{ "best_metric": 3.8419296741485596, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/3/checkpoints/checkpoint-1068480", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 1908000, "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 }, { "epoch": 0.0, "learning_rate": 4.249772170840095e-05, "loss": 3.7402, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248933576089043e-05, "loss": 3.7302, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248094981337991e-05, "loss": 3.7525, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247256386586939e-05, "loss": 3.752, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.246417791835887e-05, "loss": 3.7572, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245579197084835e-05, "loss": 3.7461, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244740602333783e-05, "loss": 3.7397, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243902007582731e-05, "loss": 3.7386, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243065050712052e-05, "loss": 3.7444, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.2422264559610006e-05, "loss": 3.7467, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.2413878612099486e-05, "loss": 3.7505, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.2405509043392695e-05, "loss": 3.7552, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.2397139474685904e-05, "loss": 3.7417, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.2388753527175384e-05, "loss": 3.7374, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2380367579664864e-05, "loss": 3.7402, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.2371981632154344e-05, "loss": 3.7266, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.2363595684643824e-05, "loss": 3.7413, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.2355209737133304e-05, "loss": 3.7367, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.2346823789622784e-05, "loss": 3.7335, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.2338437842112264e-05, "loss": 3.755, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2330051894601744e-05, "loss": 3.7448, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321665947091224e-05, "loss": 3.746, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313279999580704e-05, "loss": 3.7454, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230491043087392e-05, "loss": 3.7533, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.22965244833634e-05, "loss": 3.7295, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228813853585288e-05, "loss": 3.7456, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227975258834236e-05, "loss": 3.7415, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.227136664083183e-05, "loss": 3.7353, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226298069332131e-05, "loss": 3.7332, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.225461112461453e-05, "loss": 3.7256, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246225177104e-05, "loss": 3.748, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223783922959348e-05, "loss": 3.7446, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222945328208296e-05, "loss": 3.7406, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222108371337618e-05, "loss": 3.7464, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221269776586566e-05, "loss": 3.7342, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220431181835514e-05, "loss": 3.7401, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219592587084462e-05, "loss": 3.7375, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.21875399233341e-05, "loss": 3.7317, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217917035462731e-05, "loss": 3.7223, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.2170784407116787e-05, "loss": 3.7296, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.2162398459606267e-05, "loss": 3.731, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.2154012512095746e-05, "loss": 3.7476, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.2145642943388956e-05, "loss": 3.7347, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137256995878436e-05, "loss": 3.734, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128871048367915e-05, "loss": 3.7447, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120485100857395e-05, "loss": 3.7339, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211209915334688e-05, "loss": 3.7442, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210371320583636e-05, "loss": 3.7269, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209532725832584e-05, "loss": 3.718, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208694131081532e-05, "loss": 3.7417, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207857174210853e-05, "loss": 3.7386, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.207020217340174e-05, "loss": 3.7311, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206181622589122e-05, "loss": 3.7242, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.20534302783807e-05, "loss": 3.7328, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204504433087018e-05, "loss": 3.7111, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203667476216339e-05, "loss": 3.7379, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202828881465287e-05, "loss": 3.725, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201990286714235e-05, "loss": 3.7266, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.2011516919631836e-05, "loss": 3.7384, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.2003130972121316e-05, "loss": 3.7262, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994761403414525e-05, "loss": 3.7226, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.1986375455904005e-05, "loss": 3.7286, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.1977989508393485e-05, "loss": 3.7155, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969603560882965e-05, "loss": 3.7246, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1961217613372445e-05, "loss": 3.7335, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952831665861925e-05, "loss": 3.7257, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.1944462097155134e-05, "loss": 3.7191, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.1936076149644614e-05, "loss": 3.7176, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.1927690202134094e-05, "loss": 3.7143, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919304254623574e-05, "loss": 3.7249, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.1910918307113054e-05, "loss": 3.7367, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.1902532359602534e-05, "loss": 3.7267, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.1894146412092014e-05, "loss": 3.734, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188577684338523e-05, "loss": 3.7322, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187739089587471e-05, "loss": 3.7402, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186900494836419e-05, "loss": 3.7153, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186061900085366e-05, "loss": 3.7305, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185224943214688e-05, "loss": 3.7289, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184386348463636e-05, "loss": 3.7104, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183547753712584e-05, "loss": 3.7314, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182709158961531e-05, "loss": 3.7287, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181872202090853e-05, "loss": 3.7327, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181033607339801e-05, "loss": 3.726, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180195012588749e-05, "loss": 3.7083, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179356417837697e-05, "loss": 3.721, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178517823086645e-05, "loss": 3.7222, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177679228335593e-05, "loss": 3.7286, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1768422714649136e-05, "loss": 3.7241, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.1760036767138616e-05, "loss": 3.7293, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.1751650819628096e-05, "loss": 3.726, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.1743264872117576e-05, "loss": 3.7201, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.1734878924607056e-05, "loss": 3.7122, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.1726492977096536e-05, "loss": 3.7166, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.1718107029586016e-05, "loss": 3.7314, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709737460879225e-05, "loss": 3.7297, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701351513368705e-05, "loss": 3.727, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169296556585819e-05, "loss": 3.7123, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.168457961834767e-05, "loss": 3.7221, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167619367083715e-05, "loss": 3.7282, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166780772332663e-05, "loss": 3.7261, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165943815461984e-05, "loss": 3.722, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165105220710932e-05, "loss": 3.7181, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.16426662595988e-05, "loss": 3.72, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163428031208828e-05, "loss": 3.7235, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162589436457776e-05, "loss": 3.7047, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.161750841706724e-05, "loss": 3.7182, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160912246955672e-05, "loss": 3.7136, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.16007365220462e-05, "loss": 3.7255, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159236695333941e-05, "loss": 3.7099, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158398100582889e-05, "loss": 3.7269, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575611437122105e-05, "loss": 3.7132, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1567225489611585e-05, "loss": 3.7225, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.1558839542101065e-05, "loss": 3.7216, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.1550453594590545e-05, "loss": 3.7104, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.1542067647080025e-05, "loss": 3.7227, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.1533698078373234e-05, "loss": 3.7327, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.1525312130862714e-05, "loss": 3.7195, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.1516926183352194e-05, "loss": 3.7194, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.1508540235841674e-05, "loss": 3.7112, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150015428833115e-05, "loss": 3.7225, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149178471962436e-05, "loss": 3.7155, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148339877211384e-05, "loss": 3.7157, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147501282460333e-05, "loss": 3.7098, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.14666268770928e-05, "loss": 3.7162, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145824092958228e-05, "loss": 3.7208, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144985498207176e-05, "loss": 3.72, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144146903456124e-05, "loss": 3.7024, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143309946585445e-05, "loss": 3.7194, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.142471351834393e-05, "loss": 3.7102, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141632757083341e-05, "loss": 3.7283, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140794162332289e-05, "loss": 3.7172, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139955567581237e-05, "loss": 3.726, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139118610710558e-05, "loss": 3.7036, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138280015959507e-05, "loss": 3.7266, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137441421208455e-05, "loss": 3.7207, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136602826457403e-05, "loss": 3.7236, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357658695867237e-05, "loss": 3.7063, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1349272748356717e-05, "loss": 3.7201, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340886800846197e-05, "loss": 3.7225, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.1332500853335676e-05, "loss": 3.732, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.1324114905825156e-05, "loss": 3.7104, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315728958314636e-05, "loss": 3.7203, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307359389607845e-05, "loss": 3.7183, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1298973442097325e-05, "loss": 3.7114, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290587494586805e-05, "loss": 3.7168, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282201547076285e-05, "loss": 3.721, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.12738319783695e-05, "loss": 3.7223, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.126544603085898e-05, "loss": 3.7104, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125706008334846e-05, "loss": 3.7172, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.8581275939941406, "eval_runtime": 312.3986, "eval_samples_per_second": 1221.488, "eval_steps_per_second": 38.172, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.124867413583794e-05, "loss": 3.7101, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.124028818832742e-05, "loss": 3.6965, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.12319022408169e-05, "loss": 3.7148, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122351629330638e-05, "loss": 3.717, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121513034579586e-05, "loss": 3.7192, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120676077708907e-05, "loss": 3.715, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119839120838228e-05, "loss": 3.7059, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119000526087176e-05, "loss": 3.7036, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118161931336124e-05, "loss": 3.7111, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117323336585072e-05, "loss": 3.7099, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.11648474183402e-05, "loss": 3.7147, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.1156477849633415e-05, "loss": 3.719, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.1148091902122895e-05, "loss": 3.7078, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.1139705954612375e-05, "loss": 3.7045, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.1131320007101855e-05, "loss": 3.7049, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.1122934059591335e-05, "loss": 3.6901, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.1114564490884544e-05, "loss": 3.7076, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.1106178543374024e-05, "loss": 3.7025, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.1097792595863504e-05, "loss": 3.704, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.1089406648352984e-05, "loss": 3.7153, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108102070084246e-05, "loss": 3.7151, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.107265113213567e-05, "loss": 3.709, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106426518462515e-05, "loss": 3.7105, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105587923711463e-05, "loss": 3.7136, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104749328960411e-05, "loss": 3.6979, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103910734209359e-05, "loss": 3.7099, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103073777338681e-05, "loss": 3.7092, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102235182587628e-05, "loss": 3.7018, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101396587836576e-05, "loss": 3.6963, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.100557993085524e-05, "loss": 3.6962, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.099721036214846e-05, "loss": 3.7083, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.098882441463793e-05, "loss": 3.7141, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.098043846712741e-05, "loss": 3.7078, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.097205251961689e-05, "loss": 3.7115, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.096366657210638e-05, "loss": 3.6977, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.095528062459586e-05, "loss": 3.7059, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.094689467708534e-05, "loss": 3.7077, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938525108378546e-05, "loss": 3.6917, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0930139160868026e-05, "loss": 3.6947, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.0921753213357506e-05, "loss": 3.6946, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913367265846986e-05, "loss": 3.6968, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0904997697140195e-05, "loss": 3.7144, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.0896611749629675e-05, "loss": 3.7003, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.0888225802119155e-05, "loss": 3.696, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.0879839854608635e-05, "loss": 3.711, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.0871453907098115e-05, "loss": 3.7023, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.0863067959587595e-05, "loss": 3.7092, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.0854682012077075e-05, "loss": 3.6938, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084631244337029e-05, "loss": 3.6852, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083792649585977e-05, "loss": 3.7114, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082954054834925e-05, "loss": 3.7033, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082115460083873e-05, "loss": 3.6975, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081276865332821e-05, "loss": 3.6963, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080438270581769e-05, "loss": 3.6901, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.07960131371109e-05, "loss": 3.6846, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078762718960038e-05, "loss": 3.6983, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077924124208986e-05, "loss": 3.6934, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077085529457934e-05, "loss": 3.6959, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076248572587255e-05, "loss": 3.7034, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075409977836203e-05, "loss": 3.6946, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.0745713830851515e-05, "loss": 3.6872, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0737327883340995e-05, "loss": 3.7005, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.072894193583047e-05, "loss": 3.6817, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.0720572367123684e-05, "loss": 3.6933, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.0712186419613164e-05, "loss": 3.6961, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.0703800472102644e-05, "loss": 3.6948, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069541452459212e-05, "loss": 3.6849, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.06870285770816e-05, "loss": 3.6874, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067865900837481e-05, "loss": 3.6795, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.0670273060864286e-05, "loss": 3.6936, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.0661887113353766e-05, "loss": 3.7033, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065350116584325e-05, "loss": 3.6961, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064511521833273e-05, "loss": 3.6979, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063674564962594e-05, "loss": 3.6986, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062835970211542e-05, "loss": 3.7104, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.06199737546049e-05, "loss": 3.6804, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061158780709438e-05, "loss": 3.6999, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.060321823838759e-05, "loss": 3.7002, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.059483229087707e-05, "loss": 3.6754, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.058644634336655e-05, "loss": 3.7011, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.057806039585603e-05, "loss": 3.6926, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.056969082714924e-05, "loss": 3.7013, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056130487963872e-05, "loss": 3.6953, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.05529189321282e-05, "loss": 3.6776, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.054453298461769e-05, "loss": 3.6843, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.0536147037107167e-05, "loss": 3.6928, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.0527761089596647e-05, "loss": 3.6961, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.0519391520889856e-05, "loss": 3.6906, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.0511005573379336e-05, "loss": 3.6957, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.0502619625868816e-05, "loss": 3.6923, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.0494233678358296e-05, "loss": 3.6873, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.0485847730847775e-05, "loss": 3.6844, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.0477461783337255e-05, "loss": 3.6857, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.0469092214630465e-05, "loss": 3.6964, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.0460706267119944e-05, "loss": 3.6977, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.0452320319609424e-05, "loss": 3.7009, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.0443934372098904e-05, "loss": 3.6784, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.0435548424588384e-05, "loss": 3.6912, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042716247707787e-05, "loss": 3.6976, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041877652956735e-05, "loss": 3.6956, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041040696086056e-05, "loss": 3.6895, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040202101335004e-05, "loss": 3.6857, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039363506583952e-05, "loss": 3.6886, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.0385249118329e-05, "loss": 3.6921, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037686317081848e-05, "loss": 3.6723, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036849360211169e-05, "loss": 3.691, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036010765460117e-05, "loss": 3.6795, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035172170709065e-05, "loss": 3.6957, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034333575958012e-05, "loss": 3.6809, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033496619087334e-05, "loss": 3.689, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.0326580243362825e-05, "loss": 3.6853, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.0318194295852305e-05, "loss": 3.6934, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030980834834178e-05, "loss": 3.6886, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030142240083126e-05, "loss": 3.6764, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.0293052832124474e-05, "loss": 3.6908, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284666884613954e-05, "loss": 3.6994, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.027628093710343e-05, "loss": 3.6891, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.026789498959291e-05, "loss": 3.6899, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.025950904208239e-05, "loss": 3.6783, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.025112309457187e-05, "loss": 3.6896, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.024273714706135e-05, "loss": 3.6904, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.023436757835456e-05, "loss": 3.6788, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.022598163084404e-05, "loss": 3.6828, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.021759568333352e-05, "loss": 3.6849, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209209735823e-05, "loss": 3.691, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.020082378831248e-05, "loss": 3.6911, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019243784080196e-05, "loss": 3.6721, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.018405189329144e-05, "loss": 3.6886, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017568232458465e-05, "loss": 3.6756, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016729637707413e-05, "loss": 3.6973, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015891042956361e-05, "loss": 3.6887, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015052448205309e-05, "loss": 3.6942, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014213853454257e-05, "loss": 3.6718, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013375258703205e-05, "loss": 3.6987, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012538301832526e-05, "loss": 3.6881, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011699707081474e-05, "loss": 3.6908, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010861112330423e-05, "loss": 3.6813, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010022517579371e-05, "loss": 3.6847, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009183922828319e-05, "loss": 3.6898, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008345328077267e-05, "loss": 3.7064, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007506733326214e-05, "loss": 3.68, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006668138575162e-05, "loss": 3.6897, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.0058311817044836e-05, "loss": 3.6921, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.004992586953431e-05, "loss": 3.6817, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.004153992202379e-05, "loss": 3.6811, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003315397451327e-05, "loss": 3.6898, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.0024784405806485e-05, "loss": 3.6928, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.0016398458295965e-05, "loss": 3.6816, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.0008012510785445e-05, "loss": 3.6885, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.8512063026428223, "eval_runtime": 308.6832, "eval_samples_per_second": 1236.19, "eval_steps_per_second": 38.632, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.9999626563274925e-05, "loss": 3.6742, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.9991240615764405e-05, "loss": 3.67, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.9982854668253885e-05, "loss": 3.6822, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.9974468720743364e-05, "loss": 3.6843, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.9966099152036574e-05, "loss": 3.6922, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.9957713204526054e-05, "loss": 3.6801, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.9949327257015534e-05, "loss": 3.6786, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.9940941309505013e-05, "loss": 3.6777, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993257174079822e-05, "loss": 3.6772, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.99241857932877e-05, "loss": 3.6799, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991579984577718e-05, "loss": 3.685, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990741389826666e-05, "loss": 3.6862, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.989902795075615e-05, "loss": 3.6758, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.989064200324563e-05, "loss": 3.6782, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.988227243453884e-05, "loss": 3.6772, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.987388648702832e-05, "loss": 3.6599, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.98655005395178e-05, "loss": 3.6744, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.985711459200728e-05, "loss": 3.6734, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.984872864449676e-05, "loss": 3.6751, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.984035907578997e-05, "loss": 3.6825, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.983197312827945e-05, "loss": 3.6865, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.982358718076893e-05, "loss": 3.6807, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.981520123325841e-05, "loss": 3.6817, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9806831664551616e-05, "loss": 3.6834, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.97984457170411e-05, "loss": 3.67, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979005976953058e-05, "loss": 3.6818, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978167382202006e-05, "loss": 3.6788, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977328787450954e-05, "loss": 3.6727, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.976491830580275e-05, "loss": 3.6728, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975653235829223e-05, "loss": 3.6647, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974814641078171e-05, "loss": 3.6755, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.973976046327119e-05, "loss": 3.6877, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.97313908945644e-05, "loss": 3.6792, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972300494705388e-05, "loss": 3.6768, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971461899954336e-05, "loss": 3.6675, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970623305203284e-05, "loss": 3.6809, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.9697863483326056e-05, "loss": 3.6764, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.9689477535815536e-05, "loss": 3.6677, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.9681091588305016e-05, "loss": 3.6659, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.9672705640794496e-05, "loss": 3.6634, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.9664336072087705e-05, "loss": 3.6652, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.9655950124577185e-05, "loss": 3.686, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.9647564177066665e-05, "loss": 3.6739, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.9639178229556145e-05, "loss": 3.6701, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.9630808660849354e-05, "loss": 3.6802, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.9622422713338834e-05, "loss": 3.6713, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.9614036765828314e-05, "loss": 3.6834, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.9605650818317794e-05, "loss": 3.6679, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.9597264870807274e-05, "loss": 3.6489, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.9588878923296754e-05, "loss": 3.6854, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.9580492975786234e-05, "loss": 3.6723, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957212340707945e-05, "loss": 3.6717, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956373745956892e-05, "loss": 3.6673, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.95553515120584e-05, "loss": 3.6598, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954696556454788e-05, "loss": 3.6617, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.953859599584109e-05, "loss": 3.6696, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.953021004833057e-05, "loss": 3.6672, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.952182410082005e-05, "loss": 3.6655, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.951343815330953e-05, "loss": 3.679, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950506858460275e-05, "loss": 3.6641, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949668263709223e-05, "loss": 3.658, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.948829668958171e-05, "loss": 3.6766, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.947991074207119e-05, "loss": 3.6518, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.947152479456067e-05, "loss": 3.6593, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946315522585388e-05, "loss": 3.6732, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945476927834336e-05, "loss": 3.6672, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944638333083284e-05, "loss": 3.6545, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943799738332232e-05, "loss": 3.6601, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.9429627814615526e-05, "loss": 3.654, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.9421241867105006e-05, "loss": 3.6649, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.9412855919594486e-05, "loss": 3.6745, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.9404469972083966e-05, "loss": 3.6683, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939610040337718e-05, "loss": 3.67, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938771445586666e-05, "loss": 3.674, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937932850835614e-05, "loss": 3.6796, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.937094256084562e-05, "loss": 3.6557, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936257299213883e-05, "loss": 3.6737, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935418704462831e-05, "loss": 3.6666, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934580109711779e-05, "loss": 3.6492, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933741514960727e-05, "loss": 3.6717, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932904558090048e-05, "loss": 3.6669, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932065963338996e-05, "loss": 3.6767, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931227368587944e-05, "loss": 3.6681, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930388773836892e-05, "loss": 3.6504, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295518169662135e-05, "loss": 3.6569, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287132222151615e-05, "loss": 3.6667, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.9278746274641095e-05, "loss": 3.6656, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.9270360327130575e-05, "loss": 3.6694, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.9261974379620055e-05, "loss": 3.6649, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.9253588432109535e-05, "loss": 3.6616, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.9245202484599015e-05, "loss": 3.6636, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9236832915892224e-05, "loss": 3.6557, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.9228446968381704e-05, "loss": 3.6588, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.9220061020871184e-05, "loss": 3.6689, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.9211675073360664e-05, "loss": 3.6676, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.9203289125850144e-05, "loss": 3.6739, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919491955714335e-05, "loss": 3.6519, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918653360963283e-05, "loss": 3.6637, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917814766212232e-05, "loss": 3.6678, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.91697617146118e-05, "loss": 3.6663, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.916139214590501e-05, "loss": 3.6632, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.915300619839449e-05, "loss": 3.6601, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.914462025088397e-05, "loss": 3.6628, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.913623430337345e-05, "loss": 3.6619, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.912786473466666e-05, "loss": 3.6521, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911947878715614e-05, "loss": 3.6612, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.911109283964562e-05, "loss": 3.6517, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.91027068921351e-05, "loss": 3.6709, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909432094462458e-05, "loss": 3.6541, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.9085951375917787e-05, "loss": 3.6613, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907756542840727e-05, "loss": 3.6536, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906917948089675e-05, "loss": 3.6711, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.9060793533386226e-05, "loss": 3.6588, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.9052407585875706e-05, "loss": 3.6524, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904403801716892e-05, "loss": 3.6672, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.90356520696584e-05, "loss": 3.6711, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9027266122147875e-05, "loss": 3.6639, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.9018880174637355e-05, "loss": 3.6622, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901051060593057e-05, "loss": 3.6524, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900212465842005e-05, "loss": 3.6612, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.8993738710909524e-05, "loss": 3.6621, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898535276339901e-05, "loss": 3.6534, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897698319469223e-05, "loss": 3.6535, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.89685972471817e-05, "loss": 3.66, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.896021129967118e-05, "loss": 3.6663, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.895182535216066e-05, "loss": 3.6612, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.894343940465014e-05, "loss": 3.6493, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893506983594335e-05, "loss": 3.6596, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892668388843283e-05, "loss": 3.6515, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891829794092231e-05, "loss": 3.6696, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.890991199341179e-05, "loss": 3.6622, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.8901542424705e-05, "loss": 3.6683, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889315647719448e-05, "loss": 3.6453, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.8884770529683965e-05, "loss": 3.6722, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.8876384582173445e-05, "loss": 3.6597, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.8868015013466654e-05, "loss": 3.6642, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859629065956134e-05, "loss": 3.6566, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8851243118445614e-05, "loss": 3.6546, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.8842857170935094e-05, "loss": 3.6624, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.88344876022283e-05, "loss": 3.6831, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882610165471778e-05, "loss": 3.6522, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881771570720726e-05, "loss": 3.6631, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880932975969674e-05, "loss": 3.6667, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880096019098995e-05, "loss": 3.6537, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879257424347943e-05, "loss": 3.6577, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878418829596892e-05, "loss": 3.664, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.87758023484584e-05, "loss": 3.6659, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876743277975161e-05, "loss": 3.6583, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875904683224109e-05, "loss": 3.6612, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.846519708633423, "eval_runtime": 304.9923, "eval_samples_per_second": 1251.149, "eval_steps_per_second": 39.099, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.875066088473057e-05, "loss": 3.6488, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.874227493722005e-05, "loss": 3.6417, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873388898970953e-05, "loss": 3.6553, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872550304219901e-05, "loss": 3.6617, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.8717133473492216e-05, "loss": 3.6654, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.8708747525981696e-05, "loss": 3.6514, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.8700361578471176e-05, "loss": 3.6558, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.8691975630960656e-05, "loss": 3.649, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.8683606062253865e-05, "loss": 3.6501, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.867522011474335e-05, "loss": 3.6557, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.866683416723283e-05, "loss": 3.6605, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.865844821972231e-05, "loss": 3.6573, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.865006227221179e-05, "loss": 3.6599, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.8641692703505e-05, "loss": 3.6455, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.863330675599448e-05, "loss": 3.6496, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.862492080848396e-05, "loss": 3.6354, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.861653486097344e-05, "loss": 3.6494, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.860816529226665e-05, "loss": 3.6503, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.859977934475613e-05, "loss": 3.6458, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.859139339724561e-05, "loss": 3.6563, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.858300744973509e-05, "loss": 3.6615, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.8574637881028306e-05, "loss": 3.657, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.8566251933517786e-05, "loss": 3.6567, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.8557865986007266e-05, "loss": 3.6537, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.8549480038496746e-05, "loss": 3.6461, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.8541110469789955e-05, "loss": 3.6554, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.8532724522279435e-05, "loss": 3.6535, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.8524338574768915e-05, "loss": 3.6533, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.8515952627258395e-05, "loss": 3.6447, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.8507566679747875e-05, "loss": 3.6421, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.8499197111041084e-05, "loss": 3.6459, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.8490811163530564e-05, "loss": 3.6597, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.8482425216020044e-05, "loss": 3.6568, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.8474039268509524e-05, "loss": 3.6518, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.846566969980274e-05, "loss": 3.6419, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.845728375229222e-05, "loss": 3.6501, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.84488978047817e-05, "loss": 3.6566, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.844051185727118e-05, "loss": 3.6416, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843214228856439e-05, "loss": 3.6402, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842375634105387e-05, "loss": 3.6339, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.841537039354335e-05, "loss": 3.6423, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840698444603283e-05, "loss": 3.657, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.839861487732604e-05, "loss": 3.6523, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.839022892981552e-05, "loss": 3.6433, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.8381842982305e-05, "loss": 3.6539, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.837345703479448e-05, "loss": 3.6472, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.836507108728396e-05, "loss": 3.6541, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.835670151857717e-05, "loss": 3.6483, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.834831557106665e-05, "loss": 3.6207, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.833992962355613e-05, "loss": 3.6636, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8331543676045606e-05, "loss": 3.644, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.8323157728535086e-05, "loss": 3.6519, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.83147881598283e-05, "loss": 3.6382, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.8306402212317775e-05, "loss": 3.6415, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.8298016264807255e-05, "loss": 3.6329, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.8289630317296735e-05, "loss": 3.6437, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.828126074858995e-05, "loss": 3.6407, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.827287480107943e-05, "loss": 3.6387, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.826448885356891e-05, "loss": 3.6564, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.825610290605839e-05, "loss": 3.6378, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.82477333373516e-05, "loss": 3.6317, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.823934738984108e-05, "loss": 3.6508, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.823096144233056e-05, "loss": 3.627, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.822257549482004e-05, "loss": 3.6335, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821418954730952e-05, "loss": 3.6478, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820581997860273e-05, "loss": 3.6422, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.819743403109221e-05, "loss": 3.6333, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.818904808358169e-05, "loss": 3.6312, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.818066213607117e-05, "loss": 3.6325, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.8172292567364385e-05, "loss": 3.6395, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.8163906619853864e-05, "loss": 3.6503, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.8155520672343344e-05, "loss": 3.6414, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.8147134724832824e-05, "loss": 3.6454, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.8138748777322304e-05, "loss": 3.647, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.8130379208615513e-05, "loss": 3.6555, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.812199326110499e-05, "loss": 3.6289, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.811360731359447e-05, "loss": 3.6513, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810523774488768e-05, "loss": 3.639, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.809685179737716e-05, "loss": 3.6262, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.808846584986664e-05, "loss": 3.6434, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.808007990235612e-05, "loss": 3.6518, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.807171033364934e-05, "loss": 3.645, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806332438613882e-05, "loss": 3.6491, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.80549384386283e-05, "loss": 3.6255, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.804655249111778e-05, "loss": 3.6291, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.803816654360726e-05, "loss": 3.6449, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.802979697490047e-05, "loss": 3.6392, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.802141102738995e-05, "loss": 3.6411, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801302507987943e-05, "loss": 3.6441, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.800463913236891e-05, "loss": 3.6392, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.7996269563662116e-05, "loss": 3.638, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.7987883616151596e-05, "loss": 3.6348, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.7979497668641076e-05, "loss": 3.6329, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.7971111721130556e-05, "loss": 3.6445, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.796274215242377e-05, "loss": 3.645, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.795435620491325e-05, "loss": 3.6452, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.794597025740273e-05, "loss": 3.6318, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.793758430989221e-05, "loss": 3.6348, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.792921474118542e-05, "loss": 3.6441, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.79208287936749e-05, "loss": 3.6417, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.791244284616438e-05, "loss": 3.6391, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.790405689865386e-05, "loss": 3.6404, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789568732994707e-05, "loss": 3.6364, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.788730138243655e-05, "loss": 3.6327, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.787891543492603e-05, "loss": 3.6357, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.787052948741551e-05, "loss": 3.633, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.7862159918708725e-05, "loss": 3.6276, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.7853773971198205e-05, "loss": 3.6491, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.7845388023687685e-05, "loss": 3.6321, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.7837002076177165e-05, "loss": 3.6354, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.7828632507470374e-05, "loss": 3.6286, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.7820246559959854e-05, "loss": 3.6445, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.7811860612449334e-05, "loss": 3.6362, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.7803474664938814e-05, "loss": 3.6276, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.7795105096232023e-05, "loss": 3.6448, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.77867191487215e-05, "loss": 3.6455, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.777833320121098e-05, "loss": 3.6408, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.776994725370046e-05, "loss": 3.6366, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.776157768499368e-05, "loss": 3.6316, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.775319173748316e-05, "loss": 3.637, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.774480578997264e-05, "loss": 3.639, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773641984246212e-05, "loss": 3.6292, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772805027375533e-05, "loss": 3.6318, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.771966432624481e-05, "loss": 3.6378, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771127837873429e-05, "loss": 3.6403, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.770289243122377e-05, "loss": 3.6376, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769450648371325e-05, "loss": 3.6255, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.768613691500646e-05, "loss": 3.6383, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.767775096749594e-05, "loss": 3.627, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.766936501998542e-05, "loss": 3.6453, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.76609790724749e-05, "loss": 3.636, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.765260950376811e-05, "loss": 3.6482, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.764422355625759e-05, "loss": 3.618, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.763583760874707e-05, "loss": 3.6499, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.762745166123655e-05, "loss": 3.6354, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.761908209252976e-05, "loss": 3.6443, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.761069614501924e-05, "loss": 3.6336, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760231019750872e-05, "loss": 3.6245, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.75939242499982e-05, "loss": 3.6426, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758555468129141e-05, "loss": 3.6568, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757716873378089e-05, "loss": 3.6354, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756878278627037e-05, "loss": 3.6363, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.756039683875985e-05, "loss": 3.6406, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755201089124933e-05, "loss": 3.6311, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.7543641322542546e-05, "loss": 3.633, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.7535255375032026e-05, "loss": 3.6424, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.7526869427521506e-05, "loss": 3.64, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.7518499858814715e-05, "loss": 3.6389, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.7510113911304195e-05, "loss": 3.6363, "step": 762880 }, { "epoch": 0.03, "eval_loss": 3.8436856269836426, "eval_runtime": 312.0745, "eval_samples_per_second": 1222.756, "eval_steps_per_second": 38.212, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.7501727963793675e-05, "loss": 3.6243, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.749334201628315e-05, "loss": 3.6183, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.748495606877263e-05, "loss": 3.6327, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.7476586500065844e-05, "loss": 3.6399, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.7468200552555324e-05, "loss": 3.6416, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.7459814605044804e-05, "loss": 3.6298, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.7451428657534284e-05, "loss": 3.6339, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.74430590888275e-05, "loss": 3.6256, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.743467314131698e-05, "loss": 3.6298, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.742628719380645e-05, "loss": 3.6307, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.741790124629593e-05, "loss": 3.6329, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.740953167758915e-05, "loss": 3.6351, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.740114573007862e-05, "loss": 3.6393, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.73927597825681e-05, "loss": 3.6207, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.738437383505758e-05, "loss": 3.6294, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.73760042663508e-05, "loss": 3.6086, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.736761831884028e-05, "loss": 3.6255, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.735923237132976e-05, "loss": 3.6252, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.735084642381924e-05, "loss": 3.6241, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.7342476855112454e-05, "loss": 3.6299, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.733409090760193e-05, "loss": 3.6386, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.732570496009141e-05, "loss": 3.6352, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.731731901258089e-05, "loss": 3.6347, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.7308949443874096e-05, "loss": 3.6277, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.7300563496363576e-05, "loss": 3.6263, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.7292177548853056e-05, "loss": 3.6328, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.7283791601342536e-05, "loss": 3.6294, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.7275405653832016e-05, "loss": 3.6314, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.726703608512523e-05, "loss": 3.6205, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.725865013761471e-05, "loss": 3.6191, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.725026419010419e-05, "loss": 3.6205, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.724187824259367e-05, "loss": 3.6389, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.723350867388688e-05, "loss": 3.6376, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.722512272637636e-05, "loss": 3.6253, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.721673677886584e-05, "loss": 3.6259, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.720835083135532e-05, "loss": 3.6219, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.719998126264853e-05, "loss": 3.6366, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.719159531513801e-05, "loss": 3.6221, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.718320936762749e-05, "loss": 3.6187, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.717482342011697e-05, "loss": 3.6113, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.7166453851410185e-05, "loss": 3.6207, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.7158067903899665e-05, "loss": 3.6308, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.7149681956389145e-05, "loss": 3.6294, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.7141296008878625e-05, "loss": 3.6245, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.7132926440171834e-05, "loss": 3.6319, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.7124540492661314e-05, "loss": 3.6231, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.7116154545150794e-05, "loss": 3.6323, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.7107768597640274e-05, "loss": 3.6262, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709939902893348e-05, "loss": 3.6008, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.709101308142296e-05, "loss": 3.6387, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.708262713391244e-05, "loss": 3.6214, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.707424118640192e-05, "loss": 3.6321, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.706587161769514e-05, "loss": 3.619, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.705748567018462e-05, "loss": 3.6156, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.70490997226741e-05, "loss": 3.6108, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.704071377516358e-05, "loss": 3.6237, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.703234420645679e-05, "loss": 3.6192, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702395825894627e-05, "loss": 3.6143, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.701557231143575e-05, "loss": 3.6346, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700718636392523e-05, "loss": 3.6214, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.699881679521844e-05, "loss": 3.6031, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.699043084770792e-05, "loss": 3.631, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.69820449001974e-05, "loss": 3.6093, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.697365895268688e-05, "loss": 3.6094, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.696528938398009e-05, "loss": 3.6254, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.695690343646957e-05, "loss": 3.6179, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.694851748895905e-05, "loss": 3.6097, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.694013154144853e-05, "loss": 3.61, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.693176197274174e-05, "loss": 3.6109, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.692337602523122e-05, "loss": 3.617, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.69149900777207e-05, "loss": 3.627, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.690660413021018e-05, "loss": 3.6206, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.689823456150339e-05, "loss": 3.6254, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.688984861399287e-05, "loss": 3.6226, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.688146266648235e-05, "loss": 3.6328, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687307671897183e-05, "loss": 3.6124, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.6864707150265046e-05, "loss": 3.6257, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.6856321202754526e-05, "loss": 3.6166, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.6847935255244006e-05, "loss": 3.606, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.6839549307733486e-05, "loss": 3.6199, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.6831179739026695e-05, "loss": 3.6303, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.6822793791516175e-05, "loss": 3.6212, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.6814407844005655e-05, "loss": 3.6292, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.6806021896495135e-05, "loss": 3.5984, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.6797652327788344e-05, "loss": 3.6123, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.6789266380277824e-05, "loss": 3.6203, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.6780880432767304e-05, "loss": 3.6214, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.6772494485256784e-05, "loss": 3.6138, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.676412491655e-05, "loss": 3.6251, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.675573896903948e-05, "loss": 3.6182, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.674735302152896e-05, "loss": 3.6202, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.673896707401844e-05, "loss": 3.6068, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.673058112650792e-05, "loss": 3.6116, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.672221155780113e-05, "loss": 3.6254, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.671382561029061e-05, "loss": 3.622, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.670543966278009e-05, "loss": 3.6271, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.669705371526957e-05, "loss": 3.6125, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.668868414656278e-05, "loss": 3.6081, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.668029819905226e-05, "loss": 3.6225, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.667191225154174e-05, "loss": 3.6232, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.666352630403122e-05, "loss": 3.6184, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.66551403565207e-05, "loss": 3.6167, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.6646770787813914e-05, "loss": 3.6143, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.6638384840303393e-05, "loss": 3.6127, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.6629998892792873e-05, "loss": 3.6165, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.662161294528235e-05, "loss": 3.6087, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.661324337657556e-05, "loss": 3.6072, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.660485742906504e-05, "loss": 3.6208, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.659647148155452e-05, "loss": 3.618, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.6588085534044e-05, "loss": 3.6075, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.657971596533721e-05, "loss": 3.6141, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.657133001782669e-05, "loss": 3.6177, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.656294407031617e-05, "loss": 3.6172, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.655455812280565e-05, "loss": 3.6057, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.654618855409887e-05, "loss": 3.6213, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.653780260658835e-05, "loss": 3.6261, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.652941665907783e-05, "loss": 3.6218, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.65210307115673e-05, "loss": 3.6123, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.6512661142860516e-05, "loss": 3.6126, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.6504275195349996e-05, "loss": 3.613, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.6495889247839476e-05, "loss": 3.6217, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.648750330032895e-05, "loss": 3.6086, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.6479133731622165e-05, "loss": 3.6107, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.6470747784111645e-05, "loss": 3.6113, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.6462361836601125e-05, "loss": 3.6214, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.6453975889090605e-05, "loss": 3.6151, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.644560632038382e-05, "loss": 3.6031, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.64372203728733e-05, "loss": 3.6175, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.6428834425362774e-05, "loss": 3.6049, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.6420448477852254e-05, "loss": 3.6245, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.641207890914547e-05, "loss": 3.6147, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.640369296163495e-05, "loss": 3.624, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.639530701412442e-05, "loss": 3.5992, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.63869210666139e-05, "loss": 3.623, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.637855149790712e-05, "loss": 3.6174, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.63701655503966e-05, "loss": 3.6194, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.636177960288608e-05, "loss": 3.6148, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635339365537556e-05, "loss": 3.6019, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.6345024086668775e-05, "loss": 3.6254, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.633663813915825e-05, "loss": 3.627, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.632825219164773e-05, "loss": 3.6204, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.631986624413721e-05, "loss": 3.6132, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.631149667543042e-05, "loss": 3.6193, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.63031107279199e-05, "loss": 3.6143, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.6294724780409377e-05, "loss": 3.607, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.6286338832898857e-05, "loss": 3.6224, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.6277969264192066e-05, "loss": 3.6188, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.626958331668155e-05, "loss": 3.6216, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.626119736917103e-05, "loss": 3.6152, "step": 839168 }, { "epoch": 1.03, "eval_loss": 3.8421192169189453, "eval_runtime": 312.4339, "eval_samples_per_second": 1221.35, "eval_steps_per_second": 38.168, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.625281142166051e-05, "loss": 3.6022, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.624442547414999e-05, "loss": 3.5977, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.623603952663947e-05, "loss": 3.6121, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.622765357912895e-05, "loss": 3.6184, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.621928401042216e-05, "loss": 3.6229, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.621089806291164e-05, "loss": 3.6085, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.620251211540112e-05, "loss": 3.6113, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.61941261678906e-05, "loss": 3.6077, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.618575659918381e-05, "loss": 3.6063, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.617737065167329e-05, "loss": 3.6066, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.616898470416277e-05, "loss": 3.6157, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.616059875665225e-05, "loss": 3.6184, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.6152229187945466e-05, "loss": 3.6163, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.6143843240434946e-05, "loss": 3.5991, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.6135457292924426e-05, "loss": 3.6068, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.6127071345413906e-05, "loss": 3.5857, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.6118685397903386e-05, "loss": 3.6083, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.6110315829196595e-05, "loss": 3.609, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.6101929881686075e-05, "loss": 3.6024, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.6093543934175555e-05, "loss": 3.6086, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.6085157986665035e-05, "loss": 3.618, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.6076788417958244e-05, "loss": 3.6111, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.6068402470447724e-05, "loss": 3.6169, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.6060016522937204e-05, "loss": 3.6094, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.6051630575426684e-05, "loss": 3.6065, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.60432610067199e-05, "loss": 3.6083, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603487505920938e-05, "loss": 3.6057, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.602648911169886e-05, "loss": 3.613, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.601810316418834e-05, "loss": 3.6047, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.600973359548155e-05, "loss": 3.5965, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.600134764797103e-05, "loss": 3.6026, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.599296170046051e-05, "loss": 3.6145, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.598457575294999e-05, "loss": 3.6151, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.59762061842432e-05, "loss": 3.6082, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.596782023673268e-05, "loss": 3.6015, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.595943428922216e-05, "loss": 3.6055, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.595104834171164e-05, "loss": 3.6155, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.594267877300485e-05, "loss": 3.5967, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.593429282549433e-05, "loss": 3.5996, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.592590687798381e-05, "loss": 3.5979, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.591752093047329e-05, "loss": 3.5997, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.59091513617665e-05, "loss": 3.6114, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.590076541425598e-05, "loss": 3.6024, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.589237946674546e-05, "loss": 3.6074, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.588399351923494e-05, "loss": 3.609, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.587562395052815e-05, "loss": 3.6076, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.586723800301763e-05, "loss": 3.6078, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.585885205550711e-05, "loss": 3.6109, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.585046610799659e-05, "loss": 3.5797, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.584208016048608e-05, "loss": 3.6162, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.583371059177929e-05, "loss": 3.6035, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.582532464426877e-05, "loss": 3.6109, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.581693869675825e-05, "loss": 3.5993, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.580855274924773e-05, "loss": 3.5981, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.5800183180540936e-05, "loss": 3.5866, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.5791797233030416e-05, "loss": 3.5996, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.5783411285519896e-05, "loss": 3.6065, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.5775025338009376e-05, "loss": 3.5893, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.5766655769302585e-05, "loss": 3.6164, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.5758269821792065e-05, "loss": 3.6021, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.5749883874281545e-05, "loss": 3.5836, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.574149792677103e-05, "loss": 3.6073, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.573312835806424e-05, "loss": 3.5932, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.572474241055372e-05, "loss": 3.5898, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.57163564630432e-05, "loss": 3.6045, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.5707970515532674e-05, "loss": 3.5998, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.569960094682589e-05, "loss": 3.59, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.569121499931537e-05, "loss": 3.5901, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.568282905180485e-05, "loss": 3.5909, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.567444310429432e-05, "loss": 3.598, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.566607353558754e-05, "loss": 3.6037, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.565768758807702e-05, "loss": 3.6, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.56493016405665e-05, "loss": 3.608, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.564091569305598e-05, "loss": 3.6012, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.563252974554546e-05, "loss": 3.6126, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.5624160176838674e-05, "loss": 3.5953, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.561577422932815e-05, "loss": 3.6081, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.560738828181763e-05, "loss": 3.5942, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.559900233430711e-05, "loss": 3.5872, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.559063276560032e-05, "loss": 3.6019, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.5582246818089796e-05, "loss": 3.6049, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.5573860870579276e-05, "loss": 3.6059, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.5565474923068756e-05, "loss": 3.6106, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.555710535436197e-05, "loss": 3.5778, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.554871940685145e-05, "loss": 3.5918, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.554033345934093e-05, "loss": 3.6009, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.553194751183041e-05, "loss": 3.6043, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.552357794312362e-05, "loss": 3.5947, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.55151919956131e-05, "loss": 3.6044, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.550680604810258e-05, "loss": 3.6011, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.549842010059206e-05, "loss": 3.5966, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.549005053188527e-05, "loss": 3.5908, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.548166458437475e-05, "loss": 3.5901, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.547327863686423e-05, "loss": 3.6049, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.546489268935371e-05, "loss": 3.6054, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.5456523120646926e-05, "loss": 3.6031, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.5448137173136406e-05, "loss": 3.5953, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.5439751225625886e-05, "loss": 3.5918, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.5431365278115366e-05, "loss": 3.6026, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.5422995709408575e-05, "loss": 3.6044, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.5414609761898055e-05, "loss": 3.5967, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.5406223814387535e-05, "loss": 3.5983, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.5397837866877015e-05, "loss": 3.5946, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.5389468298170224e-05, "loss": 3.5956, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.5381082350659704e-05, "loss": 3.592, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.5372696403149184e-05, "loss": 3.5914, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.5364310455638664e-05, "loss": 3.5905, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.535594088693188e-05, "loss": 3.6027, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.534755493942136e-05, "loss": 3.594, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.533916899191084e-05, "loss": 3.5931, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.533078304440032e-05, "loss": 3.5876, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.532241347569353e-05, "loss": 3.5966, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.531402752818301e-05, "loss": 3.6023, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.530564158067249e-05, "loss": 3.5901, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.529725563316197e-05, "loss": 3.5973, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.528888606445518e-05, "loss": 3.6058, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.528050011694466e-05, "loss": 3.6048, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.527211416943414e-05, "loss": 3.5934, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.526374460072735e-05, "loss": 3.595, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.525535865321683e-05, "loss": 3.5938, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.524697270570631e-05, "loss": 3.6059, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.523858675819579e-05, "loss": 3.5885, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.5230217189489e-05, "loss": 3.5892, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.522183124197848e-05, "loss": 3.5897, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521344529446796e-05, "loss": 3.6004, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.520505934695744e-05, "loss": 3.5993, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.519667339944692e-05, "loss": 3.5878, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.518830383074013e-05, "loss": 3.5935, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.517991788322961e-05, "loss": 3.585, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.517153193571909e-05, "loss": 3.6034, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.516314598820857e-05, "loss": 3.5999, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.515477641950179e-05, "loss": 3.6038, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514639047199127e-05, "loss": 3.5838, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.513800452448075e-05, "loss": 3.6002, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.512961857697023e-05, "loss": 3.5996, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.5121249008263436e-05, "loss": 3.5964, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.5112863060752916e-05, "loss": 3.5965, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.5104477113242396e-05, "loss": 3.584, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.5096091165731876e-05, "loss": 3.6079, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.5087721597025085e-05, "loss": 3.6066, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.5079335649514565e-05, "loss": 3.6006, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.5070949702004045e-05, "loss": 3.5944, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.5062563754493525e-05, "loss": 3.6013, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.505419418578674e-05, "loss": 3.5935, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.504580823827622e-05, "loss": 3.5881, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.50374222907657e-05, "loss": 3.6023, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.502903634325518e-05, "loss": 3.5982, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.502066677454839e-05, "loss": 3.6036, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.501228082703787e-05, "loss": 3.5959, "step": 915456 }, { "epoch": 0.03, "eval_loss": 3.8426454067230225, "eval_runtime": 305.731, "eval_samples_per_second": 1248.127, "eval_steps_per_second": 39.005, "step": 915840 }, { "epoch": 1.0, "learning_rate": 3.500389487952735e-05, "loss": 3.5891, "step": 915968 }, { "epoch": 1.0, "learning_rate": 3.499550893201683e-05, "loss": 3.5744, "step": 916480 }, { "epoch": 1.0, "learning_rate": 3.498713936331004e-05, "loss": 3.5925, "step": 916992 }, { "epoch": 1.0, "learning_rate": 3.497875341579952e-05, "loss": 3.5992, "step": 917504 }, { "epoch": 1.0, "learning_rate": 3.4970367468289e-05, "loss": 3.5998, "step": 918016 }, { "epoch": 1.0, "learning_rate": 3.496198152077848e-05, "loss": 3.5917, "step": 918528 }, { "epoch": 1.0, "learning_rate": 3.4953611952071694e-05, "loss": 3.5991, "step": 919040 }, { "epoch": 1.0, "learning_rate": 3.4945226004561174e-05, "loss": 3.5843, "step": 919552 }, { "epoch": 1.0, "learning_rate": 3.4936840057050654e-05, "loss": 3.5862, "step": 920064 }, { "epoch": 1.0, "learning_rate": 3.4928454109540134e-05, "loss": 3.5854, "step": 920576 }, { "epoch": 1.0, "learning_rate": 3.492008454083334e-05, "loss": 3.6004, "step": 921088 }, { "epoch": 1.0, "learning_rate": 3.491169859332282e-05, "loss": 3.5969, "step": 921600 }, { "epoch": 1.0, "learning_rate": 3.49033126458123e-05, "loss": 3.6004, "step": 922112 }, { "epoch": 1.0, "learning_rate": 3.489492669830178e-05, "loss": 3.582, "step": 922624 }, { "epoch": 1.0, "learning_rate": 3.488655712959499e-05, "loss": 3.5894, "step": 923136 }, { "epoch": 1.0, "learning_rate": 3.487817118208447e-05, "loss": 3.5661, "step": 923648 }, { "epoch": 1.0, "learning_rate": 3.486978523457395e-05, "loss": 3.5896, "step": 924160 }, { "epoch": 1.0, "learning_rate": 3.486139928706343e-05, "loss": 3.5867, "step": 924672 }, { "epoch": 1.0, "learning_rate": 3.485302971835665e-05, "loss": 3.5816, "step": 925184 }, { "epoch": 1.0, "learning_rate": 3.484464377084613e-05, "loss": 3.5914, "step": 925696 }, { "epoch": 1.0, "learning_rate": 3.483625782333561e-05, "loss": 3.5983, "step": 926208 }, { "epoch": 1.0, "learning_rate": 3.482787187582509e-05, "loss": 3.5924, "step": 926720 }, { "epoch": 1.0, "learning_rate": 3.48195023071183e-05, "loss": 3.5999, "step": 927232 }, { "epoch": 1.0, "learning_rate": 3.481111635960778e-05, "loss": 3.588, "step": 927744 }, { "epoch": 1.0, "learning_rate": 3.480273041209726e-05, "loss": 3.59, "step": 928256 }, { "epoch": 1.0, "learning_rate": 3.4794344464586737e-05, "loss": 3.5899, "step": 928768 }, { "epoch": 1.0, "learning_rate": 3.4785974895879946e-05, "loss": 3.5854, "step": 929280 }, { "epoch": 1.0, "learning_rate": 3.4777588948369426e-05, "loss": 3.596, "step": 929792 }, { "epoch": 1.0, "learning_rate": 3.4769203000858906e-05, "loss": 3.5852, "step": 930304 }, { "epoch": 1.0, "learning_rate": 3.4760817053348386e-05, "loss": 3.5762, "step": 930816 }, { "epoch": 1.01, "learning_rate": 3.47524474846416e-05, "loss": 3.5857, "step": 931328 }, { "epoch": 1.01, "learning_rate": 3.474406153713108e-05, "loss": 3.5934, "step": 931840 }, { "epoch": 1.01, "learning_rate": 3.473567558962056e-05, "loss": 3.5948, "step": 932352 }, { "epoch": 1.01, "learning_rate": 3.472728964211004e-05, "loss": 3.5924, "step": 932864 }, { "epoch": 1.01, "learning_rate": 3.471892007340325e-05, "loss": 3.5855, "step": 933376 }, { "epoch": 1.01, "learning_rate": 3.471053412589273e-05, "loss": 3.5861, "step": 933888 }, { "epoch": 1.01, "learning_rate": 3.470214817838221e-05, "loss": 3.5957, "step": 934400 }, { "epoch": 1.01, "learning_rate": 3.469376223087169e-05, "loss": 3.579, "step": 934912 }, { "epoch": 1.01, "learning_rate": 3.46853926621649e-05, "loss": 3.5802, "step": 935424 }, { "epoch": 1.01, "learning_rate": 3.467700671465438e-05, "loss": 3.5798, "step": 935936 }, { "epoch": 1.01, "learning_rate": 3.466862076714386e-05, "loss": 3.5815, "step": 936448 }, { "epoch": 1.01, "learning_rate": 3.466023481963334e-05, "loss": 3.5878, "step": 936960 }, { "epoch": 1.01, "learning_rate": 3.4651865250926555e-05, "loss": 3.5901, "step": 937472 }, { "epoch": 1.01, "learning_rate": 3.4643479303416035e-05, "loss": 3.5879, "step": 937984 }, { "epoch": 1.01, "learning_rate": 3.4635093355905515e-05, "loss": 3.5883, "step": 938496 }, { "epoch": 1.01, "learning_rate": 3.4626707408394995e-05, "loss": 3.5879, "step": 939008 }, { "epoch": 1.01, "learning_rate": 3.4618337839688204e-05, "loss": 3.5876, "step": 939520 }, { "epoch": 1.01, "learning_rate": 3.4609951892177684e-05, "loss": 3.5959, "step": 940032 }, { "epoch": 1.01, "learning_rate": 3.4601565944667164e-05, "loss": 3.5613, "step": 940544 }, { "epoch": 1.01, "learning_rate": 3.4593179997156644e-05, "loss": 3.5966, "step": 941056 }, { "epoch": 1.01, "learning_rate": 3.458481042844985e-05, "loss": 3.5845, "step": 941568 }, { "epoch": 1.01, "learning_rate": 3.457642448093933e-05, "loss": 3.5903, "step": 942080 }, { "epoch": 1.01, "learning_rate": 3.456803853342881e-05, "loss": 3.5823, "step": 942592 }, { "epoch": 1.01, "learning_rate": 3.455965258591829e-05, "loss": 3.5784, "step": 943104 }, { "epoch": 1.01, "learning_rate": 3.455128301721151e-05, "loss": 3.5707, "step": 943616 }, { "epoch": 1.01, "learning_rate": 3.454289706970099e-05, "loss": 3.5792, "step": 944128 }, { "epoch": 1.01, "learning_rate": 3.453451112219047e-05, "loss": 3.5898, "step": 944640 }, { "epoch": 1.01, "learning_rate": 3.452612517467994e-05, "loss": 3.5716, "step": 945152 }, { "epoch": 1.01, "learning_rate": 3.451775560597316e-05, "loss": 3.5973, "step": 945664 }, { "epoch": 1.01, "learning_rate": 3.450936965846264e-05, "loss": 3.5835, "step": 946176 }, { "epoch": 1.01, "learning_rate": 3.450098371095212e-05, "loss": 3.5622, "step": 946688 }, { "epoch": 1.01, "learning_rate": 3.449259776344159e-05, "loss": 3.5905, "step": 947200 }, { "epoch": 1.01, "learning_rate": 3.448422819473481e-05, "loss": 3.573, "step": 947712 }, { "epoch": 1.01, "learning_rate": 3.447584224722429e-05, "loss": 3.5715, "step": 948224 }, { "epoch": 1.01, "learning_rate": 3.4467456299713767e-05, "loss": 3.5835, "step": 948736 }, { "epoch": 1.01, "learning_rate": 3.4459070352203247e-05, "loss": 3.5828, "step": 949248 }, { "epoch": 1.01, "learning_rate": 3.4450700783496456e-05, "loss": 3.5704, "step": 949760 }, { "epoch": 1.01, "learning_rate": 3.444231483598594e-05, "loss": 3.5756, "step": 950272 }, { "epoch": 1.01, "learning_rate": 3.4433928888475416e-05, "loss": 3.5705, "step": 950784 }, { "epoch": 1.01, "learning_rate": 3.4425542940964896e-05, "loss": 3.5755, "step": 951296 }, { "epoch": 1.01, "learning_rate": 3.441717337225811e-05, "loss": 3.5877, "step": 951808 }, { "epoch": 1.01, "learning_rate": 3.440878742474759e-05, "loss": 3.5841, "step": 952320 }, { "epoch": 1.01, "learning_rate": 3.4400401477237065e-05, "loss": 3.5898, "step": 952832 }, { "epoch": 1.01, "learning_rate": 3.4392015529726544e-05, "loss": 3.5815, "step": 953344 }, { "epoch": 1.01, "learning_rate": 3.438364596101976e-05, "loss": 3.5943, "step": 953856 }, { "epoch": 1.01, "learning_rate": 3.4375260013509234e-05, "loss": 3.5764, "step": 954368 }, { "epoch": 1.01, "learning_rate": 3.4366874065998713e-05, "loss": 3.5915, "step": 954880 }, { "epoch": 1.01, "learning_rate": 3.4358488118488193e-05, "loss": 3.5742, "step": 955392 }, { "epoch": 1.01, "learning_rate": 3.435011854978141e-05, "loss": 3.5672, "step": 955904 }, { "epoch": 1.01, "learning_rate": 3.434173260227089e-05, "loss": 3.5839, "step": 956416 }, { "epoch": 1.01, "learning_rate": 3.433334665476037e-05, "loss": 3.5837, "step": 956928 }, { "epoch": 1.01, "learning_rate": 3.432496070724985e-05, "loss": 3.588, "step": 957440 }, { "epoch": 1.01, "learning_rate": 3.4316591138543065e-05, "loss": 3.5892, "step": 957952 }, { "epoch": 1.01, "learning_rate": 3.430820519103254e-05, "loss": 3.5658, "step": 958464 }, { "epoch": 1.01, "learning_rate": 3.429981924352202e-05, "loss": 3.5724, "step": 958976 }, { "epoch": 1.01, "learning_rate": 3.42914332960115e-05, "loss": 3.5799, "step": 959488 }, { "epoch": 1.01, "learning_rate": 3.428306372730471e-05, "loss": 3.5835, "step": 960000 }, { "epoch": 1.01, "learning_rate": 3.427467777979419e-05, "loss": 3.5758, "step": 960512 }, { "epoch": 1.01, "learning_rate": 3.426629183228367e-05, "loss": 3.587, "step": 961024 }, { "epoch": 1.01, "learning_rate": 3.425790588477315e-05, "loss": 3.5893, "step": 961536 }, { "epoch": 1.02, "learning_rate": 3.424953631606636e-05, "loss": 3.5738, "step": 962048 }, { "epoch": 1.02, "learning_rate": 3.424115036855584e-05, "loss": 3.5724, "step": 962560 }, { "epoch": 1.02, "learning_rate": 3.423276442104532e-05, "loss": 3.5761, "step": 963072 }, { "epoch": 1.02, "learning_rate": 3.42243784735348e-05, "loss": 3.5821, "step": 963584 }, { "epoch": 1.02, "learning_rate": 3.421600890482801e-05, "loss": 3.5884, "step": 964096 }, { "epoch": 1.02, "learning_rate": 3.420762295731749e-05, "loss": 3.5857, "step": 964608 }, { "epoch": 1.02, "learning_rate": 3.419923700980697e-05, "loss": 3.5761, "step": 965120 }, { "epoch": 1.02, "learning_rate": 3.419085106229645e-05, "loss": 3.571, "step": 965632 }, { "epoch": 1.02, "learning_rate": 3.418248149358966e-05, "loss": 3.5879, "step": 966144 }, { "epoch": 1.02, "learning_rate": 3.417409554607914e-05, "loss": 3.5851, "step": 966656 }, { "epoch": 1.02, "learning_rate": 3.416570959856862e-05, "loss": 3.5811, "step": 967168 }, { "epoch": 1.02, "learning_rate": 3.41573236510581e-05, "loss": 3.5759, "step": 967680 }, { "epoch": 1.02, "learning_rate": 3.414895408235132e-05, "loss": 3.5769, "step": 968192 }, { "epoch": 1.02, "learning_rate": 3.41405681348408e-05, "loss": 3.5767, "step": 968704 }, { "epoch": 1.02, "learning_rate": 3.4132182187330277e-05, "loss": 3.5752, "step": 969216 }, { "epoch": 1.02, "learning_rate": 3.4123796239819757e-05, "loss": 3.5757, "step": 969728 }, { "epoch": 1.02, "learning_rate": 3.4115426671112966e-05, "loss": 3.5731, "step": 970240 }, { "epoch": 1.02, "learning_rate": 3.4107040723602446e-05, "loss": 3.5798, "step": 970752 }, { "epoch": 1.02, "learning_rate": 3.4098654776091926e-05, "loss": 3.5822, "step": 971264 }, { "epoch": 1.02, "learning_rate": 3.4090268828581405e-05, "loss": 3.5701, "step": 971776 }, { "epoch": 1.02, "learning_rate": 3.4081899259874615e-05, "loss": 3.5738, "step": 972288 }, { "epoch": 1.02, "learning_rate": 3.4073513312364095e-05, "loss": 3.5775, "step": 972800 }, { "epoch": 1.02, "learning_rate": 3.4065127364853574e-05, "loss": 3.5838, "step": 973312 }, { "epoch": 1.02, "learning_rate": 3.4056741417343054e-05, "loss": 3.5693, "step": 973824 }, { "epoch": 1.02, "learning_rate": 3.404837184863627e-05, "loss": 3.5836, "step": 974336 }, { "epoch": 1.02, "learning_rate": 3.403998590112575e-05, "loss": 3.5822, "step": 974848 }, { "epoch": 1.02, "learning_rate": 3.403159995361523e-05, "loss": 3.5907, "step": 975360 }, { "epoch": 1.02, "learning_rate": 3.402321400610471e-05, "loss": 3.5788, "step": 975872 }, { "epoch": 1.02, "learning_rate": 3.401484443739792e-05, "loss": 3.5772, "step": 976384 }, { "epoch": 1.02, "learning_rate": 3.40064584898874e-05, "loss": 3.5792, "step": 976896 }, { "epoch": 1.02, "learning_rate": 3.399807254237688e-05, "loss": 3.5837, "step": 977408 }, { "epoch": 1.02, "learning_rate": 3.398968659486636e-05, "loss": 3.5687, "step": 977920 }, { "epoch": 1.02, "learning_rate": 3.398131702615957e-05, "loss": 3.5756, "step": 978432 }, { "epoch": 1.02, "learning_rate": 3.397293107864905e-05, "loss": 3.5739, "step": 978944 }, { "epoch": 1.02, "learning_rate": 3.396454513113853e-05, "loss": 3.5795, "step": 979456 }, { "epoch": 1.02, "learning_rate": 3.395615918362801e-05, "loss": 3.5773, "step": 979968 }, { "epoch": 1.02, "learning_rate": 3.3947789614921224e-05, "loss": 3.5731, "step": 980480 }, { "epoch": 1.02, "learning_rate": 3.3939403667410704e-05, "loss": 3.5727, "step": 980992 }, { "epoch": 1.02, "learning_rate": 3.3931017719900184e-05, "loss": 3.5706, "step": 981504 }, { "epoch": 1.02, "learning_rate": 3.3922631772389664e-05, "loss": 3.5885, "step": 982016 }, { "epoch": 1.02, "learning_rate": 3.391426220368287e-05, "loss": 3.5777, "step": 982528 }, { "epoch": 1.02, "learning_rate": 3.390587625617235e-05, "loss": 3.5879, "step": 983040 }, { "epoch": 1.02, "learning_rate": 3.389749030866183e-05, "loss": 3.5645, "step": 983552 }, { "epoch": 1.02, "learning_rate": 3.388910436115131e-05, "loss": 3.584, "step": 984064 }, { "epoch": 1.02, "learning_rate": 3.388073479244452e-05, "loss": 3.5834, "step": 984576 }, { "epoch": 1.02, "learning_rate": 3.3872348844934e-05, "loss": 3.5807, "step": 985088 }, { "epoch": 1.02, "learning_rate": 3.386396289742348e-05, "loss": 3.5752, "step": 985600 }, { "epoch": 1.02, "learning_rate": 3.385557694991296e-05, "loss": 3.565, "step": 986112 }, { "epoch": 1.02, "learning_rate": 3.384720738120618e-05, "loss": 3.5939, "step": 986624 }, { "epoch": 1.02, "learning_rate": 3.383882143369566e-05, "loss": 3.5891, "step": 987136 }, { "epoch": 1.02, "learning_rate": 3.383043548618514e-05, "loss": 3.5838, "step": 987648 }, { "epoch": 1.02, "learning_rate": 3.382204953867462e-05, "loss": 3.5746, "step": 988160 }, { "epoch": 1.02, "learning_rate": 3.381367996996783e-05, "loss": 3.5862, "step": 988672 }, { "epoch": 1.02, "learning_rate": 3.3805294022457307e-05, "loss": 3.5767, "step": 989184 }, { "epoch": 1.02, "learning_rate": 3.3796908074946787e-05, "loss": 3.5679, "step": 989696 }, { "epoch": 1.02, "learning_rate": 3.3788522127436266e-05, "loss": 3.5902, "step": 990208 }, { "epoch": 1.02, "learning_rate": 3.3780152558729476e-05, "loss": 3.5767, "step": 990720 }, { "epoch": 1.02, "learning_rate": 3.3771766611218956e-05, "loss": 3.5869, "step": 991232 }, { "epoch": 1.02, "learning_rate": 3.3763380663708435e-05, "loss": 3.5758, "step": 991744 }, { "epoch": 1.03, "eval_loss": 3.842242479324341, "eval_runtime": 304.7579, "eval_samples_per_second": 1252.112, "eval_steps_per_second": 39.129, "step": 992160 }, { "epoch": 0.0, "learning_rate": 3.3754994716197915e-05, "loss": 3.5888, "step": 992256 }, { "epoch": 0.0, "learning_rate": 3.37466087686874e-05, "loss": 3.5562, "step": 992768 }, { "epoch": 0.0, "learning_rate": 3.373822282117688e-05, "loss": 3.5716, "step": 993280 }, { "epoch": 0.0, "learning_rate": 3.372983687366636e-05, "loss": 3.5857, "step": 993792 }, { "epoch": 0.0, "learning_rate": 3.372146730495957e-05, "loss": 3.5799, "step": 994304 }, { "epoch": 0.0, "learning_rate": 3.371308135744905e-05, "loss": 3.576, "step": 994816 }, { "epoch": 0.0, "learning_rate": 3.370469540993853e-05, "loss": 3.579, "step": 995328 }, { "epoch": 0.0, "learning_rate": 3.369630946242801e-05, "loss": 3.5689, "step": 995840 }, { "epoch": 0.0, "learning_rate": 3.368793989372122e-05, "loss": 3.5661, "step": 996352 }, { "epoch": 0.0, "learning_rate": 3.36795539462107e-05, "loss": 3.5709, "step": 996864 }, { "epoch": 0.0, "learning_rate": 3.367116799870018e-05, "loss": 3.5824, "step": 997376 }, { "epoch": 0.0, "learning_rate": 3.366278205118966e-05, "loss": 3.5778, "step": 997888 }, { "epoch": 0.0, "learning_rate": 3.3654428861286605e-05, "loss": 3.5877, "step": 998400 }, { "epoch": 0.0, "learning_rate": 3.3646042913776085e-05, "loss": 3.5602, "step": 998912 }, { "epoch": 0.0, "learning_rate": 3.3637656966265565e-05, "loss": 3.5664, "step": 999424 }, { "epoch": 0.0, "learning_rate": 3.3629271018755045e-05, "loss": 3.5518, "step": 999936 }, { "epoch": 0.0, "learning_rate": 3.3620885071244525e-05, "loss": 3.57, "step": 1000448 }, { "epoch": 0.0, "learning_rate": 3.3612499123734005e-05, "loss": 3.5708, "step": 1000960 }, { "epoch": 0.0, "learning_rate": 3.3604113176223485e-05, "loss": 3.5668, "step": 1001472 }, { "epoch": 0.0, "learning_rate": 3.3595727228712965e-05, "loss": 3.5666, "step": 1001984 }, { "epoch": 0.0, "learning_rate": 3.3587357660006174e-05, "loss": 3.587, "step": 1002496 }, { "epoch": 0.0, "learning_rate": 3.3578971712495654e-05, "loss": 3.5738, "step": 1003008 }, { "epoch": 0.0, "learning_rate": 3.3570585764985134e-05, "loss": 3.5811, "step": 1003520 }, { "epoch": 0.0, "learning_rate": 3.3562199817474614e-05, "loss": 3.5731, "step": 1004032 }, { "epoch": 0.0, "learning_rate": 3.355383024876782e-05, "loss": 3.576, "step": 1004544 }, { "epoch": 0.0, "learning_rate": 3.35454443012573e-05, "loss": 3.5698, "step": 1005056 }, { "epoch": 0.0, "learning_rate": 3.353705835374679e-05, "loss": 3.5684, "step": 1005568 }, { "epoch": 0.0, "learning_rate": 3.352867240623626e-05, "loss": 3.5796, "step": 1006080 }, { "epoch": 0.0, "learning_rate": 3.352030283752948e-05, "loss": 3.5704, "step": 1006592 }, { "epoch": 0.0, "learning_rate": 3.351191689001896e-05, "loss": 3.5557, "step": 1007104 }, { "epoch": 0.01, "learning_rate": 3.350353094250844e-05, "loss": 3.5727, "step": 1007616 }, { "epoch": 0.01, "learning_rate": 3.349514499499791e-05, "loss": 3.5748, "step": 1008128 }, { "epoch": 0.01, "learning_rate": 3.348677542629113e-05, "loss": 3.5765, "step": 1008640 }, { "epoch": 0.01, "learning_rate": 3.347838947878061e-05, "loss": 3.5716, "step": 1009152 }, { "epoch": 0.01, "learning_rate": 3.347000353127009e-05, "loss": 3.5706, "step": 1009664 }, { "epoch": 0.01, "learning_rate": 3.346161758375956e-05, "loss": 3.5707, "step": 1010176 }, { "epoch": 0.01, "learning_rate": 3.3453248015052776e-05, "loss": 3.579, "step": 1010688 }, { "epoch": 0.01, "learning_rate": 3.3444862067542256e-05, "loss": 3.5573, "step": 1011200 }, { "epoch": 0.01, "learning_rate": 3.3436476120031736e-05, "loss": 3.5651, "step": 1011712 }, { "epoch": 0.01, "learning_rate": 3.3428090172521216e-05, "loss": 3.5621, "step": 1012224 }, { "epoch": 0.01, "learning_rate": 3.341972060381443e-05, "loss": 3.5634, "step": 1012736 }, { "epoch": 0.01, "learning_rate": 3.341133465630391e-05, "loss": 3.5732, "step": 1013248 }, { "epoch": 0.01, "learning_rate": 3.3402948708793385e-05, "loss": 3.5767, "step": 1013760 }, { "epoch": 0.01, "learning_rate": 3.3394562761282865e-05, "loss": 3.5698, "step": 1014272 }, { "epoch": 0.01, "learning_rate": 3.338619319257608e-05, "loss": 3.5703, "step": 1014784 }, { "epoch": 0.01, "learning_rate": 3.337780724506556e-05, "loss": 3.5671, "step": 1015296 }, { "epoch": 0.01, "learning_rate": 3.3369421297555034e-05, "loss": 3.5733, "step": 1015808 }, { "epoch": 0.01, "learning_rate": 3.3361035350044514e-05, "loss": 3.5763, "step": 1016320 }, { "epoch": 0.01, "learning_rate": 3.335266578133773e-05, "loss": 3.5458, "step": 1016832 }, { "epoch": 0.01, "learning_rate": 3.334427983382721e-05, "loss": 3.5764, "step": 1017344 }, { "epoch": 0.01, "learning_rate": 3.333589388631669e-05, "loss": 3.5692, "step": 1017856 }, { "epoch": 0.01, "learning_rate": 3.332750793880617e-05, "loss": 3.5726, "step": 1018368 }, { "epoch": 0.01, "learning_rate": 3.3319138370099386e-05, "loss": 3.5666, "step": 1018880 }, { "epoch": 0.01, "learning_rate": 3.331075242258886e-05, "loss": 3.5598, "step": 1019392 }, { "epoch": 0.01, "learning_rate": 3.330236647507834e-05, "loss": 3.5575, "step": 1019904 }, { "epoch": 0.01, "learning_rate": 3.329398052756782e-05, "loss": 3.5606, "step": 1020416 }, { "epoch": 0.01, "learning_rate": 3.3285610958861035e-05, "loss": 3.573, "step": 1020928 }, { "epoch": 0.01, "learning_rate": 3.327722501135051e-05, "loss": 3.5535, "step": 1021440 }, { "epoch": 0.01, "learning_rate": 3.326883906383999e-05, "loss": 3.5825, "step": 1021952 }, { "epoch": 0.01, "learning_rate": 3.326045311632947e-05, "loss": 3.5641, "step": 1022464 }, { "epoch": 0.01, "learning_rate": 3.3252083547622684e-05, "loss": 3.5472, "step": 1022976 }, { "epoch": 0.01, "learning_rate": 3.3243697600112164e-05, "loss": 3.573, "step": 1023488 }, { "epoch": 0.01, "learning_rate": 3.3235311652601644e-05, "loss": 3.5513, "step": 1024000 }, { "epoch": 0.01, "learning_rate": 3.3226925705091124e-05, "loss": 3.5593, "step": 1024512 }, { "epoch": 0.01, "learning_rate": 3.321855613638433e-05, "loss": 3.5651, "step": 1025024 }, { "epoch": 0.01, "learning_rate": 3.321017018887381e-05, "loss": 3.5686, "step": 1025536 }, { "epoch": 0.01, "learning_rate": 3.320178424136329e-05, "loss": 3.5511, "step": 1026048 }, { "epoch": 0.01, "learning_rate": 3.319339829385277e-05, "loss": 3.5642, "step": 1026560 }, { "epoch": 0.01, "learning_rate": 3.318502872514598e-05, "loss": 3.5505, "step": 1027072 }, { "epoch": 0.01, "learning_rate": 3.317664277763546e-05, "loss": 3.561, "step": 1027584 }, { "epoch": 0.01, "learning_rate": 3.316825683012494e-05, "loss": 3.5719, "step": 1028096 }, { "epoch": 0.01, "learning_rate": 3.315987088261442e-05, "loss": 3.5626, "step": 1028608 }, { "epoch": 0.01, "learning_rate": 3.315150131390764e-05, "loss": 3.5738, "step": 1029120 }, { "epoch": 0.01, "learning_rate": 3.314311536639712e-05, "loss": 3.5656, "step": 1029632 }, { "epoch": 0.01, "learning_rate": 3.31347294188866e-05, "loss": 3.5797, "step": 1030144 }, { "epoch": 0.01, "learning_rate": 3.312634347137608e-05, "loss": 3.5585, "step": 1030656 }, { "epoch": 0.01, "learning_rate": 3.3117973902669286e-05, "loss": 3.5721, "step": 1031168 }, { "epoch": 0.01, "learning_rate": 3.3109587955158766e-05, "loss": 3.5604, "step": 1031680 }, { "epoch": 0.01, "learning_rate": 3.3101202007648246e-05, "loss": 3.5515, "step": 1032192 }, { "epoch": 0.01, "learning_rate": 3.3092816060137726e-05, "loss": 3.5675, "step": 1032704 }, { "epoch": 0.01, "learning_rate": 3.3084446491430935e-05, "loss": 3.5641, "step": 1033216 }, { "epoch": 0.01, "learning_rate": 3.3076060543920415e-05, "loss": 3.5716, "step": 1033728 }, { "epoch": 0.01, "learning_rate": 3.3067674596409895e-05, "loss": 3.5754, "step": 1034240 }, { "epoch": 0.01, "learning_rate": 3.3059288648899375e-05, "loss": 3.5545, "step": 1034752 }, { "epoch": 0.01, "learning_rate": 3.305091908019259e-05, "loss": 3.5519, "step": 1035264 }, { "epoch": 0.01, "learning_rate": 3.304253313268207e-05, "loss": 3.5634, "step": 1035776 }, { "epoch": 0.01, "learning_rate": 3.303414718517155e-05, "loss": 3.5666, "step": 1036288 }, { "epoch": 0.01, "learning_rate": 3.302576123766103e-05, "loss": 3.5617, "step": 1036800 }, { "epoch": 0.01, "learning_rate": 3.301739166895424e-05, "loss": 3.5641, "step": 1037312 }, { "epoch": 0.01, "learning_rate": 3.300900572144372e-05, "loss": 3.5688, "step": 1037824 }, { "epoch": 0.02, "learning_rate": 3.30006197739332e-05, "loss": 3.5613, "step": 1038336 }, { "epoch": 0.02, "learning_rate": 3.299223382642268e-05, "loss": 3.5596, "step": 1038848 }, { "epoch": 0.02, "learning_rate": 3.298386425771589e-05, "loss": 3.553, "step": 1039360 }, { "epoch": 0.02, "learning_rate": 3.297547831020537e-05, "loss": 3.5722, "step": 1039872 }, { "epoch": 0.02, "learning_rate": 3.296709236269485e-05, "loss": 3.5697, "step": 1040384 }, { "epoch": 0.02, "learning_rate": 3.295870641518433e-05, "loss": 3.5714, "step": 1040896 }, { "epoch": 0.02, "learning_rate": 3.2950336846477545e-05, "loss": 3.5572, "step": 1041408 }, { "epoch": 0.02, "learning_rate": 3.2941950898967025e-05, "loss": 3.5565, "step": 1041920 }, { "epoch": 0.02, "learning_rate": 3.2933564951456505e-05, "loss": 3.5705, "step": 1042432 }, { "epoch": 0.02, "learning_rate": 3.2925179003945985e-05, "loss": 3.5675, "step": 1042944 }, { "epoch": 0.02, "learning_rate": 3.2916809435239194e-05, "loss": 3.5632, "step": 1043456 }, { "epoch": 0.02, "learning_rate": 3.2908423487728674e-05, "loss": 3.5635, "step": 1043968 }, { "epoch": 0.02, "learning_rate": 3.2900037540218154e-05, "loss": 3.5568, "step": 1044480 }, { "epoch": 0.02, "learning_rate": 3.2891651592707634e-05, "loss": 3.5644, "step": 1044992 }, { "epoch": 0.02, "learning_rate": 3.288328202400084e-05, "loss": 3.5596, "step": 1045504 }, { "epoch": 0.02, "learning_rate": 3.287489607649032e-05, "loss": 3.5528, "step": 1046016 }, { "epoch": 0.02, "learning_rate": 3.28665101289798e-05, "loss": 3.5589, "step": 1046528 }, { "epoch": 0.02, "learning_rate": 3.285812418146928e-05, "loss": 3.5634, "step": 1047040 }, { "epoch": 0.02, "learning_rate": 3.28497546127625e-05, "loss": 3.5687, "step": 1047552 }, { "epoch": 0.02, "learning_rate": 3.284136866525198e-05, "loss": 3.5508, "step": 1048064 }, { "epoch": 0.02, "learning_rate": 3.283298271774146e-05, "loss": 3.5585, "step": 1048576 }, { "epoch": 0.02, "learning_rate": 3.282459677023094e-05, "loss": 3.5559, "step": 1049088 }, { "epoch": 0.02, "learning_rate": 3.281622720152415e-05, "loss": 3.5709, "step": 1049600 }, { "epoch": 0.02, "learning_rate": 3.280784125401363e-05, "loss": 3.5575, "step": 1050112 }, { "epoch": 0.02, "learning_rate": 3.279945530650311e-05, "loss": 3.5599, "step": 1050624 }, { "epoch": 0.02, "learning_rate": 3.279106935899259e-05, "loss": 3.5677, "step": 1051136 }, { "epoch": 0.02, "learning_rate": 3.2782699790285796e-05, "loss": 3.5734, "step": 1051648 }, { "epoch": 0.02, "learning_rate": 3.2774313842775276e-05, "loss": 3.5594, "step": 1052160 }, { "epoch": 0.02, "learning_rate": 3.2765927895264756e-05, "loss": 3.5609, "step": 1052672 }, { "epoch": 0.02, "learning_rate": 3.2757541947754236e-05, "loss": 3.5609, "step": 1053184 }, { "epoch": 0.02, "learning_rate": 3.274917237904745e-05, "loss": 3.5649, "step": 1053696 }, { "epoch": 0.02, "learning_rate": 3.274078643153693e-05, "loss": 3.5534, "step": 1054208 }, { "epoch": 0.02, "learning_rate": 3.273240048402641e-05, "loss": 3.5583, "step": 1054720 }, { "epoch": 0.02, "learning_rate": 3.272401453651589e-05, "loss": 3.5563, "step": 1055232 }, { "epoch": 0.02, "learning_rate": 3.27156449678091e-05, "loss": 3.5632, "step": 1055744 }, { "epoch": 0.02, "learning_rate": 3.270725902029858e-05, "loss": 3.5599, "step": 1056256 }, { "epoch": 0.02, "learning_rate": 3.269887307278806e-05, "loss": 3.5547, "step": 1056768 }, { "epoch": 0.02, "learning_rate": 3.269048712527754e-05, "loss": 3.5573, "step": 1057280 }, { "epoch": 0.02, "learning_rate": 3.268211755657075e-05, "loss": 3.5541, "step": 1057792 }, { "epoch": 0.02, "learning_rate": 3.267373160906023e-05, "loss": 3.5688, "step": 1058304 }, { "epoch": 0.02, "learning_rate": 3.266534566154971e-05, "loss": 3.5629, "step": 1058816 }, { "epoch": 0.02, "learning_rate": 3.265695971403919e-05, "loss": 3.5713, "step": 1059328 }, { "epoch": 0.02, "learning_rate": 3.264857376652867e-05, "loss": 3.5499, "step": 1059840 }, { "epoch": 0.02, "learning_rate": 3.2640204197821886e-05, "loss": 3.5662, "step": 1060352 }, { "epoch": 0.02, "learning_rate": 3.2631818250311366e-05, "loss": 3.5682, "step": 1060864 }, { "epoch": 0.02, "learning_rate": 3.2623432302800846e-05, "loss": 3.5612, "step": 1061376 }, { "epoch": 0.02, "learning_rate": 3.2615046355290326e-05, "loss": 3.5591, "step": 1061888 }, { "epoch": 0.02, "learning_rate": 3.2606676786583535e-05, "loss": 3.5507, "step": 1062400 }, { "epoch": 0.02, "learning_rate": 3.2598290839073015e-05, "loss": 3.5739, "step": 1062912 }, { "epoch": 0.02, "learning_rate": 3.2589904891562495e-05, "loss": 3.5722, "step": 1063424 }, { "epoch": 0.02, "learning_rate": 3.2581518944051975e-05, "loss": 3.567, "step": 1063936 }, { "epoch": 0.02, "learning_rate": 3.2573149375345184e-05, "loss": 3.5574, "step": 1064448 }, { "epoch": 0.02, "learning_rate": 3.2564763427834664e-05, "loss": 3.5714, "step": 1064960 }, { "epoch": 0.02, "learning_rate": 3.2556377480324144e-05, "loss": 3.5588, "step": 1065472 }, { "epoch": 0.02, "learning_rate": 3.254800791161736e-05, "loss": 3.5516, "step": 1065984 }, { "epoch": 0.02, "learning_rate": 3.253962196410684e-05, "loss": 3.5762, "step": 1066496 }, { "epoch": 0.02, "learning_rate": 3.253123601659632e-05, "loss": 3.5608, "step": 1067008 }, { "epoch": 0.02, "learning_rate": 3.25228500690858e-05, "loss": 3.5755, "step": 1067520 }, { "epoch": 0.02, "learning_rate": 3.251446412157528e-05, "loss": 3.5552, "step": 1068032 }, { "epoch": 0.03, "eval_loss": 3.8419296741485596, "eval_runtime": 307.67, "eval_samples_per_second": 1240.261, "eval_steps_per_second": 38.759, "step": 1068480 }, { "epoch": 1.0, "learning_rate": 3.250609455286849e-05, "loss": 3.5569, "step": 1068544 }, { "epoch": 1.0, "learning_rate": 3.249770860535797e-05, "loss": 3.5435, "step": 1069056 }, { "epoch": 1.0, "learning_rate": 3.248932265784745e-05, "loss": 3.555, "step": 1069568 }, { "epoch": 1.0, "learning_rate": 3.248093671033693e-05, "loss": 3.5694, "step": 1070080 }, { "epoch": 1.0, "learning_rate": 3.247256714163014e-05, "loss": 3.5665, "step": 1070592 }, { "epoch": 1.0, "learning_rate": 3.246418119411962e-05, "loss": 3.5621, "step": 1071104 }, { "epoch": 1.0, "learning_rate": 3.24557952466091e-05, "loss": 3.5562, "step": 1071616 }, { "epoch": 1.0, "learning_rate": 3.244740929909858e-05, "loss": 3.5534, "step": 1072128 }, { "epoch": 1.0, "learning_rate": 3.243903973039179e-05, "loss": 3.5516, "step": 1072640 }, { "epoch": 1.0, "learning_rate": 3.243065378288127e-05, "loss": 3.5582, "step": 1073152 }, { "epoch": 1.0, "learning_rate": 3.242226783537075e-05, "loss": 3.5625, "step": 1073664 }, { "epoch": 1.0, "learning_rate": 3.241388188786023e-05, "loss": 3.5646, "step": 1074176 }, { "epoch": 1.0, "learning_rate": 3.240552869795717e-05, "loss": 3.5667, "step": 1074688 }, { "epoch": 1.0, "learning_rate": 3.239714275044665e-05, "loss": 3.5462, "step": 1075200 }, { "epoch": 1.0, "learning_rate": 3.238875680293613e-05, "loss": 3.5555, "step": 1075712 }, { "epoch": 1.0, "learning_rate": 3.238037085542561e-05, "loss": 3.5343, "step": 1076224 }, { "epoch": 1.0, "learning_rate": 3.237198490791509e-05, "loss": 3.5542, "step": 1076736 }, { "epoch": 1.0, "learning_rate": 3.236359896040457e-05, "loss": 3.5505, "step": 1077248 }, { "epoch": 1.0, "learning_rate": 3.235521301289405e-05, "loss": 3.5532, "step": 1077760 }, { "epoch": 1.0, "learning_rate": 3.234682706538353e-05, "loss": 3.5468, "step": 1078272 }, { "epoch": 1.0, "learning_rate": 3.233845749667675e-05, "loss": 3.5723, "step": 1078784 }, { "epoch": 1.0, "learning_rate": 3.233007154916623e-05, "loss": 3.5548, "step": 1079296 }, { "epoch": 1.0, "learning_rate": 3.232168560165571e-05, "loss": 3.5655, "step": 1079808 }, { "epoch": 1.0, "learning_rate": 3.231329965414518e-05, "loss": 3.5563, "step": 1080320 }, { "epoch": 1.0, "learning_rate": 3.2304930085438396e-05, "loss": 3.5669, "step": 1080832 }, { "epoch": 1.0, "learning_rate": 3.2296544137927876e-05, "loss": 3.5476, "step": 1081344 }, { "epoch": 1.0, "learning_rate": 3.2288158190417356e-05, "loss": 3.5539, "step": 1081856 }, { "epoch": 1.0, "learning_rate": 3.227977224290683e-05, "loss": 3.5672, "step": 1082368 }, { "epoch": 1.0, "learning_rate": 3.2271402674200045e-05, "loss": 3.5517, "step": 1082880 }, { "epoch": 1.0, "learning_rate": 3.2263016726689525e-05, "loss": 3.5398, "step": 1083392 }, { "epoch": 1.01, "learning_rate": 3.2254630779179005e-05, "loss": 3.555, "step": 1083904 }, { "epoch": 1.01, "learning_rate": 3.2246244831668485e-05, "loss": 3.5543, "step": 1084416 }, { "epoch": 1.01, "learning_rate": 3.22378752629617e-05, "loss": 3.566, "step": 1084928 }, { "epoch": 1.01, "learning_rate": 3.222948931545118e-05, "loss": 3.556, "step": 1085440 }, { "epoch": 1.01, "learning_rate": 3.2221103367940654e-05, "loss": 3.5521, "step": 1085952 }, { "epoch": 1.01, "learning_rate": 3.2212717420430134e-05, "loss": 3.5575, "step": 1086464 }, { "epoch": 1.01, "learning_rate": 3.220434785172335e-05, "loss": 3.5627, "step": 1086976 }, { "epoch": 1.01, "learning_rate": 3.219596190421283e-05, "loss": 3.542, "step": 1087488 }, { "epoch": 1.01, "learning_rate": 3.21875759567023e-05, "loss": 3.5497, "step": 1088000 }, { "epoch": 1.01, "learning_rate": 3.217919000919178e-05, "loss": 3.5456, "step": 1088512 }, { "epoch": 1.01, "learning_rate": 3.2170820440485e-05, "loss": 3.5451, "step": 1089024 }, { "epoch": 1.01, "learning_rate": 3.216243449297447e-05, "loss": 3.5568, "step": 1089536 }, { "epoch": 1.01, "learning_rate": 3.215404854546396e-05, "loss": 3.562, "step": 1090048 }, { "epoch": 1.01, "learning_rate": 3.214566259795344e-05, "loss": 3.5519, "step": 1090560 }, { "epoch": 1.01, "learning_rate": 3.2137293029246654e-05, "loss": 3.5548, "step": 1091072 }, { "epoch": 1.01, "learning_rate": 3.212890708173613e-05, "loss": 3.5569, "step": 1091584 }, { "epoch": 1.01, "learning_rate": 3.212052113422561e-05, "loss": 3.5522, "step": 1092096 }, { "epoch": 1.01, "learning_rate": 3.211213518671509e-05, "loss": 3.5594, "step": 1092608 }, { "epoch": 1.01, "learning_rate": 3.21037656180083e-05, "loss": 3.5299, "step": 1093120 }, { "epoch": 1.01, "learning_rate": 3.2095379670497776e-05, "loss": 3.5586, "step": 1093632 }, { "epoch": 1.01, "learning_rate": 3.2086993722987256e-05, "loss": 3.555, "step": 1094144 }, { "epoch": 1.01, "learning_rate": 3.2078607775476736e-05, "loss": 3.5596, "step": 1094656 }, { "epoch": 1.01, "learning_rate": 3.2070238206769945e-05, "loss": 3.5489, "step": 1095168 }, { "epoch": 1.01, "learning_rate": 3.2061852259259425e-05, "loss": 3.5439, "step": 1095680 }, { "epoch": 1.01, "learning_rate": 3.205346631174891e-05, "loss": 3.5385, "step": 1096192 }, { "epoch": 1.01, "learning_rate": 3.204508036423839e-05, "loss": 3.5447, "step": 1096704 }, { "epoch": 1.01, "learning_rate": 3.20367107955316e-05, "loss": 3.5567, "step": 1097216 }, { "epoch": 1.01, "learning_rate": 3.202832484802108e-05, "loss": 3.5389, "step": 1097728 }, { "epoch": 1.01, "learning_rate": 3.201993890051056e-05, "loss": 3.5662, "step": 1098240 }, { "epoch": 1.01, "learning_rate": 3.201155295300004e-05, "loss": 3.5485, "step": 1098752 }, { "epoch": 1.01, "learning_rate": 3.200318338429325e-05, "loss": 3.5402, "step": 1099264 }, { "epoch": 1.01, "learning_rate": 3.199479743678273e-05, "loss": 3.5516, "step": 1099776 }, { "epoch": 1.01, "learning_rate": 3.198641148927221e-05, "loss": 3.5347, "step": 1100288 }, { "epoch": 1.01, "learning_rate": 3.197802554176169e-05, "loss": 3.5447, "step": 1100800 }, { "epoch": 1.01, "learning_rate": 3.19696559730549e-05, "loss": 3.5476, "step": 1101312 }, { "epoch": 1.01, "learning_rate": 3.196127002554438e-05, "loss": 3.5528, "step": 1101824 }, { "epoch": 1.01, "learning_rate": 3.1952884078033866e-05, "loss": 3.5361, "step": 1102336 }, { "epoch": 1.01, "learning_rate": 3.1944498130523346e-05, "loss": 3.5465, "step": 1102848 }, { "epoch": 1.01, "learning_rate": 3.1936128561816555e-05, "loss": 3.5331, "step": 1103360 }, { "epoch": 1.01, "learning_rate": 3.1927742614306035e-05, "loss": 3.5462, "step": 1103872 }, { "epoch": 1.01, "learning_rate": 3.1919356666795515e-05, "loss": 3.5534, "step": 1104384 }, { "epoch": 1.01, "learning_rate": 3.1910970719284995e-05, "loss": 3.5516, "step": 1104896 }, { "epoch": 1.01, "learning_rate": 3.1902601150578204e-05, "loss": 3.555, "step": 1105408 }, { "epoch": 1.01, "learning_rate": 3.1894215203067684e-05, "loss": 3.55, "step": 1105920 }, { "epoch": 1.01, "learning_rate": 3.1885829255557164e-05, "loss": 3.5639, "step": 1106432 }, { "epoch": 1.01, "learning_rate": 3.1877443308046643e-05, "loss": 3.5428, "step": 1106944 }, { "epoch": 1.01, "learning_rate": 3.186907373933985e-05, "loss": 3.5526, "step": 1107456 }, { "epoch": 1.01, "learning_rate": 3.186068779182933e-05, "loss": 3.5456, "step": 1107968 }, { "epoch": 1.01, "learning_rate": 3.185230184431882e-05, "loss": 3.5403, "step": 1108480 }, { "epoch": 1.01, "learning_rate": 3.18439158968083e-05, "loss": 3.5521, "step": 1108992 }, { "epoch": 1.01, "learning_rate": 3.183554632810151e-05, "loss": 3.5456, "step": 1109504 }, { "epoch": 1.01, "learning_rate": 3.182716038059099e-05, "loss": 3.5545, "step": 1110016 }, { "epoch": 1.01, "learning_rate": 3.181877443308047e-05, "loss": 3.5582, "step": 1110528 }, { "epoch": 1.01, "learning_rate": 3.181038848556995e-05, "loss": 3.5453, "step": 1111040 }, { "epoch": 1.01, "learning_rate": 3.180201891686316e-05, "loss": 3.5335, "step": 1111552 }, { "epoch": 1.01, "learning_rate": 3.179363296935264e-05, "loss": 3.5444, "step": 1112064 }, { "epoch": 1.01, "learning_rate": 3.178524702184212e-05, "loss": 3.5492, "step": 1112576 }, { "epoch": 1.01, "learning_rate": 3.17768610743316e-05, "loss": 3.5504, "step": 1113088 }, { "epoch": 1.01, "learning_rate": 3.1768491505624806e-05, "loss": 3.5503, "step": 1113600 }, { "epoch": 1.01, "learning_rate": 3.1760105558114286e-05, "loss": 3.5518, "step": 1114112 }, { "epoch": 1.02, "learning_rate": 3.175171961060377e-05, "loss": 3.5453, "step": 1114624 }, { "epoch": 1.02, "learning_rate": 3.174333366309325e-05, "loss": 3.5413, "step": 1115136 }, { "epoch": 1.02, "learning_rate": 3.173496409438646e-05, "loss": 3.5437, "step": 1115648 }, { "epoch": 1.02, "learning_rate": 3.172657814687594e-05, "loss": 3.5503, "step": 1116160 }, { "epoch": 1.02, "learning_rate": 3.171819219936542e-05, "loss": 3.5583, "step": 1116672 }, { "epoch": 1.02, "learning_rate": 3.17098062518549e-05, "loss": 3.5511, "step": 1117184 }, { "epoch": 1.02, "learning_rate": 3.170143668314811e-05, "loss": 3.5428, "step": 1117696 }, { "epoch": 1.02, "learning_rate": 3.169305073563759e-05, "loss": 3.5409, "step": 1118208 }, { "epoch": 1.02, "learning_rate": 3.168466478812707e-05, "loss": 3.5572, "step": 1118720 }, { "epoch": 1.02, "learning_rate": 3.167627884061655e-05, "loss": 3.5531, "step": 1119232 }, { "epoch": 1.02, "learning_rate": 3.166790927190976e-05, "loss": 3.5453, "step": 1119744 }, { "epoch": 1.02, "learning_rate": 3.165952332439924e-05, "loss": 3.5478, "step": 1120256 }, { "epoch": 1.02, "learning_rate": 3.165113737688872e-05, "loss": 3.5387, "step": 1120768 }, { "epoch": 1.02, "learning_rate": 3.1642751429378207e-05, "loss": 3.5493, "step": 1121280 }, { "epoch": 1.02, "learning_rate": 3.1634381860671416e-05, "loss": 3.5498, "step": 1121792 }, { "epoch": 1.02, "learning_rate": 3.1625995913160896e-05, "loss": 3.5369, "step": 1122304 }, { "epoch": 1.02, "learning_rate": 3.1617609965650376e-05, "loss": 3.5452, "step": 1122816 }, { "epoch": 1.02, "learning_rate": 3.1609224018139856e-05, "loss": 3.5448, "step": 1123328 }, { "epoch": 1.02, "learning_rate": 3.1600854449433065e-05, "loss": 3.5534, "step": 1123840 }, { "epoch": 1.02, "learning_rate": 3.1592468501922545e-05, "loss": 3.5335, "step": 1124352 }, { "epoch": 1.02, "learning_rate": 3.1584082554412025e-05, "loss": 3.5466, "step": 1124864 }, { "epoch": 1.02, "learning_rate": 3.1575696606901504e-05, "loss": 3.5366, "step": 1125376 }, { "epoch": 1.02, "learning_rate": 3.1567327038194714e-05, "loss": 3.5572, "step": 1125888 }, { "epoch": 1.02, "learning_rate": 3.1558941090684194e-05, "loss": 3.5398, "step": 1126400 }, { "epoch": 1.02, "learning_rate": 3.1550555143173673e-05, "loss": 3.5446, "step": 1126912 }, { "epoch": 1.02, "learning_rate": 3.154216919566316e-05, "loss": 3.5553, "step": 1127424 }, { "epoch": 1.02, "learning_rate": 3.153379962695637e-05, "loss": 3.5587, "step": 1127936 }, { "epoch": 1.02, "learning_rate": 3.152541367944585e-05, "loss": 3.5428, "step": 1128448 }, { "epoch": 1.02, "learning_rate": 3.151702773193533e-05, "loss": 3.5413, "step": 1128960 }, { "epoch": 1.02, "learning_rate": 3.150864178442481e-05, "loss": 3.5513, "step": 1129472 }, { "epoch": 1.02, "learning_rate": 3.150027221571802e-05, "loss": 3.5492, "step": 1129984 }, { "epoch": 1.02, "learning_rate": 3.14918862682075e-05, "loss": 3.536, "step": 1130496 }, { "epoch": 1.02, "learning_rate": 3.148350032069698e-05, "loss": 3.5434, "step": 1131008 }, { "epoch": 1.02, "learning_rate": 3.147511437318646e-05, "loss": 3.5422, "step": 1131520 }, { "epoch": 1.02, "learning_rate": 3.146674480447967e-05, "loss": 3.5506, "step": 1132032 }, { "epoch": 1.02, "learning_rate": 3.145835885696915e-05, "loss": 3.5471, "step": 1132544 }, { "epoch": 1.02, "learning_rate": 3.144997290945863e-05, "loss": 3.5385, "step": 1133056 }, { "epoch": 1.02, "learning_rate": 3.1441586961948114e-05, "loss": 3.5458, "step": 1133568 }, { "epoch": 1.02, "learning_rate": 3.143321739324132e-05, "loss": 3.5401, "step": 1134080 }, { "epoch": 1.02, "learning_rate": 3.14248314457308e-05, "loss": 3.5483, "step": 1134592 }, { "epoch": 1.02, "learning_rate": 3.141644549822028e-05, "loss": 3.5516, "step": 1135104 }, { "epoch": 1.02, "learning_rate": 3.140805955070976e-05, "loss": 3.5505, "step": 1135616 }, { "epoch": 1.02, "learning_rate": 3.139968998200297e-05, "loss": 3.5417, "step": 1136128 }, { "epoch": 1.02, "learning_rate": 3.139130403449245e-05, "loss": 3.5442, "step": 1136640 }, { "epoch": 1.02, "learning_rate": 3.138291808698193e-05, "loss": 3.5564, "step": 1137152 }, { "epoch": 1.02, "learning_rate": 3.137453213947141e-05, "loss": 3.5473, "step": 1137664 }, { "epoch": 1.02, "learning_rate": 3.136616257076462e-05, "loss": 3.5456, "step": 1138176 }, { "epoch": 1.02, "learning_rate": 3.13577766232541e-05, "loss": 3.5352, "step": 1138688 }, { "epoch": 1.02, "learning_rate": 3.134939067574358e-05, "loss": 3.5618, "step": 1139200 }, { "epoch": 1.02, "learning_rate": 3.13410211070368e-05, "loss": 3.55, "step": 1139712 }, { "epoch": 1.02, "learning_rate": 3.133263515952628e-05, "loss": 3.5541, "step": 1140224 }, { "epoch": 1.02, "learning_rate": 3.1324249212015757e-05, "loss": 3.543, "step": 1140736 }, { "epoch": 1.02, "learning_rate": 3.1315863264505237e-05, "loss": 3.5544, "step": 1141248 }, { "epoch": 1.02, "learning_rate": 3.1307493695798446e-05, "loss": 3.5423, "step": 1141760 }, { "epoch": 1.02, "learning_rate": 3.1299107748287926e-05, "loss": 3.5352, "step": 1142272 }, { "epoch": 1.02, "learning_rate": 3.1290721800777406e-05, "loss": 3.5621, "step": 1142784 }, { "epoch": 1.02, "learning_rate": 3.1282335853266886e-05, "loss": 3.5453, "step": 1143296 }, { "epoch": 1.02, "learning_rate": 3.1273966284560095e-05, "loss": 3.5588, "step": 1143808 }, { "epoch": 1.02, "learning_rate": 3.1265580337049575e-05, "loss": 3.5382, "step": 1144320 }, { "epoch": 1.03, "eval_loss": 3.8439955711364746, "eval_runtime": 327.0954, "eval_samples_per_second": 1166.605, "eval_steps_per_second": 36.457, "step": 1144800 }, { "epoch": 0.0, "learning_rate": 3.1257194389539055e-05, "loss": 3.5144, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.1248808442028534e-05, "loss": 3.5319, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.124042249451802e-05, "loss": 3.5367, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.12320365470075e-05, "loss": 3.553, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.122366697830071e-05, "loss": 3.5481, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.121528103079019e-05, "loss": 3.5483, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.120689508327967e-05, "loss": 3.54, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.119850913576915e-05, "loss": 3.5389, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.119013956706236e-05, "loss": 3.5385, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.118175361955184e-05, "loss": 3.5425, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.117336767204132e-05, "loss": 3.5446, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.11649817245308e-05, "loss": 3.5508, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.1156628534627744e-05, "loss": 3.5531, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.1148242587117224e-05, "loss": 3.5313, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.1139856639606704e-05, "loss": 3.5424, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.1131470692096184e-05, "loss": 3.5193, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.1123084744585664e-05, "loss": 3.5388, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.1114698797075144e-05, "loss": 3.5337, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.1106312849564624e-05, "loss": 3.5386, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.10979269020541e-05, "loss": 3.5348, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.108954095454358e-05, "loss": 3.5552, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.108117138583679e-05, "loss": 3.543, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.1072785438326266e-05, "loss": 3.5439, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.1064399490815746e-05, "loss": 3.5411, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.105602992210896e-05, "loss": 3.5533, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104764397459844e-05, "loss": 3.5323, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.103925802708792e-05, "loss": 3.5373, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.10308720795774e-05, "loss": 3.5511, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102250251087062e-05, "loss": 3.5357, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.10141165633601e-05, "loss": 3.5243, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.100573061584957e-05, "loss": 3.5383, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.099734466833905e-05, "loss": 3.5403, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.0988975099632267e-05, "loss": 3.5486, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.098058915212174e-05, "loss": 3.5413, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.097220320461122e-05, "loss": 3.5392, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.09638172571007e-05, "loss": 3.5421, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.0955447688393916e-05, "loss": 3.5464, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.0947061740883395e-05, "loss": 3.5271, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.0938675793372875e-05, "loss": 3.5397, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.0930289845862355e-05, "loss": 3.5248, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.092192027715557e-05, "loss": 3.535, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.0913534329645044e-05, "loss": 3.5361, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.0905148382134524e-05, "loss": 3.5477, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.0896762434624004e-05, "loss": 3.5393, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.0888392865917213e-05, "loss": 3.5382, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.0880006918406693e-05, "loss": 3.5392, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.087162097089617e-05, "loss": 3.5396, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.086323502338565e-05, "loss": 3.5446, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.085486545467887e-05, "loss": 3.5157, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.084647950716835e-05, "loss": 3.543, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.083809355965783e-05, "loss": 3.5401, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.082970761214731e-05, "loss": 3.5448, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.082133804344052e-05, "loss": 3.5368, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.081295209593e-05, "loss": 3.5307, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080456614841948e-05, "loss": 3.5205, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.079618020090896e-05, "loss": 3.5257, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.078781063220217e-05, "loss": 3.544, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077942468469165e-05, "loss": 3.5253, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.077103873718113e-05, "loss": 3.5464, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076265278967061e-05, "loss": 3.5357, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075428322096382e-05, "loss": 3.5257, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.07458972734533e-05, "loss": 3.5383, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.073751132594278e-05, "loss": 3.5203, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.072912537843226e-05, "loss": 3.5288, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.072075580972547e-05, "loss": 3.5298, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071236986221495e-05, "loss": 3.5425, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.070398391470443e-05, "loss": 3.5214, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.069559796719391e-05, "loss": 3.5271, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.068722839848712e-05, "loss": 3.5203, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.06788424509766e-05, "loss": 3.531, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.067045650346608e-05, "loss": 3.5395, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.066207055595556e-05, "loss": 3.5395, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0653700987248777e-05, "loss": 3.5375, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.0645315039738256e-05, "loss": 3.5362, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.0636929092227736e-05, "loss": 3.5476, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.0628543144717216e-05, "loss": 3.5313, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.0620173576010425e-05, "loss": 3.5345, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.0611787628499905e-05, "loss": 3.5337, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.0603401680989385e-05, "loss": 3.5255, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.0595015733478865e-05, "loss": 3.5377, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.0586646164772074e-05, "loss": 3.5307, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.0578260217261554e-05, "loss": 3.5426, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.0569874269751034e-05, "loss": 3.541, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.0561488322240514e-05, "loss": 3.5296, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.055311875353373e-05, "loss": 3.5186, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.054473280602321e-05, "loss": 3.5297, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.053634685851269e-05, "loss": 3.5362, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.052796091100217e-05, "loss": 3.5359, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.051959134229538e-05, "loss": 3.5333, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.051120539478486e-05, "loss": 3.5369, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.050281944727434e-05, "loss": 3.5334, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.049443349976382e-05, "loss": 3.5259, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.0486063931057028e-05, "loss": 3.5266, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.047767798354651e-05, "loss": 3.5392, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.046929203603599e-05, "loss": 3.5411, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.046090608852547e-05, "loss": 3.539, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.045253651981868e-05, "loss": 3.5259, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.044415057230816e-05, "loss": 3.5296, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.043576462479764e-05, "loss": 3.5391, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.042737867728712e-05, "loss": 3.5372, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.0419009108580333e-05, "loss": 3.5347, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.0410623161069813e-05, "loss": 3.5272, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0402237213559293e-05, "loss": 3.5271, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0393851266048773e-05, "loss": 3.5378, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.0385481697341982e-05, "loss": 3.5325, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.0377095749831465e-05, "loss": 3.5207, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.0368709802320945e-05, "loss": 3.527, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.0360323854810425e-05, "loss": 3.533, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0351954286103634e-05, "loss": 3.5345, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.0343568338593114e-05, "loss": 3.5236, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.0335182391082594e-05, "loss": 3.5348, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.0326796443572074e-05, "loss": 3.5165, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.0318426874865286e-05, "loss": 3.5451, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.0310040927354766e-05, "loss": 3.5209, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.0301654979844246e-05, "loss": 3.5327, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.0293269032333726e-05, "loss": 3.5395, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.0284899463626935e-05, "loss": 3.5449, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.0276513516116415e-05, "loss": 3.528, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.02681275686059e-05, "loss": 3.5273, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.025974162109538e-05, "loss": 3.5345, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0251372052388588e-05, "loss": 3.5335, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.0242986104878068e-05, "loss": 3.5229, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.0234600157367548e-05, "loss": 3.5273, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.0226214209857028e-05, "loss": 3.5311, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.021784464115024e-05, "loss": 3.5405, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.020945869363972e-05, "loss": 3.5286, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.02010727461292e-05, "loss": 3.5269, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.019268679861868e-05, "loss": 3.5278, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.018431722991189e-05, "loss": 3.5298, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.017593128240137e-05, "loss": 3.5265, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.0167545334890852e-05, "loss": 3.5411, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.0159159387380332e-05, "loss": 3.5417, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.015078981867354e-05, "loss": 3.5229, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.014240387116302e-05, "loss": 3.528, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.01340179236525e-05, "loss": 3.539, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.012563197614198e-05, "loss": 3.534, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0117262407435194e-05, "loss": 3.532, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0108876459924674e-05, "loss": 3.5242, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0100490512414154e-05, "loss": 3.5445, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0092104564903634e-05, "loss": 3.5349, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.0083734996196843e-05, "loss": 3.5425, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.0075349048686323e-05, "loss": 3.5275, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.0066963101175806e-05, "loss": 3.5416, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.0058577153665286e-05, "loss": 3.5283, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.0050207584958495e-05, "loss": 3.5208, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.0041821637447975e-05, "loss": 3.5469, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.0033435689937455e-05, "loss": 3.531, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.0025049742426935e-05, "loss": 3.5419, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.0016680173720147e-05, "loss": 3.5286, "step": 1220608 }, { "epoch": 0.03, "learning_rate": 3.0008294226209627e-05, "loss": 3.5253, "step": 1221120 }, { "epoch": 0.03, "eval_loss": 3.844092607498169, "eval_runtime": 304.5814, "eval_samples_per_second": 1252.838, "eval_steps_per_second": 39.152, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.9999908278699107e-05, "loss": 3.5156, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.9991522331188587e-05, "loss": 3.5211, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.9983152762481796e-05, "loss": 3.5393, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.9974766814971276e-05, "loss": 3.5344, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.996638086746076e-05, "loss": 3.5375, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.995799491995024e-05, "loss": 3.5275, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.994962535124345e-05, "loss": 3.5243, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.994123940373293e-05, "loss": 3.5179, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.993285345622241e-05, "loss": 3.5312, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.992446750871189e-05, "loss": 3.527, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.99160979400051e-05, "loss": 3.54, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.990772837129831e-05, "loss": 3.5414, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.989934242378779e-05, "loss": 3.5191, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.989095647627727e-05, "loss": 3.5228, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.988257052876675e-05, "loss": 3.5096, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.987418458125623e-05, "loss": 3.5202, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.9865798633745713e-05, "loss": 3.5254, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.9857412686235187e-05, "loss": 3.5237, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.9849026738724667e-05, "loss": 3.5195, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.9840657170017882e-05, "loss": 3.541, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.9832271222507362e-05, "loss": 3.5281, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.982388527499684e-05, "loss": 3.53, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.981549932748632e-05, "loss": 3.5294, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.9807129758779535e-05, "loss": 3.5402, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.9798743811269008e-05, "loss": 3.516, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.9790357863758488e-05, "loss": 3.5251, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.9781971916247968e-05, "loss": 3.5394, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9773602347541184e-05, "loss": 3.52, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.976521640003066e-05, "loss": 3.5148, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.975683045252014e-05, "loss": 3.5214, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.974844450500962e-05, "loss": 3.5303, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9740074936302836e-05, "loss": 3.5338, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.9731688988792313e-05, "loss": 3.5266, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.9723303041281793e-05, "loss": 3.5275, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.9714917093771273e-05, "loss": 3.5293, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.970654752506448e-05, "loss": 3.53, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.969816157755396e-05, "loss": 3.5178, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.968977563004344e-05, "loss": 3.5256, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.968138968253292e-05, "loss": 3.5078, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.9673020113826134e-05, "loss": 3.5237, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.9664634166315614e-05, "loss": 3.5205, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.9656248218805094e-05, "loss": 3.534, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.9647862271294574e-05, "loss": 3.5252, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.9639492702587783e-05, "loss": 3.5243, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.9631106755077266e-05, "loss": 3.5264, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.9622720807566746e-05, "loss": 3.5254, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.9614334860056226e-05, "loss": 3.5318, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.9605965291349435e-05, "loss": 3.5012, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.9597579343838915e-05, "loss": 3.5259, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.9589193396328395e-05, "loss": 3.5296, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.9580807448817875e-05, "loss": 3.5305, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.9572437880111088e-05, "loss": 3.5192, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.9564051932600568e-05, "loss": 3.5183, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.9555665985090048e-05, "loss": 3.5094, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.9547280037579528e-05, "loss": 3.5095, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.9538910468872737e-05, "loss": 3.5336, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.953052452136222e-05, "loss": 3.5099, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.95221385738517e-05, "loss": 3.5305, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.951375262634118e-05, "loss": 3.5236, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.950538305763439e-05, "loss": 3.5089, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.949699711012387e-05, "loss": 3.5215, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.948861116261335e-05, "loss": 3.5089, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.948022521510283e-05, "loss": 3.5141, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.947185564639604e-05, "loss": 3.5156, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.946346969888552e-05, "loss": 3.5285, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.9455083751375e-05, "loss": 3.5085, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.944669780386448e-05, "loss": 3.5123, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.943832823515769e-05, "loss": 3.5044, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.9429942287647174e-05, "loss": 3.5187, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.9421556340136654e-05, "loss": 3.5225, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.9413170392626134e-05, "loss": 3.5283, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.9404800823919343e-05, "loss": 3.5198, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9396414876408823e-05, "loss": 3.5261, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9388028928898303e-05, "loss": 3.5331, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9379642981387783e-05, "loss": 3.5176, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.9371273412680995e-05, "loss": 3.5218, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.9362887465170475e-05, "loss": 3.5169, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.9354501517659955e-05, "loss": 3.5166, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.9346115570149435e-05, "loss": 3.525, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9337746001442644e-05, "loss": 3.5088, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9329360053932124e-05, "loss": 3.534, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9320974106421607e-05, "loss": 3.5303, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9312588158911087e-05, "loss": 3.5145, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9304218590204296e-05, "loss": 3.5043, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.9295832642693776e-05, "loss": 3.5149, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.9287446695183256e-05, "loss": 3.5211, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.9279060747672736e-05, "loss": 3.5257, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.927069117896595e-05, "loss": 3.5188, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.926230523145543e-05, "loss": 3.523, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.925391928394491e-05, "loss": 3.5218, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.924553333643439e-05, "loss": 3.5097, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.9237163767727598e-05, "loss": 3.5105, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.9228777820217078e-05, "loss": 3.526, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.922039187270656e-05, "loss": 3.5238, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.921200592519604e-05, "loss": 3.5314, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.920363635648925e-05, "loss": 3.5129, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.919525040897873e-05, "loss": 3.5157, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.918686446146821e-05, "loss": 3.5266, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.917847851395769e-05, "loss": 3.5262, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.9170108945250902e-05, "loss": 3.518, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.9161722997740382e-05, "loss": 3.5201, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.9153337050229862e-05, "loss": 3.5105, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.9144951102719342e-05, "loss": 3.5177, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.913658153401255e-05, "loss": 3.5248, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.912819558650203e-05, "loss": 3.5029, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.9119809638991515e-05, "loss": 3.5147, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9111423691480995e-05, "loss": 3.5199, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9103054122774204e-05, "loss": 3.5209, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9094668175263684e-05, "loss": 3.5049, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.9086282227753164e-05, "loss": 3.5221, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.9077896280242644e-05, "loss": 3.5057, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.9069526711535856e-05, "loss": 3.5342, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.9061140764025336e-05, "loss": 3.5043, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9052754816514816e-05, "loss": 3.5197, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.9044368869004296e-05, "loss": 3.5216, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.9035999300297505e-05, "loss": 3.5329, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.9027613352786985e-05, "loss": 3.5157, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.9019227405276468e-05, "loss": 3.516, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.9010841457765948e-05, "loss": 3.5198, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.9002471889059157e-05, "loss": 3.5182, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.8994085941548637e-05, "loss": 3.5105, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.8985699994038117e-05, "loss": 3.5146, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.8977314046527597e-05, "loss": 3.5123, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.896894447782081e-05, "loss": 3.5321, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.896055853031029e-05, "loss": 3.51, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.895217258279977e-05, "loss": 3.5158, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.894378663528925e-05, "loss": 3.5128, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.893541706658246e-05, "loss": 3.5151, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.892703111907194e-05, "loss": 3.5134, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.8918645171561422e-05, "loss": 3.5283, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.8910259224050902e-05, "loss": 3.5235, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.890188965534411e-05, "loss": 3.517, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.889350370783359e-05, "loss": 3.51, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.888511776032307e-05, "loss": 3.5219, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.887673181281255e-05, "loss": 3.5213, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.8868362244105763e-05, "loss": 3.5203, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.8859976296595243e-05, "loss": 3.5103, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.8851590349084723e-05, "loss": 3.5292, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.8843204401574203e-05, "loss": 3.5189, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8834834832867412e-05, "loss": 3.5303, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8826448885356892e-05, "loss": 3.512, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.8818062937846376e-05, "loss": 3.5308, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.8809676990335856e-05, "loss": 3.5189, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.8801307421629065e-05, "loss": 3.5001, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.8792921474118545e-05, "loss": 3.535, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8784535526608025e-05, "loss": 3.5175, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8776149579097505e-05, "loss": 3.5244, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8767780010390717e-05, "loss": 3.5181, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.8759394062880197e-05, "loss": 3.5111, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 3.845029354095459, "eval_runtime": 303.4914, "eval_samples_per_second": 1257.337, "eval_steps_per_second": 39.293, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.8751008115369677e-05, "loss": 3.5034, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.8742622167859157e-05, "loss": 3.5091, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.873423622034863e-05, "loss": 3.5258, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.8725850272838113e-05, "loss": 3.5158, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.871748070413133e-05, "loss": 3.526, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.870909475662081e-05, "loss": 3.5152, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8700708809110282e-05, "loss": 3.5114, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.8692339240403498e-05, "loss": 3.5064, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.8683953292892978e-05, "loss": 3.5164, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.8675567345382455e-05, "loss": 3.5121, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.8667181397871935e-05, "loss": 3.527, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.865881182916515e-05, "loss": 3.5235, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.865044226045836e-05, "loss": 3.5124, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.864205631294784e-05, "loss": 3.5045, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.863367036543732e-05, "loss": 3.5005, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.86252844179268e-05, "loss": 3.5039, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.861689847041628e-05, "loss": 3.5121, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.8608512522905756e-05, "loss": 3.5107, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.8600126575395236e-05, "loss": 3.5024, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.8591740627884716e-05, "loss": 3.5307, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.858337105917793e-05, "loss": 3.5156, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.857498511166741e-05, "loss": 3.5141, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.856659916415689e-05, "loss": 3.516, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.855821321664637e-05, "loss": 3.5293, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8549843647939577e-05, "loss": 3.5019, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8541457700429057e-05, "loss": 3.5111, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8533071752918537e-05, "loss": 3.5216, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8524685805408017e-05, "loss": 3.5114, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.851631623670123e-05, "loss": 3.4992, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.850793028919071e-05, "loss": 3.5052, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.849954434168019e-05, "loss": 3.5167, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.84911747729734e-05, "loss": 3.5176, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.8482788825462882e-05, "loss": 3.5131, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.8474402877952362e-05, "loss": 3.5133, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8466016930441842e-05, "loss": 3.5152, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.845764736173505e-05, "loss": 3.5146, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.844926141422453e-05, "loss": 3.5084, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.844087546671401e-05, "loss": 3.5098, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.843248951920349e-05, "loss": 3.496, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.8424119950496704e-05, "loss": 3.5084, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.8415734002986184e-05, "loss": 3.5082, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.8407348055475663e-05, "loss": 3.5217, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.8398962107965143e-05, "loss": 3.5073, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.8390592539258353e-05, "loss": 3.5143, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8382206591747832e-05, "loss": 3.5128, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8373820644237316e-05, "loss": 3.5154, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8365434696726796e-05, "loss": 3.5206, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8357065128020005e-05, "loss": 3.4873, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8348679180509485e-05, "loss": 3.5077, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.8340293232998965e-05, "loss": 3.5216, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.8331907285488445e-05, "loss": 3.5156, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8323537716781657e-05, "loss": 3.5064, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8315151769271137e-05, "loss": 3.5001, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8306765821760617e-05, "loss": 3.5004, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8298379874250097e-05, "loss": 3.4925, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8290010305543306e-05, "loss": 3.5218, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8281624358032786e-05, "loss": 3.4973, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.827323841052227e-05, "loss": 3.5189, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.826485246301175e-05, "loss": 3.5088, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.825648289430496e-05, "loss": 3.5001, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.824809694679444e-05, "loss": 3.506, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.823971099928392e-05, "loss": 3.498, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.82313250517734e-05, "loss": 3.5015, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.822295548306661e-05, "loss": 3.5024, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.821456953555609e-05, "loss": 3.52, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.820618358804557e-05, "loss": 3.495, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.819779764053505e-05, "loss": 3.4996, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.818942807182826e-05, "loss": 3.4915, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.818104212431774e-05, "loss": 3.5029, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.8172656176807223e-05, "loss": 3.5131, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.8164270229296703e-05, "loss": 3.5124, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.8155900660589912e-05, "loss": 3.5081, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.8147514713079392e-05, "loss": 3.5136, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8139128765568872e-05, "loss": 3.519, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.8130742818058352e-05, "loss": 3.5054, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.8122373249351565e-05, "loss": 3.5069, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.8113987301841045e-05, "loss": 3.5058, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.8105601354330524e-05, "loss": 3.5052, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.8097215406820004e-05, "loss": 3.5096, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.8088845838113214e-05, "loss": 3.4995, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.8080459890602693e-05, "loss": 3.5174, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8072073943092177e-05, "loss": 3.511, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8063687995581657e-05, "loss": 3.5069, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8055318426874866e-05, "loss": 3.4927, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.8046932479364346e-05, "loss": 3.4989, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.8038546531853826e-05, "loss": 3.5116, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.8030160584343306e-05, "loss": 3.5107, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.8021791015636518e-05, "loss": 3.5113, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.8013405068125998e-05, "loss": 3.5056, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8005019120615478e-05, "loss": 3.5118, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7996633173104958e-05, "loss": 3.4975, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7988263604398167e-05, "loss": 3.4956, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7979877656887647e-05, "loss": 3.5143, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.797149170937713e-05, "loss": 3.5077, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.796310576186661e-05, "loss": 3.513, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.795473619315982e-05, "loss": 3.5047, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.79463502456493e-05, "loss": 3.4976, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.793796429813878e-05, "loss": 3.5139, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.792957835062826e-05, "loss": 3.5137, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.7921208781921472e-05, "loss": 3.506, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7912822834410952e-05, "loss": 3.5061, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.7904436886900432e-05, "loss": 3.496, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.7896050939389912e-05, "loss": 3.5072, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.788768137068312e-05, "loss": 3.5128, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.78792954231726e-05, "loss": 3.4933, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7870909475662084e-05, "loss": 3.5014, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7862523528151564e-05, "loss": 3.5051, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7854153959444773e-05, "loss": 3.5108, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7845768011934253e-05, "loss": 3.4926, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.7837382064423733e-05, "loss": 3.5078, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7828996116913213e-05, "loss": 3.496, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.7820626548206426e-05, "loss": 3.5156, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7812240600695906e-05, "loss": 3.4967, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7803854653185385e-05, "loss": 3.5038, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7795468705674865e-05, "loss": 3.5129, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7787099136968075e-05, "loss": 3.5169, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.7778713189457554e-05, "loss": 3.5041, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.7770327241947038e-05, "loss": 3.4996, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.7761941294436518e-05, "loss": 3.5077, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.7753571725729727e-05, "loss": 3.5087, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.7745185778219207e-05, "loss": 3.4977, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.7736799830708687e-05, "loss": 3.5038, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.7728413883198167e-05, "loss": 3.5, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.772004431449138e-05, "loss": 3.5146, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.771165836698086e-05, "loss": 3.4935, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.770327241947034e-05, "loss": 3.5043, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.769488647195982e-05, "loss": 3.4991, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.7686516903253028e-05, "loss": 3.5011, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.7678130955742508e-05, "loss": 3.4988, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.7669745008231988e-05, "loss": 3.5161, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.766135906072147e-05, "loss": 3.5125, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.765298949201468e-05, "loss": 3.5051, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.764460354450416e-05, "loss": 3.4955, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.763621759699364e-05, "loss": 3.5112, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.762783164948312e-05, "loss": 3.5088, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.7619462080776333e-05, "loss": 3.5127, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.7611076133265813e-05, "loss": 3.4908, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.7602690185755293e-05, "loss": 3.5171, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.7594304238244773e-05, "loss": 3.5068, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.7585934669537982e-05, "loss": 3.5205, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7577548722027462e-05, "loss": 3.5035, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.7569162774516942e-05, "loss": 3.5146, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.7560776827006425e-05, "loss": 3.5076, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.7552407258299634e-05, "loss": 3.4938, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7544021310789114e-05, "loss": 3.5162, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7535635363278594e-05, "loss": 3.5105, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7527249415768074e-05, "loss": 3.5084, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7518879847061287e-05, "loss": 3.5024, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7510493899550767e-05, "loss": 3.4998, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 3.846951484680176, "eval_runtime": 303.8807, "eval_samples_per_second": 1255.726, "eval_steps_per_second": 39.242, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.7502107952040246e-05, "loss": 3.494, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.749372200452972e-05, "loss": 3.4955, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.7485352435822936e-05, "loss": 3.5136, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.7476966488312415e-05, "loss": 3.5045, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7468580540801895e-05, "loss": 3.5142, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7460194593291372e-05, "loss": 3.4984, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7451825024584588e-05, "loss": 3.4994, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.7443439077074068e-05, "loss": 3.4924, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7435053129563548e-05, "loss": 3.5014, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7426667182053024e-05, "loss": 3.5059, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.741829761334624e-05, "loss": 3.5069, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.740991166583572e-05, "loss": 3.5121, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.740154209712893e-05, "loss": 3.4991, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.739315614961841e-05, "loss": 3.4911, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.738477020210789e-05, "loss": 3.4937, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.737638425459737e-05, "loss": 3.4865, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.7367998307086846e-05, "loss": 3.4954, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.7359612359576326e-05, "loss": 3.4961, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.7351226412065806e-05, "loss": 3.4902, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.7342840464555286e-05, "loss": 3.5213, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7334470895848495e-05, "loss": 3.499, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7326084948337978e-05, "loss": 3.5054, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.7317699000827458e-05, "loss": 3.5046, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.7309313053316938e-05, "loss": 3.5146, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.7300943484610147e-05, "loss": 3.4863, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.7292557537099627e-05, "loss": 3.4998, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.7284171589589107e-05, "loss": 3.5065, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7275785642078587e-05, "loss": 3.4992, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.72674160733718e-05, "loss": 3.4914, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.725903012586128e-05, "loss": 3.487, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.725064417835076e-05, "loss": 3.5061, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.724225823084024e-05, "loss": 3.5081, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.723388866213345e-05, "loss": 3.4975, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.722550271462293e-05, "loss": 3.5046, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.721711676711241e-05, "loss": 3.5019, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.720873081960189e-05, "loss": 3.4983, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.72003612508951e-05, "loss": 3.4941, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.719197530338458e-05, "loss": 3.5025, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.718358935587406e-05, "loss": 3.4809, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.717520340836354e-05, "loss": 3.4973, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.7166833839656753e-05, "loss": 3.496, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7158447892146233e-05, "loss": 3.5093, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7150061944635713e-05, "loss": 3.4966, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.7141692375928922e-05, "loss": 3.4968, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.7133306428418402e-05, "loss": 3.5032, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.7124920480907885e-05, "loss": 3.4961, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.7116534533397365e-05, "loss": 3.5091, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.7108164964690574e-05, "loss": 3.4777, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7099779017180054e-05, "loss": 3.4991, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7091393069669534e-05, "loss": 3.5035, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.7083007122159014e-05, "loss": 3.504, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7074621174648494e-05, "loss": 3.494, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7066251605941707e-05, "loss": 3.4858, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.7057865658431187e-05, "loss": 3.492, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7049479710920667e-05, "loss": 3.478, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7041110142213876e-05, "loss": 3.5099, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7032724194703356e-05, "loss": 3.4886, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.702433824719284e-05, "loss": 3.5012, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.701595229968232e-05, "loss": 3.4975, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7007582730975528e-05, "loss": 3.4881, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.6999196783465008e-05, "loss": 3.4937, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6990810835954488e-05, "loss": 3.4862, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6982424888443968e-05, "loss": 3.4888, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.697405531973718e-05, "loss": 3.4857, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.696566937222666e-05, "loss": 3.5027, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.695728342471614e-05, "loss": 3.4862, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.694889747720562e-05, "loss": 3.488, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.694052790849883e-05, "loss": 3.4797, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.693214196098831e-05, "loss": 3.4901, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.6923756013477793e-05, "loss": 3.4956, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.6915370065967273e-05, "loss": 3.5027, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.6907000497260482e-05, "loss": 3.4946, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.6898614549749962e-05, "loss": 3.5026, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.689022860223944e-05, "loss": 3.508, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.688184265472892e-05, "loss": 3.4948, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.6873473086022134e-05, "loss": 3.4861, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.6865087138511614e-05, "loss": 3.4972, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.6856701191001094e-05, "loss": 3.4908, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6848315243490574e-05, "loss": 3.4937, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6839945674783783e-05, "loss": 3.4879, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.6831559727273263e-05, "loss": 3.5024, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.6823173779762746e-05, "loss": 3.5028, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6814787832252226e-05, "loss": 3.4902, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6806418263545435e-05, "loss": 3.4811, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6798032316034915e-05, "loss": 3.486, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6789646368524395e-05, "loss": 3.4966, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.6781260421013875e-05, "loss": 3.5017, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.6772890852307088e-05, "loss": 3.4959, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6764504904796568e-05, "loss": 3.4982, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.6756118957286048e-05, "loss": 3.4967, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.6747733009775528e-05, "loss": 3.4857, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.6739363441068737e-05, "loss": 3.4853, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6730977493558217e-05, "loss": 3.4935, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.6722591546047697e-05, "loss": 3.5002, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.671420559853718e-05, "loss": 3.4998, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.670583602983039e-05, "loss": 3.4964, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669745008231987e-05, "loss": 3.4829, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668906413480935e-05, "loss": 3.5004, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.668067818729883e-05, "loss": 3.5011, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.667230861859204e-05, "loss": 3.4918, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.666392267108152e-05, "loss": 3.4952, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.6655536723571e-05, "loss": 3.4827, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.664715077606048e-05, "loss": 3.4926, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.663878120735369e-05, "loss": 3.5005, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.663039525984317e-05, "loss": 3.4783, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.662200931233265e-05, "loss": 3.491, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6613623364822134e-05, "loss": 3.496, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6605253796115343e-05, "loss": 3.4951, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6596867848604823e-05, "loss": 3.4807, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6588481901094303e-05, "loss": 3.4963, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6580095953583783e-05, "loss": 3.4818, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6571726384876995e-05, "loss": 3.5028, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.6563340437366475e-05, "loss": 3.4865, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.6554954489855955e-05, "loss": 3.4871, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.6546568542345435e-05, "loss": 3.5009, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.6538198973638644e-05, "loss": 3.5062, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.6529813026128124e-05, "loss": 3.4926, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.6521427078617604e-05, "loss": 3.4899, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.6513041131107087e-05, "loss": 3.4909, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.6504671562400296e-05, "loss": 3.4926, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.6496285614889776e-05, "loss": 3.4878, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.6487899667379256e-05, "loss": 3.493, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.6479513719868736e-05, "loss": 3.4839, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.647114415116195e-05, "loss": 3.5002, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.646275820365143e-05, "loss": 3.4899, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.645437225614091e-05, "loss": 3.4915, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.644598630863039e-05, "loss": 3.4844, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.6437616739923598e-05, "loss": 3.4915, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.6429230792413078e-05, "loss": 3.4828, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.6420844844902558e-05, "loss": 3.5041, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.641245889739204e-05, "loss": 3.5024, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.640408932868525e-05, "loss": 3.4949, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.639570338117473e-05, "loss": 3.4807, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.638731743366421e-05, "loss": 3.4971, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.637893148615369e-05, "loss": 3.495, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6370561917446902e-05, "loss": 3.4971, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6362175969936382e-05, "loss": 3.4855, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.6353790022425862e-05, "loss": 3.4976, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.6345404074915342e-05, "loss": 3.499, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.633703450620855e-05, "loss": 3.5112, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.632864855869803e-05, "loss": 3.4933, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.632026261118751e-05, "loss": 3.4959, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.6311876663676988e-05, "loss": 3.4949, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.6303507094970204e-05, "loss": 3.4811, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.6295121147459684e-05, "loss": 3.5034, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.6286735199949164e-05, "loss": 3.5034, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.627834925243864e-05, "loss": 3.4928, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.6269979683731856e-05, "loss": 3.4923, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.6261593736221336e-05, "loss": 3.4832, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 3.8482627868652344, "eval_runtime": 303.7137, "eval_samples_per_second": 1256.417, "eval_steps_per_second": 39.264, "step": 1450080 }, { "epoch": 0.0, "learning_rate": 2.6253207788710816e-05, "loss": 3.4785, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.624482184120029e-05, "loss": 3.482, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.623643589368977e-05, "loss": 3.4978, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.622804994617925e-05, "loss": 3.4893, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.621968037747246e-05, "loss": 3.5043, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.621129442996194e-05, "loss": 3.4872, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.620290848245142e-05, "loss": 3.4903, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.61945225349409e-05, "loss": 3.4772, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.618615296623411e-05, "loss": 3.4906, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.6177767018723594e-05, "loss": 3.4905, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.6169381071213074e-05, "loss": 3.497, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.6160995123702554e-05, "loss": 3.496, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.61526419337995e-05, "loss": 3.4869, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.614425598628898e-05, "loss": 3.4804, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.613587003877846e-05, "loss": 3.4829, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.6127484091267935e-05, "loss": 3.4771, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.6119098143757415e-05, "loss": 3.4815, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.6110712196246895e-05, "loss": 3.4822, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.6102326248736375e-05, "loss": 3.4795, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.6093940301225855e-05, "loss": 3.5088, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6085570732519064e-05, "loss": 3.489, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6077184785008548e-05, "loss": 3.49, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6068798837498028e-05, "loss": 3.4937, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6060412889987507e-05, "loss": 3.4977, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.6052043321280717e-05, "loss": 3.4763, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.6043657373770197e-05, "loss": 3.4873, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.6035271426259676e-05, "loss": 3.4953, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.6026885478749156e-05, "loss": 3.4894, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.601851591004237e-05, "loss": 3.4773, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.601012996253185e-05, "loss": 3.474, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.600174401502133e-05, "loss": 3.4937, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.599335806751081e-05, "loss": 3.4952, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.5984988498804018e-05, "loss": 3.4893, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.59766025512935e-05, "loss": 3.4911, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.596821660378298e-05, "loss": 3.4844, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.595983065627246e-05, "loss": 3.4887, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.595146108756567e-05, "loss": 3.4798, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.594307514005515e-05, "loss": 3.4929, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.593468919254463e-05, "loss": 3.4712, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.592630324503411e-05, "loss": 3.4839, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.5917933676327323e-05, "loss": 3.481, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.5909547728816803e-05, "loss": 3.4991, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.5901161781306282e-05, "loss": 3.4871, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.589279221259949e-05, "loss": 3.4851, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.588440626508897e-05, "loss": 3.491, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.5876020317578455e-05, "loss": 3.4884, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.5867634370067935e-05, "loss": 3.4946, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.5859264801361144e-05, "loss": 3.4672, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.5850878853850624e-05, "loss": 3.4811, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.5842492906340104e-05, "loss": 3.4939, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.5834106958829584e-05, "loss": 3.4899, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.5825721011319064e-05, "loss": 3.4812, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.5817351442612276e-05, "loss": 3.4753, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.5808965495101756e-05, "loss": 3.479, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.5800579547591236e-05, "loss": 3.4669, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.5792209978884445e-05, "loss": 3.4936, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.5783824031373925e-05, "loss": 3.476, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.5775438083863405e-05, "loss": 3.4891, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.576705213635289e-05, "loss": 3.4872, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.5758682567646098e-05, "loss": 3.4751, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.5750296620135578e-05, "loss": 3.4768, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.5741910672625058e-05, "loss": 3.4737, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5733524725114537e-05, "loss": 3.4755, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.572515515640775e-05, "loss": 3.4797, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.571676920889723e-05, "loss": 3.4873, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.570838326138671e-05, "loss": 3.4765, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.569999731387619e-05, "loss": 3.4771, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.56916277451694e-05, "loss": 3.4683, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.568324179765888e-05, "loss": 3.4754, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.567485585014836e-05, "loss": 3.4805, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.5666469902637842e-05, "loss": 3.4958, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.565810033393105e-05, "loss": 3.4798, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.564971438642053e-05, "loss": 3.4888, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.564132843891001e-05, "loss": 3.4913, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.563294249139949e-05, "loss": 3.4885, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5624572922692704e-05, "loss": 3.4691, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.5616186975182184e-05, "loss": 3.4874, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.5607801027671664e-05, "loss": 3.482, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.5599415080161143e-05, "loss": 3.4765, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.5591045511454353e-05, "loss": 3.4846, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.5582659563943833e-05, "loss": 3.4843, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5574273616433313e-05, "loss": 3.4914, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5565887668922796e-05, "loss": 3.4791, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.5557518100216005e-05, "loss": 3.4676, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.5549132152705485e-05, "loss": 3.4768, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.5540746205194965e-05, "loss": 3.479, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.5532360257684445e-05, "loss": 3.4857, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.5523990688977657e-05, "loss": 3.4878, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.5515604741467137e-05, "loss": 3.4816, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.5507218793956617e-05, "loss": 3.4845, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.5498832846446097e-05, "loss": 3.4729, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.5490463277739306e-05, "loss": 3.4729, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.5482077330228786e-05, "loss": 3.4795, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.5473691382718266e-05, "loss": 3.4861, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.546530543520775e-05, "loss": 3.486, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.545693586650096e-05, "loss": 3.4925, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.544854991899044e-05, "loss": 3.4673, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.544016397147992e-05, "loss": 3.4902, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.54317780239694e-05, "loss": 3.4881, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.542340845526261e-05, "loss": 3.4824, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.541502250775209e-05, "loss": 3.4814, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.540663656024157e-05, "loss": 3.4729, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.539825061273105e-05, "loss": 3.4826, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.538988104402426e-05, "loss": 3.4859, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.538149509651374e-05, "loss": 3.4689, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.537310914900322e-05, "loss": 3.4789, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.5364723201492703e-05, "loss": 3.4804, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.5356353632785912e-05, "loss": 3.484, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.5347967685275392e-05, "loss": 3.4668, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.5339581737764872e-05, "loss": 3.4907, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5331195790254352e-05, "loss": 3.4653, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5322826221547565e-05, "loss": 3.4928, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.5314440274037045e-05, "loss": 3.4767, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.5306054326526525e-05, "loss": 3.4732, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.5297668379016004e-05, "loss": 3.4886, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.5289298810309214e-05, "loss": 3.493, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.5280912862798694e-05, "loss": 3.4804, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.5272526915288174e-05, "loss": 3.4771, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.5264140967777657e-05, "loss": 3.4806, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.5255771399070866e-05, "loss": 3.4812, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5247385451560346e-05, "loss": 3.4729, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.5238999504049826e-05, "loss": 3.4786, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.5230613556539306e-05, "loss": 3.4781, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.5222243987832518e-05, "loss": 3.4821, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.5213858040321998e-05, "loss": 3.4796, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.5205472092811478e-05, "loss": 3.4841, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5197086145300958e-05, "loss": 3.4667, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.5188716576594167e-05, "loss": 3.4781, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.5180330629083647e-05, "loss": 3.4756, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.5171944681573127e-05, "loss": 3.4857, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.516355873406261e-05, "loss": 3.4876, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.515518916535582e-05, "loss": 3.4853, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.51468032178453e-05, "loss": 3.468, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.513841727033478e-05, "loss": 3.4857, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.5130031322824256e-05, "loss": 3.4814, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.5121661754117472e-05, "loss": 3.4858, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.5113275806606952e-05, "loss": 3.4711, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.5104889859096432e-05, "loss": 3.4875, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.5096503911585905e-05, "loss": 3.4864, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.508813434287912e-05, "loss": 3.4992, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.50797483953686e-05, "loss": 3.4756, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.507136244785808e-05, "loss": 3.4844, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.5062976500347557e-05, "loss": 3.4834, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.5054606931640773e-05, "loss": 3.4734, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.5046220984130253e-05, "loss": 3.4874, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.5037835036619726e-05, "loss": 3.4923, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.502944908910921e-05, "loss": 3.4815, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.5021079520402426e-05, "loss": 3.4779, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.5012693572891906e-05, "loss": 3.4754, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 3.8490042686462402, "eval_runtime": 304.0065, "eval_samples_per_second": 1255.207, "eval_steps_per_second": 39.226, "step": 1526400 }, { "epoch": 1.0, "learning_rate": 2.500430762538138e-05, "loss": 3.47, "step": 1526784 }, { "epoch": 1.0, "learning_rate": 2.4995921677870862e-05, "loss": 3.4722, "step": 1527296 }, { "epoch": 1.0, "learning_rate": 2.498755210916407e-05, "loss": 3.4823, "step": 1527808 }, { "epoch": 1.0, "learning_rate": 2.497916616165355e-05, "loss": 3.4833, "step": 1528320 }, { "epoch": 1.0, "learning_rate": 2.4970780214143035e-05, "loss": 3.4927, "step": 1528832 }, { "epoch": 1.0, "learning_rate": 2.4962394266632514e-05, "loss": 3.478, "step": 1529344 }, { "epoch": 1.0, "learning_rate": 2.4954024697925724e-05, "loss": 3.4782, "step": 1529856 }, { "epoch": 1.0, "learning_rate": 2.4945638750415204e-05, "loss": 3.4631, "step": 1530368 }, { "epoch": 1.0, "learning_rate": 2.4937252802904683e-05, "loss": 3.4806, "step": 1530880 }, { "epoch": 1.0, "learning_rate": 2.4928866855394163e-05, "loss": 3.4788, "step": 1531392 }, { "epoch": 1.0, "learning_rate": 2.4920497286687376e-05, "loss": 3.4788, "step": 1531904 }, { "epoch": 1.0, "learning_rate": 2.4912111339176856e-05, "loss": 3.4864, "step": 1532416 }, { "epoch": 1.0, "learning_rate": 2.4903741770470065e-05, "loss": 3.4731, "step": 1532928 }, { "epoch": 1.0, "learning_rate": 2.4895355822959545e-05, "loss": 3.4719, "step": 1533440 }, { "epoch": 1.0, "learning_rate": 2.4886969875449025e-05, "loss": 3.4692, "step": 1533952 }, { "epoch": 1.0, "learning_rate": 2.4878583927938505e-05, "loss": 3.464, "step": 1534464 }, { "epoch": 1.0, "learning_rate": 2.4870197980427988e-05, "loss": 3.472, "step": 1534976 }, { "epoch": 1.0, "learning_rate": 2.4861812032917468e-05, "loss": 3.4715, "step": 1535488 }, { "epoch": 1.0, "learning_rate": 2.4853426085406945e-05, "loss": 3.4702, "step": 1536000 }, { "epoch": 1.0, "learning_rate": 2.4845040137896425e-05, "loss": 3.4942, "step": 1536512 }, { "epoch": 1.0, "learning_rate": 2.4836670569189637e-05, "loss": 3.4789, "step": 1537024 }, { "epoch": 1.0, "learning_rate": 2.4828284621679117e-05, "loss": 3.475, "step": 1537536 }, { "epoch": 1.0, "learning_rate": 2.4819898674168597e-05, "loss": 3.4851, "step": 1538048 }, { "epoch": 1.0, "learning_rate": 2.4811512726658077e-05, "loss": 3.4856, "step": 1538560 }, { "epoch": 1.0, "learning_rate": 2.480314315795129e-05, "loss": 3.469, "step": 1539072 }, { "epoch": 1.0, "learning_rate": 2.4794757210440766e-05, "loss": 3.4778, "step": 1539584 }, { "epoch": 1.0, "learning_rate": 2.4786371262930246e-05, "loss": 3.4792, "step": 1540096 }, { "epoch": 1.0, "learning_rate": 2.4777985315419726e-05, "loss": 3.4769, "step": 1540608 }, { "epoch": 1.0, "learning_rate": 2.4769615746712942e-05, "loss": 3.4629, "step": 1541120 }, { "epoch": 1.0, "learning_rate": 2.476122979920242e-05, "loss": 3.4665, "step": 1541632 }, { "epoch": 1.01, "learning_rate": 2.47528438516919e-05, "loss": 3.4805, "step": 1542144 }, { "epoch": 1.01, "learning_rate": 2.474445790418138e-05, "loss": 3.4816, "step": 1542656 }, { "epoch": 1.01, "learning_rate": 2.473608833547459e-05, "loss": 3.4771, "step": 1543168 }, { "epoch": 1.01, "learning_rate": 2.4727702387964067e-05, "loss": 3.4832, "step": 1543680 }, { "epoch": 1.01, "learning_rate": 2.471931644045355e-05, "loss": 3.4698, "step": 1544192 }, { "epoch": 1.01, "learning_rate": 2.471093049294303e-05, "loss": 3.4764, "step": 1544704 }, { "epoch": 1.01, "learning_rate": 2.470256092423624e-05, "loss": 3.4708, "step": 1545216 }, { "epoch": 1.01, "learning_rate": 2.469417497672572e-05, "loss": 3.4776, "step": 1545728 }, { "epoch": 1.01, "learning_rate": 2.46857890292152e-05, "loss": 3.4579, "step": 1546240 }, { "epoch": 1.01, "learning_rate": 2.4677419460508412e-05, "loss": 3.4698, "step": 1546752 }, { "epoch": 1.01, "learning_rate": 2.4669033512997892e-05, "loss": 3.4671, "step": 1547264 }, { "epoch": 1.01, "learning_rate": 2.4660647565487372e-05, "loss": 3.4905, "step": 1547776 }, { "epoch": 1.01, "learning_rate": 2.4652261617976852e-05, "loss": 3.4759, "step": 1548288 }, { "epoch": 1.01, "learning_rate": 2.4643892049270065e-05, "loss": 3.4726, "step": 1548800 }, { "epoch": 1.01, "learning_rate": 2.463550610175954e-05, "loss": 3.4792, "step": 1549312 }, { "epoch": 1.01, "learning_rate": 2.462712015424902e-05, "loss": 3.4774, "step": 1549824 }, { "epoch": 1.01, "learning_rate": 2.4618734206738504e-05, "loss": 3.4837, "step": 1550336 }, { "epoch": 1.01, "learning_rate": 2.4610364638031713e-05, "loss": 3.4584, "step": 1550848 }, { "epoch": 1.01, "learning_rate": 2.4601978690521193e-05, "loss": 3.4668, "step": 1551360 }, { "epoch": 1.01, "learning_rate": 2.4593592743010673e-05, "loss": 3.4837, "step": 1551872 }, { "epoch": 1.01, "learning_rate": 2.4585206795500153e-05, "loss": 3.4811, "step": 1552384 }, { "epoch": 1.01, "learning_rate": 2.4576837226793366e-05, "loss": 3.4666, "step": 1552896 }, { "epoch": 1.01, "learning_rate": 2.4568451279282846e-05, "loss": 3.4635, "step": 1553408 }, { "epoch": 1.01, "learning_rate": 2.4560065331772326e-05, "loss": 3.4714, "step": 1553920 }, { "epoch": 1.01, "learning_rate": 2.4551679384261806e-05, "loss": 3.4581, "step": 1554432 }, { "epoch": 1.01, "learning_rate": 2.4543309815555015e-05, "loss": 3.4758, "step": 1554944 }, { "epoch": 1.01, "learning_rate": 2.4534923868044495e-05, "loss": 3.4633, "step": 1555456 }, { "epoch": 1.01, "learning_rate": 2.4526537920533975e-05, "loss": 3.475, "step": 1555968 }, { "epoch": 1.01, "learning_rate": 2.4518151973023458e-05, "loss": 3.4737, "step": 1556480 }, { "epoch": 1.01, "learning_rate": 2.4509782404316667e-05, "loss": 3.4702, "step": 1556992 }, { "epoch": 1.01, "learning_rate": 2.4501396456806147e-05, "loss": 3.4633, "step": 1557504 }, { "epoch": 1.01, "learning_rate": 2.4493010509295627e-05, "loss": 3.4649, "step": 1558016 }, { "epoch": 1.01, "learning_rate": 2.4484624561785107e-05, "loss": 3.4614, "step": 1558528 }, { "epoch": 1.01, "learning_rate": 2.447625499307832e-05, "loss": 3.4691, "step": 1559040 }, { "epoch": 1.01, "learning_rate": 2.44678690455678e-05, "loss": 3.4728, "step": 1559552 }, { "epoch": 1.01, "learning_rate": 2.445948309805728e-05, "loss": 3.466, "step": 1560064 }, { "epoch": 1.01, "learning_rate": 2.445109715054676e-05, "loss": 3.4664, "step": 1560576 }, { "epoch": 1.01, "learning_rate": 2.444272758183997e-05, "loss": 3.4559, "step": 1561088 }, { "epoch": 1.01, "learning_rate": 2.443434163432945e-05, "loss": 3.4625, "step": 1561600 }, { "epoch": 1.01, "learning_rate": 2.442595568681893e-05, "loss": 3.4701, "step": 1562112 }, { "epoch": 1.01, "learning_rate": 2.4417569739308412e-05, "loss": 3.4789, "step": 1562624 }, { "epoch": 1.01, "learning_rate": 2.440920017060162e-05, "loss": 3.4713, "step": 1563136 }, { "epoch": 1.01, "learning_rate": 2.44008142230911e-05, "loss": 3.4794, "step": 1563648 }, { "epoch": 1.01, "learning_rate": 2.439242827558058e-05, "loss": 3.4826, "step": 1564160 }, { "epoch": 1.01, "learning_rate": 2.438404232807006e-05, "loss": 3.4762, "step": 1564672 }, { "epoch": 1.01, "learning_rate": 2.4375672759363273e-05, "loss": 3.4579, "step": 1565184 }, { "epoch": 1.01, "learning_rate": 2.4367286811852753e-05, "loss": 3.4748, "step": 1565696 }, { "epoch": 1.01, "learning_rate": 2.4358900864342233e-05, "loss": 3.4728, "step": 1566208 }, { "epoch": 1.01, "learning_rate": 2.4350514916831713e-05, "loss": 3.4626, "step": 1566720 }, { "epoch": 1.01, "learning_rate": 2.4342145348124922e-05, "loss": 3.4705, "step": 1567232 }, { "epoch": 1.01, "learning_rate": 2.4333759400614402e-05, "loss": 3.4744, "step": 1567744 }, { "epoch": 1.01, "learning_rate": 2.4325373453103882e-05, "loss": 3.4826, "step": 1568256 }, { "epoch": 1.01, "learning_rate": 2.4316987505593365e-05, "loss": 3.4671, "step": 1568768 }, { "epoch": 1.01, "learning_rate": 2.4308617936886574e-05, "loss": 3.4531, "step": 1569280 }, { "epoch": 1.01, "learning_rate": 2.4300231989376054e-05, "loss": 3.4662, "step": 1569792 }, { "epoch": 1.01, "learning_rate": 2.4291846041865534e-05, "loss": 3.4705, "step": 1570304 }, { "epoch": 1.01, "learning_rate": 2.4283460094355014e-05, "loss": 3.4714, "step": 1570816 }, { "epoch": 1.01, "learning_rate": 2.4275090525648227e-05, "loss": 3.4747, "step": 1571328 }, { "epoch": 1.01, "learning_rate": 2.4266704578137707e-05, "loss": 3.4724, "step": 1571840 }, { "epoch": 1.02, "learning_rate": 2.4258318630627187e-05, "loss": 3.4729, "step": 1572352 }, { "epoch": 1.02, "learning_rate": 2.4249932683116663e-05, "loss": 3.4619, "step": 1572864 }, { "epoch": 1.02, "learning_rate": 2.4241563114409876e-05, "loss": 3.462, "step": 1573376 }, { "epoch": 1.02, "learning_rate": 2.4233177166899356e-05, "loss": 3.4653, "step": 1573888 }, { "epoch": 1.02, "learning_rate": 2.4224791219388836e-05, "loss": 3.477, "step": 1574400 }, { "epoch": 1.02, "learning_rate": 2.4216405271878316e-05, "loss": 3.4747, "step": 1574912 }, { "epoch": 1.02, "learning_rate": 2.4208035703171528e-05, "loss": 3.4814, "step": 1575424 }, { "epoch": 1.02, "learning_rate": 2.4199649755661008e-05, "loss": 3.4568, "step": 1575936 }, { "epoch": 1.02, "learning_rate": 2.4191263808150488e-05, "loss": 3.4751, "step": 1576448 }, { "epoch": 1.02, "learning_rate": 2.4182877860639965e-05, "loss": 3.4752, "step": 1576960 }, { "epoch": 1.02, "learning_rate": 2.417450829193318e-05, "loss": 3.475, "step": 1577472 }, { "epoch": 1.02, "learning_rate": 2.416612234442266e-05, "loss": 3.4695, "step": 1577984 }, { "epoch": 1.02, "learning_rate": 2.4157736396912137e-05, "loss": 3.4655, "step": 1578496 }, { "epoch": 1.02, "learning_rate": 2.4149350449401617e-05, "loss": 3.4677, "step": 1579008 }, { "epoch": 1.02, "learning_rate": 2.414098088069483e-05, "loss": 3.4744, "step": 1579520 }, { "epoch": 1.02, "learning_rate": 2.413259493318431e-05, "loss": 3.4543, "step": 1580032 }, { "epoch": 1.02, "learning_rate": 2.412420898567379e-05, "loss": 3.4714, "step": 1580544 }, { "epoch": 1.02, "learning_rate": 2.411582303816327e-05, "loss": 3.4659, "step": 1581056 }, { "epoch": 1.02, "learning_rate": 2.4107453469456482e-05, "loss": 3.4722, "step": 1581568 }, { "epoch": 1.02, "learning_rate": 2.4099067521945962e-05, "loss": 3.4542, "step": 1582080 }, { "epoch": 1.02, "learning_rate": 2.409068157443544e-05, "loss": 3.4749, "step": 1582592 }, { "epoch": 1.02, "learning_rate": 2.4082295626924918e-05, "loss": 3.4625, "step": 1583104 }, { "epoch": 1.02, "learning_rate": 2.4073926058218134e-05, "loss": 3.4754, "step": 1583616 }, { "epoch": 1.02, "learning_rate": 2.406554011070761e-05, "loss": 3.4645, "step": 1584128 }, { "epoch": 1.02, "learning_rate": 2.405715416319709e-05, "loss": 3.4602, "step": 1584640 }, { "epoch": 1.02, "learning_rate": 2.4048784594490303e-05, "loss": 3.4771, "step": 1585152 }, { "epoch": 1.02, "learning_rate": 2.4040398646979783e-05, "loss": 3.482, "step": 1585664 }, { "epoch": 1.02, "learning_rate": 2.403201269946926e-05, "loss": 3.4708, "step": 1586176 }, { "epoch": 1.02, "learning_rate": 2.4023626751958743e-05, "loss": 3.4626, "step": 1586688 }, { "epoch": 1.02, "learning_rate": 2.4015257183251956e-05, "loss": 3.47, "step": 1587200 }, { "epoch": 1.02, "learning_rate": 2.4006871235741435e-05, "loss": 3.4697, "step": 1587712 }, { "epoch": 1.02, "learning_rate": 2.3998485288230912e-05, "loss": 3.4607, "step": 1588224 }, { "epoch": 1.02, "learning_rate": 2.3990099340720392e-05, "loss": 3.4668, "step": 1588736 }, { "epoch": 1.02, "learning_rate": 2.3981729772013604e-05, "loss": 3.4643, "step": 1589248 }, { "epoch": 1.02, "learning_rate": 2.3973343824503084e-05, "loss": 3.4716, "step": 1589760 }, { "epoch": 1.02, "learning_rate": 2.3964957876992564e-05, "loss": 3.4684, "step": 1590272 }, { "epoch": 1.02, "learning_rate": 2.3956571929482044e-05, "loss": 3.4742, "step": 1590784 }, { "epoch": 1.02, "learning_rate": 2.3948202360775257e-05, "loss": 3.4559, "step": 1591296 }, { "epoch": 1.02, "learning_rate": 2.3939816413264733e-05, "loss": 3.4671, "step": 1591808 }, { "epoch": 1.02, "learning_rate": 2.3931430465754213e-05, "loss": 3.4663, "step": 1592320 }, { "epoch": 1.02, "learning_rate": 2.3923044518243697e-05, "loss": 3.4778, "step": 1592832 }, { "epoch": 1.02, "learning_rate": 2.391467494953691e-05, "loss": 3.4688, "step": 1593344 }, { "epoch": 1.02, "learning_rate": 2.3906289002026386e-05, "loss": 3.4775, "step": 1593856 }, { "epoch": 1.02, "learning_rate": 2.3897903054515866e-05, "loss": 3.4565, "step": 1594368 }, { "epoch": 1.02, "learning_rate": 2.3889517107005346e-05, "loss": 3.4743, "step": 1594880 }, { "epoch": 1.02, "learning_rate": 2.3881147538298558e-05, "loss": 3.4739, "step": 1595392 }, { "epoch": 1.02, "learning_rate": 2.3872761590788038e-05, "loss": 3.473, "step": 1595904 }, { "epoch": 1.02, "learning_rate": 2.3864375643277518e-05, "loss": 3.4565, "step": 1596416 }, { "epoch": 1.02, "learning_rate": 2.3855989695766998e-05, "loss": 3.4749, "step": 1596928 }, { "epoch": 1.02, "learning_rate": 2.3847620127060207e-05, "loss": 3.4737, "step": 1597440 }, { "epoch": 1.02, "learning_rate": 2.3839234179549687e-05, "loss": 3.4919, "step": 1597952 }, { "epoch": 1.02, "learning_rate": 2.3830848232039167e-05, "loss": 3.4609, "step": 1598464 }, { "epoch": 1.02, "learning_rate": 2.382246228452865e-05, "loss": 3.4735, "step": 1598976 }, { "epoch": 1.02, "learning_rate": 2.381409271582186e-05, "loss": 3.4714, "step": 1599488 }, { "epoch": 1.02, "learning_rate": 2.380570676831134e-05, "loss": 3.4613, "step": 1600000 }, { "epoch": 1.02, "learning_rate": 2.379732082080082e-05, "loss": 3.4747, "step": 1600512 }, { "epoch": 1.02, "learning_rate": 2.37889348732903e-05, "loss": 3.478, "step": 1601024 }, { "epoch": 1.02, "learning_rate": 2.3780565304583512e-05, "loss": 3.4737, "step": 1601536 }, { "epoch": 1.02, "learning_rate": 2.3772179357072992e-05, "loss": 3.4623, "step": 1602048 }, { "epoch": 1.02, "learning_rate": 2.3763793409562472e-05, "loss": 3.4668, "step": 1602560 }, { "epoch": 1.03, "eval_loss": 3.8499131202697754, "eval_runtime": 313.4377, "eval_samples_per_second": 1217.438, "eval_steps_per_second": 38.046, "step": 1602720 }, { "epoch": 0.0, "learning_rate": 2.375540746205195e-05, "loss": 3.4576, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.374702151454143e-05, "loss": 3.4587, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.373863556703091e-05, "loss": 3.4716, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3730249619520388e-05, "loss": 3.4726, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.3721880050813604e-05, "loss": 3.4767, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.3713494103303084e-05, "loss": 3.4681, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.370510815579256e-05, "loss": 3.4644, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.369672220828204e-05, "loss": 3.4544, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.3688352639575253e-05, "loss": 3.4669, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.3679966692064733e-05, "loss": 3.4688, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.3671580744554213e-05, "loss": 3.4676, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.3663194797043693e-05, "loss": 3.4727, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.3654841607140634e-05, "loss": 3.4618, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.3646455659630114e-05, "loss": 3.4621, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.3638069712119594e-05, "loss": 3.46, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.3629683764609074e-05, "loss": 3.4503, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.3621297817098558e-05, "loss": 3.4634, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.3612911869588034e-05, "loss": 3.4604, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.3604525922077514e-05, "loss": 3.4567, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.3596139974566994e-05, "loss": 3.4797, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.3587770405860207e-05, "loss": 3.4695, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.3579384458349683e-05, "loss": 3.4672, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.3570998510839167e-05, "loss": 3.4699, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.3562612563328647e-05, "loss": 3.4767, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.355424299462186e-05, "loss": 3.4526, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.3545857047111336e-05, "loss": 3.4657, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.3537471099600816e-05, "loss": 3.4728, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.3529085152090296e-05, "loss": 3.4611, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.3520715583383508e-05, "loss": 3.4533, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.3512329635872988e-05, "loss": 3.4563, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.3503943688362468e-05, "loss": 3.4697, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.3495557740851948e-05, "loss": 3.4689, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3487188172145157e-05, "loss": 3.4676, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.3478802224634637e-05, "loss": 3.4706, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.347041627712412e-05, "loss": 3.4588, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.34620303296136e-05, "loss": 3.4634, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.345366076090681e-05, "loss": 3.4618, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.344527481339629e-05, "loss": 3.4633, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.343688886588577e-05, "loss": 3.4481, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.342850291837525e-05, "loss": 3.4581, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.342013334966846e-05, "loss": 3.4604, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.341174740215794e-05, "loss": 3.4746, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.340336145464742e-05, "loss": 3.4644, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.33949755071369e-05, "loss": 3.4612, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.338660593843011e-05, "loss": 3.4703, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.337821999091959e-05, "loss": 3.4617, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3369834043409074e-05, "loss": 3.4714, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.3361448095898554e-05, "loss": 3.4509, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.3353078527191763e-05, "loss": 3.4512, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3344692579681243e-05, "loss": 3.4702, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3336306632170723e-05, "loss": 3.468, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3327937063463935e-05, "loss": 3.4569, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3319551115953415e-05, "loss": 3.4556, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3311165168442895e-05, "loss": 3.4607, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3302779220932375e-05, "loss": 3.4448, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.3294409652225584e-05, "loss": 3.4658, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.3286023704715064e-05, "loss": 3.4546, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3277637757204544e-05, "loss": 3.4593, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3269251809694028e-05, "loss": 3.466, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3260882240987237e-05, "loss": 3.4551, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3252496293476717e-05, "loss": 3.4533, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.3244110345966197e-05, "loss": 3.4554, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.3235724398455677e-05, "loss": 3.4504, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.322735482974889e-05, "loss": 3.4554, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.321896888223837e-05, "loss": 3.4648, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.321058293472785e-05, "loss": 3.4583, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.320219698721733e-05, "loss": 3.4517, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.319381103970681e-05, "loss": 3.4459, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.3185441471000018e-05, "loss": 3.4478, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.3177055523489498e-05, "loss": 3.4569, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.316866957597898e-05, "loss": 3.4648, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.316030000727219e-05, "loss": 3.4635, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.315191405976167e-05, "loss": 3.4658, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.314352811225115e-05, "loss": 3.4662, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.313514216474063e-05, "loss": 3.4722, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.3126772596033843e-05, "loss": 3.4442, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.3118386648523323e-05, "loss": 3.4616, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.3110000701012803e-05, "loss": 3.4636, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.3101614753502283e-05, "loss": 3.4485, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.309324518479549e-05, "loss": 3.4657, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.308485923728497e-05, "loss": 3.4585, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.307647328977445e-05, "loss": 3.4687, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.306808734226393e-05, "loss": 3.4579, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.3059717773557144e-05, "loss": 3.4432, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.3051331826046624e-05, "loss": 3.4548, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.3042945878536104e-05, "loss": 3.4564, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.303455993102558e-05, "loss": 3.4646, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3026190362318796e-05, "loss": 3.461, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3017804414808276e-05, "loss": 3.4626, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3009418467297756e-05, "loss": 3.4618, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.3001032519787233e-05, "loss": 3.452, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.2992662951080445e-05, "loss": 3.4477, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.2984277003569925e-05, "loss": 3.4547, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2975891056059405e-05, "loss": 3.4679, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2967505108548885e-05, "loss": 3.4634, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2959135539842098e-05, "loss": 3.468, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2950749592331578e-05, "loss": 3.4476, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2942363644821054e-05, "loss": 3.4626, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2933977697310534e-05, "loss": 3.4632, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2925608128603747e-05, "loss": 3.4637, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.291722218109323e-05, "loss": 3.4546, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2908836233582707e-05, "loss": 3.4545, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2900450286072187e-05, "loss": 3.4566, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.28920807173654e-05, "loss": 3.464, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2883694769854876e-05, "loss": 3.4411, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.287530882234436e-05, "loss": 3.4598, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.286692287483384e-05, "loss": 3.4502, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.285855330612705e-05, "loss": 3.4622, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.2850167358616528e-05, "loss": 3.4443, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2841781411106008e-05, "loss": 3.4663, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2833395463595488e-05, "loss": 3.4515, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.28250258948887e-05, "loss": 3.4645, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.281663994737818e-05, "loss": 3.4556, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.280825399986766e-05, "loss": 3.4531, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.279986805235714e-05, "loss": 3.4614, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.279149848365035e-05, "loss": 3.473, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.278311253613983e-05, "loss": 3.4603, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2774726588629313e-05, "loss": 3.4503, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.2766340641118793e-05, "loss": 3.4598, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.2757971072412e-05, "loss": 3.4598, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.274958512490148e-05, "loss": 3.4502, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.274119917739096e-05, "loss": 3.4579, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.273281322988044e-05, "loss": 3.4497, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.2724443661173654e-05, "loss": 3.4569, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.2716057713663134e-05, "loss": 3.4595, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.2707671766152614e-05, "loss": 3.4645, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.2699285818642094e-05, "loss": 3.4419, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.2690916249935303e-05, "loss": 3.4579, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.2682530302424783e-05, "loss": 3.4526, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.2674144354914266e-05, "loss": 3.4656, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.2665758407403746e-05, "loss": 3.4598, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.2657388838696955e-05, "loss": 3.4669, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.2649002891186435e-05, "loss": 3.4458, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.2640616943675915e-05, "loss": 3.4646, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.2632230996165395e-05, "loss": 3.4612, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.2623861427458608e-05, "loss": 3.4641, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2615475479948088e-05, "loss": 3.4506, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.2607089532437568e-05, "loss": 3.4624, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.2598703584927048e-05, "loss": 3.4621, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.2590334016220257e-05, "loss": 3.4782, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.2581948068709737e-05, "loss": 3.4506, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.2573562121199217e-05, "loss": 3.4642, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.25651761736887e-05, "loss": 3.4608, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.255680660498191e-05, "loss": 3.4527, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.254842065747139e-05, "loss": 3.4632, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.254003470996087e-05, "loss": 3.4615, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.253164876245035e-05, "loss": 3.4686, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.252327919374356e-05, "loss": 3.4494, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.251489324623304e-05, "loss": 3.4585, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 3.8525936603546143, "eval_runtime": 584.551, "eval_samples_per_second": 652.793, "eval_steps_per_second": 20.4, "step": 1679040 }, { "epoch": 1.0, "learning_rate": 2.250650729872252e-05, "loss": 3.4514, "step": 1679360 }, { "epoch": 1.0, "learning_rate": 2.2498121351212e-05, "loss": 3.4447, "step": 1679872 }, { "epoch": 1.0, "learning_rate": 2.248975178250521e-05, "loss": 3.4596, "step": 1680384 }, { "epoch": 1.0, "learning_rate": 2.248136583499469e-05, "loss": 3.4621, "step": 1680896 }, { "epoch": 1.0, "learning_rate": 2.247297988748417e-05, "loss": 3.4655, "step": 1681408 }, { "epoch": 1.0, "learning_rate": 2.2464593939973654e-05, "loss": 3.4562, "step": 1681920 }, { "epoch": 1.0, "learning_rate": 2.2456224371266863e-05, "loss": 3.4476, "step": 1682432 }, { "epoch": 1.0, "learning_rate": 2.2447838423756343e-05, "loss": 3.4467, "step": 1682944 }, { "epoch": 1.0, "learning_rate": 2.2439452476245823e-05, "loss": 3.4546, "step": 1683456 }, { "epoch": 1.0, "learning_rate": 2.243108290753903e-05, "loss": 3.4557, "step": 1683968 }, { "epoch": 1.0, "learning_rate": 2.2422696960028515e-05, "loss": 3.4581, "step": 1684480 }, { "epoch": 1.0, "learning_rate": 2.2414311012517995e-05, "loss": 3.464, "step": 1684992 }, { "epoch": 1.0, "learning_rate": 2.2405941443811204e-05, "loss": 3.4525, "step": 1685504 }, { "epoch": 1.0, "learning_rate": 2.2397555496300684e-05, "loss": 3.4474, "step": 1686016 }, { "epoch": 1.0, "learning_rate": 2.2389169548790164e-05, "loss": 3.4518, "step": 1686528 }, { "epoch": 1.0, "learning_rate": 2.2380783601279644e-05, "loss": 3.4375, "step": 1687040 }, { "epoch": 1.0, "learning_rate": 2.2372397653769124e-05, "loss": 3.4501, "step": 1687552 }, { "epoch": 1.0, "learning_rate": 2.2364011706258604e-05, "loss": 3.447, "step": 1688064 }, { "epoch": 1.0, "learning_rate": 2.2355625758748084e-05, "loss": 3.4457, "step": 1688576 }, { "epoch": 1.0, "learning_rate": 2.2347239811237564e-05, "loss": 3.4671, "step": 1689088 }, { "epoch": 1.0, "learning_rate": 2.2338870242530773e-05, "loss": 3.4593, "step": 1689600 }, { "epoch": 1.0, "learning_rate": 2.2330484295020253e-05, "loss": 3.4573, "step": 1690112 }, { "epoch": 1.0, "learning_rate": 2.2322098347509736e-05, "loss": 3.4562, "step": 1690624 }, { "epoch": 1.0, "learning_rate": 2.2313712399999216e-05, "loss": 3.4644, "step": 1691136 }, { "epoch": 1.0, "learning_rate": 2.2305342831292425e-05, "loss": 3.445, "step": 1691648 }, { "epoch": 1.0, "learning_rate": 2.2296956883781905e-05, "loss": 3.459, "step": 1692160 }, { "epoch": 1.0, "learning_rate": 2.2288570936271385e-05, "loss": 3.4566, "step": 1692672 }, { "epoch": 1.0, "learning_rate": 2.2280184988760865e-05, "loss": 3.4498, "step": 1693184 }, { "epoch": 1.0, "learning_rate": 2.2271815420054078e-05, "loss": 3.4466, "step": 1693696 }, { "epoch": 1.0, "learning_rate": 2.2263429472543557e-05, "loss": 3.4424, "step": 1694208 }, { "epoch": 1.01, "learning_rate": 2.2255043525033037e-05, "loss": 3.4602, "step": 1694720 }, { "epoch": 1.01, "learning_rate": 2.2246657577522517e-05, "loss": 3.4573, "step": 1695232 }, { "epoch": 1.01, "learning_rate": 2.2238288008815726e-05, "loss": 3.4568, "step": 1695744 }, { "epoch": 1.01, "learning_rate": 2.2229902061305206e-05, "loss": 3.4603, "step": 1696256 }, { "epoch": 1.01, "learning_rate": 2.222151611379469e-05, "loss": 3.4464, "step": 1696768 }, { "epoch": 1.01, "learning_rate": 2.22131465450879e-05, "loss": 3.4528, "step": 1697280 }, { "epoch": 1.01, "learning_rate": 2.220476059757738e-05, "loss": 3.4543, "step": 1697792 }, { "epoch": 1.01, "learning_rate": 2.219637465006686e-05, "loss": 3.4484, "step": 1698304 }, { "epoch": 1.01, "learning_rate": 2.218798870255634e-05, "loss": 3.4371, "step": 1698816 }, { "epoch": 1.01, "learning_rate": 2.217961913384955e-05, "loss": 3.4475, "step": 1699328 }, { "epoch": 1.01, "learning_rate": 2.217123318633903e-05, "loss": 3.4486, "step": 1699840 }, { "epoch": 1.01, "learning_rate": 2.216284723882851e-05, "loss": 3.4629, "step": 1700352 }, { "epoch": 1.01, "learning_rate": 2.215446129131799e-05, "loss": 3.4522, "step": 1700864 }, { "epoch": 1.01, "learning_rate": 2.21460917226112e-05, "loss": 3.4488, "step": 1701376 }, { "epoch": 1.01, "learning_rate": 2.213770577510068e-05, "loss": 3.4632, "step": 1701888 }, { "epoch": 1.01, "learning_rate": 2.212931982759016e-05, "loss": 3.4509, "step": 1702400 }, { "epoch": 1.01, "learning_rate": 2.212093388007964e-05, "loss": 3.4603, "step": 1702912 }, { "epoch": 1.01, "learning_rate": 2.2112564311372853e-05, "loss": 3.4423, "step": 1703424 }, { "epoch": 1.01, "learning_rate": 2.2104178363862333e-05, "loss": 3.4333, "step": 1703936 }, { "epoch": 1.01, "learning_rate": 2.2095792416351812e-05, "loss": 3.4608, "step": 1704448 }, { "epoch": 1.01, "learning_rate": 2.2087406468841292e-05, "loss": 3.4566, "step": 1704960 }, { "epoch": 1.01, "learning_rate": 2.2079036900134505e-05, "loss": 3.4481, "step": 1705472 }, { "epoch": 1.01, "learning_rate": 2.2070650952623985e-05, "loss": 3.4427, "step": 1705984 }, { "epoch": 1.01, "learning_rate": 2.2062265005113465e-05, "loss": 3.4493, "step": 1706496 }, { "epoch": 1.01, "learning_rate": 2.2053879057602945e-05, "loss": 3.4334, "step": 1707008 }, { "epoch": 1.01, "learning_rate": 2.2045509488896154e-05, "loss": 3.454, "step": 1707520 }, { "epoch": 1.01, "learning_rate": 2.2037123541385634e-05, "loss": 3.4453, "step": 1708032 }, { "epoch": 1.01, "learning_rate": 2.2028737593875114e-05, "loss": 3.4467, "step": 1708544 }, { "epoch": 1.01, "learning_rate": 2.2020351646364594e-05, "loss": 3.4548, "step": 1709056 }, { "epoch": 1.01, "learning_rate": 2.2011982077657806e-05, "loss": 3.4464, "step": 1709568 }, { "epoch": 1.01, "learning_rate": 2.2003596130147286e-05, "loss": 3.4426, "step": 1710080 }, { "epoch": 1.01, "learning_rate": 2.1995210182636766e-05, "loss": 3.4495, "step": 1710592 }, { "epoch": 1.01, "learning_rate": 2.1986824235126246e-05, "loss": 3.4374, "step": 1711104 }, { "epoch": 1.01, "learning_rate": 2.1978454666419455e-05, "loss": 3.4457, "step": 1711616 }, { "epoch": 1.01, "learning_rate": 2.197006871890894e-05, "loss": 3.4515, "step": 1712128 }, { "epoch": 1.01, "learning_rate": 2.196168277139842e-05, "loss": 3.4475, "step": 1712640 }, { "epoch": 1.01, "learning_rate": 2.19532968238879e-05, "loss": 3.4391, "step": 1713152 }, { "epoch": 1.01, "learning_rate": 2.1944927255181108e-05, "loss": 3.4389, "step": 1713664 }, { "epoch": 1.01, "learning_rate": 2.1936541307670587e-05, "loss": 3.4371, "step": 1714176 }, { "epoch": 1.01, "learning_rate": 2.1928155360160067e-05, "loss": 3.444, "step": 1714688 }, { "epoch": 1.01, "learning_rate": 2.1919769412649547e-05, "loss": 3.454, "step": 1715200 }, { "epoch": 1.01, "learning_rate": 2.191139984394276e-05, "loss": 3.4499, "step": 1715712 }, { "epoch": 1.01, "learning_rate": 2.190301389643224e-05, "loss": 3.4577, "step": 1716224 }, { "epoch": 1.01, "learning_rate": 2.189462794892172e-05, "loss": 3.4527, "step": 1716736 }, { "epoch": 1.01, "learning_rate": 2.1886242001411196e-05, "loss": 3.462, "step": 1717248 }, { "epoch": 1.01, "learning_rate": 2.187787243270441e-05, "loss": 3.4355, "step": 1717760 }, { "epoch": 1.01, "learning_rate": 2.1869486485193892e-05, "loss": 3.4533, "step": 1718272 }, { "epoch": 1.01, "learning_rate": 2.1861100537683372e-05, "loss": 3.4509, "step": 1718784 }, { "epoch": 1.01, "learning_rate": 2.185271459017285e-05, "loss": 3.4337, "step": 1719296 }, { "epoch": 1.01, "learning_rate": 2.184434502146606e-05, "loss": 3.4551, "step": 1719808 }, { "epoch": 1.01, "learning_rate": 2.183595907395554e-05, "loss": 3.4502, "step": 1720320 }, { "epoch": 1.01, "learning_rate": 2.182757312644502e-05, "loss": 3.4556, "step": 1720832 }, { "epoch": 1.01, "learning_rate": 2.18191871789345e-05, "loss": 3.4496, "step": 1721344 }, { "epoch": 1.01, "learning_rate": 2.1810817610227714e-05, "loss": 3.4342, "step": 1721856 }, { "epoch": 1.01, "learning_rate": 2.1802431662717194e-05, "loss": 3.4431, "step": 1722368 }, { "epoch": 1.01, "learning_rate": 2.179404571520667e-05, "loss": 3.4459, "step": 1722880 }, { "epoch": 1.01, "learning_rate": 2.178565976769615e-05, "loss": 3.4515, "step": 1723392 }, { "epoch": 1.01, "learning_rate": 2.1777290198989363e-05, "loss": 3.449, "step": 1723904 }, { "epoch": 1.01, "learning_rate": 2.1768904251478846e-05, "loss": 3.4528, "step": 1724416 }, { "epoch": 1.02, "learning_rate": 2.1760518303968322e-05, "loss": 3.4487, "step": 1724928 }, { "epoch": 1.02, "learning_rate": 2.1752132356457802e-05, "loss": 3.446, "step": 1725440 }, { "epoch": 1.02, "learning_rate": 2.1743762787751015e-05, "loss": 3.4375, "step": 1725952 }, { "epoch": 1.02, "learning_rate": 2.1735376840240495e-05, "loss": 3.4429, "step": 1726464 }, { "epoch": 1.02, "learning_rate": 2.1726990892729975e-05, "loss": 3.4588, "step": 1726976 }, { "epoch": 1.02, "learning_rate": 2.1718604945219455e-05, "loss": 3.4544, "step": 1727488 }, { "epoch": 1.02, "learning_rate": 2.1710235376512667e-05, "loss": 3.4544, "step": 1728000 }, { "epoch": 1.02, "learning_rate": 2.1701849429002144e-05, "loss": 3.4366, "step": 1728512 }, { "epoch": 1.02, "learning_rate": 2.1693463481491624e-05, "loss": 3.4512, "step": 1729024 }, { "epoch": 1.02, "learning_rate": 2.1685077533981104e-05, "loss": 3.4521, "step": 1729536 }, { "epoch": 1.02, "learning_rate": 2.1676707965274316e-05, "loss": 3.4508, "step": 1730048 }, { "epoch": 1.02, "learning_rate": 2.1668322017763796e-05, "loss": 3.4479, "step": 1730560 }, { "epoch": 1.02, "learning_rate": 2.1659936070253276e-05, "loss": 3.4451, "step": 1731072 }, { "epoch": 1.02, "learning_rate": 2.1651550122742756e-05, "loss": 3.4466, "step": 1731584 }, { "epoch": 1.02, "learning_rate": 2.164318055403597e-05, "loss": 3.451, "step": 1732096 }, { "epoch": 1.02, "learning_rate": 2.1634794606525445e-05, "loss": 3.4338, "step": 1732608 }, { "epoch": 1.02, "learning_rate": 2.1626408659014925e-05, "loss": 3.4447, "step": 1733120 }, { "epoch": 1.02, "learning_rate": 2.161802271150441e-05, "loss": 3.4398, "step": 1733632 }, { "epoch": 1.02, "learning_rate": 2.1609653142797617e-05, "loss": 3.453, "step": 1734144 }, { "epoch": 1.02, "learning_rate": 2.1601267195287097e-05, "loss": 3.4365, "step": 1734656 }, { "epoch": 1.02, "learning_rate": 2.1592881247776577e-05, "loss": 3.4552, "step": 1735168 }, { "epoch": 1.02, "learning_rate": 2.1584495300266057e-05, "loss": 3.4403, "step": 1735680 }, { "epoch": 1.02, "learning_rate": 2.157612573155927e-05, "loss": 3.4508, "step": 1736192 }, { "epoch": 1.02, "learning_rate": 2.156773978404875e-05, "loss": 3.4492, "step": 1736704 }, { "epoch": 1.02, "learning_rate": 2.155935383653823e-05, "loss": 3.44, "step": 1737216 }, { "epoch": 1.02, "learning_rate": 2.155096788902771e-05, "loss": 3.4505, "step": 1737728 }, { "epoch": 1.02, "learning_rate": 2.154259832032092e-05, "loss": 3.4608, "step": 1738240 }, { "epoch": 1.02, "learning_rate": 2.15342123728104e-05, "loss": 3.4484, "step": 1738752 }, { "epoch": 1.02, "learning_rate": 2.152582642529988e-05, "loss": 3.4439, "step": 1739264 }, { "epoch": 1.02, "learning_rate": 2.1517440477789362e-05, "loss": 3.4392, "step": 1739776 }, { "epoch": 1.02, "learning_rate": 2.150907090908257e-05, "loss": 3.4511, "step": 1740288 }, { "epoch": 1.02, "learning_rate": 2.150068496157205e-05, "loss": 3.4452, "step": 1740800 }, { "epoch": 1.02, "learning_rate": 2.149229901406153e-05, "loss": 3.4443, "step": 1741312 }, { "epoch": 1.02, "learning_rate": 2.148392944535474e-05, "loss": 3.4373, "step": 1741824 }, { "epoch": 1.02, "learning_rate": 2.1475543497844224e-05, "loss": 3.4452, "step": 1742336 }, { "epoch": 1.02, "learning_rate": 2.1467157550333703e-05, "loss": 3.4487, "step": 1742848 }, { "epoch": 1.02, "learning_rate": 2.1458771602823183e-05, "loss": 3.4509, "step": 1743360 }, { "epoch": 1.02, "learning_rate": 2.1450402034116393e-05, "loss": 3.4329, "step": 1743872 }, { "epoch": 1.02, "learning_rate": 2.1442016086605872e-05, "loss": 3.4491, "step": 1744384 }, { "epoch": 1.02, "learning_rate": 2.1433630139095352e-05, "loss": 3.4395, "step": 1744896 }, { "epoch": 1.02, "learning_rate": 2.1425244191584832e-05, "loss": 3.4581, "step": 1745408 }, { "epoch": 1.02, "learning_rate": 2.1416874622878045e-05, "loss": 3.4452, "step": 1745920 }, { "epoch": 1.02, "learning_rate": 2.1408488675367525e-05, "loss": 3.4568, "step": 1746432 }, { "epoch": 1.02, "learning_rate": 2.1400102727857005e-05, "loss": 3.4335, "step": 1746944 }, { "epoch": 1.02, "learning_rate": 2.1391716780346485e-05, "loss": 3.4553, "step": 1747456 }, { "epoch": 1.02, "learning_rate": 2.1383347211639694e-05, "loss": 3.4494, "step": 1747968 }, { "epoch": 1.02, "learning_rate": 2.1374961264129177e-05, "loss": 3.4539, "step": 1748480 }, { "epoch": 1.02, "learning_rate": 2.1366575316618657e-05, "loss": 3.4363, "step": 1748992 }, { "epoch": 1.02, "learning_rate": 2.1358189369108137e-05, "loss": 3.4492, "step": 1749504 }, { "epoch": 1.02, "learning_rate": 2.1349819800401346e-05, "loss": 3.4535, "step": 1750016 }, { "epoch": 1.02, "learning_rate": 2.1341433852890826e-05, "loss": 3.4652, "step": 1750528 }, { "epoch": 1.02, "learning_rate": 2.1333047905380306e-05, "loss": 3.4408, "step": 1751040 }, { "epoch": 1.02, "learning_rate": 2.1324661957869786e-05, "loss": 3.4508, "step": 1751552 }, { "epoch": 1.02, "learning_rate": 2.1316292389163e-05, "loss": 3.4504, "step": 1752064 }, { "epoch": 1.02, "learning_rate": 2.130790644165248e-05, "loss": 3.444, "step": 1752576 }, { "epoch": 1.02, "learning_rate": 2.129952049414196e-05, "loss": 3.4498, "step": 1753088 }, { "epoch": 1.02, "learning_rate": 2.129113454663144e-05, "loss": 3.4524, "step": 1753600 }, { "epoch": 1.02, "learning_rate": 2.1282764977924648e-05, "loss": 3.4541, "step": 1754112 }, { "epoch": 1.02, "learning_rate": 2.127437903041413e-05, "loss": 3.4409, "step": 1754624 }, { "epoch": 1.02, "learning_rate": 2.126599308290361e-05, "loss": 3.4478, "step": 1755136 }, { "epoch": 1.03, "eval_loss": 3.853626251220703, "eval_runtime": 607.4692, "eval_samples_per_second": 628.165, "eval_steps_per_second": 19.631, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.125760713539309e-05, "loss": 3.4406, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.1249221187882567e-05, "loss": 3.4325, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.1240835240372047e-05, "loss": 3.4466, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.1232449292861527e-05, "loss": 3.4515, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.122407972415474e-05, "loss": 3.4517, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.121569377664422e-05, "loss": 3.4493, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.12073078291337e-05, "loss": 3.4406, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.119892188162318e-05, "loss": 3.4368, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1190552312916392e-05, "loss": 3.4464, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.118216636540587e-05, "loss": 3.4411, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.117378041789535e-05, "loss": 3.4491, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.1165394470384832e-05, "loss": 3.4517, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.1157041280481774e-05, "loss": 3.4457, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.1148655332971254e-05, "loss": 3.4381, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.1140269385460733e-05, "loss": 3.4399, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1131883437950213e-05, "loss": 3.4252, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1123497490439693e-05, "loss": 3.4397, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1115111542929173e-05, "loss": 3.4366, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1106725595418653e-05, "loss": 3.4398, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.1098339647908133e-05, "loss": 3.4503, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.1089970079201342e-05, "loss": 3.4524, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.1081584131690822e-05, "loss": 3.444, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1073198184180302e-05, "loss": 3.4483, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1064812236669786e-05, "loss": 3.4492, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1056442667962995e-05, "loss": 3.437, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.1048056720452475e-05, "loss": 3.448, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.1039670772941955e-05, "loss": 3.4461, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1031284825431435e-05, "loss": 3.4405, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.1022915256724647e-05, "loss": 3.4352, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.1014529309214127e-05, "loss": 3.4345, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.1006143361703607e-05, "loss": 3.4447, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.0997757414193087e-05, "loss": 3.4492, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.0989387845486296e-05, "loss": 3.4449, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.0981001897975776e-05, "loss": 3.4486, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.0972615950465256e-05, "loss": 3.4347, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.096423000295474e-05, "loss": 3.4446, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.095586043424795e-05, "loss": 3.4485, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.094747448673743e-05, "loss": 3.4342, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0939088539226908e-05, "loss": 3.4329, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0930702591716388e-05, "loss": 3.4347, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.09223330230096e-05, "loss": 3.4371, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.091394707549908e-05, "loss": 3.4515, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.090556112798856e-05, "loss": 3.4419, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.089717518047804e-05, "loss": 3.4364, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.088880561177125e-05, "loss": 3.453, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.088041966426073e-05, "loss": 3.4409, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.087203371675021e-05, "loss": 3.4514, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.0863647769239693e-05, "loss": 3.4324, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.0855278200532902e-05, "loss": 3.4238, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.0846892253022382e-05, "loss": 3.452, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.0838506305511862e-05, "loss": 3.4431, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.0830120358001342e-05, "loss": 3.4384, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0821750789294554e-05, "loss": 3.4369, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0813364841784034e-05, "loss": 3.4318, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0804978894273514e-05, "loss": 3.4274, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.0796592946762994e-05, "loss": 3.4392, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.0788223378056203e-05, "loss": 3.4359, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0779837430545683e-05, "loss": 3.437, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0771451483035163e-05, "loss": 3.444, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0763065535524643e-05, "loss": 3.4372, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.0754695966817856e-05, "loss": 3.427, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.0746310019307336e-05, "loss": 3.4429, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.0737924071796816e-05, "loss": 3.4253, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.0729554503090025e-05, "loss": 3.4355, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0721168555579508e-05, "loss": 3.4401, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0712782608068988e-05, "loss": 3.4351, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0704396660558468e-05, "loss": 3.4272, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.0696027091851677e-05, "loss": 3.4303, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.0687641144341157e-05, "loss": 3.4237, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.0679255196830637e-05, "loss": 3.4367, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.0670869249320117e-05, "loss": 3.4438, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.066249968061333e-05, "loss": 3.442, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.065411373310281e-05, "loss": 3.4445, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.064572778559229e-05, "loss": 3.4413, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.0637341838081766e-05, "loss": 3.4526, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.062897226937498e-05, "loss": 3.425, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.0620586321864462e-05, "loss": 3.4432, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.0612200374353938e-05, "loss": 3.4418, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0603814426843418e-05, "loss": 3.4201, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.059544485813663e-05, "loss": 3.4468, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.058705891062611e-05, "loss": 3.4372, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.0578672963115587e-05, "loss": 3.4461, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.057028701560507e-05, "loss": 3.4411, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.0561917446898283e-05, "loss": 3.4227, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.0553531499387763e-05, "loss": 3.4284, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.054514555187724e-05, "loss": 3.4388, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.053675960436672e-05, "loss": 3.4394, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0528390035659932e-05, "loss": 3.4389, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0520004088149412e-05, "loss": 3.4402, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.0511618140638892e-05, "loss": 3.4373, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0503232193128372e-05, "loss": 3.4333, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0494862624421584e-05, "loss": 3.4322, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.048647667691106e-05, "loss": 3.4305, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.047809072940054e-05, "loss": 3.4451, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.0469704781890024e-05, "loss": 3.4434, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.0461335213183237e-05, "loss": 3.4489, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.0452949265672713e-05, "loss": 3.4231, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.0444563318162193e-05, "loss": 3.4401, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.0436177370651673e-05, "loss": 3.4438, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.0427807801944886e-05, "loss": 3.4421, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0419421854434366e-05, "loss": 3.4339, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0411035906923846e-05, "loss": 3.4346, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0402649959413326e-05, "loss": 3.4349, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0394280390706535e-05, "loss": 3.44, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.0385894443196015e-05, "loss": 3.4238, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.0377508495685495e-05, "loss": 3.4375, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.0369122548174978e-05, "loss": 3.4251, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.0360752979468187e-05, "loss": 3.4429, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.0352367031957667e-05, "loss": 3.4268, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.0343981084447147e-05, "loss": 3.4381, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.0335595136936627e-05, "loss": 3.4334, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.032722556822984e-05, "loss": 3.4449, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.031883962071932e-05, "loss": 3.4365, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.03104536732088e-05, "loss": 3.4254, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.030206772569828e-05, "loss": 3.4399, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.029369815699149e-05, "loss": 3.4493, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.0285312209480968e-05, "loss": 3.4376, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0276926261970448e-05, "loss": 3.4362, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.026854031445993e-05, "loss": 3.4286, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.026017074575314e-05, "loss": 3.4386, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.025178479824262e-05, "loss": 3.4395, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.02433988507321e-05, "loss": 3.4301, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.023502928202531e-05, "loss": 3.4313, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0226643334514793e-05, "loss": 3.4343, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0218257387004273e-05, "loss": 3.4376, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0209871439493753e-05, "loss": 3.4403, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.0201501870786962e-05, "loss": 3.4231, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0193115923276442e-05, "loss": 3.4374, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0184729975765922e-05, "loss": 3.4265, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0176344028255402e-05, "loss": 3.4424, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0167974459548614e-05, "loss": 3.4397, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.0159588512038094e-05, "loss": 3.4466, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.0151202564527574e-05, "loss": 3.4212, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.0142816617017054e-05, "loss": 3.4475, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.0134447048310263e-05, "loss": 3.4368, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0126061100799747e-05, "loss": 3.442, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0117675153289227e-05, "loss": 3.4296, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0109289205778707e-05, "loss": 3.435, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0100919637071916e-05, "loss": 3.44, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.0092533689561396e-05, "loss": 3.46, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.0084147742050876e-05, "loss": 3.4312, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.0075761794540356e-05, "loss": 3.4381, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.0067392225833568e-05, "loss": 3.4455, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0059006278323048e-05, "loss": 3.4334, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.0050620330812528e-05, "loss": 3.433, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.0042234383302008e-05, "loss": 3.4409, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.0033864814595217e-05, "loss": 3.4438, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.00254788670847e-05, "loss": 3.4314, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.001709291957418e-05, "loss": 3.4399, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.853830099105835, "eval_runtime": 302.6608, "eval_samples_per_second": 1260.787, "eval_steps_per_second": 39.401, "step": 1831680 }, { "epoch": 1.0, "learning_rate": 2.000870697206366e-05, "loss": 3.4284, "step": 1831936 }, { "epoch": 1.0, "learning_rate": 2.000033740335687e-05, "loss": 3.4246, "step": 1832448 }, { "epoch": 1.0, "learning_rate": 1.999195145584635e-05, "loss": 3.4359, "step": 1832960 }, { "epoch": 1.0, "learning_rate": 1.998356550833583e-05, "loss": 3.4382, "step": 1833472 }, { "epoch": 1.0, "learning_rate": 1.997517956082531e-05, "loss": 3.4459, "step": 1833984 }, { "epoch": 1.0, "learning_rate": 1.9966809992118522e-05, "loss": 3.4325, "step": 1834496 }, { "epoch": 1.0, "learning_rate": 1.9958424044608002e-05, "loss": 3.4334, "step": 1835008 }, { "epoch": 1.0, "learning_rate": 1.995003809709748e-05, "loss": 3.4297, "step": 1835520 }, { "epoch": 1.0, "learning_rate": 1.9941652149586958e-05, "loss": 3.4309, "step": 1836032 }, { "epoch": 1.0, "learning_rate": 1.993328258088017e-05, "loss": 3.4316, "step": 1836544 }, { "epoch": 1.0, "learning_rate": 1.9924896633369654e-05, "loss": 3.4386, "step": 1837056 }, { "epoch": 1.0, "learning_rate": 1.9916510685859134e-05, "loss": 3.4391, "step": 1837568 }, { "epoch": 1.0, "learning_rate": 1.9908141117152343e-05, "loss": 3.4339, "step": 1838080 }, { "epoch": 1.0, "learning_rate": 1.9899755169641823e-05, "loss": 3.4292, "step": 1838592 }, { "epoch": 1.0, "learning_rate": 1.9891369222131303e-05, "loss": 3.4312, "step": 1839104 }, { "epoch": 1.0, "learning_rate": 1.988298327462078e-05, "loss": 3.4149, "step": 1839616 }, { "epoch": 1.0, "learning_rate": 1.9874597327110263e-05, "loss": 3.4285, "step": 1840128 }, { "epoch": 1.0, "learning_rate": 1.9866211379599743e-05, "loss": 3.426, "step": 1840640 }, { "epoch": 1.0, "learning_rate": 1.9857825432089223e-05, "loss": 3.4296, "step": 1841152 }, { "epoch": 1.0, "learning_rate": 1.9849439484578703e-05, "loss": 3.436, "step": 1841664 }, { "epoch": 1.0, "learning_rate": 1.9841069915871912e-05, "loss": 3.4429, "step": 1842176 }, { "epoch": 1.0, "learning_rate": 1.9832683968361392e-05, "loss": 3.4338, "step": 1842688 }, { "epoch": 1.0, "learning_rate": 1.9824298020850872e-05, "loss": 3.4364, "step": 1843200 }, { "epoch": 1.0, "learning_rate": 1.9815912073340355e-05, "loss": 3.4383, "step": 1843712 }, { "epoch": 1.0, "learning_rate": 1.9807542504633564e-05, "loss": 3.4284, "step": 1844224 }, { "epoch": 1.0, "learning_rate": 1.9799156557123044e-05, "loss": 3.4375, "step": 1844736 }, { "epoch": 1.0, "learning_rate": 1.9790770609612524e-05, "loss": 3.4359, "step": 1845248 }, { "epoch": 1.0, "learning_rate": 1.9782384662102004e-05, "loss": 3.4308, "step": 1845760 }, { "epoch": 1.0, "learning_rate": 1.9774015093395217e-05, "loss": 3.4281, "step": 1846272 }, { "epoch": 1.0, "learning_rate": 1.9765629145884697e-05, "loss": 3.4213, "step": 1846784 }, { "epoch": 1.01, "learning_rate": 1.9757243198374177e-05, "loss": 3.4312, "step": 1847296 }, { "epoch": 1.01, "learning_rate": 1.9748857250863656e-05, "loss": 3.4408, "step": 1847808 }, { "epoch": 1.01, "learning_rate": 1.9740487682156866e-05, "loss": 3.4345, "step": 1848320 }, { "epoch": 1.01, "learning_rate": 1.9732101734646346e-05, "loss": 3.4329, "step": 1848832 }, { "epoch": 1.01, "learning_rate": 1.9723715787135825e-05, "loss": 3.4242, "step": 1849344 }, { "epoch": 1.01, "learning_rate": 1.971532983962531e-05, "loss": 3.4373, "step": 1849856 }, { "epoch": 1.01, "learning_rate": 1.9706960270918518e-05, "loss": 3.4371, "step": 1850368 }, { "epoch": 1.01, "learning_rate": 1.9698574323407998e-05, "loss": 3.4267, "step": 1850880 }, { "epoch": 1.01, "learning_rate": 1.9690188375897478e-05, "loss": 3.4239, "step": 1851392 }, { "epoch": 1.01, "learning_rate": 1.9681818807190687e-05, "loss": 3.4212, "step": 1851904 }, { "epoch": 1.01, "learning_rate": 1.967343285968017e-05, "loss": 3.424, "step": 1852416 }, { "epoch": 1.01, "learning_rate": 1.966504691216965e-05, "loss": 3.4415, "step": 1852928 }, { "epoch": 1.01, "learning_rate": 1.965666096465913e-05, "loss": 3.4324, "step": 1853440 }, { "epoch": 1.01, "learning_rate": 1.964829139595234e-05, "loss": 3.4259, "step": 1853952 }, { "epoch": 1.01, "learning_rate": 1.963990544844182e-05, "loss": 3.4385, "step": 1854464 }, { "epoch": 1.01, "learning_rate": 1.96315195009313e-05, "loss": 3.4282, "step": 1854976 }, { "epoch": 1.01, "learning_rate": 1.962313355342078e-05, "loss": 3.4418, "step": 1855488 }, { "epoch": 1.01, "learning_rate": 1.961476398471399e-05, "loss": 3.4248, "step": 1856000 }, { "epoch": 1.01, "learning_rate": 1.960637803720347e-05, "loss": 3.4057, "step": 1856512 }, { "epoch": 1.01, "learning_rate": 1.959799208969295e-05, "loss": 3.4453, "step": 1857024 }, { "epoch": 1.01, "learning_rate": 1.958960614218243e-05, "loss": 3.431, "step": 1857536 }, { "epoch": 1.01, "learning_rate": 1.958123657347564e-05, "loss": 3.4291, "step": 1858048 }, { "epoch": 1.01, "learning_rate": 1.9572850625965124e-05, "loss": 3.4273, "step": 1858560 }, { "epoch": 1.01, "learning_rate": 1.9564464678454604e-05, "loss": 3.4191, "step": 1859072 }, { "epoch": 1.01, "learning_rate": 1.9556078730944084e-05, "loss": 3.4203, "step": 1859584 }, { "epoch": 1.01, "learning_rate": 1.9547709162237293e-05, "loss": 3.4262, "step": 1860096 }, { "epoch": 1.01, "learning_rate": 1.9539323214726773e-05, "loss": 3.4272, "step": 1860608 }, { "epoch": 1.01, "learning_rate": 1.9530937267216253e-05, "loss": 3.4242, "step": 1861120 }, { "epoch": 1.01, "learning_rate": 1.9522551319705733e-05, "loss": 3.4371, "step": 1861632 }, { "epoch": 1.01, "learning_rate": 1.9514181750998945e-05, "loss": 3.4265, "step": 1862144 }, { "epoch": 1.01, "learning_rate": 1.9505795803488425e-05, "loss": 3.4186, "step": 1862656 }, { "epoch": 1.01, "learning_rate": 1.9497409855977905e-05, "loss": 3.4348, "step": 1863168 }, { "epoch": 1.01, "learning_rate": 1.9489023908467382e-05, "loss": 3.4111, "step": 1863680 }, { "epoch": 1.01, "learning_rate": 1.9480654339760594e-05, "loss": 3.4185, "step": 1864192 }, { "epoch": 1.01, "learning_rate": 1.9472268392250078e-05, "loss": 3.4351, "step": 1864704 }, { "epoch": 1.01, "learning_rate": 1.9463882444739558e-05, "loss": 3.4252, "step": 1865216 }, { "epoch": 1.01, "learning_rate": 1.9455496497229034e-05, "loss": 3.4161, "step": 1865728 }, { "epoch": 1.01, "learning_rate": 1.9447126928522247e-05, "loss": 3.4225, "step": 1866240 }, { "epoch": 1.01, "learning_rate": 1.9438740981011727e-05, "loss": 3.4149, "step": 1866752 }, { "epoch": 1.01, "learning_rate": 1.9430355033501207e-05, "loss": 3.4242, "step": 1867264 }, { "epoch": 1.01, "learning_rate": 1.9421969085990686e-05, "loss": 3.434, "step": 1867776 }, { "epoch": 1.01, "learning_rate": 1.94135995172839e-05, "loss": 3.4285, "step": 1868288 }, { "epoch": 1.01, "learning_rate": 1.940521356977338e-05, "loss": 3.4324, "step": 1868800 }, { "epoch": 1.01, "learning_rate": 1.9396827622262855e-05, "loss": 3.434, "step": 1869312 }, { "epoch": 1.01, "learning_rate": 1.9388441674752335e-05, "loss": 3.4424, "step": 1869824 }, { "epoch": 1.01, "learning_rate": 1.9380072106045548e-05, "loss": 3.4161, "step": 1870336 }, { "epoch": 1.01, "learning_rate": 1.9371686158535028e-05, "loss": 3.4347, "step": 1870848 }, { "epoch": 1.01, "learning_rate": 1.9363300211024508e-05, "loss": 3.428, "step": 1871360 }, { "epoch": 1.01, "learning_rate": 1.9354914263513988e-05, "loss": 3.4108, "step": 1871872 }, { "epoch": 1.01, "learning_rate": 1.93465446948072e-05, "loss": 3.4355, "step": 1872384 }, { "epoch": 1.01, "learning_rate": 1.933815874729668e-05, "loss": 3.4284, "step": 1872896 }, { "epoch": 1.01, "learning_rate": 1.9329772799786157e-05, "loss": 3.4374, "step": 1873408 }, { "epoch": 1.01, "learning_rate": 1.932138685227564e-05, "loss": 3.4297, "step": 1873920 }, { "epoch": 1.01, "learning_rate": 1.9313017283568853e-05, "loss": 3.4121, "step": 1874432 }, { "epoch": 1.01, "learning_rate": 1.930463133605833e-05, "loss": 3.4171, "step": 1874944 }, { "epoch": 1.01, "learning_rate": 1.929624538854781e-05, "loss": 3.4302, "step": 1875456 }, { "epoch": 1.01, "learning_rate": 1.928785944103729e-05, "loss": 3.4281, "step": 1875968 }, { "epoch": 1.01, "learning_rate": 1.92794898723305e-05, "loss": 3.4327, "step": 1876480 }, { "epoch": 1.01, "learning_rate": 1.927110392481998e-05, "loss": 3.4285, "step": 1876992 }, { "epoch": 1.02, "learning_rate": 1.926271797730946e-05, "loss": 3.4256, "step": 1877504 }, { "epoch": 1.02, "learning_rate": 1.9254348408602674e-05, "loss": 3.4257, "step": 1878016 }, { "epoch": 1.02, "learning_rate": 1.924596246109215e-05, "loss": 3.42, "step": 1878528 }, { "epoch": 1.02, "learning_rate": 1.923757651358163e-05, "loss": 3.4218, "step": 1879040 }, { "epoch": 1.02, "learning_rate": 1.922919056607111e-05, "loss": 3.4343, "step": 1879552 }, { "epoch": 1.02, "learning_rate": 1.9220820997364326e-05, "loss": 3.4303, "step": 1880064 }, { "epoch": 1.02, "learning_rate": 1.9212435049853803e-05, "loss": 3.4378, "step": 1880576 }, { "epoch": 1.02, "learning_rate": 1.9204049102343283e-05, "loss": 3.4134, "step": 1881088 }, { "epoch": 1.02, "learning_rate": 1.9195663154832763e-05, "loss": 3.4292, "step": 1881600 }, { "epoch": 1.02, "learning_rate": 1.9187293586125975e-05, "loss": 3.4321, "step": 1882112 }, { "epoch": 1.02, "learning_rate": 1.9178907638615455e-05, "loss": 3.4295, "step": 1882624 }, { "epoch": 1.02, "learning_rate": 1.9170521691104935e-05, "loss": 3.4245, "step": 1883136 }, { "epoch": 1.02, "learning_rate": 1.9162135743594415e-05, "loss": 3.4263, "step": 1883648 }, { "epoch": 1.02, "learning_rate": 1.9153766174887624e-05, "loss": 3.4261, "step": 1884160 }, { "epoch": 1.02, "learning_rate": 1.9145380227377104e-05, "loss": 3.4285, "step": 1884672 }, { "epoch": 1.02, "learning_rate": 1.9136994279866584e-05, "loss": 3.4171, "step": 1885184 }, { "epoch": 1.02, "learning_rate": 1.9128608332356064e-05, "loss": 3.4241, "step": 1885696 }, { "epoch": 1.02, "learning_rate": 1.9120238763649277e-05, "loss": 3.4175, "step": 1886208 }, { "epoch": 1.02, "learning_rate": 1.9111852816138757e-05, "loss": 3.4352, "step": 1886720 }, { "epoch": 1.02, "learning_rate": 1.9103466868628237e-05, "loss": 3.4158, "step": 1887232 }, { "epoch": 1.02, "learning_rate": 1.9095080921117716e-05, "loss": 3.4264, "step": 1887744 }, { "epoch": 1.02, "learning_rate": 1.9086711352410926e-05, "loss": 3.4169, "step": 1888256 }, { "epoch": 1.02, "learning_rate": 1.907832540490041e-05, "loss": 3.4373, "step": 1888768 }, { "epoch": 1.02, "learning_rate": 1.906993945738989e-05, "loss": 3.425, "step": 1889280 }, { "epoch": 1.02, "learning_rate": 1.906155350987937e-05, "loss": 3.4178, "step": 1889792 }, { "epoch": 1.02, "learning_rate": 1.9053183941172578e-05, "loss": 3.4313, "step": 1890304 }, { "epoch": 1.02, "learning_rate": 1.9044797993662058e-05, "loss": 3.4373, "step": 1890816 }, { "epoch": 1.02, "learning_rate": 1.9036412046151538e-05, "loss": 3.429, "step": 1891328 }, { "epoch": 1.02, "learning_rate": 1.9028026098641018e-05, "loss": 3.4244, "step": 1891840 }, { "epoch": 1.02, "learning_rate": 1.901965652993423e-05, "loss": 3.4179, "step": 1892352 }, { "epoch": 1.02, "learning_rate": 1.901127058242371e-05, "loss": 3.4253, "step": 1892864 }, { "epoch": 1.02, "learning_rate": 1.900288463491319e-05, "loss": 3.4269, "step": 1893376 }, { "epoch": 1.02, "learning_rate": 1.899449868740267e-05, "loss": 3.4185, "step": 1893888 }, { "epoch": 1.02, "learning_rate": 1.898612911869588e-05, "loss": 3.4197, "step": 1894400 }, { "epoch": 1.02, "learning_rate": 1.8977743171185363e-05, "loss": 3.4258, "step": 1894912 }, { "epoch": 1.02, "learning_rate": 1.8969357223674843e-05, "loss": 3.4317, "step": 1895424 }, { "epoch": 1.02, "learning_rate": 1.8960971276164322e-05, "loss": 3.4292, "step": 1895936 }, { "epoch": 1.02, "learning_rate": 1.895260170745753e-05, "loss": 3.4152, "step": 1896448 }, { "epoch": 1.02, "learning_rate": 1.894421575994701e-05, "loss": 3.4248, "step": 1896960 }, { "epoch": 1.02, "learning_rate": 1.893582981243649e-05, "loss": 3.4187, "step": 1897472 }, { "epoch": 1.02, "learning_rate": 1.892744386492597e-05, "loss": 3.4326, "step": 1897984 }, { "epoch": 1.02, "learning_rate": 1.8919074296219184e-05, "loss": 3.4298, "step": 1898496 }, { "epoch": 1.02, "learning_rate": 1.8910688348708664e-05, "loss": 3.4341, "step": 1899008 }, { "epoch": 1.02, "learning_rate": 1.8902302401198144e-05, "loss": 3.4104, "step": 1899520 }, { "epoch": 1.02, "learning_rate": 1.8893916453687624e-05, "loss": 3.4384, "step": 1900032 }, { "epoch": 1.02, "learning_rate": 1.8885546884980833e-05, "loss": 3.4245, "step": 1900544 }, { "epoch": 1.02, "learning_rate": 1.8877160937470313e-05, "loss": 3.4319, "step": 1901056 }, { "epoch": 1.02, "learning_rate": 1.8868774989959796e-05, "loss": 3.4228, "step": 1901568 }, { "epoch": 1.02, "learning_rate": 1.8860389042449276e-05, "loss": 3.4201, "step": 1902080 }, { "epoch": 1.02, "learning_rate": 1.8852019473742485e-05, "loss": 3.43, "step": 1902592 }, { "epoch": 1.02, "learning_rate": 1.8843633526231965e-05, "loss": 3.4519, "step": 1903104 }, { "epoch": 1.02, "learning_rate": 1.8835247578721445e-05, "loss": 3.419, "step": 1903616 }, { "epoch": 1.02, "learning_rate": 1.8826861631210925e-05, "loss": 3.4298, "step": 1904128 }, { "epoch": 1.02, "learning_rate": 1.8818492062504138e-05, "loss": 3.4339, "step": 1904640 }, { "epoch": 1.02, "learning_rate": 1.8810106114993618e-05, "loss": 3.4205, "step": 1905152 }, { "epoch": 1.02, "learning_rate": 1.8801720167483098e-05, "loss": 3.4249, "step": 1905664 }, { "epoch": 1.02, "learning_rate": 1.8793350598776307e-05, "loss": 3.4308, "step": 1906176 }, { "epoch": 1.02, "learning_rate": 1.8784964651265787e-05, "loss": 3.4336, "step": 1906688 }, { "epoch": 1.02, "learning_rate": 1.8776578703755267e-05, "loss": 3.4249, "step": 1907200 }, { "epoch": 1.02, "learning_rate": 1.876819275624475e-05, "loss": 3.4268, "step": 1907712 }, { "epoch": 1.03, "eval_loss": 3.8557329177856445, "eval_runtime": 302.4472, "eval_samples_per_second": 1261.678, "eval_steps_per_second": 39.428, "step": 1908000 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.3245278361090048e+18, "trial_name": null, "trial_params": null }