{ "best_metric": 3.913831949234009, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/4/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.954, "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 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.1394950979136717e+17, "trial_name": null, "trial_params": null }