{ "best_metric": 3.9513816833496094, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/transformer/4/checkpoints/checkpoint-228960", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 228960, "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": 10.8779, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8091, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1877, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9783, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8103, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.699, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.5978, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5322, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4504, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3927, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3411, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3034, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2561, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 5.2045, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 5.1717, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 5.1231, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1145, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0711, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0389, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0187, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0054, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9739, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9493, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9299, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9148, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8846, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8697, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8478, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8305, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8151, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8013, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740117521192533e-05, "loss": 4.7879, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731731573682013e-05, "loss": 4.7844, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7641, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7511, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.738, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7297, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7054, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.707, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6727, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6739, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.67, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6693, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.638, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6445, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.632, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6216, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6277, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5889, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5934, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5991, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5907, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5722, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.552, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5614, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5425, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.565, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5161, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5364, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5261, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5172, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5203, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.5003, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 4.4865, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.489, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5011, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4745, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 4.4752, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4583, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4584, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4745, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404794272397856e-05, "loss": 4.4704, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4442, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4592, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4646, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4487, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4278, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4341, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4301, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4199, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.418, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4183, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4189, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4114, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3924, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.3955, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.3959, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.3909, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3888, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3802, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3771, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3671, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3773, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.368, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3707, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.367, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3519, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3552, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3513, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3495, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3509, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3331, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3409, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3386, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3306, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3226, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3206, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3245, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3172, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3179, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3109, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3025, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3213, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3009, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.306, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3051, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3055, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.2964, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2916, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.3048, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2943, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.281, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.2816, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.2786, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2772, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2706, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2761, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.263, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2665, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2589, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2789, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2715, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2555, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2561, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.2571, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.2618, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2584, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2542, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2529, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2494, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2454, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2391, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2448, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2364, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.225, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2405, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2341, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.238, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2274, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2265, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.193294525146484, "eval_runtime": 308.4415, "eval_samples_per_second": 1237.158, "eval_steps_per_second": 38.662, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.217, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2137, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2289, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2132, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2205, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.206, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2129, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.201, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2068, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.202, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2095, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.2049, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1893, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.1894, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1852, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1839, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1858, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1816, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1822, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.1964, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1817, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1819, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1753, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1893, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1592, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1761, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1638, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.165, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1597, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.1552, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1629, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.171, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1562, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1594, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1505, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1558, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1448, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.154, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1348, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.143, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1392, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1531, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1288, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1411, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1386, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1304, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1425, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1177, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1257, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833183521875203e-05, "loss": 4.1369, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1288, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.1208, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.1167, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829830780751368e-05, "loss": 4.1199, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828992186000316e-05, "loss": 4.1101, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1284, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1017, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1153, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.1144, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824799212245056e-05, "loss": 4.1098, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.1186, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.1078, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.0937, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.0943, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.1202, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.0969, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.0979, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818093729997386e-05, "loss": 4.0897, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.0933, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816416540495282e-05, "loss": 4.1056, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.1074, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147409888735514e-05, "loss": 4.0953, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.1047, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130637993714474e-05, "loss": 4.109, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122252046203954e-05, "loss": 4.1047, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.0835, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.0953, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809711058247612e-05, "loss": 4.0902, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887246349656e-05, "loss": 4.0894, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.0862, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807196911874829e-05, "loss": 4.0898, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806358317123777e-05, "loss": 4.0972, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805519722372726e-05, "loss": 4.0911, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0719, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803844170750995e-05, "loss": 4.0765, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803005575999943e-05, "loss": 4.08, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802166981248891e-05, "loss": 4.0835, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801328386497839e-05, "loss": 4.083, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0701, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996528348761076e-05, "loss": 4.0788, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988142401250556e-05, "loss": 4.0603, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.0752, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0746, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963000937522725e-05, "loss": 4.0739, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795461499001221e-05, "loss": 4.0795, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794622904250169e-05, "loss": 4.0644, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793784309499117e-05, "loss": 4.067, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792945714748065e-05, "loss": 4.0693, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792107119997013e-05, "loss": 4.068, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791270163126334e-05, "loss": 4.0647, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790431568375282e-05, "loss": 4.0599, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.78959297362423e-05, "loss": 4.0604, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887543788731774e-05, "loss": 4.0662, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787917422002499e-05, "loss": 4.0657, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787078827251447e-05, "loss": 4.0454, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.058, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0628, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.0548, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.0512, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.0518, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782048896625508e-05, "loss": 4.0438, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781210301874456e-05, "loss": 4.0659, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780371707123404e-05, "loss": 4.0473, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779534750252725e-05, "loss": 4.0522, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778696155501673e-05, "loss": 4.051, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777857560750621e-05, "loss": 4.0606, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777018965999569e-05, "loss": 4.0487, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.0492, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.0576, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774504819626786e-05, "loss": 4.0476, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773666224875734e-05, "loss": 4.0399, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0436, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.0375, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.0402, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770313483751899e-05, "loss": 4.0408, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769474889000847e-05, "loss": 4.0406, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768637932130168e-05, "loss": 4.0321, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0338, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0306, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0498, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765285191006334e-05, "loss": 4.0476, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764446596255282e-05, "loss": 4.0351, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.76360800150423e-05, "loss": 4.0244, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762769406753178e-05, "loss": 4.0398, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0377, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610938551314466e-05, "loss": 4.0392, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602552603803946e-05, "loss": 4.0323, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594166656293426e-05, "loss": 4.0379, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.0297, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577411140076115e-05, "loss": 4.0311, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569025192565595e-05, "loss": 4.0279, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560639245055075e-05, "loss": 4.0289, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755226967634829e-05, "loss": 4.0238, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754388372883777e-05, "loss": 4.017, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753549778132725e-05, "loss": 4.0312, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752711183381673e-05, "loss": 4.0272, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751874226510994e-05, "loss": 4.0298, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751035631759942e-05, "loss": 4.0199, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.75019703700889e-05, "loss": 4.0211, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.025589942932129, "eval_runtime": 308.4504, "eval_samples_per_second": 1237.123, "eval_steps_per_second": 38.661, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749358442257838e-05, "loss": 4.0144, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748519847506786e-05, "loss": 4.011, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747681252755734e-05, "loss": 4.026, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746842658004682e-05, "loss": 4.0144, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.74600406325363e-05, "loss": 4.0249, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745165468502578e-05, "loss": 4.0082, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744326873751526e-05, "loss": 4.02, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743488279000474e-05, "loss": 4.0051, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742649684249422e-05, "loss": 4.0156, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.74181108949837e-05, "loss": 4.0103, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740972494747318e-05, "loss": 4.0167, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740135537876639e-05, "loss": 4.0124, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7392985810059604e-05, "loss": 3.9981, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384599862549084e-05, "loss": 4.0045, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737621391503856e-05, "loss": 4.0001, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736782796752804e-05, "loss": 4.0002, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735944202001752e-05, "loss": 4.0021, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7351056072507e-05, "loss": 3.997, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734267012499648e-05, "loss": 3.9986, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733428417748596e-05, "loss": 4.0164, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732591460877917e-05, "loss": 4.0045, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731752866126865e-05, "loss": 4.0024, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730914271375813e-05, "loss": 3.9991, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730077314505134e-05, "loss": 4.0073, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729238719754082e-05, "loss": 3.984, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.72840012500303e-05, "loss": 3.9975, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727561530251978e-05, "loss": 3.995, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726724573381299e-05, "loss": 3.9891, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725885978630247e-05, "loss": 3.9838, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725047383879195e-05, "loss": 3.9828, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724208789128143e-05, "loss": 3.9942, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233718322574647e-05, "loss": 4.0015, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225332375064127e-05, "loss": 3.9902, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216946427553606e-05, "loss": 3.9926, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208560480043086e-05, "loss": 3.984, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200190911336296e-05, "loss": 3.9882, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191804963825775e-05, "loss": 3.9793, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183419016315255e-05, "loss": 3.9946, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.9693, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166663500097945e-05, "loss": 3.9809, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158277552587424e-05, "loss": 3.9769, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149891605076904e-05, "loss": 3.9918, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9721, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71331360888596e-05, "loss": 3.9783, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712475014134908e-05, "loss": 3.9826, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711636419383856e-05, "loss": 3.975, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.9823, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709960867762125e-05, "loss": 3.9632, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709122273011073e-05, "loss": 3.9703, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708285316140394e-05, "loss": 3.9816, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707446721389342e-05, "loss": 3.971, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.9671, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9645, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9705, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9557, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703253747634082e-05, "loss": 3.972, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024167907634034e-05, "loss": 3.9529, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9675, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.9697, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6999010065102474e-05, "loss": 3.9598, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699064049639568e-05, "loss": 3.9669, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9679, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697386860137464e-05, "loss": 3.9457, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696548265386412e-05, "loss": 3.9521, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695711308515733e-05, "loss": 3.9663, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9588, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694034119013629e-05, "loss": 3.956, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693195524262577e-05, "loss": 3.9436, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692358567391899e-05, "loss": 3.9505, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691519972640847e-05, "loss": 3.9658, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690681377889795e-05, "loss": 3.9642, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689842783138743e-05, "loss": 3.9523, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890058262680636e-05, "loss": 3.9664, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881672315170116e-05, "loss": 3.9679, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873286367659596e-05, "loss": 3.9703, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864900420149076e-05, "loss": 3.9391, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856530851442285e-05, "loss": 3.9605, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848144903931765e-05, "loss": 3.9517, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839758956421245e-05, "loss": 3.9493, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831373008910725e-05, "loss": 3.9529, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682300344020394e-05, "loss": 3.9555, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681461749269342e-05, "loss": 3.959, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.68062315451829e-05, "loss": 3.9579, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679784559767238e-05, "loss": 3.9354, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678947602896559e-05, "loss": 3.9443, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678109008145507e-05, "loss": 3.9464, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677270413394455e-05, "loss": 3.9505, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676431818643403e-05, "loss": 3.9529, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675594861772724e-05, "loss": 3.9376, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674756267021672e-05, "loss": 3.9491, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67391767227062e-05, "loss": 3.9302, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730807153999415e-05, "loss": 3.946, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722421206488895e-05, "loss": 3.9439, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6714035258978375e-05, "loss": 3.9452, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705649311467855e-05, "loss": 3.9501, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697263363957335e-05, "loss": 3.9422, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688877416446815e-05, "loss": 3.9354, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668049146893629e-05, "loss": 3.9454, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672121900229504e-05, "loss": 3.9406, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663735952718984e-05, "loss": 3.9415, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665535000520846e-05, "loss": 3.9312, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664696405769794e-05, "loss": 3.9373, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663857811018742e-05, "loss": 3.9407, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66301921626769e-05, "loss": 3.9428, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621806215166383e-05, "loss": 3.9184, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661343664645959e-05, "loss": 3.9339, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660505069894907e-05, "loss": 3.9435, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659666475143855e-05, "loss": 3.9319, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658827880392803e-05, "loss": 3.9258, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657989285641751e-05, "loss": 3.9323, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657150690890699e-05, "loss": 3.9263, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656312096139647e-05, "loss": 3.943, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655475139268968e-05, "loss": 3.9253, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654636544517916e-05, "loss": 3.9343, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653797949766864e-05, "loss": 3.9352, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652959355015812e-05, "loss": 3.9386, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.65212076026476e-05, "loss": 3.9293, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651282165513708e-05, "loss": 3.934, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650443570762657e-05, "loss": 3.9403, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649606613891978e-05, "loss": 3.9304, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648768019140926e-05, "loss": 3.919, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647929424389874e-05, "loss": 3.9256, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647090829638822e-05, "loss": 3.921, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462538727681426e-05, "loss": 3.9271, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454152780170906e-05, "loss": 3.9237, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445766832660386e-05, "loss": 3.928, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437380885149866e-05, "loss": 3.9159, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429027695246804e-05, "loss": 3.9187, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642064174773629e-05, "loss": 3.9172, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641225580022577e-05, "loss": 3.9353, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640386985271525e-05, "loss": 3.933, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639548390520473e-05, "loss": 3.925, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638709795769421e-05, "loss": 3.9134, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637871201018369e-05, "loss": 3.9261, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637032606267317e-05, "loss": 3.9279, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636195649396638e-05, "loss": 3.9264, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635358692525959e-05, "loss": 3.9198, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634520097774907e-05, "loss": 3.9255, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633681503023855e-05, "loss": 3.9201, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632842908272803e-05, "loss": 3.926, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632004313521751e-05, "loss": 3.9131, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631165718770699e-05, "loss": 3.9215, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303271240196475e-05, "loss": 3.9147, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629488529268595e-05, "loss": 3.9063, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286532102782893e-05, "loss": 3.9227, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278146155272373e-05, "loss": 3.9217, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626976020776185e-05, "loss": 3.918, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626137426025133e-05, "loss": 3.9148, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625298831274081e-05, "loss": 3.9102, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9513816833496094, "eval_runtime": 303.4591, "eval_samples_per_second": 1257.471, "eval_steps_per_second": 39.297, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5939988909905715e+17, "trial_name": null, "trial_params": null }