{ "best_metric": 3.9090492725372314, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/4/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": 10.9889, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.826, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1945, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9797, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8194, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7109, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6086, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5346, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4515, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4029, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3415, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.2991, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2541, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2066, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1674, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1264, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.0986, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0669, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0396, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0086, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 4.9953, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9686, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 4.9364, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9247, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9133, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8768, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 4.8566, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8456, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8303, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8075, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 4.7921, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7873, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.772, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7651, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7509, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.733, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7253, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.6916, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.6974, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6702, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6715, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6588, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6606, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6397, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6351, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6266, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6095, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6199, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5848, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5777, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5909, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.585, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5602, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5547, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5534, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5357, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5588, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5201, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.529, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5198, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5039, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5122, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.4933, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4904, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4817, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4954, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4681, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.471, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4498, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4588, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4722, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4604, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4448, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.456, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4573, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4323, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4382, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4204, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.41, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4094, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4092, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4153, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4218, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4106, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3863, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.3926, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.3951, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3863, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3776, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3724, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3695, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3761, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3633, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3694, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3596, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3599, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3432, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3462, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3428, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3486, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3486, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3269, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3327, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3241, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3291, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.317, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.314, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3204, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3096, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3077, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3009, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.2963, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3112, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.2977, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.298, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3003, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3063, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.2924, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2799, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2859, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2904, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2767, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2757, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2736, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2743, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2677, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2739, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.266, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2654, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2597, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2753, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2598, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2521, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2481, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.2585, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.2519, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2587, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2438, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2511, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2427, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.246, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2361, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2457, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2328, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2206, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2409, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2298, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2271, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2335, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2157, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.188263893127441, "eval_runtime": 314.831, "eval_samples_per_second": 1212.05, "eval_steps_per_second": 37.877, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2057, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2093, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2168, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.2107, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2172, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.2046, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.2042, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.1978, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2108, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.1915, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.1916, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.196, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1914, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.1829, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.1821, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.1661, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.1782, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.1709, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.1649, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.1926, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.1684, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1728, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1688, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.1831, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541369254888915e-05, "loss": 4.156, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532983307378395e-05, "loss": 4.1587, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1634, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1604, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.152, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.1512, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.8491069948629524e-05, "loss": 4.1591, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1587, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.1594, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.1523, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845754253739117e-05, "loss": 4.1456, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1538, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1277, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.1499, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1268, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1367, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840725960993552e-05, "loss": 4.1327, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398873662425e-05, "loss": 4.1424, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.1344, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.1294, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1334, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365346251186646e-05, "loss": 4.1252, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356960303676126e-05, "loss": 4.1366, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348574356165606e-05, "loss": 4.1112, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1133, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.128, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323432892437775e-05, "loss": 4.1287, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315046944927255e-05, "loss": 4.1131, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.1099, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1172, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.1017, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281519533688904e-05, "loss": 4.1243, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1058, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1143, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.1101, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824799212245056e-05, "loss": 4.0958, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.1119, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.0964, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.0977, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.0935, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1111, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.0918, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.0929, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818093729997386e-05, "loss": 4.0835, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.0901, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1061, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1018, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147409888735514e-05, "loss": 4.0896, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.1005, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1033, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.0897, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.0936, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.0849, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.074, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0778, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.0804, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807196911874829e-05, "loss": 4.0851, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.0989, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.0872, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.066, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803844170750995e-05, "loss": 4.0762, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.082, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0772, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0676, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0688, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0698, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988158780054285e-05, "loss": 4.0728, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.0639, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0725, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963000937522725e-05, "loss": 4.0664, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.071, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0543, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.79378594737949e-05, "loss": 4.0646, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792947352628438e-05, "loss": 4.0606, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792108757877386e-05, "loss": 4.0639, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791270163126334e-05, "loss": 4.0663, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790431568375282e-05, "loss": 4.0535, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0547, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788756016753551e-05, "loss": 4.0561, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787917422002499e-05, "loss": 4.0594, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787078827251447e-05, "loss": 4.0441, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0478, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0572, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.0443, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.0473, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.0414, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782048896625508e-05, "loss": 4.0385, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781210301874456e-05, "loss": 4.0594, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780371707123404e-05, "loss": 4.0419, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779534750252725e-05, "loss": 4.0492, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778696155501673e-05, "loss": 4.0477, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777857560750621e-05, "loss": 4.0598, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777018965999569e-05, "loss": 4.0483, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.0333, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.0416, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774504819626786e-05, "loss": 4.0476, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773666224875734e-05, "loss": 4.0333, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0369, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.032, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.0434, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770313483751899e-05, "loss": 4.0297, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769474889000847e-05, "loss": 4.0398, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768636294249795e-05, "loss": 4.0339, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0352, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0275, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0493, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528355312596e-05, "loss": 4.0386, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764444958374909e-05, "loss": 4.0217, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763606363623857e-05, "loss": 4.0257, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762767768872805e-05, "loss": 4.0331, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761929174121753e-05, "loss": 4.0335, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761092217251074e-05, "loss": 4.042, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760253622500022e-05, "loss": 4.0256, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.75941502774897e-05, "loss": 4.0334, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758576432997918e-05, "loss": 4.0267, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577394761272386e-05, "loss": 4.0335, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569008813761866e-05, "loss": 4.0246, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560622866251346e-05, "loss": 4.0287, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552236918740826e-05, "loss": 4.0216, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543867350034035e-05, "loss": 4.0135, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753548140252352e-05, "loss": 4.0332, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527095455013e-05, "loss": 4.0241, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751870950750248e-05, "loss": 4.02, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751033993879569e-05, "loss": 4.0241, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750195399128517e-05, "loss": 4.0128, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.022622108459473, "eval_runtime": 302.4683, "eval_samples_per_second": 1261.59, "eval_steps_per_second": 39.426, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749356804377465e-05, "loss": 4.0044, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748518209626413e-05, "loss": 4.0043, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747679614875361e-05, "loss": 4.0202, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468410201243084e-05, "loss": 4.0106, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460024253732563e-05, "loss": 4.0234, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451638306222043e-05, "loss": 4.0068, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744325235871152e-05, "loss": 4.0101, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434866411201e-05, "loss": 4.0034, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742648046369049e-05, "loss": 4.0194, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741809451617997e-05, "loss": 4.0023, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740970856866945e-05, "loss": 4.0019, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740133899996266e-05, "loss": 4.0025, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7392985810059604e-05, "loss": 4.0035, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384599862549084e-05, "loss": 3.9957, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737621391503856e-05, "loss": 3.9983, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736782796752804e-05, "loss": 3.9866, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735944202001752e-05, "loss": 3.9911, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7351056072507e-05, "loss": 3.9877, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734267012499648e-05, "loss": 3.983, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733428417748596e-05, "loss": 4.0163, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325898229975444e-05, "loss": 3.992, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317512282464924e-05, "loss": 3.9882, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309126334954404e-05, "loss": 3.9942, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730075676624761e-05, "loss": 4.0035, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729237081873709e-05, "loss": 3.9803, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728398487122657e-05, "loss": 3.9862, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727559892371605e-05, "loss": 3.9892, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726722935500926e-05, "loss": 3.9914, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725884340749874e-05, "loss": 3.9779, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725045745998822e-05, "loss": 3.9818, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.72420715124777e-05, "loss": 3.9856, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723370194377091e-05, "loss": 3.9901, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.72253159962604e-05, "loss": 3.9956, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721693004874988e-05, "loss": 3.9834, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720854410123936e-05, "loss": 3.9779, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200174532532566e-05, "loss": 3.9887, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191788585022046e-05, "loss": 3.9684, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183402637511526e-05, "loss": 3.9845, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175016690001006e-05, "loss": 3.9642, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166647121294215e-05, "loss": 3.9719, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158261173783695e-05, "loss": 3.9742, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149875226273175e-05, "loss": 3.9831, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141489278762655e-05, "loss": 3.9749, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133119710055864e-05, "loss": 3.9703, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712473376254535e-05, "loss": 3.9734, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711634781503483e-05, "loss": 3.9704, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710796186752431e-05, "loss": 3.9785, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709959229881752e-05, "loss": 3.9586, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091206351307e-05, "loss": 3.9561, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708282040379648e-05, "loss": 3.9752, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707443445628596e-05, "loss": 3.9715, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706606488757917e-05, "loss": 3.9607, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705767894006865e-05, "loss": 3.9603, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9637, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9502, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703253747634082e-05, "loss": 3.9723, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024151528830305e-05, "loss": 3.9585, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015765581319785e-05, "loss": 3.9662, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007379633809265e-05, "loss": 3.9606, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998993686298745e-05, "loss": 3.9563, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699060773878822e-05, "loss": 3.9566, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982238170081434e-05, "loss": 3.9541, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973852222570914e-05, "loss": 3.9518, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965466275060394e-05, "loss": 3.9484, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69570967063536e-05, "loss": 3.9652, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694871075884308e-05, "loss": 3.9517, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694032481133256e-05, "loss": 3.9513, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693193886382204e-05, "loss": 3.9423, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692355291631152e-05, "loss": 3.9492, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915166968801e-05, "loss": 3.9647, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690678102129048e-05, "loss": 3.9595, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689839507377996e-05, "loss": 3.9516, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689002550507317e-05, "loss": 3.9604, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688163955756265e-05, "loss": 3.9645, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687325361005213e-05, "loss": 3.9472, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686488404134534e-05, "loss": 3.955, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685649809383482e-05, "loss": 3.9504, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.68481121463243e-05, "loss": 3.9412, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683972619881378e-05, "loss": 3.9471, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831356630106996e-05, "loss": 3.9416, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822970682596476e-05, "loss": 3.95, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814584735085956e-05, "loss": 3.9605, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806198787575436e-05, "loss": 3.9566, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797812840064916e-05, "loss": 3.9309, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789443271358125e-05, "loss": 3.9467, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781057323847605e-05, "loss": 3.9476, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772671376337085e-05, "loss": 3.9475, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764285428826565e-05, "loss": 3.9395, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755899481316045e-05, "loss": 3.9337, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747529912609254e-05, "loss": 3.9442, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739143965098734e-05, "loss": 3.9383, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730758017588214e-05, "loss": 3.9343, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722372070077694e-05, "loss": 3.9437, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713986122567174e-05, "loss": 3.9371, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670561655386039e-05, "loss": 3.9462, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669723060634987e-05, "loss": 3.9301, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668884465883935e-05, "loss": 3.9335, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668045871132883e-05, "loss": 3.9343, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667207276381831e-05, "loss": 3.9427, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666370319511152e-05, "loss": 3.9408, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655317247601e-05, "loss": 3.9297, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664693130009048e-05, "loss": 3.9314, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663854535257996e-05, "loss": 3.9307, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663015940506944e-05, "loss": 3.9374, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662177345755892e-05, "loss": 3.9191, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661340388885213e-05, "loss": 3.9241, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6605017941341614e-05, "loss": 3.9396, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596631993831094e-05, "loss": 3.928, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588246046320574e-05, "loss": 3.9211, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579860098810054e-05, "loss": 3.9213, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657147415129953e-05, "loss": 3.9198, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656308820378901e-05, "loss": 3.9365, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655470225627849e-05, "loss": 3.9258, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.65463326875717e-05, "loss": 3.9252, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537946740061176e-05, "loss": 3.9281, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529560792550656e-05, "loss": 3.9426, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521174845040136e-05, "loss": 3.9307, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651280527633335e-05, "loss": 3.9163, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650441932882283e-05, "loss": 3.9246, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649603338131231e-05, "loss": 3.9277, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648764743380179e-05, "loss": 3.919, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479277865095e-05, "loss": 3.9206, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647089191758448e-05, "loss": 3.9175, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646250597007396e-05, "loss": 3.9279, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645412002256344e-05, "loss": 3.9129, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644573407505292e-05, "loss": 3.928, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.64373481275424e-05, "loss": 3.9139, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642897855883561e-05, "loss": 3.9248, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642059261132509e-05, "loss": 3.9131, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641220666381457e-05, "loss": 3.9344, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640382071630405e-05, "loss": 3.9266, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395434768793536e-05, "loss": 3.9163, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387048821283016e-05, "loss": 3.9091, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378662873772496e-05, "loss": 3.9229, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370276926261976e-05, "loss": 3.9193, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361923736358915e-05, "loss": 3.9306, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353537788848395e-05, "loss": 3.9122, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345151841337874e-05, "loss": 3.9254, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336765893827354e-05, "loss": 3.918, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328379946316834e-05, "loss": 3.9287, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319993998806314e-05, "loss": 3.9103, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311608051295794e-05, "loss": 3.918, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303222103785274e-05, "loss": 3.9135, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629485253507848e-05, "loss": 3.9043, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628646658756797e-05, "loss": 3.9245, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627808064005745e-05, "loss": 3.9204, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626969469254693e-05, "loss": 3.9076, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626132512384014e-05, "loss": 3.9184, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625293917632962e-05, "loss": 3.9058, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.949087142944336, "eval_runtime": 302.9735, "eval_samples_per_second": 1259.487, "eval_steps_per_second": 39.36, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.62445532288191e-05, "loss": 3.9043, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623616728130858e-05, "loss": 3.8982, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622778133379806e-05, "loss": 3.9107, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621939538628753e-05, "loss": 3.9081, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621102581758075e-05, "loss": 3.9208, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620263987007023e-05, "loss": 3.899, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619425392255971e-05, "loss": 3.9062, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618586797504919e-05, "loss": 3.8996, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617748202753867e-05, "loss": 3.9187, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616909608002815e-05, "loss": 3.8961, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160726511321364e-05, "loss": 3.8955, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615234056381084e-05, "loss": 3.9069, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614397099510405e-05, "loss": 3.8972, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613558504759353e-05, "loss": 3.8971, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127199100083006e-05, "loss": 3.8962, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118813152572486e-05, "loss": 3.8891, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110427205061966e-05, "loss": 3.8877, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102041257551446e-05, "loss": 3.8896, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093655310040926e-05, "loss": 3.8839, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085269362530406e-05, "loss": 3.915, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607688341501989e-05, "loss": 3.8928, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.60685138463131e-05, "loss": 3.8924, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606012789880258e-05, "loss": 3.894, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605174195129206e-05, "loss": 3.9022, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604335600378154e-05, "loss": 3.8849, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603497005627102e-05, "loss": 3.891, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.60265841087605e-05, "loss": 3.891, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601819816124998e-05, "loss": 3.8927, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600981221373946e-05, "loss": 3.8816, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600144264503267e-05, "loss": 3.887, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599305669752215e-05, "loss": 3.8922, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598468712881536e-05, "loss": 3.8938, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976301181304846e-05, "loss": 3.9006, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5967915233794326e-05, "loss": 3.8915, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959529286283806e-05, "loss": 3.8824, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5951143338773286e-05, "loss": 3.893, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942757391262766e-05, "loss": 3.8781, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934371443752246e-05, "loss": 3.8863, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5926001875045455e-05, "loss": 3.8726, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917632306338664e-05, "loss": 3.8781, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909246358828144e-05, "loss": 3.8783, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900860411317624e-05, "loss": 3.8942, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892474463807104e-05, "loss": 3.8856, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884088516296584e-05, "loss": 3.8779, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.58757189475898e-05, "loss": 3.8802, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586733300007928e-05, "loss": 3.8791, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585894705256876e-05, "loss": 3.8865, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585056110505824e-05, "loss": 3.8701, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584219153635145e-05, "loss": 3.8625, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583380558884093e-05, "loss": 3.8854, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582541964133041e-05, "loss": 3.8809, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581703369381989e-05, "loss": 3.8671, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.58086641251131e-05, "loss": 3.8738, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580027817760258e-05, "loss": 3.8756, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579189223009206e-05, "loss": 3.8617, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578350628258154e-05, "loss": 3.8797, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577512033507102e-05, "loss": 3.8682, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576675076636423e-05, "loss": 3.8812, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575836481885371e-05, "loss": 3.867, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574997887134319e-05, "loss": 3.876, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741592923832666e-05, "loss": 3.8636, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573322335512588e-05, "loss": 3.8687, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572483740761536e-05, "loss": 3.8605, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571645146010484e-05, "loss": 3.8627, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708065512594315e-05, "loss": 3.8818, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699679565083795e-05, "loss": 3.8618, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691293617573275e-05, "loss": 3.8662, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568292404886649e-05, "loss": 3.8543, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567453810135597e-05, "loss": 3.8641, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566615215384545e-05, "loss": 3.8767, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565776620633493e-05, "loss": 3.8722, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564938025882441e-05, "loss": 3.8679, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564099431131389e-05, "loss": 3.8767, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563260836380337e-05, "loss": 3.8754, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562423879509658e-05, "loss": 3.8657, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561585284758606e-05, "loss": 3.8682, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560746690007554e-05, "loss": 3.8686, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559908095256502e-05, "loss": 3.8609, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.55906950050545e-05, "loss": 3.8618, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558232543634771e-05, "loss": 3.8605, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557393948883719e-05, "loss": 3.8655, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556555354132667e-05, "loss": 3.8744, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557167593816156e-05, "loss": 3.8716, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548781646305635e-05, "loss": 3.8469, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.5540412077598845e-05, "loss": 3.8679, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.5532026130088325e-05, "loss": 3.8643, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523640182577804e-05, "loss": 3.8641, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515254235067284e-05, "loss": 3.8579, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506868287556764e-05, "loss": 3.85, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498498718849973e-05, "loss": 3.8633, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5490112771339453e-05, "loss": 3.8562, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548174320263266e-05, "loss": 3.8564, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547335725512214e-05, "loss": 3.8612, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546497130761162e-05, "loss": 3.8576, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545658536010111e-05, "loss": 3.8685, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544819941259059e-05, "loss": 3.8537, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543981346508007e-05, "loss": 3.8509, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543142751756955e-05, "loss": 3.853, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542304157005903e-05, "loss": 3.8659, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541467200135224e-05, "loss": 3.8579, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540628605384172e-05, "loss": 3.8494, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.53979001063312e-05, "loss": 3.85, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538951415882068e-05, "loss": 3.8535, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538112821131015e-05, "loss": 3.8615, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537275864260337e-05, "loss": 3.8458, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536437269509285e-05, "loss": 3.8427, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535598674758233e-05, "loss": 3.8597, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534760080007181e-05, "loss": 3.8471, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533923123136502e-05, "loss": 3.8431, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.53308452838545e-05, "loss": 3.8422, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322459336343976e-05, "loss": 3.8464, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314073388833456e-05, "loss": 3.8588, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305687441322936e-05, "loss": 3.8443, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297301493812416e-05, "loss": 3.8494, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5288915546301896e-05, "loss": 3.8522, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280529598791376e-05, "loss": 3.8645, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272160030084585e-05, "loss": 3.859, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5263774082574065e-05, "loss": 3.8379, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255388135063545e-05, "loss": 3.8507, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524700218755303e-05, "loss": 3.8469, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523861624004251e-05, "loss": 3.8459, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523024667133572e-05, "loss": 3.8456, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.52218607238252e-05, "loss": 3.8387, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521347477631468e-05, "loss": 3.8507, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520508882880416e-05, "loss": 3.8399, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519670288129364e-05, "loss": 3.8498, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518833331258685e-05, "loss": 3.8411, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517994736507633e-05, "loss": 3.8488, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517156141756581e-05, "loss": 3.8365, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516317547005529e-05, "loss": 3.8659, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.51548059013485e-05, "loss": 3.8458, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.5146419953837985e-05, "loss": 3.8447, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5138034006327465e-05, "loss": 3.8347, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.5129648058816945e-05, "loss": 3.8516, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121278490110154e-05, "loss": 3.8447, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5112892542599634e-05, "loss": 3.8547, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104506595089114e-05, "loss": 3.8408, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096120647578594e-05, "loss": 3.8496, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087734700068074e-05, "loss": 3.844, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507936513136128e-05, "loss": 3.8575, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507097918385076e-05, "loss": 3.8357, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506259323634024e-05, "loss": 3.8462, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505420728882972e-05, "loss": 3.8407, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504583772012293e-05, "loss": 3.8372, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503745177261242e-05, "loss": 3.848, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.50290658251019e-05, "loss": 3.8464, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502067987759138e-05, "loss": 3.8389, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501229393008086e-05, "loss": 3.8437, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500392436137407e-05, "loss": 3.8369, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9090492725372314, "eval_runtime": 303.0153, "eval_samples_per_second": 1259.313, "eval_steps_per_second": 39.354, "step": 305280 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.10997743962923e+17, "trial_name": null, "trial_params": null }