{ "best_metric": 3.911149501800537, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/3/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "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 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.1288110734485504e+17, "trial_name": null, "trial_params": null }