{ "best_metric": 3.911860942840576, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/2/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": 10.9575, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8163, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1923, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9769, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8209, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7141, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6128, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5406, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.459, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4141, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3519, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3101, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2647, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2178, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1785, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1386, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1091, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0779, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0521, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0219, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0079, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.98, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9504, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9376, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9266, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8884, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8712, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.859, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8438, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8202, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.804, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7996, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7845, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7783, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7637, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7439, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7372, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7037, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.711, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6823, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6828, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6697, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6727, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6507, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6475, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6369, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6209, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6323, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5989, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5909, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.6016, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.598, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5725, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5671, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5663, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5485, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5686, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5298, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5394, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5305, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.515, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5236, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5041, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5024, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4918, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5076, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4788, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4822, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4619, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4715, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4816, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4713, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4535, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4665, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4661, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4423, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4472, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4286, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4195, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.417, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4191, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4248, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4312, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4192, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3957, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4024, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4029, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3938, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3876, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.383, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3772, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3863, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3715, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3788, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 4.3683, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 4.368, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.3522, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 4.3541, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 4.3515, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917006963612195e-05, "loss": 4.3581, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3588, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3347, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.3427, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136542224883596e-05, "loss": 4.3336, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.337, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3251, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3227, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3279, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3178, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3161, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3094, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3053, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3189, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3045, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.305, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3091, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3136, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.2986, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2873, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2933, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2994, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2851, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.284, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2826, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.2827, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2755, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2801, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.2719, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.2742, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2663, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2841, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2673, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2602, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2543, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2647, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.2594, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.266, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2528, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2583, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2514, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2514, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2431, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2512, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2393, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2275, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2481, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2362, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2334, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2397, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2236, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.196439266204834, "eval_runtime": 309.473, "eval_samples_per_second": 1233.035, "eval_steps_per_second": 38.533, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2129, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2179, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2222, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.2174, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2258, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.2104, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.2133, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.2036, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2189, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.1999, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.199, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.2005, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1963, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.1888, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.189, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.1737, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.1849, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.1797, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.1727, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.2005, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.1775, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1798, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1756, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1893, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.162, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.1664, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.169, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1677, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1568, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1577, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.1647, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1673, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1675, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1581, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1516, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1619, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1349, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1557, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1332, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1436, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1384, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.148, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1409, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1353, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1402, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1325, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1446, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1184, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1189, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833183521875203e-05, "loss": 4.1362, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1353, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.121, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830671013382793e-05, "loss": 4.1154, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1243, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1074, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.1329, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.1113, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1208, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.1154, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1034, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239638932547505e-05, "loss": 4.1184, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231252985036985e-05, "loss": 4.104, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222867037526465e-05, "loss": 4.1039, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.0994, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206111521309154e-05, "loss": 4.1166, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197725573798634e-05, "loss": 4.0986, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.0993, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.0893, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.0989, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1119, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1059, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147409888735514e-05, "loss": 4.0958, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.107, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1093, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.0949, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.0996, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.0892, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.0808, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0827, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.086, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0913, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.1052, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.095, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0718, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.0822, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0873, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0833, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0743, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004930675075325e-05, "loss": 4.0733, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0748, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988175158858015e-05, "loss": 4.0787, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0708, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0804, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.073, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.0775, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0609, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0701, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0661, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0726, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0729, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0603, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0616, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0621, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0639, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870821030121935e-05, "loss": 4.0503, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862435082611415e-05, "loss": 4.0549, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0632, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0515, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837293618883584e-05, "loss": 4.0513, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828907671373064e-05, "loss": 4.0477, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820521723862544e-05, "loss": 4.0453, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812135776352024e-05, "loss": 4.0653, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0457, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0568, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786977933820464e-05, "loss": 4.0522, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0664, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0522, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0384, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0475, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0526, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773669500636481e-05, "loss": 4.0372, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772830905885429e-05, "loss": 4.0446, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771992311134377e-05, "loss": 4.0379, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771153716383325e-05, "loss": 4.0496, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770316759512646e-05, "loss": 4.0348, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769478164761594e-05, "loss": 4.0468, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768639570010542e-05, "loss": 4.0389, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76780097525949e-05, "loss": 4.0422, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0327, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766123785757386e-05, "loss": 4.0555, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765286828886707e-05, "loss": 4.0427, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764448234135655e-05, "loss": 4.0289, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.0308, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0373, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761934087762872e-05, "loss": 4.0389, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610954930118195e-05, "loss": 4.0461, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0297, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.0397, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758581346639037e-05, "loss": 4.0307, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577427518879844e-05, "loss": 4.0368, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0298, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756065562385881e-05, "loss": 4.0345, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755228605515202e-05, "loss": 4.0268, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0195, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.04, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752712821262046e-05, "loss": 4.0292, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751874226510994e-05, "loss": 4.0257, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751037269640315e-05, "loss": 4.0288, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750198674889263e-05, "loss": 4.0182, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.027224063873291, "eval_runtime": 305.3242, "eval_samples_per_second": 1249.789, "eval_steps_per_second": 39.057, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749360080138211e-05, "loss": 4.0098, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748521485387159e-05, "loss": 4.0111, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747682890636107e-05, "loss": 4.0251, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746844295885055e-05, "loss": 4.0158, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746005701134003e-05, "loss": 4.0294, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0134, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744328511631899e-05, "loss": 4.0152, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434899168808475e-05, "loss": 4.0082, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0265, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0078, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0053, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401371757570124e-05, "loss": 4.0077, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739300218886333e-05, "loss": 4.0081, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738461624135281e-05, "loss": 4.0003, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737623029384229e-05, "loss": 4.0039, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736784434633177e-05, "loss": 3.9932, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 3.9976, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 3.9945, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 3.9884, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733431693509343e-05, "loss": 4.0224, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 3.9986, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 3.9929, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73091754713656e-05, "loss": 3.9999, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730078952385508e-05, "loss": 4.0076, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729241995514829e-05, "loss": 3.9851, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728403400763777e-05, "loss": 3.9938, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727564806012725e-05, "loss": 3.9928, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726726211261673e-05, "loss": 3.9965, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9811, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9873, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.9894, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 3.997, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722536513267159e-05, "loss": 4.0023, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721697918516107e-05, "loss": 3.9893, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720859323765055e-05, "loss": 3.9825, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720020729014003e-05, "loss": 3.9935, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719183772143324e-05, "loss": 3.9746, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718345177392272e-05, "loss": 3.9892, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.71750658264122e-05, "loss": 3.9705, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716667987890168e-05, "loss": 3.9765, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158293931391154e-05, "loss": 3.9787, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9888, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9801, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713315246766333e-05, "loss": 3.9762, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712476652015281e-05, "loss": 3.9791, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116396951446025e-05, "loss": 3.9752, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108011003935505e-05, "loss": 3.984, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709962505642498e-05, "loss": 3.9636, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709123910891446e-05, "loss": 3.9604, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082869540207674e-05, "loss": 3.9823, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074483592697154e-05, "loss": 3.9769, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706609764518663e-05, "loss": 3.9664, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705771169767611e-05, "loss": 3.9672, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704934212896932e-05, "loss": 3.9708, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.70409561814588e-05, "loss": 3.9555, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703257023394828e-05, "loss": 3.9779, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702418428643776e-05, "loss": 3.9625, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701581471773098e-05, "loss": 3.9699, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700742877022045e-05, "loss": 3.9636, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699904282270993e-05, "loss": 3.9611, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699065687519941e-05, "loss": 3.9607, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698228730649263e-05, "loss": 3.9604, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.69739013589821e-05, "loss": 3.956, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696551541147158e-05, "loss": 3.9535, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695712946396106e-05, "loss": 3.9703, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694875989525428e-05, "loss": 3.9555, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694037394774376e-05, "loss": 3.955, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693198800023324e-05, "loss": 3.9474, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692360205272272e-05, "loss": 3.954, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915232484015926e-05, "loss": 3.9702, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906846536505406e-05, "loss": 3.9651, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898460588994886e-05, "loss": 3.9573, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890074641484366e-05, "loss": 3.9658, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881705072777575e-05, "loss": 3.9692, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873319125267055e-05, "loss": 3.9518, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864933177756535e-05, "loss": 3.9608, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856547230246015e-05, "loss": 3.9545, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684817766153923e-05, "loss": 3.9457, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683979171402871e-05, "loss": 3.9528, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683140576651819e-05, "loss": 3.9461, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682301981900767e-05, "loss": 3.9568, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681465025030088e-05, "loss": 3.9639, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680626430279036e-05, "loss": 3.9617, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679787835527984e-05, "loss": 3.9356, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678949240776932e-05, "loss": 3.9517, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678112283906253e-05, "loss": 3.9515, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677273689155201e-05, "loss": 3.9505, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676435094404149e-05, "loss": 3.9458, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675596499653097e-05, "loss": 3.9379, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747595427824184e-05, "loss": 3.9477, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739209480313664e-05, "loss": 3.9448, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730823532803144e-05, "loss": 3.9417, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722437585292624e-05, "loss": 3.9501, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671406801658583e-05, "loss": 3.9414, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670568206907531e-05, "loss": 3.9504, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669729612156479e-05, "loss": 3.9367, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668891017405427e-05, "loss": 3.9379, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668054060534748e-05, "loss": 3.9386, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667215465783696e-05, "loss": 3.949, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666376871032644e-05, "loss": 3.9474, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665538276281592e-05, "loss": 3.9359, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664701319410914e-05, "loss": 3.9364, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663862724659862e-05, "loss": 3.9363, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66302412990881e-05, "loss": 3.9415, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662187173038131e-05, "loss": 3.9242, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661348578287079e-05, "loss": 3.9287, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660509983536027e-05, "loss": 3.9433, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659671388784975e-05, "loss": 3.9341, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588344319142956e-05, "loss": 3.9266, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579958371632436e-05, "loss": 3.9268, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571572424121916e-05, "loss": 3.9248, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563186476611396e-05, "loss": 3.9405, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554800529100876e-05, "loss": 3.9306, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546414581590356e-05, "loss": 3.9319, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6538028634079836e-05, "loss": 3.9336, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652964268656932e-05, "loss": 3.9483, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652127311786253e-05, "loss": 3.9361, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651288717035201e-05, "loss": 3.9203, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650450122284149e-05, "loss": 3.9299, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649611527533097e-05, "loss": 3.9321, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648774570662418e-05, "loss": 3.9229, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647935975911366e-05, "loss": 3.9252, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647097381160314e-05, "loss": 3.9213, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646258786409262e-05, "loss": 3.9332, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645421829538583e-05, "loss": 3.9178, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644583234787531e-05, "loss": 3.9335, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643744640036479e-05, "loss": 3.9183, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429060452854276e-05, "loss": 3.9283, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420690884147485e-05, "loss": 3.9182, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412304936636965e-05, "loss": 3.9396, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403918989126445e-05, "loss": 3.9309, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395549420419654e-05, "loss": 3.9203, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387163472909134e-05, "loss": 3.9135, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378777525398614e-05, "loss": 3.9265, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370391577888094e-05, "loss": 3.9232, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6362005630377574e-05, "loss": 3.9341, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635363606167078e-05, "loss": 3.9164, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345266492964e-05, "loss": 3.93, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633688054545348e-05, "loss": 3.9227, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632849459794296e-05, "loss": 3.9316, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632010865043244e-05, "loss": 3.9156, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631172270292192e-05, "loss": 3.9236, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.63033367554114e-05, "loss": 3.9186, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629495080790088e-05, "loss": 3.9105, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628656486039035e-05, "loss": 3.9276, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627819529168357e-05, "loss": 3.9248, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626980934417305e-05, "loss": 3.9113, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626142339666253e-05, "loss": 3.9212, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6253037449152e-05, "loss": 3.91, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.953357696533203, "eval_runtime": 301.6217, "eval_samples_per_second": 1265.131, "eval_steps_per_second": 39.536, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244667880445217e-05, "loss": 3.9062, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.6236281932934697e-05, "loss": 3.9047, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227895985424176e-05, "loss": 3.9162, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219510037913656e-05, "loss": 3.9135, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621114046920687e-05, "loss": 3.9271, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620275452169635e-05, "loss": 3.9031, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194368574185825e-05, "loss": 3.9113, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185982626675305e-05, "loss": 3.9041, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617761305796852e-05, "loss": 3.925, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6169227110458e-05, "loss": 3.9036, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616085754175121e-05, "loss": 3.8994, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615247159424069e-05, "loss": 3.9092, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614408564673017e-05, "loss": 3.9013, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613569969921965e-05, "loss": 3.8995, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612731375170913e-05, "loss": 3.9013, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118944183002346e-05, "loss": 3.8948, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110558235491826e-05, "loss": 3.8934, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.61021722879813e-05, "loss": 3.8953, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609378634047078e-05, "loss": 3.8902, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608540039296026e-05, "loss": 3.92, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607701444544974e-05, "loss": 3.8973, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606862849793922e-05, "loss": 3.8964, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.60602425504287e-05, "loss": 3.9002, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605187298172191e-05, "loss": 3.9047, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604348703421139e-05, "loss": 3.8897, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035101086700875e-05, "loss": 3.897, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026715139190355e-05, "loss": 3.893, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018345570483564e-05, "loss": 3.8964, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009959622973044e-05, "loss": 3.8854, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001573675462524e-05, "loss": 3.8903, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5993187727952004e-05, "loss": 3.8954, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598481815924521e-05, "loss": 3.899, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597643221173469e-05, "loss": 3.9051, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.59680626430279e-05, "loss": 3.8968, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595967669551738e-05, "loss": 3.8849, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595129074800686e-05, "loss": 3.8964, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594290480049634e-05, "loss": 3.883, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593451885298583e-05, "loss": 3.8916, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592613290547531e-05, "loss": 3.8777, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591776333676852e-05, "loss": 3.8825, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909377389258e-05, "loss": 3.8812, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590099144174748e-05, "loss": 3.898, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589260549423696e-05, "loss": 3.8904, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588421954672644e-05, "loss": 3.8821, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587583359921592e-05, "loss": 3.886, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.58674476517054e-05, "loss": 3.8833, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585906170419488e-05, "loss": 3.8889, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850692135488086e-05, "loss": 3.873, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842322566781295e-05, "loss": 3.8667, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833936619270775e-05, "loss": 3.8904, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582555067176026e-05, "loss": 3.8861, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581716472424974e-05, "loss": 3.8723, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580877877673922e-05, "loss": 3.8786, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580040920803243e-05, "loss": 3.8827, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579202326052191e-05, "loss": 3.8661, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578363731301139e-05, "loss": 3.8822, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577525136550087e-05, "loss": 3.8713, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576688179679408e-05, "loss": 3.8842, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575849584928356e-05, "loss": 3.8719, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575010990177304e-05, "loss": 3.8804, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574172395426252e-05, "loss": 3.8679, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733338006752e-05, "loss": 3.8745, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572495205924148e-05, "loss": 3.8641, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716582490534696e-05, "loss": 3.8689, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708196543024176e-05, "loss": 3.8849, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699810595513656e-05, "loss": 3.8659, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691424648003135e-05, "loss": 3.8705, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568303870049261e-05, "loss": 3.8608, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567465275298209e-05, "loss": 3.8688, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566626680547157e-05, "loss": 3.8824, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565789723676478e-05, "loss": 3.8771, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649527668057994e-05, "loss": 3.8752, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5641141720547474e-05, "loss": 3.8805, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632755773036953e-05, "loss": 3.8786, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624369825526433e-05, "loss": 3.8691, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561600025681965e-05, "loss": 3.8746, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560761430930913e-05, "loss": 3.8719, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559922836179861e-05, "loss": 3.863, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559084241428808e-05, "loss": 3.8651, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.55824728455813e-05, "loss": 3.8636, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557408689807078e-05, "loss": 3.8696, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556570095056025e-05, "loss": 3.8793, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555731500304973e-05, "loss": 3.8767, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554892905553921e-05, "loss": 3.8517, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554055948683243e-05, "loss": 3.8726, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553217353932191e-05, "loss": 3.8671, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552378759181139e-05, "loss": 3.8674, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551540164430087e-05, "loss": 3.8622, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550701569679035e-05, "loss": 3.8541, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498646128083556e-05, "loss": 3.8689, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5490260180573036e-05, "loss": 3.861, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481874233062516e-05, "loss": 3.8615, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.5473488285551996e-05, "loss": 3.8657, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.5465102338041476e-05, "loss": 3.8605, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.5456732769334685e-05, "loss": 3.8724, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448346821824165e-05, "loss": 3.8577, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5439960874313645e-05, "loss": 3.8544, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431574926803125e-05, "loss": 3.8573, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542320535809634e-05, "loss": 3.8709, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541481941058582e-05, "loss": 3.8635, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.54064334630753e-05, "loss": 3.8569, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539804751556478e-05, "loss": 3.8548, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538966156805426e-05, "loss": 3.8575, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538129199934747e-05, "loss": 3.8659, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537290605183695e-05, "loss": 3.8505, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536452010432643e-05, "loss": 3.8445, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535613415681591e-05, "loss": 3.8643, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534774820930539e-05, "loss": 3.852, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.53393786405986e-05, "loss": 3.8482, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533099269308808e-05, "loss": 3.8463, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532260674557756e-05, "loss": 3.8507, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314220798067045e-05, "loss": 3.8642, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305834850556525e-05, "loss": 3.8487, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297465281849734e-05, "loss": 3.8543, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5289079334339214e-05, "loss": 3.8568, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280693386828694e-05, "loss": 3.8679, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272307439318174e-05, "loss": 3.8627, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526393787061138e-05, "loss": 3.8415, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525555192310086e-05, "loss": 3.8542, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524716597559034e-05, "loss": 3.8508, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523878002807982e-05, "loss": 3.8501, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.52303940805693e-05, "loss": 3.8499, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522200813305878e-05, "loss": 3.844, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213638564352e-05, "loss": 3.8566, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520525261684148e-05, "loss": 3.8446, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519686666933096e-05, "loss": 3.8557, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518848072182044e-05, "loss": 3.8461, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518009477430992e-05, "loss": 3.8532, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517172520560313e-05, "loss": 3.8416, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516333925809261e-05, "loss": 3.8682, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515495331058209e-05, "loss": 3.8497, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514656736307156e-05, "loss": 3.8494, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513819779436478e-05, "loss": 3.8377, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512981184685426e-05, "loss": 3.8546, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512142589934374e-05, "loss": 3.8474, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511303995183322e-05, "loss": 3.8576, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510467038312643e-05, "loss": 3.8435, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509628443561591e-05, "loss": 3.8546, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508789848810539e-05, "loss": 3.8506, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079512540594866e-05, "loss": 3.8611, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507114297188808e-05, "loss": 3.8391, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506275702437756e-05, "loss": 3.8524, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054371076867035e-05, "loss": 3.845, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045985129356515e-05, "loss": 3.8419, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037599181845995e-05, "loss": 3.8521, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5029213234335474e-05, "loss": 3.8522, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020827286824954e-05, "loss": 3.842, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501245771811817e-05, "loss": 3.8457, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500407177060765e-05, "loss": 3.8414, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.911860942840576, "eval_runtime": 302.0292, "eval_samples_per_second": 1263.424, "eval_steps_per_second": 39.483, "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 }