "loss": 3.4722, "step": 1604608 }, { "epoch": 1.0, "learning_rate": 2.3721830914402406e-05, "loss": 3.4762, "step": 1605120 }, { "epoch": 1.0, "learning_rate": 2.3713444966891886e-05, "loss": 3.4637, "step": 1605632 }, { "epoch": 1.0, "learning_rate": 2.3705059019381366e-05, "loss": 3.468, "step": 1606144 }, { "epoch": 1.0, "learning_rate": 2.3696673071870846e-05, "loss": 3.4574, "step": 1606656 }, { "epoch": 1.0, "learning_rate": 2.368830350316406e-05, "loss": 3.4725, "step": 1607168 }, { "epoch": 1.0, "learning_rate": 2.367991755565354e-05, "loss": 3.466, "step": 1607680 }, { "epoch": 1.0, "learning_rate": 2.367153160814302e-05, "loss": 3.4691, "step": 1608192 }, { "epoch": 1.0, "learning_rate": 2.36631456606325e-05, "loss": 3.4793, "step": 1608704 }, { "epoch": 1.0, "learning_rate": 2.3654776091925708e-05, "loss": 3.4631, "step": 1609216 }, { "epoch": 1.0, "learning_rate": 2.364639014441519e-05, "loss": 3.4689, "step": 1609728 }, { "epoch": 1.0, "learning_rate": 2.363800419690467e-05, "loss": 3.4649, "step": 1610240 }, { "epoch": 1.0, "learning_rate": 2.362961824939415e-05, "loss": 3.4633, "step": 1610752 }, { "epoch": 1.0, "learning_rate": 2.362124868068736e-05, "loss": 3.4573, "step": 1611264 }, { "epoch": 1.0, "learning_rate": 2.361286273317684e-05, "loss": 3.4659, "step": 1611776 }, { "epoch": 1.0, "learning_rate": 2.360447678566632e-05, "loss": 3.4625, "step": 1612288 }, { "epoch": 1.0, "learning_rate": 2.35960908381558e-05, "loss": 3.4809, "step": 1612800 }, { "epoch": 1.0, "learning_rate": 2.3587721269449012e-05, "loss": 3.47, "step": 1613312 }, { "epoch": 1.0, "learning_rate": 2.3579335321938492e-05, "loss": 3.4689, "step": 1613824 }, { "epoch": 1.0, "learning_rate": 2.3570949374427972e-05, "loss": 3.4825, "step": 1614336 }, { "epoch": 1.0, "learning_rate": 2.356256342691745e-05, "loss": 3.4784, "step": 1614848 }, { "epoch": 1.0, "learning_rate": 2.355419385821066e-05, "loss": 3.4552, "step": 1615360 }, { "epoch": 1.0, "learning_rate": 2.3545807910700145e-05, "loss": 3.4716, "step": 1615872 }, { "epoch": 1.0, "learning_rate": 2.3537421963189625e-05, "loss": 3.4617, "step": 1616384 }, { "epoch": 1.0, "learning_rate": 2.35290360156791e-05, "loss": 3.4657, "step": 1616896 }, { "epoch": 1.0, "learning_rate": 2.3520666446972314e-05, "loss": 3.4573, "step": 1617408 }, { "epoch": 1.0, "learning_rate": 2.3512280499461794e-05, "loss": 3.4641, "step": 1617920 }, { "epoch": 1.01, "learning_rate": 2.3503894551951274e-05, "loss": 3.4756, "step": 1618432 }, { "epoch": 1.01, "learning_rate": 2.3495524983244486e-05, "loss": 3.47, "step": 1618944 }, { "epoch": 1.01, "learning_rate": 2.3487139035733966e-05, "loss": 3.4653, "step": 1619456 }, { "epoch": 1.01, "learning_rate": 2.3478753088223446e-05, "loss": 3.4749, "step": 1619968 }, { "epoch": 1.01, "learning_rate": 2.3470367140712923e-05, "loss": 3.4676, "step": 1620480 }, { "epoch": 1.01, "learning_rate": 2.3461997572006135e-05, "loss": 3.4706, "step": 1620992 }, { "epoch": 1.01, "learning_rate": 2.3453611624495615e-05, "loss": 3.4588, "step": 1621504 }, { "epoch": 1.01, "learning_rate": 2.34452256769851e-05, "loss": 3.4649, "step": 1622016 }, { "epoch": 1.01, "learning_rate": 2.3436839729474575e-05, "loss": 3.4581, "step": 1622528 }, { "epoch": 1.01, "learning_rate": 2.3428470160767787e-05, "loss": 3.4601, "step": 1623040 }, { "epoch": 1.01, "learning_rate": 2.3420084213257267e-05, "loss": 3.4612, "step": 1623552 }, { "epoch": 1.01, "learning_rate": 2.3411698265746747e-05, "loss": 3.4749, "step": 1624064 }, { "epoch": 1.01, "learning_rate": 2.3403312318236227e-05, "loss": 3.4698, "step": 1624576 }, { "epoch": 1.01, "learning_rate": 2.339494274952944e-05, "loss": 3.4683, "step": 1625088 }, { "epoch": 1.01, "learning_rate": 2.338655680201892e-05, "loss": 3.4783, "step": 1625600 }, { "epoch": 1.01, "learning_rate": 2.3378170854508396e-05, "loss": 3.4655, "step": 1626112 }, { "epoch": 1.01, "learning_rate": 2.3369784906997876e-05, "loss": 3.4674, "step": 1626624 }, { "epoch": 1.01, "learning_rate": 2.336141533829109e-05, "loss": 3.4583, "step": 1627136 }, { "epoch": 1.01, "learning_rate": 2.335302939078057e-05, "loss": 3.4492, "step": 1627648 }, { "epoch": 1.01, "learning_rate": 2.334464344327005e-05, "loss": 3.4746, "step": 1628160 }, { "epoch": 1.01, "learning_rate": 2.333625749575953e-05, "loss": 3.4632, "step": 1628672 }, { "epoch": 1.01, "learning_rate": 2.332788792705274e-05, "loss": 3.4589, "step": 1629184 }, { "epoch": 1.01, "learning_rate": 2.331950197954222e-05, "loss": 3.4593, "step": 1629696 }, { "epoch": 1.01, "learning_rate": 2.3311116032031698e-05, "loss": 3.4623, "step": 1630208 }, { "epoch": 1.01, "learning_rate": 2.330273008452118e-05, "loss": 3.4523, "step": 1630720 }, { "epoch": 1.01, "learning_rate": 2.3294360515814394e-05, "loss": 3.4601, "step": 1631232 }, { "epoch": 1.01, "learning_rate": 2.328597456830387e-05, "loss": 3.4631, "step": 1631744 }, { "epoch": 1.01, "learning_rate": 2.327758862079335e-05, "loss": 3.4628, "step": 1632256 }, { "epoch": 1.01, "learning_rate": 2.326920267328283e-05, "loss": 3.4682, "step": 1632768 }, { "epoch": 1.01, "learning_rate": 2.3260833104576042e-05, "loss": 3.4544, "step": 1633280 }, { "epoch": 1.01, "learning_rate": 2.3252447157065522e-05, "loss": 3.4573, "step": 1633792 }, { "epoch": 1.01, "learning_rate": 2.3244061209555002e-05, "loss": 3.4701, "step": 1634304 }, { "epoch": 1.01, "learning_rate": 2.3235675262044482e-05, "loss": 3.4521, "step": 1634816 }, { "epoch": 1.01, "learning_rate": 2.322730569333769e-05, "loss": 3.4542, "step": 1635328 }, { "epoch": 1.01, "learning_rate": 2.321891974582717e-05, "loss": 3.4649, "step": 1635840 }, { "epoch": 1.01, "learning_rate": 2.321053379831665e-05, "loss": 3.4685, "step": 1636352 }, { "epoch": 1.01, "learning_rate": 2.320214785080613e-05, "loss": 3.4512, "step": 1636864 }, { "epoch": 1.01, "learning_rate": 2.3193761903295615e-05, "loss": 3.4479, "step": 1637376 }, { "epoch": 1.01, "learning_rate": 2.3185392334588824e-05, "loss": 3.445, "step": 1637888 }, { "epoch": 1.01, "learning_rate": 2.3177006387078304e-05, "loss": 3.4625, "step": 1638400 }, { "epoch": 1.01, "learning_rate": 2.3168620439567784e-05, "loss": 3.4712, "step": 1638912 }, { "epoch": 1.01, "learning_rate": 2.3160234492057264e-05, "loss": 3.4607, "step": 1639424 }, { "epoch": 1.01, "learning_rate": 2.3151864923350476e-05, "loss": 3.4704, "step": 1639936 }, { "epoch": 1.01, "learning_rate": 2.3143478975839956e-05, "loss": 3.4657, "step": 1640448 }, { "epoch": 1.01, "learning_rate": 2.3135093028329436e-05, "loss": 3.4789, "step": 1640960 }, { "epoch": 1.01, "learning_rate": 2.3126707080818916e-05, "loss": 3.456, "step": 1641472 }, { "epoch": 1.01, "learning_rate": 2.3118337512112125e-05, "loss": 3.4686, "step": 1641984 }, { "epoch": 1.01, "learning_rate": 2.3109951564601605e-05, "loss": 3.4613, "step": 1642496 }, { "epoch": 1.01, "learning_rate": 2.3101565617091085e-05, "loss": 3.4547, "step": 1643008 }, { "epoch": 1.01, "learning_rate": 2.309317966958057e-05, "loss": 3.4676, "step": 1643520 }, { "epoch": 1.01, "learning_rate": 2.3084810100873777e-05, "loss": 3.4679, "step": 1644032 }, { "epoch": 1.01, "learning_rate": 2.3076424153363257e-05, "loss": 3.4649, "step": 1644544 }, { "epoch": 1.01, "learning_rate": 2.3068038205852737e-05, "loss": 3.4659, "step": 1645056 }, { "epoch": 1.01, "learning_rate": 2.3059652258342217e-05, "loss": 3.4626, "step": 1645568 }, { "epoch": 1.01, "learning_rate": 2.305128268963543e-05, "loss": 3.4568, "step": 1646080 }, { "epoch": 1.01, "learning_rate": 2.304289674212491e-05, "loss": 3.4607, "step": 1646592 }, { "epoch": 1.01, "learning_rate": 2.303451079461439e-05, "loss": 3.4654, "step": 1647104 }, { "epoch": 1.01, "learning_rate": 2.302612484710387e-05, "loss": 3.4535, "step": 1647616 }, { "epoch": 1.01, "learning_rate": 2.301775527839708e-05, "loss": 3.4593, "step": 1648128 }, { "epoch": 1.02, "learning_rate": 2.300936933088656e-05, "loss": 3.4679, "step": 1648640 }, { "epoch": 1.02, "learning_rate": 2.300098338337604e-05, "loss": 3.4649, "step": 1649152 }, { "epoch": 1.02, "learning_rate": 2.2992597435865522e-05, "loss": 3.4516, "step": 1649664 }, { "epoch": 1.02, "learning_rate": 2.298422786715873e-05, "loss": 3.458, "step": 1650176 }, { "epoch": 1.02, "learning_rate": 2.297584191964821e-05, "loss": 3.4745, "step": 1650688 }, { "epoch": 1.02, "learning_rate": 2.296745597213769e-05, "loss": 3.4681, "step": 1651200 }, { "epoch": 1.02, "learning_rate": 2.295907002462717e-05, "loss": 3.4657, "step": 1651712 }, { "epoch": 1.02, "learning_rate": 2.2950700455920383e-05, "loss": 3.4524, "step": 1652224 }, { "epoch": 1.02, "learning_rate": 2.2942314508409863e-05, "loss": 3.4653, "step": 1652736 }, { "epoch": 1.02, "learning_rate": 2.2933928560899343e-05, "loss": 3.4589, "step": 1653248 }, { "epoch": 1.02, "learning_rate": 2.292554261338882e-05, "loss": 3.4693, "step": 1653760 }, { "epoch": 1.02, "learning_rate": 2.2917173044682032e-05, "loss": 3.4685, "step": 1654272 }, { "epoch": 1.02, "learning_rate": 2.2908787097171512e-05, "loss": 3.4592, "step": 1654784 }, { "epoch": 1.02, "learning_rate": 2.2900401149660992e-05, "loss": 3.4545, "step": 1655296 }, { "epoch": 1.02, "learning_rate": 2.2892015202150472e-05, "loss": 3.4667, "step": 1655808 }, { "epoch": 1.02, "learning_rate": 2.2883645633443685e-05, "loss": 3.4385, "step": 1656320 }, { "epoch": 1.02, "learning_rate": 2.2875259685933165e-05, "loss": 3.4615, "step": 1656832 }, { "epoch": 1.02, "learning_rate": 2.2866873738422645e-05, "loss": 3.451, "step": 1657344 }, { "epoch": 1.02, "learning_rate": 2.285848779091212e-05, "loss": 3.4623, "step": 1657856 }, { "epoch": 1.02, "learning_rate": 2.2850118222205337e-05, "loss": 3.4463, "step": 1658368 }, { "epoch": 1.02, "learning_rate": 2.2841732274694817e-05, "loss": 3.4645, "step": 1658880 }, { "epoch": 1.02, "learning_rate": 2.2833346327184294e-05, "loss": 3.4542, "step": 1659392 }, { "epoch": 1.02, "learning_rate": 2.2824960379673774e-05, "loss": 3.4618, "step": 1659904 }, { "epoch": 1.02, "learning_rate": 2.2816590810966986e-05, "loss": 3.4667, "step": 1660416 }, { "epoch": 1.02, "learning_rate": 2.2808204863456466e-05, "loss": 3.458, "step": 1660928 }, { "epoch": 1.02, "learning_rate": 2.2799818915945946e-05, "loss": 3.47, "step": 1661440 }, { "epoch": 1.02, "learning_rate": 2.2791432968435426e-05, "loss": 3.4801, "step": 1661952 }, { "epoch": 1.02, "learning_rate": 2.278306339972864e-05, "loss": 3.4632, "step": 1662464 }, { "epoch": 1.02, "learning_rate": 2.277467745221812e-05, "loss": 3.4577, "step": 1662976 }, { "epoch": 1.02, "learning_rate": 2.2766291504707595e-05, "loss": 3.4629, "step": 1663488 }, { "epoch": 1.02, "learning_rate": 2.2757905557197075e-05, "loss": 3.4621, "step": 1664000 }, { "epoch": 1.02, "learning_rate": 2.274953598849029e-05, "loss": 3.4477, "step": 1664512 }, { "epoch": 1.02, "learning_rate": 2.2741150040979767e-05, "loss": 3.4738, "step": 1665024 }, { "epoch": 1.02, "learning_rate": 2.2732764093469247e-05, "loss": 3.4501, "step": 1665536 }, { "epoch": 1.02, "learning_rate": 2.2724378145958727e-05, "loss": 3.4715, "step": 1666048 }, { "epoch": 1.02, "learning_rate": 2.271600857725194e-05, "loss": 3.4602, "step": 1666560 }, { "epoch": 1.02, "learning_rate": 2.2707622629741416e-05, "loss": 3.4659, "step": 1667072 }, { "epoch": 1.02, "learning_rate": 2.26992366822309e-05, "loss": 3.4584, "step": 1667584 }, { "epoch": 1.02, "learning_rate": 2.269085073472038e-05, "loss": 3.4634, "step": 1668096 }, { "epoch": 1.02, "learning_rate": 2.2682481166013592e-05, "loss": 3.4566, "step": 1668608 }, { "epoch": 1.02, "learning_rate": 2.267409521850307e-05, "loss": 3.4688, "step": 1669120 }, { "epoch": 1.02, "learning_rate": 2.266570927099255e-05, "loss": 3.4614, "step": 1669632 }, { "epoch": 1.02, "learning_rate": 2.265733970228576e-05, "loss": 3.4681, "step": 1670144 }, { "epoch": 1.02, "learning_rate": 2.264895375477524e-05, "loss": 3.4496, "step": 1670656 }, { "epoch": 1.02, "learning_rate": 2.264056780726472e-05, "loss": 3.47, "step": 1671168 }, { "epoch": 1.02, "learning_rate": 2.26321818597542e-05, "loss": 3.4574, "step": 1671680 }, { "epoch": 1.02, "learning_rate": 2.2623812291047413e-05, "loss": 3.4632, "step": 1672192 }, { "epoch": 1.02, "learning_rate": 2.261542634353689e-05, "loss": 3.4621, "step": 1672704 }, { "epoch": 1.02, "learning_rate": 2.260704039602637e-05, "loss": 3.4662, "step": 1673216 }, { "epoch": 1.02, "learning_rate": 2.2598654448515853e-05, "loss": 3.4615, "step": 1673728 }, { "epoch": 1.02, "learning_rate": 2.2590284879809062e-05, "loss": 3.4771, "step": 1674240 }, { "epoch": 1.02, "learning_rate": 2.2581898932298542e-05, "loss": 3.4486, "step": 1674752 }, { "epoch": 1.02, "learning_rate": 2.2573512984788022e-05, "loss": 3.4611, "step": 1675264 }, { "epoch": 1.02, "learning_rate": 2.2565127037277502e-05, "loss": 3.4596, "step": 1675776 }, { "epoch": 1.02, "learning_rate": 2.2556757468570715e-05, "loss": 3.4586, "step": 1676288 }, { "epoch": 1.02, "learning_rate": 2.2548371521060195e-05, "loss": 3.4596, "step": 1676800 }, { "epoch": 1.02, "learning_rate": 2.2539985573549675e-05, "loss": 3.4694, "step": 1677312 }, { "epoch": 1.02, "learning_rate": 2.2531599626039155e-05, "loss": 3.4674, "step": 1677824 }, { "epoch": 1.02, "learning_rate": 2.2523230057332364e-05, "loss": 3.4473, "step": 1678336 }, { "epoch": 1.02, "learning_rate": 2.2514844109821844e-05, "loss": 3.4658, "step": 1678848 }, { "epoch": 1.03, "eval_loss": 3.852663993835449, "eval_runtime": 304.3868, "eval_samples_per_second": 1253.638, "eval_steps_per_second": 39.177, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.2506458162311324e-05, "loss": 3.4544, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.2498072214800807e-05, "loss": 3.4517, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.2489686267290287e-05, "loss": 3.4664, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.2481300319779767e-05, "loss": 3.4606, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.2472930751072976e-05, "loss": 3.4665, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.2464544803562456e-05, "loss": 3.4517, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.2456158856051936e-05, "loss": 3.452, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.2447772908541416e-05, "loss": 3.4491, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.243940333983463e-05, "loss": 3.459, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.2431017392324108e-05, "loss": 3.4557, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.2422631444813588e-05, "loss": 3.4595, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.2414245497303068e-05, "loss": 3.4669, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.240589230740001e-05, "loss": 3.4552, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.239750635988949e-05, "loss": 3.4558, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.238912041237897e-05, "loss": 3.4567, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.238073446486845e-05, "loss": 3.4516, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.237234851735793e-05, "loss": 3.4443, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.236396256984741e-05, "loss": 3.4542, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.235557662233689e-05, "loss": 3.4534, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.234719067482637e-05, "loss": 3.467, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.2338821106119582e-05, "loss": 3.46, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.2330435158609062e-05, "loss": 3.4593, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.2322049211098542e-05, "loss": 3.4687, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.231366326358802e-05, "loss": 3.4643, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.230529369488123e-05, "loss": 3.4468, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.2296907747370714e-05, "loss": 3.4619, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.228852179986019e-05, "loss": 3.4474, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.228013585234967e-05, "loss": 3.4545, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.2271766283642883e-05, "loss": 3.4482, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.2263380336132363e-05, "loss": 3.4502, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.225499438862184e-05, "loss": 3.466, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2246608441111323e-05, "loss": 3.4573, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.2238238872404536e-05, "loss": 3.4543, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.2229852924894016e-05, "loss": 3.4616, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.2221466977383492e-05, "loss": 3.4547, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.2213081029872972e-05, "loss": 3.4613, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.2204711461166185e-05, "loss": 3.4491, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.2196325513655665e-05, "loss": 3.4525, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.2187939566145145e-05, "loss": 3.4454, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.2179553618634625e-05, "loss": 3.4472, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.2171184049927837e-05, "loss": 3.4516, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.2162798102417314e-05, "loss": 3.461, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.2154412154906794e-05, "loss": 3.4567, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.2146026207396277e-05, "loss": 3.4564, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.213765663868949e-05, "loss": 3.4666, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.2129270691178966e-05, "loss": 3.458, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.2120884743668446e-05, "loss": 3.4566, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.2112498796157926e-05, "loss": 3.4463, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.2104129227451138e-05, "loss": 3.4363, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.2095743279940618e-05, "loss": 3.4664, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.2087357332430098e-05, "loss": 3.4534, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.2078971384919578e-05, "loss": 3.4442, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.2070601816212787e-05, "loss": 3.4537, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.2062215868702267e-05, "loss": 3.4457, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2053829921191747e-05, "loss": 3.4446, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.204544397368123e-05, "loss": 3.444, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.203707440497444e-05, "loss": 3.4508, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.202868845746392e-05, "loss": 3.4495, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.20203025099534e-05, "loss": 3.4609, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.201191656244288e-05, "loss": 3.4439, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.2003546993736092e-05, "loss": 3.4419, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.1995161046225572e-05, "loss": 3.464, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.1986775098715052e-05, "loss": 3.4354, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.1978389151204532e-05, "loss": 3.4458, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.197001958249774e-05, "loss": 3.4543, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.196163363498722e-05, "loss": 3.4601, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.19532476874767e-05, "loss": 3.4398, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1944878118769913e-05, "loss": 3.4369, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.1936492171259393e-05, "loss": 3.4346, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.1928106223748873e-05, "loss": 3.45, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.1919720276238353e-05, "loss": 3.4628, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.1911334328727833e-05, "loss": 3.4515, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.1902964760021046e-05, "loss": 3.4559, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.1894578812510526e-05, "loss": 3.4568, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.1886192865000006e-05, "loss": 3.4674, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.1877806917489486e-05, "loss": 3.4455, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.1869437348782695e-05, "loss": 3.457, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.1861051401272175e-05, "loss": 3.4522, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.1852665453761655e-05, "loss": 3.4426, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.1844279506251138e-05, "loss": 3.4575, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.1835909937544347e-05, "loss": 3.4579, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.1827523990033827e-05, "loss": 3.4557, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.1819138042523307e-05, "loss": 3.4521, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.1810752095012787e-05, "loss": 3.4533, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.1802382526306e-05, "loss": 3.4437, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.179399657879548e-05, "loss": 3.4528, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.178561063128496e-05, "loss": 3.4531, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.177722468377444e-05, "loss": 3.4459, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.1768855115067648e-05, "loss": 3.4494, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.1760469167557128e-05, "loss": 3.4506, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1752083220046608e-05, "loss": 3.4552, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.1743697272536088e-05, "loss": 3.4452, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.17353277038293e-05, "loss": 3.4452, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.172694175631878e-05, "loss": 3.4634, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.171855580880826e-05, "loss": 3.4546, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1710169861297737e-05, "loss": 3.4545, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.1701800292590953e-05, "loss": 3.4398, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.1693414345080433e-05, "loss": 3.4565, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.1685028397569913e-05, "loss": 3.4452, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.167664245005939e-05, "loss": 3.4535, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.1668272881352602e-05, "loss": 3.4602, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.1659886933842082e-05, "loss": 3.4476, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.1651500986331562e-05, "loss": 3.4476, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.1643115038821042e-05, "loss": 3.4511, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.1634745470114254e-05, "loss": 3.4294, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.1626359522603734e-05, "loss": 3.4537, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.161797357509321e-05, "loss": 3.4362, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.1609604006386423e-05, "loss": 3.4515, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.1601218058875907e-05, "loss": 3.4363, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.1592832111365387e-05, "loss": 3.4524, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.1584446163854863e-05, "loss": 3.4458, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.1576076595148076e-05, "loss": 3.4474, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.1567690647637556e-05, "loss": 3.4604, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.1559304700127032e-05, "loss": 3.4448, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.1550918752616516e-05, "loss": 3.4582, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.1542549183909728e-05, "loss": 3.4665, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.1534163236399208e-05, "loss": 3.4503, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.1525777288888685e-05, "loss": 3.4506, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.1517391341378164e-05, "loss": 3.4462, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.1509021772671377e-05, "loss": 3.4513, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.150063582516086e-05, "loss": 3.4445, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.1492249877650337e-05, "loss": 3.462, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.1483863930139817e-05, "loss": 3.4369, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.147549436143303e-05, "loss": 3.4578, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1467108413922506e-05, "loss": 3.4531, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.1458722466411986e-05, "loss": 3.4543, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.145033651890147e-05, "loss": 3.4436, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.144196695019468e-05, "loss": 3.4516, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.1433581002684158e-05, "loss": 3.4436, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1425195055173638e-05, "loss": 3.4579, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1416809107663118e-05, "loss": 3.4485, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.140843953895633e-05, "loss": 3.4584, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.140005359144581e-05, "loss": 3.4373, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.139166764393529e-05, "loss": 3.4635, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.138328169642477e-05, "loss": 3.4473, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.137491212771798e-05, "loss": 3.4524, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.136652618020746e-05, "loss": 3.4494, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.135814023269694e-05, "loss": 3.4489, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.1349754285186423e-05, "loss": 3.4538, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.1341384716479632e-05, "loss": 3.4703, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.1332998768969112e-05, "loss": 3.4359, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.1324612821458592e-05, "loss": 3.4504, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.1316226873948072e-05, "loss": 3.447, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.1307857305241284e-05, "loss": 3.4523, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1299471357730764e-05, "loss": 3.4458, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.1291085410220244e-05, "loss": 3.4569, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.1282699462709724e-05, "loss": 3.4561, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.1274329894002933e-05, "loss": 3.4395, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.1265943946492413e-05, "loss": 3.4577, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.8541486263275146, "eval_runtime": 302.8916, "eval_samples_per_second": 1259.827, "eval_steps_per_second": 39.371, "step": 1755360 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.2302096813003612e+18, "trial_name": null, "trial_params": null }