{ "best_metric": 3.8441641330718994, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/4/checkpoints/checkpoint-915840", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 915840, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 11.0368, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8134, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1877, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9788, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8108, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7032, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.5999, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5361, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4453, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4008, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3507, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3098, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2582, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2103, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1687, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1357, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1055, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0901, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0477, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0274, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0154, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9707, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9456, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9307, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9209, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8868, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782030879941405e-05, "loss": 4.8669, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773644932430885e-05, "loss": 4.8606, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765258984920364e-05, "loss": 4.8385, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8117, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7945, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740117521192533e-05, "loss": 4.7903, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731731573682013e-05, "loss": 4.7787, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7747, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7513, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.736, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7379, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7031, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.6961, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6831, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6832, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6604, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.672, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6425, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 4.6463, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6366, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6276, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6242, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5995, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.587, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6012, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.5854, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5687, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5577, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5648, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5469, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5599, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5342, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5313, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.535, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5165, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.4989, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5047, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.488, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4898, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4974, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4911, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4782, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4663, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4584, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4699, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.466, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4578, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.456, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4582, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4521, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4261, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4359, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4321, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4188, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4303, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4199, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4254, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930422841748654e-05, "loss": 4.4167, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3887, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.3998, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.3993, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3994, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3916, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3838, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3862, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.375, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.368, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3685, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3654, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3794, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3545, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3487, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.347, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3576, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3531, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3398, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.3393, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136542224883596e-05, "loss": 4.3214, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3374, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.322, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.3206, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3238, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3228, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3172, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3153, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3074, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3136, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3028, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.3023, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3076, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3048, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.3025, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2937, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2983, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2932, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2793, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.2973, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.2813, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.2894, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2709, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2661, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.2649, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2682, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.258, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2754, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.272, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2555, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2596, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.2631, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.2597, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2637, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2595, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2466, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2528, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2464, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.24, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2503, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2374, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2263, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2481, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2278, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.228, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2307, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.2235, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.195763111114502, "eval_runtime": 304.3449, "eval_samples_per_second": 1253.811, "eval_steps_per_second": 39.183, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.2068, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.2199, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2339, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.2115, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2262, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.2001, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2133, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.1979, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2083, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.2035, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.209, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.2051, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1916, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.1833, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.1845, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.1852, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.1949, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.1823, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.1885, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.205, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.179, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856651071861674e-05, "loss": 4.1732, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.1771, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.186, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.1671, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.171, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1727, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1665, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.1514, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.1567, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.8491069948629524e-05, "loss": 4.1553, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1666, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.1708, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.1529, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845754253739117e-05, "loss": 4.1501, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844915658988065e-05, "loss": 4.1648, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844077064237013e-05, "loss": 4.1387, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843238469485961e-05, "loss": 4.1448, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1371, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.1433, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840724323113178e-05, "loss": 4.1352, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839885728362126e-05, "loss": 4.1532, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.1375, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.1386, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.1346, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.1408, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.133, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.1239, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834017202985136e-05, "loss": 4.117, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.1385, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.1267, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.1169, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.1171, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298275049906215e-05, "loss": 4.1231, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289889102395695e-05, "loss": 4.112, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281503154885175e-05, "loss": 4.13, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273117207374655e-05, "loss": 4.113, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264731259864135e-05, "loss": 4.1149, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256345312353615e-05, "loss": 4.124, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8247959364843095e-05, "loss": 4.1038, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823957341733258e-05, "loss": 4.1002, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.1103, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.0924, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821443195360475e-05, "loss": 4.0985, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820604600609423e-05, "loss": 4.1096, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819766005858371e-05, "loss": 4.1122, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189274111073184e-05, "loss": 4.1009, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180888163562664e-05, "loss": 4.0957, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817253497365961e-05, "loss": 4.0861, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816414902614909e-05, "loss": 4.1051, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815576307863857e-05, "loss": 4.1013, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814737713112805e-05, "loss": 4.1016, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8138991183617535e-05, "loss": 4.102, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813060523610701e-05, "loss": 4.1048, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122235667400224e-05, "loss": 4.1031, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113849719889704e-05, "loss": 4.0819, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105480151182914e-05, "loss": 4.0935, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097094203672393e-05, "loss": 4.095, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.8088708256161873e-05, "loss": 4.0788, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808032230865135e-05, "loss": 4.1021, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.8071936361140827e-05, "loss": 4.0938, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063550413630307e-05, "loss": 4.0971, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055164466119786e-05, "loss": 4.0954, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804677851860927e-05, "loss": 4.071, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803840894990248e-05, "loss": 4.0829, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803002300239196e-05, "loss": 4.0819, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802163705488144e-05, "loss": 4.0849, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801325110737092e-05, "loss": 4.0833, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800488153866413e-05, "loss": 4.0746, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799649559115361e-05, "loss": 4.084, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798810964364309e-05, "loss": 4.0771, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797972369613257e-05, "loss": 4.0647, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797133774862205e-05, "loss": 4.0716, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796295180111153e-05, "loss": 4.0769, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795458223240474e-05, "loss": 4.0869, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794619628489423e-05, "loss": 4.0682, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793781033738371e-05, "loss": 4.0545, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792942438987319e-05, "loss": 4.0634, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792103844236267e-05, "loss": 4.074, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791265249485215e-05, "loss": 4.071, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790426654734163e-05, "loss": 4.0658, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895880599831107e-05, "loss": 4.0598, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887494652320587e-05, "loss": 4.0503, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879125083613796e-05, "loss": 4.0659, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870739136103276e-05, "loss": 4.0511, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862353188592756e-05, "loss": 4.0559, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853983619885965e-05, "loss": 4.0591, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845597672375445e-05, "loss": 4.0593, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837211724864925e-05, "loss": 4.0524, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782882577735441e-05, "loss": 4.0583, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782043982984389e-05, "loss": 4.0494, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781205388233337e-05, "loss": 4.0549, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803667934822844e-05, "loss": 4.0477, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795281987312324e-05, "loss": 4.0458, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778691241860554e-05, "loss": 4.0589, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777852647109502e-05, "loss": 4.0574, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777015690238823e-05, "loss": 4.053, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776177095487771e-05, "loss": 4.0468, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775338500736719e-05, "loss": 4.0515, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774499905985666e-05, "loss": 4.0501, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773661311234615e-05, "loss": 4.0367, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772822716483563e-05, "loss": 4.057, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771984121732511e-05, "loss": 4.041, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771145526981459e-05, "loss": 4.0523, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.77030857011078e-05, "loss": 4.0341, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769469975359728e-05, "loss": 4.0357, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768631380608676e-05, "loss": 4.0319, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767792785857624e-05, "loss": 4.0344, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766955828986945e-05, "loss": 4.0316, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766117234235893e-05, "loss": 4.0465, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765278639484841e-05, "loss": 4.0479, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764440044733789e-05, "loss": 4.0357, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763601449982737e-05, "loss": 4.0289, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762764493112058e-05, "loss": 4.0387, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761925898361006e-05, "loss": 4.0371, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761087303609954e-05, "loss": 4.0461, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760248708858902e-05, "loss": 4.0374, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759411751988223e-05, "loss": 4.0331, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758573157237171e-05, "loss": 4.0284, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757734562486119e-05, "loss": 4.0381, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756895967735067e-05, "loss": 4.0264, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756059010864388e-05, "loss": 4.0306, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755220416113336e-05, "loss": 4.0283, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754381821362284e-05, "loss": 4.0197, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753544864491605e-05, "loss": 4.0409, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527062697405536e-05, "loss": 4.0207, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518676749895016e-05, "loss": 4.0199, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510290802384496e-05, "loss": 4.0233, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7501904854873976e-05, "loss": 4.0188, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.028048515319824, "eval_runtime": 306.2895, "eval_samples_per_second": 1245.851, "eval_steps_per_second": 38.934, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493518907363456e-05, "loss": 4.0033, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485132959852936e-05, "loss": 4.0187, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476747012342416e-05, "loss": 4.0332, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468361064831896e-05, "loss": 4.0153, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7459975117321376e-05, "loss": 4.0297, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745158916981085e-05, "loss": 4.0079, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744320322230033e-05, "loss": 4.021, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743481727478981e-05, "loss": 3.9999, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742643132727929e-05, "loss": 4.017, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741804537976877e-05, "loss": 4.0142, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740965943225825e-05, "loss": 4.0125, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401289863551465e-05, "loss": 4.0213, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739292029484468e-05, "loss": 4.0019, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384534347334154e-05, "loss": 3.9977, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376148399823634e-05, "loss": 3.996, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.7367762452313114e-05, "loss": 4.004, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.7359376504802594e-05, "loss": 4.0087, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7350990557292074e-05, "loss": 4.0022, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342604609781554e-05, "loss": 4.0041, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733423504107476e-05, "loss": 4.0239, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732584909356424e-05, "loss": 3.9994, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731746314605372e-05, "loss": 3.9946, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73090771985432e-05, "loss": 4.0021, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730070762983642e-05, "loss": 4.0077, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.72923216823259e-05, "loss": 3.9908, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728393573481538e-05, "loss": 3.9969, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727554978730486e-05, "loss": 3.9984, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726718021859807e-05, "loss": 3.9948, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725879427108755e-05, "loss": 3.9809, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725040832357703e-05, "loss": 3.9865, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724202237606651e-05, "loss": 3.9889, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233652807359716e-05, "loss": 3.9934, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225266859849196e-05, "loss": 4.0065, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216880912338676e-05, "loss": 3.9845, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208494964828156e-05, "loss": 3.9848, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720010901731764e-05, "loss": 3.996, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719172306980712e-05, "loss": 3.9793, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71833371222966e-05, "loss": 3.9776, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717496755358981e-05, "loss": 3.9745, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716658160607929e-05, "loss": 3.9827, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715819565856877e-05, "loss": 3.9709, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714980971105825e-05, "loss": 3.9936, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714144014235146e-05, "loss": 3.9745, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713305419484094e-05, "loss": 3.9844, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712466824733042e-05, "loss": 3.9788, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.71162822998199e-05, "loss": 3.9783, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710791273111311e-05, "loss": 3.9774, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709952678360259e-05, "loss": 3.9654, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709114083609208e-05, "loss": 3.9623, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708275488858156e-05, "loss": 3.9837, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074385319874766e-05, "loss": 3.9745, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065999372364246e-05, "loss": 3.9643, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057613424853726e-05, "loss": 3.9668, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.7049227477343206e-05, "loss": 3.9747, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040857908636415e-05, "loss": 3.9541, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032471961125895e-05, "loss": 3.9765, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024086013615375e-05, "loss": 3.9645, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015700066104855e-05, "loss": 3.9645, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007330497398064e-05, "loss": 3.9803, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998944549887544e-05, "loss": 3.9573, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699055860237703e-05, "loss": 3.9535, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698217265486651e-05, "loss": 3.9659, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697380308615972e-05, "loss": 3.9483, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.69654171386492e-05, "loss": 3.9539, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695703119113868e-05, "loss": 3.9648, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694864524362816e-05, "loss": 3.9693, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694027567492137e-05, "loss": 3.9537, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693188972741085e-05, "loss": 3.9554, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692352015870406e-05, "loss": 3.9434, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691513421119354e-05, "loss": 3.9656, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690674826368302e-05, "loss": 3.9581, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.68983623161725e-05, "loss": 3.9644, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6889976368661984e-05, "loss": 3.9602, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688159042115146e-05, "loss": 3.9644, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687320447364094e-05, "loss": 3.9693, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686481852613042e-05, "loss": 3.9435, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685644895742363e-05, "loss": 3.9572, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848063009913106e-05, "loss": 3.9608, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839677062402586e-05, "loss": 3.944, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831291114892066e-05, "loss": 3.9648, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822905167381546e-05, "loss": 3.9586, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814519219871026e-05, "loss": 3.9626, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806133272360506e-05, "loss": 3.9618, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797747324849986e-05, "loss": 3.9387, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.67893777561432e-05, "loss": 3.9516, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678099180863268e-05, "loss": 3.9484, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677260586112216e-05, "loss": 3.9564, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676421991361164e-05, "loss": 3.9478, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675585034490485e-05, "loss": 3.9475, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674746439739433e-05, "loss": 3.9522, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673907844988381e-05, "loss": 3.9495, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673069250237329e-05, "loss": 3.9351, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.67223229336665e-05, "loss": 3.9416, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671393698615598e-05, "loss": 3.9505, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670556741744919e-05, "loss": 3.9569, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697181469938675e-05, "loss": 3.9474, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688795522428155e-05, "loss": 3.9269, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680409574917635e-05, "loss": 3.9391, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672023627407115e-05, "loss": 3.9474, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663654058700324e-05, "loss": 3.944, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655268111189804e-05, "loss": 3.9414, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646882163679284e-05, "loss": 3.9361, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638496216168764e-05, "loss": 3.9264, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630110268658244e-05, "loss": 3.9458, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662174069995145e-05, "loss": 3.9211, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661335475244093e-05, "loss": 3.9351, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660496880493041e-05, "loss": 3.9315, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659658285741989e-05, "loss": 3.943, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658821328871311e-05, "loss": 3.9272, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657982734120259e-05, "loss": 3.9401, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657144139369207e-05, "loss": 3.9298, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656305544618155e-05, "loss": 3.9292, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655466949867103e-05, "loss": 3.9344, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654628355116051e-05, "loss": 3.9229, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653789760364999e-05, "loss": 3.9399, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652951165613947e-05, "loss": 3.9386, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652115846623641e-05, "loss": 3.9365, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651277251872589e-05, "loss": 3.9297, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650438657121537e-05, "loss": 3.9341, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649600062370485e-05, "loss": 3.9345, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648761467619433e-05, "loss": 3.9155, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647922872868381e-05, "loss": 3.9416, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470842781173294e-05, "loss": 3.9279, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646245683366277e-05, "loss": 3.9346, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645408726495598e-05, "loss": 3.9222, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644570131744546e-05, "loss": 3.9244, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643731536993494e-05, "loss": 3.9128, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428929422424416e-05, "loss": 3.9204, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642055985371763e-05, "loss": 3.919, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641217390620711e-05, "loss": 3.9338, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640378795869659e-05, "loss": 3.9356, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395402011186065e-05, "loss": 3.9235, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638703244247928e-05, "loss": 3.9154, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637864649496876e-05, "loss": 3.9256, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637026054745824e-05, "loss": 3.9266, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636187459994772e-05, "loss": 3.9315, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353505031240936e-05, "loss": 3.9275, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345119083730416e-05, "loss": 3.9174, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336749515023625e-05, "loss": 3.9248, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328363567513105e-05, "loss": 3.9292, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319977620002585e-05, "loss": 3.915, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631159167249206e-05, "loss": 3.9225, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630320572498154e-05, "loss": 3.9175, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629481977747102e-05, "loss": 3.9107, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286450208764234e-05, "loss": 3.9311, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278064261253714e-05, "loss": 3.9154, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269678313743194e-05, "loss": 3.912, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261292366232674e-05, "loss": 3.9144, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6252906418722154e-05, "loss": 3.91, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9538862705230713, "eval_runtime": 302.4885, "eval_samples_per_second": 1261.506, "eval_steps_per_second": 39.423, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624453685001536e-05, "loss": 3.9037, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623615090250484e-05, "loss": 3.9107, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622776495499432e-05, "loss": 3.9273, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.62193790074838e-05, "loss": 3.9119, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621099305997328e-05, "loss": 3.9315, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620260711246276e-05, "loss": 3.8984, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619422116495224e-05, "loss": 3.9195, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618585159624545e-05, "loss": 3.8957, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617746564873494e-05, "loss": 3.9131, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616907970122442e-05, "loss": 3.9148, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.61606937537139e-05, "loss": 3.9083, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615230780620338e-05, "loss": 3.9165, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614393823749659e-05, "loss": 3.8992, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613555228998607e-05, "loss": 3.8971, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612716634247555e-05, "loss": 3.8962, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611878039496503e-05, "loss": 3.9008, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110410826258237e-05, "loss": 3.9076, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102024878747717e-05, "loss": 3.9012, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093638931237196e-05, "loss": 3.9041, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085252983726676e-05, "loss": 3.9225, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607688341501989e-05, "loss": 3.9027, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606849746750937e-05, "loss": 3.8997, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606011151999885e-05, "loss": 3.9046, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605172557248833e-05, "loss": 3.9062, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604335600378154e-05, "loss": 3.8915, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603497005627102e-05, "loss": 3.9013, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.60265841087605e-05, "loss": 3.9022, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601819816124998e-05, "loss": 3.8943, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600981221373946e-05, "loss": 3.8868, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600142626622894e-05, "loss": 3.8853, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599305669752215e-05, "loss": 3.8975, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598467075001163e-05, "loss": 3.8959, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597628480250111e-05, "loss": 3.9098, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596789885499059e-05, "loss": 3.8971, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595951290748008e-05, "loss": 3.8862, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5951143338773286e-05, "loss": 3.8985, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942757391262766e-05, "loss": 3.889, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934371443752246e-05, "loss": 3.8807, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925985496241726e-05, "loss": 3.8831, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.59175995487312e-05, "loss": 3.887, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590921360122068e-05, "loss": 3.8802, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590082765371016e-05, "loss": 3.9009, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589245808500337e-05, "loss": 3.8842, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884088516296584e-05, "loss": 3.8912, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875702568786064e-05, "loss": 3.8897, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867316621275544e-05, "loss": 3.8834, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858930673765024e-05, "loss": 3.8882, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850544726254504e-05, "loss": 3.8727, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842158778743984e-05, "loss": 3.8633, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833772831233464e-05, "loss": 3.8964, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582540326252667e-05, "loss": 3.8859, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581701731501615e-05, "loss": 3.8793, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580863136750563e-05, "loss": 3.8741, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580024541999511e-05, "loss": 3.8816, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579187585128832e-05, "loss": 3.8669, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.57834899037778e-05, "loss": 3.8855, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577510395626728e-05, "loss": 3.8802, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576671800875677e-05, "loss": 3.878, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575833206124625e-05, "loss": 3.8896, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574994611373573e-05, "loss": 3.8682, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574156016622521e-05, "loss": 3.8664, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573319059751842e-05, "loss": 3.8826, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.57248046500079e-05, "loss": 3.8575, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571641870249738e-05, "loss": 3.863, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570803275498686e-05, "loss": 3.8807, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569964680747634e-05, "loss": 3.8832, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569126085996582e-05, "loss": 3.8624, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.56828749124553e-05, "loss": 3.8739, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567448896494478e-05, "loss": 3.8554, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666119396237986e-05, "loss": 3.8799, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657733448727466e-05, "loss": 3.8728, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649347501216946e-05, "loss": 3.8802, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564096155370643e-05, "loss": 3.8711, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563257560619591e-05, "loss": 3.8786, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562420603748912e-05, "loss": 3.8855, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.56158200899786e-05, "loss": 3.8558, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560743414246808e-05, "loss": 3.8762, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599048194957555e-05, "loss": 3.8783, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590662247447035e-05, "loss": 3.8542, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558229267874025e-05, "loss": 3.8836, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557390673122973e-05, "loss": 3.8754, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.5565520783719204e-05, "loss": 3.8765, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557134836208684e-05, "loss": 3.8805, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554874888869817e-05, "loss": 3.8586, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554036294118765e-05, "loss": 3.8616, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553199337248086e-05, "loss": 3.8662, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552360742497034e-05, "loss": 3.8729, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551522147745982e-05, "loss": 3.8638, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.55068355299493e-05, "loss": 3.8668, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549844958243878e-05, "loss": 3.8659, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549008001373199e-05, "loss": 3.8741, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548169406622147e-05, "loss": 3.8544, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547330811871095e-05, "loss": 3.8592, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546492217120043e-05, "loss": 3.8692, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545655260249364e-05, "loss": 3.8778, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448166654983124e-05, "loss": 3.8687, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5439780707472604e-05, "loss": 3.8462, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431394759962084e-05, "loss": 3.8575, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542302519125529e-05, "loss": 3.8649, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541463924374477e-05, "loss": 3.8661, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540625329623425e-05, "loss": 3.8652, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539786734872373e-05, "loss": 3.8569, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538949778001694e-05, "loss": 3.8476, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538111183250642e-05, "loss": 3.864, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.53727258849959e-05, "loss": 3.8461, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536433993748538e-05, "loss": 3.8556, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535597036877859e-05, "loss": 3.85, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534758442126808e-05, "loss": 3.8645, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533919847375756e-05, "loss": 3.8494, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533081252624704e-05, "loss": 3.8662, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532242657873652e-05, "loss": 3.8469, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531405701002973e-05, "loss": 3.8539, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530567106251921e-05, "loss": 3.8554, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529728511500869e-05, "loss": 3.8511, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5288899167498167e-05, "loss": 3.8584, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280529598791376e-05, "loss": 3.8647, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272143651280856e-05, "loss": 3.8579, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5263757703770336e-05, "loss": 3.852, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255371756259816e-05, "loss": 3.8574, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5246985808749295e-05, "loss": 3.858, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523861624004251e-05, "loss": 3.8398, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523023029253199e-05, "loss": 3.8636, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522184434502147e-05, "loss": 3.8486, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521345839751095e-05, "loss": 3.8621, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520507245000043e-05, "loss": 3.85, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519670288129364e-05, "loss": 3.8495, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518831693378312e-05, "loss": 3.8367, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.51799309862726e-05, "loss": 3.8497, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517154503876208e-05, "loss": 3.8454, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516317547005529e-05, "loss": 3.8537, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515478952254477e-05, "loss": 3.859, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514640357503425e-05, "loss": 3.8537, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513801762752373e-05, "loss": 3.8374, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512963168001321e-05, "loss": 3.8531, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121262111306425e-05, "loss": 3.8536, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5112876163795905e-05, "loss": 3.8569, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104490216285385e-05, "loss": 3.8533, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096104268774865e-05, "loss": 3.8444, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087734700068074e-05, "loss": 3.8488, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079348752557554e-05, "loss": 3.8579, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070962805047034e-05, "loss": 3.8412, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062576857536514e-05, "loss": 3.8505, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505420728882972e-05, "loss": 3.8401, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.50458213413192e-05, "loss": 3.8439, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503743539380868e-05, "loss": 3.8579, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502904944629816e-05, "loss": 3.8443, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502066349878764e-05, "loss": 3.8407, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501229393008086e-05, "loss": 3.8382, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500390798257034e-05, "loss": 3.842, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9126405715942383, "eval_runtime": 301.972, "eval_samples_per_second": 1263.664, "eval_steps_per_second": 39.49, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499552203505981e-05, "loss": 3.8269, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498713608754929e-05, "loss": 3.8402, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497875014003877e-05, "loss": 3.8511, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497036419252825e-05, "loss": 3.8433, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496197824501773e-05, "loss": 3.8576, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495359229750721e-05, "loss": 3.8348, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494520634999669e-05, "loss": 3.8434, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493682040248617e-05, "loss": 3.8299, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492845083377939e-05, "loss": 3.8385, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492006488626887e-05, "loss": 3.8445, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491167893875835e-05, "loss": 3.8406, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490329299124783e-05, "loss": 3.8472, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4894923422541036e-05, "loss": 3.8299, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886537475030516e-05, "loss": 3.8302, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878151527519996e-05, "loss": 3.8279, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869765580009476e-05, "loss": 3.8321, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861396011302685e-05, "loss": 3.84, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853010063792165e-05, "loss": 3.8319, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844624116281645e-05, "loss": 3.8362, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836238168771125e-05, "loss": 3.8541, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482786860006434e-05, "loss": 3.8363, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481948265255382e-05, "loss": 3.8328, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.48110967050433e-05, "loss": 3.8348, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480271075753278e-05, "loss": 3.8362, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479434118882599e-05, "loss": 3.8243, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478595524131547e-05, "loss": 3.8355, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477756929380495e-05, "loss": 3.8307, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476918334629443e-05, "loss": 3.8292, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476079739878391e-05, "loss": 3.8197, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475242783007712e-05, "loss": 3.8227, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.47440418825666e-05, "loss": 3.8267, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473565593505608e-05, "loss": 3.8305, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472726998754556e-05, "loss": 3.8398, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.4718900418838775e-05, "loss": 3.8299, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710514471328255e-05, "loss": 3.8175, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4702128523817734e-05, "loss": 3.8322, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4693742576307214e-05, "loss": 3.8296, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685373007600424e-05, "loss": 3.8124, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4676987060089903e-05, "loss": 3.8148, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668601112579383e-05, "loss": 3.824, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466021516506886e-05, "loss": 3.8143, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465182921755834e-05, "loss": 3.8357, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464345964885155e-05, "loss": 3.8213, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463507370134103e-05, "loss": 3.8225, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462668775383051e-05, "loss": 3.8243, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461830180631999e-05, "loss": 3.8252, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460993223761321e-05, "loss": 3.8232, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460154629010269e-05, "loss": 3.8089, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459316034259217e-05, "loss": 3.7961, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458477439508165e-05, "loss": 3.8367, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457640482637486e-05, "loss": 3.817, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456801887886434e-05, "loss": 3.8192, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455963293135382e-05, "loss": 3.8147, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455124698384329e-05, "loss": 3.8109, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542877415136506e-05, "loss": 3.8052, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534491467625986e-05, "loss": 3.8196, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4526105520115466e-05, "loss": 3.8166, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517719572604946e-05, "loss": 3.8133, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450935000389816e-05, "loss": 3.8315, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450096405638764e-05, "loss": 3.8024, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449257810887712e-05, "loss": 3.8005, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4484192161366595e-05, "loss": 3.8238, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447582259265981e-05, "loss": 3.7922, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446743664514929e-05, "loss": 3.7988, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.4459050697638764e-05, "loss": 3.8222, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.4450664750128244e-05, "loss": 3.8223, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.4442278802617724e-05, "loss": 3.802, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443390923391094e-05, "loss": 3.8124, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442552328640042e-05, "loss": 3.7958, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.4417153717693636e-05, "loss": 3.8144, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.4408767770183116e-05, "loss": 3.8104, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400381822672595e-05, "loss": 3.8161, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439199587516207e-05, "loss": 3.8095, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438360992765155e-05, "loss": 3.8183, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437522398014103e-05, "loss": 3.825, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436683803263051e-05, "loss": 3.7988, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435845208511999e-05, "loss": 3.8108, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.43500825164132e-05, "loss": 3.8182, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434169656890268e-05, "loss": 3.7938, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433331062139216e-05, "loss": 3.8203, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432492467388164e-05, "loss": 3.8186, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431655510517485e-05, "loss": 3.8163, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430816915766433e-05, "loss": 3.82, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429978321015381e-05, "loss": 3.8021, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429139726264329e-05, "loss": 3.7982, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.42830276939365e-05, "loss": 3.8073, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427464174642598e-05, "loss": 3.817, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426625579891546e-05, "loss": 3.8087, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425786985140494e-05, "loss": 3.8042, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424950028269815e-05, "loss": 3.8039, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424111433518763e-05, "loss": 3.8148, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423272838767711e-05, "loss": 3.7997, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422434244016659e-05, "loss": 3.7994, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421595649265607e-05, "loss": 3.808, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.4207603302753016e-05, "loss": 3.8187, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.4199217355242496e-05, "loss": 3.8094, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.4190831407731976e-05, "loss": 3.7919, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.4182445460221456e-05, "loss": 3.7978, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4174059512710936e-05, "loss": 3.8051, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165673565200416e-05, "loss": 3.8091, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157287617689896e-05, "loss": 3.805, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4148901670179376e-05, "loss": 3.8023, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140532101472585e-05, "loss": 3.7899, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132146153962065e-05, "loss": 3.8009, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123760206451545e-05, "loss": 3.7899, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115374258941025e-05, "loss": 3.8026, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410700469023424e-05, "loss": 3.7852, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409861874272372e-05, "loss": 3.8148, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.40902327952132e-05, "loss": 3.7922, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408184684770268e-05, "loss": 3.8012, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407346090019216e-05, "loss": 3.7946, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406509133148537e-05, "loss": 3.7959, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405670538397485e-05, "loss": 3.798, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404831943646433e-05, "loss": 3.7952, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403993348895381e-05, "loss": 3.7998, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403156392024702e-05, "loss": 3.8074, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.40231779727365e-05, "loss": 3.7992, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401479202522598e-05, "loss": 3.7976, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.4006406077715465e-05, "loss": 3.7998, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.3998036509008674e-05, "loss": 3.8053, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.3989650561498154e-05, "loss": 3.7804, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.3981264613987634e-05, "loss": 3.8073, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.3972878666477114e-05, "loss": 3.791, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396450909777032e-05, "loss": 3.805, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.39561231502598e-05, "loss": 3.7916, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394773720274928e-05, "loss": 3.7958, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393935125523876e-05, "loss": 3.7857, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393098168653197e-05, "loss": 3.7916, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392259573902145e-05, "loss": 3.7943, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391420979151093e-05, "loss": 3.7971, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.390582384400042e-05, "loss": 3.7991, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.38974378964899e-05, "loss": 3.8028, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388906832778311e-05, "loss": 3.7809, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388068238027259e-05, "loss": 3.7966, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387229643276207e-05, "loss": 3.8018, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386391048525155e-05, "loss": 3.7996, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385554091654476e-05, "loss": 3.795, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384715496903424e-05, "loss": 3.7967, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383876902152372e-05, "loss": 3.7903, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.38303830740132e-05, "loss": 3.8036, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.3822013505306406e-05, "loss": 3.7849, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.3813627557795886e-05, "loss": 3.7967, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380524161028537e-05, "loss": 3.7866, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.3796855662774846e-05, "loss": 3.7893, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378848609406806e-05, "loss": 3.803, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378010014655754e-05, "loss": 3.7929, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377171419904702e-05, "loss": 3.7885, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763328251536495e-05, "loss": 3.7802, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375495868282971e-05, "loss": 3.7897, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.886935234069824, "eval_runtime": 302.3733, "eval_samples_per_second": 1261.986, "eval_steps_per_second": 39.438, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374657273531919e-05, "loss": 3.7834, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373818678780867e-05, "loss": 3.7835, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.3729800840298144e-05, "loss": 3.7993, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372143127159136e-05, "loss": 3.7898, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371304532408084e-05, "loss": 3.8058, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370465937657032e-05, "loss": 3.7817, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.36962734290598e-05, "loss": 3.7842, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368788748154928e-05, "loss": 3.7809, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.3679517912842495e-05, "loss": 3.7821, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.3671148344135704e-05, "loss": 3.7915, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.3662762396625184e-05, "loss": 3.7913, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.3654376449114664e-05, "loss": 3.7887, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.3645990501604144e-05, "loss": 3.7831, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363760455409362e-05, "loss": 3.7771, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36292186065831e-05, "loss": 3.7753, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362083265907258e-05, "loss": 3.7795, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361246309036579e-05, "loss": 3.7855, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360407714285527e-05, "loss": 3.7817, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359569119534475e-05, "loss": 3.7854, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358730524783423e-05, "loss": 3.7994, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357891930032371e-05, "loss": 3.7879, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357054973161692e-05, "loss": 3.7747, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.35621637841064e-05, "loss": 3.7834, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355377783659588e-05, "loss": 3.7839, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354540826788909e-05, "loss": 3.7748, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353702232037857e-05, "loss": 3.7847, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352863637286805e-05, "loss": 3.7804, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352025042535753e-05, "loss": 3.7795, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351186447784701e-05, "loss": 3.7738, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350349490914023e-05, "loss": 3.7658, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349510896162971e-05, "loss": 3.7762, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486723014119187e-05, "loss": 3.7794, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478337066608667e-05, "loss": 3.7873, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469967497901876e-05, "loss": 3.7821, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.3461581550391356e-05, "loss": 3.7656, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3453195602880836e-05, "loss": 3.786, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444809655370316e-05, "loss": 3.7766, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436440086663525e-05, "loss": 3.7583, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3428054139153005e-05, "loss": 3.7703, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419668191642485e-05, "loss": 3.7704, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.34112986229357e-05, "loss": 3.7673, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340291267542518e-05, "loss": 3.7827, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.339452672791466e-05, "loss": 3.7719, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338614078040414e-05, "loss": 3.7708, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337777121169735e-05, "loss": 3.7732, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336938526418683e-05, "loss": 3.7735, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336099931667631e-05, "loss": 3.7778, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335261336916579e-05, "loss": 3.7597, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.3344243800459e-05, "loss": 3.7421, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333585785294848e-05, "loss": 3.789, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332747190543796e-05, "loss": 3.7675, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331908595792744e-05, "loss": 3.7734, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.3310716389220654e-05, "loss": 3.7633, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.3302330441710134e-05, "loss": 3.7625, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.3293944494199614e-05, "loss": 3.7594, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.3285558546689094e-05, "loss": 3.7667, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.32771889779823e-05, "loss": 3.7715, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326880303047178e-05, "loss": 3.7601, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326041708296126e-05, "loss": 3.7851, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325203113545074e-05, "loss": 3.7592, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324366156674395e-05, "loss": 3.7505, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323527561923343e-05, "loss": 3.7731, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322688967172291e-05, "loss": 3.7476, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321850372421239e-05, "loss": 3.7483, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321013415550561e-05, "loss": 3.7721, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320174820799509e-05, "loss": 3.7703, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319336226048457e-05, "loss": 3.7562, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318497631297405e-05, "loss": 3.7657, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317660674426726e-05, "loss": 3.7468, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316822079675674e-05, "loss": 3.7676, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.3159834849246217e-05, "loss": 3.7601, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.3151448901735697e-05, "loss": 3.77, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.3143079333028906e-05, "loss": 3.7633, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.3134693385518386e-05, "loss": 3.7674, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.3126307438007866e-05, "loss": 3.7756, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.3117921490497346e-05, "loss": 3.7509, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310955192179056e-05, "loss": 3.7653, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310116597428004e-05, "loss": 3.7683, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309278002676952e-05, "loss": 3.7503, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.3084394079259e-05, "loss": 3.7712, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307602451055221e-05, "loss": 3.7738, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306763856304169e-05, "loss": 3.7675, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305925261553117e-05, "loss": 3.7774, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305086666802065e-05, "loss": 3.7553, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.304249709931386e-05, "loss": 3.7506, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.303411115180334e-05, "loss": 3.7622, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.302572520429282e-05, "loss": 3.7653, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.30173392567823e-05, "loss": 3.7673, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008969688075515e-05, "loss": 3.7568, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000583740564995e-05, "loss": 3.756, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2992197793054475e-05, "loss": 3.7677, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.2983811845543955e-05, "loss": 3.7546, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.2975442276837164e-05, "loss": 3.7525, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2967056329326644e-05, "loss": 3.7597, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958670381816124e-05, "loss": 3.7743, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2950284434305604e-05, "loss": 3.7643, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294191486559881e-05, "loss": 3.7448, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293352891808829e-05, "loss": 3.7527, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292514297057777e-05, "loss": 3.7611, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291675702306725e-05, "loss": 3.7636, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290838745436047e-05, "loss": 3.7609, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.290000150684995e-05, "loss": 3.758, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289161555933943e-05, "loss": 3.745, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288322961182891e-05, "loss": 3.7525, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287486004312212e-05, "loss": 3.7502, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.28664740956116e-05, "loss": 3.7549, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285808814810108e-05, "loss": 3.7407, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284970220059056e-05, "loss": 3.7701, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284133263188377e-05, "loss": 3.7469, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.2832946684373247e-05, "loss": 3.756, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824560736862727e-05, "loss": 3.7449, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2816174789352207e-05, "loss": 3.758, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.280780522064542e-05, "loss": 3.7519, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.27994192731349e-05, "loss": 3.7471, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279103332562438e-05, "loss": 3.7564, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278264737811386e-05, "loss": 3.7646, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277427780940707e-05, "loss": 3.749, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276589186189655e-05, "loss": 3.7615, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275750591438603e-05, "loss": 3.7485, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274911996687551e-05, "loss": 3.7603, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274075039816872e-05, "loss": 3.7413, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.27323644506582e-05, "loss": 3.7616, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272397850314768e-05, "loss": 3.7457, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271559255563716e-05, "loss": 3.7603, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2707222986930376e-05, "loss": 3.7503, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.2698837039419856e-05, "loss": 3.75, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.2690451091909336e-05, "loss": 3.7393, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.2682081523202545e-05, "loss": 3.7495, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.2673695575692025e-05, "loss": 3.75, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.2665309628181505e-05, "loss": 3.756, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.2656923680670985e-05, "loss": 3.7495, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.2648554111964194e-05, "loss": 3.7606, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.2640168164453674e-05, "loss": 3.7412, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.2631782216943154e-05, "loss": 3.7522, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623396269432634e-05, "loss": 3.7557, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261502670072584e-05, "loss": 3.7589, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260664075321533e-05, "loss": 3.7492, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259825480570481e-05, "loss": 3.7521, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258986885819429e-05, "loss": 3.7456, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.25814992894875e-05, "loss": 3.764, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257311334197698e-05, "loss": 3.7415, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256472739446646e-05, "loss": 3.7547, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255634144695594e-05, "loss": 3.7442, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254797187824915e-05, "loss": 3.7477, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253958593073863e-05, "loss": 3.7567, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253119998322811e-05, "loss": 3.7467, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252281403571758e-05, "loss": 3.751, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.25144444670108e-05, "loss": 3.7341, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250605851950028e-05, "loss": 3.7491, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.8715946674346924, "eval_runtime": 302.2449, "eval_samples_per_second": 1262.522, "eval_steps_per_second": 39.455, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249767257198976e-05, "loss": 3.7381, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.2489286624479237e-05, "loss": 3.7382, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.2480900676968716e-05, "loss": 3.7552, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.2472514729458196e-05, "loss": 3.7495, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.2464128781947676e-05, "loss": 3.7607, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.2455742834437156e-05, "loss": 3.7401, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.2447356886926636e-05, "loss": 3.7415, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.2438970939416116e-05, "loss": 3.7415, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.2430601370709325e-05, "loss": 3.7402, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.2422231802002534e-05, "loss": 3.7528, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241384585449202e-05, "loss": 3.7424, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.24054599069815e-05, "loss": 3.7467, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239707395947098e-05, "loss": 3.7417, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238868801196046e-05, "loss": 3.7368, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.238030206444994e-05, "loss": 3.7361, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237191611693942e-05, "loss": 3.7331, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.23635301694289e-05, "loss": 3.745, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235516060072211e-05, "loss": 3.7415, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234677465321159e-05, "loss": 3.7411, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233838870570107e-05, "loss": 3.754, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.233001913699428e-05, "loss": 3.7531, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232163318948376e-05, "loss": 3.7366, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.231324724197324e-05, "loss": 3.737, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230486129446272e-05, "loss": 3.7437, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.2296491725755935e-05, "loss": 3.7371, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.2288105778245415e-05, "loss": 3.7415, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.2279719830734895e-05, "loss": 3.741, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.2271333883224375e-05, "loss": 3.7411, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.2262947935713855e-05, "loss": 3.731, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254578367007064e-05, "loss": 3.7286, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246192419496544e-05, "loss": 3.7257, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237806471986024e-05, "loss": 3.7391, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222943690327923e-05, "loss": 3.7451, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222105095576871e-05, "loss": 3.7436, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221266500825819e-05, "loss": 3.7268, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220427906074767e-05, "loss": 3.7394, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219590949204089e-05, "loss": 3.7385, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218752354453037e-05, "loss": 3.721, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217913759701985e-05, "loss": 3.7287, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217075164950933e-05, "loss": 3.7295, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216238208080254e-05, "loss": 3.7231, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215399613329202e-05, "loss": 3.7413, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.21456101857815e-05, "loss": 3.732, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.213722423827098e-05, "loss": 3.7341, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128854669564186e-05, "loss": 3.7341, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120468722053666e-05, "loss": 3.7325, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.2112082774543146e-05, "loss": 3.7376, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.2103696827032626e-05, "loss": 3.7225, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209532725832584e-05, "loss": 3.6992, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208694131081532e-05, "loss": 3.7467, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.20785553633048e-05, "loss": 3.7282, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.207016941579428e-05, "loss": 3.7349, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206179984708749e-05, "loss": 3.7255, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.205341389957697e-05, "loss": 3.7225, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204502795206645e-05, "loss": 3.7159, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203664200455593e-05, "loss": 3.7276, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202827243584914e-05, "loss": 3.735, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201988648833862e-05, "loss": 3.7191, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.20115005408281e-05, "loss": 3.744, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200311459331758e-05, "loss": 3.7235, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994745024610796e-05, "loss": 3.7123, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.1986359077100276e-05, "loss": 3.7301, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.1977973129589756e-05, "loss": 3.7147, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969587182079236e-05, "loss": 3.7073, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1961217613372445e-05, "loss": 3.7355, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952831665861925e-05, "loss": 3.7315, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.1944445718351405e-05, "loss": 3.7183, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.1936059770840885e-05, "loss": 3.7235, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.1927690202134094e-05, "loss": 3.7108, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919304254623574e-05, "loss": 3.7278, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.1910918307113054e-05, "loss": 3.7268, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.1902532359602534e-05, "loss": 3.7258, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189416279089575e-05, "loss": 3.7269, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188577684338523e-05, "loss": 3.7287, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187739089587471e-05, "loss": 3.7385, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186900494836419e-05, "loss": 3.7141, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.18606353796574e-05, "loss": 3.73, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185224943214688e-05, "loss": 3.7263, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184386348463636e-05, "loss": 3.7129, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183547753712584e-05, "loss": 3.7315, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182710796841905e-05, "loss": 3.7367, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181872202090853e-05, "loss": 3.7275, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181033607339801e-05, "loss": 3.7403, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180195012588749e-05, "loss": 3.716, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179356417837697e-05, "loss": 3.7136, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178517823086645e-05, "loss": 3.7232, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177679228335593e-05, "loss": 3.7307, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1768422714649136e-05, "loss": 3.7217, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.1760036767138616e-05, "loss": 3.7218, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.1751650819628096e-05, "loss": 3.7211, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.1743264872117576e-05, "loss": 3.7278, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.1734895303410785e-05, "loss": 3.7171, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.1726509355900265e-05, "loss": 3.7158, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.1718123408389745e-05, "loss": 3.7218, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709737460879225e-05, "loss": 3.7363, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170136789217244e-05, "loss": 3.7262, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169298194466192e-05, "loss": 3.7052, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.16845959971514e-05, "loss": 3.719, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167621004964088e-05, "loss": 3.7198, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166784048093409e-05, "loss": 3.7276, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165945453342357e-05, "loss": 3.7204, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165106858591305e-05, "loss": 3.718, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.164268263840253e-05, "loss": 3.7099, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163431306969574e-05, "loss": 3.7099, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162592712218522e-05, "loss": 3.7197, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.16175411746747e-05, "loss": 3.7168, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160915522716418e-05, "loss": 3.703, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.1600785658457395e-05, "loss": 3.7347, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.1592399710946875e-05, "loss": 3.7102, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.1584013763436354e-05, "loss": 3.7147, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575627815925834e-05, "loss": 3.7099, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1567258247219044e-05, "loss": 3.7195, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.1558872299708523e-05, "loss": 3.7188, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.1550486352198003e-05, "loss": 3.7103, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154210040468748e-05, "loss": 3.7185, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153373083598069e-05, "loss": 3.7239, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152534488847017e-05, "loss": 3.7171, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151695894095965e-05, "loss": 3.7231, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150857299344913e-05, "loss": 3.711, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150020342474235e-05, "loss": 3.7211, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149181747723183e-05, "loss": 3.7084, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148343152972131e-05, "loss": 3.7226, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147504558221079e-05, "loss": 3.7115, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.1466676013504e-05, "loss": 3.7202, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145829006599348e-05, "loss": 3.7174, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144990411848296e-05, "loss": 3.713, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144151817097244e-05, "loss": 3.7063, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1433148602265646e-05, "loss": 3.7113, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424762654755126e-05, "loss": 3.7109, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1416376707244606e-05, "loss": 3.7243, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.1407990759734086e-05, "loss": 3.7115, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.13996211910273e-05, "loss": 3.7268, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139123524351678e-05, "loss": 3.7029, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138284929600626e-05, "loss": 3.7196, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137446334849574e-05, "loss": 3.7204, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136609377978895e-05, "loss": 3.7219, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.135770783227843e-05, "loss": 3.7167, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134932188476791e-05, "loss": 3.7164, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.134093593725739e-05, "loss": 3.7094, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.13325663685506e-05, "loss": 3.7302, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132418042104008e-05, "loss": 3.7032, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131579447352956e-05, "loss": 3.7175, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.130740852601904e-05, "loss": 3.7104, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1299038957312256e-05, "loss": 3.7193, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290669388605465e-05, "loss": 3.7128, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282283441094945e-05, "loss": 3.7123, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273897493584425e-05, "loss": 3.7145, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265511546073905e-05, "loss": 3.6988, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.1257125598563384e-05, "loss": 3.7159, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.859863758087158, "eval_runtime": 303.8718, "eval_samples_per_second": 1255.763, "eval_steps_per_second": 39.244, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248739651052864e-05, "loss": 3.7051, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.1240353703542344e-05, "loss": 3.7009, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.1231967756031824e-05, "loss": 3.7164, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.1223598187325033e-05, "loss": 3.7147, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.1215212239814513e-05, "loss": 3.7241, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120682629230399e-05, "loss": 3.7087, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119844034479347e-05, "loss": 3.7058, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119007077608669e-05, "loss": 3.7075, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118168482857617e-05, "loss": 3.7041, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117331525986938e-05, "loss": 3.7155, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116492931235886e-05, "loss": 3.7071, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115654336484834e-05, "loss": 3.7106, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114815741733782e-05, "loss": 3.71, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.11397714698273e-05, "loss": 3.7017, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113138552231678e-05, "loss": 3.6962, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112299957480626e-05, "loss": 3.6996, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.111461362729574e-05, "loss": 3.7122, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110624405858895e-05, "loss": 3.7087, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109785811107843e-05, "loss": 3.7015, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108947216356791e-05, "loss": 3.7223, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108110259486112e-05, "loss": 3.7159, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.10727166473506e-05, "loss": 3.7053, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106433069984008e-05, "loss": 3.7059, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105594475232956e-05, "loss": 3.702, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104757518362277e-05, "loss": 3.7055, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103918923611225e-05, "loss": 3.7065, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103080328860173e-05, "loss": 3.7078, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102241734109121e-05, "loss": 3.7095, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101404777238442e-05, "loss": 3.6954, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.10056618248739e-05, "loss": 3.6949, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.099727587736338e-05, "loss": 3.6898, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.098888992985286e-05, "loss": 3.7085, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0980520361146076e-05, "loss": 3.7092, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0972134413635556e-05, "loss": 3.7098, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963748466125036e-05, "loss": 3.6983, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0955362518614516e-05, "loss": 3.6971, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0946992949907725e-05, "loss": 3.7078, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938607002397205e-05, "loss": 3.6937, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0930221054886685e-05, "loss": 3.6906, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.092183510737616e-05, "loss": 3.6977, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913465538669374e-05, "loss": 3.6934, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0905079591158854e-05, "loss": 3.7027, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.0896693643648334e-05, "loss": 3.7006, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.0888307696137814e-05, "loss": 3.702, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087993812743103e-05, "loss": 3.6969, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087155217992051e-05, "loss": 3.7021, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086316623240999e-05, "loss": 3.7042, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085478028489946e-05, "loss": 3.6909, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084641071619268e-05, "loss": 3.6662, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083802476868216e-05, "loss": 3.7105, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082963882117163e-05, "loss": 3.695, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082125287366111e-05, "loss": 3.704, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081288330495433e-05, "loss": 3.691, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080449735744381e-05, "loss": 3.6922, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079611140993329e-05, "loss": 3.6783, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078772546242277e-05, "loss": 3.6937, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.0779355893715984e-05, "loss": 3.7052, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.0770969946205464e-05, "loss": 3.6832, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076258399869494e-05, "loss": 3.7132, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075419805118442e-05, "loss": 3.6933, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074582848247763e-05, "loss": 3.6789, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0737442534967106e-05, "loss": 3.6931, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0729056587456586e-05, "loss": 3.6833, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.0720670639946066e-05, "loss": 3.6767, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071230107123928e-05, "loss": 3.7009, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070391512372876e-05, "loss": 3.6984, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069552917621824e-05, "loss": 3.6869, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068714322870772e-05, "loss": 3.693, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067877366000094e-05, "loss": 3.6755, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.067038771249041e-05, "loss": 3.6981, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.066200176497989e-05, "loss": 3.6893, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065361581746937e-05, "loss": 3.6918, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064524624876258e-05, "loss": 3.6994, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063686030125206e-05, "loss": 3.6918, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062847435374154e-05, "loss": 3.709, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.062008840623102e-05, "loss": 3.6808, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061171883752423e-05, "loss": 3.6976, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0603332890013715e-05, "loss": 3.6923, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.0594946942503195e-05, "loss": 3.683, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586577373796404e-05, "loss": 3.6983, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0578191426285884e-05, "loss": 3.7042, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.0569805478775364e-05, "loss": 3.6966, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.0561419531264844e-05, "loss": 3.7079, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.0553033583754324e-05, "loss": 3.6856, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.0544647636243804e-05, "loss": 3.6793, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.0536261688733284e-05, "loss": 3.6911, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.0527875741222764e-05, "loss": 3.7005, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.051950617251597e-05, "loss": 3.6857, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051112022500545e-05, "loss": 3.6918, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050273427749493e-05, "loss": 3.6886, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049434832998441e-05, "loss": 3.6949, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048599514008136e-05, "loss": 3.6875, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047760919257084e-05, "loss": 3.6848, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046922324506032e-05, "loss": 3.6921, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.04608372975498e-05, "loss": 3.7037, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045245135003928e-05, "loss": 3.6954, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044406540252876e-05, "loss": 3.6727, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043567945501824e-05, "loss": 3.6856, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042729350750772e-05, "loss": 3.6863, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041892393880093e-05, "loss": 3.6986, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041053799129041e-05, "loss": 3.6902, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040215204377989e-05, "loss": 3.6862, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039376609626937e-05, "loss": 3.6814, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038539652756258e-05, "loss": 3.6775, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037701058005206e-05, "loss": 3.6882, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036862463254154e-05, "loss": 3.6835, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036023868503102e-05, "loss": 3.6729, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035186911632423e-05, "loss": 3.7005, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034348316881371e-05, "loss": 3.6806, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033509722130319e-05, "loss": 3.6817, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032671127379267e-05, "loss": 3.6814, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031834170508588e-05, "loss": 3.6831, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030995575757536e-05, "loss": 3.6893, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030156981006484e-05, "loss": 3.6801, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.029318386255432e-05, "loss": 3.6899, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284814293847536e-05, "loss": 3.6948, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.0276428346337016e-05, "loss": 3.6839, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.0268042398826496e-05, "loss": 3.6909, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.0259656451315976e-05, "loss": 3.6802, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.0251286882609185e-05, "loss": 3.6911, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.0242900935098665e-05, "loss": 3.6806, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.0234514987588145e-05, "loss": 3.6855, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0226129040077625e-05, "loss": 3.6814, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217759471370834e-05, "loss": 3.6909, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209373523860314e-05, "loss": 3.6906, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.0200987576349794e-05, "loss": 3.6808, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.0192601628839274e-05, "loss": 3.6704, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.018423206013249e-05, "loss": 3.684, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017584611262197e-05, "loss": 3.6791, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016746016511145e-05, "loss": 3.6888, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015907421760093e-05, "loss": 3.6811, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015070464889414e-05, "loss": 3.6936, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014231870138362e-05, "loss": 3.6718, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.01339327538731e-05, "loss": 3.6925, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012556318516631e-05, "loss": 3.6865, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011717723765579e-05, "loss": 3.6951, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010879129014527e-05, "loss": 3.6843, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010040534263475e-05, "loss": 3.6814, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.0092035773927964e-05, "loss": 3.6809, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.0083649826417444e-05, "loss": 3.6989, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.0075263878906924e-05, "loss": 3.6723, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.0066877931396404e-05, "loss": 3.688, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005850836268961e-05, "loss": 3.6826, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.005012241517909e-05, "loss": 3.6853, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.00417528464723e-05, "loss": 3.6825, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003336689896178e-05, "loss": 3.6849, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002498095145126e-05, "loss": 3.6827, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001659500394074e-05, "loss": 3.6713, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000820905643022e-05, "loss": 3.6834, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.8530285358428955, "eval_runtime": 303.7855, "eval_samples_per_second": 1256.12, "eval_steps_per_second": 39.255, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.99998231089197e-05, "loss": 3.6726, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999143716140918e-05, "loss": 3.6738, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.998305121389866e-05, "loss": 3.6856, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997466526638814e-05, "loss": 3.6834, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996627931887762e-05, "loss": 3.6973, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.99578933713671e-05, "loss": 3.6751, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994950742385658e-05, "loss": 3.6801, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994112147634606e-05, "loss": 3.6789, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993275190763927e-05, "loss": 3.6729, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992438233893248e-05, "loss": 3.6879, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991599639142196e-05, "loss": 3.6753, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990761044391144e-05, "loss": 3.6782, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.989922449640092e-05, "loss": 3.6864, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.98908385488904e-05, "loss": 3.6652, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.9882452601379886e-05, "loss": 3.6671, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.9874083032673095e-05, "loss": 3.6667, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.9865697085162575e-05, "loss": 3.6855, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.9857311137652055e-05, "loss": 3.6754, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.9848925190141535e-05, "loss": 3.6756, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840539242631015e-05, "loss": 3.6903, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9832153295120495e-05, "loss": 3.6865, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823767347609975e-05, "loss": 3.6737, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815397778903184e-05, "loss": 3.6785, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9807011831392664e-05, "loss": 3.6743, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979864226268587e-05, "loss": 3.677, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979025631517535e-05, "loss": 3.676, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978187036766484e-05, "loss": 3.6748, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977348442015432e-05, "loss": 3.6835, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.97650984726438e-05, "loss": 3.6659, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975671252513328e-05, "loss": 3.6645, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974832657762276e-05, "loss": 3.6661, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.973994063011224e-05, "loss": 3.6729, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973157106140545e-05, "loss": 3.6786, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972318511389493e-05, "loss": 3.6858, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971479916638441e-05, "loss": 3.6682, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970641321887389e-05, "loss": 3.6706, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.96980436501671e-05, "loss": 3.6801, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.968965770265658e-05, "loss": 3.6613, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968127175514606e-05, "loss": 3.6621, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967288580763554e-05, "loss": 3.6716, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966451623892875e-05, "loss": 3.6599, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965613029141823e-05, "loss": 3.6706, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964774434390771e-05, "loss": 3.6731, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963935839639719e-05, "loss": 3.6755, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.96309888276904e-05, "loss": 3.6653, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962260288017988e-05, "loss": 3.6756, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961421693266936e-05, "loss": 3.6726, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960583098515884e-05, "loss": 3.6649, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.959746141645205e-05, "loss": 3.6402, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958907546894153e-05, "loss": 3.6792, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958068952143101e-05, "loss": 3.6642, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957231995272423e-05, "loss": 3.6731, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956393400521371e-05, "loss": 3.6666, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955554805770319e-05, "loss": 3.6604, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954716211019267e-05, "loss": 3.6548, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.9538792541485876e-05, "loss": 3.6644, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.9530406593975356e-05, "loss": 3.6784, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9522037025268565e-05, "loss": 3.652, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.9513651077758045e-05, "loss": 3.6853, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.9505265130247525e-05, "loss": 3.6647, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.9496879182737005e-05, "loss": 3.6495, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.9488493235226485e-05, "loss": 3.6652, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.9480107287715965e-05, "loss": 3.6553, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.9471721340205445e-05, "loss": 3.6517, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.9463335392694925e-05, "loss": 3.6687, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945498220279187e-05, "loss": 3.6723, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944659625528135e-05, "loss": 3.6534, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943821030777083e-05, "loss": 3.6704, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.942982436026031e-05, "loss": 3.6477, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942143841274979e-05, "loss": 3.6658, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.941305246523926e-05, "loss": 3.6652, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.940466651772874e-05, "loss": 3.6599, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939628057021822e-05, "loss": 3.671, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938791100151144e-05, "loss": 3.6632, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937952505400092e-05, "loss": 3.6816, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.93711391064904e-05, "loss": 3.6551, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936275315897988e-05, "loss": 3.6696, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935438359027309e-05, "loss": 3.6613, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934599764276257e-05, "loss": 3.6551, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933762807405578e-05, "loss": 3.6694, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932924212654526e-05, "loss": 3.6705, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.9320856179034736e-05, "loss": 3.6727, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.9312470231524216e-05, "loss": 3.6786, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.9304084284013696e-05, "loss": 3.6586, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295698336503176e-05, "loss": 3.6496, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287312388992656e-05, "loss": 3.6618, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.927894282028587e-05, "loss": 3.673, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.927055687277535e-05, "loss": 3.6577, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926217092526483e-05, "loss": 3.665, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925378497775431e-05, "loss": 3.6655, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924539903024379e-05, "loss": 3.6636, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9237029461537e-05, "loss": 3.6638, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922864351402648e-05, "loss": 3.6545, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922025756651596e-05, "loss": 3.6641, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921187161900544e-05, "loss": 3.6762, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920348567149492e-05, "loss": 3.6689, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.91950997239844e-05, "loss": 3.6504, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918671377647388e-05, "loss": 3.6596, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917832782896336e-05, "loss": 3.6589, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916995826025657e-05, "loss": 3.6688, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.9161572312746056e-05, "loss": 3.667, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.9153186365235536e-05, "loss": 3.6562, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9144800417725016e-05, "loss": 3.6553, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9136430849018225e-05, "loss": 3.6492, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9128044901507705e-05, "loss": 3.6609, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.9119658953997185e-05, "loss": 3.6602, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.9111273006486665e-05, "loss": 3.6515, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.9102903437779874e-05, "loss": 3.6692, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.9094517490269354e-05, "loss": 3.6526, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.9086147921562563e-05, "loss": 3.6571, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907776197405204e-05, "loss": 3.6509, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906937602654152e-05, "loss": 3.6558, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.906099007903101e-05, "loss": 3.6641, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905260413152049e-05, "loss": 3.6506, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904421818400997e-05, "loss": 3.6645, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.903583223649945e-05, "loss": 3.6671, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.902746266779266e-05, "loss": 3.6577, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.901907672028214e-05, "loss": 3.6639, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901069077277162e-05, "loss": 3.6553, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.90023048252611e-05, "loss": 3.6652, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.899393525655431e-05, "loss": 3.6554, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898554930904379e-05, "loss": 3.6603, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897716336153327e-05, "loss": 3.6556, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.896879379282648e-05, "loss": 3.6626, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.8960407845315964e-05, "loss": 3.668, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.8952021897805444e-05, "loss": 3.6513, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.8943635950294924e-05, "loss": 3.6456, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.89352500027844e-05, "loss": 3.654, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892686405527388e-05, "loss": 3.6547, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891847810776336e-05, "loss": 3.6631, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.891010853905657e-05, "loss": 3.6559, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.8901722591546046e-05, "loss": 3.667, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.8893336644035526e-05, "loss": 3.6463, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.8884950696525006e-05, "loss": 3.6697, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.8876564749014486e-05, "loss": 3.6583, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.8868178801503966e-05, "loss": 3.6648, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859792853993446e-05, "loss": 3.6572, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.885140690648293e-05, "loss": 3.653, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.884303733777614e-05, "loss": 3.6549, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.883466776906935e-05, "loss": 3.6724, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882628182155883e-05, "loss": 3.6467, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881789587404831e-05, "loss": 3.6631, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880950992653779e-05, "loss": 3.657, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880112397902727e-05, "loss": 3.6593, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879275441032048e-05, "loss": 3.656, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878436846280996e-05, "loss": 3.659, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877598251529944e-05, "loss": 3.6536, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876759656778892e-05, "loss": 3.6516, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.8759226999082135e-05, "loss": 3.6553, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.848210573196411, "eval_runtime": 305.363, "eval_samples_per_second": 1249.631, "eval_steps_per_second": 39.052, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.8750841051571615e-05, "loss": 3.6461, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.8742455104061095e-05, "loss": 3.6461, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.8734069156550575e-05, "loss": 3.6582, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.8725683209040055e-05, "loss": 3.6609, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.8717297261529535e-05, "loss": 3.6708, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.8708927692822744e-05, "loss": 3.6455, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.8700541745312224e-05, "loss": 3.653, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.8692155797801704e-05, "loss": 3.6541, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.8683769850291184e-05, "loss": 3.6451, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.8675383902780664e-05, "loss": 3.662, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.866701433407387e-05, "loss": 3.6481, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865862838656335e-05, "loss": 3.6543, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.865024243905283e-05, "loss": 3.6625, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864185649154232e-05, "loss": 3.6407, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.86334705440318e-05, "loss": 3.6376, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.862510097532501e-05, "loss": 3.6441, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861671502781449e-05, "loss": 3.6578, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860832908030397e-05, "loss": 3.6561, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.859994313279345e-05, "loss": 3.6433, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859157356408666e-05, "loss": 3.663, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858318761657614e-05, "loss": 3.6641, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.857480166906562e-05, "loss": 3.6499, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.85664157215551e-05, "loss": 3.6513, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.855802977404458e-05, "loss": 3.6492, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.8549660205337787e-05, "loss": 3.6511, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.854127425782727e-05, "loss": 3.6502, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.853288831031675e-05, "loss": 3.6455, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.852450236280623e-05, "loss": 3.6583, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.8516116415295706e-05, "loss": 3.6439, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.8507730467785186e-05, "loss": 3.6367, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.8499344520274666e-05, "loss": 3.6407, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849097495156788e-05, "loss": 3.6485, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.8482589004057355e-05, "loss": 3.6493, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.8474203056546835e-05, "loss": 3.66, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.8465817109036315e-05, "loss": 3.6431, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.8457431161525795e-05, "loss": 3.6443, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.8449045214015275e-05, "loss": 3.6583, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.8440659266504755e-05, "loss": 3.6315, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843227331899424e-05, "loss": 3.6414, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.842390375028745e-05, "loss": 3.6464, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841551780277693e-05, "loss": 3.6385, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840713185526641e-05, "loss": 3.6407, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839874590775589e-05, "loss": 3.6483, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.83903763390491e-05, "loss": 3.6498, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.838199039153858e-05, "loss": 3.6393, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837360444402806e-05, "loss": 3.6484, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836523487532127e-05, "loss": 3.6459, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835684892781075e-05, "loss": 3.6405, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.8348479359103965e-05, "loss": 3.6183, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.8340093411593445e-05, "loss": 3.6514, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.8331707464082925e-05, "loss": 3.6404, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.8323321516572405e-05, "loss": 3.6521, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.8314935569061885e-05, "loss": 3.636, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.8306566000355094e-05, "loss": 3.6345, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.8298180052844574e-05, "loss": 3.6287, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.8289794105334054e-05, "loss": 3.6369, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.8281408157823533e-05, "loss": 3.655, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827303858911674e-05, "loss": 3.6283, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826465264160622e-05, "loss": 3.6582, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.82562666940957e-05, "loss": 3.6428, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824788074658518e-05, "loss": 3.6247, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.823949479907466e-05, "loss": 3.6379, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.823110885156415e-05, "loss": 3.6278, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822272290405363e-05, "loss": 3.6315, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821433695654311e-05, "loss": 3.6418, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.820598376664005e-05, "loss": 3.6489, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.819759781912953e-05, "loss": 3.6281, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.818921187161901e-05, "loss": 3.6447, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.818082592410849e-05, "loss": 3.6225, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.817243997659797e-05, "loss": 3.6411, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.816405402908745e-05, "loss": 3.6408, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.815566808157693e-05, "loss": 3.6397, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.814728213406641e-05, "loss": 3.6413, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.8138912565359616e-05, "loss": 3.64, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.8130526617849096e-05, "loss": 3.6561, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.812214067033858e-05, "loss": 3.6291, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.811375472282806e-05, "loss": 3.647, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810536877531754e-05, "loss": 3.6383, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.8096982827807016e-05, "loss": 3.6306, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808861325910023e-05, "loss": 3.6423, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808022731158971e-05, "loss": 3.6474, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.8071841364079185e-05, "loss": 3.6452, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.8063455416568665e-05, "loss": 3.6597, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.8055069469058145e-05, "loss": 3.6359, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804669990035136e-05, "loss": 3.6241, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.8038313952840834e-05, "loss": 3.6362, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.802992800533032e-05, "loss": 3.6455, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.80215420578198e-05, "loss": 3.636, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8013172489113016e-05, "loss": 3.6398, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.800478654160249e-05, "loss": 3.6385, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.799640059409197e-05, "loss": 3.6408, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.798801464658145e-05, "loss": 3.6385, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797964507787466e-05, "loss": 3.6303, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.797125913036414e-05, "loss": 3.6388, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.796287318285362e-05, "loss": 3.6529, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.79544872353431e-05, "loss": 3.6454, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.794610128783258e-05, "loss": 3.6229, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793771534032206e-05, "loss": 3.6348, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792932939281154e-05, "loss": 3.6362, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792094344530102e-05, "loss": 3.645, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.7912573876594234e-05, "loss": 3.641, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.7904187929083714e-05, "loss": 3.6325, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.7895801981573194e-05, "loss": 3.6316, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.7887416034062674e-05, "loss": 3.6249, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.7879030086552154e-05, "loss": 3.6383, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.7870644139041634e-05, "loss": 3.633, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.7862258191531114e-05, "loss": 3.6265, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7853872244020594e-05, "loss": 3.6391, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.78455026753138e-05, "loss": 3.6337, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.783713310660701e-05, "loss": 3.6312, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.782874715909649e-05, "loss": 3.627, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.782036121158597e-05, "loss": 3.6292, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.781197526407546e-05, "loss": 3.6427, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.780358931656494e-05, "loss": 3.6229, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.779520336905442e-05, "loss": 3.6417, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778683380034763e-05, "loss": 3.6451, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.777844785283711e-05, "loss": 3.6327, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.777006190532659e-05, "loss": 3.6396, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.776167595781607e-05, "loss": 3.6332, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.775329001030555e-05, "loss": 3.6415, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.7744920441598757e-05, "loss": 3.6331, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.7736534494088237e-05, "loss": 3.6347, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.7728148546577716e-05, "loss": 3.6334, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.7719762599067196e-05, "loss": 3.6342, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.7711376651556676e-05, "loss": 3.638, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.7702990704046156e-05, "loss": 3.6322, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.7694604756535636e-05, "loss": 3.6216, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.7686218809025116e-05, "loss": 3.6334, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.7677849240318325e-05, "loss": 3.6238, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.7669463292807805e-05, "loss": 3.6424, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766109372410102e-05, "loss": 3.6307, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.7652707776590494e-05, "loss": 3.6407, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.7644321829079974e-05, "loss": 3.6223, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.7635935881569454e-05, "loss": 3.6448, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.7627549934058934e-05, "loss": 3.6317, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.7619163986548414e-05, "loss": 3.6464, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.7610778039037894e-05, "loss": 3.6352, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760239209152738e-05, "loss": 3.6322, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759402252282059e-05, "loss": 3.6274, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.758563657531007e-05, "loss": 3.6518, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.757725062779955e-05, "loss": 3.6203, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.756888105909276e-05, "loss": 3.641, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.756049511158224e-05, "loss": 3.6308, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755210916407172e-05, "loss": 3.6344, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.75437232165612e-05, "loss": 3.6347, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.753535364785441e-05, "loss": 3.6308, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.752696770034389e-05, "loss": 3.6323, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.751858175283337e-05, "loss": 3.6311, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.751019580532285e-05, "loss": 3.628, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.8452677726745605, "eval_runtime": 302.7713, "eval_samples_per_second": 1260.328, "eval_steps_per_second": 39.386, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.750180985781233e-05, "loss": 3.6167, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.7493423910301815e-05, "loss": 3.6227, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.7485037962791294e-05, "loss": 3.6354, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.7476652015280774e-05, "loss": 3.6366, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.7468266067770254e-05, "loss": 3.648, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.7459896499063463e-05, "loss": 3.6256, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.7451510551552943e-05, "loss": 3.6288, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.744312460404242e-05, "loss": 3.6337, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.74347386565319e-05, "loss": 3.6223, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742635270902138e-05, "loss": 3.6304, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.741798314031459e-05, "loss": 3.6324, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.740959719280407e-05, "loss": 3.6306, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.740121124529355e-05, "loss": 3.6354, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.739282529778303e-05, "loss": 3.6176, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.738443935027251e-05, "loss": 3.6166, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.737606978156573e-05, "loss": 3.6174, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736768383405521e-05, "loss": 3.6397, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.735929788654468e-05, "loss": 3.63, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.735091193903416e-05, "loss": 3.6209, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.734254237032738e-05, "loss": 3.6389, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.733415642281686e-05, "loss": 3.6418, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732577047530633e-05, "loss": 3.6276, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731738452779581e-05, "loss": 3.6277, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.730899858028529e-05, "loss": 3.6241, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.7300629011578506e-05, "loss": 3.6339, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.7292243064067986e-05, "loss": 3.6247, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.7283857116557466e-05, "loss": 3.6198, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.7275471169046946e-05, "loss": 3.6375, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.7267085221536426e-05, "loss": 3.6174, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.7258715652829635e-05, "loss": 3.6115, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.7250329705319115e-05, "loss": 3.624, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.7241943757808595e-05, "loss": 3.6231, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.7233557810298075e-05, "loss": 3.6295, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.7225171862787555e-05, "loss": 3.6387, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.7216785915277035e-05, "loss": 3.6182, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.7208399967766515e-05, "loss": 3.6242, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.7200014020255995e-05, "loss": 3.6349, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.7191644451549204e-05, "loss": 3.6081, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718327488284242e-05, "loss": 3.6189, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.71748889353319e-05, "loss": 3.6237, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.716650298782138e-05, "loss": 3.6146, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.715811704031086e-05, "loss": 3.6201, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.714973109280034e-05, "loss": 3.6257, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.714134514528982e-05, "loss": 3.6303, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.713297557658303e-05, "loss": 3.6178, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.712458962907251e-05, "loss": 3.6219, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711620368156199e-05, "loss": 3.6245, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.710781773405147e-05, "loss": 3.6186, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709943178654095e-05, "loss": 3.5967, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709104583903043e-05, "loss": 3.6281, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.708265989151991e-05, "loss": 3.6217, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707427394400939e-05, "loss": 3.6276, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.7065904375302604e-05, "loss": 3.619, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705753480659581e-05, "loss": 3.6079, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.704914885908529e-05, "loss": 3.6106, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.704076291157477e-05, "loss": 3.6138, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.703237696406425e-05, "loss": 3.6301, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.702400739535746e-05, "loss": 3.6081, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.701562144784694e-05, "loss": 3.6326, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.700723550033642e-05, "loss": 3.6229, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.69988495528259e-05, "loss": 3.6029, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.699046360531538e-05, "loss": 3.6189, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.698207765780486e-05, "loss": 3.6039, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.697370808909808e-05, "loss": 3.609, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.696532214158756e-05, "loss": 3.6148, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.695693619407704e-05, "loss": 3.6284, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.694855024656652e-05, "loss": 3.607, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.694016429905599e-05, "loss": 3.6194, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693177835154547e-05, "loss": 3.6023, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.6923408782838687e-05, "loss": 3.6174, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.6915022835328167e-05, "loss": 3.62, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690663688781764e-05, "loss": 3.6204, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689825094030712e-05, "loss": 3.6182, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.6889881371600336e-05, "loss": 3.6152, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.6881495424089815e-05, "loss": 3.6344, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.6873109476579295e-05, "loss": 3.6089, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.6864723529068775e-05, "loss": 3.6205, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685635396036199e-05, "loss": 3.6154, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.6847968012851464e-05, "loss": 3.6124, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.6839582065340944e-05, "loss": 3.6207, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.6831196117830424e-05, "loss": 3.6206, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.682282654912364e-05, "loss": 3.6262, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.6814440601613113e-05, "loss": 3.6345, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.680605465410259e-05, "loss": 3.6228, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.679766870659207e-05, "loss": 3.6, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.678928275908155e-05, "loss": 3.6119, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.678091319037477e-05, "loss": 3.6244, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.677252724286425e-05, "loss": 3.6159, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676414129535373e-05, "loss": 3.6164, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675575534784321e-05, "loss": 3.6177, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.674738577913642e-05, "loss": 3.6187, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.67389998316259e-05, "loss": 3.6145, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.673061388411538e-05, "loss": 3.6081, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672222793660486e-05, "loss": 3.6196, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.671384198909434e-05, "loss": 3.6283, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670545604158382e-05, "loss": 3.6236, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669708647287703e-05, "loss": 3.5986, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668870052536651e-05, "loss": 3.6151, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.668031457785599e-05, "loss": 3.6157, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667192863034547e-05, "loss": 3.6217, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666355906163868e-05, "loss": 3.6185, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.665517311412816e-05, "loss": 3.6091, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.664678716661764e-05, "loss": 3.6091, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663840121910712e-05, "loss": 3.6052, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.66300152715966e-05, "loss": 3.6142, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662162932408608e-05, "loss": 3.6131, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.661324337657556e-05, "loss": 3.6059, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.660485742906504e-05, "loss": 3.62, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.659648786035825e-05, "loss": 3.6101, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.658811829165146e-05, "loss": 3.6094, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.657973234414094e-05, "loss": 3.6071, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.657134639663042e-05, "loss": 3.6058, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.656296044911991e-05, "loss": 3.6221, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.655457450160939e-05, "loss": 3.6041, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654618855409887e-05, "loss": 3.6162, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.6537818985392076e-05, "loss": 3.621, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.6529433037881556e-05, "loss": 3.6133, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.6521047090371036e-05, "loss": 3.615, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.6512661142860516e-05, "loss": 3.6154, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.6504291574153725e-05, "loss": 3.6185, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.6495905626643205e-05, "loss": 3.6179, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.6487519679132685e-05, "loss": 3.6091, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.6479133731622165e-05, "loss": 3.6113, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.6470764162915374e-05, "loss": 3.6147, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646237821540486e-05, "loss": 3.6191, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645399226789434e-05, "loss": 3.6079, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644560632038382e-05, "loss": 3.6006, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.64372203728733e-05, "loss": 3.6094, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.6428834425362774e-05, "loss": 3.6052, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.6420448477852254e-05, "loss": 3.623, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.641207890914547e-05, "loss": 3.61, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.640369296163495e-05, "loss": 3.6201, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.639530701412442e-05, "loss": 3.6036, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.63869210666139e-05, "loss": 3.6189, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637853511910338e-05, "loss": 3.6133, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.63701655503966e-05, "loss": 3.6241, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.636177960288608e-05, "loss": 3.6121, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635339365537556e-05, "loss": 3.6099, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.634500770786504e-05, "loss": 3.6088, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.633662176035452e-05, "loss": 3.6253, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.6328235812844e-05, "loss": 3.6036, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.631986624413721e-05, "loss": 3.6142, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631148029662669e-05, "loss": 3.6128, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.630309434911617e-05, "loss": 3.61, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.629470840160565e-05, "loss": 3.6136, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.6286338832898857e-05, "loss": 3.612, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.6277952885388337e-05, "loss": 3.6102, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.6269566937877816e-05, "loss": 3.6098, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.6261180990367296e-05, "loss": 3.605, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.844721555709839, "eval_runtime": 304.4125, "eval_samples_per_second": 1253.533, "eval_steps_per_second": 39.174, "step": 839520 }, { "epoch": 1.0, "learning_rate": 3.625281142166051e-05, "loss": 3.602, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.624442547414999e-05, "loss": 3.6011, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.623603952663947e-05, "loss": 3.6137, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.622765357912895e-05, "loss": 3.6156, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.621926763161843e-05, "loss": 3.6268, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.621089806291164e-05, "loss": 3.605, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.620251211540112e-05, "loss": 3.6081, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.61941261678906e-05, "loss": 3.6133, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.618574022038008e-05, "loss": 3.6027, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617735427286956e-05, "loss": 3.604, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.616898470416277e-05, "loss": 3.6169, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.616059875665225e-05, "loss": 3.6076, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.615221280914173e-05, "loss": 3.6171, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.614382686163122e-05, "loss": 3.5961, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.61354409141207e-05, "loss": 3.5931, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.6127071345413906e-05, "loss": 3.5985, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.6118685397903386e-05, "loss": 3.6159, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.6110299450392866e-05, "loss": 3.6134, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.6101913502882346e-05, "loss": 3.5991, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.6093543934175555e-05, "loss": 3.6139, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.6085157986665035e-05, "loss": 3.6221, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.6076772039154515e-05, "loss": 3.603, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.6068386091643995e-05, "loss": 3.6086, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.6060000144133475e-05, "loss": 3.6036, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.6051630575426684e-05, "loss": 3.615, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604324462791617e-05, "loss": 3.6025, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.603485868040565e-05, "loss": 3.5997, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602647273289513e-05, "loss": 3.6204, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.601808678538461e-05, "loss": 3.5959, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.6009700837874083e-05, "loss": 3.5927, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.60013312691673e-05, "loss": 3.5978, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599294532165678e-05, "loss": 3.6011, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.598455937414625e-05, "loss": 3.6114, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.597617342663573e-05, "loss": 3.6178, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.596778747912521e-05, "loss": 3.5952, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.595940153161469e-05, "loss": 3.6063, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.595103196290791e-05, "loss": 3.6114, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.594264601539739e-05, "loss": 3.5871, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.593426006788687e-05, "loss": 3.5975, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.592587412037635e-05, "loss": 3.606, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.591750455166956e-05, "loss": 3.5921, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.590911860415904e-05, "loss": 3.6029, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.590073265664852e-05, "loss": 3.6076, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.5892346709138e-05, "loss": 3.6069, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.5883977140431206e-05, "loss": 3.5971, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.5875591192920686e-05, "loss": 3.6038, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.5867205245410166e-05, "loss": 3.5989, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.5858819297899646e-05, "loss": 3.6028, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.5850433350389126e-05, "loss": 3.5762, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.584206378168234e-05, "loss": 3.6038, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.583367783417182e-05, "loss": 3.6026, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.58252918866613e-05, "loss": 3.6061, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.581690593915078e-05, "loss": 3.597, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.580851999164026e-05, "loss": 3.5906, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.580015042293347e-05, "loss": 3.5911, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.579176447542295e-05, "loss": 3.5932, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.578337852791243e-05, "loss": 3.6129, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.577499258040191e-05, "loss": 3.5895, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.576662301169512e-05, "loss": 3.6038, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.57582370641846e-05, "loss": 3.6038, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.574985111667408e-05, "loss": 3.5857, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.574146516916356e-05, "loss": 3.5948, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.5733095600456775e-05, "loss": 3.5855, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.5724709652946255e-05, "loss": 3.5916, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.5716323705435735e-05, "loss": 3.5894, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.5707937757925215e-05, "loss": 3.6094, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.5699568189218424e-05, "loss": 3.5926, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.5691182241707904e-05, "loss": 3.5938, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.5682796294197384e-05, "loss": 3.5853, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.5674410346686864e-05, "loss": 3.595, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.5666024399176344e-05, "loss": 3.5999, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.5657638451665824e-05, "loss": 3.5968, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.564926888295903e-05, "loss": 3.6015, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.564088293544851e-05, "loss": 3.5988, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.563249698793799e-05, "loss": 3.6095, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.562411104042748e-05, "loss": 3.5889, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.561574147172069e-05, "loss": 3.6015, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.560735552421017e-05, "loss": 3.5976, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.559896957669965e-05, "loss": 3.5937, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.559058362918913e-05, "loss": 3.6009, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.558221406048234e-05, "loss": 3.5989, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557382811297182e-05, "loss": 3.6067, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.55654421654613e-05, "loss": 3.6118, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555705621795078e-05, "loss": 3.6067, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.554867027044026e-05, "loss": 3.5801, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.554028432292974e-05, "loss": 3.5946, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.553191475422295e-05, "loss": 3.6008, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.5523528806712434e-05, "loss": 3.5997, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.5515142859201914e-05, "loss": 3.5947, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.550675691169139e-05, "loss": 3.5987, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.54983873429846e-05, "loss": 3.6, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.549000139547408e-05, "loss": 3.5922, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.548161544796356e-05, "loss": 3.5924, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.5473229500453036e-05, "loss": 3.5996, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.5464843552942516e-05, "loss": 3.6037, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.5456457605431996e-05, "loss": 3.6076, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.544808803672521e-05, "loss": 3.5788, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.5439702089214685e-05, "loss": 3.5955, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543131614170417e-05, "loss": 3.5949, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.542293019419365e-05, "loss": 3.6041, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.541456062548686e-05, "loss": 3.6011, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.540617467797634e-05, "loss": 3.5891, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.539778873046582e-05, "loss": 3.5912, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.53894027829553e-05, "loss": 3.5825, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.538101683544478e-05, "loss": 3.5985, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.537263088793426e-05, "loss": 3.5887, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.536424494042374e-05, "loss": 3.5866, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.535587537171695e-05, "loss": 3.6, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.534750580301016e-05, "loss": 3.5925, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.533911985549964e-05, "loss": 3.5884, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.5330733907989125e-05, "loss": 3.5918, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.5322347960478605e-05, "loss": 3.5836, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.5313978391771814e-05, "loss": 3.6034, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.5305592444261294e-05, "loss": 3.5822, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.5297206496750774e-05, "loss": 3.5982, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.5288820549240254e-05, "loss": 3.5965, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.5280434601729734e-05, "loss": 3.5975, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.527206503302294e-05, "loss": 3.5941, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.526367908551242e-05, "loss": 3.5942, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.52552931380019e-05, "loss": 3.601, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.524690719049138e-05, "loss": 3.5989, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.523853762178459e-05, "loss": 3.5899, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.523015167427408e-05, "loss": 3.5924, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522176572676356e-05, "loss": 3.5937, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521337977925304e-05, "loss": 3.5986, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.520499383174252e-05, "loss": 3.5882, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.5196607884232e-05, "loss": 3.5851, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.518823831552521e-05, "loss": 3.5855, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.517985236801469e-05, "loss": 3.5876, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.517146642050417e-05, "loss": 3.5986, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.516308047299365e-05, "loss": 3.5917, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.515471090428686e-05, "loss": 3.6058, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.5146324956776337e-05, "loss": 3.5806, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.5137939009265817e-05, "loss": 3.6014, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.5129553061755297e-05, "loss": 3.5954, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.512118349304851e-05, "loss": 3.5996, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.511279754553799e-05, "loss": 3.596, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.510441159802747e-05, "loss": 3.5902, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.509602565051695e-05, "loss": 3.5917, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.508763970300643e-05, "loss": 3.6048, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.507927013429964e-05, "loss": 3.5877, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.507088418678912e-05, "loss": 3.5922, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.50624982392786e-05, "loss": 3.5968, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.505411229176808e-05, "loss": 3.5915, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.504574272306129e-05, "loss": 3.5903, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.503735677555077e-05, "loss": 3.5982, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502897082804025e-05, "loss": 3.5871, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.502058488052973e-05, "loss": 3.5911, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.5012215311822946e-05, "loss": 3.5866, "step": 915456 }, { "epoch": 1.03, "eval_loss": 3.8441641330718994, "eval_runtime": 304.0696, "eval_samples_per_second": 1254.946, "eval_steps_per_second": 39.218, "step": 915840 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 6.347677072250143e+17, "trial_name": null, "trial_params": null }