{ "best_metric": 3.8689687252044678, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/3/checkpoints/checkpoint-457920", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 457920, "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": 11.041, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8208, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1887, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9835, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8256, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7214, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6172, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5503, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4645, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4135, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3668, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3346, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2827, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2231, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1934, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1408, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1213, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0969, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0565, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0301, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0163, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9896, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9608, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9411, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9324, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.896, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8803, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8719, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8417, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8213, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8122, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8035, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7897, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7732, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7628, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.758, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.738, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7115, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7093, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6795, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6909, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6766, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6764, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6533, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6553, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.641, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6338, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6356, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5972, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.95892359812181e-05, "loss": 4.6058, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6062, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.5996, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5759, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5679, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5595, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5526, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5669, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5305, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5435, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5371, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5158, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5251, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5007, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4973, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4976, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5082, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4749, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4784, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4631, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4729, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4768, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4735, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4541, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4638, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.47, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4455, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4379, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4321, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4257, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4331, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.413, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4334, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931261436499706e-05, "loss": 4.4248, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930422841748654e-05, "loss": 4.4102, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3938, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4008, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4011, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4052, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3894, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3927, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.385, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3736, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.37, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3755, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 4.37, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3724, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3568, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3541, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3617, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3612, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3517, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3477, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3396, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3364, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3391, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3157, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3247, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3282, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3278, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3157, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3223, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3028, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3276, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.2971, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.3112, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3075, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3123, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.3033, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2933, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2957, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2986, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2842, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2829, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2792, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2973, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2683, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2737, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.27, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2751, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2647, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2828, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2704, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.266, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2575, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.2696, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.2622, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2675, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.25, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2634, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2575, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2587, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2389, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2579, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2405, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.225, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2552, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.238, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2384, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2389, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2251, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.196109771728516, "eval_runtime": 304.8575, "eval_samples_per_second": 1251.703, "eval_steps_per_second": 39.117, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2048, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2137, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2327, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2192, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2243, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.2131, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2075, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.2024, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2063, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.2063, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2172, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.2116, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.1971, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.1879, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1814, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1822, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1923, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1828, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1785, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.198, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1846, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1804, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1826, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1933, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1645, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1712, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1794, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.168, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.158, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.1575, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1717, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1662, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847434719001968e-05, "loss": 4.1627, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846596124250916e-05, "loss": 4.1618, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1629, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1594, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844081977878133e-05, "loss": 4.1455, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843243383127081e-05, "loss": 4.1485, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842404788376029e-05, "loss": 4.1339, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.1474, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.145, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398906420032456e-05, "loss": 4.1532, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.8390520472521936e-05, "loss": 4.1396, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382134525011416e-05, "loss": 4.1463, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1405, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1421, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835699306128359e-05, "loss": 4.1503, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834860711377307e-05, "loss": 4.1174, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834023754506628e-05, "loss": 4.1287, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833185159755576e-05, "loss": 4.1446, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832346565004524e-05, "loss": 4.1377, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831507970253472e-05, "loss": 4.1258, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.1185, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1203, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1086, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.134, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.1095, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1266, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.1196, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1089, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.115, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231252985036985e-05, "loss": 4.1035, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222867037526465e-05, "loss": 4.1021, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.105, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1234, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197725573798634e-05, "loss": 4.0938, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.1016, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.0868, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.1017, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816419816256029e-05, "loss": 4.1128, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815581221504977e-05, "loss": 4.1076, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.0973, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.1073, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813067075132194e-05, "loss": 4.113, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812228480381141e-05, "loss": 4.0947, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.0927, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.0919, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809714334008359e-05, "loss": 4.0889, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808875739257306e-05, "loss": 4.0958, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.084, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.099, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.095, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055229981334717e-05, "loss": 4.0882, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046844033824197e-05, "loss": 4.0721, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.0803, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0893, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021702570096366e-05, "loss": 4.0886, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013316622585846e-05, "loss": 4.0829, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800494705387906e-05, "loss": 4.0798, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996561106368535e-05, "loss": 4.0834, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988175158858015e-05, "loss": 4.0712, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0676, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0818, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0731, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.079, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0716, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0634, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0741, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0799, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.79127343888708e-05, "loss": 4.0717, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790434844136028e-05, "loss": 4.0676, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789596249384976e-05, "loss": 4.0576, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.063, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0699, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0492, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862435082611415e-05, "loss": 4.0555, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0612, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0662, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837277240079855e-05, "loss": 4.0516, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828891292569335e-05, "loss": 4.0585, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820505345058815e-05, "loss": 4.0463, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812119397548295e-05, "loss": 4.0675, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803733450037775e-05, "loss": 4.046, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0544, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778699431262419e-05, "loss": 4.0614, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0598, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0555, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0426, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0505, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0562, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773667862756108e-05, "loss": 4.0402, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0454, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771992311134377e-05, "loss": 4.0412, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771153716383325e-05, "loss": 4.0591, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770315121632272e-05, "loss": 4.0319, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.76947652688122e-05, "loss": 4.0427, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768637932130168e-05, "loss": 4.038, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0431, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0349, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0558, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765285191006334e-05, "loss": 4.0467, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764446596255282e-05, "loss": 4.0377, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.76360800150423e-05, "loss": 4.0307, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762769406753178e-05, "loss": 4.0457, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0405, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610938551314466e-05, "loss": 4.0482, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602552603803946e-05, "loss": 4.0243, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.045, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.0402, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577411140076115e-05, "loss": 4.0473, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569025192565595e-05, "loss": 4.0278, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756065562385881e-05, "loss": 4.0403, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755226967634829e-05, "loss": 4.0317, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0201, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.0408, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752712821262046e-05, "loss": 4.033, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751874226510994e-05, "loss": 4.0303, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751035631759942e-05, "loss": 4.0272, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.75019703700889e-05, "loss": 4.0217, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.026325702667236, "eval_runtime": 308.3883, "eval_samples_per_second": 1237.372, "eval_steps_per_second": 38.669, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749358442257838e-05, "loss": 4.0024, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748519847506786e-05, "loss": 4.0115, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747681252755734e-05, "loss": 4.0328, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746842658004682e-05, "loss": 4.0212, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.74600406325363e-05, "loss": 4.0284, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745165468502578e-05, "loss": 4.0117, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744326873751526e-05, "loss": 4.0148, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743488279000474e-05, "loss": 4.0062, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742649684249422e-05, "loss": 4.0119, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.74181108949837e-05, "loss": 4.0174, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740972494747318e-05, "loss": 4.0213, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740135537876639e-05, "loss": 4.0224, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739300218886333e-05, "loss": 4.0079, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738461624135281e-05, "loss": 4.0013, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737623029384229e-05, "loss": 4.0023, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736784434633177e-05, "loss": 3.992, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735945839882125e-05, "loss": 4.0054, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735107245131073e-05, "loss": 3.998, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734268650380021e-05, "loss": 3.9993, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733430055628969e-05, "loss": 4.0204, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732591460877917e-05, "loss": 4.0019, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731752866126865e-05, "loss": 4.0038, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730915909256186e-05, "loss": 4.0063, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730077314505134e-05, "loss": 4.0147, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729238719754082e-05, "loss": 3.9853, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.72840012500303e-05, "loss": 3.9979, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727561530251978e-05, "loss": 4.0025, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726722935500926e-05, "loss": 3.997, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725884340749874e-05, "loss": 3.9865, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725045745998822e-05, "loss": 3.9834, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724210427008517e-05, "loss": 4.0015, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233718322574647e-05, "loss": 3.9996, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225332375064127e-05, "loss": 3.9908, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216946427553606e-05, "loss": 3.9975, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208560480043086e-05, "loss": 3.9935, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200174532532566e-05, "loss": 3.9913, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191788585022046e-05, "loss": 3.9805, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183402637511526e-05, "loss": 3.9875, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.9678, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166663500097945e-05, "loss": 3.9847, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158277552587424e-05, "loss": 3.9835, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149891605076904e-05, "loss": 3.9921, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9815, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133119710055864e-05, "loss": 3.9835, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712473376254535e-05, "loss": 3.9857, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711634781503483e-05, "loss": 3.9792, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.9919, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709959229881752e-05, "loss": 3.9602, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091206351307e-05, "loss": 3.9771, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708282040379648e-05, "loss": 3.9867, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707445083508969e-05, "loss": 3.9847, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706606488757917e-05, "loss": 3.9721, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705767894006865e-05, "loss": 3.9641, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704929299255813e-05, "loss": 3.9696, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704090704504761e-05, "loss": 3.954, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703252109753709e-05, "loss": 3.9864, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702413515002657e-05, "loss": 3.9627, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015765581319785e-05, "loss": 3.9721, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007379633809265e-05, "loss": 3.9729, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998993686298745e-05, "loss": 3.9611, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699060773878822e-05, "loss": 3.967, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.69822217912777e-05, "loss": 3.9561, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973852222570914e-05, "loss": 3.9585, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965466275060394e-05, "loss": 3.9556, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695708032754987e-05, "loss": 3.9759, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694869438003935e-05, "loss": 3.9543, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694032481133256e-05, "loss": 3.9546, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693193886382204e-05, "loss": 3.947, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692355291631152e-05, "loss": 3.9554, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915166968801e-05, "loss": 3.9676, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690678102129048e-05, "loss": 3.9695, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689841145258369e-05, "loss": 3.9575, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689002550507317e-05, "loss": 3.9662, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688163955756265e-05, "loss": 3.9748, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687325361005213e-05, "loss": 3.9576, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686486766254161e-05, "loss": 3.9488, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685649809383482e-05, "loss": 3.9593, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.68481121463243e-05, "loss": 3.9537, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683972619881378e-05, "loss": 3.9562, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683134025130326e-05, "loss": 3.9459, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682295430379274e-05, "loss": 3.9618, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814584735085956e-05, "loss": 3.9644, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806198787575436e-05, "loss": 3.9528, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797812840064916e-05, "loss": 3.9381, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789426892554396e-05, "loss": 3.9456, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781040945043876e-05, "loss": 3.9529, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772654997533356e-05, "loss": 3.9578, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764285428826565e-05, "loss": 3.9502, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755899481316045e-05, "loss": 3.9533, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747513533805525e-05, "loss": 3.9511, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739127586295005e-05, "loss": 3.942, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730741638784485e-05, "loss": 3.9395, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722355691273965e-05, "loss": 3.9447, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713969743763445e-05, "loss": 3.9488, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670560017505666e-05, "loss": 3.9513, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669721422754614e-05, "loss": 3.947, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668882828003562e-05, "loss": 3.9335, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.66804423325251e-05, "loss": 3.9492, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667205638501458e-05, "loss": 3.9533, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666368681630779e-05, "loss": 3.9429, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665530086879727e-05, "loss": 3.9467, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664691492128675e-05, "loss": 3.9322, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663852897377623e-05, "loss": 3.939, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66301430262657e-05, "loss": 3.947, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662175707875518e-05, "loss": 3.9227, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.66133875100484e-05, "loss": 3.9329, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660500156253788e-05, "loss": 3.9418, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659661561502736e-05, "loss": 3.9392, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658822966751684e-05, "loss": 3.9276, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579860098810054e-05, "loss": 3.9386, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657147415129953e-05, "loss": 3.9254, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656308820378901e-05, "loss": 3.9461, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655470225627849e-05, "loss": 3.9284, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.65463326875717e-05, "loss": 3.9296, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537946740061176e-05, "loss": 3.9429, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529560792550656e-05, "loss": 3.9421, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521174845040136e-05, "loss": 3.9368, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.6512788897529616e-05, "loss": 3.9263, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650441932882283e-05, "loss": 3.9313, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649603338131231e-05, "loss": 3.9358, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648764743380179e-05, "loss": 3.9264, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647926148629127e-05, "loss": 3.9305, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647089191758448e-05, "loss": 3.9235, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646250597007396e-05, "loss": 3.9374, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645412002256344e-05, "loss": 3.9258, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644573407505292e-05, "loss": 3.9262, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643736450634613e-05, "loss": 3.9201, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642897855883561e-05, "loss": 3.9299, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642059261132509e-05, "loss": 3.9177, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641220666381457e-05, "loss": 3.9394, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640382071630405e-05, "loss": 3.935, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395451147597266e-05, "loss": 3.9282, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387065200086746e-05, "loss": 3.9142, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378679252576226e-05, "loss": 3.936, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370293305065705e-05, "loss": 3.9282, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361923736358915e-05, "loss": 3.9327, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353537788848395e-05, "loss": 3.9175, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345151841337874e-05, "loss": 3.929, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336765893827354e-05, "loss": 3.9314, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328396325120564e-05, "loss": 3.9376, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320010377610043e-05, "loss": 3.9214, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311624430099523e-05, "loss": 3.9268, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303238482589003e-05, "loss": 3.9227, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629488529268595e-05, "loss": 3.9104, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628649934517543e-05, "loss": 3.9315, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627811339766491e-05, "loss": 3.9307, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626972745015439e-05, "loss": 3.9183, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626134150264387e-05, "loss": 3.921, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625295555513335e-05, "loss": 3.9113, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9512414932250977, "eval_runtime": 304.5377, "eval_samples_per_second": 1253.017, "eval_steps_per_second": 39.158, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624456960762283e-05, "loss": 3.907, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623618366011231e-05, "loss": 3.9022, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622781409140552e-05, "loss": 3.9252, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219428143895e-05, "loss": 3.9136, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621104219638448e-05, "loss": 3.9271, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620265624887396e-05, "loss": 3.9071, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619427030136344e-05, "loss": 3.9137, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185884353852924e-05, "loss": 3.8991, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617751478514613e-05, "loss": 3.9113, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616912883763561e-05, "loss": 3.912, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616074289012509e-05, "loss": 3.9187, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615235694261457e-05, "loss": 3.9166, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614400375271151e-05, "loss": 3.9068, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613561780520099e-05, "loss": 3.9, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612723185769047e-05, "loss": 3.8988, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611884591017995e-05, "loss": 3.8941, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611045996266943e-05, "loss": 3.899, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610207401515891e-05, "loss": 3.8985, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609368806764839e-05, "loss": 3.8963, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608530212013788e-05, "loss": 3.9245, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076932551431087e-05, "loss": 3.9036, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068546603920566e-05, "loss": 3.9027, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6060160656410046e-05, "loss": 3.9072, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051774708899526e-05, "loss": 3.9119, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043405140192735e-05, "loss": 3.889, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035019192682215e-05, "loss": 3.9004, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026633245171695e-05, "loss": 3.9057, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018247297661175e-05, "loss": 3.9006, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009877728954384e-05, "loss": 3.8861, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001491781443864e-05, "loss": 3.8864, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5993105833933344e-05, "loss": 3.9053, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598471988642283e-05, "loss": 3.9053, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597635031771604e-05, "loss": 3.8985, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596796437020552e-05, "loss": 3.8992, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959578422695e-05, "loss": 3.894, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595119247518448e-05, "loss": 3.8969, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594282290647769e-05, "loss": 3.8824, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593443695896717e-05, "loss": 3.8968, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592605101145665e-05, "loss": 3.8766, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591766506394613e-05, "loss": 3.8898, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590929549523934e-05, "loss": 3.8835, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590090954772882e-05, "loss": 3.9021, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.58925236002183e-05, "loss": 3.8894, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884137652707785e-05, "loss": 3.8876, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875768084000994e-05, "loss": 3.8916, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867382136490474e-05, "loss": 3.8928, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858996188979954e-05, "loss": 3.8972, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585061024146943e-05, "loss": 3.8709, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584224067276264e-05, "loss": 3.8815, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583385472525212e-05, "loss": 3.8945, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.58254687777416e-05, "loss": 3.8915, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5817082830231076e-05, "loss": 3.8817, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580871326152429e-05, "loss": 3.8767, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580032731401377e-05, "loss": 3.8799, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579194136650325e-05, "loss": 3.8667, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578355541899273e-05, "loss": 3.8933, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577518585028595e-05, "loss": 3.8723, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576679990277543e-05, "loss": 3.8849, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.57584139552649e-05, "loss": 3.8857, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575002800775438e-05, "loss": 3.8736, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741658439047596e-05, "loss": 3.8739, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733272491537076e-05, "loss": 3.8711, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572488654402655e-05, "loss": 3.8679, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571650059651603e-05, "loss": 3.8741, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708131027809245e-05, "loss": 3.8823, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699745080298725e-05, "loss": 3.869, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691359132788205e-05, "loss": 3.8687, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682973185277685e-05, "loss": 3.8606, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.56746036165709e-05, "loss": 3.8682, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666217669060374e-05, "loss": 3.8771, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657831721549854e-05, "loss": 3.8881, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649445774039334e-05, "loss": 3.8696, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564107620533255e-05, "loss": 3.8798, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563269025782202e-05, "loss": 3.8851, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.56243043103115e-05, "loss": 3.8805, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561591836280098e-05, "loss": 3.8593, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.56075487940942e-05, "loss": 3.8784, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559916284658368e-05, "loss": 3.8717, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559077689907316e-05, "loss": 3.8662, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558239095156264e-05, "loss": 3.8704, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557402138285585e-05, "loss": 3.8735, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556563543534533e-05, "loss": 3.8802, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555724948783481e-05, "loss": 3.8693, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554886354032429e-05, "loss": 3.8547, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.55404939716175e-05, "loss": 3.866, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553210802410698e-05, "loss": 3.866, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552372207659646e-05, "loss": 3.8748, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551533612908594e-05, "loss": 3.8717, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550696656037915e-05, "loss": 3.866, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549858061286863e-05, "loss": 3.8717, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549019466535811e-05, "loss": 3.8578, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548180871784759e-05, "loss": 3.8584, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.54734391491408e-05, "loss": 3.8625, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546505320163028e-05, "loss": 3.8679, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545666725411976e-05, "loss": 3.8692, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544828130660924e-05, "loss": 3.8736, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543991173790245e-05, "loss": 3.8487, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543152579039193e-05, "loss": 3.869, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542313984288141e-05, "loss": 3.8721, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541475389537089e-05, "loss": 3.8654, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406384326664106e-05, "loss": 3.8639, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397998379153586e-05, "loss": 3.8525, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389612431643066e-05, "loss": 3.8612, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381226484132546e-05, "loss": 3.8646, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372856915425755e-05, "loss": 3.8449, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364470967915235e-05, "loss": 3.8566, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5356085020404715e-05, "loss": 3.8601, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347699072894195e-05, "loss": 3.8635, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339329504187404e-05, "loss": 3.8454, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330943556676884e-05, "loss": 3.8663, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322557609166364e-05, "loss": 3.8412, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314171661655844e-05, "loss": 3.8693, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530580209294906e-05, "loss": 3.8541, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529741614543854e-05, "loss": 3.849, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528904657673175e-05, "loss": 3.8662, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528066062922123e-05, "loss": 3.8672, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527227468171071e-05, "loss": 3.8583, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526388873420019e-05, "loss": 3.8516, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525550278668967e-05, "loss": 3.8567, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524711683917915e-05, "loss": 3.8574, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523873089166863e-05, "loss": 3.8463, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523034494415811e-05, "loss": 3.8528, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522197537545132e-05, "loss": 3.8527, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.52135894279408e-05, "loss": 3.8572, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520520348043028e-05, "loss": 3.8536, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519681753291976e-05, "loss": 3.8543, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188447964212974e-05, "loss": 3.8378, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.5180062016702454e-05, "loss": 3.8538, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.5171676069191934e-05, "loss": 3.8465, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.5163290121681414e-05, "loss": 3.8615, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515492055297462e-05, "loss": 3.86, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.51465346054641e-05, "loss": 3.8555, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513814865795358e-05, "loss": 3.8385, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512976271044306e-05, "loss": 3.86, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512139314173627e-05, "loss": 3.8535, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511300719422575e-05, "loss": 3.8603, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510462124671523e-05, "loss": 3.8408, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509623529920471e-05, "loss": 3.8582, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508786573049793e-05, "loss": 3.8572, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507947978298741e-05, "loss": 3.8648, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507109383547689e-05, "loss": 3.8421, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506270788796637e-05, "loss": 3.8554, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054338319259576e-05, "loss": 3.8503, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045952371749056e-05, "loss": 3.8412, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037582803042265e-05, "loss": 3.8546, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5029196855531745e-05, "loss": 3.8583, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020810908021225e-05, "loss": 3.8467, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012424960510705e-05, "loss": 3.8459, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5004039013000185e-05, "loss": 3.845, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9098243713378906, "eval_runtime": 304.6475, "eval_samples_per_second": 1252.566, "eval_steps_per_second": 39.144, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.4995653065489665e-05, "loss": 3.8284, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4987267117979145e-05, "loss": 3.8318, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497888117046863e-05, "loss": 3.8498, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970495222958105e-05, "loss": 3.8442, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4962109275447585e-05, "loss": 3.8557, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953723327937065e-05, "loss": 3.8389, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945337380426545e-05, "loss": 3.8422, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.4936951432916025e-05, "loss": 3.8268, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.4928581864209234e-05, "loss": 3.8424, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.4920195916698714e-05, "loss": 3.8431, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.4911809969188194e-05, "loss": 3.8431, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.4903424021677674e-05, "loss": 3.8486, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4895087210578355e-05, "loss": 3.8339, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886701263067835e-05, "loss": 3.8354, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878315315557315e-05, "loss": 3.8291, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869929368046795e-05, "loss": 3.825, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861543420536275e-05, "loss": 3.832, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485315747302575e-05, "loss": 3.8307, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484477152551523e-05, "loss": 3.8291, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483638557800471e-05, "loss": 3.8529, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482799963049419e-05, "loss": 3.8349, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481961368298367e-05, "loss": 3.8332, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481122773547315e-05, "loss": 3.8407, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480284178796263e-05, "loss": 3.8426, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.4794472219255837e-05, "loss": 3.8236, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478608627174532e-05, "loss": 3.8367, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.47777003242348e-05, "loss": 3.8357, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476933075552801e-05, "loss": 3.8327, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476094480801749e-05, "loss": 3.8184, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475255886050697e-05, "loss": 3.8206, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474417291299645e-05, "loss": 3.8378, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473580334428966e-05, "loss": 3.837, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472741739677914e-05, "loss": 3.8312, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471903144926862e-05, "loss": 3.8354, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.47106455017581e-05, "loss": 3.826, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470227593305131e-05, "loss": 3.8334, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469388998554079e-05, "loss": 3.8189, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468550403803028e-05, "loss": 3.8269, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467711809051976e-05, "loss": 3.8109, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668748521812966e-05, "loss": 3.8233, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.4660362574302446e-05, "loss": 3.8199, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4651976626791926e-05, "loss": 3.8379, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.4643590679281406e-05, "loss": 3.826, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4635221110574615e-05, "loss": 3.8234, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.4626835163064095e-05, "loss": 3.8267, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.4618449215553575e-05, "loss": 3.8293, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.4610063268043055e-05, "loss": 3.8329, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.4601693699336264e-05, "loss": 3.8099, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4593307751825744e-05, "loss": 3.8153, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584921804315224e-05, "loss": 3.8319, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457653585680471e-05, "loss": 3.827, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456816628809792e-05, "loss": 3.8149, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.45597803405874e-05, "loss": 3.8114, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455139439307688e-05, "loss": 3.8173, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.454300844556636e-05, "loss": 3.806, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453463887685957e-05, "loss": 3.825, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452625292934905e-05, "loss": 3.81, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451786698183853e-05, "loss": 3.8208, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450948103432801e-05, "loss": 3.8212, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450111146562122e-05, "loss": 3.8151, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.44927255181107e-05, "loss": 3.8079, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448433957060018e-05, "loss": 3.8115, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475953623089664e-05, "loss": 3.803, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446758405438287e-05, "loss": 3.8125, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445919810687235e-05, "loss": 3.8203, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445081215936183e-05, "loss": 3.8086, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444242621185131e-05, "loss": 3.8078, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443405664314452e-05, "loss": 3.7984, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.4425670695634e-05, "loss": 3.8043, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441728474812348e-05, "loss": 3.8176, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440889880061296e-05, "loss": 3.8238, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440052923190617e-05, "loss": 3.8115, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439215966319939e-05, "loss": 3.8182, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438377371568887e-05, "loss": 3.8247, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437538776817835e-05, "loss": 3.8171, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436700182066783e-05, "loss": 3.7995, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435861587315731e-05, "loss": 3.8149, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435022992564679e-05, "loss": 3.8138, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434184397813627e-05, "loss": 3.8044, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433345803062575e-05, "loss": 3.8081, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4325088461918956e-05, "loss": 3.8159, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316702514408436e-05, "loss": 3.8225, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4308332945701645e-05, "loss": 3.8083, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4299946998191125e-05, "loss": 3.7916, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291561050680605e-05, "loss": 3.8087, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283175103170085e-05, "loss": 3.8086, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427478915565957e-05, "loss": 3.8086, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426640320814905e-05, "loss": 3.8111, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425801726063853e-05, "loss": 3.8091, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424964769193174e-05, "loss": 3.8117, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424126174442122e-05, "loss": 3.8023, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.42328757969107e-05, "loss": 3.7976, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422448984940018e-05, "loss": 3.8021, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421612028069339e-05, "loss": 3.8121, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420773433318287e-05, "loss": 3.8103, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419934838567235e-05, "loss": 3.815, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419096243816182e-05, "loss": 3.7931, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418259286945504e-05, "loss": 3.8077, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4174206921944525e-05, "loss": 3.8118, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165820974434005e-05, "loss": 3.8109, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415743502692348e-05, "loss": 3.8028, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4149065458216694e-05, "loss": 3.7978, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140679510706174e-05, "loss": 3.8017, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132293563195654e-05, "loss": 3.8075, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.412390761568513e-05, "loss": 3.7866, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411553804697834e-05, "loss": 3.8017, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410715209946782e-05, "loss": 3.8007, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098766151957296e-05, "loss": 3.8056, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090380204446776e-05, "loss": 3.7879, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408201063573999e-05, "loss": 3.8086, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407362468822948e-05, "loss": 3.7945, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406523874071895e-05, "loss": 3.8073, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405685279320843e-05, "loss": 3.7966, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404848322450165e-05, "loss": 3.7918, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.404011365579486e-05, "loss": 3.8072, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403172770828434e-05, "loss": 3.8121, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402334176077382e-05, "loss": 3.8019, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.40149558132633e-05, "loss": 3.7934, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400656986575277e-05, "loss": 3.7996, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399818391824225e-05, "loss": 3.8029, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398979797073173e-05, "loss": 3.7884, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398141202322122e-05, "loss": 3.799, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.3973042454514426e-05, "loss": 3.7943, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.3964656507003906e-05, "loss": 3.7985, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956270559493386e-05, "loss": 3.7973, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.3947884611982866e-05, "loss": 3.8007, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.3939515043276075e-05, "loss": 3.7834, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.3931129095765555e-05, "loss": 3.7952, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.3922743148255035e-05, "loss": 3.7943, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3914357200744515e-05, "loss": 3.8071, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905987632037724e-05, "loss": 3.799, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897601684527204e-05, "loss": 3.8037, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3889215737016684e-05, "loss": 3.7836, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388082978950617e-05, "loss": 3.8047, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387246022079938e-05, "loss": 3.8004, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386407427328886e-05, "loss": 3.8038, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385568832577834e-05, "loss": 3.7858, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384730237826782e-05, "loss": 3.8013, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383893280956103e-05, "loss": 3.8001, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383054686205051e-05, "loss": 3.8161, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382216091453999e-05, "loss": 3.7863, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381377496702947e-05, "loss": 3.7996, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380540539832268e-05, "loss": 3.7953, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379701945081216e-05, "loss": 3.7858, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378864988210537e-05, "loss": 3.8016, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378026393459485e-05, "loss": 3.8019, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377187798708433e-05, "loss": 3.797, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376349203957381e-05, "loss": 3.7882, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375510609206329e-05, "loss": 3.7952, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.8847007751464844, "eval_runtime": 320.5677, "eval_samples_per_second": 1190.36, "eval_steps_per_second": 37.2, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374672014455277e-05, "loss": 3.7847, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373833419704225e-05, "loss": 3.7763, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372996462833546e-05, "loss": 3.7951, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372157868082494e-05, "loss": 3.7931, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371319273331442e-05, "loss": 3.7984, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.37048067858039e-05, "loss": 3.7891, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369643721709711e-05, "loss": 3.7877, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368805126958659e-05, "loss": 3.777, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367966532207607e-05, "loss": 3.7884, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367127937456556e-05, "loss": 3.7898, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366290980585877e-05, "loss": 3.7898, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365452385834825e-05, "loss": 3.794, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364617066844519e-05, "loss": 3.7822, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.3637784720934665e-05, "loss": 3.7816, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.3629398773424145e-05, "loss": 3.7805, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.3621012825913625e-05, "loss": 3.7705, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.3612626878403105e-05, "loss": 3.7836, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.3604240930892585e-05, "loss": 3.7786, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.3595854983382065e-05, "loss": 3.7744, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.3587469035871545e-05, "loss": 3.7959, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.3579083088361025e-05, "loss": 3.786, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357069714085051e-05, "loss": 3.7847, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356231119333999e-05, "loss": 3.7887, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.35539416246332e-05, "loss": 3.7938, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354555567712268e-05, "loss": 3.7688, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353716972961216e-05, "loss": 3.7843, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352878378210164e-05, "loss": 3.7887, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352039783459112e-05, "loss": 3.7768, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.35120118870806e-05, "loss": 3.7709, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350362593957008e-05, "loss": 3.7683, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349523999205955e-05, "loss": 3.7871, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348687042335277e-05, "loss": 3.7857, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347848447584225e-05, "loss": 3.7841, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.347009852833173e-05, "loss": 3.7864, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346171258082121e-05, "loss": 3.7763, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3453343012114425e-05, "loss": 3.7796, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444957064603905e-05, "loss": 3.7728, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343657111709338e-05, "loss": 3.7765, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342818516958286e-05, "loss": 3.763, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419815600876074e-05, "loss": 3.7697, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411429653365554e-05, "loss": 3.7696, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340304370585503e-05, "loss": 3.7897, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.339465775834451e-05, "loss": 3.7772, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338628818963772e-05, "loss": 3.7737, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.33779022421272e-05, "loss": 3.7804, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336951629461668e-05, "loss": 3.7743, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336113034710616e-05, "loss": 3.7842, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335276077839938e-05, "loss": 3.7647, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334437483088885e-05, "loss": 3.7619, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333598888337833e-05, "loss": 3.7815, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332761931467155e-05, "loss": 3.7775, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331923336716103e-05, "loss": 3.7664, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.33108474196505e-05, "loss": 3.7675, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330246147213998e-05, "loss": 3.7701, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329407552462946e-05, "loss": 3.7552, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328568957711894e-05, "loss": 3.7776, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327730362960842e-05, "loss": 3.7628, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.32689176820979e-05, "loss": 3.768, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.3260548113391116e-05, "loss": 3.7762, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.3252162165880596e-05, "loss": 3.7668, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.3243776218370076e-05, "loss": 3.7635, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.3235390270859556e-05, "loss": 3.764, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.3227020702152765e-05, "loss": 3.7571, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.3218634754642245e-05, "loss": 3.7629, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.3210248807131725e-05, "loss": 3.7725, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.3201862859621205e-05, "loss": 3.7635, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.3193493290914414e-05, "loss": 3.7576, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.3185107343403894e-05, "loss": 3.7556, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.3176721395893374e-05, "loss": 3.7535, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.3168335448382854e-05, "loss": 3.7665, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315996587967607e-05, "loss": 3.7747, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315157993216555e-05, "loss": 3.7675, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314319398465503e-05, "loss": 3.7708, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313480803714451e-05, "loss": 3.7734, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312643846843772e-05, "loss": 3.7775, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.31180525209272e-05, "loss": 3.7514, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310966657341668e-05, "loss": 3.7668, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310128062590616e-05, "loss": 3.7698, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309291105719937e-05, "loss": 3.753, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308452510968885e-05, "loss": 3.7667, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307613916217833e-05, "loss": 3.7642, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306775321466781e-05, "loss": 3.7735, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305936726715729e-05, "loss": 3.7637, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050981319646775e-05, "loss": 3.7458, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042595372136254e-05, "loss": 3.7598, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3034209424625734e-05, "loss": 3.7617, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025839855918944e-05, "loss": 3.7672, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3017453908408424e-05, "loss": 3.7624, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300908433970163e-05, "loss": 3.766, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300069839219111e-05, "loss": 3.765, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299231244468059e-05, "loss": 3.7574, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298392649717007e-05, "loss": 3.7494, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297554054965955e-05, "loss": 3.7568, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296715460214903e-05, "loss": 3.7678, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295878503344224e-05, "loss": 3.7635, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.295039908593173e-05, "loss": 3.766, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294201313842121e-05, "loss": 3.7495, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293362719091069e-05, "loss": 3.7621, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292524124340016e-05, "loss": 3.7661, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291685529588964e-05, "loss": 3.7654, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290848572718286e-05, "loss": 3.7562, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.290009977967234e-05, "loss": 3.7552, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289171383216181e-05, "loss": 3.7549, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288332788465129e-05, "loss": 3.7638, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287494193714077e-05, "loss": 3.7394, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286655598963025e-05, "loss": 3.759, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285817004211973e-05, "loss": 3.7525, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284978409460921e-05, "loss": 3.762, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.2841414525902426e-05, "loss": 3.7421, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.2833028578391906e-05, "loss": 3.766, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824659009685115e-05, "loss": 3.7481, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2816273062174595e-05, "loss": 3.7629, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807887114664075e-05, "loss": 3.753, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2799501167153555e-05, "loss": 3.749, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2791115219643035e-05, "loss": 3.7592, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.2782745650936244e-05, "loss": 3.7698, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.2774359703425724e-05, "loss": 3.759, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.2765973755915204e-05, "loss": 3.7471, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.2757587808404684e-05, "loss": 3.7555, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.2749201860894164e-05, "loss": 3.7584, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274083229218738e-05, "loss": 3.7464, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273244634467686e-05, "loss": 3.756, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272406039716634e-05, "loss": 3.7465, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271567444965582e-05, "loss": 3.7544, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.27072885021453e-05, "loss": 3.7552, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.269890255463478e-05, "loss": 3.7574, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269051660712426e-05, "loss": 3.7369, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268213065961374e-05, "loss": 3.7526, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267376109090695e-05, "loss": 3.748, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266537514339643e-05, "loss": 3.7632, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265698919588591e-05, "loss": 3.756, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264860324837539e-05, "loss": 3.7599, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.2640233679668604e-05, "loss": 3.7401, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.2631847732158084e-05, "loss": 3.76, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623461784647564e-05, "loss": 3.7581, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2615075837137044e-05, "loss": 3.7595, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260670626843025e-05, "loss": 3.7465, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259832032091973e-05, "loss": 3.7556, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258993437340921e-05, "loss": 3.7588, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258154842589869e-05, "loss": 3.7695, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.25731788571919e-05, "loss": 3.7449, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256479290968138e-05, "loss": 3.7579, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255640696217086e-05, "loss": 3.7532, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254803739346407e-05, "loss": 3.7438, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253965144595356e-05, "loss": 3.7588, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253126549844304e-05, "loss": 3.7539, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252287955093252e-05, "loss": 3.7611, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2514493603422e-05, "loss": 3.7431, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250610765591147e-05, "loss": 3.7506, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.8689687252044678, "eval_runtime": 302.4237, "eval_samples_per_second": 1261.776, "eval_steps_per_second": 39.431, "step": 457920 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 3.1788668066616115e+17, "trial_name": null, "trial_params": null }