{ "best_metric": 3.8442649841308594, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/3/checkpoints/checkpoint-839520", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 839520, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9828, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.815, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1821, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9729, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8165, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7082, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6061, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5386, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4514, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4102, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3599, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3198, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2546, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2159, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.183, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1335, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1172, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0848, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0452, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.023, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0069, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9763, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9588, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.926, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9188, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8964, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8732, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8532, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.828, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8199, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8034, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740117521192533e-05, "loss": 4.7967, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731731573682013e-05, "loss": 4.7807, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7672, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7584, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7461, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7364, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7037, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7038, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6797, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6841, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6644, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6666, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6455, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6428, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6342, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6276, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6153, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5907, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5971, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5978, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5916, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5719, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5592, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5614, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5481, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.563, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5249, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5405, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5303, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5116, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5213, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5053, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4964, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4904, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5027, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4811, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4772, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4696, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4621, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4697, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940482703000532e-05, "loss": 4.4767, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4497, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4607, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4656, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4472, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4359, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4374, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4348, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.421, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4193, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4273, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931261436499706e-05, "loss": 4.4282, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930422841748654e-05, "loss": 4.4108, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3884, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4021, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.406, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3941, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3996, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3806, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3806, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3754, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3734, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3795, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3668, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3828, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3664, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3492, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3528, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3598, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3504, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3481, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3471, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3356, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3382, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3182, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.324, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3292, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3239, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3165, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3255, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3005, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3115, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3071, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.3115, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3189, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3064, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.2984, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2937, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2998, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2947, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2915, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.2846, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.2819, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2823, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2714, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.277, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.2747, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.271, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2606, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.279, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2791, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2664, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2571, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2637, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.2635, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2636, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.2589, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884314871364151e-05, "loss": 4.2573, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2537, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2512, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2461, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2477, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.239, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2339, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2479, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2322, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2427, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2285, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.2223, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.196377277374268, "eval_runtime": 306.8923, "eval_samples_per_second": 1243.404, "eval_steps_per_second": 38.857, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.2163, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.2165, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2265, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.2193, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2205, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.21, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2079, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.1989, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867549527864604e-05, "loss": 4.2145, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866710933113552e-05, "loss": 4.2058, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658723383625e-05, "loss": 4.2166, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865033743611448e-05, "loss": 4.1978, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864196786740769e-05, "loss": 4.1944, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863358191989717e-05, "loss": 4.1892, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862519597238665e-05, "loss": 4.1842, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861681002487613e-05, "loss": 4.1853, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860842407736561e-05, "loss": 4.1941, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860003812985509e-05, "loss": 4.1816, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859165218234457e-05, "loss": 4.1797, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.1999, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.1844, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1862, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1753, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.1852, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541369254888915e-05, "loss": 4.1707, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532983307378395e-05, "loss": 4.172, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524597359867875e-05, "loss": 4.1704, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851621141235735e-05, "loss": 4.1637, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.1582, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.1592, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1676, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1664, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.158, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.166, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1614, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1609, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1469, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.1482, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1377, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1503, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840725960993552e-05, "loss": 4.1356, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398873662425e-05, "loss": 4.1489, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.1375, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.1372, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1404, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365346251186646e-05, "loss": 4.1359, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356960303676126e-05, "loss": 4.1338, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348574356165606e-05, "loss": 4.1203, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1251, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.1366, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323432892437775e-05, "loss": 4.1329, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315046944927255e-05, "loss": 4.124, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306660997416735e-05, "loss": 4.1146, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1228, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.1109, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281519533688904e-05, "loss": 4.1329, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273133586178384e-05, "loss": 4.1051, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826474763866787e-05, "loss": 4.1251, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.1189, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824799212245056e-05, "loss": 4.1047, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823960617494004e-05, "loss": 4.1166, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823122022742952e-05, "loss": 4.11, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222834279919e-05, "loss": 4.1003, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.101, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.1148, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819769281619117e-05, "loss": 4.1036, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818930686868065e-05, "loss": 4.1005, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818093729997386e-05, "loss": 4.0983, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.0941, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816416540495282e-05, "loss": 4.1028, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.1173, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147393509931785e-05, "loss": 4.0947, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.1104, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130637993714474e-05, "loss": 4.1093, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122252046203954e-05, "loss": 4.0994, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113866098693434e-05, "loss": 4.0894, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.1022, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809711058247612e-05, "loss": 4.0984, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887246349656e-05, "loss": 4.0893, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808033868745508e-05, "loss": 4.0905, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807196911874829e-05, "loss": 4.0945, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806358317123777e-05, "loss": 4.1003, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805519722372726e-05, "loss": 4.0885, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804681127621674e-05, "loss": 4.0734, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803844170750995e-05, "loss": 4.0813, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803005575999943e-05, "loss": 4.0892, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802166981248891e-05, "loss": 4.0851, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801328386497839e-05, "loss": 4.0895, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0757, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996528348761076e-05, "loss": 4.0717, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988142401250556e-05, "loss": 4.0725, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979756453740036e-05, "loss": 4.0767, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0792, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963000937522725e-05, "loss": 4.0746, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.0931, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0785, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.79378594737949e-05, "loss": 4.0617, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792947352628438e-05, "loss": 4.0713, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792108757877386e-05, "loss": 4.0731, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791270163126334e-05, "loss": 4.0726, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790431568375282e-05, "loss": 4.0717, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.78959297362423e-05, "loss": 4.0686, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788756016753551e-05, "loss": 4.0607, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787917422002499e-05, "loss": 4.0708, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787078827251447e-05, "loss": 4.0472, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786240232500395e-05, "loss": 4.0587, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0586, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.0626, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.0525, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.0614, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782048896625508e-05, "loss": 4.0475, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781210301874456e-05, "loss": 4.0531, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803733450037775e-05, "loss": 4.0525, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779534750252725e-05, "loss": 4.0539, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778696155501673e-05, "loss": 4.0702, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777857560750621e-05, "loss": 4.0595, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770206038799423e-05, "loss": 4.0532, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.0492, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.0514, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774504819626786e-05, "loss": 4.0508, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773666224875734e-05, "loss": 4.0468, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772827630124682e-05, "loss": 4.0447, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.77198903537363e-05, "loss": 4.043, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771150440622578e-05, "loss": 4.0457, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770313483751899e-05, "loss": 4.0343, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769474889000847e-05, "loss": 4.0423, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768636294249795e-05, "loss": 4.0405, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0413, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0288, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0497, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528355312596e-05, "loss": 4.0547, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764444958374909e-05, "loss": 4.0394, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763606363623857e-05, "loss": 4.0319, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762767768872805e-05, "loss": 4.0387, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761929174121753e-05, "loss": 4.0416, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761092217251074e-05, "loss": 4.0439, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760253622500022e-05, "loss": 4.0386, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.75941502774897e-05, "loss": 4.0385, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758576432997918e-05, "loss": 4.0334, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577394761272386e-05, "loss": 4.0388, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569008813761866e-05, "loss": 4.0283, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560622866251346e-05, "loss": 4.0369, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552236918740826e-05, "loss": 4.0321, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754388372883777e-05, "loss": 4.0208, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753549778132725e-05, "loss": 4.0379, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752711183381673e-05, "loss": 4.0271, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751872588630621e-05, "loss": 4.0329, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751033993879569e-05, "loss": 4.0203, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750195399128517e-05, "loss": 4.0204, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.026838779449463, "eval_runtime": 307.1642, "eval_samples_per_second": 1242.303, "eval_steps_per_second": 38.823, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749356804377465e-05, "loss": 4.0165, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748518209626413e-05, "loss": 4.0099, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747679614875361e-05, "loss": 4.0288, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468410201243084e-05, "loss": 4.0187, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460024253732563e-05, "loss": 4.0269, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451638306222043e-05, "loss": 4.0116, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744325235871152e-05, "loss": 4.0151, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434866411201e-05, "loss": 4.0018, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742648046369049e-05, "loss": 4.0178, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741809451617997e-05, "loss": 4.0175, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740970856866945e-05, "loss": 4.0197, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740133899996266e-05, "loss": 4.01, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739296943125587e-05, "loss": 4.003, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738458348374535e-05, "loss": 4.0031, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737619753623483e-05, "loss": 3.9992, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736781158872431e-05, "loss": 4.0005, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735942564121379e-05, "loss": 4.0053, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735103969370327e-05, "loss": 3.9983, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734265374619275e-05, "loss": 3.9995, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733428417748596e-05, "loss": 4.021, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325898229975444e-05, "loss": 4.0019, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317512282464924e-05, "loss": 4.008, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309126334954404e-05, "loss": 3.9973, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730075676624761e-05, "loss": 4.0105, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729237081873709e-05, "loss": 3.9884, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728398487122657e-05, "loss": 3.9993, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727559892371605e-05, "loss": 3.9966, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726722935500926e-05, "loss": 3.9928, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725884340749874e-05, "loss": 3.982, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725045745998822e-05, "loss": 3.9886, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724208789128143e-05, "loss": 3.9988, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723370194377091e-05, "loss": 3.9982, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.72253159962604e-05, "loss": 3.9927, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721693004874988e-05, "loss": 3.9943, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720854410123936e-05, "loss": 3.9918, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720015815372884e-05, "loss": 3.9957, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719177220621832e-05, "loss": 3.9817, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71833862587078e-05, "loss": 3.9831, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175016690001006e-05, "loss": 3.9728, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166630742490486e-05, "loss": 3.9895, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158244794979966e-05, "loss": 3.9768, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149858847469446e-05, "loss": 3.9855, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141489278762655e-05, "loss": 3.9797, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133103331252135e-05, "loss": 3.9737, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124717383741615e-05, "loss": 3.9882, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116331436231095e-05, "loss": 3.9738, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710796186752431e-05, "loss": 3.9772, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709957592001379e-05, "loss": 3.9606, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709118997250327e-05, "loss": 3.9738, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082804024992744e-05, "loss": 3.9805, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707443445628596e-05, "loss": 3.9768, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706604850877544e-05, "loss": 3.9728, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705766256126492e-05, "loss": 3.9589, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704927661375439e-05, "loss": 3.972, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704090704504761e-05, "loss": 3.9606, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703252109753709e-05, "loss": 3.9809, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702413515002657e-05, "loss": 3.9563, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701574920251605e-05, "loss": 3.9739, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007379633809265e-05, "loss": 3.974, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998993686298745e-05, "loss": 3.9543, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699060773878822e-05, "loss": 3.964, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.69822217912777e-05, "loss": 3.9672, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973852222570914e-05, "loss": 3.9539, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696548265386412e-05, "loss": 3.9577, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69570967063536e-05, "loss": 3.9674, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694871075884308e-05, "loss": 3.9638, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694032481133256e-05, "loss": 3.9523, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693193886382204e-05, "loss": 3.9593, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692355291631152e-05, "loss": 3.9493, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915166968801e-05, "loss": 3.9591, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690678102129048e-05, "loss": 3.9747, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689841145258369e-05, "loss": 3.9552, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689002550507317e-05, "loss": 3.9704, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688163955756265e-05, "loss": 3.9672, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687325361005213e-05, "loss": 3.9626, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686488404134534e-05, "loss": 3.9487, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685649809383482e-05, "loss": 3.9676, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848128525128036e-05, "loss": 3.958, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683974257761751e-05, "loss": 3.9575, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831356630106996e-05, "loss": 3.9531, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822970682596476e-05, "loss": 3.9593, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814584735085956e-05, "loss": 3.9692, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806198787575436e-05, "loss": 3.9519, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797829218868645e-05, "loss": 3.938, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789443271358125e-05, "loss": 3.9448, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781057323847605e-05, "loss": 3.9566, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772671376337085e-05, "loss": 3.9553, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764285428826565e-05, "loss": 3.9582, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755915860119774e-05, "loss": 3.9422, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747529912609254e-05, "loss": 3.9436, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739143965098734e-05, "loss": 3.939, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730758017588214e-05, "loss": 3.9453, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722372070077694e-05, "loss": 3.9507, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713986122567174e-05, "loss": 3.9475, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670561655386039e-05, "loss": 3.967, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669723060634987e-05, "loss": 3.9471, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668884465883935e-05, "loss": 3.9389, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668045871132883e-05, "loss": 3.9426, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667207276381831e-05, "loss": 3.9438, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666370319511152e-05, "loss": 3.9509, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655317247601e-05, "loss": 3.9451, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664693130009048e-05, "loss": 3.94, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663854535257996e-05, "loss": 3.9385, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663015940506944e-05, "loss": 3.9475, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662177345755892e-05, "loss": 3.9251, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.66133875100484e-05, "loss": 3.9397, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6605017941341614e-05, "loss": 3.9345, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596631993831094e-05, "loss": 3.9395, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588246046320574e-05, "loss": 3.9318, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579860098810054e-05, "loss": 3.9393, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657149053010326e-05, "loss": 3.9259, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656310458259274e-05, "loss": 3.931, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655471863508222e-05, "loss": 3.9378, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.65463326875717e-05, "loss": 3.9311, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537946740061176e-05, "loss": 3.9517, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529560792550656e-05, "loss": 3.942, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652119122384387e-05, "loss": 3.938, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651280527633335e-05, "loss": 3.9281, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650441932882283e-05, "loss": 3.9324, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649603338131231e-05, "loss": 3.9334, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648764743380179e-05, "loss": 3.9317, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647926148629127e-05, "loss": 3.931, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647087553878075e-05, "loss": 3.9226, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646248959127023e-05, "loss": 3.9323, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645412002256344e-05, "loss": 3.9183, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644573407505292e-05, "loss": 3.9267, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.64373481275424e-05, "loss": 3.9253, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642897855883561e-05, "loss": 3.9268, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642059261132509e-05, "loss": 3.9145, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641220666381457e-05, "loss": 3.9395, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640382071630405e-05, "loss": 3.9399, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395434768793536e-05, "loss": 3.9297, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387048821283016e-05, "loss": 3.9154, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378679252576226e-05, "loss": 3.9295, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370293305065705e-05, "loss": 3.9276, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361907357555185e-05, "loss": 3.9337, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353521410044665e-05, "loss": 3.9272, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345135462534145e-05, "loss": 3.9247, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336749515023625e-05, "loss": 3.9241, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328379946316834e-05, "loss": 3.9309, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319993998806314e-05, "loss": 3.9219, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311608051295794e-05, "loss": 3.9262, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303222103785274e-05, "loss": 3.9228, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629485253507848e-05, "loss": 3.9155, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628646658756797e-05, "loss": 3.9279, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627808064005745e-05, "loss": 3.9239, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626969469254693e-05, "loss": 3.9206, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626130874503641e-05, "loss": 3.9132, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625292279752589e-05, "loss": 3.912, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9523091316223145, "eval_runtime": 303.3686, "eval_samples_per_second": 1257.846, "eval_steps_per_second": 39.309, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624453685001536e-05, "loss": 3.9155, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623615090250484e-05, "loss": 3.9062, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622778133379806e-05, "loss": 3.9212, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621939538628753e-05, "loss": 3.9144, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621102581758075e-05, "loss": 3.9242, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620263987007023e-05, "loss": 3.9076, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619425392255971e-05, "loss": 3.9098, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618586797504919e-05, "loss": 3.8978, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617748202753867e-05, "loss": 3.9155, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616909608002815e-05, "loss": 3.9145, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160726511321364e-05, "loss": 3.915, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615234056381084e-05, "loss": 3.9078, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614397099510405e-05, "loss": 3.9022, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613558504759353e-05, "loss": 3.9028, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127199100083006e-05, "loss": 3.8973, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118813152572486e-05, "loss": 3.9007, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110427205061966e-05, "loss": 3.9042, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102041257551446e-05, "loss": 3.8972, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093655310040926e-05, "loss": 3.8988, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085269362530406e-05, "loss": 3.9237, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607689979382362e-05, "loss": 3.9038, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.60685138463131e-05, "loss": 3.9044, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606012789880258e-05, "loss": 3.9011, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605174195129206e-05, "loss": 3.9078, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604335600378154e-05, "loss": 3.8908, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603498643507475e-05, "loss": 3.907, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602660048756423e-05, "loss": 3.8973, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601821454005371e-05, "loss": 3.894, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600982859254319e-05, "loss": 3.8853, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.60014590238364e-05, "loss": 3.8938, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599307307632588e-05, "loss": 3.8986, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.5984703507619095e-05, "loss": 3.9032, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976317560108575e-05, "loss": 3.9011, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5967931612598055e-05, "loss": 3.9012, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959545665087535e-05, "loss": 3.892, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5951159717577015e-05, "loss": 3.9039, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942773770066495e-05, "loss": 3.8853, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934387822555975e-05, "loss": 3.8927, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5926001875045455e-05, "loss": 3.8776, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917632306338664e-05, "loss": 3.8933, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909246358828144e-05, "loss": 3.8844, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900860411317624e-05, "loss": 3.8934, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892474463807104e-05, "loss": 3.8898, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884088516296584e-05, "loss": 3.8802, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.58757189475898e-05, "loss": 3.8942, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586733300007928e-05, "loss": 3.8863, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585894705256876e-05, "loss": 3.8845, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585056110505824e-05, "loss": 3.8714, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584217515754772e-05, "loss": 3.8815, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.58337892100372e-05, "loss": 3.8885, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582540326252667e-05, "loss": 3.8863, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581703369381989e-05, "loss": 3.8811, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580864774630937e-05, "loss": 3.8716, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580026179879884e-05, "loss": 3.8815, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579187585128832e-05, "loss": 3.8681, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578350628258154e-05, "loss": 3.8878, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577512033507102e-05, "loss": 3.8746, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.57667343875605e-05, "loss": 3.8798, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575834844004998e-05, "loss": 3.8845, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574996249253946e-05, "loss": 3.8678, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741592923832666e-05, "loss": 3.8717, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733206976322146e-05, "loss": 3.8802, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724821028811626e-05, "loss": 3.8659, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716435081301106e-05, "loss": 3.8741, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708065512594315e-05, "loss": 3.877, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699679565083795e-05, "loss": 3.8804, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691293617573275e-05, "loss": 3.8654, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682907670062755e-05, "loss": 3.8729, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674521722552235e-05, "loss": 3.8635, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666135775041715e-05, "loss": 3.8706, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565776620633493e-05, "loss": 3.8838, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564938025882441e-05, "loss": 3.8726, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564099431131389e-05, "loss": 3.8857, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563260836380337e-05, "loss": 3.8829, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562422241629285e-05, "loss": 3.8807, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561583646878233e-05, "loss": 3.8587, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560746690007554e-05, "loss": 3.8802, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559908095256502e-05, "loss": 3.88, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.55906950050545e-05, "loss": 3.8682, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558230905754398e-05, "loss": 3.8723, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557393948883719e-05, "loss": 3.8757, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556555354132667e-05, "loss": 3.8862, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557167593816156e-05, "loss": 3.8682, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548781646305635e-05, "loss": 3.8554, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.5540395698795115e-05, "loss": 3.8659, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.5532009751284595e-05, "loss": 3.8692, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523623803774075e-05, "loss": 3.8733, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515237856263555e-05, "loss": 3.8716, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506884666360494e-05, "loss": 3.8633, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498498718849973e-05, "loss": 3.8651, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5490112771339453e-05, "loss": 3.8566, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481726823828933e-05, "loss": 3.8619, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547335725512214e-05, "loss": 3.8643, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546497130761162e-05, "loss": 3.874, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545658536010111e-05, "loss": 3.8876, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544819941259059e-05, "loss": 3.8652, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543981346508007e-05, "loss": 3.8551, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543142751756955e-05, "loss": 3.8634, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542305794886276e-05, "loss": 3.8626, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541467200135224e-05, "loss": 3.8715, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540628605384172e-05, "loss": 3.8632, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.53979001063312e-05, "loss": 3.8628, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538953053762441e-05, "loss": 3.86, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538114459011389e-05, "loss": 3.8693, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537275864260337e-05, "loss": 3.8437, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536437269509285e-05, "loss": 3.8578, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535598674758233e-05, "loss": 3.8515, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534761717887554e-05, "loss": 3.8658, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533923123136502e-05, "loss": 3.8533, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.53308452838545e-05, "loss": 3.8601, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322459336343976e-05, "loss": 3.8496, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314073388833456e-05, "loss": 3.854, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530570382012667e-05, "loss": 3.8578, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529731787261615e-05, "loss": 3.8584, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5288931925105625e-05, "loss": 3.8711, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280545977595105e-05, "loss": 3.8683, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527219278769205e-05, "loss": 3.8599, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526380684018153e-05, "loss": 3.8523, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255420892671017e-05, "loss": 3.854, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247034945160496e-05, "loss": 3.8594, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238648997649976e-05, "loss": 3.8487, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523026305013945e-05, "loss": 3.8553, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522187710262893e-05, "loss": 3.8524, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521349115511841e-05, "loss": 3.8505, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.5205121586411625e-05, "loss": 3.8498, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.51967356389011e-05, "loss": 3.8493, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518834969139058e-05, "loss": 3.8482, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517996374388006e-05, "loss": 3.8548, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517157779636954e-05, "loss": 3.8399, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.5163208227662754e-05, "loss": 3.8655, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.5154822280152234e-05, "loss": 3.8614, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.5146436332641714e-05, "loss": 3.8604, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5138050385131194e-05, "loss": 3.837, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.51296808164244e-05, "loss": 3.8552, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512129486891388e-05, "loss": 3.8589, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511290892140336e-05, "loss": 3.8573, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510452297389284e-05, "loss": 3.853, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509615340518605e-05, "loss": 3.8505, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508776745767553e-05, "loss": 3.8499, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507938151016501e-05, "loss": 3.8566, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507099556265449e-05, "loss": 3.8489, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506260961514397e-05, "loss": 3.8523, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505424004643719e-05, "loss": 3.851, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504585409892667e-05, "loss": 3.841, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503746815141615e-05, "loss": 3.8564, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502908220390563e-05, "loss": 3.852, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502071263519884e-05, "loss": 3.8479, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501232668768832e-05, "loss": 3.84, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.50039407401778e-05, "loss": 3.8408, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.911149501800537, "eval_runtime": 304.4711, "eval_samples_per_second": 1253.291, "eval_steps_per_second": 39.166, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499555479266728e-05, "loss": 3.8417, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498716884515676e-05, "loss": 3.8358, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497878289764624e-05, "loss": 3.847, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497039695013572e-05, "loss": 3.8454, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4962011002625197e-05, "loss": 3.8584, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953625055114677e-05, "loss": 3.8345, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945239107604156e-05, "loss": 3.8389, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.4936853160093636e-05, "loss": 3.8249, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492848359138685e-05, "loss": 3.8479, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492009764387633e-05, "loss": 3.8451, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491171169636581e-05, "loss": 3.8422, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.4903325748855285e-05, "loss": 3.8407, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.48949561801485e-05, "loss": 3.8305, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488657023263798e-05, "loss": 3.8387, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487818428512746e-05, "loss": 3.8254, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869798337616934e-05, "loss": 3.8346, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486142876891015e-05, "loss": 3.8314, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485304282139963e-05, "loss": 3.8305, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484465687388911e-05, "loss": 3.8355, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483627092637859e-05, "loss": 3.8528, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827901357671806e-05, "loss": 3.8316, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.4819515410161286e-05, "loss": 3.8376, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481112946265076e-05, "loss": 3.8319, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480274351514024e-05, "loss": 3.8397, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479435756762972e-05, "loss": 3.8269, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.4785987998922935e-05, "loss": 3.8384, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477760205141241e-05, "loss": 3.8295, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476921610390189e-05, "loss": 3.8259, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476083015639137e-05, "loss": 3.8194, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475246058768458e-05, "loss": 3.8265, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.4744074640174064e-05, "loss": 3.8325, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473570507146728e-05, "loss": 3.8362, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472731912395676e-05, "loss": 3.8364, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471893317644623e-05, "loss": 3.8328, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471054722893571e-05, "loss": 3.8264, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470216128142519e-05, "loss": 3.838, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469377533391467e-05, "loss": 3.824, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468538938640415e-05, "loss": 3.8242, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467700343889363e-05, "loss": 3.8115, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466863387018684e-05, "loss": 3.8263, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466024792267632e-05, "loss": 3.8215, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.46518619751658e-05, "loss": 3.8317, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464347602765528e-05, "loss": 3.8259, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.46351064589485e-05, "loss": 3.8145, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462672051143798e-05, "loss": 3.8299, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461833456392746e-05, "loss": 3.8243, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460994861641694e-05, "loss": 3.818, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.4601579047710146e-05, "loss": 3.811, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4593193100199626e-05, "loss": 3.8121, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584807152689106e-05, "loss": 3.8244, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576421205178586e-05, "loss": 3.8209, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4568051636471795e-05, "loss": 3.8171, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.4559665688961275e-05, "loss": 3.8098, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551279741450755e-05, "loss": 3.82, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542893793940235e-05, "loss": 3.8063, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453452422523345e-05, "loss": 3.8224, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452613827772293e-05, "loss": 3.8092, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451775233021241e-05, "loss": 3.8197, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450936638270189e-05, "loss": 3.8181, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.45009968139951e-05, "loss": 3.8123, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449261086648458e-05, "loss": 3.8067, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448422491897406e-05, "loss": 3.8184, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447583897146354e-05, "loss": 3.8032, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446746940275675e-05, "loss": 3.8108, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445908345524623e-05, "loss": 3.8181, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445069750773571e-05, "loss": 3.8167, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444231156022519e-05, "loss": 3.805, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.4433941991518405e-05, "loss": 3.8079, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.4425556044007885e-05, "loss": 3.8052, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.4417170096497365e-05, "loss": 3.8049, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.4408784148986845e-05, "loss": 3.8204, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400414580280054e-05, "loss": 3.8134, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.4392028632769534e-05, "loss": 3.825, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.4383642685259014e-05, "loss": 3.8221, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.4375256737748494e-05, "loss": 3.8214, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.43668871690417e-05, "loss": 3.8011, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435850122153118e-05, "loss": 3.8134, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435011527402066e-05, "loss": 3.8216, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434172932651014e-05, "loss": 3.8083, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433335975780336e-05, "loss": 3.8094, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432497381029284e-05, "loss": 3.8129, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431658786278232e-05, "loss": 3.8281, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.43082019152718e-05, "loss": 3.8089, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429983234656501e-05, "loss": 3.795, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429144639905449e-05, "loss": 3.8057, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.428306045154397e-05, "loss": 3.8111, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427467450403345e-05, "loss": 3.8137, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426628855652293e-05, "loss": 3.8146, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257918987816136e-05, "loss": 3.8016, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249533040305616e-05, "loss": 3.8054, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.4241147092795096e-05, "loss": 3.8025, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.4232761145284576e-05, "loss": 3.7991, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422439157657779e-05, "loss": 3.8068, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421600562906727e-05, "loss": 3.813, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420761968155675e-05, "loss": 3.8276, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419923373404623e-05, "loss": 3.8104, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419086416533944e-05, "loss": 3.794, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418247821782892e-05, "loss": 3.8053, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.41740922703184e-05, "loss": 3.8016, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416570632280788e-05, "loss": 3.814, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415733675410109e-05, "loss": 3.8096, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414895080659057e-05, "loss": 3.8048, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414056485908005e-05, "loss": 3.7996, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413217891156953e-05, "loss": 3.8103, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123809342862746e-05, "loss": 3.7881, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115423395352226e-05, "loss": 3.8032, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4107037447841706e-05, "loss": 3.7911, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098651500331186e-05, "loss": 3.8096, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090281931624395e-05, "loss": 3.7975, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081895984113875e-05, "loss": 3.8, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073510036603355e-05, "loss": 3.7932, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.4065124089092835e-05, "loss": 3.7995, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056754520386044e-05, "loss": 3.8015, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.4048368572875524e-05, "loss": 3.8002, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.4039982625365004e-05, "loss": 3.8142, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.4031596677854484e-05, "loss": 3.8119, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402324348795143e-05, "loss": 3.8039, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401485754044091e-05, "loss": 3.7973, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400647159293039e-05, "loss": 3.7993, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399808564541987e-05, "loss": 3.8063, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398969969790935e-05, "loss": 3.7871, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398131375039883e-05, "loss": 3.8015, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397292780288831e-05, "loss": 3.7911, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396454185537778e-05, "loss": 3.7985, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956172286671e-05, "loss": 3.7961, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394778633916048e-05, "loss": 3.7957, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393940039164996e-05, "loss": 3.7875, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393101444413944e-05, "loss": 3.7998, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392264487543265e-05, "loss": 3.787, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391425892792213e-05, "loss": 3.8083, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905872980411606e-05, "loss": 3.8018, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897487032901086e-05, "loss": 3.811, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3889101085390566e-05, "loss": 3.7797, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388073151668378e-05, "loss": 3.8007, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872345569173255e-05, "loss": 3.8022, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3863959621662735e-05, "loss": 3.8001, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.3855573674152215e-05, "loss": 3.7986, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3847204105445424e-05, "loss": 3.7983, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383881815793491e-05, "loss": 3.7936, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383043221042439e-05, "loss": 3.8048, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382204626291387e-05, "loss": 3.7887, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381367669420708e-05, "loss": 3.8003, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380529074669656e-05, "loss": 3.7963, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379690479918604e-05, "loss": 3.7886, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378851885167552e-05, "loss": 3.7971, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378014928296873e-05, "loss": 3.8021, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377176333545821e-05, "loss": 3.7943, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376337738794769e-05, "loss": 3.782, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375499144043717e-05, "loss": 3.7917, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.8861355781555176, "eval_runtime": 312.6961, "eval_samples_per_second": 1220.325, "eval_steps_per_second": 38.136, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374662187173038e-05, "loss": 3.7948, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.3738235924219865e-05, "loss": 3.7808, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.3729849976709345e-05, "loss": 3.7903, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721464029198824e-05, "loss": 3.7985, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.3713094460492034e-05, "loss": 3.7996, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.3704708512981514e-05, "loss": 3.7869, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.3696322565470993e-05, "loss": 3.7832, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.3687936617960473e-05, "loss": 3.7748, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367956704925368e-05, "loss": 3.7935, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367118110174316e-05, "loss": 3.7956, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366279515423264e-05, "loss": 3.7857, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365440920672212e-05, "loss": 3.7893, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364603963801533e-05, "loss": 3.7781, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363765369050482e-05, "loss": 3.7867, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36292677429943e-05, "loss": 3.7763, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362088179548378e-05, "loss": 3.782, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361251222677699e-05, "loss": 3.7758, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360412627926647e-05, "loss": 3.782, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359574033175595e-05, "loss": 3.7777, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358735438424543e-05, "loss": 3.7977, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.3578984815538636e-05, "loss": 3.7832, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.3570598868028116e-05, "loss": 3.7923, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.3562212920517596e-05, "loss": 3.778, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.3553826973007076e-05, "loss": 3.7883, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.3545457404300285e-05, "loss": 3.7725, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353707145678977e-05, "loss": 3.7863, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352868550927925e-05, "loss": 3.7817, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352029956176873e-05, "loss": 3.7705, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351192999306194e-05, "loss": 3.7677, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350354404555142e-05, "loss": 3.7745, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.34951580980409e-05, "loss": 3.7841, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348678852933411e-05, "loss": 3.7839, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347840258182359e-05, "loss": 3.7856, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.347001663431307e-05, "loss": 3.7864, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346163068680255e-05, "loss": 3.7769, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345324473929203e-05, "loss": 3.7851, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344485879178151e-05, "loss": 3.7764, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343647284427099e-05, "loss": 3.7748, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342808689676047e-05, "loss": 3.761, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419717328053685e-05, "loss": 3.7778, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411331380543165e-05, "loss": 3.7709, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402945433032645e-05, "loss": 3.7823, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394559485522125e-05, "loss": 3.776, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3386189916815334e-05, "loss": 3.7666, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377803969304814e-05, "loss": 3.7812, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369418021794294e-05, "loss": 3.7703, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3361032074283774e-05, "loss": 3.771, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.3352662505576983e-05, "loss": 3.7632, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334427655806646e-05, "loss": 3.7616, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333589061055594e-05, "loss": 3.7734, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332750466304542e-05, "loss": 3.7727, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331913509433864e-05, "loss": 3.7668, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331074914682812e-05, "loss": 3.7635, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.33023631993176e-05, "loss": 3.7719, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329397725180708e-05, "loss": 3.7532, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328560768310029e-05, "loss": 3.7753, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327722173558977e-05, "loss": 3.7627, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326883578807925e-05, "loss": 3.77, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326044984056873e-05, "loss": 3.7689, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325208027186194e-05, "loss": 3.7657, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324369432435142e-05, "loss": 3.7577, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.32353083768409e-05, "loss": 3.7683, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322692242933038e-05, "loss": 3.7603, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321855286062359e-05, "loss": 3.7599, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321016691311307e-05, "loss": 3.77, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320178096560255e-05, "loss": 3.7672, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319339501809203e-05, "loss": 3.7547, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318502544938524e-05, "loss": 3.7652, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317663950187472e-05, "loss": 3.7549, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.31682535543642e-05, "loss": 3.7574, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315986760685368e-05, "loss": 3.7741, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315149803814689e-05, "loss": 3.7676, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314311209063637e-05, "loss": 3.7736, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313472614312585e-05, "loss": 3.7706, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312634019561533e-05, "loss": 3.7784, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.3117970626908546e-05, "loss": 3.758, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.3109584679398026e-05, "loss": 3.763, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.3101198731887506e-05, "loss": 3.7736, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309281278437698e-05, "loss": 3.7586, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.3084443215670195e-05, "loss": 3.767, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3076057268159675e-05, "loss": 3.7684, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067671320649155e-05, "loss": 3.7712, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305928537313863e-05, "loss": 3.7629, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050915804431844e-05, "loss": 3.751, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042529856921324e-05, "loss": 3.7577, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3034143909410804e-05, "loss": 3.7627, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025757961900284e-05, "loss": 3.7668, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.30173883931935e-05, "loss": 3.765, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300900244568298e-05, "loss": 3.7584, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300061649817245e-05, "loss": 3.7604, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299223055066193e-05, "loss": 3.7539, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298386098195515e-05, "loss": 3.753, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297547503444463e-05, "loss": 3.7581, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.29670890869341e-05, "loss": 3.7689, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295870313942358e-05, "loss": 3.7829, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.29503335707168e-05, "loss": 3.7669, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294194762320628e-05, "loss": 3.7458, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293356167569576e-05, "loss": 3.7632, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292517572818524e-05, "loss": 3.7575, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.2916806159478454e-05, "loss": 3.7675, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290842021196793e-05, "loss": 3.7612, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.290003426445741e-05, "loss": 3.7595, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289164831694689e-05, "loss": 3.7568, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.28832787482401e-05, "loss": 3.7605, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.2874892800729576e-05, "loss": 3.7473, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.2866506853219056e-05, "loss": 3.7582, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.2858120905708536e-05, "loss": 3.7445, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284975133700175e-05, "loss": 3.767, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.2841365389491225e-05, "loss": 3.7512, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283297944198071e-05, "loss": 3.7535, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282459349447019e-05, "loss": 3.7451, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.28162239257634e-05, "loss": 3.7586, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807854357056617e-05, "loss": 3.7558, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2799468409546097e-05, "loss": 3.7561, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2791082462035576e-05, "loss": 3.7681, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278269651452505e-05, "loss": 3.768, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.2774326945818266e-05, "loss": 3.7595, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.2765940998307746e-05, "loss": 3.7543, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.2757555050797225e-05, "loss": 3.7512, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.27491691032867e-05, "loss": 3.763, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274078315577618e-05, "loss": 3.7453, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2732397208265665e-05, "loss": 3.7556, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.2724011260755145e-05, "loss": 3.7444, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.2715625313244625e-05, "loss": 3.7556, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2707255744537834e-05, "loss": 3.7448, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.2698869797027314e-05, "loss": 3.7519, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.2690483849516794e-05, "loss": 3.7497, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.2682097902006274e-05, "loss": 3.7507, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267372833329948e-05, "loss": 3.7474, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266534238578896e-05, "loss": 3.7612, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265695643827844e-05, "loss": 3.7609, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264857049076792e-05, "loss": 3.7643, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.264020092206113e-05, "loss": 3.737, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263181497455062e-05, "loss": 3.7586, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.26234290270401e-05, "loss": 3.7593, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261504307952958e-05, "loss": 3.7608, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260667351082279e-05, "loss": 3.7521, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259828756331227e-05, "loss": 3.7576, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258990161580175e-05, "loss": 3.752, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258151566829123e-05, "loss": 3.7643, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257314609958444e-05, "loss": 3.7415, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256476015207392e-05, "loss": 3.7599, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.25563742045634e-05, "loss": 3.7492, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254798825705288e-05, "loss": 3.75, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539618688346086e-05, "loss": 3.7538, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253123274083557e-05, "loss": 3.7514, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252284679332505e-05, "loss": 3.7579, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251446084581453e-05, "loss": 3.7368, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250609127710774e-05, "loss": 3.7492, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.870025873184204, "eval_runtime": 311.8832, "eval_samples_per_second": 1223.506, "eval_steps_per_second": 38.235, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249770532959722e-05, "loss": 3.7486, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.24893193820867e-05, "loss": 3.7375, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248093343457618e-05, "loss": 3.7494, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247254748706566e-05, "loss": 3.7556, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.246416153955514e-05, "loss": 3.7598, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245577559204462e-05, "loss": 3.7433, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.24473896445341e-05, "loss": 3.7378, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243900369702358e-05, "loss": 3.7373, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243063412831679e-05, "loss": 3.7457, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242224818080627e-05, "loss": 3.754, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241386223329575e-05, "loss": 3.7441, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240547628578524e-05, "loss": 3.7487, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.2397123095882175e-05, "loss": 3.7395, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.2388737148371655e-05, "loss": 3.7413, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2380351200861135e-05, "loss": 3.7373, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.2371965253350615e-05, "loss": 3.7386, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.2363579305840095e-05, "loss": 3.7358, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.2355193358329575e-05, "loss": 3.7379, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.2346807410819055e-05, "loss": 3.7398, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233842146330853e-05, "loss": 3.7557, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2330051894601744e-05, "loss": 3.7425, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321665947091224e-05, "loss": 3.7498, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313279999580704e-05, "loss": 3.7353, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304894052070184e-05, "loss": 3.747, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.22965244833634e-05, "loss": 3.732, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228813853585288e-05, "loss": 3.7473, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227975258834236e-05, "loss": 3.738, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.227136664083183e-05, "loss": 3.73, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226299707212505e-05, "loss": 3.7331, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.225461112461453e-05, "loss": 3.7356, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246225177104e-05, "loss": 3.7409, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223785560839722e-05, "loss": 3.7437, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.22294696608867e-05, "loss": 3.7454, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222108371337618e-05, "loss": 3.7489, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221269776586566e-05, "loss": 3.7298, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220431181835514e-05, "loss": 3.7472, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219592587084462e-05, "loss": 3.7395, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.21875399233341e-05, "loss": 3.7275, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217915397582358e-05, "loss": 3.7235, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.2170784407116787e-05, "loss": 3.7309, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.2162398459606267e-05, "loss": 3.7346, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.2154012512095746e-05, "loss": 3.7406, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.2145626564585226e-05, "loss": 3.7342, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137256995878436e-05, "loss": 3.7285, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128871048367915e-05, "loss": 3.744, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120485100857395e-05, "loss": 3.7312, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211209915334688e-05, "loss": 3.7314, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210372958464009e-05, "loss": 3.7234, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209534363712957e-05, "loss": 3.7209, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208695768961905e-05, "loss": 3.7354, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207858812091226e-05, "loss": 3.7341, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.207020217340174e-05, "loss": 3.7296, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206181622589122e-05, "loss": 3.7236, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.20534302783807e-05, "loss": 3.7344, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204506070967391e-05, "loss": 3.7114, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203667476216339e-05, "loss": 3.7351, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202828881465287e-05, "loss": 3.7224, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201990286714235e-05, "loss": 3.7243, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.2011533298435565e-05, "loss": 3.7333, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.2003147350925045e-05, "loss": 3.7236, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994761403414525e-05, "loss": 3.7212, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.1986375455904005e-05, "loss": 3.7366, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.1978005887197214e-05, "loss": 3.7179, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969619939686694e-05, "loss": 3.7221, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1961233992176174e-05, "loss": 3.731, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952848044665654e-05, "loss": 3.7287, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194447847595886e-05, "loss": 3.7156, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193609252844834e-05, "loss": 3.7266, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192770658093782e-05, "loss": 3.7142, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.19193206334273e-05, "loss": 3.7181, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191095106472052e-05, "loss": 3.7317, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190256511721e-05, "loss": 3.7287, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189417916969948e-05, "loss": 3.7368, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188579322218896e-05, "loss": 3.7295, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187742365348217e-05, "loss": 3.7421, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186903770597165e-05, "loss": 3.7186, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186065175846113e-05, "loss": 3.7279, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185226581095061e-05, "loss": 3.735, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.1843896242243817e-05, "loss": 3.7173, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.1835510294733297e-05, "loss": 3.7279, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.1827124347222776e-05, "loss": 3.7319, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.1818738399712256e-05, "loss": 3.7352, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181036883100547e-05, "loss": 3.7244, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180198288349495e-05, "loss": 3.7159, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179359693598443e-05, "loss": 3.7177, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178521098847391e-05, "loss": 3.724, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177684141976712e-05, "loss": 3.7313, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.17684554722566e-05, "loss": 3.727, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.176006952474608e-05, "loss": 3.7257, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175168357723556e-05, "loss": 3.7141, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174331400852877e-05, "loss": 3.7191, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7169, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172654211350773e-05, "loss": 3.7203, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171815616599721e-05, "loss": 3.732, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709786597290426e-05, "loss": 3.7411, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.7295, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1693014702269386e-05, "loss": 3.7137, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684628754758866e-05, "loss": 3.7216, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.1676259186052075e-05, "loss": 3.7206, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.1667873238541555e-05, "loss": 3.7293, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659487291031035e-05, "loss": 3.7235, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.1651101343520515e-05, "loss": 3.7283, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642731774813724e-05, "loss": 3.721, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1634345827303204e-05, "loss": 3.7178, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625959879792684e-05, "loss": 3.7159, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1617573932282164e-05, "loss": 3.7181, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160920436357538e-05, "loss": 3.7083, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160081841606486e-05, "loss": 3.7296, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159243246855434e-05, "loss": 3.7144, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158404652104382e-05, "loss": 3.7167, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.157567695233703e-05, "loss": 3.7119, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156729100482651e-05, "loss": 3.7168, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155892143611972e-05, "loss": 3.723, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.15505354886092e-05, "loss": 3.7177, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154214954109868e-05, "loss": 3.7331, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153376359358816e-05, "loss": 3.7268, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152539402488137e-05, "loss": 3.7236, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151700807737085e-05, "loss": 3.7203, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150862212986033e-05, "loss": 3.708, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150023618234981e-05, "loss": 3.7306, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149185023483929e-05, "loss": 3.7148, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148346428732877e-05, "loss": 3.7174, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147507833981825e-05, "loss": 3.7092, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146669239230773e-05, "loss": 3.7166, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145832282360094e-05, "loss": 3.7101, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144993687609042e-05, "loss": 3.7163, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.14415509285799e-05, "loss": 3.7112, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143316498106938e-05, "loss": 3.72, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.142479541236259e-05, "loss": 3.7095, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141640946485207e-05, "loss": 3.7268, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140802351734155e-05, "loss": 3.7215, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139963756983103e-05, "loss": 3.7287, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139126800112425e-05, "loss": 3.7026, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138288205361373e-05, "loss": 3.7242, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137449610610321e-05, "loss": 3.722, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136611015859268e-05, "loss": 3.7215, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357740589885896e-05, "loss": 3.7198, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1349354642375376e-05, "loss": 3.7194, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340968694864856e-05, "loss": 3.7122, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133258274735433e-05, "loss": 3.7343, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.1324213178647545e-05, "loss": 3.7032, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315827231137025e-05, "loss": 3.7234, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307441283626505e-05, "loss": 3.7141, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1299055336115985e-05, "loss": 3.7143, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.12906857674092e-05, "loss": 3.7175, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128229981989868e-05, "loss": 3.7137, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273913872388154e-05, "loss": 3.7243, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265527924877634e-05, "loss": 3.6976, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125715835617085e-05, "loss": 3.7159, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.86078143119812, "eval_runtime": 306.4804, "eval_samples_per_second": 1245.075, "eval_steps_per_second": 38.91, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.124877240866032e-05, "loss": 3.7148, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.12403864611498e-05, "loss": 3.7035, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.123200051363928e-05, "loss": 3.7123, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.12236309449325e-05, "loss": 3.7168, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121524499742198e-05, "loss": 3.7243, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120685904991146e-05, "loss": 3.7105, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119847310240094e-05, "loss": 3.7044, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.1190103533694154e-05, "loss": 3.7024, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118171758618363e-05, "loss": 3.7122, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117333163867311e-05, "loss": 3.7169, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116494569116259e-05, "loss": 3.7101, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.1156576122455796e-05, "loss": 3.7129, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114820655374901e-05, "loss": 3.7087, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.113982060623849e-05, "loss": 3.706, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113143465872797e-05, "loss": 3.6996, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112304871121745e-05, "loss": 3.7014, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.111466276370693e-05, "loss": 3.7049, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110627681619641e-05, "loss": 3.7022, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109789086868589e-05, "loss": 3.707, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108950492117537e-05, "loss": 3.7162, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108113535246858e-05, "loss": 3.7117, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.107274940495806e-05, "loss": 3.7145, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106436345744754e-05, "loss": 3.7025, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105597750993702e-05, "loss": 3.711, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104760794123023e-05, "loss": 3.699, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103922199371971e-05, "loss": 3.7161, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103083604620919e-05, "loss": 3.6991, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102245009869867e-05, "loss": 3.6975, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.1014080529991886e-05, "loss": 3.6992, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005694582481366e-05, "loss": 3.7006, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0997308634970846e-05, "loss": 3.7038, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.0988939066264055e-05, "loss": 3.7108, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0980553118753535e-05, "loss": 3.7119, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0972167171243015e-05, "loss": 3.7074, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963781223732495e-05, "loss": 3.7017, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0955395276221975e-05, "loss": 3.7123, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0947009328711455e-05, "loss": 3.7085, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938623381200935e-05, "loss": 3.6903, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0930237433690414e-05, "loss": 3.6925, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.0921867864983624e-05, "loss": 3.6972, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913481917473104e-05, "loss": 3.7005, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0905095969962583e-05, "loss": 3.7064, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.089671002245207e-05, "loss": 3.7013, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088834045374528e-05, "loss": 3.6955, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087995450623476e-05, "loss": 3.7068, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087156855872424e-05, "loss": 3.7003, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086319899001745e-05, "loss": 3.7022, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085481304250693e-05, "loss": 3.6876, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084642709499641e-05, "loss": 3.6845, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083804114748589e-05, "loss": 3.7073, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.08296715787791e-05, "loss": 3.6961, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082128563126858e-05, "loss": 3.7004, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081289968375806e-05, "loss": 3.6926, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080453011505127e-05, "loss": 3.6947, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079614416754075e-05, "loss": 3.6815, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078775822003023e-05, "loss": 3.6985, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077937227251971e-05, "loss": 3.6933, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077098632500919e-05, "loss": 3.6922, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076260037749867e-05, "loss": 3.7058, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075421442998815e-05, "loss": 3.6897, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074582848247763e-05, "loss": 3.6866, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.073745891377084e-05, "loss": 3.7037, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.072907296626032e-05, "loss": 3.6874, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.07206870187498e-05, "loss": 3.684, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071230107123928e-05, "loss": 3.7002, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070393150253249e-05, "loss": 3.6963, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069554555502198e-05, "loss": 3.6823, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068715960751146e-05, "loss": 3.6971, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067877366000094e-05, "loss": 3.6826, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.0670404091294147e-05, "loss": 3.6845, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.0662018143783627e-05, "loss": 3.7016, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.0653632196273106e-05, "loss": 3.6976, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064524624876258e-05, "loss": 3.6996, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.0636876680055796e-05, "loss": 3.6974, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.0628490732545275e-05, "loss": 3.712, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.0620104785034755e-05, "loss": 3.6886, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061171883752423e-05, "loss": 3.6973, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0603349268817444e-05, "loss": 3.7027, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.059496332130693e-05, "loss": 3.6868, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586577373796404e-05, "loss": 3.6949, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0578191426285884e-05, "loss": 3.7014, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.0569805478775364e-05, "loss": 3.7022, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.0561419531264844e-05, "loss": 3.6951, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.0553033583754324e-05, "loss": 3.6839, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.0544647636243804e-05, "loss": 3.6812, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053627806753701e-05, "loss": 3.694, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052789212002649e-05, "loss": 3.7022, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.051950617251597e-05, "loss": 3.6966, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051112022500545e-05, "loss": 3.6949, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050275065629867e-05, "loss": 3.6785, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049436470878815e-05, "loss": 3.6896, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048597876127763e-05, "loss": 3.6875, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047760919257084e-05, "loss": 3.6931, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046922324506032e-05, "loss": 3.6961, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.04608372975498e-05, "loss": 3.71, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045245135003928e-05, "loss": 3.6967, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044408178133249e-05, "loss": 3.6833, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043569583382197e-05, "loss": 3.6874, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042730988631145e-05, "loss": 3.6903, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041892393880093e-05, "loss": 3.6982, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.0410554370094136e-05, "loss": 3.6927, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040216842258362e-05, "loss": 3.6983, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.03937824750731e-05, "loss": 3.6884, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038539652756258e-05, "loss": 3.679, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037702695885579e-05, "loss": 3.6903, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036864101134527e-05, "loss": 3.6842, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036025506383475e-05, "loss": 3.6804, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035186911632423e-05, "loss": 3.6942, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034349954761744e-05, "loss": 3.6865, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033511360010692e-05, "loss": 3.6832, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032674403140013e-05, "loss": 3.6837, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031835808388961e-05, "loss": 3.6812, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030997213637909e-05, "loss": 3.6932, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.0301586188868576e-05, "loss": 3.6852, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.0293200241358056e-05, "loss": 3.7032, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284814293847536e-05, "loss": 3.6979, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.0276428346337016e-05, "loss": 3.6945, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.0268058777630225e-05, "loss": 3.6873, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.0259672830119705e-05, "loss": 3.6773, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.0251286882609185e-05, "loss": 3.692, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.0242900935098665e-05, "loss": 3.6877, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.0234514987588145e-05, "loss": 3.6847, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0226129040077625e-05, "loss": 3.6785, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217743092567105e-05, "loss": 3.6875, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209373523860314e-05, "loss": 3.679, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.0200987576349794e-05, "loss": 3.6874, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.0192601628839274e-05, "loss": 3.6797, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.0184215681328754e-05, "loss": 3.6921, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017584611262197e-05, "loss": 3.6763, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016746016511145e-05, "loss": 3.6976, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015907421760093e-05, "loss": 3.6896, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015068827009041e-05, "loss": 3.6982, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014231870138362e-05, "loss": 3.6741, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.01339327538731e-05, "loss": 3.6936, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012554680636258e-05, "loss": 3.6907, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011716085885206e-05, "loss": 3.6937, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010879129014527e-05, "loss": 3.6887, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010040534263475e-05, "loss": 3.6848, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009201939512423e-05, "loss": 3.6861, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008363344761371e-05, "loss": 3.7015, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.0075263878906924e-05, "loss": 3.6739, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.0066877931396404e-05, "loss": 3.6915, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005850836268961e-05, "loss": 3.6876, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.005012241517909e-05, "loss": 3.6827, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.004173646766857e-05, "loss": 3.688, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003335052015805e-05, "loss": 3.6816, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002496457264753e-05, "loss": 3.6942, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.0016578625137006e-05, "loss": 3.6676, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000820905643022e-05, "loss": 3.6895, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.852648973464966, "eval_runtime": 304.8314, "eval_samples_per_second": 1251.81, "eval_steps_per_second": 39.12, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.99998231089197e-05, "loss": 3.679, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999143716140918e-05, "loss": 3.6764, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.998305121389866e-05, "loss": 3.6814, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997466526638814e-05, "loss": 3.6864, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996627931887762e-05, "loss": 3.6968, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.99578933713671e-05, "loss": 3.6777, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994950742385658e-05, "loss": 3.679, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994112147634606e-05, "loss": 3.6751, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993275190763927e-05, "loss": 3.6782, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992436596012875e-05, "loss": 3.6901, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991598001261823e-05, "loss": 3.6769, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990759406510771e-05, "loss": 3.6859, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.9899240875204655e-05, "loss": 3.6761, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.9890854927694135e-05, "loss": 3.6745, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.9882468980183615e-05, "loss": 3.6738, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.9874083032673095e-05, "loss": 3.6706, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.9865697085162575e-05, "loss": 3.6736, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.9857311137652055e-05, "loss": 3.673, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.9848925190141535e-05, "loss": 3.6769, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840539242631015e-05, "loss": 3.6839, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9832169673924224e-05, "loss": 3.6827, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823783726413704e-05, "loss": 3.6876, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815397778903184e-05, "loss": 3.6734, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9807011831392664e-05, "loss": 3.6794, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979864226268587e-05, "loss": 3.6717, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979025631517535e-05, "loss": 3.6855, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978187036766484e-05, "loss": 3.673, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977348442015432e-05, "loss": 3.6712, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.976511485144753e-05, "loss": 3.6698, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975672890393701e-05, "loss": 3.6696, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974834295642649e-05, "loss": 3.671, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.97399733877197e-05, "loss": 3.6843, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973158744020918e-05, "loss": 3.6793, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972320149269866e-05, "loss": 3.6799, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971481554518814e-05, "loss": 3.6713, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970642959767762e-05, "loss": 3.6848, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.9698060028970827e-05, "loss": 3.6779, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.9689674081460306e-05, "loss": 3.6626, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968128813394979e-05, "loss": 3.6656, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967290218643927e-05, "loss": 3.6673, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966451623892875e-05, "loss": 3.6706, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965613029141823e-05, "loss": 3.6777, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964776072271144e-05, "loss": 3.6745, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963937477520092e-05, "loss": 3.6669, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.96309888276904e-05, "loss": 3.6792, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962260288017988e-05, "loss": 3.6688, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961421693266936e-05, "loss": 3.6761, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960583098515884e-05, "loss": 3.6596, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.9597445037648315e-05, "loss": 3.6504, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958907546894153e-05, "loss": 3.6809, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958068952143101e-05, "loss": 3.6676, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957230357392049e-05, "loss": 3.6744, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956391762640997e-05, "loss": 3.6665, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955554805770319e-05, "loss": 3.6621, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954716211019267e-05, "loss": 3.6573, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.9538792541485876e-05, "loss": 3.6705, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.9530406593975356e-05, "loss": 3.6624, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9522020646464836e-05, "loss": 3.6672, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.9513634698954316e-05, "loss": 3.6782, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950524875144379e-05, "loss": 3.6583, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949686280393327e-05, "loss": 3.6589, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.948847685642275e-05, "loss": 3.6767, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.948009090891223e-05, "loss": 3.6577, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.9471721340205445e-05, "loss": 3.6584, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.9463335392694925e-05, "loss": 3.6747, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.9454949445184404e-05, "loss": 3.6651, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.9446563497673884e-05, "loss": 3.6549, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.9438193928967094e-05, "loss": 3.6678, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.9429807981456573e-05, "loss": 3.6568, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.9421422033946053e-05, "loss": 3.6547, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.9413036086435533e-05, "loss": 3.6722, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.940466651772874e-05, "loss": 3.6687, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939628057021822e-05, "loss": 3.6699, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938791100151144e-05, "loss": 3.6703, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937952505400092e-05, "loss": 3.6853, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.93711391064904e-05, "loss": 3.6607, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936275315897988e-05, "loss": 3.6702, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935438359027309e-05, "loss": 3.6704, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934599764276257e-05, "loss": 3.6612, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933761169525205e-05, "loss": 3.6635, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932922574774153e-05, "loss": 3.6777, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932083980023101e-05, "loss": 3.6714, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931245385272049e-05, "loss": 3.6723, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.9304084284013696e-05, "loss": 3.6547, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295698336503176e-05, "loss": 3.6505, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287312388992656e-05, "loss": 3.6692, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.9278926441482136e-05, "loss": 3.6738, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.9270540493971616e-05, "loss": 3.6682, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.92621545464611e-05, "loss": 3.6671, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925376859895058e-05, "loss": 3.6509, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924539903024379e-05, "loss": 3.6627, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.923701308273327e-05, "loss": 3.6599, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922862713522275e-05, "loss": 3.6609, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922024118771223e-05, "loss": 3.6728, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921187161900544e-05, "loss": 3.6787, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920348567149492e-05, "loss": 3.6731, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.91950997239844e-05, "loss": 3.6589, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918671377647388e-05, "loss": 3.6566, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917832782896336e-05, "loss": 3.6643, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916994188145284e-05, "loss": 3.6717, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.9161572312746056e-05, "loss": 3.6642, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.9153186365235536e-05, "loss": 3.6721, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9144800417725016e-05, "loss": 3.6644, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9136414470214496e-05, "loss": 3.6549, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9128028522703976e-05, "loss": 3.6621, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911964257519345e-05, "loss": 3.6562, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.9111273006486665e-05, "loss": 3.6547, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.9102887058976145e-05, "loss": 3.6659, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.9094501111465625e-05, "loss": 3.6626, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.90861151639551e-05, "loss": 3.6565, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.9077745595248314e-05, "loss": 3.6532, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.9069359647737794e-05, "loss": 3.6525, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.9060973700227274e-05, "loss": 3.6655, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.9052587752716754e-05, "loss": 3.6569, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.9044201805206234e-05, "loss": 3.6775, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.9035815857695714e-05, "loss": 3.6738, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9027429910185194e-05, "loss": 3.6653, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.90190603414784e-05, "loss": 3.6597, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901067439396788e-05, "loss": 3.6547, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900228844645736e-05, "loss": 3.666, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.899390249894684e-05, "loss": 3.6583, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898553293024005e-05, "loss": 3.6587, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897714698272953e-05, "loss": 3.6537, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.896876103521901e-05, "loss": 3.663, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.896037508770849e-05, "loss": 3.6552, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.895198914019798e-05, "loss": 3.6584, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.894360319268746e-05, "loss": 3.6503, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893521724517694e-05, "loss": 3.6657, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892683129766642e-05, "loss": 3.6508, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891846172895963e-05, "loss": 3.6669, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.891007578144911e-05, "loss": 3.6641, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.890168983393859e-05, "loss": 3.671, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889330388642807e-05, "loss": 3.6497, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.888491793891755e-05, "loss": 3.668, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.887653199140703e-05, "loss": 3.6582, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.886814604389651e-05, "loss": 3.6667, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859776475189716e-05, "loss": 3.6675, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8851390527679196e-05, "loss": 3.6556, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.8843004580168676e-05, "loss": 3.6604, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.8834618632658156e-05, "loss": 3.6736, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882624906395137e-05, "loss": 3.6489, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881786311644085e-05, "loss": 3.6629, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880949354773406e-05, "loss": 3.6651, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880110760022354e-05, "loss": 3.6599, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879272165271302e-05, "loss": 3.6561, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.87843357052025e-05, "loss": 3.6558, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877594975769198e-05, "loss": 3.6673, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876756381018146e-05, "loss": 3.6453, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875919424147467e-05, "loss": 3.6619, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.8480799198150635, "eval_runtime": 305.5345, "eval_samples_per_second": 1248.929, "eval_steps_per_second": 39.03, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875080829396415e-05, "loss": 3.6553, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874242234645363e-05, "loss": 3.6492, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873403639894311e-05, "loss": 3.652, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872565045143259e-05, "loss": 3.6612, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871726450392207e-05, "loss": 3.6727, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870887855641155e-05, "loss": 3.6521, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.870050898770476e-05, "loss": 3.651, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.869212304019424e-05, "loss": 3.6542, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.868373709268372e-05, "loss": 3.6464, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.86753511451732e-05, "loss": 3.6665, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.866696519766268e-05, "loss": 3.6496, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865857925015216e-05, "loss": 3.6546, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.865020968144537e-05, "loss": 3.6611, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864182373393485e-05, "loss": 3.6437, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.8633437786424334e-05, "loss": 3.6451, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.8625051838913814e-05, "loss": 3.6449, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.8616665891403294e-05, "loss": 3.6483, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.8608279943892774e-05, "loss": 3.6517, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.8599893996382254e-05, "loss": 3.647, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.8591508048871734e-05, "loss": 3.6558, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858313848016494e-05, "loss": 3.6602, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.857475253265442e-05, "loss": 3.6631, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.85663665851439e-05, "loss": 3.6533, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.855798063763338e-05, "loss": 3.6463, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.854962744773032e-05, "loss": 3.6483, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.85412415002198e-05, "loss": 3.6594, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.853285555270929e-05, "loss": 3.651, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.852446960519877e-05, "loss": 3.6474, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.851608365768825e-05, "loss": 3.6426, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.850769771017773e-05, "loss": 3.6444, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.849931176266721e-05, "loss": 3.6422, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849094219396042e-05, "loss": 3.662, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.84825562464499e-05, "loss": 3.6573, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.847417029893938e-05, "loss": 3.6535, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846578435142886e-05, "loss": 3.6459, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845739840391834e-05, "loss": 3.6499, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.8449028835211546e-05, "loss": 3.6588, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.8440642887701026e-05, "loss": 3.6398, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.8432256940190506e-05, "loss": 3.6432, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.8423870992679986e-05, "loss": 3.6389, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.84155014239732e-05, "loss": 3.644, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840711547646268e-05, "loss": 3.6528, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839872952895216e-05, "loss": 3.6479, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.839034358144164e-05, "loss": 3.6438, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.838195763393112e-05, "loss": 3.6525, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837358806522433e-05, "loss": 3.6463, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836520211771381e-05, "loss": 3.6465, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835681617020329e-05, "loss": 3.6396, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834843022269277e-05, "loss": 3.6196, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.8340044275182244e-05, "loss": 3.66, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.8331658327671724e-05, "loss": 3.6403, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832328875896494e-05, "loss": 3.6546, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831490281145442e-05, "loss": 3.637, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.83065168639439e-05, "loss": 3.6405, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.829813091643338e-05, "loss": 3.6324, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.8289761347726595e-05, "loss": 3.6414, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.828137540021607e-05, "loss": 3.6376, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827298945270555e-05, "loss": 3.6423, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826460350519503e-05, "loss": 3.6543, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.825621755768451e-05, "loss": 3.6342, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824784798897772e-05, "loss": 3.6339, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.82394620414672e-05, "loss": 3.6527, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.823107609395668e-05, "loss": 3.6355, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822269014644616e-05, "loss": 3.6304, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.8214304198935644e-05, "loss": 3.6462, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.8205918251425124e-05, "loss": 3.642, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.8197532303914604e-05, "loss": 3.6311, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.8189146356404084e-05, "loss": 3.6434, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.818077678769729e-05, "loss": 3.632, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.817239084018677e-05, "loss": 3.6341, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.816400489267625e-05, "loss": 3.6472, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.815563532396946e-05, "loss": 3.6441, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.814724937645894e-05, "loss": 3.6478, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.813886342894842e-05, "loss": 3.645, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.81304774814379e-05, "loss": 3.66, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.812209153392738e-05, "loss": 3.6339, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.81137219652206e-05, "loss": 3.6511, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810533601771008e-05, "loss": 3.6416, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.809695007019956e-05, "loss": 3.6401, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808856412268904e-05, "loss": 3.6393, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808017817517852e-05, "loss": 3.6535, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.8071808606471727e-05, "loss": 3.6452, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.8063422658961207e-05, "loss": 3.6487, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.8055036711450686e-05, "loss": 3.6281, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.8046650763940166e-05, "loss": 3.6303, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.8038264816429646e-05, "loss": 3.6438, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.8029895247722855e-05, "loss": 3.6487, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.8021509300212335e-05, "loss": 3.6385, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8013123352701815e-05, "loss": 3.6482, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.8004737405191295e-05, "loss": 3.6293, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.799635145768078e-05, "loss": 3.6378, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.7987965510170255e-05, "loss": 3.6375, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.7979579562659735e-05, "loss": 3.6356, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.7971193615149215e-05, "loss": 3.6478, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.796282404644243e-05, "loss": 3.6543, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.7954438098931904e-05, "loss": 3.6487, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.7946052151421384e-05, "loss": 3.6334, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.7937666203910864e-05, "loss": 3.6336, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.7929280256400344e-05, "loss": 3.642, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.7920894308889824e-05, "loss": 3.6447, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791252474018303e-05, "loss": 3.641, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790413879267252e-05, "loss": 3.6469, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.7895752845162e-05, "loss": 3.6426, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788736689765148e-05, "loss": 3.6326, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.787898095014096e-05, "loss": 3.6363, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.787061138143417e-05, "loss": 3.632, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.786222543392365e-05, "loss": 3.6323, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.785383948641313e-05, "loss": 3.6448, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.784545353890261e-05, "loss": 3.6392, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.783706759139209e-05, "loss": 3.6315, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.78286980226853e-05, "loss": 3.6316, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.782031207517478e-05, "loss": 3.6243, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.781192612766426e-05, "loss": 3.643, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.780354018015374e-05, "loss": 3.6321, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.779515423264322e-05, "loss": 3.6528, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.7786768285132704e-05, "loss": 3.6466, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.7778382337622184e-05, "loss": 3.6484, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.777001276891539e-05, "loss": 3.6361, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.776162682140487e-05, "loss": 3.6316, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.775324087389435e-05, "loss": 3.643, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.774485492638383e-05, "loss": 3.6386, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.773648535767704e-05, "loss": 3.6316, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.772809941016652e-05, "loss": 3.6272, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.7719713462656e-05, "loss": 3.6393, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771132751514548e-05, "loss": 3.6328, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770294156763496e-05, "loss": 3.6332, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769457199892817e-05, "loss": 3.632, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768618605141765e-05, "loss": 3.6378, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767780010390714e-05, "loss": 3.6296, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.766941415639662e-05, "loss": 3.6435, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766104458768983e-05, "loss": 3.6363, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765265864017931e-05, "loss": 3.6522, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764427269266879e-05, "loss": 3.6236, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.763588674515827e-05, "loss": 3.6435, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.7627517176451476e-05, "loss": 3.634, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.7619131228940956e-05, "loss": 3.6454, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.7610745281430436e-05, "loss": 3.6387, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760235933391991e-05, "loss": 3.6324, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759397338640939e-05, "loss": 3.637, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.7585587438898876e-05, "loss": 3.656, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.757721787019209e-05, "loss": 3.6242, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.7568831922681565e-05, "loss": 3.6436, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.7560445975171045e-05, "loss": 3.6398, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.7552060027660525e-05, "loss": 3.6352, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.7543690458953734e-05, "loss": 3.6313, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.7535304511443214e-05, "loss": 3.6337, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.7526918563932694e-05, "loss": 3.6391, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.7518532616422174e-05, "loss": 3.6303, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.751016304771538e-05, "loss": 3.6343, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.8460195064544678, "eval_runtime": 303.7551, "eval_samples_per_second": 1256.246, "eval_steps_per_second": 39.259, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.750177710020486e-05, "loss": 3.6265, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.749339115269434e-05, "loss": 3.6267, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.748500520518383e-05, "loss": 3.6292, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.747661925767331e-05, "loss": 3.6421, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.746823331016279e-05, "loss": 3.6467, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.7459863741456e-05, "loss": 3.6299, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.745147779394548e-05, "loss": 3.6303, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.744309184643496e-05, "loss": 3.6294, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.743470589892444e-05, "loss": 3.6261, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742633633021765e-05, "loss": 3.6404, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.741795038270713e-05, "loss": 3.6274, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.740956443519661e-05, "loss": 3.6344, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.740117848768609e-05, "loss": 3.6375, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.739279254017557e-05, "loss": 3.6215, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.738440659266505e-05, "loss": 3.6224, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.737603702395826e-05, "loss": 3.62, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736765107644774e-05, "loss": 3.6259, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.735926512893722e-05, "loss": 3.625, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.73508791814267e-05, "loss": 3.6252, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.734249323391618e-05, "loss": 3.6348, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.733410728640566e-05, "loss": 3.6353, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732573771769887e-05, "loss": 3.6385, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731735177018835e-05, "loss": 3.6319, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.730896582267783e-05, "loss": 3.6242, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.730057987516731e-05, "loss": 3.6292, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729219392765679e-05, "loss": 3.6347, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728382435895e-05, "loss": 3.6259, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.727543841143948e-05, "loss": 3.6285, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726705246392897e-05, "loss": 3.6208, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725866651641845e-05, "loss": 3.6185, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.7250296947711657e-05, "loss": 3.6232, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.7241911000201137e-05, "loss": 3.6341, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.7233525052690616e-05, "loss": 3.6368, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.7225139105180096e-05, "loss": 3.63, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.721675315766957e-05, "loss": 3.6287, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720836721015905e-05, "loss": 3.6239, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.7199997641452265e-05, "loss": 3.6394, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.7191611693941745e-05, "loss": 3.6194, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718322574643122e-05, "loss": 3.618, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.7174839798920705e-05, "loss": 3.6174, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.716647023021392e-05, "loss": 3.6234, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.71580842827034e-05, "loss": 3.6255, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.7149698335192874e-05, "loss": 3.6271, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.7141312387682354e-05, "loss": 3.6265, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.7132926440171834e-05, "loss": 3.6266, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.7124540492661314e-05, "loss": 3.6238, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711617092395452e-05, "loss": 3.6223, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.7107784976444e-05, "loss": 3.6199, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709939902893348e-05, "loss": 3.5989, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709101308142296e-05, "loss": 3.6352, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.708262713391244e-05, "loss": 3.6175, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707425756520566e-05, "loss": 3.6312, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.706587161769514e-05, "loss": 3.6208, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705748567018462e-05, "loss": 3.6159, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.70490997226741e-05, "loss": 3.6071, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.704073015396731e-05, "loss": 3.6198, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.703234420645679e-05, "loss": 3.6176, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.702395825894627e-05, "loss": 3.6132, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.701557231143575e-05, "loss": 3.6343, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.700718636392523e-05, "loss": 3.6183, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.699881679521844e-05, "loss": 3.6048, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.699043084770792e-05, "loss": 3.6297, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.69820449001974e-05, "loss": 3.6155, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.697365895268688e-05, "loss": 3.6125, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.696528938398009e-05, "loss": 3.6247, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.695690343646957e-05, "loss": 3.6173, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.694851748895905e-05, "loss": 3.6087, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.694013154144853e-05, "loss": 3.6216, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693174559393801e-05, "loss": 3.6092, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.692335964642749e-05, "loss": 3.6115, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691497369891697e-05, "loss": 3.6239, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690660413021018e-05, "loss": 3.6226, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689821818269966e-05, "loss": 3.6245, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.688983223518914e-05, "loss": 3.6194, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688144628767862e-05, "loss": 3.6419, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.68730603401681e-05, "loss": 3.613, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686469077146131e-05, "loss": 3.6258, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685630482395079e-05, "loss": 3.6194, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684791887644028e-05, "loss": 3.6169, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.683953292892976e-05, "loss": 3.615, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.683114698141923e-05, "loss": 3.6313, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.6822777412712446e-05, "loss": 3.6219, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.6814391465201926e-05, "loss": 3.6317, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.6806005517691406e-05, "loss": 3.6063, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.679761957018088e-05, "loss": 3.6074, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.678923362267036e-05, "loss": 3.6218, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6780864053963575e-05, "loss": 3.6308, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.6772478106453055e-05, "loss": 3.6165, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676409215894253e-05, "loss": 3.6239, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.6755706211432015e-05, "loss": 3.6132, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.6747320263921495e-05, "loss": 3.6128, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.6738950695214704e-05, "loss": 3.6169, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.6730564747704184e-05, "loss": 3.6128, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.6722178800193664e-05, "loss": 3.6243, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.6713792852683144e-05, "loss": 3.6344, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670542328397635e-05, "loss": 3.6294, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669703733646583e-05, "loss": 3.6106, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668865138895531e-05, "loss": 3.6087, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.668026544144479e-05, "loss": 3.6178, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667187949393427e-05, "loss": 3.6228, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666350992522748e-05, "loss": 3.6218, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.665512397771697e-05, "loss": 3.6216, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.664673803020645e-05, "loss": 3.6222, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663835208269593e-05, "loss": 3.6107, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.662998251398914e-05, "loss": 3.616, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662159656647862e-05, "loss": 3.6122, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.66132106189681e-05, "loss": 3.6102, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.660482467145758e-05, "loss": 3.6216, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.659643872394706e-05, "loss": 3.6181, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.658805277643654e-05, "loss": 3.6079, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.6579683207729746e-05, "loss": 3.6124, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.6571297260219226e-05, "loss": 3.6017, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.6562911312708706e-05, "loss": 3.6213, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.6554525365198186e-05, "loss": 3.6164, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.65461557964914e-05, "loss": 3.6256, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.653776984898088e-05, "loss": 3.627, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.652938390147036e-05, "loss": 3.6281, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.652101433276357e-05, "loss": 3.6144, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.651262838525305e-05, "loss": 3.6125, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.650424243774253e-05, "loss": 3.618, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.649585649023201e-05, "loss": 3.6187, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.648747054272149e-05, "loss": 3.6109, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.647908459521097e-05, "loss": 3.6043, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.647069864770045e-05, "loss": 3.6184, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646231270018993e-05, "loss": 3.6118, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645394313148314e-05, "loss": 3.614, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644555718397262e-05, "loss": 3.6078, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.64371712364621e-05, "loss": 3.6201, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.6428785288951587e-05, "loss": 3.6045, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.6420415720244796e-05, "loss": 3.6252, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.6412029772734276e-05, "loss": 3.6177, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.6403643825223756e-05, "loss": 3.6292, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.6395257877713236e-05, "loss": 3.6019, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.6386888309006445e-05, "loss": 3.6213, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.6378502361495925e-05, "loss": 3.6213, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.6370116413985405e-05, "loss": 3.6199, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.6361730466474884e-05, "loss": 3.62, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635334451896436e-05, "loss": 3.6113, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.6344974950257574e-05, "loss": 3.6154, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.6336589002747053e-05, "loss": 3.6316, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.632820305523654e-05, "loss": 3.6069, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.6319817107726013e-05, "loss": 3.6182, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631144753901923e-05, "loss": 3.6197, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.630306159150871e-05, "loss": 3.6127, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.629467564399819e-05, "loss": 3.6128, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.628628969648766e-05, "loss": 3.6144, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.627792012778088e-05, "loss": 3.6159, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.626953418027036e-05, "loss": 3.6159, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.626114823275983e-05, "loss": 3.61, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.8442649841308594, "eval_runtime": 302.6112, "eval_samples_per_second": 1260.994, "eval_steps_per_second": 39.407, "step": 839520 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 5.854230451983514e+17, "trial_name": null, "trial_params": null }