{ "best_metric": 3.8690640926361084, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/3/checkpoints/checkpoint-610560", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 610560, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9795, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8319, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1908, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9815, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8152, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7062, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.605, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5296, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4516, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4102, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3577, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3048, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2656, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2159, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.176, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1434, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1045, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0844, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0463, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0315, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0122, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9762, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9501, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9311, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9179, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8919, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8688, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8501, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8516, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8143, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 4.8051, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8014, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7837, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7696, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7677, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7476, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7423, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.707, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.705, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6869, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6822, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6748, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6693, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6485, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6524, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6359, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6376, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6371, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6062, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 4.5966, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.6056, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.6054, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5782, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 4.5741, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5719, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5521, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5608, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5346, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 4.5437, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5356, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5322, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5077, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.5247, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4972, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.5073, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5049, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4983, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4798, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4702, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4664, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4803, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4736, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.457, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4675, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4707, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4525, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4492, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4412, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4422, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4237, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4264, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4203, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4328, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4212, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.4003, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4074, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4023, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4077, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.4026, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3903, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.39, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3809, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3707, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3659, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3702, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3796, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.368, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3547, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3548, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3589, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3617, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3507, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3474, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3395, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3465, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.325, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3316, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3359, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3243, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3234, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3234, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3163, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3175, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3137, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.3084, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3182, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3144, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.3065, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.3112, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2986, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2994, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2898, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.2896, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.2878, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2882, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2856, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2864, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.2843, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2725, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2817, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2807, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.262, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2545, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2597, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2749, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.2774, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2596, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2585, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2656, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2646, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2552, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2491, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2504, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2458, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2423, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2523, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.236, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2462, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2427, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2274, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.212224006652832, "eval_runtime": 305.1426, "eval_samples_per_second": 1250.533, "eval_steps_per_second": 39.08, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2307, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2211, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2344, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2262, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2283, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2136, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2097, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.1969, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2268, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.2143, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2079, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.2152, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.202, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.1979, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1958, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1938, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1919, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1876, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1992, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.2042, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.1876, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1812, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.183, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.187, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.18, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1688, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1712, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.1813, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1564, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1627, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.1712, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1698, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1717, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1658, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1644, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.17, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1453, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1552, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1428, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.1468, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.149, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1519, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1481, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1407, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1426, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1461, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1487, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1333, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1265, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.1391, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323432892437775e-05, "loss": 4.1475, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.1297, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.1318, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1284, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.1193, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1272, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1149, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1274, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.127, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1209, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.105, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.1277, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.1006, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.1161, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1199, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.1167, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.1003, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.0991, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.0986, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.11, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1106, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.1049, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.1129, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1105, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.1088, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.0957, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.1053, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.1051, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0842, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.1042, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0876, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.1094, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.0977, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0752, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.0927, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0836, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0971, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0901, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800494705387906e-05, "loss": 4.0834, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996561106368535e-05, "loss": 4.0868, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988175158858015e-05, "loss": 4.0768, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0711, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0699, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0768, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.0869, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0777, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0678, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0689, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0766, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0806, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0737, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0706, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0675, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0749, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0527, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0648, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0676, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0598, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837277240079855e-05, "loss": 4.0575, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828891292569335e-05, "loss": 4.0602, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820505345058815e-05, "loss": 4.0587, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812119397548295e-05, "loss": 4.058, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803733450037775e-05, "loss": 4.0587, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0557, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786977933820464e-05, "loss": 4.0676, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778591986309944e-05, "loss": 4.0646, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0578, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0601, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0574, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0538, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773667862756108e-05, "loss": 4.0447, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0448, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.0497, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.0526, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770315121632272e-05, "loss": 4.0491, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.76947652688122e-05, "loss": 4.0503, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768637932130168e-05, "loss": 4.0476, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0464, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0451, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766123785757386e-05, "loss": 4.053, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765285191006334e-05, "loss": 4.0367, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764446596255282e-05, "loss": 4.0274, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.031, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0506, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0513, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610938551314466e-05, "loss": 4.0426, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0366, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.048, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.0449, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577411140076115e-05, "loss": 4.0415, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0348, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756065562385881e-05, "loss": 4.033, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755226967634829e-05, "loss": 4.0356, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0267, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.0442, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752712821262046e-05, "loss": 4.0255, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751874226510994e-05, "loss": 4.0371, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751035631759942e-05, "loss": 4.0344, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.75019703700889e-05, "loss": 4.0217, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.04292106628418, "eval_runtime": 305.2067, "eval_samples_per_second": 1250.271, "eval_steps_per_second": 39.072, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749358442257838e-05, "loss": 4.0254, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748519847506786e-05, "loss": 4.0203, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747681252755734e-05, "loss": 4.0294, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746842658004682e-05, "loss": 4.0261, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.74600406325363e-05, "loss": 4.0334, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745165468502578e-05, "loss": 4.0164, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744326873751526e-05, "loss": 4.0138, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743488279000474e-05, "loss": 4.0026, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742649684249422e-05, "loss": 4.0353, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.74181108949837e-05, "loss": 4.0223, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740972494747318e-05, "loss": 4.0123, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740135537876639e-05, "loss": 4.0285, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739300218886333e-05, "loss": 4.0102, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738461624135281e-05, "loss": 4.0125, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737623029384229e-05, "loss": 4.0032, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736784434633177e-05, "loss": 4.0056, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735945839882125e-05, "loss": 4.0101, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735107245131073e-05, "loss": 4.0014, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734268650380021e-05, "loss": 4.0167, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733430055628969e-05, "loss": 4.0207, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732591460877917e-05, "loss": 4.007, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731752866126865e-05, "loss": 4.0038, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730914271375813e-05, "loss": 4.0045, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730077314505134e-05, "loss": 4.0085, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729238719754082e-05, "loss": 3.9981, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.72840012500303e-05, "loss": 3.9996, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727561530251978e-05, "loss": 3.9924, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726724573381299e-05, "loss": 4.0092, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725885978630247e-05, "loss": 3.9801, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725047383879195e-05, "loss": 3.9924, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724208789128143e-05, "loss": 3.999, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233718322574647e-05, "loss": 4.0029, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225332375064127e-05, "loss": 3.9993, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216946427553606e-05, "loss": 3.999, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208560480043086e-05, "loss": 3.9943, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200190911336296e-05, "loss": 4.0039, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191804963825775e-05, "loss": 3.9838, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183419016315255e-05, "loss": 3.9894, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.9764, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166663500097945e-05, "loss": 3.985, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158277552587424e-05, "loss": 3.9816, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149891605076904e-05, "loss": 3.9938, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9866, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71331360888596e-05, "loss": 3.9823, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712475014134908e-05, "loss": 3.9861, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711636419383856e-05, "loss": 3.9875, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.9877, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709960867762125e-05, "loss": 3.9762, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709123910891446e-05, "loss": 3.969, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708285316140394e-05, "loss": 3.9881, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707446721389342e-05, "loss": 3.9886, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.978, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9775, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9718, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9685, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703253747634082e-05, "loss": 3.9785, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024167907634034e-05, "loss": 3.9651, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9767, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.9779, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6999010065102474e-05, "loss": 3.9685, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699064049639568e-05, "loss": 3.9589, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9811, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697386860137464e-05, "loss": 3.9554, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696548265386412e-05, "loss": 3.97, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695711308515733e-05, "loss": 3.9703, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9738, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694035756894003e-05, "loss": 3.9551, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693197162142951e-05, "loss": 3.9609, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692358567391899e-05, "loss": 3.9507, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691519972640847e-05, "loss": 3.9668, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690681377889795e-05, "loss": 3.9689, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689842783138743e-05, "loss": 3.9644, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689004188387691e-05, "loss": 3.97, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881672315170116e-05, "loss": 3.9699, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873286367659596e-05, "loss": 3.9743, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864900420149076e-05, "loss": 3.9541, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856514472638556e-05, "loss": 3.9666, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848128525128036e-05, "loss": 3.9689, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683974257761751e-05, "loss": 3.9477, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831356630106996e-05, "loss": 3.964, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822970682596476e-05, "loss": 3.9507, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681460111388969e-05, "loss": 3.9755, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806215166379165e-05, "loss": 3.9615, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679784559767238e-05, "loss": 3.9413, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678945965016186e-05, "loss": 3.9534, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678107370265134e-05, "loss": 3.9532, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772687755140814e-05, "loss": 3.9623, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764301807630294e-05, "loss": 3.9557, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755915860119774e-05, "loss": 3.9506, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747529912609254e-05, "loss": 3.9527, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739143965098734e-05, "loss": 3.9474, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673077439639194e-05, "loss": 3.9441, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672238844888143e-05, "loss": 3.9367, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671401888017464e-05, "loss": 3.9485, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670563293266412e-05, "loss": 3.9588, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.66972469851536e-05, "loss": 3.9513, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668886103764308e-05, "loss": 3.9387, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668047509013256e-05, "loss": 3.9413, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667208914262204e-05, "loss": 3.9458, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666370319511152e-05, "loss": 3.957, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655317247601e-05, "loss": 3.9471, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664694767889421e-05, "loss": 3.9437, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663856173138369e-05, "loss": 3.9399, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663017578387317e-05, "loss": 3.9515, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621806215166383e-05, "loss": 3.9268, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613420267655863e-05, "loss": 3.9423, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660503432014534e-05, "loss": 3.9395, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659664837263482e-05, "loss": 3.9395, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658827880392803e-05, "loss": 3.9329, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657989285641751e-05, "loss": 3.9384, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657150690890699e-05, "loss": 3.9365, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656312096139647e-05, "loss": 3.9372, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655473501388595e-05, "loss": 3.9397, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654636544517916e-05, "loss": 3.9348, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653797949766864e-05, "loss": 3.9424, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652959355015812e-05, "loss": 3.9441, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.65212076026476e-05, "loss": 3.9434, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651282165513708e-05, "loss": 3.9417, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650443570762657e-05, "loss": 3.9384, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649604976011605e-05, "loss": 3.9308, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648766381260553e-05, "loss": 3.9292, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647929424389874e-05, "loss": 3.9315, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647090829638822e-05, "loss": 3.929, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.64625223488777e-05, "loss": 3.9403, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645413640136718e-05, "loss": 3.9308, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445766832660386e-05, "loss": 3.9343, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437380885149866e-05, "loss": 3.9334, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428994937639346e-05, "loss": 3.929, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420625368932555e-05, "loss": 3.9272, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412239421422035e-05, "loss": 3.9413, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640385347391152e-05, "loss": 3.9223, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395467526401e-05, "loss": 3.9195, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387081578890475e-05, "loss": 3.9135, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378695631379955e-05, "loss": 3.9333, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637032606267317e-05, "loss": 3.9372, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636194011516265e-05, "loss": 3.934, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353554167652124e-05, "loss": 3.9233, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345168220141604e-05, "loss": 3.9385, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336782272631084e-05, "loss": 3.9281, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328396325120564e-05, "loss": 3.9326, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320010377610043e-05, "loss": 3.9247, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631164080890326e-05, "loss": 3.9265, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630325486139274e-05, "loss": 3.926, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629486891388222e-05, "loss": 3.9149, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.62864829663717e-05, "loss": 3.9343, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627811339766491e-05, "loss": 3.9233, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626972745015439e-05, "loss": 3.9237, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626134150264387e-05, "loss": 3.9257, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625295555513335e-05, "loss": 3.9138, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9681129455566406, "eval_runtime": 304.8956, "eval_samples_per_second": 1251.547, "eval_steps_per_second": 39.112, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624456960762283e-05, "loss": 3.9225, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623618366011231e-05, "loss": 3.9155, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622781409140552e-05, "loss": 3.9203, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219428143895e-05, "loss": 3.9177, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621104219638448e-05, "loss": 3.9314, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620265624887396e-05, "loss": 3.9134, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619427030136344e-05, "loss": 3.9073, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185884353852924e-05, "loss": 3.8987, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177498406342404e-05, "loss": 3.9265, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6169112458831884e-05, "loss": 3.9221, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616074289012509e-05, "loss": 3.9025, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.61523733214183e-05, "loss": 3.9251, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614400375271151e-05, "loss": 3.9092, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613561780520099e-05, "loss": 3.9109, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612723185769047e-05, "loss": 3.9055, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611884591017995e-05, "loss": 3.9038, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611045996266943e-05, "loss": 3.9056, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610207401515891e-05, "loss": 3.9008, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609368806764839e-05, "loss": 3.9153, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608530212013788e-05, "loss": 3.9193, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607691617262736e-05, "loss": 3.9116, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606853022511684e-05, "loss": 3.9045, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606014427760631e-05, "loss": 3.901, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051774708899526e-05, "loss": 3.9137, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043388761389006e-05, "loss": 3.8981, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603500281387848e-05, "loss": 3.9012, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602661686636796e-05, "loss": 3.8953, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601823091885744e-05, "loss": 3.9108, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600984497134692e-05, "loss": 3.8848, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.60014590238364e-05, "loss": 3.8936, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599307307632588e-05, "loss": 3.9052, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.5984703507619095e-05, "loss": 3.9031, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976317560108575e-05, "loss": 3.9044, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5967947991401784e-05, "loss": 3.9048, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959562043891264e-05, "loss": 3.8993, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5951176096380744e-05, "loss": 3.9077, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942790148870224e-05, "loss": 3.8922, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934404201359704e-05, "loss": 3.8871, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5926018253849184e-05, "loss": 3.8846, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917632306338664e-05, "loss": 3.8916, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909246358828144e-05, "loss": 3.8865, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590089316892508e-05, "loss": 3.9009, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589250722141457e-05, "loss": 3.8935, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588412127390405e-05, "loss": 3.8889, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587573532639353e-05, "loss": 3.8964, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586736575768674e-05, "loss": 3.8888, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585897981017622e-05, "loss": 3.8988, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.58505938626657e-05, "loss": 3.8838, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584220791515518e-05, "loss": 3.8694, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583382196764466e-05, "loss": 3.9013, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582545239893787e-05, "loss": 3.8953, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581706645142735e-05, "loss": 3.8922, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580868050391683e-05, "loss": 3.8851, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580029455640631e-05, "loss": 3.8819, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579190860889579e-05, "loss": 3.8772, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783522661385267e-05, "loss": 3.8866, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577515309267848e-05, "loss": 3.8761, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576676714516796e-05, "loss": 3.8836, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575838119765744e-05, "loss": 3.8937, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574999525014692e-05, "loss": 3.8777, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.57416093026364e-05, "loss": 3.8694, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573322335512588e-05, "loss": 3.8936, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572483740761536e-05, "loss": 3.8668, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571645146010484e-05, "loss": 3.8763, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570809827020178e-05, "loss": 3.8859, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569971232269126e-05, "loss": 3.8871, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569132637518074e-05, "loss": 3.8659, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568294042767022e-05, "loss": 3.8746, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567455448015971e-05, "loss": 3.8604, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566616853264919e-05, "loss": 3.8837, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565778258513867e-05, "loss": 3.8811, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564939663762814e-05, "loss": 3.8793, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5641027068921356e-05, "loss": 3.8815, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632641121410836e-05, "loss": 3.8844, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624255173900316e-05, "loss": 3.89, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561586922638979e-05, "loss": 3.867, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.5607499657683005e-05, "loss": 3.8807, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599113710172485e-05, "loss": 3.8842, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590727762661965e-05, "loss": 3.8623, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582341815151445e-05, "loss": 3.8805, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.5573955867640925e-05, "loss": 3.8689, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556558629893414e-05, "loss": 3.8851, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557200351423614e-05, "loss": 3.8783, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548814403913094e-05, "loss": 3.8596, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.5540428456402574e-05, "loss": 3.8712, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.5532042508892054e-05, "loss": 3.8679, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552367294018526e-05, "loss": 3.8808, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551528699267474e-05, "loss": 3.8685, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550690104516422e-05, "loss": 3.866, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.54985150976537e-05, "loss": 3.8699, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549012915014318e-05, "loss": 3.8696, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548175958143639e-05, "loss": 3.8611, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547337363392588e-05, "loss": 3.8539, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546498768641536e-05, "loss": 3.8658, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545660173890484e-05, "loss": 3.8771, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544821579139432e-05, "loss": 3.8752, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543984622268753e-05, "loss": 3.8511, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543146027517701e-05, "loss": 3.8626, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542307432766649e-05, "loss": 3.8629, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541468838015597e-05, "loss": 3.8743, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406318811449176e-05, "loss": 3.8668, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397932863938656e-05, "loss": 3.8649, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389546916428136e-05, "loss": 3.8597, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381160968917616e-05, "loss": 3.8737, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537279140021083e-05, "loss": 3.8478, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536440545270031e-05, "loss": 3.8634, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535601950518979e-05, "loss": 3.858, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534763355767927e-05, "loss": 3.8623, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533924761016875e-05, "loss": 3.8538, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533086166265823e-05, "loss": 3.8638, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532247571514771e-05, "loss": 3.8523, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531410614644092e-05, "loss": 3.8592, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.53057201989304e-05, "loss": 3.8613, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529733425141988e-05, "loss": 3.8584, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528894830390936e-05, "loss": 3.8669, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528057873520257e-05, "loss": 3.8657, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527219278769205e-05, "loss": 3.8622, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526380684018153e-05, "loss": 3.8669, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255420892671017e-05, "loss": 3.8623, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247051323964226e-05, "loss": 3.8533, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238665376453706e-05, "loss": 3.8522, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230279428943186e-05, "loss": 3.8566, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221893481432665e-05, "loss": 3.8559, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213507533922145e-05, "loss": 3.8632, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.5205137965215355e-05, "loss": 3.8549, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.5196752017704834e-05, "loss": 3.8596, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188366070194314e-05, "loss": 3.854, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.5179980122683794e-05, "loss": 3.8528, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.5171610553977003e-05, "loss": 3.8518, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.5163224606466483e-05, "loss": 3.8653, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515483865895597e-05, "loss": 3.8513, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514645271144545e-05, "loss": 3.8445, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513808314273866e-05, "loss": 3.8386, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512969719522814e-05, "loss": 3.857, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512131124771762e-05, "loss": 3.8618, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.51129253002071e-05, "loss": 3.8615, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510455573150031e-05, "loss": 3.8523, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509616978398979e-05, "loss": 3.8631, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508778383647927e-05, "loss": 3.8545, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507939788896874e-05, "loss": 3.8583, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507101194145822e-05, "loss": 3.8498, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506264237275144e-05, "loss": 3.8543, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054256425240924e-05, "loss": 3.8528, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.50458704777304e-05, "loss": 3.8401, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503748453021988e-05, "loss": 3.8611, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502911496151309e-05, "loss": 3.8542, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502072901400257e-05, "loss": 3.8486, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012343066492046e-05, "loss": 3.8497, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5003957118981526e-05, "loss": 3.847, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9266185760498047, "eval_runtime": 305.1784, "eval_samples_per_second": 1250.387, "eval_steps_per_second": 39.076, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.4995571171471006e-05, "loss": 3.8457, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4987185223960486e-05, "loss": 3.8437, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.4978799276449966e-05, "loss": 3.851, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970413328939446e-05, "loss": 3.8456, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4962027381428926e-05, "loss": 3.8599, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953641433918406e-05, "loss": 3.8448, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945255486407886e-05, "loss": 3.8328, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493686953889737e-05, "loss": 3.8331, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492849997019058e-05, "loss": 3.8524, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492011402268006e-05, "loss": 3.8509, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491172807516954e-05, "loss": 3.8361, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490334212765902e-05, "loss": 3.8522, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489498893775596e-05, "loss": 3.8412, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488660299024544e-05, "loss": 3.8428, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487821704273492e-05, "loss": 3.8325, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.48698310952244e-05, "loss": 3.8338, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486144514771388e-05, "loss": 3.8341, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485305920020336e-05, "loss": 3.8313, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484467325269284e-05, "loss": 3.8461, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836287305182326e-05, "loss": 3.8484, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827917736475535e-05, "loss": 3.8439, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.4819531788965015e-05, "loss": 3.838, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.4811145841454495e-05, "loss": 3.8335, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.4802759893943975e-05, "loss": 3.8436, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.4794390325237184e-05, "loss": 3.8309, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.4786004377726664e-05, "loss": 3.8345, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.4777618430216144e-05, "loss": 3.8269, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.4769232482705624e-05, "loss": 3.8388, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476086291399883e-05, "loss": 3.8221, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475247696648831e-05, "loss": 3.8223, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474409101897779e-05, "loss": 3.8408, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473570507146728e-05, "loss": 3.8339, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472733550276049e-05, "loss": 3.8423, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471894955524997e-05, "loss": 3.8394, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471056360773945e-05, "loss": 3.8299, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470217766022893e-05, "loss": 3.8416, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469380809152214e-05, "loss": 3.8309, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468542214401162e-05, "loss": 3.8186, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.46770361965011e-05, "loss": 3.8168, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466865024899058e-05, "loss": 3.8217, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466028068028379e-05, "loss": 3.8234, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465189473277327e-05, "loss": 3.8378, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464350878526275e-05, "loss": 3.8258, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463512283775223e-05, "loss": 3.8245, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462675326904544e-05, "loss": 3.8341, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461836732153492e-05, "loss": 3.8284, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.46099813740244e-05, "loss": 3.8314, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460159542651388e-05, "loss": 3.8169, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459322585780709e-05, "loss": 3.8028, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458483991029657e-05, "loss": 3.8368, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457645396278605e-05, "loss": 3.8345, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4568068015275525e-05, "loss": 3.8272, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455969844656874e-05, "loss": 3.8206, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455131249905822e-05, "loss": 3.8187, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.45429265515477e-05, "loss": 3.8115, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453454060403718e-05, "loss": 3.8226, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4526171035330396e-05, "loss": 3.8159, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517785087819876e-05, "loss": 3.8183, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.4509399140309356e-05, "loss": 3.8307, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450101319279883e-05, "loss": 3.8187, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.4492643624092045e-05, "loss": 3.8091, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4484257676581525e-05, "loss": 3.8321, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475871729071e-05, "loss": 3.8051, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446748578156048e-05, "loss": 3.8098, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445909983404996e-05, "loss": 3.8279, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.4450730265343174e-05, "loss": 3.8266, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.4442344317832654e-05, "loss": 3.8025, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.4433958370322134e-05, "loss": 3.8133, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.4425572422811614e-05, "loss": 3.7981, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441720285410482e-05, "loss": 3.8215, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.44088169065943e-05, "loss": 3.8236, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440043095908378e-05, "loss": 3.812, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439204501157326e-05, "loss": 3.8213, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438367544286647e-05, "loss": 3.819, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437528949535595e-05, "loss": 3.8343, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436690354784543e-05, "loss": 3.8073, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435851760033491e-05, "loss": 3.8203, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435014803162813e-05, "loss": 3.8209, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434176208411761e-05, "loss": 3.8005, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433337613660709e-05, "loss": 3.8214, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432499018909657e-05, "loss": 3.8092, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431660424158605e-05, "loss": 3.8225, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430821829407553e-05, "loss": 3.8182, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429983234656501e-05, "loss": 3.8033, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291462777858217e-05, "loss": 3.8063, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283076830347696e-05, "loss": 3.8086, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274690882837176e-05, "loss": 3.8252, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.4266304935326656e-05, "loss": 3.8097, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257935366619865e-05, "loss": 3.8051, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249549419109345e-05, "loss": 3.8082, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424116347159883e-05, "loss": 3.8129, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423277752408831e-05, "loss": 3.8041, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422440795538152e-05, "loss": 3.7932, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.4216022007871e-05, "loss": 3.8068, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420763606036048e-05, "loss": 3.8166, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419925011284996e-05, "loss": 3.816, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419088054414317e-05, "loss": 3.793, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418249459663265e-05, "loss": 3.8051, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417410864912213e-05, "loss": 3.8065, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416572270161161e-05, "loss": 3.814, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415735313290482e-05, "loss": 3.8109, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.41489671853943e-05, "loss": 3.8057, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414058123788378e-05, "loss": 3.8016, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132195290373266e-05, "loss": 3.8128, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123825721666475e-05, "loss": 3.7897, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115439774155955e-05, "loss": 3.8059, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4107053826645435e-05, "loss": 3.7979, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098667879134915e-05, "loss": 3.8087, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090281931624395e-05, "loss": 3.7911, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081912362917604e-05, "loss": 3.8079, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073526415407084e-05, "loss": 3.7972, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.4065140467896564e-05, "loss": 3.8011, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056754520386044e-05, "loss": 3.8031, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404838495167925e-05, "loss": 3.8007, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403999900416873e-05, "loss": 3.8066, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403161305665822e-05, "loss": 3.8134, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.40232271091477e-05, "loss": 3.8074, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401485754044091e-05, "loss": 3.8095, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400647159293039e-05, "loss": 3.8056, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399808564541987e-05, "loss": 3.7982, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398969969790935e-05, "loss": 3.7912, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398133012920256e-05, "loss": 3.8041, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397294418169204e-05, "loss": 3.7982, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396455823418152e-05, "loss": 3.8048, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956172286671e-05, "loss": 3.8009, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.3947802717964206e-05, "loss": 3.8034, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.3939416770453686e-05, "loss": 3.8005, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393103082294317e-05, "loss": 3.7967, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392264487543265e-05, "loss": 3.7929, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391427530672586e-05, "loss": 3.8075, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.390588935921534e-05, "loss": 3.7983, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389750341170482e-05, "loss": 3.7909, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.38891174641943e-05, "loss": 3.781, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388074789548751e-05, "loss": 3.8035, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387236194797699e-05, "loss": 3.804, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386397600046647e-05, "loss": 3.8057, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385559005295595e-05, "loss": 3.7979, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384722048424916e-05, "loss": 3.8059, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383883453673864e-05, "loss": 3.7984, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383044858922813e-05, "loss": 3.8066, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382206264171761e-05, "loss": 3.7945, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.3813693073010816e-05, "loss": 3.798, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.3805307125500296e-05, "loss": 3.7959, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.3796921177989776e-05, "loss": 3.7907, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.3788535230479256e-05, "loss": 3.8039, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3780165661772465e-05, "loss": 3.7989, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771779714261945e-05, "loss": 3.7963, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763393766751425e-05, "loss": 3.7935, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.37550078192409e-05, "loss": 3.7968, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.902155876159668, "eval_runtime": 305.2126, "eval_samples_per_second": 1250.246, "eval_steps_per_second": 39.071, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.3746638250534114e-05, "loss": 3.7915, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.3738252303023594e-05, "loss": 3.7915, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372986635551308e-05, "loss": 3.7962, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721480408002554e-05, "loss": 3.7918, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371311083929577e-05, "loss": 3.8063, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370472489178525e-05, "loss": 3.7915, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369633894427473e-05, "loss": 3.7809, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.36879529967642e-05, "loss": 3.7774, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367958342805742e-05, "loss": 3.7973, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.36711974805469e-05, "loss": 3.7972, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366281153303637e-05, "loss": 3.786, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365442558552585e-05, "loss": 3.7966, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.36460723956228e-05, "loss": 3.7913, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363768644811228e-05, "loss": 3.7892, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362930050060176e-05, "loss": 3.783, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362091455309124e-05, "loss": 3.7779, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361252860558072e-05, "loss": 3.7838, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.36041426580702e-05, "loss": 3.7785, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.3595756710559676e-05, "loss": 3.7926, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.3587370763049156e-05, "loss": 3.7975, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357900119434237e-05, "loss": 3.7948, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.3570615246831845e-05, "loss": 3.7862, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.3562229299321325e-05, "loss": 3.7836, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.3553843351810805e-05, "loss": 3.7873, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354547378310402e-05, "loss": 3.7799, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.35370878355935e-05, "loss": 3.7869, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352870188808298e-05, "loss": 3.7716, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352031594057246e-05, "loss": 3.7903, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351194637186568e-05, "loss": 3.776, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350356042435515e-05, "loss": 3.7711, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349517447684463e-05, "loss": 3.7835, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348678852933411e-05, "loss": 3.7888, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347841896062732e-05, "loss": 3.7936, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.34700330131168e-05, "loss": 3.7857, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346164706560628e-05, "loss": 3.7775, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345326111809576e-05, "loss": 3.7904, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444891549388975e-05, "loss": 3.7851, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436505601878455e-05, "loss": 3.7658, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3428119654367935e-05, "loss": 3.7704, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.341975008566115e-05, "loss": 3.7696, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411364138150624e-05, "loss": 3.7755, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402978190640104e-05, "loss": 3.7853, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394592243129584e-05, "loss": 3.7787, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338622267442279e-05, "loss": 3.7717, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337783672691227e-05, "loss": 3.7838, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336945077940175e-05, "loss": 3.7748, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336106483189123e-05, "loss": 3.7885, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335269526318445e-05, "loss": 3.7677, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334430931567393e-05, "loss": 3.7495, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333592336816341e-05, "loss": 3.7905, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332753742065289e-05, "loss": 3.7803, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.33191678519461e-05, "loss": 3.7819, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331078190443558e-05, "loss": 3.775, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330239595692506e-05, "loss": 3.7702, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329401000941454e-05, "loss": 3.7631, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.3285640440707746e-05, "loss": 3.7717, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.3277254493197226e-05, "loss": 3.7683, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.3268868545686706e-05, "loss": 3.7694, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.3260482598176186e-05, "loss": 3.7807, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.32521130294694e-05, "loss": 3.7703, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324372708195888e-05, "loss": 3.7629, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323534113444836e-05, "loss": 3.7799, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322695518693784e-05, "loss": 3.7619, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321858561823105e-05, "loss": 3.7611, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321019967072053e-05, "loss": 3.7773, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320181372321001e-05, "loss": 3.7773, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319342777569949e-05, "loss": 3.7544, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.31850582069927e-05, "loss": 3.7674, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317667225948218e-05, "loss": 3.7532, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316828631197166e-05, "loss": 3.7689, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315990036446114e-05, "loss": 3.7733, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.3151530795754356e-05, "loss": 3.77, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.3143144848243836e-05, "loss": 3.7717, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.3134758900733316e-05, "loss": 3.7731, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.3126372953222796e-05, "loss": 3.7825, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.3118003384516005e-05, "loss": 3.759, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.3109617437005485e-05, "loss": 3.7769, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.3101247868298694e-05, "loss": 3.772, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.3092861920788174e-05, "loss": 3.7519, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.3084475973277654e-05, "loss": 3.774, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3076090025767134e-05, "loss": 3.761, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067704078256614e-05, "loss": 3.7763, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3059318130746094e-05, "loss": 3.7714, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050932183235574e-05, "loss": 3.7582, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.304256261452879e-05, "loss": 3.7553, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.303417666701827e-05, "loss": 3.7622, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.302579071950775e-05, "loss": 3.779, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.301740477199723e-05, "loss": 3.7612, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300903520329044e-05, "loss": 3.7617, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300064925577992e-05, "loss": 3.7623, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.29922633082694e-05, "loss": 3.7666, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298387736075888e-05, "loss": 3.7589, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297550779205209e-05, "loss": 3.7457, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296712184454157e-05, "loss": 3.7599, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295873589703105e-05, "loss": 3.7704, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.295034994952053e-05, "loss": 3.7719, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294198038081374e-05, "loss": 3.7482, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293359443330322e-05, "loss": 3.7562, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.29252084857927e-05, "loss": 3.7607, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291682253828218e-05, "loss": 3.765, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290845296957539e-05, "loss": 3.7706, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.290006702206487e-05, "loss": 3.7546, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289168107455435e-05, "loss": 3.7604, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288329512704383e-05, "loss": 3.7654, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287492555833704e-05, "loss": 3.7455, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286653961082652e-05, "loss": 3.7599, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.2858153663316e-05, "loss": 3.7518, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284976771580548e-05, "loss": 3.7647, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.28413981470987e-05, "loss": 3.748, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283301219958818e-05, "loss": 3.7632, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282462625207766e-05, "loss": 3.752, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.281624030456714e-05, "loss": 3.7578, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807870735860346e-05, "loss": 3.7576, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2799484788349826e-05, "loss": 3.7586, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2791098840839306e-05, "loss": 3.7583, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.2782712893328786e-05, "loss": 3.7713, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.2774343324621995e-05, "loss": 3.7637, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.2765957377111475e-05, "loss": 3.765, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.2757571429600955e-05, "loss": 3.7554, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.2749185482090435e-05, "loss": 3.7589, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274081591338365e-05, "loss": 3.7481, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273242996587313e-05, "loss": 3.7542, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272404401836261e-05, "loss": 3.7572, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271565807085209e-05, "loss": 3.7596, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.27072885021453e-05, "loss": 3.7592, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.269890255463478e-05, "loss": 3.7556, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269051660712426e-05, "loss": 3.7549, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268213065961374e-05, "loss": 3.757, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267376109090695e-05, "loss": 3.7544, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266537514339643e-05, "loss": 3.7583, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265698919588591e-05, "loss": 3.755, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264860324837539e-05, "loss": 3.7495, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.2640233679668604e-05, "loss": 3.7357, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.2631847732158084e-05, "loss": 3.7622, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623461784647564e-05, "loss": 3.759, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2615075837137044e-05, "loss": 3.7626, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260670626843025e-05, "loss": 3.753, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259832032091973e-05, "loss": 3.7605, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258993437340921e-05, "loss": 3.7538, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258154842589869e-05, "loss": 3.7675, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.25731788571919e-05, "loss": 3.7502, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256479290968138e-05, "loss": 3.7543, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255640696217086e-05, "loss": 3.752, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254802101466034e-05, "loss": 3.749, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253965144595356e-05, "loss": 3.7616, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253126549844304e-05, "loss": 3.753, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252287955093252e-05, "loss": 3.7602, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2514493603422e-05, "loss": 3.7451, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250612403471521e-05, "loss": 3.7555, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.885396957397461, "eval_runtime": 306.085, "eval_samples_per_second": 1246.683, "eval_steps_per_second": 38.96, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249773808720469e-05, "loss": 3.7544, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248935213969417e-05, "loss": 3.7475, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248096619218364e-05, "loss": 3.7524, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247258024467312e-05, "loss": 3.7485, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.24641942971626e-05, "loss": 3.7644, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245580834965208e-05, "loss": 3.7501, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244742240214156e-05, "loss": 3.7437, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243903645463104e-05, "loss": 3.7347, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.2430666885924255e-05, "loss": 3.7567, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.2422280938413735e-05, "loss": 3.753, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.2413894990903215e-05, "loss": 3.7442, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.2405509043392695e-05, "loss": 3.7527, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239715585348964e-05, "loss": 3.7503, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.2388769905979114e-05, "loss": 3.7469, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2380383958468593e-05, "loss": 3.7396, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.2371998010958073e-05, "loss": 3.7372, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.2363612063447553e-05, "loss": 3.7413, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235522611593703e-05, "loss": 3.7386, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234684016842651e-05, "loss": 3.7482, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233845422091599e-05, "loss": 3.755, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.233008465220921e-05, "loss": 3.7552, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232169870469869e-05, "loss": 3.7463, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.231331275718817e-05, "loss": 3.7405, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230492680967765e-05, "loss": 3.7446, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229655724097086e-05, "loss": 3.7408, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228817129346034e-05, "loss": 3.7439, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227978534594982e-05, "loss": 3.7271, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.22713993984393e-05, "loss": 3.7511, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226302982973251e-05, "loss": 3.7372, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.225464388222199e-05, "loss": 3.7295, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.224625793471147e-05, "loss": 3.7411, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223787198720095e-05, "loss": 3.7505, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222950241849416e-05, "loss": 3.7456, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222111647098364e-05, "loss": 3.7472, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221273052347312e-05, "loss": 3.736, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.22043445759626e-05, "loss": 3.7508, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219597500725581e-05, "loss": 3.7442, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218758905974529e-05, "loss": 3.7272, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217920311223477e-05, "loss": 3.7317, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217083354352798e-05, "loss": 3.7285, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216244759601746e-05, "loss": 3.7367, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215406164850694e-05, "loss": 3.7464, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214567570099642e-05, "loss": 3.7354, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137306132289637e-05, "loss": 3.7337, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128920184779116e-05, "loss": 3.7393, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120534237268596e-05, "loss": 3.7351, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.2112148289758076e-05, "loss": 3.7486, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.2103778721051285e-05, "loss": 3.7301, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.2095392773540765e-05, "loss": 3.7075, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.2087006826030245e-05, "loss": 3.7494, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.2078620878519725e-05, "loss": 3.7438, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.2070251309812934e-05, "loss": 3.7414, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061865362302414e-05, "loss": 3.7331, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.2053479414791894e-05, "loss": 3.7301, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2045093467281374e-05, "loss": 3.7223, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203672389857459e-05, "loss": 3.7347, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202833795106407e-05, "loss": 3.7313, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201995200355355e-05, "loss": 3.7284, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.201156605604303e-05, "loss": 3.7409, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200319648733624e-05, "loss": 3.7329, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.199481053982572e-05, "loss": 3.7221, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.19864245923152e-05, "loss": 3.7406, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197803864480468e-05, "loss": 3.7223, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.196966907609789e-05, "loss": 3.7264, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.196128312858737e-05, "loss": 3.7389, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195289718107685e-05, "loss": 3.7391, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194451123356633e-05, "loss": 3.7145, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.1936141664859544e-05, "loss": 3.7266, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.1927755717349024e-05, "loss": 3.7143, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919369769838504e-05, "loss": 3.7332, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.1910983822327984e-05, "loss": 3.7343, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190261425362119e-05, "loss": 3.7328, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189422830611067e-05, "loss": 3.7315, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188584235860015e-05, "loss": 3.7343, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187745641108963e-05, "loss": 3.7449, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186908684238284e-05, "loss": 3.724, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186070089487232e-05, "loss": 3.7365, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.18523149473618e-05, "loss": 3.7318, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184392899985128e-05, "loss": 3.7168, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183554305234076e-05, "loss": 3.7326, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182715710483024e-05, "loss": 3.729, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181877115731972e-05, "loss": 3.7315, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.18103852098092e-05, "loss": 3.7358, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180201564110242e-05, "loss": 3.7196, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.17936296935919e-05, "loss": 3.7207, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178524374608137e-05, "loss": 3.7256, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177685779857085e-05, "loss": 3.7348, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1768488229864066e-05, "loss": 3.7254, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.1760102282353546e-05, "loss": 3.7226, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175171633484302e-05, "loss": 3.7265, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.1743346766136235e-05, "loss": 3.7289, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.1734960818625715e-05, "loss": 3.721, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.1726574871115195e-05, "loss": 3.7078, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171820530240841e-05, "loss": 3.7237, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170981935489789e-05, "loss": 3.7291, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170143340738737e-05, "loss": 3.7341, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1693047459876844e-05, "loss": 3.7135, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684661512366324e-05, "loss": 3.719, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.1676275564855804e-05, "loss": 3.7247, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.1667889617345284e-05, "loss": 3.7244, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659503669834764e-05, "loss": 3.7337, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165113410112797e-05, "loss": 3.7204, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.164274815361745e-05, "loss": 3.7235, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163436220610693e-05, "loss": 3.7278, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162599263740015e-05, "loss": 3.7101, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.161760668988963e-05, "loss": 3.7226, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160922074237911e-05, "loss": 3.7109, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160083479486859e-05, "loss": 3.732, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.15924652261618e-05, "loss": 3.7095, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158407927865128e-05, "loss": 3.7251, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.157569333114076e-05, "loss": 3.7181, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156730738363024e-05, "loss": 3.7195, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155893781492345e-05, "loss": 3.7214, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.155055186741293e-05, "loss": 3.7246, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154216591990241e-05, "loss": 3.7207, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153377997239189e-05, "loss": 3.7351, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.15254104036851e-05, "loss": 3.7227, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151702445617458e-05, "loss": 3.7341, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150863850866406e-05, "loss": 3.72, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150025256115354e-05, "loss": 3.7181, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149188299244675e-05, "loss": 3.7164, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148349704493623e-05, "loss": 3.7141, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147511109742571e-05, "loss": 3.7186, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146672514991519e-05, "loss": 3.7244, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.14583555812084e-05, "loss": 3.7191, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144996963369788e-05, "loss": 3.7228, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144158368618736e-05, "loss": 3.7194, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143319773867684e-05, "loss": 3.7202, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424828169970056e-05, "loss": 3.72, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1416442222459536e-05, "loss": 3.7167, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.1408056274949016e-05, "loss": 3.7191, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.1399670327438496e-05, "loss": 3.7154, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.1391300758731705e-05, "loss": 3.7009, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.1382914811221185e-05, "loss": 3.7236, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.1374528863710665e-05, "loss": 3.7234, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.1366142916200145e-05, "loss": 3.7282, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357773347493354e-05, "loss": 3.7153, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1349387399982834e-05, "loss": 3.7266, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1341001452472314e-05, "loss": 3.7205, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.1332615504961794e-05, "loss": 3.7307, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132424593625501e-05, "loss": 3.7133, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131585998874449e-05, "loss": 3.7143, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.130747404123397e-05, "loss": 3.718, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.129908809372345e-05, "loss": 3.7171, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.129071852501666e-05, "loss": 3.7218, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128233257750614e-05, "loss": 3.7195, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.127394662999562e-05, "loss": 3.7229, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.12655606824851e-05, "loss": 3.7105, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125719111377831e-05, "loss": 3.7231, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.8755502700805664, "eval_runtime": 307.7129, "eval_samples_per_second": 1240.088, "eval_steps_per_second": 38.754, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.124880516626779e-05, "loss": 3.7127, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.124041921875727e-05, "loss": 3.7173, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.123203327124675e-05, "loss": 3.7112, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.1223663702539964e-05, "loss": 3.7139, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.1215277755029444e-05, "loss": 3.7273, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.1206891807518923e-05, "loss": 3.7168, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.1198505860008403e-05, "loss": 3.7089, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119013629130161e-05, "loss": 3.7055, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118175034379109e-05, "loss": 3.7141, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117336439628057e-05, "loss": 3.7237, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116499482757378e-05, "loss": 3.7084, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115660888006326e-05, "loss": 3.7172, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114823931135647e-05, "loss": 3.7193, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.113985336384595e-05, "loss": 3.7088, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113146741633544e-05, "loss": 3.7082, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112308146882492e-05, "loss": 3.7029, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.11146955213144e-05, "loss": 3.7062, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110630957380388e-05, "loss": 3.7035, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109792362629336e-05, "loss": 3.7092, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108953767878284e-05, "loss": 3.725, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.1081168110076046e-05, "loss": 3.7205, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.1072782162565526e-05, "loss": 3.7112, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.1064396215055006e-05, "loss": 3.707, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.1056010267544486e-05, "loss": 3.709, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.1047640698837695e-05, "loss": 3.7074, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.1039254751327175e-05, "loss": 3.7092, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.1030868803816655e-05, "loss": 3.6957, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.1022482856306135e-05, "loss": 3.7164, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101411328759935e-05, "loss": 3.7049, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.100572734008883e-05, "loss": 3.6962, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.099734139257831e-05, "loss": 3.7, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.098895544506779e-05, "loss": 3.7209, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0980585876361e-05, "loss": 3.7156, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.097219992885048e-05, "loss": 3.7119, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.096381398133996e-05, "loss": 3.7016, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.095542803382944e-05, "loss": 3.7128, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.094705846512265e-05, "loss": 3.7138, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.093867251761213e-05, "loss": 3.6938, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.093028657010161e-05, "loss": 3.6969, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.092190062259109e-05, "loss": 3.6931, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913531053884305e-05, "loss": 3.704, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0905145106373784e-05, "loss": 3.7078, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.0896759158863264e-05, "loss": 3.7075, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.0888389590156474e-05, "loss": 3.6994, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.0880003642645953e-05, "loss": 3.7051, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.0871617695135433e-05, "loss": 3.7038, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.0863231747624913e-05, "loss": 3.712, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085486217891812e-05, "loss": 3.7013, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.08464762314076e-05, "loss": 3.6739, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083809028389708e-05, "loss": 3.713, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082970433638656e-05, "loss": 3.7089, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082133476767978e-05, "loss": 3.7122, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081294882016926e-05, "loss": 3.6977, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080456287265874e-05, "loss": 3.6961, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079617692514822e-05, "loss": 3.6927, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078780735644143e-05, "loss": 3.7007, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077942140893091e-05, "loss": 3.7012, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077103546142039e-05, "loss": 3.6909, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076264951390987e-05, "loss": 3.7086, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.0754279945203076e-05, "loss": 3.7016, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.0745893997692556e-05, "loss": 3.6855, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0737508050182036e-05, "loss": 3.7072, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0729122102671516e-05, "loss": 3.6914, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.072075253396473e-05, "loss": 3.6899, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071236658645421e-05, "loss": 3.7048, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070398063894369e-05, "loss": 3.7063, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.0695594691433165e-05, "loss": 3.6841, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068722512272638e-05, "loss": 3.6945, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067883917521586e-05, "loss": 3.6805, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.067045322770534e-05, "loss": 3.6995, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.0662067280194814e-05, "loss": 3.7016, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065369771148803e-05, "loss": 3.701, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064531176397751e-05, "loss": 3.6981, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063692581646699e-05, "loss": 3.7004, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062853986895647e-05, "loss": 3.7155, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.0620170300249686e-05, "loss": 3.6874, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.0611784352739166e-05, "loss": 3.7057, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0603414784032375e-05, "loss": 3.7007, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.0595028836521855e-05, "loss": 3.6848, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586642889011335e-05, "loss": 3.7027, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0578256941500814e-05, "loss": 3.695, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.056987099399029e-05, "loss": 3.6974, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056148504647977e-05, "loss": 3.7068, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.055309909896925e-05, "loss": 3.683, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.054472953026246e-05, "loss": 3.6882, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053634358275194e-05, "loss": 3.6926, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052795763524142e-05, "loss": 3.7041, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.05195716877309e-05, "loss": 3.6916, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051120211902411e-05, "loss": 3.6951, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050281617151359e-05, "loss": 3.6966, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049443022400307e-05, "loss": 3.6901, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048604427649255e-05, "loss": 3.6923, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047767470778576e-05, "loss": 3.6769, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046930513907898e-05, "loss": 3.6907, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.046091919156846e-05, "loss": 3.6966, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045253324405793e-05, "loss": 3.7047, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044414729654741e-05, "loss": 3.6819, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043576134903689e-05, "loss": 3.6845, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042737540152638e-05, "loss": 3.6939, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041898945401586e-05, "loss": 3.6937, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041060350650534e-05, "loss": 3.6978, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.0402233937798546e-05, "loss": 3.6917, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.0393847990288026e-05, "loss": 3.6925, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.0385462042777506e-05, "loss": 3.6917, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.0377076095266986e-05, "loss": 3.6829, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.0368706526560195e-05, "loss": 3.6876, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.0360336957853404e-05, "loss": 3.6814, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.0351951010342884e-05, "loss": 3.7007, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.0343565062832364e-05, "loss": 3.6786, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.0335179115321844e-05, "loss": 3.6927, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032679316781133e-05, "loss": 3.6861, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031840722030081e-05, "loss": 3.6934, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.031002127279029e-05, "loss": 3.6887, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030163532527977e-05, "loss": 3.6927, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.029326575657298e-05, "loss": 3.6888, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.028487980906246e-05, "loss": 3.7059, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.027649386155194e-05, "loss": 3.6881, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.026810791404142e-05, "loss": 3.7042, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.025973834533463e-05, "loss": 3.6882, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.025135239782411e-05, "loss": 3.689, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.024296645031359e-05, "loss": 3.6848, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.023458050280307e-05, "loss": 3.6874, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0226210934096284e-05, "loss": 3.6831, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217824986585764e-05, "loss": 3.6928, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209439039075244e-05, "loss": 3.687, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.0201053091564724e-05, "loss": 3.6921, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019268352285793e-05, "loss": 3.6936, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.018429757534741e-05, "loss": 3.6854, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017591162783689e-05, "loss": 3.6915, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016752568032637e-05, "loss": 3.6916, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015915611161958e-05, "loss": 3.6829, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015077016410906e-05, "loss": 3.6887, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014238421659854e-05, "loss": 3.6683, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013399826908802e-05, "loss": 3.6931, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012562870038124e-05, "loss": 3.6911, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011724275287072e-05, "loss": 3.6969, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.01088568053602e-05, "loss": 3.685, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010047085784968e-05, "loss": 3.694, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009210128914289e-05, "loss": 3.6886, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008371534163237e-05, "loss": 3.6991, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007532939412185e-05, "loss": 3.684, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006694344661133e-05, "loss": 3.6869, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.0058573877904536e-05, "loss": 3.6867, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.0050187930394016e-05, "loss": 3.6918, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.0041801982883496e-05, "loss": 3.6899, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.0033416035372976e-05, "loss": 3.6859, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002504646666619e-05, "loss": 3.6966, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001666051915567e-05, "loss": 3.6767, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000827457164515e-05, "loss": 3.696, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.8690640926361084, "eval_runtime": 303.8257, "eval_samples_per_second": 1255.954, "eval_steps_per_second": 39.249, "step": 610560 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 4.078348705585889e+17, "trial_name": null, "trial_params": null }