{ "best_metric": 3.9820053577423096, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/lstm/1/checkpoints/checkpoint-3052726", "epoch": 2.0249763653862156, "eval_steps": 10, "global_step": 3052726, "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": 10.8195, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5561, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0599, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9972, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9475, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.9188, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.7574, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994131474623009e-05, "loss": 6.6474, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993292879871958e-05, "loss": 6.5534, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992454285120906e-05, "loss": 6.4733, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.991615690369854e-05, "loss": 6.4162, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990777095618801e-05, "loss": 6.3506, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 6.2788, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 6.2098, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 6.154, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 6.0923, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 6.0503, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 6.0096, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.963, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.9206, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8923, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.8495, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.8265, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.980713958606178e-05, "loss": 5.788, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.979875363855125e-05, "loss": 5.7724, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.979036769104073e-05, "loss": 5.7327, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.978198174353021e-05, "loss": 5.7102, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.6808, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6655, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.975684027980238e-05, "loss": 5.6388, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.974845433229186e-05, "loss": 5.6265, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 5.6087, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 5.5848, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 5.5705, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5555, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 5.5334, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 5.5301, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 5.4959, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4843, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4547, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966467675120532e-05, "loss": 5.4546, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.96562908036948e-05, "loss": 5.4389, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964790485618428e-05, "loss": 5.4366, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963951890867376e-05, "loss": 5.409, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 5.3987, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 5.3976, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 5.3891, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.9605991497435414e-05, "loss": 5.3773, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.9597605549924894e-05, "loss": 5.3578, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 5.3439, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 5.3611, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 5.3472, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 5.3271, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.3072, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.3151, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 5.294, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 5.3014, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 5.27, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 5.2815, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 5.266, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949702331620985e-05, "loss": 5.2482, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948863736869932e-05, "loss": 5.235, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 5.2471, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 5.2046, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 5.2193, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 5.2267, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 5.2094, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 5.2021, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 5.1768, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 5.1731, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 5.171, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404794272397856e-05, "loss": 5.1818, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396408324887336e-05, "loss": 5.1619, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 5.1702, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 5.1592, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 5.1568, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 5.1342, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 5.1321, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 5.1243, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 5.1194, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 5.1185, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 5.1013, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 5.1026, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 5.1017, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 5.0774, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 5.0845, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 5.0835, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 5.0844, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.92622823011302e-05, "loss": 5.0655, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925389635361968e-05, "loss": 5.062, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924551040610916e-05, "loss": 5.0485, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923712445859864e-05, "loss": 5.0456, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922875488989185e-05, "loss": 5.0451, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.0429, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921198299487081e-05, "loss": 5.0349, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920359704736029e-05, "loss": 5.037, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 5.0276, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 5.0119, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 5.0076, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917006963612195e-05, "loss": 5.0109, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916168368861143e-05, "loss": 5.0064, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 5.0103, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.9923, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.9852, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.9892, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.9695, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.975, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9103014813645245e-05, "loss": 4.9649, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909462886613473e-05, "loss": 4.9654, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908624291862421e-05, "loss": 4.9521, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907785697111369e-05, "loss": 4.9555, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906947102360317e-05, "loss": 4.9455, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.9481, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905271550738586e-05, "loss": 4.9428, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.9335, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903594361236482e-05, "loss": 4.9442, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.9418, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901918809614751e-05, "loss": 4.9294, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901080214863699e-05, "loss": 4.9164, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900241620112647e-05, "loss": 4.9174, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.9151, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.9168, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.9108, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.9012, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.9047, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952116894867085e-05, "loss": 4.8905, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943730947356565e-05, "loss": 4.8952, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893534499984604e-05, "loss": 4.8811, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892695905233552e-05, "loss": 4.8873, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918573104825e-05, "loss": 4.876, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8856, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890181758860769e-05, "loss": 4.8846, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889343164109717e-05, "loss": 4.882, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888504569358665e-05, "loss": 4.8584, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.8876659746076134e-05, "loss": 4.8639, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.8868273798565614e-05, "loss": 4.862, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.8859887851055094e-05, "loss": 4.8639, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515182823483e-05, "loss": 4.852, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884313233483778e-05, "loss": 4.8572, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883474638732726e-05, "loss": 4.8458, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882636043981674e-05, "loss": 4.861, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881797449230622e-05, "loss": 4.8289, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880960492359943e-05, "loss": 4.8484, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880121897608891e-05, "loss": 4.8358, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879283302857839e-05, "loss": 4.8287, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878444708106787e-05, "loss": 4.8282, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877607751236109e-05, "loss": 4.813, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876769156485057e-05, "loss": 4.8183, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.8269, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.8123, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.779831886291504, "eval_runtime": 288.1178, "eval_samples_per_second": 1324.427, "eval_steps_per_second": 41.389, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.8111, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.8048, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.87257782061017e-05, "loss": 4.8175, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871739225859118e-05, "loss": 4.8068, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709006311080657e-05, "loss": 4.8127, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.7888, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.796, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683864847352826e-05, "loss": 4.7801, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675478899842306e-05, "loss": 4.7839, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667092952331785e-05, "loss": 4.788, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865870700482127e-05, "loss": 4.7842, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865033743611448e-05, "loss": 4.7876, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864196786740769e-05, "loss": 4.7664, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863358191989717e-05, "loss": 4.7803, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862519597238665e-05, "loss": 4.7618, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.7667, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.7686, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.7593, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.7627, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.775, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.7505, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856651071861674e-05, "loss": 4.7575, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.7503, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.85497388235957e-05, "loss": 4.7591, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854135287608518e-05, "loss": 4.748, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853296692857466e-05, "loss": 4.7478, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852458098106414e-05, "loss": 4.7309, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851619503355362e-05, "loss": 4.7403, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.85078090860431e-05, "loss": 4.7271, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849942313853258e-05, "loss": 4.738, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849105356982579e-05, "loss": 4.7333, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848266762231527e-05, "loss": 4.7318, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847428167480475e-05, "loss": 4.7342, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846589572729423e-05, "loss": 4.725, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.8457526158587444e-05, "loss": 4.7303, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.8449140211076924e-05, "loss": 4.7232, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.8440754263566404e-05, "loss": 4.7129, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432368316055884e-05, "loss": 4.7066, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8423982368545363e-05, "loss": 4.6953, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415596421034843e-05, "loss": 4.7051, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840721047352432e-05, "loss": 4.7039, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839884090481753e-05, "loss": 4.7105, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839045495730701e-05, "loss": 4.6933, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838206900979649e-05, "loss": 4.6952, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837368306228597e-05, "loss": 4.6984, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836529711477545e-05, "loss": 4.6911, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835691116726493e-05, "loss": 4.6973, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834852521975441e-05, "loss": 4.6833, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834013927224389e-05, "loss": 4.675, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833176970353711e-05, "loss": 4.7029, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832338375602659e-05, "loss": 4.6967, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831499780851606e-05, "loss": 4.6819, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830661186100554e-05, "loss": 4.678, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829822591349502e-05, "loss": 4.6853, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828985634478824e-05, "loss": 4.6695, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828147039727771e-05, "loss": 4.687, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827308444976719e-05, "loss": 4.6578, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826469850225667e-05, "loss": 4.682, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825631255474615e-05, "loss": 4.6739, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824792660723563e-05, "loss": 4.6568, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823954065972511e-05, "loss": 4.6549, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.82311547122146e-05, "loss": 4.6691, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222801522311535e-05, "loss": 4.6315, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214415574801015e-05, "loss": 4.654, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206029627290495e-05, "loss": 4.6645, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197643679779975e-05, "loss": 4.656, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189274111073184e-05, "loss": 4.6474, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180888163562664e-05, "loss": 4.6334, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172502216052144e-05, "loss": 4.639, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164116268541624e-05, "loss": 4.6418, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815574669983483e-05, "loss": 4.6485, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814736075232432e-05, "loss": 4.6363, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.81389748048138e-05, "loss": 4.6456, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813058885730328e-05, "loss": 4.649, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812220290979276e-05, "loss": 4.6462, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811381696228224e-05, "loss": 4.6283, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810543101477172e-05, "loss": 4.6338, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.80970450672612e-05, "loss": 4.6326, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808867549855441e-05, "loss": 4.625, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808028955104389e-05, "loss": 4.6308, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807190360353337e-05, "loss": 4.6205, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806351765602285e-05, "loss": 4.6291, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805514808731606e-05, "loss": 4.6264, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804676213980554e-05, "loss": 4.6066, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803837619229502e-05, "loss": 4.6191, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8029990244784504e-05, "loss": 4.6188, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021604297273984e-05, "loss": 4.6249, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801323472856719e-05, "loss": 4.6154, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800484878105667e-05, "loss": 4.6108, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799646283354615e-05, "loss": 4.6036, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798807688603563e-05, "loss": 4.5998, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797970731732884e-05, "loss": 4.604, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797132136981832e-05, "loss": 4.6104, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.79629354223078e-05, "loss": 4.6054, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795454947479728e-05, "loss": 4.6106, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794616352728676e-05, "loss": 4.6005, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.595, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5925, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792102206355894e-05, "loss": 4.5972, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791263611604842e-05, "loss": 4.6017, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.79042501685379e-05, "loss": 4.6028, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895880599831107e-05, "loss": 4.5901, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887494652320587e-05, "loss": 4.5824, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879108704810067e-05, "loss": 4.5922, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870722757299546e-05, "loss": 4.577, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786233680978902e-05, "loss": 4.584, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853967241082236e-05, "loss": 4.5802, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845581293571715e-05, "loss": 4.5804, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837195346061195e-05, "loss": 4.5706, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828809398550675e-05, "loss": 4.5814, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820423451040155e-05, "loss": 4.5675, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781205388233337e-05, "loss": 4.5722, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803667934822844e-05, "loss": 4.5762, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795281987312324e-05, "loss": 4.5642, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786896039801804e-05, "loss": 4.5851, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777852647109502e-05, "loss": 4.5813, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777014052358449e-05, "loss": 4.5737, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776175457607397e-05, "loss": 4.5632, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775336862856345e-05, "loss": 4.5608, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774499905985666e-05, "loss": 4.5673, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773661311234615e-05, "loss": 4.5617, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772822716483563e-05, "loss": 4.5727, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771984121732511e-05, "loss": 4.5525, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771145526981459e-05, "loss": 4.5608, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770306932230407e-05, "loss": 4.5584, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769468337479355e-05, "loss": 4.5635, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768629742728303e-05, "loss": 4.546, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767792785857624e-05, "loss": 4.5561, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766954191106572e-05, "loss": 4.5529, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.76611559635552e-05, "loss": 4.555, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765277001604468e-05, "loss": 4.5589, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764438406853416e-05, "loss": 4.5623, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763599812102364e-05, "loss": 4.5398, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762761217351312e-05, "loss": 4.5484, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.76192262260026e-05, "loss": 4.5526, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610856657295813e-05, "loss": 4.5491, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602470709785293e-05, "loss": 4.5443, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.75941011410785e-05, "loss": 4.5479, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758571519356798e-05, "loss": 4.5424, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757732924605746e-05, "loss": 4.5595, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756894329854694e-05, "loss": 4.5306, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756055735103642e-05, "loss": 4.5488, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.75521714035259e-05, "loss": 4.5361, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543785456015375e-05, "loss": 4.5327, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753541588730859e-05, "loss": 4.5343, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752702993979807e-05, "loss": 4.5265, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751864399228755e-05, "loss": 4.5283, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751025804477703e-05, "loss": 4.534, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750187209726651e-05, "loss": 4.5274, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.494524002075195, "eval_runtime": 288.449, "eval_samples_per_second": 1322.906, "eval_steps_per_second": 41.342, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749348614975599e-05, "loss": 4.5262, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748510020224547e-05, "loss": 4.5186, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747671425473495e-05, "loss": 4.5382, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746832830722443e-05, "loss": 4.5264, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745994235971391e-05, "loss": 4.5361, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745155641220339e-05, "loss": 4.5141, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744317046469287e-05, "loss": 4.5224, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743478451718235e-05, "loss": 4.5078, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742639856967183e-05, "loss": 4.5174, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741801262216131e-05, "loss": 4.5193, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740962667465079e-05, "loss": 4.5152, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401240727140264e-05, "loss": 4.5262, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739287115843348e-05, "loss": 4.5013, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384485210922966e-05, "loss": 4.5182, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376099263412446e-05, "loss": 4.5033, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736771331590192e-05, "loss": 4.5029, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.73593273683914e-05, "loss": 4.5036, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735094142088088e-05, "loss": 4.5115, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734255547337036e-05, "loss": 4.5026, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733416952585984e-05, "loss": 4.5215, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732578357834932e-05, "loss": 4.5029, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.73173976308388e-05, "loss": 4.5042, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730901168332828e-05, "loss": 4.503, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730062573581776e-05, "loss": 4.5126, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729225616711097e-05, "loss": 4.4995, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728387021960045e-05, "loss": 4.503, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727548427208993e-05, "loss": 4.4894, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267098324579415e-05, "loss": 4.4941, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725874513467635e-05, "loss": 4.4833, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725035918716583e-05, "loss": 4.4986, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724197323965531e-05, "loss": 4.4974, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723358729214479e-05, "loss": 4.4935, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722520134463427e-05, "loss": 4.5015, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721681539712375e-05, "loss": 4.4897, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720844582841696e-05, "loss": 4.4901, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720005988090644e-05, "loss": 4.4915, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719169031219965e-05, "loss": 4.4862, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718330436468914e-05, "loss": 4.4764, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717491841717862e-05, "loss": 4.4676, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.71665324696681e-05, "loss": 4.4776, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715814652215758e-05, "loss": 4.4798, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714976057464706e-05, "loss": 4.4838, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714137462713654e-05, "loss": 4.4753, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713298867962602e-05, "loss": 4.4687, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.71246027321155e-05, "loss": 4.4825, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711623316340871e-05, "loss": 4.473, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710784721589819e-05, "loss": 4.4749, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099461268387667e-05, "loss": 4.4669, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091075320877147e-05, "loss": 4.4554, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082689373366627e-05, "loss": 4.4871, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074319804659836e-05, "loss": 4.4797, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706593385714932e-05, "loss": 4.4676, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.70575479096388e-05, "loss": 4.4653, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704916196212828e-05, "loss": 4.4741, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040776014617755e-05, "loss": 4.4556, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703240644591097e-05, "loss": 4.4764, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702402049840045e-05, "loss": 4.4508, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015634550889924e-05, "loss": 4.469, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.4738, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699887903467262e-05, "loss": 4.4546, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.69904930871621e-05, "loss": 4.4467, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982107139651573e-05, "loss": 4.465, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4352, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4534, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4594, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694857972841323e-05, "loss": 4.4581, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694019378090271e-05, "loss": 4.4516, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693180783339219e-05, "loss": 4.4364, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692342188588167e-05, "loss": 4.4406, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691503593837115e-05, "loss": 4.4428, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690666636966436e-05, "loss": 4.4552, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689828042215384e-05, "loss": 4.4428, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.4518, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.458, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.455, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686473663211176e-05, "loss": 4.4371, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856367063404974e-05, "loss": 4.4433, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847981115894454e-05, "loss": 4.4492, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839595168383934e-05, "loss": 4.4361, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683122559967714e-05, "loss": 4.4411, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682283965216662e-05, "loss": 4.4373, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68144537046561e-05, "loss": 4.4382, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.4438, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679769818843879e-05, "loss": 4.4227, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678931224092827e-05, "loss": 4.4412, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678092629341775e-05, "loss": 4.4312, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677254034590723e-05, "loss": 4.4441, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676415439839671e-05, "loss": 4.4348, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4311, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.4247, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673899655586516e-05, "loss": 4.4232, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673061060835464e-05, "loss": 4.4229, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672222466084412e-05, "loss": 4.4311, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671383871333359e-05, "loss": 4.4378, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670545276582307e-05, "loss": 4.4318, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669708319711629e-05, "loss": 4.4237, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688713628409496e-05, "loss": 4.4198, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680327680898976e-05, "loss": 4.4215, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6671941733388456e-05, "loss": 4.4234, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663555785877936e-05, "loss": 4.4318, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655169838367416e-05, "loss": 4.4312, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.4199, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663841432215011e-05, "loss": 4.4116, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663002837463959e-05, "loss": 4.4286, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621642427129065e-05, "loss": 4.4094, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613256479618545e-05, "loss": 4.4189, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604870532108025e-05, "loss": 4.411, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596500963401234e-05, "loss": 4.4159, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588115015890714e-05, "loss": 4.4065, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579729068380194e-05, "loss": 4.417, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571343120869674e-05, "loss": 4.4063, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562957173359154e-05, "loss": 4.4024, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554571225848634e-05, "loss": 4.4189, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546185278338114e-05, "loss": 4.3986, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65377993308276e-05, "loss": 4.4243, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652941338331708e-05, "loss": 4.4206, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652104381461029e-05, "loss": 4.4142, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651265786709977e-05, "loss": 4.4049, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650427191958925e-05, "loss": 4.403, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649588597207873e-05, "loss": 4.4038, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648751640337194e-05, "loss": 4.4043, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647914683466515e-05, "loss": 4.4138, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647076088715463e-05, "loss": 4.3966, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646237493964411e-05, "loss": 4.4073, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645398899213359e-05, "loss": 4.4052, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644560304462307e-05, "loss": 4.4055, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437217097112554e-05, "loss": 4.3951, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428831149602034e-05, "loss": 4.4013, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420445202091514e-05, "loss": 4.401, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412059254580994e-05, "loss": 4.403, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403673307070474e-05, "loss": 4.4031, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639528735955995e-05, "loss": 4.4114, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638690141204943e-05, "loss": 4.3866, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637853184334264e-05, "loss": 4.3996, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637014589583212e-05, "loss": 4.4052, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361759948321596e-05, "loss": 4.3959, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353374000811076e-05, "loss": 4.3934, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634500443210429e-05, "loss": 4.4041, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633663486339751e-05, "loss": 4.3935, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632824891588699e-05, "loss": 4.4104, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.63198793471802e-05, "loss": 4.3835, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631149339966968e-05, "loss": 4.397, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630310745215916e-05, "loss": 4.3932, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629472150464864e-05, "loss": 4.3882, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628633555713812e-05, "loss": 4.3865, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6277949609627597e-05, "loss": 4.3833, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626956366211707e-05, "loss": 4.3806, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626117771460655e-05, "loss": 4.3906, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625279176709603e-05, "loss": 4.3857, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.3582868576049805, "eval_runtime": 293.5432, "eval_samples_per_second": 1299.948, "eval_steps_per_second": 40.624, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244422198389246e-05, "loss": 4.3887, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.6236036250878726e-05, "loss": 4.3754, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227650303368205e-05, "loss": 4.3947, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219264355857685e-05, "loss": 4.3826, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210878408347165e-05, "loss": 4.3988, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202492460836645e-05, "loss": 4.3769, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194106513326125e-05, "loss": 4.3828, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185720565815605e-05, "loss": 4.3684, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177350997108814e-05, "loss": 4.3816, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168965049598294e-05, "loss": 4.382, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160579102087774e-05, "loss": 4.3795, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152193154577254e-05, "loss": 4.3837, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614382358587046e-05, "loss": 4.3677, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613545401716368e-05, "loss": 4.3831, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612706806965316e-05, "loss": 4.3696, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611868212214264e-05, "loss": 4.3639, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611029617463212e-05, "loss": 4.3692, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.61019102271216e-05, "loss": 4.3744, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609354065841481e-05, "loss": 4.3704, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608515471090429e-05, "loss": 4.3866, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607676876339377e-05, "loss": 4.3714, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606838281588325e-05, "loss": 4.3769, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.605999686837273e-05, "loss": 4.3679, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605161092086221e-05, "loss": 4.3785, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604322497335169e-05, "loss": 4.368, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603483902584117e-05, "loss": 4.3728, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602645307833065e-05, "loss": 4.3629, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601806713082013e-05, "loss": 4.3584, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009697562113344e-05, "loss": 4.3592, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001311614602824e-05, "loss": 4.3679, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5992925667092303e-05, "loss": 4.37, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.5984539719581783e-05, "loss": 4.3664, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976153772071257e-05, "loss": 4.3754, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.59678005821682e-05, "loss": 4.3645, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595941463465768e-05, "loss": 4.36, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595102868714716e-05, "loss": 4.3633, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594264273963664e-05, "loss": 4.3668, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593425679212612e-05, "loss": 4.3479, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.59258708446156e-05, "loss": 4.3428, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591748489710508e-05, "loss": 4.3506, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590909894959456e-05, "loss": 4.3588, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590071300208404e-05, "loss": 4.3584, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589232705457352e-05, "loss": 4.3526, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5883941107063e-05, "loss": 4.3427, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587557153835621e-05, "loss": 4.3586, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586718559084569e-05, "loss": 4.3524, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585879964333517e-05, "loss": 4.3523, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585041369582465e-05, "loss": 4.3456, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584202774831413e-05, "loss": 4.3306, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583364180080361e-05, "loss": 4.3749, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582527223209682e-05, "loss": 4.3568, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.58168862845863e-05, "loss": 4.3493, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808500337075786e-05, "loss": 4.3493, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.5800114389565266e-05, "loss": 4.3509, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791728442054746e-05, "loss": 4.3403, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783358873347955e-05, "loss": 4.3533, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5774972925837435e-05, "loss": 4.3367, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.5766586978326915e-05, "loss": 4.3481, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758201030816395e-05, "loss": 4.3593, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5749815083305875e-05, "loss": 4.338, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741429135795355e-05, "loss": 4.3261, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733043188284835e-05, "loss": 4.3532, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724657240774315e-05, "loss": 4.3204, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716287672067524e-05, "loss": 4.3331, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570791810336074e-05, "loss": 4.346, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569953215585022e-05, "loss": 4.3441, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.56911462083397e-05, "loss": 4.3354, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568276026082918e-05, "loss": 4.3288, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567437431331866e-05, "loss": 4.3209, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566598836580814e-05, "loss": 4.3281, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565760241829762e-05, "loss": 4.3445, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564921647078709e-05, "loss": 4.3284, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564084690208031e-05, "loss": 4.3444, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563246095456979e-05, "loss": 4.3405, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562407500705927e-05, "loss": 4.3471, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561568905954874e-05, "loss": 4.3282, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560731949084196e-05, "loss": 4.3286, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559893354333144e-05, "loss": 4.3388, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559054759582092e-05, "loss": 4.324, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558217802711413e-05, "loss": 4.3378, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557379207960361e-05, "loss": 4.3254, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556540613209309e-05, "loss": 4.3274, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557020184582566e-05, "loss": 4.3353, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548634237072046e-05, "loss": 4.3179, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.5540248289561526e-05, "loss": 4.3285, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.5531862342051006e-05, "loss": 4.3276, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523476394540486e-05, "loss": 4.3344, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515090447029966e-05, "loss": 4.3233, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506720878323175e-05, "loss": 4.327, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498334930812655e-05, "loss": 4.3156, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.548994898330214e-05, "loss": 4.3153, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548156303579162e-05, "loss": 4.3196, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.54731770882811e-05, "loss": 4.324, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546479114077058e-05, "loss": 4.3319, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545642157206379e-05, "loss": 4.3303, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544803562455327e-05, "loss": 4.3201, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543964967704275e-05, "loss": 4.3138, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543126372953223e-05, "loss": 4.3171, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542289416082544e-05, "loss": 4.3218, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541450821331492e-05, "loss": 4.3253, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.54061222658044e-05, "loss": 4.3271, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539773631829388e-05, "loss": 4.317, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538935037078336e-05, "loss": 4.3099, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538096442327284e-05, "loss": 4.328, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372578475762326e-05, "loss": 4.3029, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364192528251806e-05, "loss": 4.3195, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5355822959545015e-05, "loss": 4.3065, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347437012034495e-05, "loss": 4.3141, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339051064523975e-05, "loss": 4.3064, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330665117013455e-05, "loss": 4.314, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532227916950293e-05, "loss": 4.3067, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5313909600796144e-05, "loss": 4.302, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305523653285624e-05, "loss": 4.3139, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297137705775104e-05, "loss": 4.3027, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528875175826458e-05, "loss": 4.3223, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280365810754064e-05, "loss": 4.3231, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527199624204728e-05, "loss": 4.3175, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526361029453675e-05, "loss": 4.3067, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525522434702623e-05, "loss": 4.3067, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524683839951571e-05, "loss": 4.3046, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523845245200519e-05, "loss": 4.3072, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523006650449467e-05, "loss": 4.3175, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522168055698415e-05, "loss": 4.2948, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521329460947363e-05, "loss": 4.3092, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520492504076684e-05, "loss": 4.3055, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519655547206005e-05, "loss": 4.312, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518816952454953e-05, "loss": 4.2991, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517978357703902e-05, "loss": 4.3067, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517141400833223e-05, "loss": 4.2991, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516302806082171e-05, "loss": 4.3151, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.5154642113311187e-05, "loss": 4.3065, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.5146256165800667e-05, "loss": 4.3162, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5137870218290147e-05, "loss": 4.2916, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.5129484270779626e-05, "loss": 4.3078, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121098323269106e-05, "loss": 4.3099, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5112712375758586e-05, "loss": 4.296, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104326428248066e-05, "loss": 4.3028, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5095940480737546e-05, "loss": 4.3106, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087570912030755e-05, "loss": 4.3006, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079184964520235e-05, "loss": 4.3186, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070799017009715e-05, "loss": 4.2898, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062413069499195e-05, "loss": 4.3069, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505404350079241e-05, "loss": 4.2947, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504565755328189e-05, "loss": 4.2977, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503727160577137e-05, "loss": 4.2981, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502888565826085e-05, "loss": 4.2905, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502049971075033e-05, "loss": 4.288, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501211376323981e-05, "loss": 4.2969, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500372781572929e-05, "loss": 4.2964, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.2750773429870605, "eval_runtime": 293.1439, "eval_samples_per_second": 1301.719, "eval_steps_per_second": 40.68, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.4995341868218764e-05, "loss": 4.2958, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4986955920708244e-05, "loss": 4.2852, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.4978569973197724e-05, "loss": 4.3043, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970184025687204e-05, "loss": 4.293, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4961798078176684e-05, "loss": 4.3037, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953412130666164e-05, "loss": 4.2926, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494502618315565e-05, "loss": 4.2921, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493664023564513e-05, "loss": 4.2802, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492825428813461e-05, "loss": 4.2896, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491986834062409e-05, "loss": 4.2923, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491148239311357e-05, "loss": 4.2916, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490309644560305e-05, "loss": 4.2929, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489472687689626e-05, "loss": 4.2806, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488634092938574e-05, "loss": 4.2963, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487795498187522e-05, "loss": 4.2803, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486958541316843e-05, "loss": 4.2775, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486119946565791e-05, "loss": 4.281, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485281351814739e-05, "loss": 4.2898, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484442757063687e-05, "loss": 4.2827, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483604162312635e-05, "loss": 4.2987, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482765567561583e-05, "loss": 4.2862, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481926972810531e-05, "loss": 4.2932, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481088378059479e-05, "loss": 4.2809, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480249783308427e-05, "loss": 4.2902, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479411188557375e-05, "loss": 4.2834, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478572593806323e-05, "loss": 4.288, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477733999055271e-05, "loss": 4.2782, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476897042184592e-05, "loss": 4.2767, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.47605844743354e-05, "loss": 4.2726, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475219852682488e-05, "loss": 4.2809, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474381257931436e-05, "loss": 4.2861, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473542663180384e-05, "loss": 4.2828, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472704068429332e-05, "loss": 4.2886, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471867111558653e-05, "loss": 4.2777, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471028516807601e-05, "loss": 4.2777, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470189922056549e-05, "loss": 4.2856, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469351327305497e-05, "loss": 4.2844, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468512732554445e-05, "loss": 4.2607, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467674137803393e-05, "loss": 4.2671, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466837180932714e-05, "loss": 4.265, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.465998586181662e-05, "loss": 4.2714, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.46515999143061e-05, "loss": 4.2813, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464321396679558e-05, "loss": 4.2696, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463484439808879e-05, "loss": 4.2651, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462645845057827e-05, "loss": 4.2755, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461807250306775e-05, "loss": 4.2689, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460968655555724e-05, "loss": 4.2737, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460130060804672e-05, "loss": 4.268, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4592931039339926e-05, "loss": 4.2446, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584545091829406e-05, "loss": 4.2936, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576159144318886e-05, "loss": 4.2772, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4567773196808366e-05, "loss": 4.2751, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455938724929784e-05, "loss": 4.2675, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455100130178732e-05, "loss": 4.2674, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542631733080535e-05, "loss": 4.2608, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534262164373744e-05, "loss": 4.2699, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4525876216863224e-05, "loss": 4.2617, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517490269352704e-05, "loss": 4.2662, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450910432184219e-05, "loss": 4.2816, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.4500718374331664e-05, "loss": 4.2594, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.4492332426821144e-05, "loss": 4.2508, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4483946479310624e-05, "loss": 4.2747, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475560531800104e-05, "loss": 4.2426, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446719096309331e-05, "loss": 4.2581, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445880501558279e-05, "loss": 4.2659, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445041906807227e-05, "loss": 4.2655, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444203312056175e-05, "loss": 4.2577, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443366355185496e-05, "loss": 4.2551, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442527760434444e-05, "loss": 4.2392, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441689165683393e-05, "loss": 4.2539, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440850570932341e-05, "loss": 4.2646, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440011976181289e-05, "loss": 4.255, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439173381430237e-05, "loss": 4.2615, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438334786679185e-05, "loss": 4.2676, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437497829808506e-05, "loss": 4.2746, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436660872937827e-05, "loss": 4.2516, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.4358222781867747e-05, "loss": 4.2493, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4349836834357227e-05, "loss": 4.2652, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341450886846707e-05, "loss": 4.2448, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333064939336186e-05, "loss": 4.2649, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324678991825666e-05, "loss": 4.25, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316293044315146e-05, "loss": 4.2513, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4307907096804626e-05, "loss": 4.2634, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429952114929411e-05, "loss": 4.2422, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429113520178359e-05, "loss": 4.2523, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.428274925427307e-05, "loss": 4.2503, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427436330676255e-05, "loss": 4.2621, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426599373805576e-05, "loss": 4.2458, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425760779054524e-05, "loss": 4.2544, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424922184303472e-05, "loss": 4.2432, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.42408358955242e-05, "loss": 4.2444, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423248270562114e-05, "loss": 4.2422, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422409675811062e-05, "loss": 4.2521, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.42157108106001e-05, "loss": 4.2584, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420732486308958e-05, "loss": 4.2536, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419893891557907e-05, "loss": 4.2526, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419055296806855e-05, "loss": 4.2402, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.4182183399361756e-05, "loss": 4.2437, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4173797451851236e-05, "loss": 4.2472, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165411504340716e-05, "loss": 4.2536, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157025556830196e-05, "loss": 4.254, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4148672366927134e-05, "loss": 4.2441, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140286419416614e-05, "loss": 4.2397, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4131900471906094e-05, "loss": 4.2568, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123514524395574e-05, "loss": 4.2326, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115128576885054e-05, "loss": 4.247, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4106742629374534e-05, "loss": 4.238, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409835668186402e-05, "loss": 4.2452, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.40899707343535e-05, "loss": 4.2346, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081584786842974e-05, "loss": 4.2447, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073198839332453e-05, "loss": 4.2333, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.4064812891821933e-05, "loss": 4.2345, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056426944311413e-05, "loss": 4.243, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404804099680089e-05, "loss": 4.2353, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403965504929037e-05, "loss": 4.2501, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403126910177985e-05, "loss": 4.254, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402289953307306e-05, "loss": 4.2439, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401451358556254e-05, "loss": 4.2417, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400612763805202e-05, "loss": 4.2321, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.39977416905415e-05, "loss": 4.2376, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398935574303098e-05, "loss": 4.2368, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.39809861743242e-05, "loss": 4.2531, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397260022681368e-05, "loss": 4.2227, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396421427930316e-05, "loss": 4.2415, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395582833179264e-05, "loss": 4.2369, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394745876308585e-05, "loss": 4.2417, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393907281557533e-05, "loss": 4.2327, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.3930703246868536e-05, "loss": 4.2389, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.3922317299358016e-05, "loss": 4.2284, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3913931351847496e-05, "loss": 4.2459, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905545404336976e-05, "loss": 4.2412, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897159456826456e-05, "loss": 4.2438, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3888773509315936e-05, "loss": 4.2273, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388038756180542e-05, "loss": 4.2393, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.38720016142949e-05, "loss": 4.2423, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386361566678438e-05, "loss": 4.2302, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385522971927386e-05, "loss": 4.2351, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3846843771763336e-05, "loss": 4.2437, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.3838457824252816e-05, "loss": 4.231, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.3830071876742296e-05, "loss": 4.2556, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.3821685929231775e-05, "loss": 4.2251, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.3813299981721255e-05, "loss": 4.2382, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.3804914034210735e-05, "loss": 4.2279, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.3796544465503944e-05, "loss": 4.2325, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378817489679716e-05, "loss": 4.2333, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.377978894928664e-05, "loss": 4.2245, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771419380579856e-05, "loss": 4.2265, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763033433069336e-05, "loss": 4.2206, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375464748555881e-05, "loss": 4.2348, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.217353343963623, "eval_runtime": 294.6691, "eval_samples_per_second": 1294.981, "eval_steps_per_second": 40.469, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374626153804829e-05, "loss": 4.2351, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373787559053777e-05, "loss": 4.2208, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372948964302725e-05, "loss": 4.2363, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372110369551673e-05, "loss": 4.2326, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371271774800621e-05, "loss": 4.2341, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370433180049569e-05, "loss": 4.226, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369594585298517e-05, "loss": 4.227, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368755990547465e-05, "loss": 4.2156, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367917395796413e-05, "loss": 4.2251, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.3670804389257345e-05, "loss": 4.228, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.3662418441746825e-05, "loss": 4.2298, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.3654032494236305e-05, "loss": 4.2242, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.3645662925529514e-05, "loss": 4.2222, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.3637276978018994e-05, "loss": 4.2263, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.3628891030508474e-05, "loss": 4.2174, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.3620505082997954e-05, "loss": 4.2101, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.3612119135487434e-05, "loss": 4.2188, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360374956678064e-05, "loss": 4.2245, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359536361927012e-05, "loss": 4.2206, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.35869776717596e-05, "loss": 4.2341, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357859172424908e-05, "loss": 4.2259, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357020577673856e-05, "loss": 4.2302, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356181982922804e-05, "loss": 4.218, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355343388171752e-05, "loss": 4.2259, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.3545047934207e-05, "loss": 4.2199, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353667836550022e-05, "loss": 4.227, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352830879679343e-05, "loss": 4.2175, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.351992284928291e-05, "loss": 4.2122, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351153690177239e-05, "loss": 4.211, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350315095426187e-05, "loss": 4.222, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349476500675134e-05, "loss": 4.2209, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486395438044556e-05, "loss": 4.2222, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478009490534036e-05, "loss": 4.225, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469623543023516e-05, "loss": 4.2197, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.3461237595512996e-05, "loss": 4.2161, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3452851648002476e-05, "loss": 4.2242, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444465700491956e-05, "loss": 4.2207, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436079752981436e-05, "loss": 4.2044, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3427710184274645e-05, "loss": 4.2058, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419324236764125e-05, "loss": 4.2041, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3410938289253605e-05, "loss": 4.2059, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402552341743085e-05, "loss": 4.2213, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394182773036294e-05, "loss": 4.2101, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3385796825525774e-05, "loss": 4.2036, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377410878015254e-05, "loss": 4.2159, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369024930504734e-05, "loss": 4.208, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3360638982994214e-05, "loss": 4.2149, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.33522530354837e-05, "loss": 4.2049, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334386708797318e-05, "loss": 4.1849, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333548114046266e-05, "loss": 4.2359, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332711157175587e-05, "loss": 4.2134, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331874200304908e-05, "loss": 4.2177, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331035605553856e-05, "loss": 4.2031, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330197010802804e-05, "loss": 4.2129, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329358416051752e-05, "loss": 4.2021, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.3285198213007e-05, "loss": 4.2069, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327681226549648e-05, "loss": 4.2063, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326842631798596e-05, "loss": 4.2058, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326005674927917e-05, "loss": 4.2249, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.3251670801768654e-05, "loss": 4.1977, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.3243301233061863e-05, "loss": 4.1894, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323491528555134e-05, "loss": 4.2168, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322652933804082e-05, "loss": 4.1854, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.32181433905303e-05, "loss": 4.1956, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.320975744301978e-05, "loss": 4.2117, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320137149550926e-05, "loss": 4.2112, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319298554799874e-05, "loss": 4.195, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318459960048822e-05, "loss": 4.2029, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317623003178143e-05, "loss": 4.1802, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316784408427091e-05, "loss": 4.1993, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315945813676039e-05, "loss": 4.2054, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315107218924987e-05, "loss": 4.1953, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314270262054309e-05, "loss": 4.2062, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313431667303257e-05, "loss": 4.2077, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312593072552205e-05, "loss": 4.2196, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311754477801153e-05, "loss": 4.1921, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.3109158830501e-05, "loss": 4.197, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310077288299048e-05, "loss": 4.2104, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309238693547996e-05, "loss": 4.1893, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308400098796944e-05, "loss": 4.2046, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307561504045892e-05, "loss": 4.1967, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.30672290929484e-05, "loss": 4.1952, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305885952424161e-05, "loss": 4.2095, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305047357673109e-05, "loss": 4.1889, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042087629220577e-05, "loss": 4.1922, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3033701681710057e-05, "loss": 4.2001, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025315734199536e-05, "loss": 4.2043, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3016929786689016e-05, "loss": 4.191, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008543839178496e-05, "loss": 4.2, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000157891667976e-05, "loss": 4.1827, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2991788322961185e-05, "loss": 4.1934, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.2983418754254395e-05, "loss": 4.1892, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.2975032806743874e-05, "loss": 4.1968, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2966646859233354e-05, "loss": 4.209, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958260911722834e-05, "loss": 4.1961, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2949874964212314e-05, "loss": 4.1971, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294150539550553e-05, "loss": 4.187, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293311944799501e-05, "loss": 4.19, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292473350048449e-05, "loss": 4.1928, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291634755297397e-05, "loss": 4.2012, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290796160546345e-05, "loss": 4.1966, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289957565795293e-05, "loss": 4.1976, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289118971044241e-05, "loss": 4.1873, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288280376293189e-05, "loss": 4.2008, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.28744341942251e-05, "loss": 4.1791, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286604824671458e-05, "loss": 4.1943, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285767867800779e-05, "loss": 4.1794, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284929273049727e-05, "loss": 4.1966, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284090678298675e-05, "loss": 4.1835, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283252083547623e-05, "loss": 4.1888, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824151266769444e-05, "loss": 4.1834, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2815765319258924e-05, "loss": 4.1824, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807379371748404e-05, "loss": 4.1866, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2798993424237884e-05, "loss": 4.1842, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2790607476727364e-05, "loss": 4.1954, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278222152921684e-05, "loss": 4.2001, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277383558170632e-05, "loss": 4.1935, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.27654496341958e-05, "loss": 4.1945, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275706368668528e-05, "loss": 4.1763, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274867773917476e-05, "loss": 4.1841, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.2740291791664237e-05, "loss": 4.1874, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2731905844153717e-05, "loss": 4.1977, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272353627544693e-05, "loss": 4.1705, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271515032793641e-05, "loss": 4.1887, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270676438042589e-05, "loss": 4.1893, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.26983948117191e-05, "loss": 4.1849, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269000886420858e-05, "loss": 4.1823, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268162291669806e-05, "loss": 4.1897, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267323696918754e-05, "loss": 4.1784, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266485102167702e-05, "loss": 4.1931, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.26564650741665e-05, "loss": 4.1902, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264809550545971e-05, "loss": 4.1922, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.263970955794919e-05, "loss": 4.1765, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263132361043867e-05, "loss": 4.1892, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.262293766292815e-05, "loss": 4.1914, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261455171541763e-05, "loss": 4.1797, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260616576790712e-05, "loss": 4.1846, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.2597796199200326e-05, "loss": 4.1905, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.2589426630493535e-05, "loss": 4.1858, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.2581040682983015e-05, "loss": 4.2009, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.2572671114276224e-05, "loss": 4.178, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.2564285166765704e-05, "loss": 4.1862, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.2555899219255184e-05, "loss": 4.1804, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2547513271744664e-05, "loss": 4.1835, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539127324234144e-05, "loss": 4.1771, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.2530741376723624e-05, "loss": 4.1728, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.2522355429213104e-05, "loss": 4.1814, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2513969481702584e-05, "loss": 4.1694, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250558353419207e-05, "loss": 4.1869, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.17576265335083, "eval_runtime": 291.3672, "eval_samples_per_second": 1309.657, "eval_steps_per_second": 40.928, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249719758668155e-05, "loss": 4.1877, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.2488811639171024e-05, "loss": 4.1711, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.2480425691660504e-05, "loss": 4.1857, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.2472039744149984e-05, "loss": 4.18, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.2463653796639464e-05, "loss": 4.1882, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.2455267849128943e-05, "loss": 4.1773, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.2446881901618423e-05, "loss": 4.1795, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.24384959541079e-05, "loss": 4.1674, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243011000659738e-05, "loss": 4.1771, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242172405908686e-05, "loss": 4.1802, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241333811157634e-05, "loss": 4.1802, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240495216406582e-05, "loss": 4.1757, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239658259535903e-05, "loss": 4.1744, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238819664784852e-05, "loss": 4.1768, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2379810700338e-05, "loss": 4.1746, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237142475282748e-05, "loss": 4.1608, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236303880531696e-05, "loss": 4.1717, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235465285780644e-05, "loss": 4.1765, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234626691029591e-05, "loss": 4.1743, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233788096278539e-05, "loss": 4.1847, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.232949501527487e-05, "loss": 4.1816, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232110906776435e-05, "loss": 4.1841, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.231272312025383e-05, "loss": 4.1666, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230433717274331e-05, "loss": 4.1787, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229598398284026e-05, "loss": 4.1754, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228759803532974e-05, "loss": 4.1786, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227921208781922e-05, "loss": 4.1684, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.22708261403087e-05, "loss": 4.1692, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226244019279818e-05, "loss": 4.1661, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254054245287657e-05, "loss": 4.1704, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2245684676580866e-05, "loss": 4.1714, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237298729070346e-05, "loss": 4.1789, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.2228912781559826e-05, "loss": 4.1795, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.2220526834049306e-05, "loss": 4.1757, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.2212157265342515e-05, "loss": 4.1699, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.2203771317831995e-05, "loss": 4.1722, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219540174912521e-05, "loss": 4.1773, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218701580161469e-05, "loss": 4.1612, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217862985410417e-05, "loss": 4.1565, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217024390659365e-05, "loss": 4.1565, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216185795908313e-05, "loss": 4.1639, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215347201157261e-05, "loss": 4.1701, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214508606406209e-05, "loss": 4.1666, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.213670011655157e-05, "loss": 4.1627, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.212831416904105e-05, "loss": 4.1669, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.211992822153053e-05, "loss": 4.165, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211154227402001e-05, "loss": 4.1681, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210315632650949e-05, "loss": 4.1597, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209477037899897e-05, "loss": 4.1424, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208638443148845e-05, "loss": 4.1858, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207799848397792e-05, "loss": 4.17, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.206961253646741e-05, "loss": 4.1745, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061242967760626e-05, "loss": 4.1618, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.20528570202501e-05, "loss": 4.1659, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204447107273958e-05, "loss": 4.1618, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203608512522906e-05, "loss": 4.1619, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202769917771854e-05, "loss": 4.1652, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201932960901175e-05, "loss": 4.1595, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.201094366150123e-05, "loss": 4.1808, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200255771399071e-05, "loss": 4.1569, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994188145283924e-05, "loss": 4.1468, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.19858021977734e-05, "loss": 4.1718, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197741625026288e-05, "loss": 4.1426, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969030302752363e-05, "loss": 4.1453, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1960644355241843e-05, "loss": 4.1707, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952258407731323e-05, "loss": 4.1662, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.19438724602208e-05, "loss": 4.1493, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193548651271028e-05, "loss": 4.1625, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192711694400349e-05, "loss": 4.137, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.191873099649297e-05, "loss": 4.1559, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191034504898245e-05, "loss": 4.1601, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190195910147193e-05, "loss": 4.155, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189358953276514e-05, "loss": 4.1625, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188520358525462e-05, "loss": 4.1623, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.18768176377441e-05, "loss": 4.1737, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186843169023358e-05, "loss": 4.1514, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.18600621215268e-05, "loss": 4.1538, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185167617401628e-05, "loss": 4.1641, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184329022650576e-05, "loss": 4.1487, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183490427899524e-05, "loss": 4.1605, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.1826551089092175e-05, "loss": 4.1556, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.1818165141581655e-05, "loss": 4.1518, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.1809779194071135e-05, "loss": 4.1717, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.1801393246560615e-05, "loss": 4.1442, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.1793007299050095e-05, "loss": 4.1477, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.1784621351539575e-05, "loss": 4.1588, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.1776235404029055e-05, "loss": 4.1613, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1767849456518535e-05, "loss": 4.1514, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.175947988781175e-05, "loss": 4.1579, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175111031910496e-05, "loss": 4.1396, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174272437159444e-05, "loss": 4.1488, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173433842408392e-05, "loss": 4.1485, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.17259524765734e-05, "loss": 4.154, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171756652906288e-05, "loss": 4.1663, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170918058155236e-05, "loss": 4.1526, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170079463404184e-05, "loss": 4.1557, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169240868653132e-05, "loss": 4.1477, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.16840227390208e-05, "loss": 4.1466, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167563679151028e-05, "loss": 4.1489, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166725084399975e-05, "loss": 4.1606, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165886489648923e-05, "loss": 4.156, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165049532778245e-05, "loss": 4.1564, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642125759075664e-05, "loss": 4.143, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1633739811565144e-05, "loss": 4.1564, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625353864054624e-05, "loss": 4.1427, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1616967916544104e-05, "loss": 4.1521, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160859834783731e-05, "loss": 4.1375, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160021240032679e-05, "loss": 4.1538, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159182645281627e-05, "loss": 4.1422, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158344050530575e-05, "loss": 4.1489, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575054557795226e-05, "loss": 4.139, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1566668610284706e-05, "loss": 4.148, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155829904157792e-05, "loss": 4.1429, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.15499130940674e-05, "loss": 4.1403, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154152714655688e-05, "loss": 4.1584, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153314119904636e-05, "loss": 4.1587, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152475525153584e-05, "loss": 4.1541, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151636930402532e-05, "loss": 4.1491, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.15079833565148e-05, "loss": 4.1393, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.149959740900428e-05, "loss": 4.1439, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149122784029749e-05, "loss": 4.1479, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148284189278697e-05, "loss": 4.1516, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147445594527645e-05, "loss": 4.1333, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146606999776593e-05, "loss": 4.149, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145768405025541e-05, "loss": 4.1486, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144931448154863e-05, "loss": 4.1454, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144092853403811e-05, "loss": 4.1418, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1432542586527587e-05, "loss": 4.1462, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424156639017067e-05, "loss": 4.1381, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1415787070310276e-05, "loss": 4.1563, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.1407401122799756e-05, "loss": 4.1516, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.1399015175289236e-05, "loss": 4.1502, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.1390629227778716e-05, "loss": 4.1346, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.1382259659071925e-05, "loss": 4.1536, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.1373873711561405e-05, "loss": 4.1497, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.1365487764050885e-05, "loss": 4.1393, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357118195344094e-05, "loss": 4.1481, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134874862663731e-05, "loss": 4.148, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.134036267912679e-05, "loss": 4.1444, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133197673161627e-05, "loss": 4.1619, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132359078410575e-05, "loss": 4.1375, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131520483659523e-05, "loss": 4.1472, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.130681888908471e-05, "loss": 4.1446, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.129843294157419e-05, "loss": 4.1437, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.129004699406367e-05, "loss": 4.136, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128166104655315e-05, "loss": 4.133, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.127327509904263e-05, "loss": 4.1396, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.126488915153211e-05, "loss": 4.1337, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125650320402159e-05, "loss": 4.1461, "step": 534016 }, { "epoch": 0.03, "eval_loss": 4.14478063583374, "eval_runtime": 294.6857, "eval_samples_per_second": 1294.908, "eval_steps_per_second": 40.467, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248150014118534e-05, "loss": 4.1446, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.1239764066608014e-05, "loss": 4.1332, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.1231378119097494e-05, "loss": 4.1452, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.1222992171586974e-05, "loss": 4.1421, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.1214606224076454e-05, "loss": 4.1471, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.1206220276565934e-05, "loss": 4.1392, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.1197834329055414e-05, "loss": 4.1432, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.118944838154489e-05, "loss": 4.1318, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.11810788128381e-05, "loss": 4.1304, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117270924413131e-05, "loss": 4.1464, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116432329662079e-05, "loss": 4.1415, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115593734911027e-05, "loss": 4.1344, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114756778040348e-05, "loss": 4.1455, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.113918183289297e-05, "loss": 4.1318, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113079588538245e-05, "loss": 4.1317, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112240993787193e-05, "loss": 4.1251, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.111402399036141e-05, "loss": 4.1336, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110563804285089e-05, "loss": 4.1379, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109725209534036e-05, "loss": 4.1321, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108886614782984e-05, "loss": 4.1482, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108048020031932e-05, "loss": 4.1428, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.10720942528088e-05, "loss": 4.1445, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106370830529828e-05, "loss": 4.132, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105532235778776e-05, "loss": 4.1363, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104695278908097e-05, "loss": 4.1452, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103856684157045e-05, "loss": 4.1374, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.1030197272863665e-05, "loss": 4.1305, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.1021811325353145e-05, "loss": 4.1346, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.1013425377842625e-05, "loss": 4.1241, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005039430332105e-05, "loss": 4.1335, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0996653482821585e-05, "loss": 4.1343, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.0988267535311065e-05, "loss": 4.1413, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0979881587800545e-05, "loss": 4.1411, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0971512019093754e-05, "loss": 4.1401, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963126071583234e-05, "loss": 4.1335, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0954740124072714e-05, "loss": 4.1329, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0946354176562194e-05, "loss": 4.1388, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.09379846078554e-05, "loss": 4.1242, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.092959866034489e-05, "loss": 4.1217, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.092121271283437e-05, "loss": 4.1188, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.091282676532385e-05, "loss": 4.1273, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.090444081781333e-05, "loss": 4.1297, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.089605487030281e-05, "loss": 4.1322, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088766892279229e-05, "loss": 4.1268, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087928297528177e-05, "loss": 4.1279, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087089702777125e-05, "loss": 4.1302, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086251108026072e-05, "loss": 4.1349, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.08541251327502e-05, "loss": 4.1225, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084575556404342e-05, "loss": 4.1062, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.08373696165329e-05, "loss": 4.1441, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082898366902237e-05, "loss": 4.1347, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082059772151186e-05, "loss": 4.1403, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081221177400134e-05, "loss": 4.1244, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080382582649082e-05, "loss": 4.1288, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079545625778403e-05, "loss": 4.1246, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078707031027351e-05, "loss": 4.1247, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077868436276299e-05, "loss": 4.1326, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077029841525247e-05, "loss": 4.117, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076191246774195e-05, "loss": 4.1466, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075355927783889e-05, "loss": 4.1258, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074517333032837e-05, "loss": 4.105, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0736787382817845e-05, "loss": 4.1362, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0728401435307325e-05, "loss": 4.112, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.072001548779681e-05, "loss": 4.1093, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071162954028629e-05, "loss": 4.1355, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070324359277577e-05, "loss": 4.128, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069485764526525e-05, "loss": 4.115, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068647169775473e-05, "loss": 4.1249, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067808575024421e-05, "loss": 4.1047, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.066969980273369e-05, "loss": 4.118, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.066131385522317e-05, "loss": 4.1249, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065294428651638e-05, "loss": 4.1176, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064455833900586e-05, "loss": 4.1265, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063617239149534e-05, "loss": 4.1232, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062778644398482e-05, "loss": 4.138, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.06194004964743e-05, "loss": 4.1163, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061101454896378e-05, "loss": 4.1201, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.060262860145326e-05, "loss": 4.1279, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.059424265394274e-05, "loss": 4.1145, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0585873085235956e-05, "loss": 4.1257, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0577487137725436e-05, "loss": 4.1205, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.056910119021491e-05, "loss": 4.1129, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056071524270439e-05, "loss": 4.1341, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.055232929519387e-05, "loss": 4.1084, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.0543959726487085e-05, "loss": 4.1121, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053557377897656e-05, "loss": 4.124, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052718783146604e-05, "loss": 4.1229, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.051880188395552e-05, "loss": 4.1149, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.0510448694052463e-05, "loss": 4.1241, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.0502062746541943e-05, "loss": 4.1037, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049367679903143e-05, "loss": 4.1108, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048529085152091e-05, "loss": 4.114, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047690490401038e-05, "loss": 4.1163, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046851895649986e-05, "loss": 4.1319, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.046013300898934e-05, "loss": 4.119, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045174706147882e-05, "loss": 4.1228, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044337749277203e-05, "loss": 4.112, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043500792406525e-05, "loss": 4.1136, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042662197655473e-05, "loss": 4.1149, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041823602904421e-05, "loss": 4.1245, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.040985008153368e-05, "loss": 4.1223, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040146413402317e-05, "loss": 4.1232, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039307818651265e-05, "loss": 4.113, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038470861780586e-05, "loss": 4.117, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037633904909907e-05, "loss": 4.1115, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036795310158855e-05, "loss": 4.1152, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.035956715407803e-05, "loss": 4.1038, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.0351181206567506e-05, "loss": 4.1212, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.0342795259056986e-05, "loss": 4.1083, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.0334409311546466e-05, "loss": 4.1142, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.0326023364035946e-05, "loss": 4.1057, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.0317637416525426e-05, "loss": 4.1124, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.0309251469014906e-05, "loss": 4.1111, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.0300865521504386e-05, "loss": 4.1085, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.0292479573993866e-05, "loss": 4.1208, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.028409362648335e-05, "loss": 4.1266, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.027572405777656e-05, "loss": 4.1251, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.026733811026604e-05, "loss": 4.1141, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.025895216275552e-05, "loss": 4.105, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.025058259404873e-05, "loss": 4.109, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.024219664653821e-05, "loss": 4.1143, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.023381069902769e-05, "loss": 4.117, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.022542475151717e-05, "loss": 4.0999, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.021703880400665e-05, "loss": 4.1167, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.020866923529986e-05, "loss": 4.1165, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.020028328778934e-05, "loss": 4.1088, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019189734027882e-05, "loss": 4.1084, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.0183527771572035e-05, "loss": 4.1148, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.0175141824061515e-05, "loss": 4.1057, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.0166755876550995e-05, "loss": 4.1213, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.0158369929040475e-05, "loss": 4.1133, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.0149983981529955e-05, "loss": 4.12, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.0141598034019435e-05, "loss": 4.102, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.0133212086508915e-05, "loss": 4.1204, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.0124826138998395e-05, "loss": 4.1174, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011644019148787e-05, "loss": 4.1076, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010805424397735e-05, "loss": 4.1149, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.0099684675270564e-05, "loss": 4.1132, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.0091298727760044e-05, "loss": 4.1143, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.0082912780249524e-05, "loss": 4.1307, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.0074526832739004e-05, "loss": 4.1025, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.0066140885228484e-05, "loss": 4.1165, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.0057754937717964e-05, "loss": 4.1122, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.0049368990207444e-05, "loss": 4.1119, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.0040983042696924e-05, "loss": 4.1041, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003261347399013e-05, "loss": 4.0998, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002422752647961e-05, "loss": 4.1098, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001585795777282e-05, "loss": 4.1006, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.00074720102623e-05, "loss": 4.1147, "step": 610304 }, { "epoch": 1.03, "eval_loss": 4.119741916656494, "eval_runtime": 295.1931, "eval_samples_per_second": 1292.683, "eval_steps_per_second": 40.397, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.999908606275178e-05, "loss": 4.1065, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999070011524126e-05, "loss": 4.1047, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.998231416773074e-05, "loss": 4.112, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997392822022022e-05, "loss": 4.1107, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996554227270971e-05, "loss": 4.1156, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.995715632519919e-05, "loss": 4.1081, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994877037768867e-05, "loss": 4.1144, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994038443017815e-05, "loss": 4.0992, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993199848266763e-05, "loss": 4.099, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992361253515711e-05, "loss": 4.116, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991522658764658e-05, "loss": 4.109, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990684064013606e-05, "loss": 4.1025, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.989847107142928e-05, "loss": 4.115, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.989008512391876e-05, "loss": 4.0985, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.988169917640823e-05, "loss": 4.103, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.987331322889771e-05, "loss": 4.0881, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.986492728138719e-05, "loss": 4.1038, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.985654133387668e-05, "loss": 4.1096, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.984815538636616e-05, "loss": 4.0968, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.983976943885564e-05, "loss": 4.116, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.983138349134512e-05, "loss": 4.1141, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9822997543834597e-05, "loss": 4.1105, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9814611596324077e-05, "loss": 4.1042, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9806225648813557e-05, "loss": 4.1066, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.9797856080106766e-05, "loss": 4.1101, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.9789470132596246e-05, "loss": 4.1053, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.9781084185085726e-05, "loss": 4.096, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.9772714616378935e-05, "loss": 4.1058, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.9764328668868415e-05, "loss": 4.0938, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.9755942721357895e-05, "loss": 4.1017, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.9747556773847374e-05, "loss": 4.1015, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.973917082633686e-05, "loss": 4.1066, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973080125763007e-05, "loss": 4.1113, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972241531011955e-05, "loss": 4.1132, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971402936260903e-05, "loss": 4.0965, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970565979390224e-05, "loss": 4.1042, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.969727384639172e-05, "loss": 4.1102, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.96888878988812e-05, "loss": 4.0916, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968050195137068e-05, "loss": 4.093, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967211600386016e-05, "loss": 4.0922, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966373005634964e-05, "loss": 4.0909, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965534410883912e-05, "loss": 4.1006, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.96469581613286e-05, "loss": 4.1019, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963857221381808e-05, "loss": 4.0933, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.963018626630756e-05, "loss": 4.0953, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962180031879704e-05, "loss": 4.097, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961341437128652e-05, "loss": 4.1074, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960504480257973e-05, "loss": 4.0875, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.9596675233872944e-05, "loss": 4.08, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958828928636242e-05, "loss": 4.1094, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.95799033388519e-05, "loss": 4.1031, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957151739134138e-05, "loss": 4.108, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956313144383086e-05, "loss": 4.0943, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.9554761875124066e-05, "loss": 4.0969, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.9546375927613546e-05, "loss": 4.0959, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.953800635890676e-05, "loss": 4.0944, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.952962041139624e-05, "loss": 4.1015, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.952123446388572e-05, "loss": 4.0845, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.95128485163752e-05, "loss": 4.1204, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950446256886468e-05, "loss": 4.091, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949607662135416e-05, "loss": 4.0762, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.948769067384364e-05, "loss": 4.1063, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.947930472633312e-05, "loss": 4.087, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.94709187788226e-05, "loss": 4.0771, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946253283131208e-05, "loss": 4.1038, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945414688380156e-05, "loss": 4.0997, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944576093629104e-05, "loss": 4.0903, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943739136758425e-05, "loss": 4.0919, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.942900542007373e-05, "loss": 4.0741, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942061947256322e-05, "loss": 4.0861, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.94122335250527e-05, "loss": 4.0976, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.9403863956345906e-05, "loss": 4.0905, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.9395478008835386e-05, "loss": 4.0943, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.9387108440128595e-05, "loss": 4.0916, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.9378722492618075e-05, "loss": 4.1084, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.9370336545107555e-05, "loss": 4.0897, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.9361950597597035e-05, "loss": 4.0918, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.9353564650086515e-05, "loss": 4.0946, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.9345178702575995e-05, "loss": 4.0886, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.9336792755065475e-05, "loss": 4.0975, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.9328406807554955e-05, "loss": 4.0896, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932003723884817e-05, "loss": 4.0875, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931165129133765e-05, "loss": 4.1027, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930326534382713e-05, "loss": 4.079, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.929489577512034e-05, "loss": 4.0844, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.928650982760982e-05, "loss": 4.0909, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.92781238800993e-05, "loss": 4.0941, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.926973793258878e-05, "loss": 4.0831, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926135198507825e-05, "loss": 4.0965, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925296603756773e-05, "loss": 4.0806, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924458009005721e-05, "loss": 4.0834, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.923619414254669e-05, "loss": 4.0809, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922784095264364e-05, "loss": 4.0859, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.9219471383936854e-05, "loss": 4.1019, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.9211085436426334e-05, "loss": 4.0876, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.9202699488915813e-05, "loss": 4.0921, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.9194313541405293e-05, "loss": 4.0838, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918592759389477e-05, "loss": 4.0835, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917754164638425e-05, "loss": 4.0864, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.9169155698873727e-05, "loss": 4.0957, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.9160769751363206e-05, "loss": 4.0937, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.9152383803852686e-05, "loss": 4.0913, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9143997856342166e-05, "loss": 4.0912, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9135611908831646e-05, "loss": 4.0873, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9127225961321126e-05, "loss": 4.0851, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911885639261434e-05, "loss": 4.0859, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.911047044510382e-05, "loss": 4.0751, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.91020844975933e-05, "loss": 4.0911, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909369855008278e-05, "loss": 4.0809, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.908531260257226e-05, "loss": 4.0834, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907694303386547e-05, "loss": 4.0807, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906855708635495e-05, "loss": 4.0781, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.906017113884443e-05, "loss": 4.0847, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905178519133391e-05, "loss": 4.0793, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904341562262712e-05, "loss": 4.0959, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.90350296751166e-05, "loss": 4.0958, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9026660106409816e-05, "loss": 4.0943, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.9018274158899296e-05, "loss": 4.0855, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.9009904590192505e-05, "loss": 4.0805, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.9001518642681985e-05, "loss": 4.079, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.8993132695171465e-05, "loss": 4.0876, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.8984746747660945e-05, "loss": 4.0915, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.8976360800150425e-05, "loss": 4.0741, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.8967974852639905e-05, "loss": 4.0845, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.8959588905129385e-05, "loss": 4.0881, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.8951219336422594e-05, "loss": 4.0844, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.8942833388912074e-05, "loss": 4.0793, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.8934447441401554e-05, "loss": 4.0856, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.8926061493891034e-05, "loss": 4.0762, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.8917675546380514e-05, "loss": 4.0941, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.8909289598869994e-05, "loss": 4.0846, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.890090365135948e-05, "loss": 4.0962, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889251770384896e-05, "loss": 4.0769, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.888413175633844e-05, "loss": 4.0879, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.887574580882791e-05, "loss": 4.0925, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.886737624012113e-05, "loss": 4.0814, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.885899029261061e-05, "loss": 4.0849, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.885060434510009e-05, "loss": 4.0867, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.884221839758956e-05, "loss": 4.0832, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.883383245007904e-05, "loss": 4.1008, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882544650256852e-05, "loss": 4.0796, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.8817060555058e-05, "loss": 4.0891, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880867460754748e-05, "loss": 4.0861, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.88003050388407e-05, "loss": 4.0833, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879191909133018e-05, "loss": 4.0766, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878353314381966e-05, "loss": 4.0749, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877516357511287e-05, "loss": 4.08, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876677762760235e-05, "loss": 4.0777, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875839168009183e-05, "loss": 4.0844, "step": 686592 }, { "epoch": 0.03, "eval_loss": 4.099898815155029, "eval_runtime": 286.0052, "eval_samples_per_second": 1334.21, "eval_steps_per_second": 41.695, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875000573258131e-05, "loss": 4.0793, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874161978507079e-05, "loss": 4.0783, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873323383756027e-05, "loss": 4.0808, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872484789004975e-05, "loss": 4.0872, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871646194253923e-05, "loss": 4.092, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870807599502871e-05, "loss": 4.0819, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.8699706426321916e-05, "loss": 4.083, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.86913204788114e-05, "loss": 4.0733, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.868293453130088e-05, "loss": 4.0744, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.867454858379036e-05, "loss": 4.0843, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.866617901508357e-05, "loss": 4.0827, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865779306757305e-05, "loss": 4.0779, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.864943987766999e-05, "loss": 4.0875, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864105393015947e-05, "loss": 4.0729, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.863266798264895e-05, "loss": 4.0749, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.862428203513843e-05, "loss": 4.0593, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861589608762791e-05, "loss": 4.0812, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860751014011739e-05, "loss": 4.0814, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.859912419260687e-05, "loss": 4.0708, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.8590738245096356e-05, "loss": 4.0884, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.8582368676389565e-05, "loss": 4.0857, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.8573982728879045e-05, "loss": 4.0865, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.8565596781368525e-05, "loss": 4.0796, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.8557210833858005e-05, "loss": 4.0802, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.8548824886347485e-05, "loss": 4.0814, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.8540438938836965e-05, "loss": 4.0832, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.8532052991326445e-05, "loss": 4.0658, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.852366704381592e-05, "loss": 4.0804, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.85152810963054e-05, "loss": 4.0673, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.8506911527598614e-05, "loss": 4.0764, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.849854195889182e-05, "loss": 4.0779, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849015601138131e-05, "loss": 4.0833, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.848177006387079e-05, "loss": 4.0767, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.847338411636027e-05, "loss": 4.0888, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846499816884975e-05, "loss": 4.0721, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845662860014296e-05, "loss": 4.0776, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.844824265263244e-05, "loss": 4.0824, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.843985670512192e-05, "loss": 4.0621, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843147075761139e-05, "loss": 4.0662, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.842308481010087e-05, "loss": 4.0706, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841469886259035e-05, "loss": 4.0652, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840631291507983e-05, "loss": 4.0737, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839794334637305e-05, "loss": 4.0811, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.838955739886253e-05, "loss": 4.0672, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.838117145135201e-05, "loss": 4.0732, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837278550384149e-05, "loss": 4.0705, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836439955633097e-05, "loss": 4.0775, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835601360882045e-05, "loss": 4.0632, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834762766130993e-05, "loss": 4.0565, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.833924171379941e-05, "loss": 4.0833, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.8330872145092616e-05, "loss": 4.078, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.8322486197582096e-05, "loss": 4.0885, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.8314100250071576e-05, "loss": 4.0657, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.8305714302561056e-05, "loss": 4.0702, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.8297344733854265e-05, "loss": 4.0718, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.828897516514748e-05, "loss": 4.0668, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.828058921763696e-05, "loss": 4.0815, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827220327012644e-05, "loss": 4.0546, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826381732261592e-05, "loss": 4.0959, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.82554313751054e-05, "loss": 4.07, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824704542759488e-05, "loss": 4.0487, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.823865948008436e-05, "loss": 4.0773, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.823027353257384e-05, "loss": 4.0637, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822188758506332e-05, "loss": 4.0512, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.82135016375528e-05, "loss": 4.0754, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.820511569004228e-05, "loss": 4.0782, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.8196729742531754e-05, "loss": 4.0615, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.8188343795021234e-05, "loss": 4.0701, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.817999060511818e-05, "loss": 4.048, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.8171604657607666e-05, "loss": 4.063, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.8163218710097146e-05, "loss": 4.0685, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.8154832762586626e-05, "loss": 4.064, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.8146463193879835e-05, "loss": 4.0759, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.8138077246369315e-05, "loss": 4.062, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.8129691298858795e-05, "loss": 4.0861, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.8121305351348275e-05, "loss": 4.0655, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.8112919403837755e-05, "loss": 4.0691, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810453345632723e-05, "loss": 4.0687, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.809614750881671e-05, "loss": 4.0621, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808776156130619e-05, "loss": 4.0697, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.807937561379567e-05, "loss": 4.0626, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807098966628515e-05, "loss": 4.0696, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.8062603718774634e-05, "loss": 4.0726, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.8054217771264114e-05, "loss": 4.0626, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804584820255732e-05, "loss": 4.0558, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.803747863385053e-05, "loss": 4.066, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.802909268634001e-05, "loss": 4.0727, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.802070673882949e-05, "loss": 4.0582, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.801232079131897e-05, "loss": 4.0673, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.800393484380845e-05, "loss": 4.0543, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.799554889629793e-05, "loss": 4.0614, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.798717932759114e-05, "loss": 4.0591, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797879338008062e-05, "loss": 4.0631, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.79704074325701e-05, "loss": 4.0759, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.796202148505959e-05, "loss": 4.0648, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795363553754907e-05, "loss": 4.069, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.794526596884228e-05, "loss": 4.0595, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793688002133176e-05, "loss": 4.059, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792849407382124e-05, "loss": 4.0625, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792010812631072e-05, "loss": 4.0707, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.79117221788002e-05, "loss": 4.0704, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790333623128968e-05, "loss": 4.067, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789495028377916e-05, "loss": 4.065, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788656433626864e-05, "loss": 4.0606, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.7878194767561846e-05, "loss": 4.0643, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.7869808820051326e-05, "loss": 4.0611, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.7861422872540806e-05, "loss": 4.0562, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7853036925030286e-05, "loss": 4.0648, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.78446673563235e-05, "loss": 4.0572, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.783628140881298e-05, "loss": 4.0591, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.782789546130246e-05, "loss": 4.0551, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.781950951379194e-05, "loss": 4.0535, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.781113994508515e-05, "loss": 4.0611, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.780275399757463e-05, "loss": 4.0538, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.779436805006411e-05, "loss": 4.0689, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778598210255359e-05, "loss": 4.069, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.77776125338468e-05, "loss": 4.0754, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.776922658633628e-05, "loss": 4.0627, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.776084063882576e-05, "loss": 4.0582, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.7752471070118975e-05, "loss": 4.0529, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.7744085122608455e-05, "loss": 4.0687, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.7735699175097935e-05, "loss": 4.0651, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.7727313227587415e-05, "loss": 4.048, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771892728007689e-05, "loss": 4.0606, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771054133256637e-05, "loss": 4.0626, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770215538505585e-05, "loss": 4.0616, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769376943754533e-05, "loss": 4.0568, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768539986883854e-05, "loss": 4.0607, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767701392132802e-05, "loss": 4.0522, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.76686279738175e-05, "loss": 4.0723, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766024202630698e-05, "loss": 4.0616, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765187245760019e-05, "loss": 4.0699, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764348651008967e-05, "loss": 4.0527, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.763510056257915e-05, "loss": 4.0665, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.762671461506863e-05, "loss": 4.0693, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.761834504636184e-05, "loss": 4.0549, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.760995909885132e-05, "loss": 4.0639, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.76015731513408e-05, "loss": 4.0618, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759320358263401e-05, "loss": 4.0657, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.758481763512349e-05, "loss": 4.0739, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.757643168761297e-05, "loss": 4.0595, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.756804574010245e-05, "loss": 4.0626, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.755965979259193e-05, "loss": 4.063, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755127384508141e-05, "loss": 4.061, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.7542904276374627e-05, "loss": 4.0539, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.7534518328864107e-05, "loss": 4.0523, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.7526132381353586e-05, "loss": 4.0547, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.7517746433843066e-05, "loss": 4.055, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.7509360486332546e-05, "loss": 4.0589, "step": 762880 }, { "epoch": 1.03, "eval_loss": 4.083510875701904, "eval_runtime": 283.4154, "eval_samples_per_second": 1346.402, "eval_steps_per_second": 42.076, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.7500974538822026e-05, "loss": 4.059, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.7492588591311506e-05, "loss": 4.0533, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.7484202643800986e-05, "loss": 4.0576, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.7475816696290466e-05, "loss": 4.0637, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.7467430748779946e-05, "loss": 4.0705, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.7459044801269426e-05, "loss": 4.0576, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.74506588537589e-05, "loss": 4.0631, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.744227290624838e-05, "loss": 4.0519, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.7433886958737866e-05, "loss": 4.0487, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.7425501011227346e-05, "loss": 4.0568, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.7417115063716826e-05, "loss": 4.0647, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.7408729116206306e-05, "loss": 4.0564, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.7400359547499515e-05, "loss": 4.0634, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.7391973599988995e-05, "loss": 4.0482, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.7383587652478475e-05, "loss": 4.0552, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.7375201704967955e-05, "loss": 4.0329, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.7366815757457435e-05, "loss": 4.0593, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.7358429809946915e-05, "loss": 4.0581, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.7350043862436395e-05, "loss": 4.0472, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.7341657914925875e-05, "loss": 4.0639, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.7333271967415355e-05, "loss": 4.0652, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.7324886019904835e-05, "loss": 4.0639, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.7316500072394315e-05, "loss": 4.053, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.7308114124883794e-05, "loss": 4.0578, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.729976093498074e-05, "loss": 4.0586, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729137498747022e-05, "loss": 4.0619, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.72829890399597e-05, "loss": 4.0421, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.727460309244918e-05, "loss": 4.0555, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726621714493866e-05, "loss": 4.0482, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725784757623187e-05, "loss": 4.049, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.724946162872135e-05, "loss": 4.0575, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.724107568121083e-05, "loss": 4.0592, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.723268973370031e-05, "loss": 4.0563, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.722430378618979e-05, "loss": 4.0661, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.7215934217483e-05, "loss": 4.0524, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720756464877621e-05, "loss": 4.0565, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.719917870126569e-05, "loss": 4.0632, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.719079275375517e-05, "loss": 4.0386, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718240680624465e-05, "loss": 4.0428, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.717402085873413e-05, "loss": 4.0472, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.716565129002734e-05, "loss": 4.0377, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.715726534251682e-05, "loss": 4.0525, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.71488793950063e-05, "loss": 4.0597, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.714049344749578e-05, "loss": 4.0439, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.713212387878899e-05, "loss": 4.0504, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.712373793127847e-05, "loss": 4.0505, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711535198376795e-05, "loss": 4.0521, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.710696603625744e-05, "loss": 4.0419, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709858008874691e-05, "loss": 4.0336, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709019414123639e-05, "loss": 4.0577, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.708180819372587e-05, "loss": 4.0591, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707342224621535e-05, "loss": 4.0673, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.706503629870483e-05, "loss": 4.0451, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705665035119431e-05, "loss": 4.046, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.704826440368379e-05, "loss": 4.0506, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.703987845617327e-05, "loss": 4.0455, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.703150888746648e-05, "loss": 4.0605, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.702312293995596e-05, "loss": 4.0312, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.7014753371249176e-05, "loss": 4.0746, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.7006367423738655e-05, "loss": 4.0509, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.6997981476228135e-05, "loss": 4.0284, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.6989595528717615e-05, "loss": 4.0537, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.6981209581207095e-05, "loss": 4.0414, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6972823633696575e-05, "loss": 4.0296, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.6964437686186055e-05, "loss": 4.0556, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.6956051738675535e-05, "loss": 4.0552, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.6947665791165015e-05, "loss": 4.04, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.6939296222458224e-05, "loss": 4.0535, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693092665375143e-05, "loss": 4.0244, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.692254070624091e-05, "loss": 4.0423, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691415475873039e-05, "loss": 4.0409, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690576881121987e-05, "loss": 4.0455, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689738286370936e-05, "loss": 4.0484, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.688899691619884e-05, "loss": 4.042, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688062734749205e-05, "loss": 4.0664, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687224139998153e-05, "loss": 4.045, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686385545247101e-05, "loss": 4.0499, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685546950496049e-05, "loss": 4.0439, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684708355744997e-05, "loss": 4.0397, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.683869760993945e-05, "loss": 4.0485, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.683031166242892e-05, "loss": 4.0416, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.682194209372214e-05, "loss": 4.0455, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.681355614621162e-05, "loss": 4.0563, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.68051701987011e-05, "loss": 4.0415, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.679678425119058e-05, "loss": 4.0315, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.6788414682483794e-05, "loss": 4.0426, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6780028734973274e-05, "loss": 4.0528, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.677164278746275e-05, "loss": 4.0333, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676325683995223e-05, "loss": 4.0502, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675488727124544e-05, "loss": 4.0396, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.674650132373492e-05, "loss": 4.0349, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.6738115376224396e-05, "loss": 4.0381, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.6729729428713876e-05, "loss": 4.038, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.6721343481203356e-05, "loss": 4.0596, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.6712957533692836e-05, "loss": 4.0416, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.6704587964986045e-05, "loss": 4.0474, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669620201747553e-05, "loss": 4.0398, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668781606996501e-05, "loss": 4.0383, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.667943012245449e-05, "loss": 4.0389, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667104417494397e-05, "loss": 4.0501, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666265822743345e-05, "loss": 4.0498, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.665428865872666e-05, "loss": 4.046, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.664590271121614e-05, "loss": 4.0458, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663751676370562e-05, "loss": 4.0356, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.66291308161951e-05, "loss": 4.047, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662074486868458e-05, "loss": 4.0389, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.661239167878152e-05, "loss": 4.0347, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.6604005731271e-05, "loss": 4.0396, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.6595619783760485e-05, "loss": 4.0391, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.6587233836249965e-05, "loss": 4.0394, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.6578847888739445e-05, "loss": 4.032, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.6570461941228925e-05, "loss": 4.0314, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.6562075993718405e-05, "loss": 4.0409, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.6553690046207885e-05, "loss": 4.0423, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.6545304098697365e-05, "loss": 4.0443, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.6536918151186845e-05, "loss": 4.049, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.6528532203676325e-05, "loss": 4.0564, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.6520162634969534e-05, "loss": 4.0396, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.6511776687459014e-05, "loss": 4.0397, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.6503390739948494e-05, "loss": 4.0321, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.6495004792437974e-05, "loss": 4.045, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.648663522373118e-05, "loss": 4.0438, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.647824927622067e-05, "loss": 4.0329, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.646987970751388e-05, "loss": 4.0342, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646149376000336e-05, "loss": 4.0465, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645310781249284e-05, "loss": 4.0424, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644472186498232e-05, "loss": 4.0328, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.643635229627553e-05, "loss": 4.0377, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.642796634876501e-05, "loss": 4.0368, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.641958040125449e-05, "loss": 4.0469, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.641119445374397e-05, "loss": 4.0441, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.640280850623345e-05, "loss": 4.0492, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.639442255872293e-05, "loss": 4.0339, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.638603661121241e-05, "loss": 4.0457, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637765066370189e-05, "loss": 4.0484, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.636926471619137e-05, "loss": 4.031, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.636087876868085e-05, "loss": 4.0408, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635249282117033e-05, "loss": 4.0431, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.6344123252463536e-05, "loss": 4.0477, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.6335737304953016e-05, "loss": 4.0499, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.6327351357442496e-05, "loss": 4.038, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.6318965409931976e-05, "loss": 4.0421, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.6310579462421456e-05, "loss": 4.0439, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.6302193514910936e-05, "loss": 4.0379, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.6293807567400416e-05, "loss": 4.0327, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.6285421619889896e-05, "loss": 4.0336, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.6277052051183105e-05, "loss": 4.0306, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.626866610367259e-05, "loss": 4.0391, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.626028015616207e-05, "loss": 4.0397, "step": 839168 }, { "epoch": 0.03, "eval_loss": 4.069751739501953, "eval_runtime": 290.1959, "eval_samples_per_second": 1314.943, "eval_steps_per_second": 41.093, "step": 839520 }, { "epoch": 1.0, "learning_rate": 3.625189420865155e-05, "loss": 4.0365, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.624350826114103e-05, "loss": 4.0351, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.623513869243424e-05, "loss": 4.0383, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.622675274492372e-05, "loss": 4.0417, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.62183667974132e-05, "loss": 4.047, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.620998084990268e-05, "loss": 4.039, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.620161128119589e-05, "loss": 4.0431, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.619322533368537e-05, "loss": 4.0346, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.618483938617485e-05, "loss": 4.0272, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617646981746806e-05, "loss": 4.0357, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.616808386995754e-05, "loss": 4.049, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.6159697922447025e-05, "loss": 4.0313, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.6151328353740234e-05, "loss": 4.0465, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.6142942406229714e-05, "loss": 4.0262, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.6134556458719194e-05, "loss": 4.0338, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.6126170511208674e-05, "loss": 4.0166, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.6117784563698154e-05, "loss": 4.0405, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.6109398616187634e-05, "loss": 4.0367, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.6101012668677114e-05, "loss": 4.0312, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.609262672116659e-05, "loss": 4.0364, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.608424077365607e-05, "loss": 4.0504, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.607585482614555e-05, "loss": 4.042, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.606746887863503e-05, "loss": 4.0381, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.605908293112451e-05, "loss": 4.0347, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.605072974122146e-05, "loss": 4.0436, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604234379371094e-05, "loss": 4.0378, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.603395784620042e-05, "loss": 4.0272, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602557189868989e-05, "loss": 4.0341, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.601718595117937e-05, "loss": 4.0285, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.600881638247259e-05, "loss": 4.0272, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.600043043496206e-05, "loss": 4.04, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599204448745154e-05, "loss": 4.033, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.598365853994102e-05, "loss": 4.0427, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.59752725924305e-05, "loss": 4.0437, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.596688664491998e-05, "loss": 4.0313, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.59585170762132e-05, "loss": 4.0378, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.595013112870268e-05, "loss": 4.0406, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.594174518119216e-05, "loss": 4.0228, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.5933359233681637e-05, "loss": 4.0273, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.5924973286171117e-05, "loss": 4.0215, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.5916587338660597e-05, "loss": 4.0217, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.5908201391150076e-05, "loss": 4.032, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.5899831822443286e-05, "loss": 4.0416, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.5891445874932766e-05, "loss": 4.0251, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.5883059927422245e-05, "loss": 4.0269, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.5874673979911725e-05, "loss": 4.0346, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.5866288032401205e-05, "loss": 4.0326, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.5857918463694414e-05, "loss": 4.0244, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.58495325161839e-05, "loss": 4.0151, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.584114656867338e-05, "loss": 4.0362, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.583276062116286e-05, "loss": 4.0419, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.582437467365234e-05, "loss": 4.0423, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.581598872614182e-05, "loss": 4.0263, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.58076027786313e-05, "loss": 4.027, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.579923320992451e-05, "loss": 4.0299, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.579084726241399e-05, "loss": 4.0239, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.578246131490347e-05, "loss": 4.0433, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.577407536739295e-05, "loss": 4.0147, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.576568941988242e-05, "loss": 4.0513, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.57573034723719e-05, "loss": 4.0316, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.574891752486138e-05, "loss": 4.0116, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.57405479561546e-05, "loss": 4.0308, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.573216200864408e-05, "loss": 4.0233, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.572377606113356e-05, "loss": 4.0129, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.571539011362304e-05, "loss": 4.0313, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.570700416611252e-05, "loss": 4.0355, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.5698618218602e-05, "loss": 4.0225, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.569024864989521e-05, "loss": 4.0344, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.568186270238469e-05, "loss": 4.0056, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.567347675487417e-05, "loss": 4.0241, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.566509080736365e-05, "loss": 4.023, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.565670485985313e-05, "loss": 4.0283, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.564833529114634e-05, "loss": 4.0263, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.5639949343635823e-05, "loss": 4.024, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.5631563396125303e-05, "loss": 4.0444, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.562317744861478e-05, "loss": 4.0289, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.561479150110426e-05, "loss": 4.0283, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.560640555359374e-05, "loss": 4.0264, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.559803598488695e-05, "loss": 4.0218, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.558965003737643e-05, "loss": 4.0319, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.558126408986591e-05, "loss": 4.0234, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557287814235539e-05, "loss": 4.0232, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.556449219484487e-05, "loss": 4.0352, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555610624733435e-05, "loss": 4.0264, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.554773667862756e-05, "loss": 4.0095, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.553935073111704e-05, "loss": 4.0254, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.553096478360652e-05, "loss": 4.0317, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.552259521489974e-05, "loss": 4.0165, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.551420926738922e-05, "loss": 4.0273, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.55058233198787e-05, "loss": 4.024, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.549743737236818e-05, "loss": 4.0143, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.548905142485766e-05, "loss": 4.0231, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.548066547734714e-05, "loss": 4.0177, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.547227952983661e-05, "loss": 4.0382, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.546389358232609e-05, "loss": 4.0256, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.5455524013619306e-05, "loss": 4.0304, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.5447138066108786e-05, "loss": 4.0171, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.543875211859826e-05, "loss": 4.0181, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543036617108774e-05, "loss": 4.0256, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.5421980223577226e-05, "loss": 4.0302, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.5413594276066706e-05, "loss": 4.0296, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.5405224707359915e-05, "loss": 4.0269, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.5396838759849395e-05, "loss": 4.0244, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.5388452812338875e-05, "loss": 4.0155, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.5380066864828355e-05, "loss": 4.0293, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.5371680917317835e-05, "loss": 4.0197, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.5363311348611044e-05, "loss": 4.0221, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.5354925401100524e-05, "loss": 4.0192, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.5346539453590004e-05, "loss": 4.0198, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.5338153506079483e-05, "loss": 4.0213, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.5329767558568963e-05, "loss": 4.0114, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.532139798986218e-05, "loss": 4.0121, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.531301204235166e-05, "loss": 4.0244, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.530464247364487e-05, "loss": 4.0222, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.529625652613435e-05, "loss": 4.0236, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.528787057862383e-05, "loss": 4.0294, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.527948463111331e-05, "loss": 4.0381, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.527109868360279e-05, "loss": 4.0208, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.526271273609227e-05, "loss": 4.0171, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.525432678858175e-05, "loss": 4.0183, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.524594084107123e-05, "loss": 4.0243, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.523755489356071e-05, "loss": 4.0244, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.522916894605019e-05, "loss": 4.0176, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522078299853967e-05, "loss": 4.0169, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521239705102915e-05, "loss": 4.0268, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.5204027482322364e-05, "loss": 4.0184, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.5195641534811844e-05, "loss": 4.0191, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.5187255587301324e-05, "loss": 4.0253, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.51788696397908e-05, "loss": 4.0201, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.517050007108401e-05, "loss": 4.0223, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.516211412357349e-05, "loss": 4.029, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.515372817606297e-05, "loss": 4.0295, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.5145342228552446e-05, "loss": 4.0179, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.5136956281041926e-05, "loss": 4.0279, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.5128570333531406e-05, "loss": 4.031, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.5120184386020886e-05, "loss": 4.0169, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.51118148173141e-05, "loss": 4.0211, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.510344524860731e-05, "loss": 4.0256, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.50950593010968e-05, "loss": 4.031, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.508667335358627e-05, "loss": 4.0335, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.507828740607575e-05, "loss": 4.0251, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.506990145856523e-05, "loss": 4.0212, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.506151551105471e-05, "loss": 4.0256, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.505312956354419e-05, "loss": 4.0244, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.504474361603367e-05, "loss": 4.0127, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.503637404732688e-05, "loss": 4.0211, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502798809981636e-05, "loss": 4.0084, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.501960215230584e-05, "loss": 4.0197, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.501123258359905e-05, "loss": 4.0201, "step": 915456 }, { "epoch": 1.03, "eval_loss": 4.058034420013428, "eval_runtime": 291.6524, "eval_samples_per_second": 1308.376, "eval_steps_per_second": 40.888, "step": 915840 }, { "epoch": 0.0, "learning_rate": 3.5002846636088535e-05, "loss": 4.0278, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.4994460688578015e-05, "loss": 4.0125, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.4986074741067495e-05, "loss": 4.0176, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.4977688793556975e-05, "loss": 4.0322, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.4969302846046455e-05, "loss": 4.0252, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.4960916898535935e-05, "loss": 4.0267, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.4952530951025415e-05, "loss": 4.0241, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.4944145003514895e-05, "loss": 4.0166, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.4935775434808104e-05, "loss": 4.0086, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.4927389487297584e-05, "loss": 4.0251, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.4919003539787064e-05, "loss": 4.0219, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.4910617592276544e-05, "loss": 4.0211, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.490224802356975e-05, "loss": 4.0274, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.489386207605923e-05, "loss": 4.0081, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.488547612854872e-05, "loss": 4.0177, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.48770901810382e-05, "loss": 3.9988, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.486870423352768e-05, "loss": 4.0251, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.486031828601716e-05, "loss": 4.016, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.485193233850663e-05, "loss": 4.0185, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.484354639099611e-05, "loss": 4.0223, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.483516044348559e-05, "loss": 4.0296, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.482679087477881e-05, "loss": 4.0246, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.481840492726828e-05, "loss": 4.0178, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481001897975776e-05, "loss": 4.0169, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.480163303224724e-05, "loss": 4.0303, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.479324708473672e-05, "loss": 4.0203, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.47848611372262e-05, "loss": 4.0093, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.477649156851942e-05, "loss": 4.0201, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.47681056210089e-05, "loss": 4.0074, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.475971967349838e-05, "loss": 4.0155, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.475133372598786e-05, "loss": 4.0234, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474294777847734e-05, "loss": 4.0154, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.473456183096682e-05, "loss": 4.0228, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.47261758834563e-05, "loss": 4.0277, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.471778993594578e-05, "loss": 4.0162, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.4709420367238986e-05, "loss": 4.0227, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.4701034419728466e-05, "loss": 4.0245, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.4692648472217946e-05, "loss": 4.0044, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.4684262524707426e-05, "loss": 4.0126, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.4675876577196906e-05, "loss": 4.0035, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.4667490629686386e-05, "loss": 4.0071, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.46591210609796e-05, "loss": 4.0166, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.465073511346908e-05, "loss": 4.0221, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.464234916595856e-05, "loss": 4.0071, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.463396321844804e-05, "loss": 4.0129, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.462557727093752e-05, "loss": 4.0142, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.4617191323426995e-05, "loss": 4.0192, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.4608805375916475e-05, "loss": 4.0083, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.4600419428405955e-05, "loss": 3.9969, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.459204985969917e-05, "loss": 4.0161, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.4583663912188644e-05, "loss": 4.0305, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.4575277964678124e-05, "loss": 4.0267, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.456690839597134e-05, "loss": 4.0059, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455852244846082e-05, "loss": 4.0124, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.45501365009503e-05, "loss": 4.0145, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.4541783311047244e-05, "loss": 4.0012, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.4533397363536724e-05, "loss": 4.0317, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.4525011416026204e-05, "loss": 3.9953, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.4516625468515684e-05, "loss": 4.0341, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.4508239521005164e-05, "loss": 4.0135, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.4499853573494644e-05, "loss": 3.9987, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.449146762598412e-05, "loss": 4.0133, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.44830816784736e-05, "loss": 4.0098, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447469573096308e-05, "loss": 3.9943, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.446630978345256e-05, "loss": 4.0153, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.445794021474577e-05, "loss": 4.02, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.444955426723525e-05, "loss": 4.0069, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.444116831972473e-05, "loss": 4.0151, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.443278237221421e-05, "loss": 3.9902, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.442439642470369e-05, "loss": 4.0081, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.441601047719317e-05, "loss": 4.0046, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.440762452968265e-05, "loss": 4.0143, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.439923858217213e-05, "loss": 4.0069, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.439085263466161e-05, "loss": 4.01, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.438246668715109e-05, "loss": 4.0256, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.43740971184443e-05, "loss": 4.0128, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.436571117093378e-05, "loss": 4.0109, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.435732522342326e-05, "loss": 4.0096, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.434893927591274e-05, "loss": 4.0075, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.434055332840223e-05, "loss": 4.0151, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.433218375969544e-05, "loss": 4.0057, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.432379781218492e-05, "loss": 4.0132, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.43154118646744e-05, "loss": 4.0145, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.430702591716388e-05, "loss": 4.0143, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.429863996965336e-05, "loss": 3.9905, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.429025402214283e-05, "loss": 4.0122, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.428186807463231e-05, "loss": 4.0122, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.427348212712179e-05, "loss": 4.0023, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.4265128937218735e-05, "loss": 4.011, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.4256742989708215e-05, "loss": 4.0061, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.4248357042197695e-05, "loss": 4.0014, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.423998747349091e-05, "loss": 4.0034, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.423160152598039e-05, "loss": 4.0055, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.422321557846987e-05, "loss": 4.0173, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.421482963095935e-05, "loss": 4.0097, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.420644368344883e-05, "loss": 4.0136, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.4198057735938304e-05, "loss": 4.0036, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.4189671788427784e-05, "loss": 4.0037, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.4181285840917264e-05, "loss": 4.0074, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.4172899893406744e-05, "loss": 4.0157, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.4164513945896224e-05, "loss": 4.0123, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.4156127998385704e-05, "loss": 4.0114, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.4147742050875184e-05, "loss": 4.0105, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.41393724821684e-05, "loss": 4.0007, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.413098653465788e-05, "loss": 4.0126, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.412260058714736e-05, "loss": 4.0061, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.411423101844057e-05, "loss": 4.007, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.410584507093005e-05, "loss": 4.0018, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.409745912341953e-05, "loss": 4.0046, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.408907317590901e-05, "loss": 4.0043, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.408068722839849e-05, "loss": 4.0002, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.407230128088797e-05, "loss": 3.9934, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.406391533337745e-05, "loss": 4.0073, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.405552938586693e-05, "loss": 4.0133, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.404715981716014e-05, "loss": 4.0022, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.403877386964962e-05, "loss": 4.0135, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.40303879221391e-05, "loss": 4.0227, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.4022001974628584e-05, "loss": 4.0048, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.4013616027118064e-05, "loss": 4.0022, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.4005230079607544e-05, "loss": 4.0035, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.399684413209702e-05, "loss": 4.0068, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.398847456339023e-05, "loss": 4.0066, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.398008861587971e-05, "loss": 4.0025, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.397170266836919e-05, "loss": 4.0039, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.3963316720858666e-05, "loss": 4.011, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.3954930773348146e-05, "loss": 4.0033, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.3946544825837626e-05, "loss": 4.0088, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.3938158878327106e-05, "loss": 4.0052, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.392978930962032e-05, "loss": 4.004, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.39214033621098e-05, "loss": 4.0008, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.391301741459928e-05, "loss": 4.0169, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.390463146708876e-05, "loss": 4.0112, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.389624551957824e-05, "loss": 4.0023, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.388785957206772e-05, "loss": 4.0079, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.38794736245572e-05, "loss": 4.0171, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.387108767704668e-05, "loss": 3.9982, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386270172953616e-05, "loss": 4.0085, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.385433216082937e-05, "loss": 4.0096, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.384594621331885e-05, "loss": 4.0162, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.383756026580833e-05, "loss": 4.0144, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.382917431829781e-05, "loss": 4.0116, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.382080474959102e-05, "loss": 4.005, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.3812418802080507e-05, "loss": 4.0175, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.3804032854569986e-05, "loss": 4.0046, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.3795646907059466e-05, "loss": 3.9957, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.3787260959548946e-05, "loss": 4.0057, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.3778907769645885e-05, "loss": 3.9948, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.3770521822135365e-05, "loss": 4.0065, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.3762135874624845e-05, "loss": 4.002, "step": 991744 }, { "epoch": 0.03, "eval_loss": 4.048644065856934, "eval_runtime": 294.6646, "eval_samples_per_second": 1295.001, "eval_steps_per_second": 40.47, "step": 992160 }, { "epoch": 1.0, "learning_rate": 3.3753749927114324e-05, "loss": 4.0052, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.3745363979603804e-05, "loss": 3.9988, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.3736978032093284e-05, "loss": 4.0037, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.3728608463386493e-05, "loss": 4.016, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.3720222515875973e-05, "loss": 4.0084, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371183656836546e-05, "loss": 4.0148, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.370345062085494e-05, "loss": 4.0044, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.369506467334442e-05, "loss": 4.0023, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.36866787258339e-05, "loss": 3.99, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.367830915712711e-05, "loss": 4.0097, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.366992320961659e-05, "loss": 4.0061, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366153726210607e-05, "loss": 4.0055, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.365316769339928e-05, "loss": 4.017, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.364478174588876e-05, "loss": 3.9886, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.363639579837824e-05, "loss": 3.9987, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.362800985086772e-05, "loss": 3.9907, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.36196239033572e-05, "loss": 4.0036, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.361123795584668e-05, "loss": 4.0045, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.360285200833616e-05, "loss": 3.9987, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.359446606082564e-05, "loss": 4.0101, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.358608011331512e-05, "loss": 4.0119, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.35776941658046e-05, "loss": 4.0085, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.356930821829408e-05, "loss": 4.005, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.356092227078356e-05, "loss": 4.0019, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.355255270207677e-05, "loss": 4.0157, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.3544183133369976e-05, "loss": 4.0034, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.3535797185859456e-05, "loss": 3.9948, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.352742761715267e-05, "loss": 4.0048, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.351904166964215e-05, "loss": 3.9916, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.351065572213163e-05, "loss": 3.9998, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.350226977462111e-05, "loss": 4.0027, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.349388382711059e-05, "loss": 4.0012, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.348549787960007e-05, "loss": 4.0101, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.347711193208955e-05, "loss": 4.012, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.346872598457903e-05, "loss": 4.001, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.346037279467597e-05, "loss": 4.0082, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.345198684716545e-05, "loss": 4.0095, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.344360089965493e-05, "loss": 3.9911, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.343521495214441e-05, "loss": 3.9979, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.342682900463389e-05, "loss": 3.9864, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.341844305712337e-05, "loss": 3.9946, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.341005710961285e-05, "loss": 3.9967, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.340167116210233e-05, "loss": 4.0143, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.3393285214591816e-05, "loss": 3.99, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.3384899267081296e-05, "loss": 3.9963, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.3376513319570776e-05, "loss": 4.0005, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.3368127372060256e-05, "loss": 4.0016, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.3359757803353465e-05, "loss": 3.9957, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.3351371855842945e-05, "loss": 3.985, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.3343002287136154e-05, "loss": 4.0027, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.3334616339625634e-05, "loss": 4.0122, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.3326230392115114e-05, "loss": 4.0072, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.3317844444604594e-05, "loss": 3.9959, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.33094748758978e-05, "loss": 3.9925, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.330108892838728e-05, "loss": 4.0032, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.329270298087677e-05, "loss": 3.9877, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.328431703336625e-05, "loss": 4.0143, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.327594746465946e-05, "loss": 3.9845, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.326756151714894e-05, "loss": 4.018, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.325917556963842e-05, "loss": 4.0033, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.32507896221279e-05, "loss": 3.9816, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.324240367461738e-05, "loss": 3.997, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.323401772710686e-05, "loss": 3.9979, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.322564815840007e-05, "loss": 3.9817, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.321726221088955e-05, "loss": 3.9924, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.320887626337903e-05, "loss": 4.0098, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.320049031586851e-05, "loss": 3.9931, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.319210436835799e-05, "loss": 3.9961, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.318371842084747e-05, "loss": 3.9798, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.317534885214068e-05, "loss": 3.9943, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.316696290463016e-05, "loss": 3.9893, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.3158576957119636e-05, "loss": 3.9998, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.3150191009609116e-05, "loss": 3.9931, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.3141805062098596e-05, "loss": 3.9965, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.3133435493391805e-05, "loss": 4.0083, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.3125049545881285e-05, "loss": 3.9983, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.3116663598370765e-05, "loss": 3.997, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.3108277650860245e-05, "loss": 3.9986, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.3099891703349725e-05, "loss": 3.996, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.3091505755839205e-05, "loss": 3.9996, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.308311980832869e-05, "loss": 3.9899, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.307473386081817e-05, "loss": 3.9966, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.306636429211138e-05, "loss": 4.0041, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.305799472340459e-05, "loss": 3.998, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.304960877589407e-05, "loss": 3.9807, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.304122282838355e-05, "loss": 3.9961, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.303283688087303e-05, "loss": 3.9933, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.302446731216624e-05, "loss": 3.9942, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.301608136465572e-05, "loss": 3.9918, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.30076954171452e-05, "loss": 3.9989, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.299930946963468e-05, "loss": 3.9829, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.2990939900927895e-05, "loss": 3.9908, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.2982553953417375e-05, "loss": 3.9867, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.2974168005906855e-05, "loss": 4.0057, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.2965782058396335e-05, "loss": 3.9923, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.2957396110885815e-05, "loss": 4.0037, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.2949010163375295e-05, "loss": 3.9852, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.2940624215864775e-05, "loss": 3.9912, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.2932254647157984e-05, "loss": 3.9929, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.2923868699647464e-05, "loss": 4.0, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.2915482752136944e-05, "loss": 3.9999, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.2907096804626423e-05, "loss": 3.9971, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.2898710857115903e-05, "loss": 3.994, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.2890324909605383e-05, "loss": 3.9881, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.288193896209486e-05, "loss": 4.0009, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.287356939338808e-05, "loss": 3.9873, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.286518344587756e-05, "loss": 3.9907, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285681387717077e-05, "loss": 3.9912, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.284842792966025e-05, "loss": 3.9889, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284004198214973e-05, "loss": 3.9902, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.283165603463921e-05, "loss": 3.9914, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.282327008712869e-05, "loss": 3.9791, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.281488413961817e-05, "loss": 3.9933, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.280651457091138e-05, "loss": 3.9977, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.279812862340086e-05, "loss": 3.9883, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.278974267589034e-05, "loss": 4.0013, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.278135672837982e-05, "loss": 4.008, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.277298715967303e-05, "loss": 3.9926, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.276460121216251e-05, "loss": 3.9896, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.275621526465199e-05, "loss": 3.987, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.2747829317141466e-05, "loss": 3.9925, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.2739443369630946e-05, "loss": 3.9913, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.2731057422120426e-05, "loss": 3.9901, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.2722671474609906e-05, "loss": 3.9877, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.2714285527099386e-05, "loss": 3.9994, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.2705915958392595e-05, "loss": 3.9922, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.2697530010882075e-05, "loss": 3.9888, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.2689144063371555e-05, "loss": 3.9919, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.2680758115861035e-05, "loss": 3.9918, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.2672372168350515e-05, "loss": 3.9857, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.266398622084e-05, "loss": 4.004, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.265561665213321e-05, "loss": 4.0004, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.264723070462269e-05, "loss": 3.992, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.263884475711217e-05, "loss": 3.9935, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.263045880960165e-05, "loss": 3.9992, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.262207286209113e-05, "loss": 3.9904, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.261368691458061e-05, "loss": 3.994, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.260530096707009e-05, "loss": 3.9936, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.25969313983633e-05, "loss": 4.0076, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.258854545085278e-05, "loss": 3.9936, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.258015950334226e-05, "loss": 3.9999, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.257177355583174e-05, "loss": 3.9896, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.256338760832122e-05, "loss": 4.0025, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.25550016608107e-05, "loss": 3.9905, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.2546615713300186e-05, "loss": 3.9822, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.253822976578966e-05, "loss": 3.9928, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.2529860197082875e-05, "loss": 3.9805, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.2521474249572355e-05, "loss": 3.9938, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.2513104680865564e-05, "loss": 3.9871, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 4.0411176681518555, "eval_runtime": 286.0545, "eval_samples_per_second": 1333.98, "eval_steps_per_second": 41.688, "step": 1068480 }, { "epoch": 0.0, "learning_rate": 3.2504718733355044e-05, "loss": 3.9871, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.2496332785844524e-05, "loss": 3.988, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.2487946838334004e-05, "loss": 3.9874, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.247956089082348e-05, "loss": 4.0032, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.247117494331296e-05, "loss": 3.9943, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.246278899580244e-05, "loss": 4.0021, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.2454403048291924e-05, "loss": 3.9902, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.2446017100781404e-05, "loss": 3.9868, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.2437631153270884e-05, "loss": 3.9815, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.2429245205760364e-05, "loss": 3.9931, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.2420859258249843e-05, "loss": 3.9918, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.2412473310739323e-05, "loss": 3.9928, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.240410374203253e-05, "loss": 4.0051, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.239571779452201e-05, "loss": 3.9783, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.238733184701149e-05, "loss": 3.9809, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.237894589950097e-05, "loss": 3.9789, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.237055995199045e-05, "loss": 3.9862, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.236217400447993e-05, "loss": 3.9908, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.235378805696941e-05, "loss": 3.988, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.234540210945889e-05, "loss": 3.9914, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.233701616194837e-05, "loss": 4.0008, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.232863021443785e-05, "loss": 3.9908, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.232024426692733e-05, "loss": 3.9945, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.231185831941681e-05, "loss": 3.986, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.230348875071002e-05, "loss": 4.0029, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.22951028031995e-05, "loss": 3.9899, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.228671685568898e-05, "loss": 3.9858, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.227833090817846e-05, "loss": 3.9864, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.226996133947167e-05, "loss": 3.9801, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.226157539196115e-05, "loss": 3.988, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.225318944445063e-05, "loss": 3.9887, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.224481987574384e-05, "loss": 3.9893, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.2236433928233326e-05, "loss": 3.9959, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.2228047980722806e-05, "loss": 3.9985, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.2219662033212286e-05, "loss": 3.9874, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.2211292464505495e-05, "loss": 3.9957, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.2202906516994975e-05, "loss": 3.9925, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.2194520569484455e-05, "loss": 3.9798, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.2186134621973935e-05, "loss": 3.9851, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.2177748674463415e-05, "loss": 3.9713, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.2169379105756624e-05, "loss": 3.9867, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.2160993158246104e-05, "loss": 3.9838, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.2152607210735584e-05, "loss": 3.9972, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.2144221263225064e-05, "loss": 3.9765, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.2135835315714544e-05, "loss": 3.9832, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212746574700776e-05, "loss": 3.9896, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.211907979949724e-05, "loss": 3.9875, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.211069385198672e-05, "loss": 3.9874, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.21023079044762e-05, "loss": 3.9665, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.209392195696568e-05, "loss": 3.9878, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.208553600945516e-05, "loss": 3.9995, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.207715006194464e-05, "loss": 3.9955, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.206878049323785e-05, "loss": 3.9814, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.206039454572733e-05, "loss": 3.9789, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.205200859821681e-05, "loss": 3.9904, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.204362265070629e-05, "loss": 3.9745, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.203523670319577e-05, "loss": 3.9997, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.202685075568525e-05, "loss": 3.9697, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.201846480817473e-05, "loss": 4.0072, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.201007886066421e-05, "loss": 3.9895, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.2001709291957424e-05, "loss": 3.9671, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.1993323344446904e-05, "loss": 3.9807, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198493739693638e-05, "loss": 3.988, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.197656782822959e-05, "loss": 3.9668, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.196818188071907e-05, "loss": 3.9758, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.195979593320855e-05, "loss": 3.9988, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.1951409985698026e-05, "loss": 3.9841, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.1943024038187506e-05, "loss": 3.9815, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.1934638090676986e-05, "loss": 3.9637, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.1926252143166466e-05, "loss": 3.9811, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.191788257445968e-05, "loss": 3.9749, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.190949662694916e-05, "loss": 3.9921, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.190111067943864e-05, "loss": 3.9753, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.189272473192812e-05, "loss": 3.986, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.18843387844176e-05, "loss": 3.992, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.187596921571081e-05, "loss": 3.9882, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.186758326820029e-05, "loss": 3.9817, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.185919732068977e-05, "loss": 3.9824, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.185081137317925e-05, "loss": 3.986, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.184242542566873e-05, "loss": 3.986, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.183403947815821e-05, "loss": 3.9789, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.182565353064769e-05, "loss": 3.981, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.18172839619409e-05, "loss": 3.9878, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.180889801443038e-05, "loss": 3.9866, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.1800512066919866e-05, "loss": 3.9673, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.1792126119409346e-05, "loss": 3.9836, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.1783740171898826e-05, "loss": 3.9813, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.1775354224388306e-05, "loss": 3.9813, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.1766968276877786e-05, "loss": 3.9814, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.1758598708170995e-05, "loss": 3.9849, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.1750212760660475e-05, "loss": 3.973, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.1741826813149955e-05, "loss": 3.9734, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.1733440865639435e-05, "loss": 3.9754, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.1725054918128915e-05, "loss": 3.9908, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.171666897061839e-05, "loss": 3.9809, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.1708299401911604e-05, "loss": 3.9888, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.1699913454401084e-05, "loss": 3.9777, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.1691527506890564e-05, "loss": 3.9797, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.1683141559380044e-05, "loss": 3.9763, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.1674755611869524e-05, "loss": 3.99, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.1666369664359004e-05, "loss": 3.9822, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.1657983716848484e-05, "loss": 3.9851, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.1649597769337964e-05, "loss": 3.9812, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.1641211821827444e-05, "loss": 3.9731, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.163284225312065e-05, "loss": 3.9926, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.162447268441386e-05, "loss": 3.9694, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.161608673690334e-05, "loss": 3.9772, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.160770078939282e-05, "loss": 3.9825, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.15993148418823e-05, "loss": 3.9721, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.159094527317552e-05, "loss": 3.976, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.1582559325665e-05, "loss": 3.9792, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.157417337815448e-05, "loss": 3.9673, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.156578743064396e-05, "loss": 3.9829, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.155740148313344e-05, "loss": 3.9807, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.154901553562292e-05, "loss": 3.9804, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.1540645966916126e-05, "loss": 3.9894, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.1532260019405606e-05, "loss": 3.9956, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.1523874071895086e-05, "loss": 3.9827, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.1515488124384566e-05, "loss": 3.9771, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.1507102176874046e-05, "loss": 3.9746, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.1498716229363526e-05, "loss": 3.9793, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.1490330281853006e-05, "loss": 3.9766, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.1481944334342486e-05, "loss": 3.9802, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.147355838683197e-05, "loss": 3.9707, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.146517243932145e-05, "loss": 3.9871, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.145680287061466e-05, "loss": 3.977, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.144841692310414e-05, "loss": 3.9807, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.144003097559362e-05, "loss": 3.9785, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143166140688683e-05, "loss": 3.9765, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.142327545937631e-05, "loss": 3.9731, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.141488951186579e-05, "loss": 3.9907, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140650356435527e-05, "loss": 3.9864, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.139811761684475e-05, "loss": 3.9843, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.138974804813796e-05, "loss": 3.9746, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.138136210062744e-05, "loss": 3.9849, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.137297615311692e-05, "loss": 3.9797, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.13645902056064e-05, "loss": 3.9815, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.1356220636899616e-05, "loss": 3.9846, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.1347834689389095e-05, "loss": 3.9901, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.1339448741878575e-05, "loss": 3.9825, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.133106279436805e-05, "loss": 3.9892, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.132267684685753e-05, "loss": 3.9799, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.131429089934701e-05, "loss": 3.9866, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.130590495183649e-05, "loss": 3.9758, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.129751900432597e-05, "loss": 3.9743, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.128914943561918e-05, "loss": 3.9798, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.128076348810866e-05, "loss": 3.9656, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.1272377540598144e-05, "loss": 3.9791, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.126400797189135e-05, "loss": 3.9785, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 4.034204006195068, "eval_runtime": 291.2505, "eval_samples_per_second": 1310.181, "eval_steps_per_second": 40.944, "step": 1144800 }, { "epoch": 1.0, "learning_rate": 3.125562202438083e-05, "loss": 3.9767, "step": 1144832 }, { "epoch": 1.0, "learning_rate": 3.124723607687031e-05, "loss": 3.976, "step": 1145344 }, { "epoch": 1.0, "learning_rate": 3.123885012935979e-05, "loss": 3.9756, "step": 1145856 }, { "epoch": 1.0, "learning_rate": 3.123046418184927e-05, "loss": 3.9892, "step": 1146368 }, { "epoch": 1.0, "learning_rate": 3.122207823433875e-05, "loss": 3.9824, "step": 1146880 }, { "epoch": 1.0, "learning_rate": 3.121369228682823e-05, "loss": 3.9915, "step": 1147392 }, { "epoch": 1.0, "learning_rate": 3.120530633931771e-05, "loss": 3.9759, "step": 1147904 }, { "epoch": 1.0, "learning_rate": 3.119693677061092e-05, "loss": 3.9769, "step": 1148416 }, { "epoch": 1.0, "learning_rate": 3.11885508231004e-05, "loss": 3.9678, "step": 1148928 }, { "epoch": 1.0, "learning_rate": 3.118016487558988e-05, "loss": 3.9844, "step": 1149440 }, { "epoch": 1.0, "learning_rate": 3.117177892807936e-05, "loss": 3.9789, "step": 1149952 }, { "epoch": 1.0, "learning_rate": 3.116340935937258e-05, "loss": 3.9809, "step": 1150464 }, { "epoch": 1.0, "learning_rate": 3.115503979066579e-05, "loss": 3.9843, "step": 1150976 }, { "epoch": 1.0, "learning_rate": 3.1146670221958996e-05, "loss": 3.9729, "step": 1151488 }, { "epoch": 1.0, "learning_rate": 3.1138284274448476e-05, "loss": 3.9729, "step": 1152000 }, { "epoch": 1.0, "learning_rate": 3.1129898326937956e-05, "loss": 3.9692, "step": 1152512 }, { "epoch": 1.0, "learning_rate": 3.1121512379427436e-05, "loss": 3.9676, "step": 1153024 }, { "epoch": 1.0, "learning_rate": 3.1113126431916916e-05, "loss": 3.9767, "step": 1153536 }, { "epoch": 1.0, "learning_rate": 3.1104740484406396e-05, "loss": 3.9772, "step": 1154048 }, { "epoch": 1.0, "learning_rate": 3.1096354536895876e-05, "loss": 3.9789, "step": 1154560 }, { "epoch": 1.0, "learning_rate": 3.1087968589385356e-05, "loss": 3.99, "step": 1155072 }, { "epoch": 1.0, "learning_rate": 3.1079599020678565e-05, "loss": 3.9785, "step": 1155584 }, { "epoch": 1.0, "learning_rate": 3.107121307316805e-05, "loss": 3.9814, "step": 1156096 }, { "epoch": 1.0, "learning_rate": 3.106282712565753e-05, "loss": 3.976, "step": 1156608 }, { "epoch": 1.0, "learning_rate": 3.105444117814701e-05, "loss": 3.9882, "step": 1157120 }, { "epoch": 1.0, "learning_rate": 3.104605523063649e-05, "loss": 3.9732, "step": 1157632 }, { "epoch": 1.0, "learning_rate": 3.103766928312597e-05, "loss": 3.9748, "step": 1158144 }, { "epoch": 1.0, "learning_rate": 3.102929971441918e-05, "loss": 3.9719, "step": 1158656 }, { "epoch": 1.0, "learning_rate": 3.102091376690866e-05, "loss": 3.9723, "step": 1159168 }, { "epoch": 1.0, "learning_rate": 3.101252781939814e-05, "loss": 3.9755, "step": 1159680 }, { "epoch": 1.01, "learning_rate": 3.100414187188762e-05, "loss": 3.9743, "step": 1160192 }, { "epoch": 1.01, "learning_rate": 3.09957559243771e-05, "loss": 3.9811, "step": 1160704 }, { "epoch": 1.01, "learning_rate": 3.098736997686658e-05, "loss": 3.9845, "step": 1161216 }, { "epoch": 1.01, "learning_rate": 3.0978984029356053e-05, "loss": 3.9802, "step": 1161728 }, { "epoch": 1.01, "learning_rate": 3.097061446064927e-05, "loss": 3.9781, "step": 1162240 }, { "epoch": 1.01, "learning_rate": 3.0962244891942485e-05, "loss": 3.9824, "step": 1162752 }, { "epoch": 1.01, "learning_rate": 3.0953858944431965e-05, "loss": 3.9813, "step": 1163264 }, { "epoch": 1.01, "learning_rate": 3.0945472996921445e-05, "loss": 3.9656, "step": 1163776 }, { "epoch": 1.01, "learning_rate": 3.0937087049410925e-05, "loss": 3.9765, "step": 1164288 }, { "epoch": 1.01, "learning_rate": 3.0928701101900405e-05, "loss": 3.959, "step": 1164800 }, { "epoch": 1.01, "learning_rate": 3.0920315154389885e-05, "loss": 3.9719, "step": 1165312 }, { "epoch": 1.01, "learning_rate": 3.091192920687936e-05, "loss": 3.968, "step": 1165824 }, { "epoch": 1.01, "learning_rate": 3.090354325936884e-05, "loss": 3.9861, "step": 1166336 }, { "epoch": 1.01, "learning_rate": 3.089515731185832e-05, "loss": 3.9695, "step": 1166848 }, { "epoch": 1.01, "learning_rate": 3.08867713643478e-05, "loss": 3.9683, "step": 1167360 }, { "epoch": 1.01, "learning_rate": 3.087838541683728e-05, "loss": 3.9745, "step": 1167872 }, { "epoch": 1.01, "learning_rate": 3.086999946932676e-05, "loss": 3.9773, "step": 1168384 }, { "epoch": 1.01, "learning_rate": 3.08616462794237e-05, "loss": 3.9729, "step": 1168896 }, { "epoch": 1.01, "learning_rate": 3.085326033191318e-05, "loss": 3.956, "step": 1169408 }, { "epoch": 1.01, "learning_rate": 3.084487438440266e-05, "loss": 3.9715, "step": 1169920 }, { "epoch": 1.01, "learning_rate": 3.083648843689214e-05, "loss": 3.9883, "step": 1170432 }, { "epoch": 1.01, "learning_rate": 3.082810248938162e-05, "loss": 3.9816, "step": 1170944 }, { "epoch": 1.01, "learning_rate": 3.08197165418711e-05, "loss": 3.9725, "step": 1171456 }, { "epoch": 1.01, "learning_rate": 3.081133059436058e-05, "loss": 3.9676, "step": 1171968 }, { "epoch": 1.01, "learning_rate": 3.080294464685006e-05, "loss": 3.9809, "step": 1172480 }, { "epoch": 1.01, "learning_rate": 3.079455869933954e-05, "loss": 3.9612, "step": 1172992 }, { "epoch": 1.01, "learning_rate": 3.078618913063275e-05, "loss": 3.9877, "step": 1173504 }, { "epoch": 1.01, "learning_rate": 3.077780318312223e-05, "loss": 3.9565, "step": 1174016 }, { "epoch": 1.01, "learning_rate": 3.076941723561171e-05, "loss": 3.9876, "step": 1174528 }, { "epoch": 1.01, "learning_rate": 3.076103128810119e-05, "loss": 3.9816, "step": 1175040 }, { "epoch": 1.01, "learning_rate": 3.075264534059067e-05, "loss": 3.9576, "step": 1175552 }, { "epoch": 1.01, "learning_rate": 3.074425939308015e-05, "loss": 3.97, "step": 1176064 }, { "epoch": 1.01, "learning_rate": 3.073587344556964e-05, "loss": 3.9779, "step": 1176576 }, { "epoch": 1.01, "learning_rate": 3.072750387686285e-05, "loss": 3.9505, "step": 1177088 }, { "epoch": 1.01, "learning_rate": 3.071911792935233e-05, "loss": 3.9668, "step": 1177600 }, { "epoch": 1.01, "learning_rate": 3.071073198184181e-05, "loss": 3.9837, "step": 1178112 }, { "epoch": 1.01, "learning_rate": 3.070234603433129e-05, "loss": 3.9718, "step": 1178624 }, { "epoch": 1.01, "learning_rate": 3.069396008682077e-05, "loss": 3.9691, "step": 1179136 }, { "epoch": 1.01, "learning_rate": 3.0685590518113976e-05, "loss": 3.9563, "step": 1179648 }, { "epoch": 1.01, "learning_rate": 3.0677204570603456e-05, "loss": 3.9684, "step": 1180160 }, { "epoch": 1.01, "learning_rate": 3.0668818623092936e-05, "loss": 3.9605, "step": 1180672 }, { "epoch": 1.01, "learning_rate": 3.0660432675582416e-05, "loss": 3.9795, "step": 1181184 }, { "epoch": 1.01, "learning_rate": 3.0652063106875625e-05, "loss": 3.9636, "step": 1181696 }, { "epoch": 1.01, "learning_rate": 3.0643677159365105e-05, "loss": 3.9758, "step": 1182208 }, { "epoch": 1.01, "learning_rate": 3.063529121185459e-05, "loss": 3.979, "step": 1182720 }, { "epoch": 1.01, "learning_rate": 3.062690526434407e-05, "loss": 3.9752, "step": 1183232 }, { "epoch": 1.01, "learning_rate": 3.0618519316833545e-05, "loss": 3.9695, "step": 1183744 }, { "epoch": 1.01, "learning_rate": 3.061014974812676e-05, "loss": 3.9713, "step": 1184256 }, { "epoch": 1.01, "learning_rate": 3.060176380061624e-05, "loss": 3.9756, "step": 1184768 }, { "epoch": 1.01, "learning_rate": 3.059337785310572e-05, "loss": 3.9747, "step": 1185280 }, { "epoch": 1.01, "learning_rate": 3.0584991905595194e-05, "loss": 3.9695, "step": 1185792 }, { "epoch": 1.01, "learning_rate": 3.0576605958084674e-05, "loss": 3.9689, "step": 1186304 }, { "epoch": 1.01, "learning_rate": 3.0568220010574154e-05, "loss": 3.975, "step": 1186816 }, { "epoch": 1.01, "learning_rate": 3.0559834063063634e-05, "loss": 3.9751, "step": 1187328 }, { "epoch": 1.01, "learning_rate": 3.0551448115553114e-05, "loss": 3.9564, "step": 1187840 }, { "epoch": 1.01, "learning_rate": 3.0543062168042594e-05, "loss": 3.9698, "step": 1188352 }, { "epoch": 1.01, "learning_rate": 3.053469259933581e-05, "loss": 3.968, "step": 1188864 }, { "epoch": 1.01, "learning_rate": 3.052630665182529e-05, "loss": 3.9694, "step": 1189376 }, { "epoch": 1.01, "learning_rate": 3.051792070431477e-05, "loss": 3.9716, "step": 1189888 }, { "epoch": 1.01, "learning_rate": 3.050955113560798e-05, "loss": 3.9708, "step": 1190400 }, { "epoch": 1.02, "learning_rate": 3.050116518809746e-05, "loss": 3.964, "step": 1190912 }, { "epoch": 1.02, "learning_rate": 3.049277924058694e-05, "loss": 3.9583, "step": 1191424 }, { "epoch": 1.02, "learning_rate": 3.048439329307642e-05, "loss": 3.9639, "step": 1191936 }, { "epoch": 1.02, "learning_rate": 3.04760073455659e-05, "loss": 3.9779, "step": 1192448 }, { "epoch": 1.02, "learning_rate": 3.046762139805538e-05, "loss": 3.9691, "step": 1192960 }, { "epoch": 1.02, "learning_rate": 3.045925182934859e-05, "loss": 3.9779, "step": 1193472 }, { "epoch": 1.02, "learning_rate": 3.045086588183807e-05, "loss": 3.9649, "step": 1193984 }, { "epoch": 1.02, "learning_rate": 3.044247993432755e-05, "loss": 3.9657, "step": 1194496 }, { "epoch": 1.02, "learning_rate": 3.043411036562076e-05, "loss": 3.963, "step": 1195008 }, { "epoch": 1.02, "learning_rate": 3.042572441811024e-05, "loss": 3.9804, "step": 1195520 }, { "epoch": 1.02, "learning_rate": 3.041733847059972e-05, "loss": 3.9689, "step": 1196032 }, { "epoch": 1.02, "learning_rate": 3.04089525230892e-05, "loss": 3.9768, "step": 1196544 }, { "epoch": 1.02, "learning_rate": 3.0400566575578683e-05, "loss": 3.9668, "step": 1197056 }, { "epoch": 1.02, "learning_rate": 3.0392180628068163e-05, "loss": 3.9615, "step": 1197568 }, { "epoch": 1.02, "learning_rate": 3.0383811059361372e-05, "loss": 3.9795, "step": 1198080 }, { "epoch": 1.02, "learning_rate": 3.0375425111850852e-05, "loss": 3.9616, "step": 1198592 }, { "epoch": 1.02, "learning_rate": 3.0367039164340332e-05, "loss": 3.9639, "step": 1199104 }, { "epoch": 1.02, "learning_rate": 3.0358653216829812e-05, "loss": 3.9696, "step": 1199616 }, { "epoch": 1.02, "learning_rate": 3.0350267269319292e-05, "loss": 3.9673, "step": 1200128 }, { "epoch": 1.02, "learning_rate": 3.0341881321808775e-05, "loss": 3.9609, "step": 1200640 }, { "epoch": 1.02, "learning_rate": 3.0333495374298255e-05, "loss": 3.9658, "step": 1201152 }, { "epoch": 1.02, "learning_rate": 3.032510942678773e-05, "loss": 3.9561, "step": 1201664 }, { "epoch": 1.02, "learning_rate": 3.031672347927721e-05, "loss": 3.9693, "step": 1202176 }, { "epoch": 1.02, "learning_rate": 3.030833753176669e-05, "loss": 3.9691, "step": 1202688 }, { "epoch": 1.02, "learning_rate": 3.029995158425617e-05, "loss": 3.9676, "step": 1203200 }, { "epoch": 1.02, "learning_rate": 3.029156563674565e-05, "loss": 3.974, "step": 1203712 }, { "epoch": 1.02, "learning_rate": 3.028319606803886e-05, "loss": 3.9857, "step": 1204224 }, { "epoch": 1.02, "learning_rate": 3.027481012052834e-05, "loss": 3.971, "step": 1204736 }, { "epoch": 1.02, "learning_rate": 3.026642417301782e-05, "loss": 3.9653, "step": 1205248 }, { "epoch": 1.02, "learning_rate": 3.02580382255073e-05, "loss": 3.9591, "step": 1205760 }, { "epoch": 1.02, "learning_rate": 3.0249668656800513e-05, "loss": 3.967, "step": 1206272 }, { "epoch": 1.02, "learning_rate": 3.0241282709289993e-05, "loss": 3.9648, "step": 1206784 }, { "epoch": 1.02, "learning_rate": 3.0232896761779473e-05, "loss": 3.9672, "step": 1207296 }, { "epoch": 1.02, "learning_rate": 3.0224510814268953e-05, "loss": 3.9621, "step": 1207808 }, { "epoch": 1.02, "learning_rate": 3.0216124866758433e-05, "loss": 3.9761, "step": 1208320 }, { "epoch": 1.02, "learning_rate": 3.0207738919247913e-05, "loss": 3.9675, "step": 1208832 }, { "epoch": 1.02, "learning_rate": 3.0199352971737393e-05, "loss": 3.9701, "step": 1209344 }, { "epoch": 1.02, "learning_rate": 3.0190967024226873e-05, "loss": 3.964, "step": 1209856 }, { "epoch": 1.02, "learning_rate": 3.0182597455520085e-05, "loss": 3.9656, "step": 1210368 }, { "epoch": 1.02, "learning_rate": 3.0174227886813294e-05, "loss": 3.96, "step": 1210880 }, { "epoch": 1.02, "learning_rate": 3.0165841939302774e-05, "loss": 3.9774, "step": 1211392 }, { "epoch": 1.02, "learning_rate": 3.0157455991792254e-05, "loss": 3.9796, "step": 1211904 }, { "epoch": 1.02, "learning_rate": 3.0149070044281734e-05, "loss": 3.9738, "step": 1212416 }, { "epoch": 1.02, "learning_rate": 3.0140684096771214e-05, "loss": 3.9626, "step": 1212928 }, { "epoch": 1.02, "learning_rate": 3.0132298149260698e-05, "loss": 3.9688, "step": 1213440 }, { "epoch": 1.02, "learning_rate": 3.0123912201750177e-05, "loss": 3.9712, "step": 1213952 }, { "epoch": 1.02, "learning_rate": 3.0115542633043387e-05, "loss": 3.9689, "step": 1214464 }, { "epoch": 1.02, "learning_rate": 3.0107156685532867e-05, "loss": 3.9725, "step": 1214976 }, { "epoch": 1.02, "learning_rate": 3.0098770738022347e-05, "loss": 3.9785, "step": 1215488 }, { "epoch": 1.02, "learning_rate": 3.009040116931556e-05, "loss": 3.9692, "step": 1216000 }, { "epoch": 1.02, "learning_rate": 3.008201522180504e-05, "loss": 3.9805, "step": 1216512 }, { "epoch": 1.02, "learning_rate": 3.007362927429452e-05, "loss": 3.9623, "step": 1217024 }, { "epoch": 1.02, "learning_rate": 3.0065243326784e-05, "loss": 3.9747, "step": 1217536 }, { "epoch": 1.02, "learning_rate": 3.0056873758077208e-05, "loss": 3.9686, "step": 1218048 }, { "epoch": 1.02, "learning_rate": 3.0048487810566688e-05, "loss": 3.9586, "step": 1218560 }, { "epoch": 1.02, "learning_rate": 3.0040101863056168e-05, "loss": 3.9718, "step": 1219072 }, { "epoch": 1.02, "learning_rate": 3.003171591554565e-05, "loss": 3.9586, "step": 1219584 }, { "epoch": 1.02, "learning_rate": 3.002332996803513e-05, "loss": 3.9634, "step": 1220096 }, { "epoch": 1.02, "learning_rate": 3.001494402052461e-05, "loss": 3.969, "step": 1220608 }, { "epoch": 1.03, "learning_rate": 3.000655807301409e-05, "loss": 3.9657, "step": 1221120 }, { "epoch": 1.03, "eval_loss": 4.028191089630127, "eval_runtime": 292.8413, "eval_samples_per_second": 1303.064, "eval_steps_per_second": 40.722, "step": 1221120 }, { "epoch": 0.0, "learning_rate": 2.9998172125503564e-05, "loss": 3.9641, "step": 1221632 }, { "epoch": 0.0, "learning_rate": 2.9989786177993044e-05, "loss": 3.9657, "step": 1222144 }, { "epoch": 0.0, "learning_rate": 2.9981400230482528e-05, "loss": 3.9755, "step": 1222656 }, { "epoch": 0.0, "learning_rate": 2.9973014282972008e-05, "loss": 3.9712, "step": 1223168 }, { "epoch": 0.0, "learning_rate": 2.9964628335461487e-05, "loss": 3.98, "step": 1223680 }, { "epoch": 0.0, "learning_rate": 2.9956242387950967e-05, "loss": 3.9631, "step": 1224192 }, { "epoch": 0.0, "learning_rate": 2.9947856440440447e-05, "loss": 3.9607, "step": 1224704 }, { "epoch": 0.0, "learning_rate": 2.9939470492929927e-05, "loss": 3.9617, "step": 1225216 }, { "epoch": 0.0, "learning_rate": 2.9931084545419407e-05, "loss": 3.9707, "step": 1225728 }, { "epoch": 0.0, "learning_rate": 2.9922698597908887e-05, "loss": 3.9673, "step": 1226240 }, { "epoch": 0.0, "learning_rate": 2.9914312650398367e-05, "loss": 3.9702, "step": 1226752 }, { "epoch": 0.0, "learning_rate": 2.9905926702887847e-05, "loss": 3.9706, "step": 1227264 }, { "epoch": 0.0, "learning_rate": 2.989755713418106e-05, "loss": 3.9599, "step": 1227776 }, { "epoch": 0.0, "learning_rate": 2.988917118667054e-05, "loss": 3.9642, "step": 1228288 }, { "epoch": 0.0, "learning_rate": 2.988080161796375e-05, "loss": 3.9564, "step": 1228800 }, { "epoch": 0.0, "learning_rate": 2.987241567045323e-05, "loss": 3.9562, "step": 1229312 }, { "epoch": 0.0, "learning_rate": 2.986402972294271e-05, "loss": 3.9661, "step": 1229824 }, { "epoch": 0.0, "learning_rate": 2.9855643775432192e-05, "loss": 3.9661, "step": 1230336 }, { "epoch": 0.0, "learning_rate": 2.9847257827921672e-05, "loss": 3.9672, "step": 1230848 }, { "epoch": 0.0, "learning_rate": 2.9838871880411152e-05, "loss": 3.9824, "step": 1231360 }, { "epoch": 0.0, "learning_rate": 2.9830485932900625e-05, "loss": 3.965, "step": 1231872 }, { "epoch": 0.0, "learning_rate": 2.9822099985390105e-05, "loss": 3.9713, "step": 1232384 }, { "epoch": 0.0, "learning_rate": 2.9813714037879585e-05, "loss": 3.9648, "step": 1232896 }, { "epoch": 0.0, "learning_rate": 2.9805328090369068e-05, "loss": 3.9766, "step": 1233408 }, { "epoch": 0.0, "learning_rate": 2.9796942142858548e-05, "loss": 3.966, "step": 1233920 }, { "epoch": 0.0, "learning_rate": 2.9788556195348028e-05, "loss": 3.9655, "step": 1234432 }, { "epoch": 0.0, "learning_rate": 2.9780186626641237e-05, "loss": 3.9584, "step": 1234944 }, { "epoch": 0.0, "learning_rate": 2.9771800679130717e-05, "loss": 3.9646, "step": 1235456 }, { "epoch": 0.0, "learning_rate": 2.9763414731620197e-05, "loss": 3.9598, "step": 1235968 }, { "epoch": 0.01, "learning_rate": 2.9755028784109677e-05, "loss": 3.9657, "step": 1236480 }, { "epoch": 0.01, "learning_rate": 2.974664283659916e-05, "loss": 3.9678, "step": 1236992 }, { "epoch": 0.01, "learning_rate": 2.973825688908864e-05, "loss": 3.9686, "step": 1237504 }, { "epoch": 0.01, "learning_rate": 2.972987094157812e-05, "loss": 3.9706, "step": 1238016 }, { "epoch": 0.01, "learning_rate": 2.972150137287133e-05, "loss": 3.9686, "step": 1238528 }, { "epoch": 0.01, "learning_rate": 2.971313180416454e-05, "loss": 3.9667, "step": 1239040 }, { "epoch": 0.01, "learning_rate": 2.9704745856654022e-05, "loss": 3.9738, "step": 1239552 }, { "epoch": 0.01, "learning_rate": 2.9696359909143502e-05, "loss": 3.9573, "step": 1240064 }, { "epoch": 0.01, "learning_rate": 2.9687973961632982e-05, "loss": 3.9626, "step": 1240576 }, { "epoch": 0.01, "learning_rate": 2.9679588014122462e-05, "loss": 3.9493, "step": 1241088 }, { "epoch": 0.01, "learning_rate": 2.9671202066611942e-05, "loss": 3.9584, "step": 1241600 }, { "epoch": 0.01, "learning_rate": 2.9662816119101422e-05, "loss": 3.9579, "step": 1242112 }, { "epoch": 0.01, "learning_rate": 2.96544301715909e-05, "loss": 3.9702, "step": 1242624 }, { "epoch": 0.01, "learning_rate": 2.964604422408038e-05, "loss": 3.9595, "step": 1243136 }, { "epoch": 0.01, "learning_rate": 2.963765827656986e-05, "loss": 3.9575, "step": 1243648 }, { "epoch": 0.01, "learning_rate": 2.9629272329059345e-05, "loss": 3.9667, "step": 1244160 }, { "epoch": 0.01, "learning_rate": 2.9620886381548818e-05, "loss": 3.9671, "step": 1244672 }, { "epoch": 0.01, "learning_rate": 2.9612500434038298e-05, "loss": 3.9591, "step": 1245184 }, { "epoch": 0.01, "learning_rate": 2.9604114486527778e-05, "loss": 3.9521, "step": 1245696 }, { "epoch": 0.01, "learning_rate": 2.9595728539017258e-05, "loss": 3.9559, "step": 1246208 }, { "epoch": 0.01, "learning_rate": 2.9587342591506738e-05, "loss": 3.9769, "step": 1246720 }, { "epoch": 0.01, "learning_rate": 2.9578989401603686e-05, "loss": 3.9734, "step": 1247232 }, { "epoch": 0.01, "learning_rate": 2.9570603454093166e-05, "loss": 3.9573, "step": 1247744 }, { "epoch": 0.01, "learning_rate": 2.956221750658264e-05, "loss": 3.9586, "step": 1248256 }, { "epoch": 0.01, "learning_rate": 2.955383155907212e-05, "loss": 3.9683, "step": 1248768 }, { "epoch": 0.01, "learning_rate": 2.95454456115616e-05, "loss": 3.9508, "step": 1249280 }, { "epoch": 0.01, "learning_rate": 2.9537076042854815e-05, "loss": 3.972, "step": 1249792 }, { "epoch": 0.01, "learning_rate": 2.9528690095344292e-05, "loss": 3.9488, "step": 1250304 }, { "epoch": 0.01, "learning_rate": 2.9520304147833772e-05, "loss": 3.9793, "step": 1250816 }, { "epoch": 0.01, "learning_rate": 2.9511918200323252e-05, "loss": 3.9671, "step": 1251328 }, { "epoch": 0.01, "learning_rate": 2.9503532252812732e-05, "loss": 3.9523, "step": 1251840 }, { "epoch": 0.01, "learning_rate": 2.949514630530221e-05, "loss": 3.9528, "step": 1252352 }, { "epoch": 0.01, "learning_rate": 2.948676035779169e-05, "loss": 3.97, "step": 1252864 }, { "epoch": 0.01, "learning_rate": 2.947837441028117e-05, "loss": 3.9384, "step": 1253376 }, { "epoch": 0.01, "learning_rate": 2.9469988462770655e-05, "loss": 3.9557, "step": 1253888 }, { "epoch": 0.01, "learning_rate": 2.9461602515260135e-05, "loss": 3.9693, "step": 1254400 }, { "epoch": 0.01, "learning_rate": 2.9453216567749615e-05, "loss": 3.962, "step": 1254912 }, { "epoch": 0.01, "learning_rate": 2.9444830620239095e-05, "loss": 3.9586, "step": 1255424 }, { "epoch": 0.01, "learning_rate": 2.9436477430336033e-05, "loss": 3.9453, "step": 1255936 }, { "epoch": 0.01, "learning_rate": 2.9428091482825516e-05, "loss": 3.9539, "step": 1256448 }, { "epoch": 0.01, "learning_rate": 2.9419705535314996e-05, "loss": 3.9498, "step": 1256960 }, { "epoch": 0.01, "learning_rate": 2.9411319587804476e-05, "loss": 3.9723, "step": 1257472 }, { "epoch": 0.01, "learning_rate": 2.9402933640293956e-05, "loss": 3.9521, "step": 1257984 }, { "epoch": 0.01, "learning_rate": 2.9394547692783436e-05, "loss": 3.9642, "step": 1258496 }, { "epoch": 0.01, "learning_rate": 2.9386161745272916e-05, "loss": 3.9651, "step": 1259008 }, { "epoch": 0.01, "learning_rate": 2.9377792176566125e-05, "loss": 3.97, "step": 1259520 }, { "epoch": 0.01, "learning_rate": 2.936940622905561e-05, "loss": 3.9547, "step": 1260032 }, { "epoch": 0.01, "learning_rate": 2.936102028154509e-05, "loss": 3.9606, "step": 1260544 }, { "epoch": 0.01, "learning_rate": 2.935263433403457e-05, "loss": 3.9642, "step": 1261056 }, { "epoch": 0.01, "learning_rate": 2.934424838652405e-05, "loss": 3.964, "step": 1261568 }, { "epoch": 0.01, "learning_rate": 2.933586243901353e-05, "loss": 3.9573, "step": 1262080 }, { "epoch": 0.01, "learning_rate": 2.9327476491503e-05, "loss": 3.9568, "step": 1262592 }, { "epoch": 0.01, "learning_rate": 2.9319090543992485e-05, "loss": 3.9636, "step": 1263104 }, { "epoch": 0.01, "learning_rate": 2.93107209752857e-05, "loss": 3.962, "step": 1263616 }, { "epoch": 0.01, "learning_rate": 2.9302335027775174e-05, "loss": 3.9498, "step": 1264128 }, { "epoch": 0.01, "learning_rate": 2.929396545906839e-05, "loss": 3.9544, "step": 1264640 }, { "epoch": 0.01, "learning_rate": 2.928557951155787e-05, "loss": 3.959, "step": 1265152 }, { "epoch": 0.01, "learning_rate": 2.927719356404735e-05, "loss": 3.9641, "step": 1265664 }, { "epoch": 0.01, "learning_rate": 2.9268807616536826e-05, "loss": 3.9565, "step": 1266176 }, { "epoch": 0.01, "learning_rate": 2.9260421669026306e-05, "loss": 3.9597, "step": 1266688 }, { "epoch": 0.02, "learning_rate": 2.9252035721515786e-05, "loss": 3.9546, "step": 1267200 }, { "epoch": 0.02, "learning_rate": 2.9243649774005266e-05, "loss": 3.9489, "step": 1267712 }, { "epoch": 0.02, "learning_rate": 2.9235263826494746e-05, "loss": 3.9524, "step": 1268224 }, { "epoch": 0.02, "learning_rate": 2.9226894257787955e-05, "loss": 3.9636, "step": 1268736 }, { "epoch": 0.02, "learning_rate": 2.921850831027744e-05, "loss": 3.9573, "step": 1269248 }, { "epoch": 0.02, "learning_rate": 2.9210138741570648e-05, "loss": 3.9688, "step": 1269760 }, { "epoch": 0.02, "learning_rate": 2.9201769172863864e-05, "loss": 3.9629, "step": 1270272 }, { "epoch": 0.02, "learning_rate": 2.9193383225353344e-05, "loss": 3.9509, "step": 1270784 }, { "epoch": 0.02, "learning_rate": 2.9184997277842823e-05, "loss": 3.953, "step": 1271296 }, { "epoch": 0.02, "learning_rate": 2.91766113303323e-05, "loss": 3.9657, "step": 1271808 }, { "epoch": 0.02, "learning_rate": 2.916822538282178e-05, "loss": 3.9634, "step": 1272320 }, { "epoch": 0.02, "learning_rate": 2.915983943531126e-05, "loss": 3.9647, "step": 1272832 }, { "epoch": 0.02, "learning_rate": 2.915145348780074e-05, "loss": 3.9548, "step": 1273344 }, { "epoch": 0.02, "learning_rate": 2.914306754029022e-05, "loss": 3.953, "step": 1273856 }, { "epoch": 0.02, "learning_rate": 2.91346815927797e-05, "loss": 3.9703, "step": 1274368 }, { "epoch": 0.02, "learning_rate": 2.912631202407291e-05, "loss": 3.9484, "step": 1274880 }, { "epoch": 0.02, "learning_rate": 2.9117926076562392e-05, "loss": 3.9572, "step": 1275392 }, { "epoch": 0.02, "learning_rate": 2.9109540129051872e-05, "loss": 3.9579, "step": 1275904 }, { "epoch": 0.02, "learning_rate": 2.9101154181541352e-05, "loss": 3.9586, "step": 1276416 }, { "epoch": 0.02, "learning_rate": 2.9092768234030832e-05, "loss": 3.9486, "step": 1276928 }, { "epoch": 0.02, "learning_rate": 2.9084382286520312e-05, "loss": 3.9541, "step": 1277440 }, { "epoch": 0.02, "learning_rate": 2.9075996339009792e-05, "loss": 3.948, "step": 1277952 }, { "epoch": 0.02, "learning_rate": 2.9067610391499272e-05, "loss": 3.9578, "step": 1278464 }, { "epoch": 0.02, "learning_rate": 2.9059224443988752e-05, "loss": 3.9555, "step": 1278976 }, { "epoch": 0.02, "learning_rate": 2.9050854875281964e-05, "loss": 3.9551, "step": 1279488 }, { "epoch": 0.02, "learning_rate": 2.9042468927771444e-05, "loss": 3.9651, "step": 1280000 }, { "epoch": 0.02, "learning_rate": 2.9034082980260924e-05, "loss": 3.9753, "step": 1280512 }, { "epoch": 0.02, "learning_rate": 2.9025713411554133e-05, "loss": 3.9613, "step": 1281024 }, { "epoch": 0.02, "learning_rate": 2.9017327464043613e-05, "loss": 3.9532, "step": 1281536 }, { "epoch": 0.02, "learning_rate": 2.9008941516533093e-05, "loss": 3.9516, "step": 1282048 }, { "epoch": 0.02, "learning_rate": 2.9000555569022573e-05, "loss": 3.9527, "step": 1282560 }, { "epoch": 0.02, "learning_rate": 2.8992169621512057e-05, "loss": 3.9583, "step": 1283072 }, { "epoch": 0.02, "learning_rate": 2.8983783674001537e-05, "loss": 3.9577, "step": 1283584 }, { "epoch": 0.02, "learning_rate": 2.897539772649101e-05, "loss": 3.9488, "step": 1284096 }, { "epoch": 0.02, "learning_rate": 2.896701177898049e-05, "loss": 3.9617, "step": 1284608 }, { "epoch": 0.02, "learning_rate": 2.8958642210273706e-05, "loss": 3.9583, "step": 1285120 }, { "epoch": 0.02, "learning_rate": 2.8950256262763186e-05, "loss": 3.9572, "step": 1285632 }, { "epoch": 0.02, "learning_rate": 2.8941870315252662e-05, "loss": 3.9535, "step": 1286144 }, { "epoch": 0.02, "learning_rate": 2.8933484367742142e-05, "loss": 3.9559, "step": 1286656 }, { "epoch": 0.02, "learning_rate": 2.8925098420231622e-05, "loss": 3.9507, "step": 1287168 }, { "epoch": 0.02, "learning_rate": 2.8916745230328567e-05, "loss": 3.9673, "step": 1287680 }, { "epoch": 0.02, "learning_rate": 2.8908359282818047e-05, "loss": 3.9675, "step": 1288192 }, { "epoch": 0.02, "learning_rate": 2.8899973335307527e-05, "loss": 3.9648, "step": 1288704 }, { "epoch": 0.02, "learning_rate": 2.889158738779701e-05, "loss": 3.9488, "step": 1289216 }, { "epoch": 0.02, "learning_rate": 2.8883201440286483e-05, "loss": 3.963, "step": 1289728 }, { "epoch": 0.02, "learning_rate": 2.8874815492775963e-05, "loss": 3.9588, "step": 1290240 }, { "epoch": 0.02, "learning_rate": 2.8866429545265443e-05, "loss": 3.9597, "step": 1290752 }, { "epoch": 0.02, "learning_rate": 2.885805997655866e-05, "loss": 3.9564, "step": 1291264 }, { "epoch": 0.02, "learning_rate": 2.8849674029048136e-05, "loss": 3.9678, "step": 1291776 }, { "epoch": 0.02, "learning_rate": 2.8841304460341352e-05, "loss": 3.9574, "step": 1292288 }, { "epoch": 0.02, "learning_rate": 2.883291851283083e-05, "loss": 3.9755, "step": 1292800 }, { "epoch": 0.02, "learning_rate": 2.8824532565320305e-05, "loss": 3.9502, "step": 1293312 }, { "epoch": 0.02, "learning_rate": 2.8816146617809785e-05, "loss": 3.9695, "step": 1293824 }, { "epoch": 0.02, "learning_rate": 2.8807760670299265e-05, "loss": 3.9552, "step": 1294336 }, { "epoch": 0.02, "learning_rate": 2.8799374722788748e-05, "loss": 3.9517, "step": 1294848 }, { "epoch": 0.02, "learning_rate": 2.8790988775278228e-05, "loss": 3.9585, "step": 1295360 }, { "epoch": 0.02, "learning_rate": 2.8782602827767708e-05, "loss": 3.9493, "step": 1295872 }, { "epoch": 0.02, "learning_rate": 2.8774216880257188e-05, "loss": 3.9541, "step": 1296384 }, { "epoch": 0.02, "learning_rate": 2.8765847311550397e-05, "loss": 3.9585, "step": 1296896 }, { "epoch": 0.02, "learning_rate": 2.8757461364039877e-05, "loss": 3.9505, "step": 1297408 }, { "epoch": 0.03, "eval_loss": 4.022686004638672, "eval_runtime": 294.2769, "eval_samples_per_second": 1296.707, "eval_steps_per_second": 40.523, "step": 1297440 }, { "epoch": 1.0, "learning_rate": 2.8749075416529357e-05, "loss": 3.957, "step": 1297920 }, { "epoch": 1.0, "learning_rate": 2.874068946901884e-05, "loss": 3.9538, "step": 1298432 }, { "epoch": 1.0, "learning_rate": 2.873230352150832e-05, "loss": 3.9669, "step": 1298944 }, { "epoch": 1.0, "learning_rate": 2.87239175739978e-05, "loss": 3.9606, "step": 1299456 }, { "epoch": 1.0, "learning_rate": 2.871553162648728e-05, "loss": 3.9706, "step": 1299968 }, { "epoch": 1.0, "learning_rate": 2.870714567897676e-05, "loss": 3.9521, "step": 1300480 }, { "epoch": 1.0, "learning_rate": 2.869877611026997e-05, "loss": 3.9548, "step": 1300992 }, { "epoch": 1.0, "learning_rate": 2.869039016275945e-05, "loss": 3.9484, "step": 1301504 }, { "epoch": 1.0, "learning_rate": 2.8682004215248933e-05, "loss": 3.9608, "step": 1302016 }, { "epoch": 1.0, "learning_rate": 2.8673618267738412e-05, "loss": 3.9556, "step": 1302528 }, { "epoch": 1.0, "learning_rate": 2.866524869903162e-05, "loss": 3.9563, "step": 1303040 }, { "epoch": 1.0, "learning_rate": 2.86568627515211e-05, "loss": 3.9631, "step": 1303552 }, { "epoch": 1.0, "learning_rate": 2.864849318281431e-05, "loss": 3.946, "step": 1304064 }, { "epoch": 1.0, "learning_rate": 2.8640107235303794e-05, "loss": 3.958, "step": 1304576 }, { "epoch": 1.0, "learning_rate": 2.8631721287793274e-05, "loss": 3.9476, "step": 1305088 }, { "epoch": 1.0, "learning_rate": 2.8623335340282754e-05, "loss": 3.9483, "step": 1305600 }, { "epoch": 1.0, "learning_rate": 2.8614965771575963e-05, "loss": 3.9541, "step": 1306112 }, { "epoch": 1.0, "learning_rate": 2.8606579824065443e-05, "loss": 3.9522, "step": 1306624 }, { "epoch": 1.0, "learning_rate": 2.8598193876554923e-05, "loss": 3.9567, "step": 1307136 }, { "epoch": 1.0, "learning_rate": 2.8589807929044403e-05, "loss": 3.9758, "step": 1307648 }, { "epoch": 1.0, "learning_rate": 2.8581421981533886e-05, "loss": 3.9526, "step": 1308160 }, { "epoch": 1.0, "learning_rate": 2.8573036034023366e-05, "loss": 3.9566, "step": 1308672 }, { "epoch": 1.0, "learning_rate": 2.8564666465316575e-05, "loss": 3.9583, "step": 1309184 }, { "epoch": 1.0, "learning_rate": 2.8556280517806055e-05, "loss": 3.9622, "step": 1309696 }, { "epoch": 1.0, "learning_rate": 2.8547894570295535e-05, "loss": 3.959, "step": 1310208 }, { "epoch": 1.0, "learning_rate": 2.8539508622785015e-05, "loss": 3.959, "step": 1310720 }, { "epoch": 1.0, "learning_rate": 2.8531122675274495e-05, "loss": 3.9454, "step": 1311232 }, { "epoch": 1.0, "learning_rate": 2.852273672776397e-05, "loss": 3.9551, "step": 1311744 }, { "epoch": 1.0, "learning_rate": 2.851435078025345e-05, "loss": 3.9453, "step": 1312256 }, { "epoch": 1.01, "learning_rate": 2.850596483274293e-05, "loss": 3.9579, "step": 1312768 }, { "epoch": 1.01, "learning_rate": 2.849759526403614e-05, "loss": 3.9536, "step": 1313280 }, { "epoch": 1.01, "learning_rate": 2.8489225695329357e-05, "loss": 3.959, "step": 1313792 }, { "epoch": 1.01, "learning_rate": 2.848083974781884e-05, "loss": 3.9651, "step": 1314304 }, { "epoch": 1.01, "learning_rate": 2.847245380030832e-05, "loss": 3.9552, "step": 1314816 }, { "epoch": 1.01, "learning_rate": 2.846408423160153e-05, "loss": 3.9607, "step": 1315328 }, { "epoch": 1.01, "learning_rate": 2.845569828409101e-05, "loss": 3.958, "step": 1315840 }, { "epoch": 1.01, "learning_rate": 2.844731233658049e-05, "loss": 3.9509, "step": 1316352 }, { "epoch": 1.01, "learning_rate": 2.843892638906997e-05, "loss": 3.9497, "step": 1316864 }, { "epoch": 1.01, "learning_rate": 2.8430540441559445e-05, "loss": 3.9396, "step": 1317376 }, { "epoch": 1.01, "learning_rate": 2.8422154494048925e-05, "loss": 3.948, "step": 1317888 }, { "epoch": 1.01, "learning_rate": 2.8413768546538405e-05, "loss": 3.9505, "step": 1318400 }, { "epoch": 1.01, "learning_rate": 2.8405382599027885e-05, "loss": 3.9619, "step": 1318912 }, { "epoch": 1.01, "learning_rate": 2.8396996651517365e-05, "loss": 3.9486, "step": 1319424 }, { "epoch": 1.01, "learning_rate": 2.8388610704006845e-05, "loss": 3.9486, "step": 1319936 }, { "epoch": 1.01, "learning_rate": 2.8380241135300058e-05, "loss": 3.9554, "step": 1320448 }, { "epoch": 1.01, "learning_rate": 2.8371855187789538e-05, "loss": 3.9503, "step": 1320960 }, { "epoch": 1.01, "learning_rate": 2.8363469240279018e-05, "loss": 3.9538, "step": 1321472 }, { "epoch": 1.01, "learning_rate": 2.8355099671572227e-05, "loss": 3.9418, "step": 1321984 }, { "epoch": 1.01, "learning_rate": 2.8346713724061707e-05, "loss": 3.9414, "step": 1322496 }, { "epoch": 1.01, "learning_rate": 2.8338327776551187e-05, "loss": 3.9671, "step": 1323008 }, { "epoch": 1.01, "learning_rate": 2.8329941829040666e-05, "loss": 3.965, "step": 1323520 }, { "epoch": 1.01, "learning_rate": 2.832155588153015e-05, "loss": 3.9459, "step": 1324032 }, { "epoch": 1.01, "learning_rate": 2.831316993401963e-05, "loss": 3.952, "step": 1324544 }, { "epoch": 1.01, "learning_rate": 2.830478398650911e-05, "loss": 3.9578, "step": 1325056 }, { "epoch": 1.01, "learning_rate": 2.829639803899859e-05, "loss": 3.9415, "step": 1325568 }, { "epoch": 1.01, "learning_rate": 2.82880284702918e-05, "loss": 3.9623, "step": 1326080 }, { "epoch": 1.01, "learning_rate": 2.827964252278128e-05, "loss": 3.9374, "step": 1326592 }, { "epoch": 1.01, "learning_rate": 2.827125657527076e-05, "loss": 3.9673, "step": 1327104 }, { "epoch": 1.01, "learning_rate": 2.8262870627760242e-05, "loss": 3.9586, "step": 1327616 }, { "epoch": 1.01, "learning_rate": 2.8254484680249722e-05, "loss": 3.9445, "step": 1328128 }, { "epoch": 1.01, "learning_rate": 2.824611511154293e-05, "loss": 3.945, "step": 1328640 }, { "epoch": 1.01, "learning_rate": 2.823772916403241e-05, "loss": 3.9585, "step": 1329152 }, { "epoch": 1.01, "learning_rate": 2.822934321652189e-05, "loss": 3.9259, "step": 1329664 }, { "epoch": 1.01, "learning_rate": 2.822095726901137e-05, "loss": 3.9465, "step": 1330176 }, { "epoch": 1.01, "learning_rate": 2.821257132150085e-05, "loss": 3.9591, "step": 1330688 }, { "epoch": 1.01, "learning_rate": 2.8204185373990328e-05, "loss": 3.9557, "step": 1331200 }, { "epoch": 1.01, "learning_rate": 2.8195799426479807e-05, "loss": 3.9465, "step": 1331712 }, { "epoch": 1.01, "learning_rate": 2.8187413478969287e-05, "loss": 3.9353, "step": 1332224 }, { "epoch": 1.01, "learning_rate": 2.8179027531458767e-05, "loss": 3.9433, "step": 1332736 }, { "epoch": 1.01, "learning_rate": 2.817065796275198e-05, "loss": 3.9426, "step": 1333248 }, { "epoch": 1.01, "learning_rate": 2.816227201524146e-05, "loss": 3.9538, "step": 1333760 }, { "epoch": 1.01, "learning_rate": 2.815388606773094e-05, "loss": 3.9446, "step": 1334272 }, { "epoch": 1.01, "learning_rate": 2.814550012022042e-05, "loss": 3.9543, "step": 1334784 }, { "epoch": 1.01, "learning_rate": 2.813713055151363e-05, "loss": 3.9557, "step": 1335296 }, { "epoch": 1.01, "learning_rate": 2.8128760982806845e-05, "loss": 3.9604, "step": 1335808 }, { "epoch": 1.01, "learning_rate": 2.8120375035296325e-05, "loss": 3.9425, "step": 1336320 }, { "epoch": 1.01, "learning_rate": 2.81119890877858e-05, "loss": 3.9513, "step": 1336832 }, { "epoch": 1.01, "learning_rate": 2.810360314027528e-05, "loss": 3.9547, "step": 1337344 }, { "epoch": 1.01, "learning_rate": 2.809521719276476e-05, "loss": 3.9504, "step": 1337856 }, { "epoch": 1.01, "learning_rate": 2.808683124525424e-05, "loss": 3.9496, "step": 1338368 }, { "epoch": 1.01, "learning_rate": 2.807844529774372e-05, "loss": 3.9457, "step": 1338880 }, { "epoch": 1.01, "learning_rate": 2.80700593502332e-05, "loss": 3.9554, "step": 1339392 }, { "epoch": 1.01, "learning_rate": 2.806167340272268e-05, "loss": 3.9503, "step": 1339904 }, { "epoch": 1.01, "learning_rate": 2.8053303834015893e-05, "loss": 3.9365, "step": 1340416 }, { "epoch": 1.01, "learning_rate": 2.8044917886505373e-05, "loss": 3.9466, "step": 1340928 }, { "epoch": 1.01, "learning_rate": 2.8036548317798582e-05, "loss": 3.9472, "step": 1341440 }, { "epoch": 1.01, "learning_rate": 2.8028162370288062e-05, "loss": 3.9544, "step": 1341952 }, { "epoch": 1.01, "learning_rate": 2.8019776422777542e-05, "loss": 3.9498, "step": 1342464 }, { "epoch": 1.01, "learning_rate": 2.8011390475267026e-05, "loss": 3.9457, "step": 1342976 }, { "epoch": 1.02, "learning_rate": 2.8003004527756506e-05, "loss": 3.9441, "step": 1343488 }, { "epoch": 1.02, "learning_rate": 2.7994634959049715e-05, "loss": 3.9378, "step": 1344000 }, { "epoch": 1.02, "learning_rate": 2.7986249011539195e-05, "loss": 3.9398, "step": 1344512 }, { "epoch": 1.02, "learning_rate": 2.7977863064028675e-05, "loss": 3.9534, "step": 1345024 }, { "epoch": 1.02, "learning_rate": 2.7969477116518155e-05, "loss": 3.9495, "step": 1345536 }, { "epoch": 1.02, "learning_rate": 2.7961107547811367e-05, "loss": 3.9566, "step": 1346048 }, { "epoch": 1.02, "learning_rate": 2.7952721600300847e-05, "loss": 3.9516, "step": 1346560 }, { "epoch": 1.02, "learning_rate": 2.7944335652790327e-05, "loss": 3.9444, "step": 1347072 }, { "epoch": 1.02, "learning_rate": 2.7935949705279807e-05, "loss": 3.9453, "step": 1347584 }, { "epoch": 1.02, "learning_rate": 2.7927563757769287e-05, "loss": 3.9513, "step": 1348096 }, { "epoch": 1.02, "learning_rate": 2.7919177810258767e-05, "loss": 3.9578, "step": 1348608 }, { "epoch": 1.02, "learning_rate": 2.7910791862748247e-05, "loss": 3.9553, "step": 1349120 }, { "epoch": 1.02, "learning_rate": 2.7902405915237727e-05, "loss": 3.9456, "step": 1349632 }, { "epoch": 1.02, "learning_rate": 2.789401996772721e-05, "loss": 3.9415, "step": 1350144 }, { "epoch": 1.02, "learning_rate": 2.788563402021669e-05, "loss": 3.9584, "step": 1350656 }, { "epoch": 1.02, "learning_rate": 2.7877248072706163e-05, "loss": 3.9384, "step": 1351168 }, { "epoch": 1.02, "learning_rate": 2.786887850399938e-05, "loss": 3.9478, "step": 1351680 }, { "epoch": 1.02, "learning_rate": 2.7860508935292588e-05, "loss": 3.9474, "step": 1352192 }, { "epoch": 1.02, "learning_rate": 2.785212298778207e-05, "loss": 3.948, "step": 1352704 }, { "epoch": 1.02, "learning_rate": 2.784373704027155e-05, "loss": 3.9376, "step": 1353216 }, { "epoch": 1.02, "learning_rate": 2.783535109276103e-05, "loss": 3.9483, "step": 1353728 }, { "epoch": 1.02, "learning_rate": 2.782696514525051e-05, "loss": 3.9359, "step": 1354240 }, { "epoch": 1.02, "learning_rate": 2.781859557654372e-05, "loss": 3.9449, "step": 1354752 }, { "epoch": 1.02, "learning_rate": 2.78102096290332e-05, "loss": 3.9474, "step": 1355264 }, { "epoch": 1.02, "learning_rate": 2.780182368152268e-05, "loss": 3.9428, "step": 1355776 }, { "epoch": 1.02, "learning_rate": 2.779343773401216e-05, "loss": 3.9617, "step": 1356288 }, { "epoch": 1.02, "learning_rate": 2.7785051786501637e-05, "loss": 3.9633, "step": 1356800 }, { "epoch": 1.02, "learning_rate": 2.7776698596598582e-05, "loss": 3.9526, "step": 1357312 }, { "epoch": 1.02, "learning_rate": 2.7768329027891795e-05, "loss": 3.9436, "step": 1357824 }, { "epoch": 1.02, "learning_rate": 2.7759943080381274e-05, "loss": 3.94, "step": 1358336 }, { "epoch": 1.02, "learning_rate": 2.7751557132870754e-05, "loss": 3.9472, "step": 1358848 }, { "epoch": 1.02, "learning_rate": 2.7743171185360234e-05, "loss": 3.9435, "step": 1359360 }, { "epoch": 1.02, "learning_rate": 2.7734785237849714e-05, "loss": 3.9548, "step": 1359872 }, { "epoch": 1.02, "learning_rate": 2.7726399290339194e-05, "loss": 3.9361, "step": 1360384 }, { "epoch": 1.02, "learning_rate": 2.7718013342828674e-05, "loss": 3.9478, "step": 1360896 }, { "epoch": 1.02, "learning_rate": 2.7709627395318154e-05, "loss": 3.9495, "step": 1361408 }, { "epoch": 1.02, "learning_rate": 2.7701241447807634e-05, "loss": 3.9515, "step": 1361920 }, { "epoch": 1.02, "learning_rate": 2.769285550029711e-05, "loss": 3.9389, "step": 1362432 }, { "epoch": 1.02, "learning_rate": 2.768446955278659e-05, "loss": 3.9459, "step": 1362944 }, { "epoch": 1.02, "learning_rate": 2.767608360527607e-05, "loss": 3.9473, "step": 1363456 }, { "epoch": 1.02, "learning_rate": 2.766769765776555e-05, "loss": 3.9518, "step": 1363968 }, { "epoch": 1.02, "learning_rate": 2.765931171025503e-05, "loss": 3.9566, "step": 1364480 }, { "epoch": 1.02, "learning_rate": 2.765092576274451e-05, "loss": 3.956, "step": 1364992 }, { "epoch": 1.02, "learning_rate": 2.764253981523399e-05, "loss": 3.9382, "step": 1365504 }, { "epoch": 1.02, "learning_rate": 2.7634170246527203e-05, "loss": 3.9525, "step": 1366016 }, { "epoch": 1.02, "learning_rate": 2.7625784299016683e-05, "loss": 3.9515, "step": 1366528 }, { "epoch": 1.02, "learning_rate": 2.7617414730309892e-05, "loss": 3.9472, "step": 1367040 }, { "epoch": 1.02, "learning_rate": 2.7609028782799372e-05, "loss": 3.9504, "step": 1367552 }, { "epoch": 1.02, "learning_rate": 2.7600642835288852e-05, "loss": 3.9559, "step": 1368064 }, { "epoch": 1.02, "learning_rate": 2.7592256887778335e-05, "loss": 3.9482, "step": 1368576 }, { "epoch": 1.02, "learning_rate": 2.7583870940267815e-05, "loss": 3.9649, "step": 1369088 }, { "epoch": 1.02, "learning_rate": 2.7575484992757295e-05, "loss": 3.942, "step": 1369600 }, { "epoch": 1.02, "learning_rate": 2.7567099045246775e-05, "loss": 3.9555, "step": 1370112 }, { "epoch": 1.02, "learning_rate": 2.7558713097736255e-05, "loss": 3.9483, "step": 1370624 }, { "epoch": 1.02, "learning_rate": 2.7550343529029464e-05, "loss": 3.9424, "step": 1371136 }, { "epoch": 1.02, "learning_rate": 2.7541957581518944e-05, "loss": 3.9466, "step": 1371648 }, { "epoch": 1.02, "learning_rate": 2.7533588012812157e-05, "loss": 3.9429, "step": 1372160 }, { "epoch": 1.02, "learning_rate": 2.7525202065301637e-05, "loss": 3.945, "step": 1372672 }, { "epoch": 1.02, "learning_rate": 2.7516816117791117e-05, "loss": 3.9448, "step": 1373184 }, { "epoch": 1.02, "learning_rate": 2.7508446549084326e-05, "loss": 3.9411, "step": 1373696 }, { "epoch": 1.03, "eval_loss": 4.0179524421691895, "eval_runtime": 295.0017, "eval_samples_per_second": 1293.521, "eval_steps_per_second": 40.423, "step": 1373760 }, { "epoch": 0.0, "learning_rate": 2.7500060601573806e-05, "loss": 3.9461, "step": 1374208 }, { "epoch": 0.0, "learning_rate": 2.749167465406329e-05, "loss": 3.9418, "step": 1374720 }, { "epoch": 0.0, "learning_rate": 2.748328870655277e-05, "loss": 3.9574, "step": 1375232 }, { "epoch": 0.0, "learning_rate": 2.747490275904225e-05, "loss": 3.9492, "step": 1375744 }, { "epoch": 0.0, "learning_rate": 2.746651681153173e-05, "loss": 3.9646, "step": 1376256 }, { "epoch": 0.0, "learning_rate": 2.745813086402121e-05, "loss": 3.9409, "step": 1376768 }, { "epoch": 0.0, "learning_rate": 2.744974491651069e-05, "loss": 3.9462, "step": 1377280 }, { "epoch": 0.0, "learning_rate": 2.744135896900017e-05, "loss": 3.9351, "step": 1377792 }, { "epoch": 0.0, "learning_rate": 2.743297302148965e-05, "loss": 3.9519, "step": 1378304 }, { "epoch": 0.0, "learning_rate": 2.7424587073979125e-05, "loss": 3.9473, "step": 1378816 }, { "epoch": 0.0, "learning_rate": 2.7416201126468605e-05, "loss": 3.9458, "step": 1379328 }, { "epoch": 0.0, "learning_rate": 2.7407815178958085e-05, "loss": 3.956, "step": 1379840 }, { "epoch": 0.0, "learning_rate": 2.739946198905503e-05, "loss": 3.9347, "step": 1380352 }, { "epoch": 0.0, "learning_rate": 2.739107604154451e-05, "loss": 3.9489, "step": 1380864 }, { "epoch": 0.0, "learning_rate": 2.738269009403399e-05, "loss": 3.9366, "step": 1381376 }, { "epoch": 0.0, "learning_rate": 2.7374304146523473e-05, "loss": 3.9394, "step": 1381888 }, { "epoch": 0.0, "learning_rate": 2.7365918199012947e-05, "loss": 3.9384, "step": 1382400 }, { "epoch": 0.0, "learning_rate": 2.7357532251502426e-05, "loss": 3.9492, "step": 1382912 }, { "epoch": 0.0, "learning_rate": 2.7349146303991906e-05, "loss": 3.9455, "step": 1383424 }, { "epoch": 0.0, "learning_rate": 2.7340760356481386e-05, "loss": 3.9647, "step": 1383936 }, { "epoch": 0.0, "learning_rate": 2.7332374408970866e-05, "loss": 3.9449, "step": 1384448 }, { "epoch": 0.0, "learning_rate": 2.732398846146035e-05, "loss": 3.9475, "step": 1384960 }, { "epoch": 0.0, "learning_rate": 2.731560251394983e-05, "loss": 3.9461, "step": 1385472 }, { "epoch": 0.0, "learning_rate": 2.730721656643931e-05, "loss": 3.9536, "step": 1385984 }, { "epoch": 0.0, "learning_rate": 2.729883061892879e-05, "loss": 3.9448, "step": 1386496 }, { "epoch": 0.0, "learning_rate": 2.729044467141827e-05, "loss": 3.9499, "step": 1387008 }, { "epoch": 0.0, "learning_rate": 2.728205872390775e-05, "loss": 3.9377, "step": 1387520 }, { "epoch": 0.0, "learning_rate": 2.727367277639723e-05, "loss": 3.9427, "step": 1388032 }, { "epoch": 0.0, "learning_rate": 2.726530320769044e-05, "loss": 3.9335, "step": 1388544 }, { "epoch": 0.01, "learning_rate": 2.7256917260179922e-05, "loss": 3.9489, "step": 1389056 }, { "epoch": 0.01, "learning_rate": 2.7248531312669402e-05, "loss": 3.9493, "step": 1389568 }, { "epoch": 0.01, "learning_rate": 2.7240145365158882e-05, "loss": 3.9487, "step": 1390080 }, { "epoch": 0.01, "learning_rate": 2.723177579645209e-05, "loss": 3.9554, "step": 1390592 }, { "epoch": 0.01, "learning_rate": 2.722338984894157e-05, "loss": 3.9458, "step": 1391104 }, { "epoch": 0.01, "learning_rate": 2.7215020280234783e-05, "loss": 3.947, "step": 1391616 }, { "epoch": 0.01, "learning_rate": 2.7206634332724263e-05, "loss": 3.9508, "step": 1392128 }, { "epoch": 0.01, "learning_rate": 2.7198264764017472e-05, "loss": 3.9423, "step": 1392640 }, { "epoch": 0.01, "learning_rate": 2.7189878816506952e-05, "loss": 3.9389, "step": 1393152 }, { "epoch": 0.01, "learning_rate": 2.7181492868996432e-05, "loss": 3.93, "step": 1393664 }, { "epoch": 0.01, "learning_rate": 2.7173106921485912e-05, "loss": 3.9396, "step": 1394176 }, { "epoch": 0.01, "learning_rate": 2.7164720973975392e-05, "loss": 3.9418, "step": 1394688 }, { "epoch": 0.01, "learning_rate": 2.7156335026464876e-05, "loss": 3.9499, "step": 1395200 }, { "epoch": 0.01, "learning_rate": 2.7147949078954356e-05, "loss": 3.9428, "step": 1395712 }, { "epoch": 0.01, "learning_rate": 2.7139563131443835e-05, "loss": 3.9338, "step": 1396224 }, { "epoch": 0.01, "learning_rate": 2.713117718393331e-05, "loss": 3.9508, "step": 1396736 }, { "epoch": 0.01, "learning_rate": 2.712279123642279e-05, "loss": 3.9442, "step": 1397248 }, { "epoch": 0.01, "learning_rate": 2.7114421667716004e-05, "loss": 3.9407, "step": 1397760 }, { "epoch": 0.01, "learning_rate": 2.7106035720205484e-05, "loss": 3.9365, "step": 1398272 }, { "epoch": 0.01, "learning_rate": 2.709764977269496e-05, "loss": 3.9295, "step": 1398784 }, { "epoch": 0.01, "learning_rate": 2.708926382518444e-05, "loss": 3.9598, "step": 1399296 }, { "epoch": 0.01, "learning_rate": 2.708087787767392e-05, "loss": 3.9545, "step": 1399808 }, { "epoch": 0.01, "learning_rate": 2.70724919301634e-05, "loss": 3.9371, "step": 1400320 }, { "epoch": 0.01, "learning_rate": 2.706410598265288e-05, "loss": 3.9404, "step": 1400832 }, { "epoch": 0.01, "learning_rate": 2.705572003514236e-05, "loss": 3.9496, "step": 1401344 }, { "epoch": 0.01, "learning_rate": 2.7047350466435573e-05, "loss": 3.9318, "step": 1401856 }, { "epoch": 0.01, "learning_rate": 2.7038980897728782e-05, "loss": 3.9525, "step": 1402368 }, { "epoch": 0.01, "learning_rate": 2.7030594950218262e-05, "loss": 3.9291, "step": 1402880 }, { "epoch": 0.01, "learning_rate": 2.7022209002707742e-05, "loss": 3.9531, "step": 1403392 }, { "epoch": 0.01, "learning_rate": 2.7013823055197222e-05, "loss": 3.9534, "step": 1403904 }, { "epoch": 0.01, "learning_rate": 2.7005437107686706e-05, "loss": 3.9367, "step": 1404416 }, { "epoch": 0.01, "learning_rate": 2.6997051160176186e-05, "loss": 3.9302, "step": 1404928 }, { "epoch": 0.01, "learning_rate": 2.6988665212665665e-05, "loss": 3.9497, "step": 1405440 }, { "epoch": 0.01, "learning_rate": 2.6980279265155145e-05, "loss": 3.9222, "step": 1405952 }, { "epoch": 0.01, "learning_rate": 2.6971893317644625e-05, "loss": 3.9386, "step": 1406464 }, { "epoch": 0.01, "learning_rate": 2.6963507370134105e-05, "loss": 3.9475, "step": 1406976 }, { "epoch": 0.01, "learning_rate": 2.6955137801427314e-05, "loss": 3.9478, "step": 1407488 }, { "epoch": 0.01, "learning_rate": 2.6946751853916798e-05, "loss": 3.9405, "step": 1408000 }, { "epoch": 0.01, "learning_rate": 2.6938365906406278e-05, "loss": 3.9277, "step": 1408512 }, { "epoch": 0.01, "learning_rate": 2.6929979958895758e-05, "loss": 3.9318, "step": 1409024 }, { "epoch": 0.01, "learning_rate": 2.6921594011385238e-05, "loss": 3.9326, "step": 1409536 }, { "epoch": 0.01, "learning_rate": 2.6913208063874718e-05, "loss": 3.9453, "step": 1410048 }, { "epoch": 0.01, "learning_rate": 2.6904822116364198e-05, "loss": 3.9357, "step": 1410560 }, { "epoch": 0.01, "learning_rate": 2.6896436168853674e-05, "loss": 3.9453, "step": 1411072 }, { "epoch": 0.01, "learning_rate": 2.688806660014689e-05, "loss": 3.9492, "step": 1411584 }, { "epoch": 0.01, "learning_rate": 2.68796970314401e-05, "loss": 3.9514, "step": 1412096 }, { "epoch": 0.01, "learning_rate": 2.687131108392958e-05, "loss": 3.9328, "step": 1412608 }, { "epoch": 0.01, "learning_rate": 2.686292513641906e-05, "loss": 3.9402, "step": 1413120 }, { "epoch": 0.01, "learning_rate": 2.685453918890854e-05, "loss": 3.9485, "step": 1413632 }, { "epoch": 0.01, "learning_rate": 2.684615324139802e-05, "loss": 3.9376, "step": 1414144 }, { "epoch": 0.01, "learning_rate": 2.6837767293887495e-05, "loss": 3.9415, "step": 1414656 }, { "epoch": 0.01, "learning_rate": 2.6829381346376975e-05, "loss": 3.9394, "step": 1415168 }, { "epoch": 0.01, "learning_rate": 2.6820995398866455e-05, "loss": 3.9424, "step": 1415680 }, { "epoch": 0.01, "learning_rate": 2.6812609451355935e-05, "loss": 3.943, "step": 1416192 }, { "epoch": 0.01, "learning_rate": 2.6804239882649144e-05, "loss": 3.9274, "step": 1416704 }, { "epoch": 0.01, "learning_rate": 2.6795853935138628e-05, "loss": 3.9408, "step": 1417216 }, { "epoch": 0.01, "learning_rate": 2.6787467987628108e-05, "loss": 3.9355, "step": 1417728 }, { "epoch": 0.01, "learning_rate": 2.6779082040117588e-05, "loss": 3.9452, "step": 1418240 }, { "epoch": 0.01, "learning_rate": 2.6770728850214533e-05, "loss": 3.9389, "step": 1418752 }, { "epoch": 0.01, "learning_rate": 2.6762342902704013e-05, "loss": 3.9378, "step": 1419264 }, { "epoch": 0.02, "learning_rate": 2.6753956955193493e-05, "loss": 3.9354, "step": 1419776 }, { "epoch": 0.02, "learning_rate": 2.674557100768297e-05, "loss": 3.9304, "step": 1420288 }, { "epoch": 0.02, "learning_rate": 2.6737201438976185e-05, "loss": 3.9277, "step": 1420800 }, { "epoch": 0.02, "learning_rate": 2.6728815491465665e-05, "loss": 3.9416, "step": 1421312 }, { "epoch": 0.02, "learning_rate": 2.6720429543955145e-05, "loss": 3.9513, "step": 1421824 }, { "epoch": 0.02, "learning_rate": 2.6712043596444618e-05, "loss": 3.9446, "step": 1422336 }, { "epoch": 0.02, "learning_rate": 2.6703657648934098e-05, "loss": 3.9399, "step": 1422848 }, { "epoch": 0.02, "learning_rate": 2.669527170142358e-05, "loss": 3.9344, "step": 1423360 }, { "epoch": 0.02, "learning_rate": 2.668688575391306e-05, "loss": 3.9382, "step": 1423872 }, { "epoch": 0.02, "learning_rate": 2.667849980640254e-05, "loss": 3.9398, "step": 1424384 }, { "epoch": 0.02, "learning_rate": 2.667011385889202e-05, "loss": 3.947, "step": 1424896 }, { "epoch": 0.02, "learning_rate": 2.666174429018523e-05, "loss": 3.9439, "step": 1425408 }, { "epoch": 0.02, "learning_rate": 2.665335834267471e-05, "loss": 3.9374, "step": 1425920 }, { "epoch": 0.02, "learning_rate": 2.664497239516419e-05, "loss": 3.9298, "step": 1426432 }, { "epoch": 0.02, "learning_rate": 2.663658644765367e-05, "loss": 3.9498, "step": 1426944 }, { "epoch": 0.02, "learning_rate": 2.6628216878946883e-05, "loss": 3.9286, "step": 1427456 }, { "epoch": 0.02, "learning_rate": 2.6619830931436363e-05, "loss": 3.9409, "step": 1427968 }, { "epoch": 0.02, "learning_rate": 2.6611444983925843e-05, "loss": 3.9326, "step": 1428480 }, { "epoch": 0.02, "learning_rate": 2.6603059036415323e-05, "loss": 3.9406, "step": 1428992 }, { "epoch": 0.02, "learning_rate": 2.6594689467708532e-05, "loss": 3.9304, "step": 1429504 }, { "epoch": 0.02, "learning_rate": 2.6586303520198015e-05, "loss": 3.941, "step": 1430016 }, { "epoch": 0.02, "learning_rate": 2.6577917572687495e-05, "loss": 3.93, "step": 1430528 }, { "epoch": 0.02, "learning_rate": 2.6569531625176975e-05, "loss": 3.9316, "step": 1431040 }, { "epoch": 0.02, "learning_rate": 2.6561162056470184e-05, "loss": 3.9435, "step": 1431552 }, { "epoch": 0.02, "learning_rate": 2.6552776108959664e-05, "loss": 3.9309, "step": 1432064 }, { "epoch": 0.02, "learning_rate": 2.6544390161449144e-05, "loss": 3.9522, "step": 1432576 }, { "epoch": 0.02, "learning_rate": 2.6536004213938624e-05, "loss": 3.9525, "step": 1433088 }, { "epoch": 0.02, "learning_rate": 2.6527651024035566e-05, "loss": 3.9448, "step": 1433600 }, { "epoch": 0.02, "learning_rate": 2.6519265076525046e-05, "loss": 3.9343, "step": 1434112 }, { "epoch": 0.02, "learning_rate": 2.6510879129014525e-05, "loss": 3.9323, "step": 1434624 }, { "epoch": 0.02, "learning_rate": 2.6502493181504005e-05, "loss": 3.9354, "step": 1435136 }, { "epoch": 0.02, "learning_rate": 2.6494107233993485e-05, "loss": 3.9357, "step": 1435648 }, { "epoch": 0.02, "learning_rate": 2.648572128648297e-05, "loss": 3.9456, "step": 1436160 }, { "epoch": 0.02, "learning_rate": 2.647733533897245e-05, "loss": 3.9281, "step": 1436672 }, { "epoch": 0.02, "learning_rate": 2.646894939146193e-05, "loss": 3.9392, "step": 1437184 }, { "epoch": 0.02, "learning_rate": 2.646056344395141e-05, "loss": 3.9433, "step": 1437696 }, { "epoch": 0.02, "learning_rate": 2.645217749644089e-05, "loss": 3.941, "step": 1438208 }, { "epoch": 0.02, "learning_rate": 2.644379154893037e-05, "loss": 3.9335, "step": 1438720 }, { "epoch": 0.02, "learning_rate": 2.643540560141985e-05, "loss": 3.9345, "step": 1439232 }, { "epoch": 0.02, "learning_rate": 2.642703603271306e-05, "loss": 3.9382, "step": 1439744 }, { "epoch": 0.02, "learning_rate": 2.641866646400627e-05, "loss": 3.9419, "step": 1440256 }, { "epoch": 0.02, "learning_rate": 2.641028051649575e-05, "loss": 3.9437, "step": 1440768 }, { "epoch": 0.02, "learning_rate": 2.640189456898523e-05, "loss": 3.9512, "step": 1441280 }, { "epoch": 0.02, "learning_rate": 2.639350862147471e-05, "loss": 3.9296, "step": 1441792 }, { "epoch": 0.02, "learning_rate": 2.638512267396419e-05, "loss": 3.9449, "step": 1442304 }, { "epoch": 0.02, "learning_rate": 2.637673672645367e-05, "loss": 3.9444, "step": 1442816 }, { "epoch": 0.02, "learning_rate": 2.6368350778943153e-05, "loss": 3.9375, "step": 1443328 }, { "epoch": 0.02, "learning_rate": 2.6359964831432626e-05, "loss": 3.939, "step": 1443840 }, { "epoch": 0.02, "learning_rate": 2.6351578883922106e-05, "loss": 3.9488, "step": 1444352 }, { "epoch": 0.02, "learning_rate": 2.6343209315215322e-05, "loss": 3.9397, "step": 1444864 }, { "epoch": 0.02, "learning_rate": 2.6334823367704802e-05, "loss": 3.9562, "step": 1445376 }, { "epoch": 0.02, "learning_rate": 2.632643742019428e-05, "loss": 3.9324, "step": 1445888 }, { "epoch": 0.02, "learning_rate": 2.631805147268376e-05, "loss": 3.9426, "step": 1446400 }, { "epoch": 0.02, "learning_rate": 2.630966552517324e-05, "loss": 3.9392, "step": 1446912 }, { "epoch": 0.02, "learning_rate": 2.6301295956466448e-05, "loss": 3.9359, "step": 1447424 }, { "epoch": 0.02, "learning_rate": 2.6292910008955928e-05, "loss": 3.9365, "step": 1447936 }, { "epoch": 0.02, "learning_rate": 2.6284524061445408e-05, "loss": 3.9347, "step": 1448448 }, { "epoch": 0.02, "learning_rate": 2.627613811393489e-05, "loss": 3.933, "step": 1448960 }, { "epoch": 0.02, "learning_rate": 2.6267784924031836e-05, "loss": 3.9372, "step": 1449472 }, { "epoch": 0.02, "learning_rate": 2.6259398976521316e-05, "loss": 3.9354, "step": 1449984 }, { "epoch": 0.03, "eval_loss": 4.013299465179443, "eval_runtime": 295.3219, "eval_samples_per_second": 1292.119, "eval_steps_per_second": 40.38, "step": 1450080 }, { "epoch": 1.0, "learning_rate": 2.6251013029010796e-05, "loss": 3.9386, "step": 1450496 }, { "epoch": 1.0, "learning_rate": 2.6242643460304005e-05, "loss": 3.9333, "step": 1451008 }, { "epoch": 1.0, "learning_rate": 2.6234257512793485e-05, "loss": 3.9461, "step": 1451520 }, { "epoch": 1.0, "learning_rate": 2.6225871565282968e-05, "loss": 3.9392, "step": 1452032 }, { "epoch": 1.0, "learning_rate": 2.6217485617772448e-05, "loss": 3.9573, "step": 1452544 }, { "epoch": 1.0, "learning_rate": 2.620909967026192e-05, "loss": 3.9345, "step": 1453056 }, { "epoch": 1.0, "learning_rate": 2.62007137227514e-05, "loss": 3.9382, "step": 1453568 }, { "epoch": 1.0, "learning_rate": 2.619232777524088e-05, "loss": 3.9267, "step": 1454080 }, { "epoch": 1.0, "learning_rate": 2.618394182773036e-05, "loss": 3.9397, "step": 1454592 }, { "epoch": 1.0, "learning_rate": 2.6175555880219845e-05, "loss": 3.9416, "step": 1455104 }, { "epoch": 1.0, "learning_rate": 2.6167169932709325e-05, "loss": 3.9356, "step": 1455616 }, { "epoch": 1.0, "learning_rate": 2.6158783985198805e-05, "loss": 3.9421, "step": 1456128 }, { "epoch": 1.0, "learning_rate": 2.6150414416492014e-05, "loss": 3.931, "step": 1456640 }, { "epoch": 1.0, "learning_rate": 2.6142028468981494e-05, "loss": 3.9404, "step": 1457152 }, { "epoch": 1.0, "learning_rate": 2.6133642521470974e-05, "loss": 3.9299, "step": 1457664 }, { "epoch": 1.0, "learning_rate": 2.6125256573960454e-05, "loss": 3.9285, "step": 1458176 }, { "epoch": 1.0, "learning_rate": 2.6116870626449937e-05, "loss": 3.9298, "step": 1458688 }, { "epoch": 1.0, "learning_rate": 2.6108484678939417e-05, "loss": 3.9358, "step": 1459200 }, { "epoch": 1.0, "learning_rate": 2.6100098731428897e-05, "loss": 3.9379, "step": 1459712 }, { "epoch": 1.0, "learning_rate": 2.6091712783918377e-05, "loss": 3.954, "step": 1460224 }, { "epoch": 1.0, "learning_rate": 2.6083343215211586e-05, "loss": 3.9378, "step": 1460736 }, { "epoch": 1.0, "learning_rate": 2.6074973646504798e-05, "loss": 3.9438, "step": 1461248 }, { "epoch": 1.0, "learning_rate": 2.6066587698994278e-05, "loss": 3.9355, "step": 1461760 }, { "epoch": 1.0, "learning_rate": 2.6058201751483758e-05, "loss": 3.9425, "step": 1462272 }, { "epoch": 1.0, "learning_rate": 2.6049815803973238e-05, "loss": 3.9387, "step": 1462784 }, { "epoch": 1.0, "learning_rate": 2.6041429856462718e-05, "loss": 3.9415, "step": 1463296 }, { "epoch": 1.0, "learning_rate": 2.6033060287755927e-05, "loss": 3.9316, "step": 1463808 }, { "epoch": 1.0, "learning_rate": 2.6024674340245407e-05, "loss": 3.9288, "step": 1464320 }, { "epoch": 1.0, "learning_rate": 2.6016288392734887e-05, "loss": 3.93, "step": 1464832 }, { "epoch": 1.01, "learning_rate": 2.600790244522437e-05, "loss": 3.939, "step": 1465344 }, { "epoch": 1.01, "learning_rate": 2.599951649771385e-05, "loss": 3.9409, "step": 1465856 }, { "epoch": 1.01, "learning_rate": 2.599114692900706e-05, "loss": 3.9396, "step": 1466368 }, { "epoch": 1.01, "learning_rate": 2.598276098149654e-05, "loss": 3.9486, "step": 1466880 }, { "epoch": 1.01, "learning_rate": 2.597437503398602e-05, "loss": 3.9394, "step": 1467392 }, { "epoch": 1.01, "learning_rate": 2.5966005465279232e-05, "loss": 3.9348, "step": 1467904 }, { "epoch": 1.01, "learning_rate": 2.5957619517768712e-05, "loss": 3.9398, "step": 1468416 }, { "epoch": 1.01, "learning_rate": 2.5949233570258192e-05, "loss": 3.9398, "step": 1468928 }, { "epoch": 1.01, "learning_rate": 2.5940847622747672e-05, "loss": 3.9279, "step": 1469440 }, { "epoch": 1.01, "learning_rate": 2.5932461675237152e-05, "loss": 3.9215, "step": 1469952 }, { "epoch": 1.01, "learning_rate": 2.5924075727726632e-05, "loss": 3.9274, "step": 1470464 }, { "epoch": 1.01, "learning_rate": 2.591568978021611e-05, "loss": 3.9374, "step": 1470976 }, { "epoch": 1.01, "learning_rate": 2.5907303832705588e-05, "loss": 3.9396, "step": 1471488 }, { "epoch": 1.01, "learning_rate": 2.5898917885195068e-05, "loss": 3.9362, "step": 1472000 }, { "epoch": 1.01, "learning_rate": 2.5890531937684548e-05, "loss": 3.9231, "step": 1472512 }, { "epoch": 1.01, "learning_rate": 2.5882162368977757e-05, "loss": 3.9406, "step": 1473024 }, { "epoch": 1.01, "learning_rate": 2.5873776421467237e-05, "loss": 3.9352, "step": 1473536 }, { "epoch": 1.01, "learning_rate": 2.5865390473956717e-05, "loss": 3.9327, "step": 1474048 }, { "epoch": 1.01, "learning_rate": 2.58570045264462e-05, "loss": 3.9271, "step": 1474560 }, { "epoch": 1.01, "learning_rate": 2.584861857893568e-05, "loss": 3.9144, "step": 1475072 }, { "epoch": 1.01, "learning_rate": 2.584023263142516e-05, "loss": 3.9565, "step": 1475584 }, { "epoch": 1.01, "learning_rate": 2.583184668391464e-05, "loss": 3.9426, "step": 1476096 }, { "epoch": 1.01, "learning_rate": 2.582346073640412e-05, "loss": 3.9319, "step": 1476608 }, { "epoch": 1.01, "learning_rate": 2.581509116769733e-05, "loss": 3.9356, "step": 1477120 }, { "epoch": 1.01, "learning_rate": 2.5806721598990542e-05, "loss": 3.9361, "step": 1477632 }, { "epoch": 1.01, "learning_rate": 2.5798335651480022e-05, "loss": 3.926, "step": 1478144 }, { "epoch": 1.01, "learning_rate": 2.5789949703969502e-05, "loss": 3.941, "step": 1478656 }, { "epoch": 1.01, "learning_rate": 2.5781563756458982e-05, "loss": 3.9235, "step": 1479168 }, { "epoch": 1.01, "learning_rate": 2.5773177808948462e-05, "loss": 3.94, "step": 1479680 }, { "epoch": 1.01, "learning_rate": 2.576479186143794e-05, "loss": 3.9485, "step": 1480192 }, { "epoch": 1.01, "learning_rate": 2.575640591392742e-05, "loss": 3.9294, "step": 1480704 }, { "epoch": 1.01, "learning_rate": 2.57480199664169e-05, "loss": 3.9191, "step": 1481216 }, { "epoch": 1.01, "learning_rate": 2.5739634018906385e-05, "loss": 3.9465, "step": 1481728 }, { "epoch": 1.01, "learning_rate": 2.5731264450199594e-05, "loss": 3.9133, "step": 1482240 }, { "epoch": 1.01, "learning_rate": 2.5722878502689074e-05, "loss": 3.9249, "step": 1482752 }, { "epoch": 1.01, "learning_rate": 2.5714492555178554e-05, "loss": 3.9418, "step": 1483264 }, { "epoch": 1.01, "learning_rate": 2.5706106607668034e-05, "loss": 3.9374, "step": 1483776 }, { "epoch": 1.01, "learning_rate": 2.5697737038961246e-05, "loss": 3.9308, "step": 1484288 }, { "epoch": 1.01, "learning_rate": 2.5689351091450726e-05, "loss": 3.9243, "step": 1484800 }, { "epoch": 1.01, "learning_rate": 2.5680965143940206e-05, "loss": 3.9158, "step": 1485312 }, { "epoch": 1.01, "learning_rate": 2.5672579196429686e-05, "loss": 3.9245, "step": 1485824 }, { "epoch": 1.01, "learning_rate": 2.5664209627722895e-05, "loss": 3.9399, "step": 1486336 }, { "epoch": 1.01, "learning_rate": 2.5655823680212375e-05, "loss": 3.9243, "step": 1486848 }, { "epoch": 1.01, "learning_rate": 2.5647437732701855e-05, "loss": 3.9407, "step": 1487360 }, { "epoch": 1.01, "learning_rate": 2.563905178519134e-05, "loss": 3.9357, "step": 1487872 }, { "epoch": 1.01, "learning_rate": 2.563066583768082e-05, "loss": 3.9469, "step": 1488384 }, { "epoch": 1.01, "learning_rate": 2.5622296268974028e-05, "loss": 3.9278, "step": 1488896 }, { "epoch": 1.01, "learning_rate": 2.5613926700267237e-05, "loss": 3.9279, "step": 1489408 }, { "epoch": 1.01, "learning_rate": 2.5605540752756717e-05, "loss": 3.9405, "step": 1489920 }, { "epoch": 1.01, "learning_rate": 2.55971548052462e-05, "loss": 3.9272, "step": 1490432 }, { "epoch": 1.01, "learning_rate": 2.558876885773568e-05, "loss": 3.9383, "step": 1490944 }, { "epoch": 1.01, "learning_rate": 2.558038291022516e-05, "loss": 3.9299, "step": 1491456 }, { "epoch": 1.01, "learning_rate": 2.557199696271464e-05, "loss": 3.9321, "step": 1491968 }, { "epoch": 1.01, "learning_rate": 2.556362739400785e-05, "loss": 3.9362, "step": 1492480 }, { "epoch": 1.01, "learning_rate": 2.555524144649733e-05, "loss": 3.9204, "step": 1492992 }, { "epoch": 1.01, "learning_rate": 2.554685549898681e-05, "loss": 3.9306, "step": 1493504 }, { "epoch": 1.01, "learning_rate": 2.5538469551476292e-05, "loss": 3.9304, "step": 1494016 }, { "epoch": 1.01, "learning_rate": 2.55300999827695e-05, "loss": 3.9357, "step": 1494528 }, { "epoch": 1.01, "learning_rate": 2.552171403525898e-05, "loss": 3.9298, "step": 1495040 }, { "epoch": 1.01, "learning_rate": 2.551332808774846e-05, "loss": 3.9303, "step": 1495552 }, { "epoch": 1.02, "learning_rate": 2.550494214023794e-05, "loss": 3.925, "step": 1496064 }, { "epoch": 1.02, "learning_rate": 2.5496572571531154e-05, "loss": 3.9228, "step": 1496576 }, { "epoch": 1.02, "learning_rate": 2.5488186624020634e-05, "loss": 3.9239, "step": 1497088 }, { "epoch": 1.02, "learning_rate": 2.5479800676510114e-05, "loss": 3.9311, "step": 1497600 }, { "epoch": 1.02, "learning_rate": 2.5471414728999594e-05, "loss": 3.9422, "step": 1498112 }, { "epoch": 1.02, "learning_rate": 2.5463028781489067e-05, "loss": 3.9383, "step": 1498624 }, { "epoch": 1.02, "learning_rate": 2.5454642833978547e-05, "loss": 3.9329, "step": 1499136 }, { "epoch": 1.02, "learning_rate": 2.5446273265271763e-05, "loss": 3.9233, "step": 1499648 }, { "epoch": 1.02, "learning_rate": 2.5437887317761243e-05, "loss": 3.9289, "step": 1500160 }, { "epoch": 1.02, "learning_rate": 2.542950137025072e-05, "loss": 3.9336, "step": 1500672 }, { "epoch": 1.02, "learning_rate": 2.54211154227402e-05, "loss": 3.9391, "step": 1501184 }, { "epoch": 1.02, "learning_rate": 2.541272947522968e-05, "loss": 3.9365, "step": 1501696 }, { "epoch": 1.02, "learning_rate": 2.540434352771916e-05, "loss": 3.9302, "step": 1502208 }, { "epoch": 1.02, "learning_rate": 2.539595758020864e-05, "loss": 3.9228, "step": 1502720 }, { "epoch": 1.02, "learning_rate": 2.538757163269812e-05, "loss": 3.9455, "step": 1503232 }, { "epoch": 1.02, "learning_rate": 2.537920206399133e-05, "loss": 3.9141, "step": 1503744 }, { "epoch": 1.02, "learning_rate": 2.537083249528454e-05, "loss": 3.9352, "step": 1504256 }, { "epoch": 1.02, "learning_rate": 2.536244654777402e-05, "loss": 3.9251, "step": 1504768 }, { "epoch": 1.02, "learning_rate": 2.53540606002635e-05, "loss": 3.9324, "step": 1505280 }, { "epoch": 1.02, "learning_rate": 2.5345674652752984e-05, "loss": 3.9215, "step": 1505792 }, { "epoch": 1.02, "learning_rate": 2.5337288705242464e-05, "loss": 3.9321, "step": 1506304 }, { "epoch": 1.02, "learning_rate": 2.5328902757731944e-05, "loss": 3.9233, "step": 1506816 }, { "epoch": 1.02, "learning_rate": 2.5320533189025153e-05, "loss": 3.9233, "step": 1507328 }, { "epoch": 1.02, "learning_rate": 2.5312147241514633e-05, "loss": 3.9315, "step": 1507840 }, { "epoch": 1.02, "learning_rate": 2.5303761294004113e-05, "loss": 3.9239, "step": 1508352 }, { "epoch": 1.02, "learning_rate": 2.5295375346493593e-05, "loss": 3.9426, "step": 1508864 }, { "epoch": 1.02, "learning_rate": 2.5286989398983073e-05, "loss": 3.9447, "step": 1509376 }, { "epoch": 1.02, "learning_rate": 2.5278603451472556e-05, "loss": 3.9379, "step": 1509888 }, { "epoch": 1.02, "learning_rate": 2.5270217503962036e-05, "loss": 3.9267, "step": 1510400 }, { "epoch": 1.02, "learning_rate": 2.5261831556451516e-05, "loss": 3.9267, "step": 1510912 }, { "epoch": 1.02, "learning_rate": 2.5253445608940996e-05, "loss": 3.9244, "step": 1511424 }, { "epoch": 1.02, "learning_rate": 2.5245076040234205e-05, "loss": 3.9256, "step": 1511936 }, { "epoch": 1.02, "learning_rate": 2.5236706471527417e-05, "loss": 3.9379, "step": 1512448 }, { "epoch": 1.02, "learning_rate": 2.5228320524016897e-05, "loss": 3.9151, "step": 1512960 }, { "epoch": 1.02, "learning_rate": 2.5219934576506377e-05, "loss": 3.934, "step": 1513472 }, { "epoch": 1.02, "learning_rate": 2.5211548628995857e-05, "loss": 3.9313, "step": 1513984 }, { "epoch": 1.02, "learning_rate": 2.5203162681485337e-05, "loss": 3.9351, "step": 1514496 }, { "epoch": 1.02, "learning_rate": 2.5194793112778546e-05, "loss": 3.9239, "step": 1515008 }, { "epoch": 1.02, "learning_rate": 2.5186407165268026e-05, "loss": 3.9287, "step": 1515520 }, { "epoch": 1.02, "learning_rate": 2.517802121775751e-05, "loss": 3.9257, "step": 1516032 }, { "epoch": 1.02, "learning_rate": 2.516963527024699e-05, "loss": 3.9408, "step": 1516544 }, { "epoch": 1.02, "learning_rate": 2.516124932273647e-05, "loss": 3.9343, "step": 1517056 }, { "epoch": 1.02, "learning_rate": 2.515286337522595e-05, "loss": 3.9428, "step": 1517568 }, { "epoch": 1.02, "learning_rate": 2.514449380651916e-05, "loss": 3.9186, "step": 1518080 }, { "epoch": 1.02, "learning_rate": 2.513610785900864e-05, "loss": 3.9375, "step": 1518592 }, { "epoch": 1.02, "learning_rate": 2.512772191149812e-05, "loss": 3.9376, "step": 1519104 }, { "epoch": 1.02, "learning_rate": 2.511935234279133e-05, "loss": 3.9229, "step": 1519616 }, { "epoch": 1.02, "learning_rate": 2.511096639528081e-05, "loss": 3.932, "step": 1520128 }, { "epoch": 1.02, "learning_rate": 2.510258044777029e-05, "loss": 3.9419, "step": 1520640 }, { "epoch": 1.02, "learning_rate": 2.509419450025977e-05, "loss": 3.934, "step": 1521152 }, { "epoch": 1.02, "learning_rate": 2.508580855274925e-05, "loss": 3.9488, "step": 1521664 }, { "epoch": 1.02, "learning_rate": 2.5077422605238727e-05, "loss": 3.9245, "step": 1522176 }, { "epoch": 1.02, "learning_rate": 2.5069036657728207e-05, "loss": 3.9389, "step": 1522688 }, { "epoch": 1.02, "learning_rate": 2.5060650710217687e-05, "loss": 3.9279, "step": 1523200 }, { "epoch": 1.02, "learning_rate": 2.5052264762707167e-05, "loss": 3.9299, "step": 1523712 }, { "epoch": 1.02, "learning_rate": 2.5043878815196647e-05, "loss": 3.9284, "step": 1524224 }, { "epoch": 1.02, "learning_rate": 2.5035492867686127e-05, "loss": 3.9283, "step": 1524736 }, { "epoch": 1.02, "learning_rate": 2.5027106920175607e-05, "loss": 3.9237, "step": 1525248 }, { "epoch": 1.02, "learning_rate": 2.501875373027255e-05, "loss": 3.9262, "step": 1525760 }, { "epoch": 1.02, "learning_rate": 2.501036778276203e-05, "loss": 3.927, "step": 1526272 }, { "epoch": 1.03, "eval_loss": 4.009834289550781, "eval_runtime": 293.7762, "eval_samples_per_second": 1298.917, "eval_steps_per_second": 40.592, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.500198183525151e-05, "loss": 3.9292, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4993595887740992e-05, "loss": 3.9251, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.498520994023047e-05, "loss": 3.9401, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.497682399271995e-05, "loss": 3.9309, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4968438045209432e-05, "loss": 3.946, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4960052097698912e-05, "loss": 3.9313, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4951666150188392e-05, "loss": 3.9276, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.494328020267787e-05, "loss": 3.9205, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.4934894255167348e-05, "loss": 3.9304, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.4926508307656828e-05, "loss": 3.9329, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4918122360146308e-05, "loss": 3.9297, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4909736412635788e-05, "loss": 3.932, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.4901366843929e-05, "loss": 3.924, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.489298089641848e-05, "loss": 3.9347, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.488459494890796e-05, "loss": 3.9207, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.487620900139744e-05, "loss": 3.9195, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.486782305388692e-05, "loss": 3.9226, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.48594371063764e-05, "loss": 3.9316, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.4851067537669613e-05, "loss": 3.9289, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4842681590159093e-05, "loss": 3.9447, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4834295642648573e-05, "loss": 3.9314, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.4825909695138053e-05, "loss": 3.9395, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.481752374762753e-05, "loss": 3.925, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.480913780011701e-05, "loss": 3.9316, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.480075185260649e-05, "loss": 3.9301, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.4792365905095973e-05, "loss": 3.9354, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.4783979957585452e-05, "loss": 3.9252, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.4775594010074932e-05, "loss": 3.9257, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.4767208062564412e-05, "loss": 3.9213, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.475883849385762e-05, "loss": 3.9279, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.4750468925150834e-05, "loss": 3.9348, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.4742082977640314e-05, "loss": 3.9329, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4733697030129794e-05, "loss": 3.9376, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4725311082619274e-05, "loss": 3.9292, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4716925135108754e-05, "loss": 3.9281, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.4708555566401963e-05, "loss": 3.9376, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.4700169618891443e-05, "loss": 3.9339, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.4691783671380926e-05, "loss": 3.9155, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4683397723870406e-05, "loss": 3.9182, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4675028155163615e-05, "loss": 3.9182, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4666642207653095e-05, "loss": 3.9247, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4658272638946304e-05, "loss": 3.9346, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.4649886691435788e-05, "loss": 3.9241, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.4641500743925268e-05, "loss": 3.9212, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.4633114796414748e-05, "loss": 3.9292, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.4624728848904228e-05, "loss": 3.9253, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4616342901393707e-05, "loss": 3.9278, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4607956953883184e-05, "loss": 3.922, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4599571006372664e-05, "loss": 3.9019, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.4591185058862144e-05, "loss": 3.9503, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.4582799111351627e-05, "loss": 3.9333, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.4574413163841107e-05, "loss": 3.9314, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.4566027216330587e-05, "loss": 3.9266, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4557657647623796e-05, "loss": 3.9256, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.4549271700113276e-05, "loss": 3.9193, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.454090213140649e-05, "loss": 3.9298, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.453251618389597e-05, "loss": 3.9199, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.452413023638545e-05, "loss": 3.9286, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.451574428887493e-05, "loss": 3.9402, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.450735834136441e-05, "loss": 3.9207, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.449897239385389e-05, "loss": 3.9137, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.4490586446343365e-05, "loss": 3.9356, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.448220049883285e-05, "loss": 3.9061, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.447381455132233e-05, "loss": 3.9193, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.446542860381181e-05, "loss": 3.9289, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.445707541390875e-05, "loss": 3.9293, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.444868946639823e-05, "loss": 3.9228, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.444030351888771e-05, "loss": 3.9195, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.443191757137719e-05, "loss": 3.9066, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.442353162386667e-05, "loss": 3.9184, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4415162055159882e-05, "loss": 3.9305, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.4406776107649362e-05, "loss": 3.9186, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.439840653894257e-05, "loss": 3.9276, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.439002059143205e-05, "loss": 3.9296, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4381634643921535e-05, "loss": 3.9411, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4373248696411015e-05, "loss": 3.9203, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.436486274890049e-05, "loss": 3.918, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.435647680138997e-05, "loss": 3.9326, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.434809085387945e-05, "loss": 3.9174, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.433970490636893e-05, "loss": 3.9348, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.433131895885841e-05, "loss": 3.9222, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.432293301134789e-05, "loss": 3.9238, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.431454706383737e-05, "loss": 3.9303, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.430616111632685e-05, "loss": 3.9133, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.429777516881633e-05, "loss": 3.9225, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.4289405600109543e-05, "loss": 3.9204, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.428101965259902e-05, "loss": 3.9286, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4272633705088503e-05, "loss": 3.9173, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.4264247757577983e-05, "loss": 3.9252, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.4255878188871196e-05, "loss": 3.917, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.4247492241360672e-05, "loss": 3.9177, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.4239106293850152e-05, "loss": 3.9117, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.4230736725143365e-05, "loss": 3.9261, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.4222350777632845e-05, "loss": 3.9357, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.4213964830122325e-05, "loss": 3.926, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.4205578882611804e-05, "loss": 3.9301, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.4197192935101284e-05, "loss": 3.9153, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.4188806987590764e-05, "loss": 3.9198, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.4180437418883974e-05, "loss": 3.9243, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.4172051471373457e-05, "loss": 3.9315, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.4163665523862937e-05, "loss": 3.9281, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.4155295955156146e-05, "loss": 3.9216, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.4146910007645626e-05, "loss": 3.9194, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4138524060135106e-05, "loss": 3.9372, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.4130138112624586e-05, "loss": 3.9097, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.4121752165114066e-05, "loss": 3.9257, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.411336621760355e-05, "loss": 3.9163, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.4104980270093026e-05, "loss": 3.9262, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.4096594322582506e-05, "loss": 3.9147, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4088208375071986e-05, "loss": 3.9239, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4079822427561466e-05, "loss": 3.9151, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4071452858854675e-05, "loss": 3.9181, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4063066911344158e-05, "loss": 3.9233, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4054680963833638e-05, "loss": 3.9182, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4046295016323118e-05, "loss": 3.9313, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4037909068812598e-05, "loss": 3.9374, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4029523121302078e-05, "loss": 3.9266, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4021137173791554e-05, "loss": 3.9245, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4012751226281034e-05, "loss": 3.914, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.400438165757425e-05, "loss": 3.9191, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.399599571006373e-05, "loss": 3.92, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.3987609762553207e-05, "loss": 3.9348, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3979223815042687e-05, "loss": 3.9055, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.39708542463359e-05, "loss": 3.9244, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.396246829882538e-05, "loss": 3.9213, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.395408235131486e-05, "loss": 3.9276, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.394569640380434e-05, "loss": 3.9195, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.393732683509755e-05, "loss": 3.9206, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.3928940887587028e-05, "loss": 3.9149, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.3920554940076508e-05, "loss": 3.9323, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.3912168992565988e-05, "loss": 3.9284, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3903799423859204e-05, "loss": 3.9322, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.389541347634868e-05, "loss": 3.9139, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.388702752883816e-05, "loss": 3.9298, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.387864158132764e-05, "loss": 3.9297, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.387025563381712e-05, "loss": 3.9199, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.38618696863066e-05, "loss": 3.9253, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.385348373879608e-05, "loss": 3.9312, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.3845114170089293e-05, "loss": 3.9234, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3836728222578773e-05, "loss": 3.9459, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3828342275068253e-05, "loss": 3.9162, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.3819956327557733e-05, "loss": 3.9279, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.381157038004721e-05, "loss": 3.9193, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.380318443253669e-05, "loss": 3.9232, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.3794798485026172e-05, "loss": 3.9238, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.3786428916319385e-05, "loss": 3.9188, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.377804296880886e-05, "loss": 3.9206, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.376965702129834e-05, "loss": 3.9117, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.376127107378782e-05, "loss": 3.9227, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 4.006990909576416, "eval_runtime": 296.3428, "eval_samples_per_second": 1287.668, "eval_steps_per_second": 40.241, "step": 1602720 }, { "epoch": 0.0, "learning_rate": 2.37528851262773e-05, "loss": 3.9251, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.374449917876678e-05, "loss": 3.9168, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.373611323125626e-05, "loss": 3.9311, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3727727283745745e-05, "loss": 3.9271, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.371934133623522e-05, "loss": 3.9335, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.37109553887247e-05, "loss": 3.922, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.370256944121418e-05, "loss": 3.9239, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.369418349370366e-05, "loss": 3.9117, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.3685813924996873e-05, "loss": 3.9222, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.3677427977486353e-05, "loss": 3.9251, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.3669042029975833e-05, "loss": 3.927, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.3660656082465313e-05, "loss": 3.921, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.3652270134954793e-05, "loss": 3.9219, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.3643884187444273e-05, "loss": 3.9211, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.363549823993375e-05, "loss": 3.9168, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.362711229242323e-05, "loss": 3.9091, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.3618726344912713e-05, "loss": 3.9164, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.3610340397402193e-05, "loss": 3.9234, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.3601954449891673e-05, "loss": 3.9209, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.3593568502381153e-05, "loss": 3.9361, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.3585182554870633e-05, "loss": 3.9258, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.357679660736011e-05, "loss": 3.9326, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.356841065984959e-05, "loss": 3.92, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.356002471233907e-05, "loss": 3.9232, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.3551655143632282e-05, "loss": 3.9216, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.3543269196121762e-05, "loss": 3.9318, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.3534899627414974e-05, "loss": 3.9179, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.3526513679904454e-05, "loss": 3.9164, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.351812773239393e-05, "loss": 3.9132, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.3509741784883414e-05, "loss": 3.9233, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.3501355837372894e-05, "loss": 3.924, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.3492986268666103e-05, "loss": 3.9272, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3484600321155583e-05, "loss": 3.9281, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.3476230752448796e-05, "loss": 3.9227, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.3467844804938276e-05, "loss": 3.9215, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.3459475236231488e-05, "loss": 3.93, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.3451089288720968e-05, "loss": 3.9254, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.3442703341210448e-05, "loss": 3.9112, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.3434317393699928e-05, "loss": 3.9109, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.3425931446189405e-05, "loss": 3.9093, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.3417545498678885e-05, "loss": 3.913, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.3409159551168368e-05, "loss": 3.9301, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.3400773603657848e-05, "loss": 3.9195, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.3392387656147328e-05, "loss": 3.913, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.3384001708636808e-05, "loss": 3.9228, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.3375615761126284e-05, "loss": 3.917, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3367229813615764e-05, "loss": 3.9216, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.3358843866105244e-05, "loss": 3.9123, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.335047429739846e-05, "loss": 3.8948, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3342088349887937e-05, "loss": 3.9435, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3333702402377417e-05, "loss": 3.9246, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3325316454866897e-05, "loss": 3.9262, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3316930507356377e-05, "loss": 3.9142, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3308544559845856e-05, "loss": 3.9226, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3300158612335336e-05, "loss": 3.9118, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.329180542243228e-05, "loss": 3.9194, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.3283419474921758e-05, "loss": 3.9182, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3275033527411238e-05, "loss": 3.9209, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3266647579900718e-05, "loss": 3.936, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3258261632390198e-05, "loss": 3.9114, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3249875684879678e-05, "loss": 3.9041, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.324148973736916e-05, "loss": 3.9309, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.323310378985864e-05, "loss": 3.9001, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.3224717842348118e-05, "loss": 3.9076, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.3216331894837598e-05, "loss": 3.9258, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.3207945947327078e-05, "loss": 3.9249, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.3199559999816558e-05, "loss": 3.9115, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.319119043110977e-05, "loss": 3.9173, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.318280448359925e-05, "loss": 3.897, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.317441853608873e-05, "loss": 3.9138, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.316603258857821e-05, "loss": 3.9214, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.315766301987142e-05, "loss": 3.9096, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.3149309829968364e-05, "loss": 3.9218, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.3140923882457844e-05, "loss": 3.9207, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.3132537934947324e-05, "loss": 3.9345, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.3124168366240533e-05, "loss": 3.9105, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.3115782418730013e-05, "loss": 3.9152, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.3107396471219493e-05, "loss": 3.9252, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.3099010523708976e-05, "loss": 3.9101, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.3090624576198456e-05, "loss": 3.9227, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.3082238628687936e-05, "loss": 3.9192, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.3073852681177413e-05, "loss": 3.9148, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.3065466733666893e-05, "loss": 3.9254, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.3057080786156373e-05, "loss": 3.9071, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.3048694838645853e-05, "loss": 3.9097, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.3040308891135336e-05, "loss": 3.9164, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.3031922943624816e-05, "loss": 3.9219, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3023536996114296e-05, "loss": 3.9128, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3015151048603772e-05, "loss": 3.9183, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3006765101093252e-05, "loss": 3.9063, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.2998379153582732e-05, "loss": 3.9156, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.2990009584875945e-05, "loss": 3.9071, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.2981623637365425e-05, "loss": 3.9161, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2973237689854905e-05, "loss": 3.9311, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2964868121148117e-05, "loss": 3.9163, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2956482173637594e-05, "loss": 3.922, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2948096226127074e-05, "loss": 3.9101, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2939710278616554e-05, "loss": 3.9135, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2931324331106037e-05, "loss": 3.9157, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2922938383595517e-05, "loss": 3.9258, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.2914552436084997e-05, "loss": 3.9178, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2906166488574477e-05, "loss": 3.9195, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2897780541063954e-05, "loss": 3.9106, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.2889410972357166e-05, "loss": 3.9261, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2881025024846646e-05, "loss": 3.905, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.287265545613986e-05, "loss": 3.9196, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.286426950862934e-05, "loss": 3.9061, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.285588356111882e-05, "loss": 3.9223, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.28474976136083e-05, "loss": 3.9101, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2839111666097775e-05, "loss": 3.9149, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2830725718587255e-05, "loss": 3.9109, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.282235614988047e-05, "loss": 3.9108, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.281397020236995e-05, "loss": 3.9136, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.2805584254859427e-05, "loss": 3.914, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.2797198307348907e-05, "loss": 3.9218, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.2788812359838387e-05, "loss": 3.9285, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.2780426412327867e-05, "loss": 3.9211, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2772040464817347e-05, "loss": 3.9199, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.276365451730683e-05, "loss": 3.9048, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.2755268569796307e-05, "loss": 3.9105, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.2746882622285787e-05, "loss": 3.9143, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.2738513053579e-05, "loss": 3.9257, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.273012710606848e-05, "loss": 3.8991, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.2721773916165424e-05, "loss": 3.9203, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.27133879686549e-05, "loss": 3.9182, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.270500202114438e-05, "loss": 3.9165, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.269661607363386e-05, "loss": 3.9135, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.268823012612334e-05, "loss": 3.9182, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.267984417861282e-05, "loss": 3.9089, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.26714582311023e-05, "loss": 3.9253, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.266307228359178e-05, "loss": 3.9212, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.265468633608126e-05, "loss": 3.9253, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.264630038857074e-05, "loss": 3.9064, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.2637930819863953e-05, "loss": 3.9236, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.262954487235343e-05, "loss": 3.9237, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.262115892484291e-05, "loss": 3.9125, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2612772977332393e-05, "loss": 3.9184, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.2604387029821873e-05, "loss": 3.9229, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.2596001082311353e-05, "loss": 3.9201, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.2587631513604562e-05, "loss": 3.9332, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.2579245566094042e-05, "loss": 3.9151, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.2570859618583522e-05, "loss": 3.9197, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.2562473671073002e-05, "loss": 3.9136, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.2554087723562485e-05, "loss": 3.9181, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.2545701776051962e-05, "loss": 3.9124, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.253731582854144e-05, "loss": 3.9118, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.252892988103092e-05, "loss": 3.9161, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.2520576691127863e-05, "loss": 3.9042, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.2512190743617347e-05, "loss": 3.9201, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 4.004070281982422, "eval_runtime": 292.0611, "eval_samples_per_second": 1306.545, "eval_steps_per_second": 40.83, "step": 1679040 }, { "epoch": 1.0, "learning_rate": 2.2503804796106827e-05, "loss": 3.9189, "step": 1679360 }, { "epoch": 1.0, "learning_rate": 2.2495418848596307e-05, "loss": 3.9116, "step": 1679872 }, { "epoch": 1.0, "learning_rate": 2.2487032901085786e-05, "loss": 3.9211, "step": 1680384 }, { "epoch": 1.0, "learning_rate": 2.2478646953575263e-05, "loss": 3.9195, "step": 1680896 }, { "epoch": 1.0, "learning_rate": 2.2470261006064743e-05, "loss": 3.9281, "step": 1681408 }, { "epoch": 1.0, "learning_rate": 2.2461875058554223e-05, "loss": 3.9162, "step": 1681920 }, { "epoch": 1.0, "learning_rate": 2.2453505489847435e-05, "loss": 3.9173, "step": 1682432 }, { "epoch": 1.0, "learning_rate": 2.2445119542336915e-05, "loss": 3.9065, "step": 1682944 }, { "epoch": 1.0, "learning_rate": 2.2436733594826395e-05, "loss": 3.9154, "step": 1683456 }, { "epoch": 1.0, "learning_rate": 2.2428364026119608e-05, "loss": 3.9186, "step": 1683968 }, { "epoch": 1.0, "learning_rate": 2.2419978078609084e-05, "loss": 3.9164, "step": 1684480 }, { "epoch": 1.0, "learning_rate": 2.2411592131098564e-05, "loss": 3.9139, "step": 1684992 }, { "epoch": 1.0, "learning_rate": 2.240322256239178e-05, "loss": 3.9133, "step": 1685504 }, { "epoch": 1.0, "learning_rate": 2.239483661488126e-05, "loss": 3.9142, "step": 1686016 }, { "epoch": 1.0, "learning_rate": 2.2386450667370737e-05, "loss": 3.9124, "step": 1686528 }, { "epoch": 1.0, "learning_rate": 2.2378064719860217e-05, "loss": 3.9034, "step": 1687040 }, { "epoch": 1.0, "learning_rate": 2.2369678772349697e-05, "loss": 3.9096, "step": 1687552 }, { "epoch": 1.0, "learning_rate": 2.2361292824839177e-05, "loss": 3.9135, "step": 1688064 }, { "epoch": 1.0, "learning_rate": 2.2352906877328657e-05, "loss": 3.9163, "step": 1688576 }, { "epoch": 1.0, "learning_rate": 2.234452092981814e-05, "loss": 3.9262, "step": 1689088 }, { "epoch": 1.0, "learning_rate": 2.2336134982307616e-05, "loss": 3.9228, "step": 1689600 }, { "epoch": 1.0, "learning_rate": 2.2327749034797096e-05, "loss": 3.9264, "step": 1690112 }, { "epoch": 1.0, "learning_rate": 2.231937946609031e-05, "loss": 3.9084, "step": 1690624 }, { "epoch": 1.0, "learning_rate": 2.231099351857979e-05, "loss": 3.9179, "step": 1691136 }, { "epoch": 1.0, "learning_rate": 2.230260757106927e-05, "loss": 3.9129, "step": 1691648 }, { "epoch": 1.0, "learning_rate": 2.229422162355875e-05, "loss": 3.9224, "step": 1692160 }, { "epoch": 1.0, "learning_rate": 2.228583567604823e-05, "loss": 3.9108, "step": 1692672 }, { "epoch": 1.0, "learning_rate": 2.227744972853771e-05, "loss": 3.913, "step": 1693184 }, { "epoch": 1.0, "learning_rate": 2.226906378102719e-05, "loss": 3.9101, "step": 1693696 }, { "epoch": 1.0, "learning_rate": 2.226067783351667e-05, "loss": 3.9129, "step": 1694208 }, { "epoch": 1.01, "learning_rate": 2.2252308264809878e-05, "loss": 3.9136, "step": 1694720 }, { "epoch": 1.01, "learning_rate": 2.224392231729936e-05, "loss": 3.9249, "step": 1695232 }, { "epoch": 1.01, "learning_rate": 2.223555274859257e-05, "loss": 3.9211, "step": 1695744 }, { "epoch": 1.01, "learning_rate": 2.2227183179885783e-05, "loss": 3.9204, "step": 1696256 }, { "epoch": 1.01, "learning_rate": 2.2218797232375263e-05, "loss": 3.9139, "step": 1696768 }, { "epoch": 1.01, "learning_rate": 2.221042766366847e-05, "loss": 3.9194, "step": 1697280 }, { "epoch": 1.01, "learning_rate": 2.2202041716157955e-05, "loss": 3.92, "step": 1697792 }, { "epoch": 1.01, "learning_rate": 2.2193655768647435e-05, "loss": 3.9064, "step": 1698304 }, { "epoch": 1.01, "learning_rate": 2.218526982113691e-05, "loss": 3.9015, "step": 1698816 }, { "epoch": 1.01, "learning_rate": 2.217688387362639e-05, "loss": 3.9016, "step": 1699328 }, { "epoch": 1.01, "learning_rate": 2.216849792611587e-05, "loss": 3.9097, "step": 1699840 }, { "epoch": 1.01, "learning_rate": 2.216011197860535e-05, "loss": 3.9158, "step": 1700352 }, { "epoch": 1.01, "learning_rate": 2.215172603109483e-05, "loss": 3.9138, "step": 1700864 }, { "epoch": 1.01, "learning_rate": 2.214334008358431e-05, "loss": 3.908, "step": 1701376 }, { "epoch": 1.01, "learning_rate": 2.2134970514877524e-05, "loss": 3.9156, "step": 1701888 }, { "epoch": 1.01, "learning_rate": 2.2126584567367004e-05, "loss": 3.9135, "step": 1702400 }, { "epoch": 1.01, "learning_rate": 2.2118198619856484e-05, "loss": 3.9149, "step": 1702912 }, { "epoch": 1.01, "learning_rate": 2.2109812672345964e-05, "loss": 3.9072, "step": 1703424 }, { "epoch": 1.01, "learning_rate": 2.2101426724835444e-05, "loss": 3.8901, "step": 1703936 }, { "epoch": 1.01, "learning_rate": 2.2093040777324924e-05, "loss": 3.9328, "step": 1704448 }, { "epoch": 1.01, "learning_rate": 2.2084654829814404e-05, "loss": 3.9158, "step": 1704960 }, { "epoch": 1.01, "learning_rate": 2.2076268882303884e-05, "loss": 3.9223, "step": 1705472 }, { "epoch": 1.01, "learning_rate": 2.2067882934793363e-05, "loss": 3.9105, "step": 1705984 }, { "epoch": 1.01, "learning_rate": 2.2059496987282843e-05, "loss": 3.9134, "step": 1706496 }, { "epoch": 1.01, "learning_rate": 2.2051111039772323e-05, "loss": 3.9065, "step": 1707008 }, { "epoch": 1.01, "learning_rate": 2.2042741471065532e-05, "loss": 3.9107, "step": 1707520 }, { "epoch": 1.01, "learning_rate": 2.2034355523555016e-05, "loss": 3.9125, "step": 1708032 }, { "epoch": 1.01, "learning_rate": 2.2025969576044496e-05, "loss": 3.9094, "step": 1708544 }, { "epoch": 1.01, "learning_rate": 2.2017583628533976e-05, "loss": 3.9295, "step": 1709056 }, { "epoch": 1.01, "learning_rate": 2.2009197681023452e-05, "loss": 3.9084, "step": 1709568 }, { "epoch": 1.01, "learning_rate": 2.2000811733512932e-05, "loss": 3.8986, "step": 1710080 }, { "epoch": 1.01, "learning_rate": 2.1992425786002412e-05, "loss": 3.9221, "step": 1710592 }, { "epoch": 1.01, "learning_rate": 2.1984039838491892e-05, "loss": 3.8944, "step": 1711104 }, { "epoch": 1.01, "learning_rate": 2.1975670269785105e-05, "loss": 3.8963, "step": 1711616 }, { "epoch": 1.01, "learning_rate": 2.1967300701078317e-05, "loss": 3.9222, "step": 1712128 }, { "epoch": 1.01, "learning_rate": 2.1958914753567797e-05, "loss": 3.9169, "step": 1712640 }, { "epoch": 1.01, "learning_rate": 2.1950528806057274e-05, "loss": 3.9044, "step": 1713152 }, { "epoch": 1.01, "learning_rate": 2.1942159237350486e-05, "loss": 3.9131, "step": 1713664 }, { "epoch": 1.01, "learning_rate": 2.193377328983997e-05, "loss": 3.8911, "step": 1714176 }, { "epoch": 1.01, "learning_rate": 2.192538734232945e-05, "loss": 3.9077, "step": 1714688 }, { "epoch": 1.01, "learning_rate": 2.1917001394818926e-05, "loss": 3.9097, "step": 1715200 }, { "epoch": 1.01, "learning_rate": 2.1908615447308406e-05, "loss": 3.9064, "step": 1715712 }, { "epoch": 1.01, "learning_rate": 2.1900229499797886e-05, "loss": 3.9131, "step": 1716224 }, { "epoch": 1.01, "learning_rate": 2.1891843552287366e-05, "loss": 3.9142, "step": 1716736 }, { "epoch": 1.01, "learning_rate": 2.1883457604776846e-05, "loss": 3.9267, "step": 1717248 }, { "epoch": 1.01, "learning_rate": 2.1875071657266326e-05, "loss": 3.9063, "step": 1717760 }, { "epoch": 1.01, "learning_rate": 2.186668570975581e-05, "loss": 3.9088, "step": 1718272 }, { "epoch": 1.01, "learning_rate": 2.1858299762245286e-05, "loss": 3.9161, "step": 1718784 }, { "epoch": 1.01, "learning_rate": 2.1849913814734766e-05, "loss": 3.9039, "step": 1719296 }, { "epoch": 1.01, "learning_rate": 2.1841544246027978e-05, "loss": 3.9147, "step": 1719808 }, { "epoch": 1.01, "learning_rate": 2.1833158298517455e-05, "loss": 3.912, "step": 1720320 }, { "epoch": 1.01, "learning_rate": 2.1824772351006935e-05, "loss": 3.9073, "step": 1720832 }, { "epoch": 1.01, "learning_rate": 2.1816386403496418e-05, "loss": 3.9239, "step": 1721344 }, { "epoch": 1.01, "learning_rate": 2.180801683478963e-05, "loss": 3.8967, "step": 1721856 }, { "epoch": 1.01, "learning_rate": 2.1799630887279107e-05, "loss": 3.9023, "step": 1722368 }, { "epoch": 1.01, "learning_rate": 2.1791244939768587e-05, "loss": 3.913, "step": 1722880 }, { "epoch": 1.01, "learning_rate": 2.1782858992258067e-05, "loss": 3.9146, "step": 1723392 }, { "epoch": 1.01, "learning_rate": 2.177448942355128e-05, "loss": 3.9088, "step": 1723904 }, { "epoch": 1.01, "learning_rate": 2.176610347604076e-05, "loss": 3.9107, "step": 1724416 }, { "epoch": 1.02, "learning_rate": 2.1757733907333972e-05, "loss": 3.897, "step": 1724928 }, { "epoch": 1.02, "learning_rate": 2.1749347959823452e-05, "loss": 3.9074, "step": 1725440 }, { "epoch": 1.02, "learning_rate": 2.174096201231293e-05, "loss": 3.9021, "step": 1725952 }, { "epoch": 1.02, "learning_rate": 2.173257606480241e-05, "loss": 3.9107, "step": 1726464 }, { "epoch": 1.02, "learning_rate": 2.172419011729189e-05, "loss": 3.923, "step": 1726976 }, { "epoch": 1.02, "learning_rate": 2.1715820548585104e-05, "loss": 3.9094, "step": 1727488 }, { "epoch": 1.02, "learning_rate": 2.170743460107458e-05, "loss": 3.9147, "step": 1728000 }, { "epoch": 1.02, "learning_rate": 2.1699065032367793e-05, "loss": 3.903, "step": 1728512 }, { "epoch": 1.02, "learning_rate": 2.1690679084857273e-05, "loss": 3.9061, "step": 1729024 }, { "epoch": 1.02, "learning_rate": 2.168229313734675e-05, "loss": 3.9062, "step": 1729536 }, { "epoch": 1.02, "learning_rate": 2.1673907189836233e-05, "loss": 3.9207, "step": 1730048 }, { "epoch": 1.02, "learning_rate": 2.1665521242325713e-05, "loss": 3.9125, "step": 1730560 }, { "epoch": 1.02, "learning_rate": 2.1657135294815193e-05, "loss": 3.9148, "step": 1731072 }, { "epoch": 1.02, "learning_rate": 2.1648749347304673e-05, "loss": 3.9022, "step": 1731584 }, { "epoch": 1.02, "learning_rate": 2.1640363399794153e-05, "loss": 3.9179, "step": 1732096 }, { "epoch": 1.02, "learning_rate": 2.1631993831087362e-05, "loss": 3.9016, "step": 1732608 }, { "epoch": 1.02, "learning_rate": 2.1623607883576842e-05, "loss": 3.9115, "step": 1733120 }, { "epoch": 1.02, "learning_rate": 2.1615221936066325e-05, "loss": 3.8972, "step": 1733632 }, { "epoch": 1.02, "learning_rate": 2.1606835988555805e-05, "loss": 3.913, "step": 1734144 }, { "epoch": 1.02, "learning_rate": 2.1598450041045285e-05, "loss": 3.9041, "step": 1734656 }, { "epoch": 1.02, "learning_rate": 2.1590064093534762e-05, "loss": 3.9095, "step": 1735168 }, { "epoch": 1.02, "learning_rate": 2.1581678146024242e-05, "loss": 3.8997, "step": 1735680 }, { "epoch": 1.02, "learning_rate": 2.1573292198513722e-05, "loss": 3.9099, "step": 1736192 }, { "epoch": 1.02, "learning_rate": 2.1564922629806934e-05, "loss": 3.9038, "step": 1736704 }, { "epoch": 1.02, "learning_rate": 2.1556536682296414e-05, "loss": 3.9058, "step": 1737216 }, { "epoch": 1.02, "learning_rate": 2.1548150734785894e-05, "loss": 3.9206, "step": 1737728 }, { "epoch": 1.02, "learning_rate": 2.1539764787275374e-05, "loss": 3.9209, "step": 1738240 }, { "epoch": 1.02, "learning_rate": 2.1531395218568583e-05, "loss": 3.9147, "step": 1738752 }, { "epoch": 1.02, "learning_rate": 2.1523009271058063e-05, "loss": 3.9126, "step": 1739264 }, { "epoch": 1.02, "learning_rate": 2.1514623323547543e-05, "loss": 3.9019, "step": 1739776 }, { "epoch": 1.02, "learning_rate": 2.1506237376037026e-05, "loss": 3.9035, "step": 1740288 }, { "epoch": 1.02, "learning_rate": 2.1497851428526506e-05, "loss": 3.9103, "step": 1740800 }, { "epoch": 1.02, "learning_rate": 2.1489481859819715e-05, "loss": 3.9135, "step": 1741312 }, { "epoch": 1.02, "learning_rate": 2.1481095912309195e-05, "loss": 3.8946, "step": 1741824 }, { "epoch": 1.02, "learning_rate": 2.1472709964798675e-05, "loss": 3.9132, "step": 1742336 }, { "epoch": 1.02, "learning_rate": 2.1464324017288155e-05, "loss": 3.9136, "step": 1742848 }, { "epoch": 1.02, "learning_rate": 2.1455938069777635e-05, "loss": 3.9093, "step": 1743360 }, { "epoch": 1.02, "learning_rate": 2.1447552122267115e-05, "loss": 3.9063, "step": 1743872 }, { "epoch": 1.02, "learning_rate": 2.1439166174756595e-05, "loss": 3.9078, "step": 1744384 }, { "epoch": 1.02, "learning_rate": 2.1430780227246075e-05, "loss": 3.9009, "step": 1744896 }, { "epoch": 1.02, "learning_rate": 2.1422394279735555e-05, "loss": 3.9207, "step": 1745408 }, { "epoch": 1.02, "learning_rate": 2.1414024711028764e-05, "loss": 3.9154, "step": 1745920 }, { "epoch": 1.02, "learning_rate": 2.140565514232198e-05, "loss": 3.915, "step": 1746432 }, { "epoch": 1.02, "learning_rate": 2.139726919481146e-05, "loss": 3.9001, "step": 1746944 }, { "epoch": 1.02, "learning_rate": 2.138888324730094e-05, "loss": 3.9182, "step": 1747456 }, { "epoch": 1.02, "learning_rate": 2.1380497299790417e-05, "loss": 3.9161, "step": 1747968 }, { "epoch": 1.02, "learning_rate": 2.1372111352279897e-05, "loss": 3.9061, "step": 1748480 }, { "epoch": 1.02, "learning_rate": 2.1363725404769376e-05, "loss": 3.9152, "step": 1748992 }, { "epoch": 1.02, "learning_rate": 2.1355339457258856e-05, "loss": 3.9136, "step": 1749504 }, { "epoch": 1.02, "learning_rate": 2.1346953509748336e-05, "loss": 3.9133, "step": 1750016 }, { "epoch": 1.02, "learning_rate": 2.133858394104155e-05, "loss": 3.9277, "step": 1750528 }, { "epoch": 1.02, "learning_rate": 2.133019799353103e-05, "loss": 3.9055, "step": 1751040 }, { "epoch": 1.02, "learning_rate": 2.132181204602051e-05, "loss": 3.9136, "step": 1751552 }, { "epoch": 1.02, "learning_rate": 2.131342609850999e-05, "loss": 3.9115, "step": 1752064 }, { "epoch": 1.02, "learning_rate": 2.130504015099947e-05, "loss": 3.9119, "step": 1752576 }, { "epoch": 1.02, "learning_rate": 2.129665420348895e-05, "loss": 3.9033, "step": 1753088 }, { "epoch": 1.02, "learning_rate": 2.128828463478216e-05, "loss": 3.9034, "step": 1753600 }, { "epoch": 1.02, "learning_rate": 2.127991506607537e-05, "loss": 3.9081, "step": 1754112 }, { "epoch": 1.02, "learning_rate": 2.127152911856485e-05, "loss": 3.9008, "step": 1754624 }, { "epoch": 1.02, "learning_rate": 2.126314317105433e-05, "loss": 3.9119, "step": 1755136 }, { "epoch": 1.03, "eval_loss": 4.001281261444092, "eval_runtime": 291.7896, "eval_samples_per_second": 1307.761, "eval_steps_per_second": 40.868, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.125475722354381e-05, "loss": 3.9151, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.124637127603329e-05, "loss": 3.9042, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.123798532852277e-05, "loss": 3.9137, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.122959938101225e-05, "loss": 3.9142, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.122121343350173e-05, "loss": 3.9213, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.121282748599121e-05, "loss": 3.9077, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.120444153848069e-05, "loss": 3.9144, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.119605559097017e-05, "loss": 3.9037, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.118766964345965e-05, "loss": 3.9011, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.117928369594913e-05, "loss": 3.917, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.117089774843861e-05, "loss": 3.9093, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.116251180092809e-05, "loss": 3.9052, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.1154142232221302e-05, "loss": 3.9156, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.114575628471078e-05, "loss": 3.9024, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.113737033720026e-05, "loss": 3.9025, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1128984389689742e-05, "loss": 3.8963, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1120598442179222e-05, "loss": 3.9028, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1112212494668702e-05, "loss": 3.9107, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1103826547158182e-05, "loss": 3.9033, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.109544059964766e-05, "loss": 3.923, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.108705465213714e-05, "loss": 3.9163, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.107868508343035e-05, "loss": 3.9174, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1070299135919834e-05, "loss": 3.905, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.106191318840931e-05, "loss": 3.9057, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.105352724089879e-05, "loss": 3.9156, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.104514129338827e-05, "loss": 3.9143, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.103677172468148e-05, "loss": 3.9044, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1028402155974696e-05, "loss": 3.9075, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.1020016208464176e-05, "loss": 3.899, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.1011630260953656e-05, "loss": 3.9077, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.1003244313443132e-05, "loss": 3.9084, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.0994858365932612e-05, "loss": 3.9172, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.0986472418422092e-05, "loss": 3.9134, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.0978086470911572e-05, "loss": 3.9135, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.0969700523401052e-05, "loss": 3.9084, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.0961330954694264e-05, "loss": 3.91, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.0952961385987477e-05, "loss": 3.9131, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.0944575438476953e-05, "loss": 3.9001, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0936189490966433e-05, "loss": 3.898, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0927803543455913e-05, "loss": 3.8942, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.0919417595945397e-05, "loss": 3.9025, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.0911031648434877e-05, "loss": 3.9048, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.0902645700924357e-05, "loss": 3.911, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.0894259753413837e-05, "loss": 3.9053, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.0885873805903313e-05, "loss": 3.9051, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.0877487858392793e-05, "loss": 3.9063, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.0869101910882273e-05, "loss": 3.9115, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.0860715963371753e-05, "loss": 3.8994, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.0852346394664966e-05, "loss": 3.8844, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.0843960447154445e-05, "loss": 3.9208, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.0835590878447658e-05, "loss": 3.912, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.0827204930937135e-05, "loss": 3.917, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0818818983426618e-05, "loss": 3.9044, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0810433035916098e-05, "loss": 3.9071, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0802047088405578e-05, "loss": 3.9016, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.0793661140895058e-05, "loss": 3.9022, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.0785275193384538e-05, "loss": 3.9099, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0776889245874018e-05, "loss": 3.8981, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0768519677167227e-05, "loss": 3.9256, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0760133729656707e-05, "loss": 3.9064, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.075174778214619e-05, "loss": 3.887, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.074336183463567e-05, "loss": 3.9163, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.0734975887125147e-05, "loss": 3.8893, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.072660631841836e-05, "loss": 3.8891, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0718236749711568e-05, "loss": 3.916, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.070985080220105e-05, "loss": 3.9071, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.070146485469053e-05, "loss": 3.8965, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.069307890718001e-05, "loss": 3.9047, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.068469295966949e-05, "loss": 3.8875, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.06763233909627e-05, "loss": 3.8995, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.066793744345218e-05, "loss": 3.9057, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.065955149594166e-05, "loss": 3.8971, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.0651165548431144e-05, "loss": 3.9068, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.064277960092062e-05, "loss": 3.9049, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.06343936534101e-05, "loss": 3.9187, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.062600770589958e-05, "loss": 3.8996, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.061762175838906e-05, "loss": 3.9054, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.060923581087854e-05, "loss": 3.907, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0600882620975485e-05, "loss": 3.8977, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.0592496673464965e-05, "loss": 3.9102, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.058411072595444e-05, "loss": 3.9064, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.057572477844392e-05, "loss": 3.8967, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.05673388309334e-05, "loss": 3.9182, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.0558969262226614e-05, "loss": 3.8909, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.0550583314716094e-05, "loss": 3.8952, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.0542197367205574e-05, "loss": 3.9081, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.0533811419695054e-05, "loss": 3.9057, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0525425472184534e-05, "loss": 3.9004, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0517055903477743e-05, "loss": 3.909, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.0508669955967226e-05, "loss": 3.8908, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0500284008456706e-05, "loss": 3.8983, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0491898060946186e-05, "loss": 3.8991, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0483512113435666e-05, "loss": 3.8995, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0475126165925146e-05, "loss": 3.9165, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.0466756597218355e-05, "loss": 3.9025, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.0458370649707835e-05, "loss": 3.9105, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.0449984702197315e-05, "loss": 3.8965, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.0441598754686795e-05, "loss": 3.9018, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.0433212807176275e-05, "loss": 3.9015, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.0424826859665755e-05, "loss": 3.9106, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0416457290958967e-05, "loss": 3.906, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0408071343448444e-05, "loss": 3.9098, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0399685395937927e-05, "loss": 3.899, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0391299448427407e-05, "loss": 3.9054, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.0382913500916887e-05, "loss": 3.9016, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.0374527553406367e-05, "loss": 3.9017, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.0366157984699576e-05, "loss": 3.8924, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.0357772037189056e-05, "loss": 3.9094, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.0349386089678536e-05, "loss": 3.8953, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.034100014216802e-05, "loss": 3.901, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.03326141946575e-05, "loss": 3.8926, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.0324228247146976e-05, "loss": 3.9019, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0315842299636456e-05, "loss": 3.8981, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.0307456352125936e-05, "loss": 3.8989, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.029910316222288e-05, "loss": 3.9086, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.029071721471236e-05, "loss": 3.9163, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.028233126720184e-05, "loss": 3.9142, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.027394531969132e-05, "loss": 3.902, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.02655593721808e-05, "loss": 3.8944, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.025718980347401e-05, "loss": 3.897, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.024880385596349e-05, "loss": 3.9031, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.0240417908452973e-05, "loss": 3.9061, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.023203196094245e-05, "loss": 3.8896, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0223662392235662e-05, "loss": 3.9061, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0215276444725142e-05, "loss": 3.909, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0206890497214622e-05, "loss": 3.8997, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.01985045497041e-05, "loss": 3.899, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0190118602193582e-05, "loss": 3.904, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0181732654683062e-05, "loss": 3.8969, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0173346707172542e-05, "loss": 3.9103, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.016497713846575e-05, "loss": 3.906, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.015659119095523e-05, "loss": 3.9122, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.014820524344471e-05, "loss": 3.8939, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.013981929593419e-05, "loss": 3.911, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.0131433348423674e-05, "loss": 3.9098, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0123047400913154e-05, "loss": 3.9008, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.011466145340263e-05, "loss": 3.9052, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.010627550589211e-05, "loss": 3.9045, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0097905937185323e-05, "loss": 3.9078, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.0089519989674803e-05, "loss": 3.9225, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.0081150420968016e-05, "loss": 3.8963, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.0072764473457496e-05, "loss": 3.9103, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.0064378525946976e-05, "loss": 3.9058, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0055992578436456e-05, "loss": 3.9044, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.0047606630925932e-05, "loss": 3.8987, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.0039220683415412e-05, "loss": 3.8944, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.0030851114708628e-05, "loss": 3.9036, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.0022465167198105e-05, "loss": 3.894, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.0014079219687585e-05, "loss": 3.9052, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.998615026473999, "eval_runtime": 293.0898, "eval_samples_per_second": 1301.959, "eval_steps_per_second": 40.687, "step": 1831680 }, { "epoch": 0.0, "learning_rate": 2.0005693272177065e-05, "loss": 3.9013, "step": 1831936 }, { "epoch": 0.0, "learning_rate": 1.9997307324666544e-05, "loss": 3.8998, "step": 1832448 }, { "epoch": 0.0, "learning_rate": 1.9988921377156024e-05, "loss": 3.9066, "step": 1832960 }, { "epoch": 0.0, "learning_rate": 1.9980535429645504e-05, "loss": 3.9071, "step": 1833472 }, { "epoch": 0.0, "learning_rate": 1.9972149482134984e-05, "loss": 3.9131, "step": 1833984 }, { "epoch": 0.0, "learning_rate": 1.9963763534624464e-05, "loss": 3.9026, "step": 1834496 }, { "epoch": 0.0, "learning_rate": 1.9955377587113944e-05, "loss": 3.9105, "step": 1835008 }, { "epoch": 0.0, "learning_rate": 1.9946991639603424e-05, "loss": 3.8957, "step": 1835520 }, { "epoch": 0.0, "learning_rate": 1.9938605692092904e-05, "loss": 3.8973, "step": 1836032 }, { "epoch": 0.0, "learning_rate": 1.9930219744582384e-05, "loss": 3.9112, "step": 1836544 }, { "epoch": 0.0, "learning_rate": 1.9921833797071864e-05, "loss": 3.9037, "step": 1837056 }, { "epoch": 0.0, "learning_rate": 1.9913447849561344e-05, "loss": 3.8976, "step": 1837568 }, { "epoch": 0.0, "learning_rate": 1.9905078280854557e-05, "loss": 3.911, "step": 1838080 }, { "epoch": 0.0, "learning_rate": 1.9896692333344036e-05, "loss": 3.8946, "step": 1838592 }, { "epoch": 0.0, "learning_rate": 1.9888322764637246e-05, "loss": 3.8981, "step": 1839104 }, { "epoch": 0.0, "learning_rate": 1.9879936817126726e-05, "loss": 3.8854, "step": 1839616 }, { "epoch": 0.0, "learning_rate": 1.9871550869616205e-05, "loss": 3.9008, "step": 1840128 }, { "epoch": 0.0, "learning_rate": 1.9863164922105685e-05, "loss": 3.9068, "step": 1840640 }, { "epoch": 0.0, "learning_rate": 1.985477897459517e-05, "loss": 3.895, "step": 1841152 }, { "epoch": 0.0, "learning_rate": 1.9846393027084645e-05, "loss": 3.915, "step": 1841664 }, { "epoch": 0.0, "learning_rate": 1.9838007079574125e-05, "loss": 3.91, "step": 1842176 }, { "epoch": 0.0, "learning_rate": 1.9829621132063605e-05, "loss": 3.9107, "step": 1842688 }, { "epoch": 0.0, "learning_rate": 1.9821235184553085e-05, "loss": 3.9029, "step": 1843200 }, { "epoch": 0.0, "learning_rate": 1.9812849237042565e-05, "loss": 3.904, "step": 1843712 }, { "epoch": 0.0, "learning_rate": 1.9804463289532045e-05, "loss": 3.9061, "step": 1844224 }, { "epoch": 0.0, "learning_rate": 1.9796077342021525e-05, "loss": 3.9048, "step": 1844736 }, { "epoch": 0.0, "learning_rate": 1.9787691394511005e-05, "loss": 3.8959, "step": 1845248 }, { "epoch": 0.0, "learning_rate": 1.9779305447000485e-05, "loss": 3.9029, "step": 1845760 }, { "epoch": 0.0, "learning_rate": 1.9770919499489965e-05, "loss": 3.8943, "step": 1846272 }, { "epoch": 0.0, "learning_rate": 1.9762549930783174e-05, "loss": 3.9011, "step": 1846784 }, { "epoch": 0.01, "learning_rate": 1.9754163983272654e-05, "loss": 3.9013, "step": 1847296 }, { "epoch": 0.01, "learning_rate": 1.9745778035762137e-05, "loss": 3.9071, "step": 1847808 }, { "epoch": 0.01, "learning_rate": 1.9737392088251617e-05, "loss": 3.9107, "step": 1848320 }, { "epoch": 0.01, "learning_rate": 1.9729022519544826e-05, "loss": 3.9116, "step": 1848832 }, { "epoch": 0.01, "learning_rate": 1.9720636572034306e-05, "loss": 3.8971, "step": 1849344 }, { "epoch": 0.01, "learning_rate": 1.971226700332752e-05, "loss": 3.9067, "step": 1849856 }, { "epoch": 0.01, "learning_rate": 1.9703881055817e-05, "loss": 3.9079, "step": 1850368 }, { "epoch": 0.01, "learning_rate": 1.969549510830648e-05, "loss": 3.891, "step": 1850880 }, { "epoch": 0.01, "learning_rate": 1.968710916079596e-05, "loss": 3.8956, "step": 1851392 }, { "epoch": 0.01, "learning_rate": 1.967872321328544e-05, "loss": 3.8905, "step": 1851904 }, { "epoch": 0.01, "learning_rate": 1.967033726577492e-05, "loss": 3.8925, "step": 1852416 }, { "epoch": 0.01, "learning_rate": 1.96619513182644e-05, "loss": 3.9005, "step": 1852928 }, { "epoch": 0.01, "learning_rate": 1.965356537075388e-05, "loss": 3.9047, "step": 1853440 }, { "epoch": 0.01, "learning_rate": 1.9645179423243355e-05, "loss": 3.8972, "step": 1853952 }, { "epoch": 0.01, "learning_rate": 1.963679347573284e-05, "loss": 3.896, "step": 1854464 }, { "epoch": 0.01, "learning_rate": 1.962840752822232e-05, "loss": 3.8993, "step": 1854976 }, { "epoch": 0.01, "learning_rate": 1.96200215807118e-05, "loss": 3.9097, "step": 1855488 }, { "epoch": 0.01, "learning_rate": 1.9611635633201278e-05, "loss": 3.8916, "step": 1856000 }, { "epoch": 0.01, "learning_rate": 1.9603249685690758e-05, "loss": 3.8808, "step": 1856512 }, { "epoch": 0.01, "learning_rate": 1.9594880116983967e-05, "loss": 3.9123, "step": 1857024 }, { "epoch": 0.01, "learning_rate": 1.9586494169473447e-05, "loss": 3.9045, "step": 1857536 }, { "epoch": 0.01, "learning_rate": 1.957810822196293e-05, "loss": 3.9102, "step": 1858048 }, { "epoch": 0.01, "learning_rate": 1.956972227445241e-05, "loss": 3.8981, "step": 1858560 }, { "epoch": 0.01, "learning_rate": 1.9561336326941887e-05, "loss": 3.8969, "step": 1859072 }, { "epoch": 0.01, "learning_rate": 1.9552950379431367e-05, "loss": 3.8978, "step": 1859584 }, { "epoch": 0.01, "learning_rate": 1.954458081072458e-05, "loss": 3.8977, "step": 1860096 }, { "epoch": 0.01, "learning_rate": 1.953619486321406e-05, "loss": 3.9063, "step": 1860608 }, { "epoch": 0.01, "learning_rate": 1.9527825294507272e-05, "loss": 3.8894, "step": 1861120 }, { "epoch": 0.01, "learning_rate": 1.9519439346996752e-05, "loss": 3.9221, "step": 1861632 }, { "epoch": 0.01, "learning_rate": 1.9511053399486232e-05, "loss": 3.8955, "step": 1862144 }, { "epoch": 0.01, "learning_rate": 1.9502667451975712e-05, "loss": 3.8804, "step": 1862656 }, { "epoch": 0.01, "learning_rate": 1.949428150446519e-05, "loss": 3.9116, "step": 1863168 }, { "epoch": 0.01, "learning_rate": 1.948589555695467e-05, "loss": 3.8913, "step": 1863680 }, { "epoch": 0.01, "learning_rate": 1.947750960944415e-05, "loss": 3.8804, "step": 1864192 }, { "epoch": 0.01, "learning_rate": 1.9469123661933632e-05, "loss": 3.9063, "step": 1864704 }, { "epoch": 0.01, "learning_rate": 1.946073771442311e-05, "loss": 3.9041, "step": 1865216 }, { "epoch": 0.01, "learning_rate": 1.945235176691259e-05, "loss": 3.8959, "step": 1865728 }, { "epoch": 0.01, "learning_rate": 1.9443965819402068e-05, "loss": 3.8957, "step": 1866240 }, { "epoch": 0.01, "learning_rate": 1.9435579871891548e-05, "loss": 3.8799, "step": 1866752 }, { "epoch": 0.01, "learning_rate": 1.942721030318476e-05, "loss": 3.8925, "step": 1867264 }, { "epoch": 0.01, "learning_rate": 1.941882435567424e-05, "loss": 3.9024, "step": 1867776 }, { "epoch": 0.01, "learning_rate": 1.9410454786967453e-05, "loss": 3.8943, "step": 1868288 }, { "epoch": 0.01, "learning_rate": 1.9402068839456933e-05, "loss": 3.899, "step": 1868800 }, { "epoch": 0.01, "learning_rate": 1.9393682891946413e-05, "loss": 3.8973, "step": 1869312 }, { "epoch": 0.01, "learning_rate": 1.938529694443589e-05, "loss": 3.9134, "step": 1869824 }, { "epoch": 0.01, "learning_rate": 1.937691099692537e-05, "loss": 3.8972, "step": 1870336 }, { "epoch": 0.01, "learning_rate": 1.9368525049414853e-05, "loss": 3.8992, "step": 1870848 }, { "epoch": 0.01, "learning_rate": 1.9360139101904333e-05, "loss": 3.9009, "step": 1871360 }, { "epoch": 0.01, "learning_rate": 1.9351753154393813e-05, "loss": 3.8943, "step": 1871872 }, { "epoch": 0.01, "learning_rate": 1.9343383585687022e-05, "loss": 3.9045, "step": 1872384 }, { "epoch": 0.01, "learning_rate": 1.9334997638176502e-05, "loss": 3.8984, "step": 1872896 }, { "epoch": 0.01, "learning_rate": 1.9326611690665982e-05, "loss": 3.8967, "step": 1873408 }, { "epoch": 0.01, "learning_rate": 1.9318225743155462e-05, "loss": 3.9083, "step": 1873920 }, { "epoch": 0.01, "learning_rate": 1.9309856174448674e-05, "loss": 3.8862, "step": 1874432 }, { "epoch": 0.01, "learning_rate": 1.9301486605741887e-05, "loss": 3.8922, "step": 1874944 }, { "epoch": 0.01, "learning_rate": 1.9293100658231363e-05, "loss": 3.8997, "step": 1875456 }, { "epoch": 0.01, "learning_rate": 1.9284714710720843e-05, "loss": 3.9006, "step": 1875968 }, { "epoch": 0.01, "learning_rate": 1.9276328763210323e-05, "loss": 3.8914, "step": 1876480 }, { "epoch": 0.01, "learning_rate": 1.9267942815699807e-05, "loss": 3.9034, "step": 1876992 }, { "epoch": 0.02, "learning_rate": 1.9259556868189286e-05, "loss": 3.8893, "step": 1877504 }, { "epoch": 0.02, "learning_rate": 1.9251187299482496e-05, "loss": 3.8915, "step": 1878016 }, { "epoch": 0.02, "learning_rate": 1.9242801351971976e-05, "loss": 3.8891, "step": 1878528 }, { "epoch": 0.02, "learning_rate": 1.9234415404461455e-05, "loss": 3.8941, "step": 1879040 }, { "epoch": 0.02, "learning_rate": 1.9226029456950935e-05, "loss": 3.9128, "step": 1879552 }, { "epoch": 0.02, "learning_rate": 1.9217643509440415e-05, "loss": 3.898, "step": 1880064 }, { "epoch": 0.02, "learning_rate": 1.9209257561929895e-05, "loss": 3.902, "step": 1880576 }, { "epoch": 0.02, "learning_rate": 1.9200887993223108e-05, "loss": 3.8937, "step": 1881088 }, { "epoch": 0.02, "learning_rate": 1.9192502045712588e-05, "loss": 3.8928, "step": 1881600 }, { "epoch": 0.02, "learning_rate": 1.9184116098202068e-05, "loss": 3.8956, "step": 1882112 }, { "epoch": 0.02, "learning_rate": 1.9175730150691544e-05, "loss": 3.9057, "step": 1882624 }, { "epoch": 0.02, "learning_rate": 1.9167344203181024e-05, "loss": 3.9006, "step": 1883136 }, { "epoch": 0.02, "learning_rate": 1.9158958255670508e-05, "loss": 3.8983, "step": 1883648 }, { "epoch": 0.02, "learning_rate": 1.9150572308159988e-05, "loss": 3.9004, "step": 1884160 }, { "epoch": 0.02, "learning_rate": 1.9142202739453197e-05, "loss": 3.8984, "step": 1884672 }, { "epoch": 0.02, "learning_rate": 1.9133816791942677e-05, "loss": 3.8956, "step": 1885184 }, { "epoch": 0.02, "learning_rate": 1.9125430844432157e-05, "loss": 3.8951, "step": 1885696 }, { "epoch": 0.02, "learning_rate": 1.9117044896921637e-05, "loss": 3.8875, "step": 1886208 }, { "epoch": 0.02, "learning_rate": 1.910867532821485e-05, "loss": 3.9012, "step": 1886720 }, { "epoch": 0.02, "learning_rate": 1.910028938070433e-05, "loss": 3.8915, "step": 1887232 }, { "epoch": 0.02, "learning_rate": 1.909190343319381e-05, "loss": 3.8925, "step": 1887744 }, { "epoch": 0.02, "learning_rate": 1.908351748568329e-05, "loss": 3.8914, "step": 1888256 }, { "epoch": 0.02, "learning_rate": 1.907513153817277e-05, "loss": 3.8914, "step": 1888768 }, { "epoch": 0.02, "learning_rate": 1.9066761969465978e-05, "loss": 3.8951, "step": 1889280 }, { "epoch": 0.02, "learning_rate": 1.905837602195546e-05, "loss": 3.8923, "step": 1889792 }, { "epoch": 0.02, "learning_rate": 1.905000645324867e-05, "loss": 3.907, "step": 1890304 }, { "epoch": 0.02, "learning_rate": 1.904162050573815e-05, "loss": 3.9077, "step": 1890816 }, { "epoch": 0.02, "learning_rate": 1.903323455822763e-05, "loss": 3.9066, "step": 1891328 }, { "epoch": 0.02, "learning_rate": 1.902484861071711e-05, "loss": 3.897, "step": 1891840 }, { "epoch": 0.02, "learning_rate": 1.901646266320659e-05, "loss": 3.8934, "step": 1892352 }, { "epoch": 0.02, "learning_rate": 1.900807671569607e-05, "loss": 3.8914, "step": 1892864 }, { "epoch": 0.02, "learning_rate": 1.8999690768185554e-05, "loss": 3.8994, "step": 1893376 }, { "epoch": 0.02, "learning_rate": 1.899130482067503e-05, "loss": 3.9032, "step": 1893888 }, { "epoch": 0.02, "learning_rate": 1.8982935251968243e-05, "loss": 3.8864, "step": 1894400 }, { "epoch": 0.02, "learning_rate": 1.8974549304457723e-05, "loss": 3.8967, "step": 1894912 }, { "epoch": 0.02, "learning_rate": 1.89661633569472e-05, "loss": 3.9022, "step": 1895424 }, { "epoch": 0.02, "learning_rate": 1.895777740943668e-05, "loss": 3.8966, "step": 1895936 }, { "epoch": 0.02, "learning_rate": 1.8949391461926162e-05, "loss": 3.8936, "step": 1896448 }, { "epoch": 0.02, "learning_rate": 1.8941005514415642e-05, "loss": 3.8986, "step": 1896960 }, { "epoch": 0.02, "learning_rate": 1.8932619566905122e-05, "loss": 3.8895, "step": 1897472 }, { "epoch": 0.02, "learning_rate": 1.892424999819833e-05, "loss": 3.9077, "step": 1897984 }, { "epoch": 0.02, "learning_rate": 1.891586405068781e-05, "loss": 3.898, "step": 1898496 }, { "epoch": 0.02, "learning_rate": 1.890747810317729e-05, "loss": 3.9103, "step": 1899008 }, { "epoch": 0.02, "learning_rate": 1.889909215566677e-05, "loss": 3.8887, "step": 1899520 }, { "epoch": 0.02, "learning_rate": 1.8890706208156255e-05, "loss": 3.9007, "step": 1900032 }, { "epoch": 0.02, "learning_rate": 1.8882320260645735e-05, "loss": 3.9075, "step": 1900544 }, { "epoch": 0.02, "learning_rate": 1.887393431313521e-05, "loss": 3.8949, "step": 1901056 }, { "epoch": 0.02, "learning_rate": 1.886554836562469e-05, "loss": 3.8973, "step": 1901568 }, { "epoch": 0.02, "learning_rate": 1.8857178796917904e-05, "loss": 3.8991, "step": 1902080 }, { "epoch": 0.02, "learning_rate": 1.884879284940738e-05, "loss": 3.8994, "step": 1902592 }, { "epoch": 0.02, "learning_rate": 1.8840406901896863e-05, "loss": 3.9153, "step": 1903104 }, { "epoch": 0.02, "learning_rate": 1.8832020954386343e-05, "loss": 3.8947, "step": 1903616 }, { "epoch": 0.02, "learning_rate": 1.8823651385679556e-05, "loss": 3.9031, "step": 1904128 }, { "epoch": 0.02, "learning_rate": 1.8815265438169032e-05, "loss": 3.9014, "step": 1904640 }, { "epoch": 0.02, "learning_rate": 1.8806895869462245e-05, "loss": 3.8968, "step": 1905152 }, { "epoch": 0.02, "learning_rate": 1.8798509921951725e-05, "loss": 3.8911, "step": 1905664 }, { "epoch": 0.02, "learning_rate": 1.8790123974441205e-05, "loss": 3.8912, "step": 1906176 }, { "epoch": 0.02, "learning_rate": 1.8781738026930685e-05, "loss": 3.8959, "step": 1906688 }, { "epoch": 0.02, "learning_rate": 1.8773368458223897e-05, "loss": 3.8926, "step": 1907200 }, { "epoch": 0.02, "learning_rate": 1.8764982510713377e-05, "loss": 3.898, "step": 1907712 }, { "epoch": 0.03, "eval_loss": 3.9966838359832764, "eval_runtime": 293.1458, "eval_samples_per_second": 1301.711, "eval_steps_per_second": 40.679, "step": 1908000 }, { "epoch": 1.0, "learning_rate": 1.8756596563202854e-05, "loss": 3.8957, "step": 1908224 }, { "epoch": 1.0, "learning_rate": 1.8748210615692334e-05, "loss": 3.8943, "step": 1908736 }, { "epoch": 1.0, "learning_rate": 1.8739824668181817e-05, "loss": 3.8988, "step": 1909248 }, { "epoch": 1.0, "learning_rate": 1.8731438720671297e-05, "loss": 3.9061, "step": 1909760 }, { "epoch": 1.0, "learning_rate": 1.8723052773160777e-05, "loss": 3.9108, "step": 1910272 }, { "epoch": 1.0, "learning_rate": 1.8714666825650257e-05, "loss": 3.8977, "step": 1910784 }, { "epoch": 1.0, "learning_rate": 1.8706297256943466e-05, "loss": 3.9003, "step": 1911296 }, { "epoch": 1.0, "learning_rate": 1.8697911309432946e-05, "loss": 3.8917, "step": 1911808 }, { "epoch": 1.0, "learning_rate": 1.8689525361922426e-05, "loss": 3.8914, "step": 1912320 }, { "epoch": 1.0, "learning_rate": 1.868113941441191e-05, "loss": 3.9027, "step": 1912832 }, { "epoch": 1.0, "learning_rate": 1.867276984570512e-05, "loss": 3.9002, "step": 1913344 }, { "epoch": 1.0, "learning_rate": 1.86643838981946e-05, "loss": 3.894, "step": 1913856 }, { "epoch": 1.0, "learning_rate": 1.8656014329487808e-05, "loss": 3.9032, "step": 1914368 }, { "epoch": 1.0, "learning_rate": 1.8647628381977287e-05, "loss": 3.8884, "step": 1914880 }, { "epoch": 1.0, "learning_rate": 1.863924243446677e-05, "loss": 3.8915, "step": 1915392 }, { "epoch": 1.0, "learning_rate": 1.863085648695625e-05, "loss": 3.8791, "step": 1915904 }, { "epoch": 1.0, "learning_rate": 1.862248691824946e-05, "loss": 3.9002, "step": 1916416 }, { "epoch": 1.0, "learning_rate": 1.861410097073894e-05, "loss": 3.9012, "step": 1916928 }, { "epoch": 1.0, "learning_rate": 1.860571502322842e-05, "loss": 3.8892, "step": 1917440 }, { "epoch": 1.0, "learning_rate": 1.85973290757179e-05, "loss": 3.9051, "step": 1917952 }, { "epoch": 1.0, "learning_rate": 1.858894312820738e-05, "loss": 3.9042, "step": 1918464 }, { "epoch": 1.0, "learning_rate": 1.858055718069686e-05, "loss": 3.9053, "step": 1918976 }, { "epoch": 1.0, "learning_rate": 1.857217123318634e-05, "loss": 3.8986, "step": 1919488 }, { "epoch": 1.0, "learning_rate": 1.856378528567582e-05, "loss": 3.8978, "step": 1920000 }, { "epoch": 1.0, "learning_rate": 1.85553993381653e-05, "loss": 3.8982, "step": 1920512 }, { "epoch": 1.0, "learning_rate": 1.854702976945851e-05, "loss": 3.9047, "step": 1921024 }, { "epoch": 1.0, "learning_rate": 1.853864382194799e-05, "loss": 3.8861, "step": 1921536 }, { "epoch": 1.0, "learning_rate": 1.8530257874437472e-05, "loss": 3.899, "step": 1922048 }, { "epoch": 1.0, "learning_rate": 1.8521888305730684e-05, "loss": 3.8894, "step": 1922560 }, { "epoch": 1.0, "learning_rate": 1.851350235822016e-05, "loss": 3.896, "step": 1923072 }, { "epoch": 1.01, "learning_rate": 1.850511641070964e-05, "loss": 3.8982, "step": 1923584 }, { "epoch": 1.01, "learning_rate": 1.849673046319912e-05, "loss": 3.9058, "step": 1924096 }, { "epoch": 1.01, "learning_rate": 1.84883445156886e-05, "loss": 3.8962, "step": 1924608 }, { "epoch": 1.01, "learning_rate": 1.847995856817808e-05, "loss": 3.9116, "step": 1925120 }, { "epoch": 1.01, "learning_rate": 1.8471572620667564e-05, "loss": 3.8942, "step": 1925632 }, { "epoch": 1.01, "learning_rate": 1.8463203051960773e-05, "loss": 3.9007, "step": 1926144 }, { "epoch": 1.01, "learning_rate": 1.8454833483253982e-05, "loss": 3.9036, "step": 1926656 }, { "epoch": 1.01, "learning_rate": 1.8446447535743462e-05, "loss": 3.8833, "step": 1927168 }, { "epoch": 1.01, "learning_rate": 1.8438061588232942e-05, "loss": 3.8897, "step": 1927680 }, { "epoch": 1.01, "learning_rate": 1.8429675640722426e-05, "loss": 3.8891, "step": 1928192 }, { "epoch": 1.01, "learning_rate": 1.8421289693211906e-05, "loss": 3.8867, "step": 1928704 }, { "epoch": 1.01, "learning_rate": 1.8412903745701385e-05, "loss": 3.8955, "step": 1929216 }, { "epoch": 1.01, "learning_rate": 1.8404517798190865e-05, "loss": 3.9025, "step": 1929728 }, { "epoch": 1.01, "learning_rate": 1.8396131850680342e-05, "loss": 3.8896, "step": 1930240 }, { "epoch": 1.01, "learning_rate": 1.8387745903169822e-05, "loss": 3.8927, "step": 1930752 }, { "epoch": 1.01, "learning_rate": 1.8379359955659302e-05, "loss": 3.8928, "step": 1931264 }, { "epoch": 1.01, "learning_rate": 1.8370974008148782e-05, "loss": 3.899, "step": 1931776 }, { "epoch": 1.01, "learning_rate": 1.8362588060638265e-05, "loss": 3.8848, "step": 1932288 }, { "epoch": 1.01, "learning_rate": 1.8354218491931474e-05, "loss": 3.8785, "step": 1932800 }, { "epoch": 1.01, "learning_rate": 1.8345832544420954e-05, "loss": 3.9055, "step": 1933312 }, { "epoch": 1.01, "learning_rate": 1.8337446596910434e-05, "loss": 3.8992, "step": 1933824 }, { "epoch": 1.01, "learning_rate": 1.8329060649399914e-05, "loss": 3.9094, "step": 1934336 }, { "epoch": 1.01, "learning_rate": 1.8320691080693127e-05, "loss": 3.8884, "step": 1934848 }, { "epoch": 1.01, "learning_rate": 1.8312305133182607e-05, "loss": 3.8918, "step": 1935360 }, { "epoch": 1.01, "learning_rate": 1.8303919185672087e-05, "loss": 3.8927, "step": 1935872 }, { "epoch": 1.01, "learning_rate": 1.8295549616965296e-05, "loss": 3.8912, "step": 1936384 }, { "epoch": 1.01, "learning_rate": 1.8287163669454776e-05, "loss": 3.9051, "step": 1936896 }, { "epoch": 1.01, "learning_rate": 1.8278777721944256e-05, "loss": 3.878, "step": 1937408 }, { "epoch": 1.01, "learning_rate": 1.8270391774433736e-05, "loss": 3.9196, "step": 1937920 }, { "epoch": 1.01, "learning_rate": 1.826200582692322e-05, "loss": 3.8948, "step": 1938432 }, { "epoch": 1.01, "learning_rate": 1.8253619879412695e-05, "loss": 3.8735, "step": 1938944 }, { "epoch": 1.01, "learning_rate": 1.8245250310705908e-05, "loss": 3.9017, "step": 1939456 }, { "epoch": 1.01, "learning_rate": 1.8236864363195388e-05, "loss": 3.8895, "step": 1939968 }, { "epoch": 1.01, "learning_rate": 1.8228478415684868e-05, "loss": 3.8753, "step": 1940480 }, { "epoch": 1.01, "learning_rate": 1.8220092468174348e-05, "loss": 3.8999, "step": 1940992 }, { "epoch": 1.01, "learning_rate": 1.8211706520663828e-05, "loss": 3.9005, "step": 1941504 }, { "epoch": 1.01, "learning_rate": 1.8203320573153308e-05, "loss": 3.8869, "step": 1942016 }, { "epoch": 1.01, "learning_rate": 1.8194934625642788e-05, "loss": 3.8949, "step": 1942528 }, { "epoch": 1.01, "learning_rate": 1.8186565056935997e-05, "loss": 3.8739, "step": 1943040 }, { "epoch": 1.01, "learning_rate": 1.8178179109425477e-05, "loss": 3.8872, "step": 1943552 }, { "epoch": 1.01, "learning_rate": 1.8169793161914957e-05, "loss": 3.8958, "step": 1944064 }, { "epoch": 1.01, "learning_rate": 1.816142359320817e-05, "loss": 3.8886, "step": 1944576 }, { "epoch": 1.01, "learning_rate": 1.815303764569765e-05, "loss": 3.8996, "step": 1945088 }, { "epoch": 1.01, "learning_rate": 1.814465169818713e-05, "loss": 3.8867, "step": 1945600 }, { "epoch": 1.01, "learning_rate": 1.813626575067661e-05, "loss": 3.9095, "step": 1946112 }, { "epoch": 1.01, "learning_rate": 1.812787980316609e-05, "loss": 3.8904, "step": 1946624 }, { "epoch": 1.01, "learning_rate": 1.811949385565557e-05, "loss": 3.8956, "step": 1947136 }, { "epoch": 1.01, "learning_rate": 1.811110790814505e-05, "loss": 3.8934, "step": 1947648 }, { "epoch": 1.01, "learning_rate": 1.810272196063453e-05, "loss": 3.8894, "step": 1948160 }, { "epoch": 1.01, "learning_rate": 1.809433601312401e-05, "loss": 3.897, "step": 1948672 }, { "epoch": 1.01, "learning_rate": 1.808596644441722e-05, "loss": 3.8903, "step": 1949184 }, { "epoch": 1.01, "learning_rate": 1.8077580496906698e-05, "loss": 3.8972, "step": 1949696 }, { "epoch": 1.01, "learning_rate": 1.8069194549396178e-05, "loss": 3.899, "step": 1950208 }, { "epoch": 1.01, "learning_rate": 1.8060824980689394e-05, "loss": 3.8886, "step": 1950720 }, { "epoch": 1.01, "learning_rate": 1.8052439033178874e-05, "loss": 3.8808, "step": 1951232 }, { "epoch": 1.01, "learning_rate": 1.804405308566835e-05, "loss": 3.8911, "step": 1951744 }, { "epoch": 1.01, "learning_rate": 1.803566713815783e-05, "loss": 3.8981, "step": 1952256 }, { "epoch": 1.01, "learning_rate": 1.802728119064731e-05, "loss": 3.886, "step": 1952768 }, { "epoch": 1.01, "learning_rate": 1.801889524313679e-05, "loss": 3.8945, "step": 1953280 }, { "epoch": 1.02, "learning_rate": 1.801050929562627e-05, "loss": 3.8843, "step": 1953792 }, { "epoch": 1.02, "learning_rate": 1.800212334811575e-05, "loss": 3.888, "step": 1954304 }, { "epoch": 1.02, "learning_rate": 1.7993737400605233e-05, "loss": 3.8846, "step": 1954816 }, { "epoch": 1.02, "learning_rate": 1.7985367831898442e-05, "loss": 3.889, "step": 1955328 }, { "epoch": 1.02, "learning_rate": 1.7976981884387922e-05, "loss": 3.9044, "step": 1955840 }, { "epoch": 1.02, "learning_rate": 1.7968595936877402e-05, "loss": 3.8929, "step": 1956352 }, { "epoch": 1.02, "learning_rate": 1.796020998936688e-05, "loss": 3.8978, "step": 1956864 }, { "epoch": 1.02, "learning_rate": 1.7951840420660095e-05, "loss": 3.8892, "step": 1957376 }, { "epoch": 1.02, "learning_rate": 1.7943454473149575e-05, "loss": 3.8885, "step": 1957888 }, { "epoch": 1.02, "learning_rate": 1.7935068525639055e-05, "loss": 3.8904, "step": 1958400 }, { "epoch": 1.02, "learning_rate": 1.792668257812853e-05, "loss": 3.8987, "step": 1958912 }, { "epoch": 1.02, "learning_rate": 1.791829663061801e-05, "loss": 3.8974, "step": 1959424 }, { "epoch": 1.02, "learning_rate": 1.790991068310749e-05, "loss": 3.8977, "step": 1959936 }, { "epoch": 1.02, "learning_rate": 1.790152473559697e-05, "loss": 3.8943, "step": 1960448 }, { "epoch": 1.02, "learning_rate": 1.789313878808645e-05, "loss": 3.8898, "step": 1960960 }, { "epoch": 1.02, "learning_rate": 1.7884752840575934e-05, "loss": 3.8951, "step": 1961472 }, { "epoch": 1.02, "learning_rate": 1.7876399650672876e-05, "loss": 3.8887, "step": 1961984 }, { "epoch": 1.02, "learning_rate": 1.7868013703162353e-05, "loss": 3.8852, "step": 1962496 }, { "epoch": 1.02, "learning_rate": 1.7859627755651833e-05, "loss": 3.8953, "step": 1963008 }, { "epoch": 1.02, "learning_rate": 1.7851241808141313e-05, "loss": 3.8872, "step": 1963520 }, { "epoch": 1.02, "learning_rate": 1.7842855860630796e-05, "loss": 3.8863, "step": 1964032 }, { "epoch": 1.02, "learning_rate": 1.7834469913120276e-05, "loss": 3.8849, "step": 1964544 }, { "epoch": 1.02, "learning_rate": 1.7826100344413485e-05, "loss": 3.8844, "step": 1965056 }, { "epoch": 1.02, "learning_rate": 1.7817714396902965e-05, "loss": 3.893, "step": 1965568 }, { "epoch": 1.02, "learning_rate": 1.7809328449392445e-05, "loss": 3.8868, "step": 1966080 }, { "epoch": 1.02, "learning_rate": 1.7800942501881925e-05, "loss": 3.8991, "step": 1966592 }, { "epoch": 1.02, "learning_rate": 1.7792556554371405e-05, "loss": 3.8998, "step": 1967104 }, { "epoch": 1.02, "learning_rate": 1.7784186985664617e-05, "loss": 3.9051, "step": 1967616 }, { "epoch": 1.02, "learning_rate": 1.7775801038154097e-05, "loss": 3.8915, "step": 1968128 }, { "epoch": 1.02, "learning_rate": 1.7767431469447306e-05, "loss": 3.8908, "step": 1968640 }, { "epoch": 1.02, "learning_rate": 1.7759045521936786e-05, "loss": 3.8826, "step": 1969152 }, { "epoch": 1.02, "learning_rate": 1.7750659574426266e-05, "loss": 3.8987, "step": 1969664 }, { "epoch": 1.02, "learning_rate": 1.774227362691575e-05, "loss": 3.896, "step": 1970176 }, { "epoch": 1.02, "learning_rate": 1.773388767940523e-05, "loss": 3.8793, "step": 1970688 }, { "epoch": 1.02, "learning_rate": 1.772551811069844e-05, "loss": 3.8898, "step": 1971200 }, { "epoch": 1.02, "learning_rate": 1.771713216318792e-05, "loss": 3.894, "step": 1971712 }, { "epoch": 1.02, "learning_rate": 1.77087462156774e-05, "loss": 3.896, "step": 1972224 }, { "epoch": 1.02, "learning_rate": 1.770037664697061e-05, "loss": 3.8884, "step": 1972736 }, { "epoch": 1.02, "learning_rate": 1.769199069946009e-05, "loss": 3.8893, "step": 1973248 }, { "epoch": 1.02, "learning_rate": 1.768360475194957e-05, "loss": 3.8842, "step": 1973760 }, { "epoch": 1.02, "learning_rate": 1.767521880443905e-05, "loss": 3.9025, "step": 1974272 }, { "epoch": 1.02, "learning_rate": 1.766683285692853e-05, "loss": 3.8917, "step": 1974784 }, { "epoch": 1.02, "learning_rate": 1.7658446909418007e-05, "loss": 3.9043, "step": 1975296 }, { "epoch": 1.02, "learning_rate": 1.7650060961907487e-05, "loss": 3.884, "step": 1975808 }, { "epoch": 1.02, "learning_rate": 1.7641675014396967e-05, "loss": 3.8988, "step": 1976320 }, { "epoch": 1.02, "learning_rate": 1.763328906688645e-05, "loss": 3.9028, "step": 1976832 }, { "epoch": 1.02, "learning_rate": 1.762490311937593e-05, "loss": 3.8873, "step": 1977344 }, { "epoch": 1.02, "learning_rate": 1.761651717186541e-05, "loss": 3.8956, "step": 1977856 }, { "epoch": 1.02, "learning_rate": 1.760813122435489e-05, "loss": 3.8942, "step": 1978368 }, { "epoch": 1.02, "learning_rate": 1.7599745276844367e-05, "loss": 3.9003, "step": 1978880 }, { "epoch": 1.02, "learning_rate": 1.7591359329333847e-05, "loss": 3.9079, "step": 1979392 }, { "epoch": 1.02, "learning_rate": 1.7582973381823327e-05, "loss": 3.8952, "step": 1979904 }, { "epoch": 1.02, "learning_rate": 1.757458743431281e-05, "loss": 3.8959, "step": 1980416 }, { "epoch": 1.02, "learning_rate": 1.756620148680229e-05, "loss": 3.8976, "step": 1980928 }, { "epoch": 1.02, "learning_rate": 1.75578319180955e-05, "loss": 3.8928, "step": 1981440 }, { "epoch": 1.02, "learning_rate": 1.754944597058498e-05, "loss": 3.8878, "step": 1981952 }, { "epoch": 1.02, "learning_rate": 1.754106002307446e-05, "loss": 3.8869, "step": 1982464 }, { "epoch": 1.02, "learning_rate": 1.753267407556394e-05, "loss": 3.8889, "step": 1982976 }, { "epoch": 1.02, "learning_rate": 1.7524304506857152e-05, "loss": 3.8891, "step": 1983488 }, { "epoch": 1.02, "learning_rate": 1.751591855934663e-05, "loss": 3.8925, "step": 1984000 }, { "epoch": 1.03, "eval_loss": 3.9946038722991943, "eval_runtime": 301.4588, "eval_samples_per_second": 1265.815, "eval_steps_per_second": 39.558, "step": 1984320 }, { "epoch": 0.0, "learning_rate": 1.750753261183611e-05, "loss": 3.8923, "step": 1984512 }, { "epoch": 0.0, "learning_rate": 1.749914666432559e-05, "loss": 3.8873, "step": 1985024 }, { "epoch": 0.0, "learning_rate": 1.749076071681507e-05, "loss": 3.8927, "step": 1985536 }, { "epoch": 0.0, "learning_rate": 1.7482374769304548e-05, "loss": 3.8992, "step": 1986048 }, { "epoch": 0.0, "learning_rate": 1.7473988821794028e-05, "loss": 3.9066, "step": 1986560 }, { "epoch": 0.0, "learning_rate": 1.746560287428351e-05, "loss": 3.8932, "step": 1987072 }, { "epoch": 0.0, "learning_rate": 1.745721692677299e-05, "loss": 3.8966, "step": 1987584 }, { "epoch": 0.0, "learning_rate": 1.744883097926247e-05, "loss": 3.8874, "step": 1988096 }, { "epoch": 0.0, "learning_rate": 1.744044503175195e-05, "loss": 3.8858, "step": 1988608 }, { "epoch": 0.0, "learning_rate": 1.7432059084241428e-05, "loss": 3.8947, "step": 1989120 }, { "epoch": 0.0, "learning_rate": 1.7423673136730908e-05, "loss": 3.8993, "step": 1989632 }, { "epoch": 0.0, "learning_rate": 1.7415287189220388e-05, "loss": 3.8901, "step": 1990144 }, { "epoch": 0.0, "learning_rate": 1.7406917620513604e-05, "loss": 3.8974, "step": 1990656 }, { "epoch": 0.0, "learning_rate": 1.739853167300308e-05, "loss": 3.8833, "step": 1991168 }, { "epoch": 0.0, "learning_rate": 1.739014572549256e-05, "loss": 3.8898, "step": 1991680 }, { "epoch": 0.0, "learning_rate": 1.738175977798204e-05, "loss": 3.8712, "step": 1992192 }, { "epoch": 0.0, "learning_rate": 1.737337383047152e-05, "loss": 3.8957, "step": 1992704 }, { "epoch": 0.0, "learning_rate": 1.736500426176473e-05, "loss": 3.895, "step": 1993216 }, { "epoch": 0.0, "learning_rate": 1.7356618314254213e-05, "loss": 3.8844, "step": 1993728 }, { "epoch": 0.0, "learning_rate": 1.7348232366743692e-05, "loss": 3.8993, "step": 1994240 }, { "epoch": 0.0, "learning_rate": 1.7339846419233172e-05, "loss": 3.903, "step": 1994752 }, { "epoch": 0.0, "learning_rate": 1.7331460471722652e-05, "loss": 3.9025, "step": 1995264 }, { "epoch": 0.0, "learning_rate": 1.7323074524212132e-05, "loss": 3.8911, "step": 1995776 }, { "epoch": 0.0, "learning_rate": 1.731468857670161e-05, "loss": 3.8942, "step": 1996288 }, { "epoch": 0.0, "learning_rate": 1.730630262919109e-05, "loss": 3.8956, "step": 1996800 }, { "epoch": 0.0, "learning_rate": 1.729791668168057e-05, "loss": 3.8998, "step": 1997312 }, { "epoch": 0.0, "learning_rate": 1.7289530734170052e-05, "loss": 3.8805, "step": 1997824 }, { "epoch": 0.0, "learning_rate": 1.7281144786659532e-05, "loss": 3.8909, "step": 1998336 }, { "epoch": 0.0, "learning_rate": 1.727277521795274e-05, "loss": 3.889, "step": 1998848 }, { "epoch": 0.0, "learning_rate": 1.726438927044222e-05, "loss": 3.8874, "step": 1999360 }, { "epoch": 0.01, "learning_rate": 1.72560033229317e-05, "loss": 3.8935, "step": 1999872 }, { "epoch": 0.01, "learning_rate": 1.724761737542118e-05, "loss": 3.8997, "step": 2000384 }, { "epoch": 0.01, "learning_rate": 1.7239264185518126e-05, "loss": 3.8947, "step": 2000896 }, { "epoch": 0.01, "learning_rate": 1.7230878238007606e-05, "loss": 3.9027, "step": 2001408 }, { "epoch": 0.01, "learning_rate": 1.7222492290497083e-05, "loss": 3.8893, "step": 2001920 }, { "epoch": 0.01, "learning_rate": 1.7214122721790295e-05, "loss": 3.8966, "step": 2002432 }, { "epoch": 0.01, "learning_rate": 1.7205736774279775e-05, "loss": 3.9013, "step": 2002944 }, { "epoch": 0.01, "learning_rate": 1.719735082676926e-05, "loss": 3.8778, "step": 2003456 }, { "epoch": 0.01, "learning_rate": 1.7188964879258735e-05, "loss": 3.8826, "step": 2003968 }, { "epoch": 0.01, "learning_rate": 1.7180578931748215e-05, "loss": 3.885, "step": 2004480 }, { "epoch": 0.01, "learning_rate": 1.7172192984237695e-05, "loss": 3.8775, "step": 2004992 }, { "epoch": 0.01, "learning_rate": 1.7163807036727175e-05, "loss": 3.8898, "step": 2005504 }, { "epoch": 0.01, "learning_rate": 1.7155421089216655e-05, "loss": 3.8999, "step": 2006016 }, { "epoch": 0.01, "learning_rate": 1.7147035141706135e-05, "loss": 3.8853, "step": 2006528 }, { "epoch": 0.01, "learning_rate": 1.7138649194195615e-05, "loss": 3.8876, "step": 2007040 }, { "epoch": 0.01, "learning_rate": 1.7130263246685095e-05, "loss": 3.8919, "step": 2007552 }, { "epoch": 0.01, "learning_rate": 1.7121877299174575e-05, "loss": 3.8941, "step": 2008064 }, { "epoch": 0.01, "learning_rate": 1.7113507730467787e-05, "loss": 3.8802, "step": 2008576 }, { "epoch": 0.01, "learning_rate": 1.7105121782957264e-05, "loss": 3.872, "step": 2009088 }, { "epoch": 0.01, "learning_rate": 1.7096735835446744e-05, "loss": 3.897, "step": 2009600 }, { "epoch": 0.01, "learning_rate": 1.7088349887936227e-05, "loss": 3.8967, "step": 2010112 }, { "epoch": 0.01, "learning_rate": 1.7079963940425707e-05, "loss": 3.9063, "step": 2010624 }, { "epoch": 0.01, "learning_rate": 1.7071577992915187e-05, "loss": 3.8828, "step": 2011136 }, { "epoch": 0.01, "learning_rate": 1.7063192045404667e-05, "loss": 3.885, "step": 2011648 }, { "epoch": 0.01, "learning_rate": 1.7054806097894147e-05, "loss": 3.8886, "step": 2012160 }, { "epoch": 0.01, "learning_rate": 1.704646928679482e-05, "loss": 3.8851, "step": 2012672 }, { "epoch": 0.01, "learning_rate": 1.70380833392843e-05, "loss": 3.9, "step": 2013184 }, { "epoch": 0.01, "learning_rate": 1.702969739177378e-05, "loss": 3.8709, "step": 2013696 }, { "epoch": 0.01, "learning_rate": 1.702131144426326e-05, "loss": 3.9151, "step": 2014208 }, { "epoch": 0.01, "learning_rate": 1.7012925496752737e-05, "loss": 3.8936, "step": 2014720 }, { "epoch": 0.01, "learning_rate": 1.7004539549242217e-05, "loss": 3.8706, "step": 2015232 }, { "epoch": 0.01, "learning_rate": 1.6996153601731697e-05, "loss": 3.8934, "step": 2015744 }, { "epoch": 0.01, "learning_rate": 1.6987767654221177e-05, "loss": 3.8842, "step": 2016256 }, { "epoch": 0.01, "learning_rate": 1.697938170671066e-05, "loss": 3.8714, "step": 2016768 }, { "epoch": 0.01, "learning_rate": 1.697099575920014e-05, "loss": 3.8966, "step": 2017280 }, { "epoch": 0.01, "learning_rate": 1.696262619049335e-05, "loss": 3.8959, "step": 2017792 }, { "epoch": 0.01, "learning_rate": 1.695424024298283e-05, "loss": 3.8813, "step": 2018304 }, { "epoch": 0.01, "learning_rate": 1.694585429547231e-05, "loss": 3.8938, "step": 2018816 }, { "epoch": 0.01, "learning_rate": 1.693746834796179e-05, "loss": 3.8677, "step": 2019328 }, { "epoch": 0.01, "learning_rate": 1.6929098779255002e-05, "loss": 3.883, "step": 2019840 }, { "epoch": 0.01, "learning_rate": 1.6920712831744482e-05, "loss": 3.8839, "step": 2020352 }, { "epoch": 0.01, "learning_rate": 1.6912326884233962e-05, "loss": 3.8869, "step": 2020864 }, { "epoch": 0.01, "learning_rate": 1.6903940936723442e-05, "loss": 3.892, "step": 2021376 }, { "epoch": 0.01, "learning_rate": 1.689555498921292e-05, "loss": 3.8851, "step": 2021888 }, { "epoch": 0.01, "learning_rate": 1.68871690417024e-05, "loss": 3.9069, "step": 2022400 }, { "epoch": 0.01, "learning_rate": 1.6878783094191882e-05, "loss": 3.8861, "step": 2022912 }, { "epoch": 0.01, "learning_rate": 1.687039714668136e-05, "loss": 3.8935, "step": 2023424 }, { "epoch": 0.01, "learning_rate": 1.686202757797457e-05, "loss": 3.8864, "step": 2023936 }, { "epoch": 0.01, "learning_rate": 1.685364163046405e-05, "loss": 3.8838, "step": 2024448 }, { "epoch": 0.01, "learning_rate": 1.684525568295353e-05, "loss": 3.8939, "step": 2024960 }, { "epoch": 0.01, "learning_rate": 1.6836886114246743e-05, "loss": 3.8866, "step": 2025472 }, { "epoch": 0.01, "learning_rate": 1.6828500166736223e-05, "loss": 3.8906, "step": 2025984 }, { "epoch": 0.01, "learning_rate": 1.6820114219225703e-05, "loss": 3.8972, "step": 2026496 }, { "epoch": 0.01, "learning_rate": 1.6811728271715183e-05, "loss": 3.8844, "step": 2027008 }, { "epoch": 0.01, "learning_rate": 1.6803342324204663e-05, "loss": 3.8743, "step": 2027520 }, { "epoch": 0.01, "learning_rate": 1.6794956376694143e-05, "loss": 3.8849, "step": 2028032 }, { "epoch": 0.01, "learning_rate": 1.6786586807987352e-05, "loss": 3.8966, "step": 2028544 }, { "epoch": 0.01, "learning_rate": 1.6778200860476835e-05, "loss": 3.877, "step": 2029056 }, { "epoch": 0.01, "learning_rate": 1.6769814912966315e-05, "loss": 3.8941, "step": 2029568 }, { "epoch": 0.01, "learning_rate": 1.6761428965455795e-05, "loss": 3.8849, "step": 2030080 }, { "epoch": 0.02, "learning_rate": 1.6753043017945275e-05, "loss": 3.8787, "step": 2030592 }, { "epoch": 0.02, "learning_rate": 1.6744673449238484e-05, "loss": 3.8805, "step": 2031104 }, { "epoch": 0.02, "learning_rate": 1.6736287501727964e-05, "loss": 3.8839, "step": 2031616 }, { "epoch": 0.02, "learning_rate": 1.6727901554217444e-05, "loss": 3.9027, "step": 2032128 }, { "epoch": 0.02, "learning_rate": 1.6719515606706924e-05, "loss": 3.8855, "step": 2032640 }, { "epoch": 0.02, "learning_rate": 1.6711129659196404e-05, "loss": 3.8923, "step": 2033152 }, { "epoch": 0.02, "learning_rate": 1.6702743711685884e-05, "loss": 3.8838, "step": 2033664 }, { "epoch": 0.02, "learning_rate": 1.6694357764175364e-05, "loss": 3.8811, "step": 2034176 }, { "epoch": 0.02, "learning_rate": 1.6685971816664844e-05, "loss": 3.8837, "step": 2034688 }, { "epoch": 0.02, "learning_rate": 1.6677585869154324e-05, "loss": 3.8954, "step": 2035200 }, { "epoch": 0.02, "learning_rate": 1.6669216300447536e-05, "loss": 3.8949, "step": 2035712 }, { "epoch": 0.02, "learning_rate": 1.6660830352937016e-05, "loss": 3.8909, "step": 2036224 }, { "epoch": 0.02, "learning_rate": 1.6652444405426496e-05, "loss": 3.8907, "step": 2036736 }, { "epoch": 0.02, "learning_rate": 1.6644074836719705e-05, "loss": 3.8818, "step": 2037248 }, { "epoch": 0.02, "learning_rate": 1.6635688889209185e-05, "loss": 3.8915, "step": 2037760 }, { "epoch": 0.02, "learning_rate": 1.6627302941698665e-05, "loss": 3.8858, "step": 2038272 }, { "epoch": 0.02, "learning_rate": 1.6618916994188145e-05, "loss": 3.8815, "step": 2038784 }, { "epoch": 0.02, "learning_rate": 1.661053104667763e-05, "loss": 3.887, "step": 2039296 }, { "epoch": 0.02, "learning_rate": 1.6602145099167105e-05, "loss": 3.8841, "step": 2039808 }, { "epoch": 0.02, "learning_rate": 1.6593759151656585e-05, "loss": 3.884, "step": 2040320 }, { "epoch": 0.02, "learning_rate": 1.6585373204146065e-05, "loss": 3.8808, "step": 2040832 }, { "epoch": 0.02, "learning_rate": 1.6577020014243007e-05, "loss": 3.8786, "step": 2041344 }, { "epoch": 0.02, "learning_rate": 1.656863406673249e-05, "loss": 3.8862, "step": 2041856 }, { "epoch": 0.02, "learning_rate": 1.656024811922197e-05, "loss": 3.8879, "step": 2042368 }, { "epoch": 0.02, "learning_rate": 1.655186217171145e-05, "loss": 3.8896, "step": 2042880 }, { "epoch": 0.02, "learning_rate": 1.654347622420093e-05, "loss": 3.8958, "step": 2043392 }, { "epoch": 0.02, "learning_rate": 1.6535090276690407e-05, "loss": 3.9015, "step": 2043904 }, { "epoch": 0.02, "learning_rate": 1.6526704329179887e-05, "loss": 3.8858, "step": 2044416 }, { "epoch": 0.02, "learning_rate": 1.6518318381669366e-05, "loss": 3.8866, "step": 2044928 }, { "epoch": 0.02, "learning_rate": 1.650994881296258e-05, "loss": 3.8785, "step": 2045440 }, { "epoch": 0.02, "learning_rate": 1.650156286545206e-05, "loss": 3.8907, "step": 2045952 }, { "epoch": 0.02, "learning_rate": 1.649317691794154e-05, "loss": 3.889, "step": 2046464 }, { "epoch": 0.02, "learning_rate": 1.648479097043102e-05, "loss": 3.8783, "step": 2046976 }, { "epoch": 0.02, "learning_rate": 1.6476421401724228e-05, "loss": 3.8819, "step": 2047488 }, { "epoch": 0.02, "learning_rate": 1.6468035454213708e-05, "loss": 3.8927, "step": 2048000 }, { "epoch": 0.02, "learning_rate": 1.645964950670319e-05, "loss": 3.8912, "step": 2048512 }, { "epoch": 0.02, "learning_rate": 1.645126355919267e-05, "loss": 3.8815, "step": 2049024 }, { "epoch": 0.02, "learning_rate": 1.644287761168215e-05, "loss": 3.8845, "step": 2049536 }, { "epoch": 0.02, "learning_rate": 1.643450804297536e-05, "loss": 3.8836, "step": 2050048 }, { "epoch": 0.02, "learning_rate": 1.642612209546484e-05, "loss": 3.8932, "step": 2050560 }, { "epoch": 0.02, "learning_rate": 1.6417752526758053e-05, "loss": 3.8907, "step": 2051072 }, { "epoch": 0.02, "learning_rate": 1.6409366579247533e-05, "loss": 3.8992, "step": 2051584 }, { "epoch": 0.02, "learning_rate": 1.6400980631737013e-05, "loss": 3.8804, "step": 2052096 }, { "epoch": 0.02, "learning_rate": 1.6392611063030225e-05, "loss": 3.8941, "step": 2052608 }, { "epoch": 0.02, "learning_rate": 1.63842251155197e-05, "loss": 3.8959, "step": 2053120 }, { "epoch": 0.02, "learning_rate": 1.637583916800918e-05, "loss": 3.88, "step": 2053632 }, { "epoch": 0.02, "learning_rate": 1.636745322049866e-05, "loss": 3.8881, "step": 2054144 }, { "epoch": 0.02, "learning_rate": 1.6359067272988145e-05, "loss": 3.8914, "step": 2054656 }, { "epoch": 0.02, "learning_rate": 1.6350681325477625e-05, "loss": 3.8978, "step": 2055168 }, { "epoch": 0.02, "learning_rate": 1.6342295377967105e-05, "loss": 3.8989, "step": 2055680 }, { "epoch": 0.02, "learning_rate": 1.633390943045658e-05, "loss": 3.8872, "step": 2056192 }, { "epoch": 0.02, "learning_rate": 1.632552348294606e-05, "loss": 3.8922, "step": 2056704 }, { "epoch": 0.02, "learning_rate": 1.631713753543554e-05, "loss": 3.8933, "step": 2057216 }, { "epoch": 0.02, "learning_rate": 1.630875158792502e-05, "loss": 3.8873, "step": 2057728 }, { "epoch": 0.02, "learning_rate": 1.63003656404145e-05, "loss": 3.8838, "step": 2058240 }, { "epoch": 0.02, "learning_rate": 1.6292012450511446e-05, "loss": 3.8814, "step": 2058752 }, { "epoch": 0.02, "learning_rate": 1.6283626503000926e-05, "loss": 3.8804, "step": 2059264 }, { "epoch": 0.02, "learning_rate": 1.6275240555490406e-05, "loss": 3.8872, "step": 2059776 }, { "epoch": 0.02, "learning_rate": 1.6266854607979883e-05, "loss": 3.8861, "step": 2060288 }, { "epoch": 0.03, "eval_loss": 3.9931588172912598, "eval_runtime": 293.1849, "eval_samples_per_second": 1301.537, "eval_steps_per_second": 40.674, "step": 2060640 }, { "epoch": 1.0, "learning_rate": 1.6258468660469363e-05, "loss": 3.8847, "step": 2060800 }, { "epoch": 1.0, "learning_rate": 1.6250082712958846e-05, "loss": 3.8838, "step": 2061312 }, { "epoch": 1.0, "learning_rate": 1.6241696765448326e-05, "loss": 3.8898, "step": 2061824 }, { "epoch": 1.0, "learning_rate": 1.6233310817937806e-05, "loss": 3.8923, "step": 2062336 }, { "epoch": 1.0, "learning_rate": 1.6224924870427286e-05, "loss": 3.9009, "step": 2062848 }, { "epoch": 1.0, "learning_rate": 1.6216538922916762e-05, "loss": 3.8897, "step": 2063360 }, { "epoch": 1.0, "learning_rate": 1.6208169354209975e-05, "loss": 3.8936, "step": 2063872 }, { "epoch": 1.0, "learning_rate": 1.6199783406699455e-05, "loss": 3.8863, "step": 2064384 }, { "epoch": 1.0, "learning_rate": 1.6191397459188938e-05, "loss": 3.8792, "step": 2064896 }, { "epoch": 1.0, "learning_rate": 1.6183011511678415e-05, "loss": 3.8858, "step": 2065408 }, { "epoch": 1.0, "learning_rate": 1.6174625564167895e-05, "loss": 3.8989, "step": 2065920 }, { "epoch": 1.0, "learning_rate": 1.6166239616657375e-05, "loss": 3.8823, "step": 2066432 }, { "epoch": 1.0, "learning_rate": 1.6157870047950587e-05, "loss": 3.8973, "step": 2066944 }, { "epoch": 1.0, "learning_rate": 1.6149484100440067e-05, "loss": 3.8762, "step": 2067456 }, { "epoch": 1.0, "learning_rate": 1.6141098152929547e-05, "loss": 3.8832, "step": 2067968 }, { "epoch": 1.0, "learning_rate": 1.6132712205419027e-05, "loss": 3.8698, "step": 2068480 }, { "epoch": 1.0, "learning_rate": 1.6124342636712236e-05, "loss": 3.89, "step": 2068992 }, { "epoch": 1.0, "learning_rate": 1.6115956689201716e-05, "loss": 3.888, "step": 2069504 }, { "epoch": 1.0, "learning_rate": 1.6107570741691196e-05, "loss": 3.8849, "step": 2070016 }, { "epoch": 1.0, "learning_rate": 1.6099184794180676e-05, "loss": 3.8864, "step": 2070528 }, { "epoch": 1.0, "learning_rate": 1.6090798846670156e-05, "loss": 3.9021, "step": 2071040 }, { "epoch": 1.0, "learning_rate": 1.608241289915964e-05, "loss": 3.8925, "step": 2071552 }, { "epoch": 1.0, "learning_rate": 1.607402695164912e-05, "loss": 3.8902, "step": 2072064 }, { "epoch": 1.0, "learning_rate": 1.6065641004138596e-05, "loss": 3.8844, "step": 2072576 }, { "epoch": 1.0, "learning_rate": 1.6057255056628076e-05, "loss": 3.8953, "step": 2073088 }, { "epoch": 1.0, "learning_rate": 1.6048885487921288e-05, "loss": 3.8902, "step": 2073600 }, { "epoch": 1.0, "learning_rate": 1.6040499540410768e-05, "loss": 3.8815, "step": 2074112 }, { "epoch": 1.0, "learning_rate": 1.603212997170398e-05, "loss": 3.8862, "step": 2074624 }, { "epoch": 1.0, "learning_rate": 1.602374402419346e-05, "loss": 3.8821, "step": 2075136 }, { "epoch": 1.0, "learning_rate": 1.601535807668294e-05, "loss": 3.8781, "step": 2075648 }, { "epoch": 1.01, "learning_rate": 1.6006972129172417e-05, "loss": 3.8922, "step": 2076160 }, { "epoch": 1.01, "learning_rate": 1.599860256046563e-05, "loss": 3.8872, "step": 2076672 }, { "epoch": 1.01, "learning_rate": 1.599021661295511e-05, "loss": 3.8942, "step": 2077184 }, { "epoch": 1.01, "learning_rate": 1.5981830665444593e-05, "loss": 3.897, "step": 2077696 }, { "epoch": 1.01, "learning_rate": 1.597344471793407e-05, "loss": 3.8834, "step": 2078208 }, { "epoch": 1.01, "learning_rate": 1.5965075149227282e-05, "loss": 3.8937, "step": 2078720 }, { "epoch": 1.01, "learning_rate": 1.5956689201716762e-05, "loss": 3.8961, "step": 2079232 }, { "epoch": 1.01, "learning_rate": 1.5948303254206242e-05, "loss": 3.8759, "step": 2079744 }, { "epoch": 1.01, "learning_rate": 1.5939917306695722e-05, "loss": 3.8832, "step": 2080256 }, { "epoch": 1.01, "learning_rate": 1.5931531359185202e-05, "loss": 3.8746, "step": 2080768 }, { "epoch": 1.01, "learning_rate": 1.5923145411674682e-05, "loss": 3.8765, "step": 2081280 }, { "epoch": 1.01, "learning_rate": 1.5914759464164162e-05, "loss": 3.8871, "step": 2081792 }, { "epoch": 1.01, "learning_rate": 1.5906373516653642e-05, "loss": 3.894, "step": 2082304 }, { "epoch": 1.01, "learning_rate": 1.589798756914312e-05, "loss": 3.8794, "step": 2082816 }, { "epoch": 1.01, "learning_rate": 1.5889601621632598e-05, "loss": 3.8813, "step": 2083328 }, { "epoch": 1.01, "learning_rate": 1.588123205292581e-05, "loss": 3.8874, "step": 2083840 }, { "epoch": 1.01, "learning_rate": 1.5872846105415294e-05, "loss": 3.8876, "step": 2084352 }, { "epoch": 1.01, "learning_rate": 1.5864460157904774e-05, "loss": 3.8785, "step": 2084864 }, { "epoch": 1.01, "learning_rate": 1.585607421039425e-05, "loss": 3.8686, "step": 2085376 }, { "epoch": 1.01, "learning_rate": 1.584768826288373e-05, "loss": 3.8921, "step": 2085888 }, { "epoch": 1.01, "learning_rate": 1.583930231537321e-05, "loss": 3.8968, "step": 2086400 }, { "epoch": 1.01, "learning_rate": 1.583091636786269e-05, "loss": 3.8982, "step": 2086912 }, { "epoch": 1.01, "learning_rate": 1.5822546799155903e-05, "loss": 3.8796, "step": 2087424 }, { "epoch": 1.01, "learning_rate": 1.5814160851645383e-05, "loss": 3.8822, "step": 2087936 }, { "epoch": 1.01, "learning_rate": 1.5805774904134863e-05, "loss": 3.8831, "step": 2088448 }, { "epoch": 1.01, "learning_rate": 1.5797405335428072e-05, "loss": 3.8786, "step": 2088960 }, { "epoch": 1.01, "learning_rate": 1.5789019387917552e-05, "loss": 3.8962, "step": 2089472 }, { "epoch": 1.01, "learning_rate": 1.5780633440407032e-05, "loss": 3.87, "step": 2089984 }, { "epoch": 1.01, "learning_rate": 1.5772247492896515e-05, "loss": 3.9073, "step": 2090496 }, { "epoch": 1.01, "learning_rate": 1.5763861545385995e-05, "loss": 3.8881, "step": 2091008 }, { "epoch": 1.01, "learning_rate": 1.5755475597875475e-05, "loss": 3.8687, "step": 2091520 }, { "epoch": 1.01, "learning_rate": 1.5747089650364955e-05, "loss": 3.8876, "step": 2092032 }, { "epoch": 1.01, "learning_rate": 1.573870370285443e-05, "loss": 3.8818, "step": 2092544 }, { "epoch": 1.01, "learning_rate": 1.573031775534391e-05, "loss": 3.8692, "step": 2093056 }, { "epoch": 1.01, "learning_rate": 1.5721948186637124e-05, "loss": 3.8862, "step": 2093568 }, { "epoch": 1.01, "learning_rate": 1.5713562239126604e-05, "loss": 3.8915, "step": 2094080 }, { "epoch": 1.01, "learning_rate": 1.5705176291616084e-05, "loss": 3.878, "step": 2094592 }, { "epoch": 1.01, "learning_rate": 1.5696790344105564e-05, "loss": 3.8897, "step": 2095104 }, { "epoch": 1.01, "learning_rate": 1.5688404396595044e-05, "loss": 3.8644, "step": 2095616 }, { "epoch": 1.01, "learning_rate": 1.5680034827888253e-05, "loss": 3.8795, "step": 2096128 }, { "epoch": 1.01, "learning_rate": 1.5671648880377733e-05, "loss": 3.88, "step": 2096640 }, { "epoch": 1.01, "learning_rate": 1.5663262932867216e-05, "loss": 3.8842, "step": 2097152 }, { "epoch": 1.01, "learning_rate": 1.5654876985356696e-05, "loss": 3.8811, "step": 2097664 }, { "epoch": 1.01, "learning_rate": 1.5646491037846176e-05, "loss": 3.8802, "step": 2098176 }, { "epoch": 1.01, "learning_rate": 1.5638105090335656e-05, "loss": 3.8985, "step": 2098688 }, { "epoch": 1.01, "learning_rate": 1.5629719142825136e-05, "loss": 3.8866, "step": 2099200 }, { "epoch": 1.01, "learning_rate": 1.5621333195314613e-05, "loss": 3.8867, "step": 2099712 }, { "epoch": 1.01, "learning_rate": 1.5612963626607825e-05, "loss": 3.8826, "step": 2100224 }, { "epoch": 1.01, "learning_rate": 1.560457767909731e-05, "loss": 3.8781, "step": 2100736 }, { "epoch": 1.01, "learning_rate": 1.5596191731586785e-05, "loss": 3.8909, "step": 2101248 }, { "epoch": 1.01, "learning_rate": 1.5587805784076265e-05, "loss": 3.8821, "step": 2101760 }, { "epoch": 1.01, "learning_rate": 1.5579436215369478e-05, "loss": 3.8822, "step": 2102272 }, { "epoch": 1.01, "learning_rate": 1.5571050267858957e-05, "loss": 3.8914, "step": 2102784 }, { "epoch": 1.01, "learning_rate": 1.5562664320348434e-05, "loss": 3.8853, "step": 2103296 }, { "epoch": 1.01, "learning_rate": 1.5554278372837917e-05, "loss": 3.8665, "step": 2103808 }, { "epoch": 1.01, "learning_rate": 1.5545892425327397e-05, "loss": 3.8828, "step": 2104320 }, { "epoch": 1.01, "learning_rate": 1.553752285662061e-05, "loss": 3.8887, "step": 2104832 }, { "epoch": 1.01, "learning_rate": 1.552915328791382e-05, "loss": 3.8749, "step": 2105344 }, { "epoch": 1.01, "learning_rate": 1.55207673404033e-05, "loss": 3.8857, "step": 2105856 }, { "epoch": 1.01, "learning_rate": 1.551238139289278e-05, "loss": 3.8825, "step": 2106368 }, { "epoch": 1.02, "learning_rate": 1.550401182418599e-05, "loss": 3.8717, "step": 2106880 }, { "epoch": 1.02, "learning_rate": 1.549562587667547e-05, "loss": 3.8804, "step": 2107392 }, { "epoch": 1.02, "learning_rate": 1.548723992916495e-05, "loss": 3.8745, "step": 2107904 }, { "epoch": 1.02, "learning_rate": 1.547885398165443e-05, "loss": 3.8944, "step": 2108416 }, { "epoch": 1.02, "learning_rate": 1.5470468034143908e-05, "loss": 3.8837, "step": 2108928 }, { "epoch": 1.02, "learning_rate": 1.5462082086633388e-05, "loss": 3.8904, "step": 2109440 }, { "epoch": 1.02, "learning_rate": 1.545369613912287e-05, "loss": 3.8768, "step": 2109952 }, { "epoch": 1.02, "learning_rate": 1.544531019161235e-05, "loss": 3.8775, "step": 2110464 }, { "epoch": 1.02, "learning_rate": 1.543692424410183e-05, "loss": 3.8829, "step": 2110976 }, { "epoch": 1.02, "learning_rate": 1.542853829659131e-05, "loss": 3.89, "step": 2111488 }, { "epoch": 1.02, "learning_rate": 1.542015234908079e-05, "loss": 3.8891, "step": 2112000 }, { "epoch": 1.02, "learning_rate": 1.5411766401570267e-05, "loss": 3.8852, "step": 2112512 }, { "epoch": 1.02, "learning_rate": 1.540339683286348e-05, "loss": 3.8827, "step": 2113024 }, { "epoch": 1.02, "learning_rate": 1.5395010885352963e-05, "loss": 3.8767, "step": 2113536 }, { "epoch": 1.02, "learning_rate": 1.538662493784244e-05, "loss": 3.8884, "step": 2114048 }, { "epoch": 1.02, "learning_rate": 1.537823899033192e-05, "loss": 3.8787, "step": 2114560 }, { "epoch": 1.02, "learning_rate": 1.53698530428214e-05, "loss": 3.8799, "step": 2115072 }, { "epoch": 1.02, "learning_rate": 1.5361483474114612e-05, "loss": 3.8812, "step": 2115584 }, { "epoch": 1.02, "learning_rate": 1.5353113905407825e-05, "loss": 3.881, "step": 2116096 }, { "epoch": 1.02, "learning_rate": 1.5344727957897305e-05, "loss": 3.8807, "step": 2116608 }, { "epoch": 1.02, "learning_rate": 1.5336358389190514e-05, "loss": 3.8742, "step": 2117120 }, { "epoch": 1.02, "learning_rate": 1.5327972441679994e-05, "loss": 3.8727, "step": 2117632 }, { "epoch": 1.02, "learning_rate": 1.5319586494169474e-05, "loss": 3.8845, "step": 2118144 }, { "epoch": 1.02, "learning_rate": 1.5311200546658954e-05, "loss": 3.8829, "step": 2118656 }, { "epoch": 1.02, "learning_rate": 1.5302814599148434e-05, "loss": 3.8832, "step": 2119168 }, { "epoch": 1.02, "learning_rate": 1.5294428651637914e-05, "loss": 3.8908, "step": 2119680 }, { "epoch": 1.02, "learning_rate": 1.5286042704127394e-05, "loss": 3.8987, "step": 2120192 }, { "epoch": 1.02, "learning_rate": 1.5277656756616873e-05, "loss": 3.8805, "step": 2120704 }, { "epoch": 1.02, "learning_rate": 1.5269270809106353e-05, "loss": 3.8774, "step": 2121216 }, { "epoch": 1.02, "learning_rate": 1.5260884861595833e-05, "loss": 3.877, "step": 2121728 }, { "epoch": 1.02, "learning_rate": 1.5252498914085315e-05, "loss": 3.8861, "step": 2122240 }, { "epoch": 1.02, "learning_rate": 1.5244129345378524e-05, "loss": 3.8834, "step": 2122752 }, { "epoch": 1.02, "learning_rate": 1.5235743397868004e-05, "loss": 3.8757, "step": 2123264 }, { "epoch": 1.02, "learning_rate": 1.5227357450357486e-05, "loss": 3.8781, "step": 2123776 }, { "epoch": 1.02, "learning_rate": 1.5218971502846966e-05, "loss": 3.8896, "step": 2124288 }, { "epoch": 1.02, "learning_rate": 1.5210585555336442e-05, "loss": 3.8811, "step": 2124800 }, { "epoch": 1.02, "learning_rate": 1.5202199607825924e-05, "loss": 3.8792, "step": 2125312 }, { "epoch": 1.02, "learning_rate": 1.5193813660315404e-05, "loss": 3.8859, "step": 2125824 }, { "epoch": 1.02, "learning_rate": 1.5185444091608616e-05, "loss": 3.8794, "step": 2126336 }, { "epoch": 1.02, "learning_rate": 1.5177058144098095e-05, "loss": 3.8821, "step": 2126848 }, { "epoch": 1.02, "learning_rate": 1.5168672196587575e-05, "loss": 3.889, "step": 2127360 }, { "epoch": 1.02, "learning_rate": 1.5160286249077055e-05, "loss": 3.8917, "step": 2127872 }, { "epoch": 1.02, "learning_rate": 1.5151900301566534e-05, "loss": 3.8771, "step": 2128384 }, { "epoch": 1.02, "learning_rate": 1.5143514354056016e-05, "loss": 3.8894, "step": 2128896 }, { "epoch": 1.02, "learning_rate": 1.5135128406545496e-05, "loss": 3.8908, "step": 2129408 }, { "epoch": 1.02, "learning_rate": 1.5126758837838705e-05, "loss": 3.8789, "step": 2129920 }, { "epoch": 1.02, "learning_rate": 1.5118372890328187e-05, "loss": 3.8818, "step": 2130432 }, { "epoch": 1.02, "learning_rate": 1.5109986942817667e-05, "loss": 3.8851, "step": 2130944 }, { "epoch": 1.02, "learning_rate": 1.5101600995307147e-05, "loss": 3.8942, "step": 2131456 }, { "epoch": 1.02, "learning_rate": 1.5093215047796625e-05, "loss": 3.8936, "step": 2131968 }, { "epoch": 1.02, "learning_rate": 1.5084845479089837e-05, "loss": 3.8862, "step": 2132480 }, { "epoch": 1.02, "learning_rate": 1.5076459531579317e-05, "loss": 3.8855, "step": 2132992 }, { "epoch": 1.02, "learning_rate": 1.5068073584068797e-05, "loss": 3.8893, "step": 2133504 }, { "epoch": 1.02, "learning_rate": 1.5059687636558276e-05, "loss": 3.8872, "step": 2134016 }, { "epoch": 1.02, "learning_rate": 1.5051318067851488e-05, "loss": 3.8746, "step": 2134528 }, { "epoch": 1.02, "learning_rate": 1.504293212034097e-05, "loss": 3.8835, "step": 2135040 }, { "epoch": 1.02, "learning_rate": 1.503454617283045e-05, "loss": 3.874, "step": 2135552 }, { "epoch": 1.02, "learning_rate": 1.5026160225319926e-05, "loss": 3.8829, "step": 2136064 }, { "epoch": 1.02, "learning_rate": 1.501779065661314e-05, "loss": 3.8822, "step": 2136576 }, { "epoch": 1.03, "eval_loss": 3.9916534423828125, "eval_runtime": 294.0708, "eval_samples_per_second": 1297.616, "eval_steps_per_second": 40.551, "step": 2136960 }, { "epoch": 0.0, "learning_rate": 1.500940470910262e-05, "loss": 3.8905, "step": 2137088 }, { "epoch": 0.0, "learning_rate": 1.5001018761592097e-05, "loss": 3.8747, "step": 2137600 }, { "epoch": 0.0, "learning_rate": 1.4992632814081579e-05, "loss": 3.883, "step": 2138112 }, { "epoch": 0.0, "learning_rate": 1.4984246866571059e-05, "loss": 3.8935, "step": 2138624 }, { "epoch": 0.0, "learning_rate": 1.4975860919060539e-05, "loss": 3.8913, "step": 2139136 }, { "epoch": 0.0, "learning_rate": 1.4967474971550019e-05, "loss": 3.8913, "step": 2139648 }, { "epoch": 0.0, "learning_rate": 1.4959089024039498e-05, "loss": 3.8882, "step": 2140160 }, { "epoch": 0.0, "learning_rate": 1.495070307652898e-05, "loss": 3.8795, "step": 2140672 }, { "epoch": 0.0, "learning_rate": 1.4942317129018457e-05, "loss": 3.8726, "step": 2141184 }, { "epoch": 0.0, "learning_rate": 1.4933931181507937e-05, "loss": 3.889, "step": 2141696 }, { "epoch": 0.0, "learning_rate": 1.4925545233997418e-05, "loss": 3.8839, "step": 2142208 }, { "epoch": 0.0, "learning_rate": 1.4917159286486898e-05, "loss": 3.8835, "step": 2142720 }, { "epoch": 0.0, "learning_rate": 1.4908789717780109e-05, "loss": 3.8927, "step": 2143232 }, { "epoch": 0.0, "learning_rate": 1.4900403770269589e-05, "loss": 3.8718, "step": 2143744 }, { "epoch": 0.0, "learning_rate": 1.4892017822759069e-05, "loss": 3.88, "step": 2144256 }, { "epoch": 0.0, "learning_rate": 1.488364825405228e-05, "loss": 3.8646, "step": 2144768 }, { "epoch": 0.0, "learning_rate": 1.487526230654176e-05, "loss": 3.889, "step": 2145280 }, { "epoch": 0.0, "learning_rate": 1.486687635903124e-05, "loss": 3.8794, "step": 2145792 }, { "epoch": 0.0, "learning_rate": 1.485849041152072e-05, "loss": 3.8813, "step": 2146304 }, { "epoch": 0.0, "learning_rate": 1.4850104464010201e-05, "loss": 3.8858, "step": 2146816 }, { "epoch": 0.0, "learning_rate": 1.4841718516499681e-05, "loss": 3.8935, "step": 2147328 }, { "epoch": 0.0, "learning_rate": 1.4833332568989161e-05, "loss": 3.8889, "step": 2147840 }, { "epoch": 0.0, "learning_rate": 1.482494662147864e-05, "loss": 3.8829, "step": 2148352 }, { "epoch": 0.0, "learning_rate": 1.481656067396812e-05, "loss": 3.8812, "step": 2148864 }, { "epoch": 0.0, "learning_rate": 1.48081747264576e-05, "loss": 3.8944, "step": 2149376 }, { "epoch": 0.0, "learning_rate": 1.479978877894708e-05, "loss": 3.8852, "step": 2149888 }, { "epoch": 0.0, "learning_rate": 1.479140283143656e-05, "loss": 3.8737, "step": 2150400 }, { "epoch": 0.0, "learning_rate": 1.4783016883926041e-05, "loss": 3.8844, "step": 2150912 }, { "epoch": 0.0, "learning_rate": 1.4774630936415521e-05, "loss": 3.8715, "step": 2151424 }, { "epoch": 0.0, "learning_rate": 1.4766244988904997e-05, "loss": 3.8798, "step": 2151936 }, { "epoch": 0.01, "learning_rate": 1.4757875420198212e-05, "loss": 3.8876, "step": 2152448 }, { "epoch": 0.01, "learning_rate": 1.4749489472687692e-05, "loss": 3.8832, "step": 2152960 }, { "epoch": 0.01, "learning_rate": 1.4741103525177168e-05, "loss": 3.8869, "step": 2153472 }, { "epoch": 0.01, "learning_rate": 1.473271757766665e-05, "loss": 3.892, "step": 2153984 }, { "epoch": 0.01, "learning_rate": 1.472433163015613e-05, "loss": 3.8817, "step": 2154496 }, { "epoch": 0.01, "learning_rate": 1.4715978440253073e-05, "loss": 3.8881, "step": 2155008 }, { "epoch": 0.01, "learning_rate": 1.4707592492742553e-05, "loss": 3.8905, "step": 2155520 }, { "epoch": 0.01, "learning_rate": 1.4699206545232033e-05, "loss": 3.8716, "step": 2156032 }, { "epoch": 0.01, "learning_rate": 1.4690820597721513e-05, "loss": 3.8785, "step": 2156544 }, { "epoch": 0.01, "learning_rate": 1.4682434650210991e-05, "loss": 3.8687, "step": 2157056 }, { "epoch": 0.01, "learning_rate": 1.4674048702700471e-05, "loss": 3.8728, "step": 2157568 }, { "epoch": 0.01, "learning_rate": 1.4665662755189951e-05, "loss": 3.8814, "step": 2158080 }, { "epoch": 0.01, "learning_rate": 1.4657276807679433e-05, "loss": 3.8901, "step": 2158592 }, { "epoch": 0.01, "learning_rate": 1.4648890860168913e-05, "loss": 3.8728, "step": 2159104 }, { "epoch": 0.01, "learning_rate": 1.4640504912658393e-05, "loss": 3.8792, "step": 2159616 }, { "epoch": 0.01, "learning_rate": 1.4632135343951603e-05, "loss": 3.8822, "step": 2160128 }, { "epoch": 0.01, "learning_rate": 1.4623749396441083e-05, "loss": 3.8854, "step": 2160640 }, { "epoch": 0.01, "learning_rate": 1.4615363448930563e-05, "loss": 3.8748, "step": 2161152 }, { "epoch": 0.01, "learning_rate": 1.4606977501420043e-05, "loss": 3.8621, "step": 2161664 }, { "epoch": 0.01, "learning_rate": 1.4598591553909525e-05, "loss": 3.8802, "step": 2162176 }, { "epoch": 0.01, "learning_rate": 1.4590205606399002e-05, "loss": 3.896, "step": 2162688 }, { "epoch": 0.01, "learning_rate": 1.4581819658888481e-05, "loss": 3.8926, "step": 2163200 }, { "epoch": 0.01, "learning_rate": 1.4573433711377963e-05, "loss": 3.8731, "step": 2163712 }, { "epoch": 0.01, "learning_rate": 1.4565064142671172e-05, "loss": 3.877, "step": 2164224 }, { "epoch": 0.01, "learning_rate": 1.4556678195160652e-05, "loss": 3.8817, "step": 2164736 }, { "epoch": 0.01, "learning_rate": 1.4548308626453866e-05, "loss": 3.87, "step": 2165248 }, { "epoch": 0.01, "learning_rate": 1.4539922678943346e-05, "loss": 3.8969, "step": 2165760 }, { "epoch": 0.01, "learning_rate": 1.4531536731432825e-05, "loss": 3.8631, "step": 2166272 }, { "epoch": 0.01, "learning_rate": 1.4523150783922305e-05, "loss": 3.9007, "step": 2166784 }, { "epoch": 0.01, "learning_rate": 1.4514764836411784e-05, "loss": 3.8806, "step": 2167296 }, { "epoch": 0.01, "learning_rate": 1.4506378888901264e-05, "loss": 3.8667, "step": 2167808 }, { "epoch": 0.01, "learning_rate": 1.4497992941390744e-05, "loss": 3.8815, "step": 2168320 }, { "epoch": 0.01, "learning_rate": 1.4489606993880226e-05, "loss": 3.879, "step": 2168832 }, { "epoch": 0.01, "learning_rate": 1.4481237425173435e-05, "loss": 3.8621, "step": 2169344 }, { "epoch": 0.01, "learning_rate": 1.4472851477662915e-05, "loss": 3.8839, "step": 2169856 }, { "epoch": 0.01, "learning_rate": 1.4464481908956126e-05, "loss": 3.8858, "step": 2170368 }, { "epoch": 0.01, "learning_rate": 1.4456095961445606e-05, "loss": 3.8743, "step": 2170880 }, { "epoch": 0.01, "learning_rate": 1.4447710013935088e-05, "loss": 3.8828, "step": 2171392 }, { "epoch": 0.01, "learning_rate": 1.4439324066424567e-05, "loss": 3.8588, "step": 2171904 }, { "epoch": 0.01, "learning_rate": 1.4430938118914047e-05, "loss": 3.8767, "step": 2172416 }, { "epoch": 0.01, "learning_rate": 1.4422552171403527e-05, "loss": 3.8734, "step": 2172928 }, { "epoch": 0.01, "learning_rate": 1.4414166223893006e-05, "loss": 3.882, "step": 2173440 }, { "epoch": 0.01, "learning_rate": 1.4405780276382486e-05, "loss": 3.8766, "step": 2173952 }, { "epoch": 0.01, "learning_rate": 1.4397410707675698e-05, "loss": 3.879, "step": 2174464 }, { "epoch": 0.01, "learning_rate": 1.4389041138968909e-05, "loss": 3.8933, "step": 2174976 }, { "epoch": 0.01, "learning_rate": 1.4380655191458389e-05, "loss": 3.8815, "step": 2175488 }, { "epoch": 0.01, "learning_rate": 1.4372269243947869e-05, "loss": 3.8811, "step": 2176000 }, { "epoch": 0.01, "learning_rate": 1.436388329643735e-05, "loss": 3.8787, "step": 2176512 }, { "epoch": 0.01, "learning_rate": 1.4355497348926827e-05, "loss": 3.874, "step": 2177024 }, { "epoch": 0.01, "learning_rate": 1.4347111401416307e-05, "loss": 3.8843, "step": 2177536 }, { "epoch": 0.01, "learning_rate": 1.4338725453905789e-05, "loss": 3.874, "step": 2178048 }, { "epoch": 0.01, "learning_rate": 1.4330339506395269e-05, "loss": 3.884, "step": 2178560 }, { "epoch": 0.01, "learning_rate": 1.432196993768848e-05, "loss": 3.8823, "step": 2179072 }, { "epoch": 0.01, "learning_rate": 1.4313600368981692e-05, "loss": 3.8826, "step": 2179584 }, { "epoch": 0.01, "learning_rate": 1.4305214421471172e-05, "loss": 3.8611, "step": 2180096 }, { "epoch": 0.01, "learning_rate": 1.4296828473960652e-05, "loss": 3.8813, "step": 2180608 }, { "epoch": 0.01, "learning_rate": 1.428844252645013e-05, "loss": 3.8809, "step": 2181120 }, { "epoch": 0.01, "learning_rate": 1.428005657893961e-05, "loss": 3.8702, "step": 2181632 }, { "epoch": 0.01, "learning_rate": 1.4271687010232822e-05, "loss": 3.8804, "step": 2182144 }, { "epoch": 0.01, "learning_rate": 1.42633010627223e-05, "loss": 3.8746, "step": 2182656 }, { "epoch": 0.02, "learning_rate": 1.425491511521178e-05, "loss": 3.8721, "step": 2183168 }, { "epoch": 0.02, "learning_rate": 1.424652916770126e-05, "loss": 3.8737, "step": 2183680 }, { "epoch": 0.02, "learning_rate": 1.4238143220190742e-05, "loss": 3.8745, "step": 2184192 }, { "epoch": 0.02, "learning_rate": 1.4229757272680222e-05, "loss": 3.886, "step": 2184704 }, { "epoch": 0.02, "learning_rate": 1.4221371325169702e-05, "loss": 3.881, "step": 2185216 }, { "epoch": 0.02, "learning_rate": 1.4212985377659182e-05, "loss": 3.8848, "step": 2185728 }, { "epoch": 0.02, "learning_rate": 1.420459943014866e-05, "loss": 3.8751, "step": 2186240 }, { "epoch": 0.02, "learning_rate": 1.4196229861441873e-05, "loss": 3.8747, "step": 2186752 }, { "epoch": 0.02, "learning_rate": 1.4187843913931353e-05, "loss": 3.8795, "step": 2187264 }, { "epoch": 0.02, "learning_rate": 1.4179457966420834e-05, "loss": 3.8856, "step": 2187776 }, { "epoch": 0.02, "learning_rate": 1.4171072018910311e-05, "loss": 3.8842, "step": 2188288 }, { "epoch": 0.02, "learning_rate": 1.4162702450203524e-05, "loss": 3.8808, "step": 2188800 }, { "epoch": 0.02, "learning_rate": 1.4154316502693005e-05, "loss": 3.8782, "step": 2189312 }, { "epoch": 0.02, "learning_rate": 1.4145946933986214e-05, "loss": 3.8723, "step": 2189824 }, { "epoch": 0.02, "learning_rate": 1.4137560986475696e-05, "loss": 3.8822, "step": 2190336 }, { "epoch": 0.02, "learning_rate": 1.4129191417768905e-05, "loss": 3.8755, "step": 2190848 }, { "epoch": 0.02, "learning_rate": 1.4120805470258387e-05, "loss": 3.8764, "step": 2191360 }, { "epoch": 0.02, "learning_rate": 1.4112419522747867e-05, "loss": 3.8732, "step": 2191872 }, { "epoch": 0.02, "learning_rate": 1.4104033575237347e-05, "loss": 3.8759, "step": 2192384 }, { "epoch": 0.02, "learning_rate": 1.4095647627726827e-05, "loss": 3.8744, "step": 2192896 }, { "epoch": 0.02, "learning_rate": 1.4087261680216305e-05, "loss": 3.8724, "step": 2193408 }, { "epoch": 0.02, "learning_rate": 1.4078875732705785e-05, "loss": 3.8645, "step": 2193920 }, { "epoch": 0.02, "learning_rate": 1.4070489785195265e-05, "loss": 3.8781, "step": 2194432 }, { "epoch": 0.02, "learning_rate": 1.4062103837684745e-05, "loss": 3.8834, "step": 2194944 }, { "epoch": 0.02, "learning_rate": 1.4053717890174226e-05, "loss": 3.8735, "step": 2195456 }, { "epoch": 0.02, "learning_rate": 1.4045331942663706e-05, "loss": 3.8857, "step": 2195968 }, { "epoch": 0.02, "learning_rate": 1.4036945995153186e-05, "loss": 3.8936, "step": 2196480 }, { "epoch": 0.02, "learning_rate": 1.4028576426446397e-05, "loss": 3.8764, "step": 2196992 }, { "epoch": 0.02, "learning_rate": 1.4020206857739606e-05, "loss": 3.8752, "step": 2197504 }, { "epoch": 0.02, "learning_rate": 1.4011820910229088e-05, "loss": 3.8751, "step": 2198016 }, { "epoch": 0.02, "learning_rate": 1.4003434962718568e-05, "loss": 3.8787, "step": 2198528 }, { "epoch": 0.02, "learning_rate": 1.3995049015208048e-05, "loss": 3.8778, "step": 2199040 }, { "epoch": 0.02, "learning_rate": 1.3986663067697528e-05, "loss": 3.8728, "step": 2199552 }, { "epoch": 0.02, "learning_rate": 1.3978277120187008e-05, "loss": 3.8736, "step": 2200064 }, { "epoch": 0.02, "learning_rate": 1.3969891172676486e-05, "loss": 3.8837, "step": 2200576 }, { "epoch": 0.02, "learning_rate": 1.3961505225165966e-05, "loss": 3.8747, "step": 2201088 }, { "epoch": 0.02, "learning_rate": 1.3953119277655446e-05, "loss": 3.8811, "step": 2201600 }, { "epoch": 0.02, "learning_rate": 1.394474970894866e-05, "loss": 3.8772, "step": 2202112 }, { "epoch": 0.02, "learning_rate": 1.3936380140241869e-05, "loss": 3.8752, "step": 2202624 }, { "epoch": 0.02, "learning_rate": 1.392799419273135e-05, "loss": 3.8743, "step": 2203136 }, { "epoch": 0.02, "learning_rate": 1.391960824522083e-05, "loss": 3.8898, "step": 2203648 }, { "epoch": 0.02, "learning_rate": 1.391122229771031e-05, "loss": 3.884, "step": 2204160 }, { "epoch": 0.02, "learning_rate": 1.3902852729003521e-05, "loss": 3.8753, "step": 2204672 }, { "epoch": 0.02, "learning_rate": 1.3894466781493001e-05, "loss": 3.8798, "step": 2205184 }, { "epoch": 0.02, "learning_rate": 1.3886080833982481e-05, "loss": 3.891, "step": 2205696 }, { "epoch": 0.02, "learning_rate": 1.387769488647196e-05, "loss": 3.8705, "step": 2206208 }, { "epoch": 0.02, "learning_rate": 1.386930893896144e-05, "loss": 3.8786, "step": 2206720 }, { "epoch": 0.02, "learning_rate": 1.386092299145092e-05, "loss": 3.8812, "step": 2207232 }, { "epoch": 0.02, "learning_rate": 1.3852553422744134e-05, "loss": 3.8888, "step": 2207744 }, { "epoch": 0.02, "learning_rate": 1.384416747523361e-05, "loss": 3.8885, "step": 2208256 }, { "epoch": 0.02, "learning_rate": 1.383578152772309e-05, "loss": 3.8858, "step": 2208768 }, { "epoch": 0.02, "learning_rate": 1.382739558021257e-05, "loss": 3.8779, "step": 2209280 }, { "epoch": 0.02, "learning_rate": 1.3819009632702052e-05, "loss": 3.8864, "step": 2209792 }, { "epoch": 0.02, "learning_rate": 1.3810623685191532e-05, "loss": 3.8785, "step": 2210304 }, { "epoch": 0.02, "learning_rate": 1.3802254116484743e-05, "loss": 3.8701, "step": 2210816 }, { "epoch": 0.02, "learning_rate": 1.3793868168974222e-05, "loss": 3.8779, "step": 2211328 }, { "epoch": 0.02, "learning_rate": 1.3785482221463702e-05, "loss": 3.8672, "step": 2211840 }, { "epoch": 0.02, "learning_rate": 1.3777096273953182e-05, "loss": 3.8798, "step": 2212352 }, { "epoch": 0.02, "learning_rate": 1.3768710326442662e-05, "loss": 3.8764, "step": 2212864 }, { "epoch": 0.03, "eval_loss": 3.9897549152374268, "eval_runtime": 295.1785, "eval_samples_per_second": 1292.747, "eval_steps_per_second": 40.399, "step": 2213280 }, { "epoch": 1.0, "learning_rate": 1.376032437893214e-05, "loss": 3.8778, "step": 2213376 }, { "epoch": 1.0, "learning_rate": 1.375193843142162e-05, "loss": 3.8727, "step": 2213888 }, { "epoch": 1.0, "learning_rate": 1.37435524839111e-05, "loss": 3.8787, "step": 2214400 }, { "epoch": 1.0, "learning_rate": 1.3735166536400582e-05, "loss": 3.8898, "step": 2214912 }, { "epoch": 1.0, "learning_rate": 1.3726796967693791e-05, "loss": 3.8845, "step": 2215424 }, { "epoch": 1.0, "learning_rate": 1.3718411020183273e-05, "loss": 3.8897, "step": 2215936 }, { "epoch": 1.0, "learning_rate": 1.3710025072672753e-05, "loss": 3.8774, "step": 2216448 }, { "epoch": 1.0, "learning_rate": 1.3701639125162233e-05, "loss": 3.877, "step": 2216960 }, { "epoch": 1.0, "learning_rate": 1.3693253177651713e-05, "loss": 3.8655, "step": 2217472 }, { "epoch": 1.0, "learning_rate": 1.3684867230141193e-05, "loss": 3.8834, "step": 2217984 }, { "epoch": 1.0, "learning_rate": 1.3676481282630674e-05, "loss": 3.8801, "step": 2218496 }, { "epoch": 1.0, "learning_rate": 1.3668095335120151e-05, "loss": 3.8797, "step": 2219008 }, { "epoch": 1.0, "learning_rate": 1.3659758524020827e-05, "loss": 3.8904, "step": 2219520 }, { "epoch": 1.0, "learning_rate": 1.3651372576510307e-05, "loss": 3.8626, "step": 2220032 }, { "epoch": 1.0, "learning_rate": 1.3642986628999788e-05, "loss": 3.8728, "step": 2220544 }, { "epoch": 1.0, "learning_rate": 1.3634600681489265e-05, "loss": 3.8663, "step": 2221056 }, { "epoch": 1.0, "learning_rate": 1.3626214733978745e-05, "loss": 3.8791, "step": 2221568 }, { "epoch": 1.0, "learning_rate": 1.3617828786468227e-05, "loss": 3.8787, "step": 2222080 }, { "epoch": 1.0, "learning_rate": 1.3609442838957707e-05, "loss": 3.8733, "step": 2222592 }, { "epoch": 1.0, "learning_rate": 1.3601056891447186e-05, "loss": 3.8842, "step": 2223104 }, { "epoch": 1.0, "learning_rate": 1.3592670943936666e-05, "loss": 3.8878, "step": 2223616 }, { "epoch": 1.0, "learning_rate": 1.3584301375229877e-05, "loss": 3.8835, "step": 2224128 }, { "epoch": 1.0, "learning_rate": 1.3575915427719357e-05, "loss": 3.8797, "step": 2224640 }, { "epoch": 1.0, "learning_rate": 1.3567529480208837e-05, "loss": 3.8758, "step": 2225152 }, { "epoch": 1.0, "learning_rate": 1.3559143532698317e-05, "loss": 3.8884, "step": 2225664 }, { "epoch": 1.0, "learning_rate": 1.3550773963991528e-05, "loss": 3.8782, "step": 2226176 }, { "epoch": 1.0, "learning_rate": 1.3542388016481008e-05, "loss": 3.8718, "step": 2226688 }, { "epoch": 1.0, "learning_rate": 1.353400206897049e-05, "loss": 3.8803, "step": 2227200 }, { "epoch": 1.0, "learning_rate": 1.352561612145997e-05, "loss": 3.8683, "step": 2227712 }, { "epoch": 1.0, "learning_rate": 1.351724655275318e-05, "loss": 3.8761, "step": 2228224 }, { "epoch": 1.01, "learning_rate": 1.350886060524266e-05, "loss": 3.8789, "step": 2228736 }, { "epoch": 1.01, "learning_rate": 1.350047465773214e-05, "loss": 3.8778, "step": 2229248 }, { "epoch": 1.01, "learning_rate": 1.3492088710221618e-05, "loss": 3.8867, "step": 2229760 }, { "epoch": 1.01, "learning_rate": 1.3483702762711098e-05, "loss": 3.888, "step": 2230272 }, { "epoch": 1.01, "learning_rate": 1.3475316815200578e-05, "loss": 3.878, "step": 2230784 }, { "epoch": 1.01, "learning_rate": 1.346694724649379e-05, "loss": 3.8838, "step": 2231296 }, { "epoch": 1.01, "learning_rate": 1.3458561298983269e-05, "loss": 3.8871, "step": 2231808 }, { "epoch": 1.01, "learning_rate": 1.3450191730276482e-05, "loss": 3.8666, "step": 2232320 }, { "epoch": 1.01, "learning_rate": 1.3441805782765962e-05, "loss": 3.8741, "step": 2232832 }, { "epoch": 1.01, "learning_rate": 1.3433419835255443e-05, "loss": 3.8634, "step": 2233344 }, { "epoch": 1.01, "learning_rate": 1.342503388774492e-05, "loss": 3.8715, "step": 2233856 }, { "epoch": 1.01, "learning_rate": 1.34166479402344e-05, "loss": 3.8722, "step": 2234368 }, { "epoch": 1.01, "learning_rate": 1.3408261992723881e-05, "loss": 3.8906, "step": 2234880 }, { "epoch": 1.01, "learning_rate": 1.3399876045213361e-05, "loss": 3.8674, "step": 2235392 }, { "epoch": 1.01, "learning_rate": 1.3391490097702841e-05, "loss": 3.8723, "step": 2235904 }, { "epoch": 1.01, "learning_rate": 1.3383120528996052e-05, "loss": 3.8776, "step": 2236416 }, { "epoch": 1.01, "learning_rate": 1.3374734581485532e-05, "loss": 3.8786, "step": 2236928 }, { "epoch": 1.01, "learning_rate": 1.3366348633975012e-05, "loss": 3.872, "step": 2237440 }, { "epoch": 1.01, "learning_rate": 1.3357962686464492e-05, "loss": 3.8616, "step": 2237952 }, { "epoch": 1.01, "learning_rate": 1.3349576738953974e-05, "loss": 3.88, "step": 2238464 }, { "epoch": 1.01, "learning_rate": 1.334119079144345e-05, "loss": 3.8895, "step": 2238976 }, { "epoch": 1.01, "learning_rate": 1.333280484393293e-05, "loss": 3.8838, "step": 2239488 }, { "epoch": 1.01, "learning_rate": 1.3324418896422412e-05, "loss": 3.8729, "step": 2240000 }, { "epoch": 1.01, "learning_rate": 1.3316049327715624e-05, "loss": 3.8688, "step": 2240512 }, { "epoch": 1.01, "learning_rate": 1.33076633802051e-05, "loss": 3.8813, "step": 2241024 }, { "epoch": 1.01, "learning_rate": 1.3299293811498315e-05, "loss": 3.8642, "step": 2241536 }, { "epoch": 1.01, "learning_rate": 1.3290907863987795e-05, "loss": 3.892, "step": 2242048 }, { "epoch": 1.01, "learning_rate": 1.3282521916477273e-05, "loss": 3.8608, "step": 2242560 }, { "epoch": 1.01, "learning_rate": 1.3274135968966753e-05, "loss": 3.8956, "step": 2243072 }, { "epoch": 1.01, "learning_rate": 1.3265750021456233e-05, "loss": 3.8793, "step": 2243584 }, { "epoch": 1.01, "learning_rate": 1.3257380452749446e-05, "loss": 3.8611, "step": 2244096 }, { "epoch": 1.01, "learning_rate": 1.3248994505238924e-05, "loss": 3.8755, "step": 2244608 }, { "epoch": 1.01, "learning_rate": 1.3240608557728404e-05, "loss": 3.8761, "step": 2245120 }, { "epoch": 1.01, "learning_rate": 1.3232222610217884e-05, "loss": 3.8608, "step": 2245632 }, { "epoch": 1.01, "learning_rate": 1.3223836662707364e-05, "loss": 3.8694, "step": 2246144 }, { "epoch": 1.01, "learning_rate": 1.3215450715196845e-05, "loss": 3.887, "step": 2246656 }, { "epoch": 1.01, "learning_rate": 1.3207064767686325e-05, "loss": 3.8711, "step": 2247168 }, { "epoch": 1.01, "learning_rate": 1.3198678820175805e-05, "loss": 3.8739, "step": 2247680 }, { "epoch": 1.01, "learning_rate": 1.3190325630272745e-05, "loss": 3.8581, "step": 2248192 }, { "epoch": 1.01, "learning_rate": 1.318195606156596e-05, "loss": 3.8731, "step": 2248704 }, { "epoch": 1.01, "learning_rate": 1.317357011405544e-05, "loss": 3.867, "step": 2249216 }, { "epoch": 1.01, "learning_rate": 1.316518416654492e-05, "loss": 3.878, "step": 2249728 }, { "epoch": 1.01, "learning_rate": 1.3156798219034398e-05, "loss": 3.8722, "step": 2250240 }, { "epoch": 1.01, "learning_rate": 1.3148412271523878e-05, "loss": 3.8743, "step": 2250752 }, { "epoch": 1.01, "learning_rate": 1.3140026324013357e-05, "loss": 3.8843, "step": 2251264 }, { "epoch": 1.01, "learning_rate": 1.3131640376502837e-05, "loss": 3.8782, "step": 2251776 }, { "epoch": 1.01, "learning_rate": 1.3123270807796048e-05, "loss": 3.8757, "step": 2252288 }, { "epoch": 1.01, "learning_rate": 1.3114884860285528e-05, "loss": 3.8764, "step": 2252800 }, { "epoch": 1.01, "learning_rate": 1.3106498912775008e-05, "loss": 3.8738, "step": 2253312 }, { "epoch": 1.01, "learning_rate": 1.309811296526449e-05, "loss": 3.8795, "step": 2253824 }, { "epoch": 1.01, "learning_rate": 1.308972701775397e-05, "loss": 3.8706, "step": 2254336 }, { "epoch": 1.01, "learning_rate": 1.308134107024345e-05, "loss": 3.8748, "step": 2254848 }, { "epoch": 1.01, "learning_rate": 1.307297150153666e-05, "loss": 3.8809, "step": 2255360 }, { "epoch": 1.01, "learning_rate": 1.306458555402614e-05, "loss": 3.8769, "step": 2255872 }, { "epoch": 1.01, "learning_rate": 1.305619960651562e-05, "loss": 3.8598, "step": 2256384 }, { "epoch": 1.01, "learning_rate": 1.30478136590051e-05, "loss": 3.8752, "step": 2256896 }, { "epoch": 1.01, "learning_rate": 1.3039427711494579e-05, "loss": 3.8737, "step": 2257408 }, { "epoch": 1.01, "learning_rate": 1.3031041763984059e-05, "loss": 3.8733, "step": 2257920 }, { "epoch": 1.01, "learning_rate": 1.3022655816473539e-05, "loss": 3.8707, "step": 2258432 }, { "epoch": 1.01, "learning_rate": 1.301426986896302e-05, "loss": 3.8781, "step": 2258944 }, { "epoch": 1.02, "learning_rate": 1.30058839214525e-05, "loss": 3.8627, "step": 2259456 }, { "epoch": 1.02, "learning_rate": 1.299749797394198e-05, "loss": 3.8694, "step": 2259968 }, { "epoch": 1.02, "learning_rate": 1.2989128405235191e-05, "loss": 3.8662, "step": 2260480 }, { "epoch": 1.02, "learning_rate": 1.298074245772467e-05, "loss": 3.8833, "step": 2260992 }, { "epoch": 1.02, "learning_rate": 1.297235651021415e-05, "loss": 3.8718, "step": 2261504 }, { "epoch": 1.02, "learning_rate": 1.296397056270363e-05, "loss": 3.8844, "step": 2262016 }, { "epoch": 1.02, "learning_rate": 1.2955584615193109e-05, "loss": 3.8671, "step": 2262528 }, { "epoch": 1.02, "learning_rate": 1.2947198667682589e-05, "loss": 3.8722, "step": 2263040 }, { "epoch": 1.02, "learning_rate": 1.2938812720172069e-05, "loss": 3.8732, "step": 2263552 }, { "epoch": 1.02, "learning_rate": 1.2930443151465283e-05, "loss": 3.8788, "step": 2264064 }, { "epoch": 1.02, "learning_rate": 1.292205720395476e-05, "loss": 3.8782, "step": 2264576 }, { "epoch": 1.02, "learning_rate": 1.291367125644424e-05, "loss": 3.8768, "step": 2265088 }, { "epoch": 1.02, "learning_rate": 1.2905285308933721e-05, "loss": 3.874, "step": 2265600 }, { "epoch": 1.02, "learning_rate": 1.2896899361423201e-05, "loss": 3.8691, "step": 2266112 }, { "epoch": 1.02, "learning_rate": 1.2888513413912681e-05, "loss": 3.8821, "step": 2266624 }, { "epoch": 1.02, "learning_rate": 1.2880127466402161e-05, "loss": 3.8671, "step": 2267136 }, { "epoch": 1.02, "learning_rate": 1.2871757897695372e-05, "loss": 3.8725, "step": 2267648 }, { "epoch": 1.02, "learning_rate": 1.2863371950184852e-05, "loss": 3.8713, "step": 2268160 }, { "epoch": 1.02, "learning_rate": 1.2854986002674332e-05, "loss": 3.8684, "step": 2268672 }, { "epoch": 1.02, "learning_rate": 1.2846616433967543e-05, "loss": 3.8707, "step": 2269184 }, { "epoch": 1.02, "learning_rate": 1.2838230486457023e-05, "loss": 3.8738, "step": 2269696 }, { "epoch": 1.02, "learning_rate": 1.2829844538946503e-05, "loss": 3.8604, "step": 2270208 }, { "epoch": 1.02, "learning_rate": 1.2821458591435984e-05, "loss": 3.874, "step": 2270720 }, { "epoch": 1.02, "learning_rate": 1.2813072643925464e-05, "loss": 3.8773, "step": 2271232 }, { "epoch": 1.02, "learning_rate": 1.280468669641494e-05, "loss": 3.8693, "step": 2271744 }, { "epoch": 1.02, "learning_rate": 1.2796300748904422e-05, "loss": 3.8833, "step": 2272256 }, { "epoch": 1.02, "learning_rate": 1.2787914801393902e-05, "loss": 3.8889, "step": 2272768 }, { "epoch": 1.02, "learning_rate": 1.2779528853883382e-05, "loss": 3.8735, "step": 2273280 }, { "epoch": 1.02, "learning_rate": 1.2771142906372862e-05, "loss": 3.8712, "step": 2273792 }, { "epoch": 1.02, "learning_rate": 1.2762773337666073e-05, "loss": 3.8697, "step": 2274304 }, { "epoch": 1.02, "learning_rate": 1.2754387390155553e-05, "loss": 3.8738, "step": 2274816 }, { "epoch": 1.02, "learning_rate": 1.2746001442645033e-05, "loss": 3.8721, "step": 2275328 }, { "epoch": 1.02, "learning_rate": 1.2737615495134515e-05, "loss": 3.8703, "step": 2275840 }, { "epoch": 1.02, "learning_rate": 1.2729229547623995e-05, "loss": 3.8691, "step": 2276352 }, { "epoch": 1.02, "learning_rate": 1.2720843600113471e-05, "loss": 3.8798, "step": 2276864 }, { "epoch": 1.02, "learning_rate": 1.2712457652602953e-05, "loss": 3.8747, "step": 2277376 }, { "epoch": 1.02, "learning_rate": 1.2704071705092433e-05, "loss": 3.871, "step": 2277888 }, { "epoch": 1.02, "learning_rate": 1.2695702136385645e-05, "loss": 3.8726, "step": 2278400 }, { "epoch": 1.02, "learning_rate": 1.2687332567678856e-05, "loss": 3.8721, "step": 2278912 }, { "epoch": 1.02, "learning_rate": 1.2678946620168336e-05, "loss": 3.8683, "step": 2279424 }, { "epoch": 1.02, "learning_rate": 1.2670560672657816e-05, "loss": 3.8853, "step": 2279936 }, { "epoch": 1.02, "learning_rate": 1.2662174725147294e-05, "loss": 3.8819, "step": 2280448 }, { "epoch": 1.02, "learning_rate": 1.2653788777636774e-05, "loss": 3.8745, "step": 2280960 }, { "epoch": 1.02, "learning_rate": 1.2645402830126254e-05, "loss": 3.8748, "step": 2281472 }, { "epoch": 1.02, "learning_rate": 1.2637033261419468e-05, "loss": 3.8806, "step": 2281984 }, { "epoch": 1.02, "learning_rate": 1.2628647313908945e-05, "loss": 3.8726, "step": 2282496 }, { "epoch": 1.02, "learning_rate": 1.2620261366398425e-05, "loss": 3.8758, "step": 2283008 }, { "epoch": 1.02, "learning_rate": 1.2611875418887906e-05, "loss": 3.8745, "step": 2283520 }, { "epoch": 1.02, "learning_rate": 1.2603489471377386e-05, "loss": 3.892, "step": 2284032 }, { "epoch": 1.02, "learning_rate": 1.2595119902670595e-05, "loss": 3.8764, "step": 2284544 }, { "epoch": 1.02, "learning_rate": 1.2586733955160077e-05, "loss": 3.8827, "step": 2285056 }, { "epoch": 1.02, "learning_rate": 1.2578348007649557e-05, "loss": 3.8736, "step": 2285568 }, { "epoch": 1.02, "learning_rate": 1.2569962060139037e-05, "loss": 3.8847, "step": 2286080 }, { "epoch": 1.02, "learning_rate": 1.2561592491432248e-05, "loss": 3.8749, "step": 2286592 }, { "epoch": 1.02, "learning_rate": 1.2553206543921728e-05, "loss": 3.8663, "step": 2287104 }, { "epoch": 1.02, "learning_rate": 1.2544820596411208e-05, "loss": 3.875, "step": 2287616 }, { "epoch": 1.02, "learning_rate": 1.2536434648900688e-05, "loss": 3.8636, "step": 2288128 }, { "epoch": 1.02, "learning_rate": 1.252804870139017e-05, "loss": 3.8775, "step": 2288640 }, { "epoch": 1.02, "learning_rate": 1.2519679132683378e-05, "loss": 3.8712, "step": 2289152 }, { "epoch": 1.03, "eval_loss": 3.9878368377685547, "eval_runtime": 295.7305, "eval_samples_per_second": 1290.333, "eval_steps_per_second": 40.324, "step": 2289600 }, { "epoch": 0.0, "learning_rate": 1.251129318517286e-05, "loss": 3.869, "step": 2289664 }, { "epoch": 0.0, "learning_rate": 1.250290723766234e-05, "loss": 3.8728, "step": 2290176 }, { "epoch": 0.0, "learning_rate": 1.2494521290151818e-05, "loss": 3.8712, "step": 2290688 }, { "epoch": 0.0, "learning_rate": 1.2486135342641298e-05, "loss": 3.8863, "step": 2291200 }, { "epoch": 0.0, "learning_rate": 1.247774939513078e-05, "loss": 3.8796, "step": 2291712 }, { "epoch": 0.0, "learning_rate": 1.2469363447620258e-05, "loss": 3.8878, "step": 2292224 }, { "epoch": 0.0, "learning_rate": 1.2460977500109738e-05, "loss": 3.8735, "step": 2292736 }, { "epoch": 0.0, "learning_rate": 1.2452591552599218e-05, "loss": 3.8711, "step": 2293248 }, { "epoch": 0.0, "learning_rate": 1.24442056050887e-05, "loss": 3.867, "step": 2293760 }, { "epoch": 0.0, "learning_rate": 1.2435819657578178e-05, "loss": 3.8774, "step": 2294272 }, { "epoch": 0.0, "learning_rate": 1.2427433710067658e-05, "loss": 3.8746, "step": 2294784 }, { "epoch": 0.0, "learning_rate": 1.2419047762557138e-05, "loss": 3.8761, "step": 2295296 }, { "epoch": 0.0, "learning_rate": 1.2410678193850349e-05, "loss": 3.8879, "step": 2295808 }, { "epoch": 0.0, "learning_rate": 1.2402292246339829e-05, "loss": 3.8623, "step": 2296320 }, { "epoch": 0.0, "learning_rate": 1.239390629882931e-05, "loss": 3.8644, "step": 2296832 }, { "epoch": 0.0, "learning_rate": 1.238552035131879e-05, "loss": 3.865, "step": 2297344 }, { "epoch": 0.0, "learning_rate": 1.2377134403808268e-05, "loss": 3.8703, "step": 2297856 }, { "epoch": 0.0, "learning_rate": 1.2368748456297748e-05, "loss": 3.8739, "step": 2298368 }, { "epoch": 0.0, "learning_rate": 1.236036250878723e-05, "loss": 3.873, "step": 2298880 }, { "epoch": 0.0, "learning_rate": 1.2351976561276708e-05, "loss": 3.8773, "step": 2299392 }, { "epoch": 0.0, "learning_rate": 1.2343590613766188e-05, "loss": 3.8831, "step": 2299904 }, { "epoch": 0.0, "learning_rate": 1.23352210450594e-05, "loss": 3.8763, "step": 2300416 }, { "epoch": 0.0, "learning_rate": 1.2326835097548879e-05, "loss": 3.8784, "step": 2300928 }, { "epoch": 0.0, "learning_rate": 1.2318449150038359e-05, "loss": 3.8709, "step": 2301440 }, { "epoch": 0.0, "learning_rate": 1.2310063202527839e-05, "loss": 3.8847, "step": 2301952 }, { "epoch": 0.0, "learning_rate": 1.230167725501732e-05, "loss": 3.8745, "step": 2302464 }, { "epoch": 0.0, "learning_rate": 1.229330768631053e-05, "loss": 3.8699, "step": 2302976 }, { "epoch": 0.0, "learning_rate": 1.2284921738800011e-05, "loss": 3.8718, "step": 2303488 }, { "epoch": 0.0, "learning_rate": 1.2276535791289491e-05, "loss": 3.8657, "step": 2304000 }, { "epoch": 0.0, "learning_rate": 1.226814984377897e-05, "loss": 3.8717, "step": 2304512 }, { "epoch": 0.01, "learning_rate": 1.225976389626845e-05, "loss": 3.8747, "step": 2305024 }, { "epoch": 0.01, "learning_rate": 1.2251394327561662e-05, "loss": 3.8758, "step": 2305536 }, { "epoch": 0.01, "learning_rate": 1.2243008380051142e-05, "loss": 3.8835, "step": 2306048 }, { "epoch": 0.01, "learning_rate": 1.2234622432540622e-05, "loss": 3.8838, "step": 2306560 }, { "epoch": 0.01, "learning_rate": 1.2226236485030102e-05, "loss": 3.8737, "step": 2307072 }, { "epoch": 0.01, "learning_rate": 1.2217866916323313e-05, "loss": 3.8804, "step": 2307584 }, { "epoch": 0.01, "learning_rate": 1.2209480968812793e-05, "loss": 3.8776, "step": 2308096 }, { "epoch": 0.01, "learning_rate": 1.2201111400106003e-05, "loss": 3.867, "step": 2308608 }, { "epoch": 0.01, "learning_rate": 1.2192725452595483e-05, "loss": 3.8715, "step": 2309120 }, { "epoch": 0.01, "learning_rate": 1.2184339505084965e-05, "loss": 3.8577, "step": 2309632 }, { "epoch": 0.01, "learning_rate": 1.2175953557574443e-05, "loss": 3.8696, "step": 2310144 }, { "epoch": 0.01, "learning_rate": 1.2167567610063923e-05, "loss": 3.8692, "step": 2310656 }, { "epoch": 0.01, "learning_rate": 1.2159181662553403e-05, "loss": 3.8844, "step": 2311168 }, { "epoch": 0.01, "learning_rate": 1.2150795715042885e-05, "loss": 3.8616, "step": 2311680 }, { "epoch": 0.01, "learning_rate": 1.2142409767532363e-05, "loss": 3.8683, "step": 2312192 }, { "epoch": 0.01, "learning_rate": 1.2134023820021843e-05, "loss": 3.877, "step": 2312704 }, { "epoch": 0.01, "learning_rate": 1.2125637872511323e-05, "loss": 3.8744, "step": 2313216 }, { "epoch": 0.01, "learning_rate": 1.2117251925000803e-05, "loss": 3.8739, "step": 2313728 }, { "epoch": 0.01, "learning_rate": 1.2108882356294014e-05, "loss": 3.8527, "step": 2314240 }, { "epoch": 0.01, "learning_rate": 1.2100496408783495e-05, "loss": 3.8731, "step": 2314752 }, { "epoch": 0.01, "learning_rate": 1.2092110461272975e-05, "loss": 3.8847, "step": 2315264 }, { "epoch": 0.01, "learning_rate": 1.2083724513762454e-05, "loss": 3.8824, "step": 2315776 }, { "epoch": 0.01, "learning_rate": 1.2075338566251934e-05, "loss": 3.8688, "step": 2316288 }, { "epoch": 0.01, "learning_rate": 1.2066952618741415e-05, "loss": 3.8655, "step": 2316800 }, { "epoch": 0.01, "learning_rate": 1.2058566671230894e-05, "loss": 3.8769, "step": 2317312 }, { "epoch": 0.01, "learning_rate": 1.2050213481327837e-05, "loss": 3.863, "step": 2317824 }, { "epoch": 0.01, "learning_rate": 1.2041827533817317e-05, "loss": 3.8855, "step": 2318336 }, { "epoch": 0.01, "learning_rate": 1.2033441586306797e-05, "loss": 3.8563, "step": 2318848 }, { "epoch": 0.01, "learning_rate": 1.2025055638796277e-05, "loss": 3.8923, "step": 2319360 }, { "epoch": 0.01, "learning_rate": 1.2016669691285757e-05, "loss": 3.877, "step": 2319872 }, { "epoch": 0.01, "learning_rate": 1.2008283743775237e-05, "loss": 3.8556, "step": 2320384 }, { "epoch": 0.01, "learning_rate": 1.1999897796264715e-05, "loss": 3.8685, "step": 2320896 }, { "epoch": 0.01, "learning_rate": 1.1991511848754197e-05, "loss": 3.8776, "step": 2321408 }, { "epoch": 0.01, "learning_rate": 1.1983125901243676e-05, "loss": 3.8549, "step": 2321920 }, { "epoch": 0.01, "learning_rate": 1.1974756332536887e-05, "loss": 3.8634, "step": 2322432 }, { "epoch": 0.01, "learning_rate": 1.1966370385026367e-05, "loss": 3.8836, "step": 2322944 }, { "epoch": 0.01, "learning_rate": 1.1957984437515847e-05, "loss": 3.8703, "step": 2323456 }, { "epoch": 0.01, "learning_rate": 1.1949598490005327e-05, "loss": 3.8682, "step": 2323968 }, { "epoch": 0.01, "learning_rate": 1.1941212542494807e-05, "loss": 3.8517, "step": 2324480 }, { "epoch": 0.01, "learning_rate": 1.1932842973788018e-05, "loss": 3.869, "step": 2324992 }, { "epoch": 0.01, "learning_rate": 1.1924457026277498e-05, "loss": 3.8628, "step": 2325504 }, { "epoch": 0.01, "learning_rate": 1.191608745757071e-05, "loss": 3.8784, "step": 2326016 }, { "epoch": 0.01, "learning_rate": 1.1907701510060189e-05, "loss": 3.8635, "step": 2326528 }, { "epoch": 0.01, "learning_rate": 1.1899315562549669e-05, "loss": 3.8744, "step": 2327040 }, { "epoch": 0.01, "learning_rate": 1.189092961503915e-05, "loss": 3.8793, "step": 2327552 }, { "epoch": 0.01, "learning_rate": 1.188254366752863e-05, "loss": 3.8772, "step": 2328064 }, { "epoch": 0.01, "learning_rate": 1.1874157720018108e-05, "loss": 3.87, "step": 2328576 }, { "epoch": 0.01, "learning_rate": 1.1865771772507588e-05, "loss": 3.869, "step": 2329088 }, { "epoch": 0.01, "learning_rate": 1.185738582499707e-05, "loss": 3.8727, "step": 2329600 }, { "epoch": 0.01, "learning_rate": 1.1848999877486548e-05, "loss": 3.8762, "step": 2330112 }, { "epoch": 0.01, "learning_rate": 1.1840613929976028e-05, "loss": 3.8672, "step": 2330624 }, { "epoch": 0.01, "learning_rate": 1.1832227982465508e-05, "loss": 3.8707, "step": 2331136 }, { "epoch": 0.01, "learning_rate": 1.1823842034954988e-05, "loss": 3.8744, "step": 2331648 }, { "epoch": 0.01, "learning_rate": 1.1815456087444468e-05, "loss": 3.873, "step": 2332160 }, { "epoch": 0.01, "learning_rate": 1.180708651873768e-05, "loss": 3.8567, "step": 2332672 }, { "epoch": 0.01, "learning_rate": 1.179870057122716e-05, "loss": 3.8719, "step": 2333184 }, { "epoch": 0.01, "learning_rate": 1.179033100252037e-05, "loss": 3.8689, "step": 2333696 }, { "epoch": 0.01, "learning_rate": 1.1781945055009851e-05, "loss": 3.8692, "step": 2334208 }, { "epoch": 0.01, "learning_rate": 1.1773559107499331e-05, "loss": 3.87, "step": 2334720 }, { "epoch": 0.01, "learning_rate": 1.1765173159988811e-05, "loss": 3.8727, "step": 2335232 }, { "epoch": 0.02, "learning_rate": 1.175678721247829e-05, "loss": 3.8628, "step": 2335744 }, { "epoch": 0.02, "learning_rate": 1.1748417643771502e-05, "loss": 3.8609, "step": 2336256 }, { "epoch": 0.02, "learning_rate": 1.1740031696260982e-05, "loss": 3.8631, "step": 2336768 }, { "epoch": 0.02, "learning_rate": 1.1731645748750462e-05, "loss": 3.8793, "step": 2337280 }, { "epoch": 0.02, "learning_rate": 1.1723259801239942e-05, "loss": 3.8687, "step": 2337792 }, { "epoch": 0.02, "learning_rate": 1.1714890232533153e-05, "loss": 3.8779, "step": 2338304 }, { "epoch": 0.02, "learning_rate": 1.1706504285022633e-05, "loss": 3.8666, "step": 2338816 }, { "epoch": 0.02, "learning_rate": 1.1698118337512113e-05, "loss": 3.8698, "step": 2339328 }, { "epoch": 0.02, "learning_rate": 1.1689748768805323e-05, "loss": 3.8652, "step": 2339840 }, { "epoch": 0.02, "learning_rate": 1.1681362821294805e-05, "loss": 3.88, "step": 2340352 }, { "epoch": 0.02, "learning_rate": 1.1672976873784283e-05, "loss": 3.8728, "step": 2340864 }, { "epoch": 0.02, "learning_rate": 1.1664590926273763e-05, "loss": 3.8752, "step": 2341376 }, { "epoch": 0.02, "learning_rate": 1.1656204978763243e-05, "loss": 3.8702, "step": 2341888 }, { "epoch": 0.02, "learning_rate": 1.1647819031252725e-05, "loss": 3.8634, "step": 2342400 }, { "epoch": 0.02, "learning_rate": 1.1639433083742203e-05, "loss": 3.8824, "step": 2342912 }, { "epoch": 0.02, "learning_rate": 1.1631047136231683e-05, "loss": 3.8584, "step": 2343424 }, { "epoch": 0.02, "learning_rate": 1.1622661188721163e-05, "loss": 3.8663, "step": 2343936 }, { "epoch": 0.02, "learning_rate": 1.1614291620014374e-05, "loss": 3.8721, "step": 2344448 }, { "epoch": 0.02, "learning_rate": 1.1605905672503854e-05, "loss": 3.863, "step": 2344960 }, { "epoch": 0.02, "learning_rate": 1.1597519724993335e-05, "loss": 3.8657, "step": 2345472 }, { "epoch": 0.02, "learning_rate": 1.1589133777482815e-05, "loss": 3.8697, "step": 2345984 }, { "epoch": 0.02, "learning_rate": 1.1580747829972294e-05, "loss": 3.8598, "step": 2346496 }, { "epoch": 0.02, "learning_rate": 1.1572361882461774e-05, "loss": 3.8706, "step": 2347008 }, { "epoch": 0.02, "learning_rate": 1.1563975934951255e-05, "loss": 3.8687, "step": 2347520 }, { "epoch": 0.02, "learning_rate": 1.1555589987440733e-05, "loss": 3.869, "step": 2348032 }, { "epoch": 0.02, "learning_rate": 1.1547220418733944e-05, "loss": 3.8802, "step": 2348544 }, { "epoch": 0.02, "learning_rate": 1.1538850850027157e-05, "loss": 3.8845, "step": 2349056 }, { "epoch": 0.02, "learning_rate": 1.1530464902516637e-05, "loss": 3.8726, "step": 2349568 }, { "epoch": 0.02, "learning_rate": 1.1522078955006117e-05, "loss": 3.8684, "step": 2350080 }, { "epoch": 0.02, "learning_rate": 1.1513693007495597e-05, "loss": 3.8667, "step": 2350592 }, { "epoch": 0.02, "learning_rate": 1.1505307059985077e-05, "loss": 3.8712, "step": 2351104 }, { "epoch": 0.02, "learning_rate": 1.1496921112474555e-05, "loss": 3.8683, "step": 2351616 }, { "epoch": 0.02, "learning_rate": 1.1488535164964036e-05, "loss": 3.8687, "step": 2352128 }, { "epoch": 0.02, "learning_rate": 1.1480149217453516e-05, "loss": 3.8621, "step": 2352640 }, { "epoch": 0.02, "learning_rate": 1.1471779648746727e-05, "loss": 3.878, "step": 2353152 }, { "epoch": 0.02, "learning_rate": 1.1463393701236207e-05, "loss": 3.8693, "step": 2353664 }, { "epoch": 0.02, "learning_rate": 1.1455007753725687e-05, "loss": 3.8714, "step": 2354176 }, { "epoch": 0.02, "learning_rate": 1.1446621806215167e-05, "loss": 3.8706, "step": 2354688 }, { "epoch": 0.02, "learning_rate": 1.143826861631211e-05, "loss": 3.8654, "step": 2355200 }, { "epoch": 0.02, "learning_rate": 1.1429882668801589e-05, "loss": 3.8652, "step": 2355712 }, { "epoch": 0.02, "learning_rate": 1.142149672129107e-05, "loss": 3.8811, "step": 2356224 }, { "epoch": 0.02, "learning_rate": 1.141311077378055e-05, "loss": 3.8778, "step": 2356736 }, { "epoch": 0.02, "learning_rate": 1.1404724826270028e-05, "loss": 3.8752, "step": 2357248 }, { "epoch": 0.02, "learning_rate": 1.1396338878759508e-05, "loss": 3.8664, "step": 2357760 }, { "epoch": 0.02, "learning_rate": 1.138795293124899e-05, "loss": 3.8761, "step": 2358272 }, { "epoch": 0.02, "learning_rate": 1.137956698373847e-05, "loss": 3.8719, "step": 2358784 }, { "epoch": 0.02, "learning_rate": 1.1371181036227948e-05, "loss": 3.871, "step": 2359296 }, { "epoch": 0.02, "learning_rate": 1.1362795088717428e-05, "loss": 3.8752, "step": 2359808 }, { "epoch": 0.02, "learning_rate": 1.135440914120691e-05, "loss": 3.8824, "step": 2360320 }, { "epoch": 0.02, "learning_rate": 1.1346039572500119e-05, "loss": 3.8751, "step": 2360832 }, { "epoch": 0.02, "learning_rate": 1.1337653624989599e-05, "loss": 3.8826, "step": 2361344 }, { "epoch": 0.02, "learning_rate": 1.132926767747908e-05, "loss": 3.8711, "step": 2361856 }, { "epoch": 0.02, "learning_rate": 1.132088172996856e-05, "loss": 3.8763, "step": 2362368 }, { "epoch": 0.02, "learning_rate": 1.1312495782458039e-05, "loss": 3.8674, "step": 2362880 }, { "epoch": 0.02, "learning_rate": 1.1304126213751251e-05, "loss": 3.8662, "step": 2363392 }, { "epoch": 0.02, "learning_rate": 1.1295740266240731e-05, "loss": 3.8735, "step": 2363904 }, { "epoch": 0.02, "learning_rate": 1.128735431873021e-05, "loss": 3.8583, "step": 2364416 }, { "epoch": 0.02, "learning_rate": 1.1278968371219691e-05, "loss": 3.8719, "step": 2364928 }, { "epoch": 0.02, "learning_rate": 1.1270582423709171e-05, "loss": 3.8703, "step": 2365440 }, { "epoch": 0.03, "eval_loss": 3.9871666431427, "eval_runtime": 303.1151, "eval_samples_per_second": 1258.898, "eval_steps_per_second": 39.341, "step": 2365920 }, { "epoch": 0.0, "learning_rate": 1.1262196476198651e-05, "loss": 3.8689, "step": 2365952 }, { "epoch": 0.0, "learning_rate": 1.125381052868813e-05, "loss": 3.8688, "step": 2366464 }, { "epoch": 0.0, "learning_rate": 1.1245424581177611e-05, "loss": 3.8675, "step": 2366976 }, { "epoch": 0.0, "learning_rate": 1.1237038633667091e-05, "loss": 3.8815, "step": 2367488 }, { "epoch": 0.0, "learning_rate": 1.122865268615657e-05, "loss": 3.8764, "step": 2368000 }, { "epoch": 0.0, "learning_rate": 1.122026673864605e-05, "loss": 3.8835, "step": 2368512 }, { "epoch": 0.0, "learning_rate": 1.1211897169939262e-05, "loss": 3.8689, "step": 2369024 }, { "epoch": 0.0, "learning_rate": 1.1203511222428742e-05, "loss": 3.8701, "step": 2369536 }, { "epoch": 0.0, "learning_rate": 1.1195125274918222e-05, "loss": 3.8608, "step": 2370048 }, { "epoch": 0.0, "learning_rate": 1.1186739327407702e-05, "loss": 3.8769, "step": 2370560 }, { "epoch": 0.0, "learning_rate": 1.1178353379897181e-05, "loss": 3.8717, "step": 2371072 }, { "epoch": 0.0, "learning_rate": 1.116996743238666e-05, "loss": 3.873, "step": 2371584 }, { "epoch": 0.0, "learning_rate": 1.1161581484876141e-05, "loss": 3.879, "step": 2372096 }, { "epoch": 0.0, "learning_rate": 1.1153195537365621e-05, "loss": 3.8631, "step": 2372608 }, { "epoch": 0.0, "learning_rate": 1.11448095898551e-05, "loss": 3.8655, "step": 2373120 }, { "epoch": 0.0, "learning_rate": 1.113642364234458e-05, "loss": 3.8621, "step": 2373632 }, { "epoch": 0.0, "learning_rate": 1.1128037694834061e-05, "loss": 3.861, "step": 2374144 }, { "epoch": 0.0, "learning_rate": 1.111965174732354e-05, "loss": 3.8687, "step": 2374656 }, { "epoch": 0.0, "learning_rate": 1.111126579981302e-05, "loss": 3.8712, "step": 2375168 }, { "epoch": 0.0, "learning_rate": 1.11028798523025e-05, "loss": 3.8715, "step": 2375680 }, { "epoch": 0.0, "learning_rate": 1.1094510283595712e-05, "loss": 3.8848, "step": 2376192 }, { "epoch": 0.0, "learning_rate": 1.108612433608519e-05, "loss": 3.8719, "step": 2376704 }, { "epoch": 0.0, "learning_rate": 1.1077738388574672e-05, "loss": 3.8748, "step": 2377216 }, { "epoch": 0.0, "learning_rate": 1.1069352441064152e-05, "loss": 3.8718, "step": 2377728 }, { "epoch": 0.0, "learning_rate": 1.106096649355363e-05, "loss": 3.8815, "step": 2378240 }, { "epoch": 0.0, "learning_rate": 1.105258054604311e-05, "loss": 3.8678, "step": 2378752 }, { "epoch": 0.0, "learning_rate": 1.1044194598532592e-05, "loss": 3.8696, "step": 2379264 }, { "epoch": 0.0, "learning_rate": 1.1035808651022072e-05, "loss": 3.8644, "step": 2379776 }, { "epoch": 0.0, "learning_rate": 1.102742270351155e-05, "loss": 3.8674, "step": 2380288 }, { "epoch": 0.0, "learning_rate": 1.101903675600103e-05, "loss": 3.8696, "step": 2380800 }, { "epoch": 0.01, "learning_rate": 1.1010667187294242e-05, "loss": 3.8697, "step": 2381312 }, { "epoch": 0.01, "learning_rate": 1.100228123978372e-05, "loss": 3.8752, "step": 2381824 }, { "epoch": 0.01, "learning_rate": 1.0993895292273202e-05, "loss": 3.8788, "step": 2382336 }, { "epoch": 0.01, "learning_rate": 1.0985509344762682e-05, "loss": 3.8746, "step": 2382848 }, { "epoch": 0.01, "learning_rate": 1.0977123397252162e-05, "loss": 3.8728, "step": 2383360 }, { "epoch": 0.01, "learning_rate": 1.0968753828545373e-05, "loss": 3.878, "step": 2383872 }, { "epoch": 0.01, "learning_rate": 1.0960367881034853e-05, "loss": 3.8755, "step": 2384384 }, { "epoch": 0.01, "learning_rate": 1.0951998312328064e-05, "loss": 3.8589, "step": 2384896 }, { "epoch": 0.01, "learning_rate": 1.0943612364817545e-05, "loss": 3.8722, "step": 2385408 }, { "epoch": 0.01, "learning_rate": 1.0935226417307024e-05, "loss": 3.8524, "step": 2385920 }, { "epoch": 0.01, "learning_rate": 1.0926840469796503e-05, "loss": 3.8675, "step": 2386432 }, { "epoch": 0.01, "learning_rate": 1.0918454522285983e-05, "loss": 3.864, "step": 2386944 }, { "epoch": 0.01, "learning_rate": 1.0910068574775463e-05, "loss": 3.8828, "step": 2387456 }, { "epoch": 0.01, "learning_rate": 1.0901682627264943e-05, "loss": 3.8642, "step": 2387968 }, { "epoch": 0.01, "learning_rate": 1.0893296679754423e-05, "loss": 3.8626, "step": 2388480 }, { "epoch": 0.01, "learning_rate": 1.0884927111047636e-05, "loss": 3.8714, "step": 2388992 }, { "epoch": 0.01, "learning_rate": 1.0876541163537114e-05, "loss": 3.8729, "step": 2389504 }, { "epoch": 0.01, "learning_rate": 1.0868155216026594e-05, "loss": 3.8687, "step": 2390016 }, { "epoch": 0.01, "learning_rate": 1.0859769268516076e-05, "loss": 3.8512, "step": 2390528 }, { "epoch": 0.01, "learning_rate": 1.0851399699809285e-05, "loss": 3.8677, "step": 2391040 }, { "epoch": 0.01, "learning_rate": 1.0843013752298765e-05, "loss": 3.8827, "step": 2391552 }, { "epoch": 0.01, "learning_rate": 1.0834627804788246e-05, "loss": 3.8783, "step": 2392064 }, { "epoch": 0.01, "learning_rate": 1.0826241857277726e-05, "loss": 3.8687, "step": 2392576 }, { "epoch": 0.01, "learning_rate": 1.0817855909767205e-05, "loss": 3.8629, "step": 2393088 }, { "epoch": 0.01, "learning_rate": 1.0809469962256685e-05, "loss": 3.8742, "step": 2393600 }, { "epoch": 0.01, "learning_rate": 1.0801084014746166e-05, "loss": 3.8567, "step": 2394112 }, { "epoch": 0.01, "learning_rate": 1.0792714446039375e-05, "loss": 3.8826, "step": 2394624 }, { "epoch": 0.01, "learning_rate": 1.0784328498528857e-05, "loss": 3.8519, "step": 2395136 }, { "epoch": 0.01, "learning_rate": 1.0775942551018337e-05, "loss": 3.8839, "step": 2395648 }, { "epoch": 0.01, "learning_rate": 1.0767556603507817e-05, "loss": 3.8773, "step": 2396160 }, { "epoch": 0.01, "learning_rate": 1.0759170655997295e-05, "loss": 3.854, "step": 2396672 }, { "epoch": 0.01, "learning_rate": 1.0750784708486777e-05, "loss": 3.8671, "step": 2397184 }, { "epoch": 0.01, "learning_rate": 1.0742398760976257e-05, "loss": 3.8742, "step": 2397696 }, { "epoch": 0.01, "learning_rate": 1.0734029192269466e-05, "loss": 3.8468, "step": 2398208 }, { "epoch": 0.01, "learning_rate": 1.0725643244758947e-05, "loss": 3.8634, "step": 2398720 }, { "epoch": 0.01, "learning_rate": 1.0717273676052158e-05, "loss": 3.8781, "step": 2399232 }, { "epoch": 0.01, "learning_rate": 1.0708887728541638e-05, "loss": 3.869, "step": 2399744 }, { "epoch": 0.01, "learning_rate": 1.0700501781031118e-05, "loss": 3.8646, "step": 2400256 }, { "epoch": 0.01, "learning_rate": 1.0692132212324329e-05, "loss": 3.8539, "step": 2400768 }, { "epoch": 0.01, "learning_rate": 1.068374626481381e-05, "loss": 3.8672, "step": 2401280 }, { "epoch": 0.01, "learning_rate": 1.067536031730329e-05, "loss": 3.8584, "step": 2401792 }, { "epoch": 0.01, "learning_rate": 1.0666974369792769e-05, "loss": 3.8734, "step": 2402304 }, { "epoch": 0.01, "learning_rate": 1.0658588422282249e-05, "loss": 3.8597, "step": 2402816 }, { "epoch": 0.01, "learning_rate": 1.065020247477173e-05, "loss": 3.8722, "step": 2403328 }, { "epoch": 0.01, "learning_rate": 1.0641816527261209e-05, "loss": 3.8762, "step": 2403840 }, { "epoch": 0.01, "learning_rate": 1.0633430579750689e-05, "loss": 3.8713, "step": 2404352 }, { "epoch": 0.01, "learning_rate": 1.0625061011043901e-05, "loss": 3.8675, "step": 2404864 }, { "epoch": 0.01, "learning_rate": 1.0616675063533381e-05, "loss": 3.8655, "step": 2405376 }, { "epoch": 0.01, "learning_rate": 1.060828911602286e-05, "loss": 3.8727, "step": 2405888 }, { "epoch": 0.01, "learning_rate": 1.059990316851234e-05, "loss": 3.8711, "step": 2406400 }, { "epoch": 0.01, "learning_rate": 1.0591533599805552e-05, "loss": 3.8652, "step": 2406912 }, { "epoch": 0.01, "learning_rate": 1.058314765229503e-05, "loss": 3.8641, "step": 2407424 }, { "epoch": 0.01, "learning_rate": 1.0574761704784512e-05, "loss": 3.8726, "step": 2407936 }, { "epoch": 0.01, "learning_rate": 1.0566375757273992e-05, "loss": 3.8715, "step": 2408448 }, { "epoch": 0.01, "learning_rate": 1.055798980976347e-05, "loss": 3.8541, "step": 2408960 }, { "epoch": 0.01, "learning_rate": 1.054960386225295e-05, "loss": 3.8672, "step": 2409472 }, { "epoch": 0.01, "learning_rate": 1.0541217914742432e-05, "loss": 3.8661, "step": 2409984 }, { "epoch": 0.01, "learning_rate": 1.0532831967231911e-05, "loss": 3.8684, "step": 2410496 }, { "epoch": 0.01, "learning_rate": 1.0524462398525122e-05, "loss": 3.8686, "step": 2411008 }, { "epoch": 0.01, "learning_rate": 1.0516076451014602e-05, "loss": 3.8658, "step": 2411520 }, { "epoch": 0.02, "learning_rate": 1.0507690503504082e-05, "loss": 3.8627, "step": 2412032 }, { "epoch": 0.02, "learning_rate": 1.049930455599356e-05, "loss": 3.8567, "step": 2412544 }, { "epoch": 0.02, "learning_rate": 1.0490934987286773e-05, "loss": 3.8608, "step": 2413056 }, { "epoch": 0.02, "learning_rate": 1.0482549039776253e-05, "loss": 3.876, "step": 2413568 }, { "epoch": 0.02, "learning_rate": 1.0474163092265733e-05, "loss": 3.8664, "step": 2414080 }, { "epoch": 0.02, "learning_rate": 1.0465777144755213e-05, "loss": 3.8768, "step": 2414592 }, { "epoch": 0.02, "learning_rate": 1.0457391197244693e-05, "loss": 3.8649, "step": 2415104 }, { "epoch": 0.02, "learning_rate": 1.0449005249734173e-05, "loss": 3.8639, "step": 2415616 }, { "epoch": 0.02, "learning_rate": 1.0440619302223651e-05, "loss": 3.8617, "step": 2416128 }, { "epoch": 0.02, "learning_rate": 1.0432233354713133e-05, "loss": 3.8776, "step": 2416640 }, { "epoch": 0.02, "learning_rate": 1.0423847407202613e-05, "loss": 3.8662, "step": 2417152 }, { "epoch": 0.02, "learning_rate": 1.0415477838495823e-05, "loss": 3.8758, "step": 2417664 }, { "epoch": 0.02, "learning_rate": 1.0407108269789034e-05, "loss": 3.8639, "step": 2418176 }, { "epoch": 0.02, "learning_rate": 1.0398722322278514e-05, "loss": 3.8607, "step": 2418688 }, { "epoch": 0.02, "learning_rate": 1.0390336374767996e-05, "loss": 3.8804, "step": 2419200 }, { "epoch": 0.02, "learning_rate": 1.0381950427257476e-05, "loss": 3.8601, "step": 2419712 }, { "epoch": 0.02, "learning_rate": 1.0373564479746954e-05, "loss": 3.8613, "step": 2420224 }, { "epoch": 0.02, "learning_rate": 1.0365178532236434e-05, "loss": 3.8685, "step": 2420736 }, { "epoch": 0.02, "learning_rate": 1.0356792584725916e-05, "loss": 3.8658, "step": 2421248 }, { "epoch": 0.02, "learning_rate": 1.0348406637215394e-05, "loss": 3.8592, "step": 2421760 }, { "epoch": 0.02, "learning_rate": 1.0340020689704874e-05, "loss": 3.8648, "step": 2422272 }, { "epoch": 0.02, "learning_rate": 1.0331634742194354e-05, "loss": 3.8558, "step": 2422784 }, { "epoch": 0.02, "learning_rate": 1.0323248794683834e-05, "loss": 3.8671, "step": 2423296 }, { "epoch": 0.02, "learning_rate": 1.0314862847173314e-05, "loss": 3.8684, "step": 2423808 }, { "epoch": 0.02, "learning_rate": 1.0306493278466524e-05, "loss": 3.8679, "step": 2424320 }, { "epoch": 0.02, "learning_rate": 1.0298107330956006e-05, "loss": 3.8727, "step": 2424832 }, { "epoch": 0.02, "learning_rate": 1.0289721383445484e-05, "loss": 3.8857, "step": 2425344 }, { "epoch": 0.02, "learning_rate": 1.0281335435934964e-05, "loss": 3.8685, "step": 2425856 }, { "epoch": 0.02, "learning_rate": 1.0272949488424444e-05, "loss": 3.8649, "step": 2426368 }, { "epoch": 0.02, "learning_rate": 1.0264563540913924e-05, "loss": 3.8594, "step": 2426880 }, { "epoch": 0.02, "learning_rate": 1.0256177593403404e-05, "loss": 3.864, "step": 2427392 }, { "epoch": 0.02, "learning_rate": 1.0247808024696617e-05, "loss": 3.8628, "step": 2427904 }, { "epoch": 0.02, "learning_rate": 1.0239422077186097e-05, "loss": 3.8662, "step": 2428416 }, { "epoch": 0.02, "learning_rate": 1.0231052508479307e-05, "loss": 3.8602, "step": 2428928 }, { "epoch": 0.02, "learning_rate": 1.0222666560968787e-05, "loss": 3.875, "step": 2429440 }, { "epoch": 0.02, "learning_rate": 1.0214280613458267e-05, "loss": 3.8665, "step": 2429952 }, { "epoch": 0.02, "learning_rate": 1.0205894665947747e-05, "loss": 3.8688, "step": 2430464 }, { "epoch": 0.02, "learning_rate": 1.0197508718437227e-05, "loss": 3.8641, "step": 2430976 }, { "epoch": 0.02, "learning_rate": 1.0189122770926707e-05, "loss": 3.8639, "step": 2431488 }, { "epoch": 0.02, "learning_rate": 1.0180753202219918e-05, "loss": 3.8594, "step": 2432000 }, { "epoch": 0.02, "learning_rate": 1.0172367254709398e-05, "loss": 3.8766, "step": 2432512 }, { "epoch": 0.02, "learning_rate": 1.0163981307198878e-05, "loss": 3.8793, "step": 2433024 }, { "epoch": 0.02, "learning_rate": 1.0155595359688358e-05, "loss": 3.8747, "step": 2433536 }, { "epoch": 0.02, "learning_rate": 1.0147209412177838e-05, "loss": 3.8631, "step": 2434048 }, { "epoch": 0.02, "learning_rate": 1.0138823464667318e-05, "loss": 3.87, "step": 2434560 }, { "epoch": 0.02, "learning_rate": 1.0130437517156798e-05, "loss": 3.8721, "step": 2435072 }, { "epoch": 0.02, "learning_rate": 1.0122051569646278e-05, "loss": 3.8675, "step": 2435584 }, { "epoch": 0.02, "learning_rate": 1.0113665622135756e-05, "loss": 3.8708, "step": 2436096 }, { "epoch": 0.02, "learning_rate": 1.0105279674625238e-05, "loss": 3.8777, "step": 2436608 }, { "epoch": 0.02, "learning_rate": 1.0096910105918448e-05, "loss": 3.8685, "step": 2437120 }, { "epoch": 0.02, "learning_rate": 1.0088524158407928e-05, "loss": 3.8823, "step": 2437632 }, { "epoch": 0.02, "learning_rate": 1.0080138210897408e-05, "loss": 3.8618, "step": 2438144 }, { "epoch": 0.02, "learning_rate": 1.0071752263386888e-05, "loss": 3.8755, "step": 2438656 }, { "epoch": 0.02, "learning_rate": 1.00633826946801e-05, "loss": 3.8675, "step": 2439168 }, { "epoch": 0.02, "learning_rate": 1.0054996747169579e-05, "loss": 3.8574, "step": 2439680 }, { "epoch": 0.02, "learning_rate": 1.0046610799659059e-05, "loss": 3.8703, "step": 2440192 }, { "epoch": 0.02, "learning_rate": 1.0038224852148539e-05, "loss": 3.8593, "step": 2440704 }, { "epoch": 0.02, "learning_rate": 1.002983890463802e-05, "loss": 3.8654, "step": 2441216 }, { "epoch": 0.02, "learning_rate": 1.002146933593123e-05, "loss": 3.8701, "step": 2441728 }, { "epoch": 0.03, "learning_rate": 1.001308338842071e-05, "loss": 3.8647, "step": 2442240 }, { "epoch": 0.03, "eval_loss": 3.9861438274383545, "eval_runtime": 333.803, "eval_samples_per_second": 1143.162, "eval_steps_per_second": 35.725, "step": 2442240 }, { "epoch": 1.0, "learning_rate": 1.0004697440910191e-05, "loss": 3.8644, "step": 2442752 }, { "epoch": 1.0, "learning_rate": 9.99631149339967e-06, "loss": 3.8667, "step": 2443264 }, { "epoch": 1.0, "learning_rate": 9.98792554588915e-06, "loss": 3.8765, "step": 2443776 }, { "epoch": 1.0, "learning_rate": 9.979555977182362e-06, "loss": 3.8732, "step": 2444288 }, { "epoch": 1.0, "learning_rate": 9.971170029671842e-06, "loss": 3.8841, "step": 2444800 }, { "epoch": 1.0, "learning_rate": 9.962800460965053e-06, "loss": 3.8653, "step": 2445312 }, { "epoch": 1.0, "learning_rate": 9.954414513454533e-06, "loss": 3.8615, "step": 2445824 }, { "epoch": 1.0, "learning_rate": 9.946028565944013e-06, "loss": 3.8627, "step": 2446336 }, { "epoch": 1.0, "learning_rate": 9.937642618433491e-06, "loss": 3.8727, "step": 2446848 }, { "epoch": 1.0, "learning_rate": 9.929256670922973e-06, "loss": 3.8675, "step": 2447360 }, { "epoch": 1.0, "learning_rate": 9.920870723412452e-06, "loss": 3.8719, "step": 2447872 }, { "epoch": 1.0, "learning_rate": 9.912484775901932e-06, "loss": 3.8705, "step": 2448384 }, { "epoch": 1.0, "learning_rate": 9.904115207195143e-06, "loss": 3.8605, "step": 2448896 }, { "epoch": 1.0, "learning_rate": 9.895729259684623e-06, "loss": 3.8665, "step": 2449408 }, { "epoch": 1.0, "learning_rate": 9.887343312174103e-06, "loss": 3.8603, "step": 2449920 }, { "epoch": 1.0, "learning_rate": 9.878957364663583e-06, "loss": 3.859, "step": 2450432 }, { "epoch": 1.0, "learning_rate": 9.870587795956794e-06, "loss": 3.8663, "step": 2450944 }, { "epoch": 1.0, "learning_rate": 9.862201848446274e-06, "loss": 3.8678, "step": 2451456 }, { "epoch": 1.0, "learning_rate": 9.853815900935755e-06, "loss": 3.8678, "step": 2451968 }, { "epoch": 1.0, "learning_rate": 9.845429953425234e-06, "loss": 3.8838, "step": 2452480 }, { "epoch": 1.0, "learning_rate": 9.837044005914714e-06, "loss": 3.867, "step": 2452992 }, { "epoch": 1.0, "learning_rate": 9.828658058404194e-06, "loss": 3.8714, "step": 2453504 }, { "epoch": 1.0, "learning_rate": 9.820272110893674e-06, "loss": 3.8673, "step": 2454016 }, { "epoch": 1.0, "learning_rate": 9.811886163383154e-06, "loss": 3.8761, "step": 2454528 }, { "epoch": 1.0, "learning_rate": 9.803500215872634e-06, "loss": 3.8665, "step": 2455040 }, { "epoch": 1.0, "learning_rate": 9.795130647165846e-06, "loss": 3.868, "step": 2455552 }, { "epoch": 1.0, "learning_rate": 9.786744699655324e-06, "loss": 3.8614, "step": 2456064 }, { "epoch": 1.0, "learning_rate": 9.778358752144804e-06, "loss": 3.866, "step": 2456576 }, { "epoch": 1.0, "learning_rate": 9.769972804634286e-06, "loss": 3.8603, "step": 2457088 }, { "epoch": 1.01, "learning_rate": 9.761586857123764e-06, "loss": 3.8669, "step": 2457600 }, { "epoch": 1.01, "learning_rate": 9.753200909613244e-06, "loss": 3.873, "step": 2458112 }, { "epoch": 1.01, "learning_rate": 9.744814962102724e-06, "loss": 3.8715, "step": 2458624 }, { "epoch": 1.01, "learning_rate": 9.736429014592206e-06, "loss": 3.8727, "step": 2459136 }, { "epoch": 1.01, "learning_rate": 9.728059445885415e-06, "loss": 3.8694, "step": 2459648 }, { "epoch": 1.01, "learning_rate": 9.719689877178627e-06, "loss": 3.8685, "step": 2460160 }, { "epoch": 1.01, "learning_rate": 9.711303929668107e-06, "loss": 3.8769, "step": 2460672 }, { "epoch": 1.01, "learning_rate": 9.702934360961318e-06, "loss": 3.8591, "step": 2461184 }, { "epoch": 1.01, "learning_rate": 9.694548413450798e-06, "loss": 3.8657, "step": 2461696 }, { "epoch": 1.01, "learning_rate": 9.686162465940278e-06, "loss": 3.8532, "step": 2462208 }, { "epoch": 1.01, "learning_rate": 9.677776518429758e-06, "loss": 3.8621, "step": 2462720 }, { "epoch": 1.01, "learning_rate": 9.669390570919238e-06, "loss": 3.8609, "step": 2463232 }, { "epoch": 1.01, "learning_rate": 9.661004623408718e-06, "loss": 3.8748, "step": 2463744 }, { "epoch": 1.01, "learning_rate": 9.652618675898198e-06, "loss": 3.8623, "step": 2464256 }, { "epoch": 1.01, "learning_rate": 9.64424910719141e-06, "loss": 3.86, "step": 2464768 }, { "epoch": 1.01, "learning_rate": 9.635863159680889e-06, "loss": 3.8701, "step": 2465280 }, { "epoch": 1.01, "learning_rate": 9.627477212170368e-06, "loss": 3.87, "step": 2465792 }, { "epoch": 1.01, "learning_rate": 9.619091264659848e-06, "loss": 3.8617, "step": 2466304 }, { "epoch": 1.01, "learning_rate": 9.610705317149328e-06, "loss": 3.8527, "step": 2466816 }, { "epoch": 1.01, "learning_rate": 9.602319369638808e-06, "loss": 3.8579, "step": 2467328 }, { "epoch": 1.01, "learning_rate": 9.593933422128288e-06, "loss": 3.8799, "step": 2467840 }, { "epoch": 1.01, "learning_rate": 9.585547474617768e-06, "loss": 3.878, "step": 2468352 }, { "epoch": 1.01, "learning_rate": 9.577161527107248e-06, "loss": 3.8613, "step": 2468864 }, { "epoch": 1.01, "learning_rate": 9.568775579596728e-06, "loss": 3.8623, "step": 2469376 }, { "epoch": 1.01, "learning_rate": 9.560389632086208e-06, "loss": 3.8718, "step": 2469888 }, { "epoch": 1.01, "learning_rate": 9.552020063379419e-06, "loss": 3.8561, "step": 2470400 }, { "epoch": 1.01, "learning_rate": 9.543634115868899e-06, "loss": 3.874, "step": 2470912 }, { "epoch": 1.01, "learning_rate": 9.535248168358379e-06, "loss": 3.8508, "step": 2471424 }, { "epoch": 1.01, "learning_rate": 9.52686222084786e-06, "loss": 3.8817, "step": 2471936 }, { "epoch": 1.01, "learning_rate": 9.518476273337339e-06, "loss": 3.8711, "step": 2472448 }, { "epoch": 1.01, "learning_rate": 9.510090325826819e-06, "loss": 3.86, "step": 2472960 }, { "epoch": 1.01, "learning_rate": 9.501704378316299e-06, "loss": 3.857, "step": 2473472 }, { "epoch": 1.01, "learning_rate": 9.493318430805779e-06, "loss": 3.8752, "step": 2473984 }, { "epoch": 1.01, "learning_rate": 9.48494886209899e-06, "loss": 3.8443, "step": 2474496 }, { "epoch": 1.01, "learning_rate": 9.476579293392202e-06, "loss": 3.8584, "step": 2475008 }, { "epoch": 1.01, "learning_rate": 9.468193345881682e-06, "loss": 3.874, "step": 2475520 }, { "epoch": 1.01, "learning_rate": 9.45980739837116e-06, "loss": 3.8676, "step": 2476032 }, { "epoch": 1.01, "learning_rate": 9.451421450860642e-06, "loss": 3.863, "step": 2476544 }, { "epoch": 1.01, "learning_rate": 9.443035503350122e-06, "loss": 3.8512, "step": 2477056 }, { "epoch": 1.01, "learning_rate": 9.4346495558396e-06, "loss": 3.8586, "step": 2477568 }, { "epoch": 1.01, "learning_rate": 9.426279987132812e-06, "loss": 3.8549, "step": 2478080 }, { "epoch": 1.01, "learning_rate": 9.417894039622292e-06, "loss": 3.8766, "step": 2478592 }, { "epoch": 1.01, "learning_rate": 9.409508092111772e-06, "loss": 3.8568, "step": 2479104 }, { "epoch": 1.01, "learning_rate": 9.401122144601252e-06, "loss": 3.8708, "step": 2479616 }, { "epoch": 1.01, "learning_rate": 9.392736197090732e-06, "loss": 3.8678, "step": 2480128 }, { "epoch": 1.01, "learning_rate": 9.384350249580212e-06, "loss": 3.8754, "step": 2480640 }, { "epoch": 1.01, "learning_rate": 9.37596430206969e-06, "loss": 3.8601, "step": 2481152 }, { "epoch": 1.01, "learning_rate": 9.367578354559172e-06, "loss": 3.8645, "step": 2481664 }, { "epoch": 1.01, "learning_rate": 9.359208785852383e-06, "loss": 3.8685, "step": 2482176 }, { "epoch": 1.01, "learning_rate": 9.350822838341863e-06, "loss": 3.8685, "step": 2482688 }, { "epoch": 1.01, "learning_rate": 9.342436890831343e-06, "loss": 3.8617, "step": 2483200 }, { "epoch": 1.01, "learning_rate": 9.334050943320823e-06, "loss": 3.8625, "step": 2483712 }, { "epoch": 1.01, "learning_rate": 9.325697753417766e-06, "loss": 3.8679, "step": 2484224 }, { "epoch": 1.01, "learning_rate": 9.317311805907246e-06, "loss": 3.8651, "step": 2484736 }, { "epoch": 1.01, "learning_rate": 9.308925858396724e-06, "loss": 3.8561, "step": 2485248 }, { "epoch": 1.01, "learning_rate": 9.300539910886206e-06, "loss": 3.861, "step": 2485760 }, { "epoch": 1.01, "learning_rate": 9.292153963375686e-06, "loss": 3.8651, "step": 2486272 }, { "epoch": 1.01, "learning_rate": 9.283768015865164e-06, "loss": 3.8665, "step": 2486784 }, { "epoch": 1.01, "learning_rate": 9.275398447158377e-06, "loss": 3.8609, "step": 2487296 }, { "epoch": 1.01, "learning_rate": 9.267012499647857e-06, "loss": 3.8633, "step": 2487808 }, { "epoch": 1.02, "learning_rate": 9.258626552137337e-06, "loss": 3.859, "step": 2488320 }, { "epoch": 1.02, "learning_rate": 9.250240604626815e-06, "loss": 3.8541, "step": 2488832 }, { "epoch": 1.02, "learning_rate": 9.241854657116296e-06, "loss": 3.8585, "step": 2489344 }, { "epoch": 1.02, "learning_rate": 9.233468709605776e-06, "loss": 3.8702, "step": 2489856 }, { "epoch": 1.02, "learning_rate": 9.225082762095255e-06, "loss": 3.8624, "step": 2490368 }, { "epoch": 1.02, "learning_rate": 9.216713193388467e-06, "loss": 3.8749, "step": 2490880 }, { "epoch": 1.02, "learning_rate": 9.208327245877947e-06, "loss": 3.8692, "step": 2491392 }, { "epoch": 1.02, "learning_rate": 9.199941298367427e-06, "loss": 3.8551, "step": 2491904 }, { "epoch": 1.02, "learning_rate": 9.191555350856907e-06, "loss": 3.8604, "step": 2492416 }, { "epoch": 1.02, "learning_rate": 9.183185782150118e-06, "loss": 3.8716, "step": 2492928 }, { "epoch": 1.02, "learning_rate": 9.174799834639598e-06, "loss": 3.8701, "step": 2493440 }, { "epoch": 1.02, "learning_rate": 9.166413887129078e-06, "loss": 3.8706, "step": 2493952 }, { "epoch": 1.02, "learning_rate": 9.158027939618558e-06, "loss": 3.8611, "step": 2494464 }, { "epoch": 1.02, "learning_rate": 9.149641992108038e-06, "loss": 3.8598, "step": 2494976 }, { "epoch": 1.02, "learning_rate": 9.141256044597518e-06, "loss": 3.8752, "step": 2495488 }, { "epoch": 1.02, "learning_rate": 9.132870097086998e-06, "loss": 3.854, "step": 2496000 }, { "epoch": 1.02, "learning_rate": 9.124484149576478e-06, "loss": 3.8623, "step": 2496512 }, { "epoch": 1.02, "learning_rate": 9.116098202065957e-06, "loss": 3.8634, "step": 2497024 }, { "epoch": 1.02, "learning_rate": 9.1077450121629e-06, "loss": 3.8649, "step": 2497536 }, { "epoch": 1.02, "learning_rate": 9.099359064652379e-06, "loss": 3.8545, "step": 2498048 }, { "epoch": 1.02, "learning_rate": 9.09097311714186e-06, "loss": 3.8615, "step": 2498560 }, { "epoch": 1.02, "learning_rate": 9.08258716963134e-06, "loss": 3.855, "step": 2499072 }, { "epoch": 1.02, "learning_rate": 9.074201222120819e-06, "loss": 3.8655, "step": 2499584 }, { "epoch": 1.02, "learning_rate": 9.065815274610299e-06, "loss": 3.8615, "step": 2500096 }, { "epoch": 1.02, "learning_rate": 9.05742932709978e-06, "loss": 3.8606, "step": 2500608 }, { "epoch": 1.02, "learning_rate": 9.049043379589259e-06, "loss": 3.8734, "step": 2501120 }, { "epoch": 1.02, "learning_rate": 9.040657432078739e-06, "loss": 3.8816, "step": 2501632 }, { "epoch": 1.02, "learning_rate": 9.032287863371951e-06, "loss": 3.8664, "step": 2502144 }, { "epoch": 1.02, "learning_rate": 9.023901915861431e-06, "loss": 3.8592, "step": 2502656 }, { "epoch": 1.02, "learning_rate": 9.015532347154642e-06, "loss": 3.8582, "step": 2503168 }, { "epoch": 1.02, "learning_rate": 9.007146399644122e-06, "loss": 3.8576, "step": 2503680 }, { "epoch": 1.02, "learning_rate": 8.998760452133602e-06, "loss": 3.8653, "step": 2504192 }, { "epoch": 1.02, "learning_rate": 8.990374504623082e-06, "loss": 3.8641, "step": 2504704 }, { "epoch": 1.02, "learning_rate": 8.981988557112562e-06, "loss": 3.8559, "step": 2505216 }, { "epoch": 1.02, "learning_rate": 8.973618988405773e-06, "loss": 3.8679, "step": 2505728 }, { "epoch": 1.02, "learning_rate": 8.965233040895253e-06, "loss": 3.8649, "step": 2506240 }, { "epoch": 1.02, "learning_rate": 8.956847093384733e-06, "loss": 3.8664, "step": 2506752 }, { "epoch": 1.02, "learning_rate": 8.948461145874212e-06, "loss": 3.862, "step": 2507264 }, { "epoch": 1.02, "learning_rate": 8.940075198363692e-06, "loss": 3.8612, "step": 2507776 }, { "epoch": 1.02, "learning_rate": 8.931689250853172e-06, "loss": 3.859, "step": 2508288 }, { "epoch": 1.02, "learning_rate": 8.923303303342652e-06, "loss": 3.8732, "step": 2508800 }, { "epoch": 1.02, "learning_rate": 8.914933734635863e-06, "loss": 3.874, "step": 2509312 }, { "epoch": 1.02, "learning_rate": 8.906547787125343e-06, "loss": 3.8718, "step": 2509824 }, { "epoch": 1.02, "learning_rate": 8.898161839614823e-06, "loss": 3.856, "step": 2510336 }, { "epoch": 1.02, "learning_rate": 8.889775892104303e-06, "loss": 3.8714, "step": 2510848 }, { "epoch": 1.02, "learning_rate": 8.881406323397515e-06, "loss": 3.8659, "step": 2511360 }, { "epoch": 1.02, "learning_rate": 8.873020375886995e-06, "loss": 3.8685, "step": 2511872 }, { "epoch": 1.02, "learning_rate": 8.864634428376474e-06, "loss": 3.8617, "step": 2512384 }, { "epoch": 1.02, "learning_rate": 8.856248480865954e-06, "loss": 3.8764, "step": 2512896 }, { "epoch": 1.02, "learning_rate": 8.847878912159166e-06, "loss": 3.8639, "step": 2513408 }, { "epoch": 1.02, "learning_rate": 8.839492964648646e-06, "loss": 3.8818, "step": 2513920 }, { "epoch": 1.02, "learning_rate": 8.831107017138126e-06, "loss": 3.8595, "step": 2514432 }, { "epoch": 1.02, "learning_rate": 8.822721069627606e-06, "loss": 3.8761, "step": 2514944 }, { "epoch": 1.02, "learning_rate": 8.814335122117086e-06, "loss": 3.8641, "step": 2515456 }, { "epoch": 1.02, "learning_rate": 8.805949174606564e-06, "loss": 3.8595, "step": 2515968 }, { "epoch": 1.02, "learning_rate": 8.797563227096046e-06, "loss": 3.8656, "step": 2516480 }, { "epoch": 1.02, "learning_rate": 8.789177279585526e-06, "loss": 3.8567, "step": 2516992 }, { "epoch": 1.02, "learning_rate": 8.780807710878735e-06, "loss": 3.8631, "step": 2517504 }, { "epoch": 1.02, "learning_rate": 8.772438142171947e-06, "loss": 3.8647, "step": 2518016 }, { "epoch": 1.02, "learning_rate": 8.764052194661427e-06, "loss": 3.859, "step": 2518528 }, { "epoch": 1.03, "eval_loss": 3.9857332706451416, "eval_runtime": 335.9763, "eval_samples_per_second": 1135.768, "eval_steps_per_second": 35.494, "step": 2518560 }, { "epoch": 0.0, "learning_rate": 8.755666247150907e-06, "loss": 3.8634, "step": 2519040 }, { "epoch": 0.0, "learning_rate": 8.747280299640387e-06, "loss": 3.8622, "step": 2519552 }, { "epoch": 0.0, "learning_rate": 8.738894352129867e-06, "loss": 3.8739, "step": 2520064 }, { "epoch": 0.0, "learning_rate": 8.730508404619347e-06, "loss": 3.8698, "step": 2520576 }, { "epoch": 0.0, "learning_rate": 8.722122457108827e-06, "loss": 3.8794, "step": 2521088 }, { "epoch": 0.0, "learning_rate": 8.713736509598307e-06, "loss": 3.8619, "step": 2521600 }, { "epoch": 0.0, "learning_rate": 8.705350562087787e-06, "loss": 3.8628, "step": 2522112 }, { "epoch": 0.0, "learning_rate": 8.696964614577267e-06, "loss": 3.8579, "step": 2522624 }, { "epoch": 0.0, "learning_rate": 8.688578667066747e-06, "loss": 3.8682, "step": 2523136 }, { "epoch": 0.0, "learning_rate": 8.680192719556227e-06, "loss": 3.864, "step": 2523648 }, { "epoch": 0.0, "learning_rate": 8.671806772045707e-06, "loss": 3.8646, "step": 2524160 }, { "epoch": 0.0, "learning_rate": 8.663420824535185e-06, "loss": 3.8714, "step": 2524672 }, { "epoch": 0.0, "learning_rate": 8.655051255828398e-06, "loss": 3.8557, "step": 2525184 }, { "epoch": 0.0, "learning_rate": 8.646665308317878e-06, "loss": 3.865, "step": 2525696 }, { "epoch": 0.0, "learning_rate": 8.638279360807358e-06, "loss": 3.8559, "step": 2526208 }, { "epoch": 0.0, "learning_rate": 8.629893413296837e-06, "loss": 3.8575, "step": 2526720 }, { "epoch": 0.0, "learning_rate": 8.621507465786317e-06, "loss": 3.8634, "step": 2527232 }, { "epoch": 0.0, "learning_rate": 8.613121518275797e-06, "loss": 3.8617, "step": 2527744 }, { "epoch": 0.0, "learning_rate": 8.604735570765277e-06, "loss": 3.8649, "step": 2528256 }, { "epoch": 0.0, "learning_rate": 8.596349623254757e-06, "loss": 3.8852, "step": 2528768 }, { "epoch": 0.0, "learning_rate": 8.587963675744237e-06, "loss": 3.8602, "step": 2529280 }, { "epoch": 0.0, "learning_rate": 8.579577728233716e-06, "loss": 3.8669, "step": 2529792 }, { "epoch": 0.0, "learning_rate": 8.571191780723197e-06, "loss": 3.867, "step": 2530304 }, { "epoch": 0.0, "learning_rate": 8.562805833212677e-06, "loss": 3.8709, "step": 2530816 }, { "epoch": 0.0, "learning_rate": 8.554436264505888e-06, "loss": 3.8679, "step": 2531328 }, { "epoch": 0.0, "learning_rate": 8.546050316995368e-06, "loss": 3.8683, "step": 2531840 }, { "epoch": 0.0, "learning_rate": 8.537664369484848e-06, "loss": 3.8548, "step": 2532352 }, { "epoch": 0.0, "learning_rate": 8.529278421974328e-06, "loss": 3.865, "step": 2532864 }, { "epoch": 0.0, "learning_rate": 8.52090885326754e-06, "loss": 3.8554, "step": 2533376 }, { "epoch": 0.01, "learning_rate": 8.512522905757019e-06, "loss": 3.8693, "step": 2533888 }, { "epoch": 0.01, "learning_rate": 8.504153337050231e-06, "loss": 3.8656, "step": 2534400 }, { "epoch": 0.01, "learning_rate": 8.495767389539711e-06, "loss": 3.8716, "step": 2534912 }, { "epoch": 0.01, "learning_rate": 8.48738144202919e-06, "loss": 3.8739, "step": 2535424 }, { "epoch": 0.01, "learning_rate": 8.47899549451867e-06, "loss": 3.8645, "step": 2535936 }, { "epoch": 0.01, "learning_rate": 8.470625925811882e-06, "loss": 3.8698, "step": 2536448 }, { "epoch": 0.01, "learning_rate": 8.462239978301362e-06, "loss": 3.8686, "step": 2536960 }, { "epoch": 0.01, "learning_rate": 8.453870409594572e-06, "loss": 3.8594, "step": 2537472 }, { "epoch": 0.01, "learning_rate": 8.445484462084052e-06, "loss": 3.8605, "step": 2537984 }, { "epoch": 0.01, "learning_rate": 8.437098514573532e-06, "loss": 3.8483, "step": 2538496 }, { "epoch": 0.01, "learning_rate": 8.428712567063012e-06, "loss": 3.8582, "step": 2539008 }, { "epoch": 0.01, "learning_rate": 8.420326619552492e-06, "loss": 3.8616, "step": 2539520 }, { "epoch": 0.01, "learning_rate": 8.411940672041972e-06, "loss": 3.8728, "step": 2540032 }, { "epoch": 0.01, "learning_rate": 8.403554724531452e-06, "loss": 3.8608, "step": 2540544 }, { "epoch": 0.01, "learning_rate": 8.395168777020932e-06, "loss": 3.8586, "step": 2541056 }, { "epoch": 0.01, "learning_rate": 8.386782829510412e-06, "loss": 3.8674, "step": 2541568 }, { "epoch": 0.01, "learning_rate": 8.378413260803623e-06, "loss": 3.8625, "step": 2542080 }, { "epoch": 0.01, "learning_rate": 8.370027313293105e-06, "loss": 3.8628, "step": 2542592 }, { "epoch": 0.01, "learning_rate": 8.361641365782583e-06, "loss": 3.8522, "step": 2543104 }, { "epoch": 0.01, "learning_rate": 8.353271797075794e-06, "loss": 3.8532, "step": 2543616 }, { "epoch": 0.01, "learning_rate": 8.344885849565275e-06, "loss": 3.8778, "step": 2544128 }, { "epoch": 0.01, "learning_rate": 8.336499902054753e-06, "loss": 3.8744, "step": 2544640 }, { "epoch": 0.01, "learning_rate": 8.328113954544233e-06, "loss": 3.8558, "step": 2545152 }, { "epoch": 0.01, "learning_rate": 8.319728007033713e-06, "loss": 3.8614, "step": 2545664 }, { "epoch": 0.01, "learning_rate": 8.311342059523195e-06, "loss": 3.8692, "step": 2546176 }, { "epoch": 0.01, "learning_rate": 8.302972490816404e-06, "loss": 3.8539, "step": 2546688 }, { "epoch": 0.01, "learning_rate": 8.294586543305886e-06, "loss": 3.8731, "step": 2547200 }, { "epoch": 0.01, "learning_rate": 8.286200595795366e-06, "loss": 3.8479, "step": 2547712 }, { "epoch": 0.01, "learning_rate": 8.277814648284844e-06, "loss": 3.8778, "step": 2548224 }, { "epoch": 0.01, "learning_rate": 8.269428700774324e-06, "loss": 3.8691, "step": 2548736 }, { "epoch": 0.01, "learning_rate": 8.261042753263806e-06, "loss": 3.8565, "step": 2549248 }, { "epoch": 0.01, "learning_rate": 8.252673184557016e-06, "loss": 3.8547, "step": 2549760 }, { "epoch": 0.01, "learning_rate": 8.244287237046495e-06, "loss": 3.871, "step": 2550272 }, { "epoch": 0.01, "learning_rate": 8.235901289535976e-06, "loss": 3.8389, "step": 2550784 }, { "epoch": 0.01, "learning_rate": 8.227515342025456e-06, "loss": 3.8594, "step": 2551296 }, { "epoch": 0.01, "learning_rate": 8.219129394514935e-06, "loss": 3.8703, "step": 2551808 }, { "epoch": 0.01, "learning_rate": 8.210743447004416e-06, "loss": 3.8659, "step": 2552320 }, { "epoch": 0.01, "learning_rate": 8.202357499493896e-06, "loss": 3.8573, "step": 2552832 }, { "epoch": 0.01, "learning_rate": 8.193971551983374e-06, "loss": 3.8478, "step": 2553344 }, { "epoch": 0.01, "learning_rate": 8.185585604472854e-06, "loss": 3.8559, "step": 2553856 }, { "epoch": 0.01, "learning_rate": 8.177199656962336e-06, "loss": 3.8548, "step": 2554368 }, { "epoch": 0.01, "learning_rate": 8.168830088255547e-06, "loss": 3.866, "step": 2554880 }, { "epoch": 0.01, "learning_rate": 8.160444140745025e-06, "loss": 3.8566, "step": 2555392 }, { "epoch": 0.01, "learning_rate": 8.152058193234507e-06, "loss": 3.8664, "step": 2555904 }, { "epoch": 0.01, "learning_rate": 8.143672245723987e-06, "loss": 3.8689, "step": 2556416 }, { "epoch": 0.01, "learning_rate": 8.135286298213465e-06, "loss": 3.8721, "step": 2556928 }, { "epoch": 0.01, "learning_rate": 8.126900350702945e-06, "loss": 3.857, "step": 2557440 }, { "epoch": 0.01, "learning_rate": 8.118514403192427e-06, "loss": 3.8626, "step": 2557952 }, { "epoch": 0.01, "learning_rate": 8.110128455681906e-06, "loss": 3.8669, "step": 2558464 }, { "epoch": 0.01, "learning_rate": 8.101758886975117e-06, "loss": 3.8637, "step": 2558976 }, { "epoch": 0.01, "learning_rate": 8.093372939464597e-06, "loss": 3.8623, "step": 2559488 }, { "epoch": 0.01, "learning_rate": 8.084986991954077e-06, "loss": 3.8597, "step": 2560000 }, { "epoch": 0.01, "learning_rate": 8.076601044443555e-06, "loss": 3.8668, "step": 2560512 }, { "epoch": 0.01, "learning_rate": 8.068215096933037e-06, "loss": 3.8636, "step": 2561024 }, { "epoch": 0.01, "learning_rate": 8.059845528226248e-06, "loss": 3.8486, "step": 2561536 }, { "epoch": 0.01, "learning_rate": 8.051459580715728e-06, "loss": 3.8574, "step": 2562048 }, { "epoch": 0.01, "learning_rate": 8.043073633205208e-06, "loss": 3.86, "step": 2562560 }, { "epoch": 0.01, "learning_rate": 8.034687685694688e-06, "loss": 3.8674, "step": 2563072 }, { "epoch": 0.01, "learning_rate": 8.026318116987899e-06, "loss": 3.8618, "step": 2563584 }, { "epoch": 0.01, "learning_rate": 8.017948548281111e-06, "loss": 3.8577, "step": 2564096 }, { "epoch": 0.02, "learning_rate": 8.00956260077059e-06, "loss": 3.8558, "step": 2564608 }, { "epoch": 0.02, "learning_rate": 8.001176653260071e-06, "loss": 3.8508, "step": 2565120 }, { "epoch": 0.02, "learning_rate": 7.992790705749551e-06, "loss": 3.8514, "step": 2565632 }, { "epoch": 0.02, "learning_rate": 7.98440475823903e-06, "loss": 3.8662, "step": 2566144 }, { "epoch": 0.02, "learning_rate": 7.976051568335972e-06, "loss": 3.8627, "step": 2566656 }, { "epoch": 0.02, "learning_rate": 7.967665620825452e-06, "loss": 3.8696, "step": 2567168 }, { "epoch": 0.02, "learning_rate": 7.959279673314932e-06, "loss": 3.8653, "step": 2567680 }, { "epoch": 0.02, "learning_rate": 7.950893725804412e-06, "loss": 3.8563, "step": 2568192 }, { "epoch": 0.02, "learning_rate": 7.942507778293892e-06, "loss": 3.8569, "step": 2568704 }, { "epoch": 0.02, "learning_rate": 7.934121830783372e-06, "loss": 3.8619, "step": 2569216 }, { "epoch": 0.02, "learning_rate": 7.925735883272852e-06, "loss": 3.8704, "step": 2569728 }, { "epoch": 0.02, "learning_rate": 7.917349935762332e-06, "loss": 3.8675, "step": 2570240 }, { "epoch": 0.02, "learning_rate": 7.908963988251812e-06, "loss": 3.8594, "step": 2570752 }, { "epoch": 0.02, "learning_rate": 7.900578040741292e-06, "loss": 3.8536, "step": 2571264 }, { "epoch": 0.02, "learning_rate": 7.892192093230772e-06, "loss": 3.8729, "step": 2571776 }, { "epoch": 0.02, "learning_rate": 7.883822524523983e-06, "loss": 3.8515, "step": 2572288 }, { "epoch": 0.02, "learning_rate": 7.875436577013463e-06, "loss": 3.861, "step": 2572800 }, { "epoch": 0.02, "learning_rate": 7.867050629502944e-06, "loss": 3.8613, "step": 2573312 }, { "epoch": 0.02, "learning_rate": 7.858664681992423e-06, "loss": 3.8614, "step": 2573824 }, { "epoch": 0.02, "learning_rate": 7.850278734481903e-06, "loss": 3.85, "step": 2574336 }, { "epoch": 0.02, "learning_rate": 7.841892786971383e-06, "loss": 3.8628, "step": 2574848 }, { "epoch": 0.02, "learning_rate": 7.833506839460863e-06, "loss": 3.8494, "step": 2575360 }, { "epoch": 0.02, "learning_rate": 7.825120891950343e-06, "loss": 3.8588, "step": 2575872 }, { "epoch": 0.02, "learning_rate": 7.816751323243553e-06, "loss": 3.8608, "step": 2576384 }, { "epoch": 0.02, "learning_rate": 7.808381754536766e-06, "loss": 3.8558, "step": 2576896 }, { "epoch": 0.02, "learning_rate": 7.799995807026244e-06, "loss": 3.8745, "step": 2577408 }, { "epoch": 0.02, "learning_rate": 7.791609859515726e-06, "loss": 3.8764, "step": 2577920 }, { "epoch": 0.02, "learning_rate": 7.783223912005206e-06, "loss": 3.8668, "step": 2578432 }, { "epoch": 0.02, "learning_rate": 7.774837964494684e-06, "loss": 3.8584, "step": 2578944 }, { "epoch": 0.02, "learning_rate": 7.766468395787896e-06, "loss": 3.8536, "step": 2579456 }, { "epoch": 0.02, "learning_rate": 7.758082448277376e-06, "loss": 3.8587, "step": 2579968 }, { "epoch": 0.02, "learning_rate": 7.749696500766856e-06, "loss": 3.8552, "step": 2580480 }, { "epoch": 0.02, "learning_rate": 7.741310553256336e-06, "loss": 3.8695, "step": 2580992 }, { "epoch": 0.02, "learning_rate": 7.732924605745816e-06, "loss": 3.8493, "step": 2581504 }, { "epoch": 0.02, "learning_rate": 7.724538658235296e-06, "loss": 3.8604, "step": 2582016 }, { "epoch": 0.02, "learning_rate": 7.716152710724774e-06, "loss": 3.864, "step": 2582528 }, { "epoch": 0.02, "learning_rate": 7.707783142017987e-06, "loss": 3.8646, "step": 2583040 }, { "epoch": 0.02, "learning_rate": 7.699397194507467e-06, "loss": 3.8534, "step": 2583552 }, { "epoch": 0.02, "learning_rate": 7.691011246996947e-06, "loss": 3.8578, "step": 2584064 }, { "epoch": 0.02, "learning_rate": 7.682625299486427e-06, "loss": 3.8616, "step": 2584576 }, { "epoch": 0.02, "learning_rate": 7.674239351975907e-06, "loss": 3.8643, "step": 2585088 }, { "epoch": 0.02, "learning_rate": 7.665853404465387e-06, "loss": 3.871, "step": 2585600 }, { "epoch": 0.02, "learning_rate": 7.6574838357586e-06, "loss": 3.8708, "step": 2586112 }, { "epoch": 0.02, "learning_rate": 7.649097888248077e-06, "loss": 3.8547, "step": 2586624 }, { "epoch": 0.02, "learning_rate": 7.640728319541288e-06, "loss": 3.8667, "step": 2587136 }, { "epoch": 0.02, "learning_rate": 7.63234237203077e-06, "loss": 3.8671, "step": 2587648 }, { "epoch": 0.02, "learning_rate": 7.623956424520248e-06, "loss": 3.8619, "step": 2588160 }, { "epoch": 0.02, "learning_rate": 7.615570477009729e-06, "loss": 3.8631, "step": 2588672 }, { "epoch": 0.02, "learning_rate": 7.607184529499209e-06, "loss": 3.8692, "step": 2589184 }, { "epoch": 0.02, "learning_rate": 7.598798581988688e-06, "loss": 3.8638, "step": 2589696 }, { "epoch": 0.02, "learning_rate": 7.590412634478168e-06, "loss": 3.8803, "step": 2590208 }, { "epoch": 0.02, "learning_rate": 7.582026686967649e-06, "loss": 3.8576, "step": 2590720 }, { "epoch": 0.02, "learning_rate": 7.573640739457129e-06, "loss": 3.8699, "step": 2591232 }, { "epoch": 0.02, "learning_rate": 7.565254791946608e-06, "loss": 3.863, "step": 2591744 }, { "epoch": 0.02, "learning_rate": 7.556868844436088e-06, "loss": 3.8563, "step": 2592256 }, { "epoch": 0.02, "learning_rate": 7.548482896925569e-06, "loss": 3.8623, "step": 2592768 }, { "epoch": 0.02, "learning_rate": 7.5401133282187785e-06, "loss": 3.8582, "step": 2593280 }, { "epoch": 0.02, "learning_rate": 7.53174375951199e-06, "loss": 3.8605, "step": 2593792 }, { "epoch": 0.02, "learning_rate": 7.52335781200147e-06, "loss": 3.8592, "step": 2594304 }, { "epoch": 0.02, "learning_rate": 7.514971864490951e-06, "loss": 3.8551, "step": 2594816 }, { "epoch": 0.03, "eval_loss": 3.9849202632904053, "eval_runtime": 299.8077, "eval_samples_per_second": 1272.786, "eval_steps_per_second": 39.775, "step": 2594880 }, { "epoch": 1.0, "learning_rate": 7.50658591698043e-06, "loss": 3.8611, "step": 2595328 }, { "epoch": 1.0, "learning_rate": 7.49819996946991e-06, "loss": 3.8581, "step": 2595840 }, { "epoch": 1.0, "learning_rate": 7.489830400763122e-06, "loss": 3.8726, "step": 2596352 }, { "epoch": 1.0, "learning_rate": 7.481460832056333e-06, "loss": 3.8646, "step": 2596864 }, { "epoch": 1.0, "learning_rate": 7.473074884545812e-06, "loss": 3.8794, "step": 2597376 }, { "epoch": 1.0, "learning_rate": 7.464688937035292e-06, "loss": 3.8569, "step": 2597888 }, { "epoch": 1.0, "learning_rate": 7.456302989524773e-06, "loss": 3.8614, "step": 2598400 }, { "epoch": 1.0, "learning_rate": 7.447917042014252e-06, "loss": 3.8515, "step": 2598912 }, { "epoch": 1.0, "learning_rate": 7.439531094503732e-06, "loss": 3.867, "step": 2599424 }, { "epoch": 1.0, "learning_rate": 7.431145146993212e-06, "loss": 3.8631, "step": 2599936 }, { "epoch": 1.0, "learning_rate": 7.422759199482693e-06, "loss": 3.8609, "step": 2600448 }, { "epoch": 1.0, "learning_rate": 7.414389630775903e-06, "loss": 3.8715, "step": 2600960 }, { "epoch": 1.0, "learning_rate": 7.4060200620691145e-06, "loss": 3.8502, "step": 2601472 }, { "epoch": 1.0, "learning_rate": 7.397634114558595e-06, "loss": 3.8642, "step": 2601984 }, { "epoch": 1.0, "learning_rate": 7.389248167048075e-06, "loss": 3.8522, "step": 2602496 }, { "epoch": 1.0, "learning_rate": 7.380862219537554e-06, "loss": 3.8557, "step": 2603008 }, { "epoch": 1.0, "learning_rate": 7.372476272027034e-06, "loss": 3.8529, "step": 2603520 }, { "epoch": 1.0, "learning_rate": 7.364090324516515e-06, "loss": 3.8637, "step": 2604032 }, { "epoch": 1.0, "learning_rate": 7.3557043770059934e-06, "loss": 3.86, "step": 2604544 }, { "epoch": 1.0, "learning_rate": 7.347318429495474e-06, "loss": 3.8793, "step": 2605056 }, { "epoch": 1.0, "learning_rate": 7.338932481984954e-06, "loss": 3.8615, "step": 2605568 }, { "epoch": 1.0, "learning_rate": 7.330546534474433e-06, "loss": 3.864, "step": 2606080 }, { "epoch": 1.0, "learning_rate": 7.322160586963914e-06, "loss": 3.8633, "step": 2606592 }, { "epoch": 1.0, "learning_rate": 7.313774639453394e-06, "loss": 3.8692, "step": 2607104 }, { "epoch": 1.0, "learning_rate": 7.305405070746606e-06, "loss": 3.8615, "step": 2607616 }, { "epoch": 1.0, "learning_rate": 7.297035502039816e-06, "loss": 3.8665, "step": 2608128 }, { "epoch": 1.0, "learning_rate": 7.2886495545292964e-06, "loss": 3.8559, "step": 2608640 }, { "epoch": 1.0, "learning_rate": 7.280263607018776e-06, "loss": 3.859, "step": 2609152 }, { "epoch": 1.0, "learning_rate": 7.271877659508257e-06, "loss": 3.8516, "step": 2609664 }, { "epoch": 1.01, "learning_rate": 7.263508090801467e-06, "loss": 3.867, "step": 2610176 }, { "epoch": 1.01, "learning_rate": 7.255122143290947e-06, "loss": 3.8657, "step": 2610688 }, { "epoch": 1.01, "learning_rate": 7.246736195780428e-06, "loss": 3.8683, "step": 2611200 }, { "epoch": 1.01, "learning_rate": 7.238350248269907e-06, "loss": 3.8733, "step": 2611712 }, { "epoch": 1.01, "learning_rate": 7.229964300759387e-06, "loss": 3.8608, "step": 2612224 }, { "epoch": 1.01, "learning_rate": 7.22161111085633e-06, "loss": 3.8612, "step": 2612736 }, { "epoch": 1.01, "learning_rate": 7.21322516334581e-06, "loss": 3.8671, "step": 2613248 }, { "epoch": 1.01, "learning_rate": 7.204855594639022e-06, "loss": 3.8588, "step": 2613760 }, { "epoch": 1.01, "learning_rate": 7.196469647128501e-06, "loss": 3.8576, "step": 2614272 }, { "epoch": 1.01, "learning_rate": 7.188083699617981e-06, "loss": 3.8466, "step": 2614784 }, { "epoch": 1.01, "learning_rate": 7.179697752107462e-06, "loss": 3.8552, "step": 2615296 }, { "epoch": 1.01, "learning_rate": 7.171311804596941e-06, "loss": 3.8587, "step": 2615808 }, { "epoch": 1.01, "learning_rate": 7.162925857086421e-06, "loss": 3.8681, "step": 2616320 }, { "epoch": 1.01, "learning_rate": 7.154539909575901e-06, "loss": 3.8602, "step": 2616832 }, { "epoch": 1.01, "learning_rate": 7.14615396206538e-06, "loss": 3.8502, "step": 2617344 }, { "epoch": 1.01, "learning_rate": 7.137768014554861e-06, "loss": 3.8684, "step": 2617856 }, { "epoch": 1.01, "learning_rate": 7.129382067044341e-06, "loss": 3.8615, "step": 2618368 }, { "epoch": 1.01, "learning_rate": 7.120996119533821e-06, "loss": 3.856, "step": 2618880 }, { "epoch": 1.01, "learning_rate": 7.1126101720233e-06, "loss": 3.8528, "step": 2619392 }, { "epoch": 1.01, "learning_rate": 7.1042242245127805e-06, "loss": 3.8478, "step": 2619904 }, { "epoch": 1.01, "learning_rate": 7.0958382770022605e-06, "loss": 3.8757, "step": 2620416 }, { "epoch": 1.01, "learning_rate": 7.0874523294917396e-06, "loss": 3.8719, "step": 2620928 }, { "epoch": 1.01, "learning_rate": 7.079082760784951e-06, "loss": 3.8557, "step": 2621440 }, { "epoch": 1.01, "learning_rate": 7.070696813274431e-06, "loss": 3.8593, "step": 2621952 }, { "epoch": 1.01, "learning_rate": 7.062310865763912e-06, "loss": 3.8668, "step": 2622464 }, { "epoch": 1.01, "learning_rate": 7.05392491825339e-06, "loss": 3.8469, "step": 2622976 }, { "epoch": 1.01, "learning_rate": 7.045538970742871e-06, "loss": 3.8678, "step": 2623488 }, { "epoch": 1.01, "learning_rate": 7.037169402036083e-06, "loss": 3.8454, "step": 2624000 }, { "epoch": 1.01, "learning_rate": 7.028799833329293e-06, "loss": 3.8682, "step": 2624512 }, { "epoch": 1.01, "learning_rate": 7.020413885818773e-06, "loss": 3.871, "step": 2625024 }, { "epoch": 1.01, "learning_rate": 7.012027938308253e-06, "loss": 3.8544, "step": 2625536 }, { "epoch": 1.01, "learning_rate": 7.003641990797734e-06, "loss": 3.847, "step": 2626048 }, { "epoch": 1.01, "learning_rate": 6.9952560432872124e-06, "loss": 3.8686, "step": 2626560 }, { "epoch": 1.01, "learning_rate": 6.986870095776693e-06, "loss": 3.8406, "step": 2627072 }, { "epoch": 1.01, "learning_rate": 6.978484148266173e-06, "loss": 3.8574, "step": 2627584 }, { "epoch": 1.01, "learning_rate": 6.970098200755652e-06, "loss": 3.8643, "step": 2628096 }, { "epoch": 1.01, "learning_rate": 6.961712253245132e-06, "loss": 3.8646, "step": 2628608 }, { "epoch": 1.01, "learning_rate": 6.953326305734613e-06, "loss": 3.8585, "step": 2629120 }, { "epoch": 1.01, "learning_rate": 6.944956737027825e-06, "loss": 3.8466, "step": 2629632 }, { "epoch": 1.01, "learning_rate": 6.936570789517304e-06, "loss": 3.8507, "step": 2630144 }, { "epoch": 1.01, "learning_rate": 6.928184842006784e-06, "loss": 3.8505, "step": 2630656 }, { "epoch": 1.01, "learning_rate": 6.919798894496264e-06, "loss": 3.8633, "step": 2631168 }, { "epoch": 1.01, "learning_rate": 6.911412946985743e-06, "loss": 3.8523, "step": 2631680 }, { "epoch": 1.01, "learning_rate": 6.903026999475224e-06, "loss": 3.8649, "step": 2632192 }, { "epoch": 1.01, "learning_rate": 6.8946410519647036e-06, "loss": 3.8665, "step": 2632704 }, { "epoch": 1.01, "learning_rate": 6.886255104454183e-06, "loss": 3.8686, "step": 2633216 }, { "epoch": 1.01, "learning_rate": 6.877869156943663e-06, "loss": 3.8514, "step": 2633728 }, { "epoch": 1.01, "learning_rate": 6.869499588236874e-06, "loss": 3.8571, "step": 2634240 }, { "epoch": 1.01, "learning_rate": 6.861130019530086e-06, "loss": 3.8652, "step": 2634752 }, { "epoch": 1.01, "learning_rate": 6.852744072019565e-06, "loss": 3.858, "step": 2635264 }, { "epoch": 1.01, "learning_rate": 6.844374503312777e-06, "loss": 3.8611, "step": 2635776 }, { "epoch": 1.01, "learning_rate": 6.8359885558022575e-06, "loss": 3.8574, "step": 2636288 }, { "epoch": 1.01, "learning_rate": 6.827602608291737e-06, "loss": 3.8603, "step": 2636800 }, { "epoch": 1.01, "learning_rate": 6.8192166607812165e-06, "loss": 3.8617, "step": 2637312 }, { "epoch": 1.01, "learning_rate": 6.8108307132706965e-06, "loss": 3.8453, "step": 2637824 }, { "epoch": 1.01, "learning_rate": 6.802444765760177e-06, "loss": 3.8592, "step": 2638336 }, { "epoch": 1.01, "learning_rate": 6.7940588182496555e-06, "loss": 3.8543, "step": 2638848 }, { "epoch": 1.01, "learning_rate": 6.785672870739136e-06, "loss": 3.8642, "step": 2639360 }, { "epoch": 1.01, "learning_rate": 6.777303302032348e-06, "loss": 3.8584, "step": 2639872 }, { "epoch": 1.01, "learning_rate": 6.768917354521828e-06, "loss": 3.8548, "step": 2640384 }, { "epoch": 1.02, "learning_rate": 6.760531407011307e-06, "loss": 3.8525, "step": 2640896 }, { "epoch": 1.02, "learning_rate": 6.752145459500787e-06, "loss": 3.8498, "step": 2641408 }, { "epoch": 1.02, "learning_rate": 6.743759511990268e-06, "loss": 3.8472, "step": 2641920 }, { "epoch": 1.02, "learning_rate": 6.735373564479747e-06, "loss": 3.8612, "step": 2642432 }, { "epoch": 1.02, "learning_rate": 6.726987616969227e-06, "loss": 3.8685, "step": 2642944 }, { "epoch": 1.02, "learning_rate": 6.718601669458708e-06, "loss": 3.8627, "step": 2643456 }, { "epoch": 1.02, "learning_rate": 6.710215721948188e-06, "loss": 3.8605, "step": 2643968 }, { "epoch": 1.02, "learning_rate": 6.701829774437667e-06, "loss": 3.8528, "step": 2644480 }, { "epoch": 1.02, "learning_rate": 6.693443826927147e-06, "loss": 3.8554, "step": 2644992 }, { "epoch": 1.02, "learning_rate": 6.685074258220358e-06, "loss": 3.8579, "step": 2645504 }, { "epoch": 1.02, "learning_rate": 6.6766883107098374e-06, "loss": 3.8678, "step": 2646016 }, { "epoch": 1.02, "learning_rate": 6.668318742003049e-06, "loss": 3.8621, "step": 2646528 }, { "epoch": 1.02, "learning_rate": 6.659932794492529e-06, "loss": 3.8569, "step": 2647040 }, { "epoch": 1.02, "learning_rate": 6.65154684698201e-06, "loss": 3.8511, "step": 2647552 }, { "epoch": 1.02, "learning_rate": 6.643160899471489e-06, "loss": 3.8703, "step": 2648064 }, { "epoch": 1.02, "learning_rate": 6.634774951960969e-06, "loss": 3.8473, "step": 2648576 }, { "epoch": 1.02, "learning_rate": 6.626389004450449e-06, "loss": 3.8605, "step": 2649088 }, { "epoch": 1.02, "learning_rate": 6.618003056939928e-06, "loss": 3.8517, "step": 2649600 }, { "epoch": 1.02, "learning_rate": 6.609617109429409e-06, "loss": 3.8603, "step": 2650112 }, { "epoch": 1.02, "learning_rate": 6.60124754072262e-06, "loss": 3.8509, "step": 2650624 }, { "epoch": 1.02, "learning_rate": 6.5928615932121e-06, "loss": 3.862, "step": 2651136 }, { "epoch": 1.02, "learning_rate": 6.5844756457015795e-06, "loss": 3.8506, "step": 2651648 }, { "epoch": 1.02, "learning_rate": 6.5760896981910594e-06, "loss": 3.8518, "step": 2652160 }, { "epoch": 1.02, "learning_rate": 6.567720129484271e-06, "loss": 3.8632, "step": 2652672 }, { "epoch": 1.02, "learning_rate": 6.559334181973752e-06, "loss": 3.8499, "step": 2653184 }, { "epoch": 1.02, "learning_rate": 6.550948234463231e-06, "loss": 3.8705, "step": 2653696 }, { "epoch": 1.02, "learning_rate": 6.542578665756443e-06, "loss": 3.8713, "step": 2654208 }, { "epoch": 1.02, "learning_rate": 6.534209097049654e-06, "loss": 3.8638, "step": 2654720 }, { "epoch": 1.02, "learning_rate": 6.525823149539134e-06, "loss": 3.8542, "step": 2655232 }, { "epoch": 1.02, "learning_rate": 6.517437202028613e-06, "loss": 3.8533, "step": 2655744 }, { "epoch": 1.02, "learning_rate": 6.509051254518093e-06, "loss": 3.8549, "step": 2656256 }, { "epoch": 1.02, "learning_rate": 6.500665307007574e-06, "loss": 3.8547, "step": 2656768 }, { "epoch": 1.02, "learning_rate": 6.492279359497052e-06, "loss": 3.8657, "step": 2657280 }, { "epoch": 1.02, "learning_rate": 6.483909790790264e-06, "loss": 3.8483, "step": 2657792 }, { "epoch": 1.02, "learning_rate": 6.475523843279745e-06, "loss": 3.8621, "step": 2658304 }, { "epoch": 1.02, "learning_rate": 6.467137895769225e-06, "loss": 3.864, "step": 2658816 }, { "epoch": 1.02, "learning_rate": 6.458751948258704e-06, "loss": 3.8629, "step": 2659328 }, { "epoch": 1.02, "learning_rate": 6.4503823795519155e-06, "loss": 3.8517, "step": 2659840 }, { "epoch": 1.02, "learning_rate": 6.4419964320413954e-06, "loss": 3.8553, "step": 2660352 }, { "epoch": 1.02, "learning_rate": 6.4336104845308745e-06, "loss": 3.861, "step": 2660864 }, { "epoch": 1.02, "learning_rate": 6.425224537020355e-06, "loss": 3.8616, "step": 2661376 }, { "epoch": 1.02, "learning_rate": 6.416838589509835e-06, "loss": 3.8646, "step": 2661888 }, { "epoch": 1.02, "learning_rate": 6.408452641999314e-06, "loss": 3.8709, "step": 2662400 }, { "epoch": 1.02, "learning_rate": 6.400066694488794e-06, "loss": 3.8496, "step": 2662912 }, { "epoch": 1.02, "learning_rate": 6.391697125782006e-06, "loss": 3.8654, "step": 2663424 }, { "epoch": 1.02, "learning_rate": 6.383311178271487e-06, "loss": 3.866, "step": 2663936 }, { "epoch": 1.02, "learning_rate": 6.374925230760966e-06, "loss": 3.8588, "step": 2664448 }, { "epoch": 1.02, "learning_rate": 6.366539283250446e-06, "loss": 3.8591, "step": 2664960 }, { "epoch": 1.02, "learning_rate": 6.358153335739926e-06, "loss": 3.8687, "step": 2665472 }, { "epoch": 1.02, "learning_rate": 6.349767388229405e-06, "loss": 3.8607, "step": 2665984 }, { "epoch": 1.02, "learning_rate": 6.341381440718886e-06, "loss": 3.8767, "step": 2666496 }, { "epoch": 1.02, "learning_rate": 6.332995493208366e-06, "loss": 3.8556, "step": 2667008 }, { "epoch": 1.02, "learning_rate": 6.324609545697846e-06, "loss": 3.8635, "step": 2667520 }, { "epoch": 1.02, "learning_rate": 6.316223598187325e-06, "loss": 3.8608, "step": 2668032 }, { "epoch": 1.02, "learning_rate": 6.307854029480536e-06, "loss": 3.8558, "step": 2668544 }, { "epoch": 1.02, "learning_rate": 6.299468081970017e-06, "loss": 3.857, "step": 2669056 }, { "epoch": 1.02, "learning_rate": 6.2910821344594955e-06, "loss": 3.857, "step": 2669568 }, { "epoch": 1.02, "learning_rate": 6.282696186948976e-06, "loss": 3.854, "step": 2670080 }, { "epoch": 1.02, "learning_rate": 6.27434299704592e-06, "loss": 3.8579, "step": 2670592 }, { "epoch": 1.02, "learning_rate": 6.2659570495353995e-06, "loss": 3.8554, "step": 2671104 }, { "epoch": 1.03, "eval_loss": 3.9845287799835205, "eval_runtime": 298.3991, "eval_samples_per_second": 1278.794, "eval_steps_per_second": 39.963, "step": 2671200 }, { "epoch": 0.0, "learning_rate": 6.257571102024879e-06, "loss": 3.8597, "step": 2671616 }, { "epoch": 0.0, "learning_rate": 6.249185154514359e-06, "loss": 3.8545, "step": 2672128 }, { "epoch": 0.0, "learning_rate": 6.240799207003839e-06, "loss": 3.8681, "step": 2672640 }, { "epoch": 0.0, "learning_rate": 6.2324132594933185e-06, "loss": 3.8616, "step": 2673152 }, { "epoch": 0.0, "learning_rate": 6.224027311982799e-06, "loss": 3.8795, "step": 2673664 }, { "epoch": 0.0, "learning_rate": 6.215641364472278e-06, "loss": 3.857, "step": 2674176 }, { "epoch": 0.0, "learning_rate": 6.207255416961758e-06, "loss": 3.8587, "step": 2674688 }, { "epoch": 0.0, "learning_rate": 6.198869469451238e-06, "loss": 3.8479, "step": 2675200 }, { "epoch": 0.0, "learning_rate": 6.190483521940718e-06, "loss": 3.8634, "step": 2675712 }, { "epoch": 0.0, "learning_rate": 6.182097574430198e-06, "loss": 3.8629, "step": 2676224 }, { "epoch": 0.0, "learning_rate": 6.173711626919678e-06, "loss": 3.8559, "step": 2676736 }, { "epoch": 0.0, "learning_rate": 6.165325679409157e-06, "loss": 3.8668, "step": 2677248 }, { "epoch": 0.0, "learning_rate": 6.156956110702369e-06, "loss": 3.8526, "step": 2677760 }, { "epoch": 0.0, "learning_rate": 6.148570163191849e-06, "loss": 3.8613, "step": 2678272 }, { "epoch": 0.0, "learning_rate": 6.140184215681329e-06, "loss": 3.852, "step": 2678784 }, { "epoch": 0.0, "learning_rate": 6.131798268170809e-06, "loss": 3.8503, "step": 2679296 }, { "epoch": 0.0, "learning_rate": 6.123412320660289e-06, "loss": 3.8518, "step": 2679808 }, { "epoch": 0.0, "learning_rate": 6.115026373149769e-06, "loss": 3.86, "step": 2680320 }, { "epoch": 0.0, "learning_rate": 6.106640425639249e-06, "loss": 3.8579, "step": 2680832 }, { "epoch": 0.0, "learning_rate": 6.098254478128729e-06, "loss": 3.8767, "step": 2681344 }, { "epoch": 0.0, "learning_rate": 6.0898849094219394e-06, "loss": 3.8584, "step": 2681856 }, { "epoch": 0.0, "learning_rate": 6.08149896191142e-06, "loss": 3.8668, "step": 2682368 }, { "epoch": 0.0, "learning_rate": 6.073113014400899e-06, "loss": 3.8582, "step": 2682880 }, { "epoch": 0.0, "learning_rate": 6.064727066890379e-06, "loss": 3.8628, "step": 2683392 }, { "epoch": 0.0, "learning_rate": 6.056341119379859e-06, "loss": 3.861, "step": 2683904 }, { "epoch": 0.0, "learning_rate": 6.047971550673071e-06, "loss": 3.8639, "step": 2684416 }, { "epoch": 0.0, "learning_rate": 6.039585603162551e-06, "loss": 3.8548, "step": 2684928 }, { "epoch": 0.0, "learning_rate": 6.031199655652031e-06, "loss": 3.852, "step": 2685440 }, { "epoch": 0.0, "learning_rate": 6.0228300869452424e-06, "loss": 3.8524, "step": 2685952 }, { "epoch": 0.01, "learning_rate": 6.0144441394347215e-06, "loss": 3.8613, "step": 2686464 }, { "epoch": 0.01, "learning_rate": 6.006058191924202e-06, "loss": 3.865, "step": 2686976 }, { "epoch": 0.01, "learning_rate": 5.9976722444136815e-06, "loss": 3.8624, "step": 2687488 }, { "epoch": 0.01, "learning_rate": 5.989286296903161e-06, "loss": 3.8718, "step": 2688000 }, { "epoch": 0.01, "learning_rate": 5.980900349392641e-06, "loss": 3.861, "step": 2688512 }, { "epoch": 0.01, "learning_rate": 5.972530780685852e-06, "loss": 3.8591, "step": 2689024 }, { "epoch": 0.01, "learning_rate": 5.964144833175333e-06, "loss": 3.8616, "step": 2689536 }, { "epoch": 0.01, "learning_rate": 5.955758885664813e-06, "loss": 3.864, "step": 2690048 }, { "epoch": 0.01, "learning_rate": 5.947372938154293e-06, "loss": 3.849, "step": 2690560 }, { "epoch": 0.01, "learning_rate": 5.938986990643773e-06, "loss": 3.8435, "step": 2691072 }, { "epoch": 0.01, "learning_rate": 5.930601043133252e-06, "loss": 3.8499, "step": 2691584 }, { "epoch": 0.01, "learning_rate": 5.922215095622733e-06, "loss": 3.8613, "step": 2692096 }, { "epoch": 0.01, "learning_rate": 5.913829148112212e-06, "loss": 3.8633, "step": 2692608 }, { "epoch": 0.01, "learning_rate": 5.905443200601693e-06, "loss": 3.8586, "step": 2693120 }, { "epoch": 0.01, "learning_rate": 5.897057253091172e-06, "loss": 3.8467, "step": 2693632 }, { "epoch": 0.01, "learning_rate": 5.888671305580652e-06, "loss": 3.865, "step": 2694144 }, { "epoch": 0.01, "learning_rate": 5.880285358070132e-06, "loss": 3.858, "step": 2694656 }, { "epoch": 0.01, "learning_rate": 5.8719157893633425e-06, "loss": 3.8548, "step": 2695168 }, { "epoch": 0.01, "learning_rate": 5.863529841852823e-06, "loss": 3.8503, "step": 2695680 }, { "epoch": 0.01, "learning_rate": 5.855143894342302e-06, "loss": 3.8376, "step": 2696192 }, { "epoch": 0.01, "learning_rate": 5.846757946831783e-06, "loss": 3.8797, "step": 2696704 }, { "epoch": 0.01, "learning_rate": 5.838371999321262e-06, "loss": 3.8661, "step": 2697216 }, { "epoch": 0.01, "learning_rate": 5.829986051810742e-06, "loss": 3.8548, "step": 2697728 }, { "epoch": 0.01, "learning_rate": 5.821616483103954e-06, "loss": 3.8595, "step": 2698240 }, { "epoch": 0.01, "learning_rate": 5.813230535593434e-06, "loss": 3.8582, "step": 2698752 }, { "epoch": 0.01, "learning_rate": 5.804844588082914e-06, "loss": 3.8487, "step": 2699264 }, { "epoch": 0.01, "learning_rate": 5.796458640572394e-06, "loss": 3.8638, "step": 2699776 }, { "epoch": 0.01, "learning_rate": 5.788089071865605e-06, "loss": 3.8482, "step": 2700288 }, { "epoch": 0.01, "learning_rate": 5.779719503158816e-06, "loss": 3.8624, "step": 2700800 }, { "epoch": 0.01, "learning_rate": 5.771333555648296e-06, "loss": 3.8715, "step": 2701312 }, { "epoch": 0.01, "learning_rate": 5.762947608137776e-06, "loss": 3.854, "step": 2701824 }, { "epoch": 0.01, "learning_rate": 5.754561660627256e-06, "loss": 3.8418, "step": 2702336 }, { "epoch": 0.01, "learning_rate": 5.746175713116736e-06, "loss": 3.8685, "step": 2702848 }, { "epoch": 0.01, "learning_rate": 5.737789765606216e-06, "loss": 3.8384, "step": 2703360 }, { "epoch": 0.01, "learning_rate": 5.729403818095696e-06, "loss": 3.8503, "step": 2703872 }, { "epoch": 0.01, "learning_rate": 5.721017870585176e-06, "loss": 3.8654, "step": 2704384 }, { "epoch": 0.01, "learning_rate": 5.712631923074656e-06, "loss": 3.8622, "step": 2704896 }, { "epoch": 0.01, "learning_rate": 5.704245975564136e-06, "loss": 3.854, "step": 2705408 }, { "epoch": 0.01, "learning_rate": 5.695876406857347e-06, "loss": 3.8484, "step": 2705920 }, { "epoch": 0.01, "learning_rate": 5.6874904593468265e-06, "loss": 3.8394, "step": 2706432 }, { "epoch": 0.01, "learning_rate": 5.6791045118363065e-06, "loss": 3.8469, "step": 2706944 }, { "epoch": 0.01, "learning_rate": 5.6707185643257864e-06, "loss": 3.862, "step": 2707456 }, { "epoch": 0.01, "learning_rate": 5.662332616815266e-06, "loss": 3.8488, "step": 2707968 }, { "epoch": 0.01, "learning_rate": 5.653946669304746e-06, "loss": 3.8641, "step": 2708480 }, { "epoch": 0.01, "learning_rate": 5.645560721794226e-06, "loss": 3.86, "step": 2708992 }, { "epoch": 0.01, "learning_rate": 5.637174774283706e-06, "loss": 3.8704, "step": 2709504 }, { "epoch": 0.01, "learning_rate": 5.628805205576918e-06, "loss": 3.8528, "step": 2710016 }, { "epoch": 0.01, "learning_rate": 5.620419258066397e-06, "loss": 3.852, "step": 2710528 }, { "epoch": 0.01, "learning_rate": 5.612049689359609e-06, "loss": 3.864, "step": 2711040 }, { "epoch": 0.01, "learning_rate": 5.603663741849089e-06, "loss": 3.8513, "step": 2711552 }, { "epoch": 0.01, "learning_rate": 5.5952777943385685e-06, "loss": 3.8636, "step": 2712064 }, { "epoch": 0.01, "learning_rate": 5.5868918468280485e-06, "loss": 3.8554, "step": 2712576 }, { "epoch": 0.01, "learning_rate": 5.578505899317528e-06, "loss": 3.8572, "step": 2713088 }, { "epoch": 0.01, "learning_rate": 5.570119951807008e-06, "loss": 3.8616, "step": 2713600 }, { "epoch": 0.01, "learning_rate": 5.5617340042964875e-06, "loss": 3.8473, "step": 2714112 }, { "epoch": 0.01, "learning_rate": 5.553364435589699e-06, "loss": 3.8537, "step": 2714624 }, { "epoch": 0.01, "learning_rate": 5.544978488079179e-06, "loss": 3.8555, "step": 2715136 }, { "epoch": 0.01, "learning_rate": 5.536592540568659e-06, "loss": 3.8622, "step": 2715648 }, { "epoch": 0.01, "learning_rate": 5.528206593058139e-06, "loss": 3.854, "step": 2716160 }, { "epoch": 0.01, "learning_rate": 5.519820645547619e-06, "loss": 3.855, "step": 2716672 }, { "epoch": 0.02, "learning_rate": 5.511434698037099e-06, "loss": 3.85, "step": 2717184 }, { "epoch": 0.02, "learning_rate": 5.503048750526579e-06, "loss": 3.8467, "step": 2717696 }, { "epoch": 0.02, "learning_rate": 5.4946791818197905e-06, "loss": 3.8476, "step": 2718208 }, { "epoch": 0.02, "learning_rate": 5.48629323430927e-06, "loss": 3.8544, "step": 2718720 }, { "epoch": 0.02, "learning_rate": 5.4779072867987504e-06, "loss": 3.8658, "step": 2719232 }, { "epoch": 0.02, "learning_rate": 5.4695213392882295e-06, "loss": 3.8621, "step": 2719744 }, { "epoch": 0.02, "learning_rate": 5.4611353917777095e-06, "loss": 3.8572, "step": 2720256 }, { "epoch": 0.02, "learning_rate": 5.4527494442671895e-06, "loss": 3.8492, "step": 2720768 }, { "epoch": 0.02, "learning_rate": 5.444363496756669e-06, "loss": 3.8524, "step": 2721280 }, { "epoch": 0.02, "learning_rate": 5.435993928049881e-06, "loss": 3.8587, "step": 2721792 }, { "epoch": 0.02, "learning_rate": 5.427607980539361e-06, "loss": 3.8631, "step": 2722304 }, { "epoch": 0.02, "learning_rate": 5.419222033028841e-06, "loss": 3.8602, "step": 2722816 }, { "epoch": 0.02, "learning_rate": 5.410836085518321e-06, "loss": 3.8548, "step": 2723328 }, { "epoch": 0.02, "learning_rate": 5.4024501380078e-06, "loss": 3.8475, "step": 2723840 }, { "epoch": 0.02, "learning_rate": 5.394064190497281e-06, "loss": 3.8706, "step": 2724352 }, { "epoch": 0.02, "learning_rate": 5.38567824298676e-06, "loss": 3.841, "step": 2724864 }, { "epoch": 0.02, "learning_rate": 5.3773086742799716e-06, "loss": 3.8606, "step": 2725376 }, { "epoch": 0.02, "learning_rate": 5.3689227267694515e-06, "loss": 3.8497, "step": 2725888 }, { "epoch": 0.02, "learning_rate": 5.360553158062663e-06, "loss": 3.8584, "step": 2726400 }, { "epoch": 0.02, "learning_rate": 5.352167210552142e-06, "loss": 3.8491, "step": 2726912 }, { "epoch": 0.02, "learning_rate": 5.343781263041623e-06, "loss": 3.857, "step": 2727424 }, { "epoch": 0.02, "learning_rate": 5.335395315531103e-06, "loss": 3.8498, "step": 2727936 }, { "epoch": 0.02, "learning_rate": 5.327009368020582e-06, "loss": 3.8496, "step": 2728448 }, { "epoch": 0.02, "learning_rate": 5.318639799313794e-06, "loss": 3.8559, "step": 2728960 }, { "epoch": 0.02, "learning_rate": 5.310270230607005e-06, "loss": 3.8502, "step": 2729472 }, { "epoch": 0.02, "learning_rate": 5.301884283096485e-06, "loss": 3.8659, "step": 2729984 }, { "epoch": 0.02, "learning_rate": 5.2934983355859645e-06, "loss": 3.8699, "step": 2730496 }, { "epoch": 0.02, "learning_rate": 5.285112388075445e-06, "loss": 3.8627, "step": 2731008 }, { "epoch": 0.02, "learning_rate": 5.276726440564924e-06, "loss": 3.8507, "step": 2731520 }, { "epoch": 0.02, "learning_rate": 5.268340493054405e-06, "loss": 3.8533, "step": 2732032 }, { "epoch": 0.02, "learning_rate": 5.259954545543884e-06, "loss": 3.849, "step": 2732544 }, { "epoch": 0.02, "learning_rate": 5.251568598033364e-06, "loss": 3.8526, "step": 2733056 }, { "epoch": 0.02, "learning_rate": 5.243199029326576e-06, "loss": 3.8637, "step": 2733568 }, { "epoch": 0.02, "learning_rate": 5.234813081816056e-06, "loss": 3.8402, "step": 2734080 }, { "epoch": 0.02, "learning_rate": 5.226427134305536e-06, "loss": 3.86, "step": 2734592 }, { "epoch": 0.02, "learning_rate": 5.218041186795016e-06, "loss": 3.8567, "step": 2735104 }, { "epoch": 0.02, "learning_rate": 5.209655239284496e-06, "loss": 3.8612, "step": 2735616 }, { "epoch": 0.02, "learning_rate": 5.201269291773976e-06, "loss": 3.8489, "step": 2736128 }, { "epoch": 0.02, "learning_rate": 5.192883344263455e-06, "loss": 3.8549, "step": 2736640 }, { "epoch": 0.02, "learning_rate": 5.184497396752936e-06, "loss": 3.8523, "step": 2737152 }, { "epoch": 0.02, "learning_rate": 5.176111449242415e-06, "loss": 3.8665, "step": 2737664 }, { "epoch": 0.02, "learning_rate": 5.1677255017318955e-06, "loss": 3.8593, "step": 2738176 }, { "epoch": 0.02, "learning_rate": 5.159339554221375e-06, "loss": 3.8703, "step": 2738688 }, { "epoch": 0.02, "learning_rate": 5.150969985514586e-06, "loss": 3.8469, "step": 2739200 }, { "epoch": 0.02, "learning_rate": 5.142584038004066e-06, "loss": 3.8626, "step": 2739712 }, { "epoch": 0.02, "learning_rate": 5.134198090493546e-06, "loss": 3.8649, "step": 2740224 }, { "epoch": 0.02, "learning_rate": 5.125812142983026e-06, "loss": 3.8514, "step": 2740736 }, { "epoch": 0.02, "learning_rate": 5.117426195472506e-06, "loss": 3.8575, "step": 2741248 }, { "epoch": 0.02, "learning_rate": 5.109056626765718e-06, "loss": 3.8672, "step": 2741760 }, { "epoch": 0.02, "learning_rate": 5.100670679255197e-06, "loss": 3.8606, "step": 2742272 }, { "epoch": 0.02, "learning_rate": 5.092284731744678e-06, "loss": 3.8753, "step": 2742784 }, { "epoch": 0.02, "learning_rate": 5.083898784234157e-06, "loss": 3.8516, "step": 2743296 }, { "epoch": 0.02, "learning_rate": 5.075529215527368e-06, "loss": 3.8653, "step": 2743808 }, { "epoch": 0.02, "learning_rate": 5.067143268016848e-06, "loss": 3.8537, "step": 2744320 }, { "epoch": 0.02, "learning_rate": 5.0587573205063274e-06, "loss": 3.8546, "step": 2744832 }, { "epoch": 0.02, "learning_rate": 5.050371372995808e-06, "loss": 3.8571, "step": 2745344 }, { "epoch": 0.02, "learning_rate": 5.042018183092751e-06, "loss": 3.8545, "step": 2745856 }, { "epoch": 0.02, "learning_rate": 5.033632235582231e-06, "loss": 3.8522, "step": 2746368 }, { "epoch": 0.02, "learning_rate": 5.025246288071711e-06, "loss": 3.8538, "step": 2746880 }, { "epoch": 0.02, "learning_rate": 5.0168603405611906e-06, "loss": 3.8535, "step": 2747392 }, { "epoch": 0.03, "eval_loss": 3.98368501663208, "eval_runtime": 298.5053, "eval_samples_per_second": 1278.339, "eval_steps_per_second": 39.949, "step": 2747520 }, { "epoch": 1.0, "learning_rate": 5.008490771854401e-06, "loss": 3.8586, "step": 2747904 }, { "epoch": 1.0, "learning_rate": 5.000104824343882e-06, "loss": 3.8523, "step": 2748416 }, { "epoch": 1.0, "learning_rate": 4.991718876833361e-06, "loss": 3.8669, "step": 2748928 }, { "epoch": 1.0, "learning_rate": 4.983332929322842e-06, "loss": 3.8572, "step": 2749440 }, { "epoch": 1.0, "learning_rate": 4.974946981812321e-06, "loss": 3.8736, "step": 2749952 }, { "epoch": 1.0, "learning_rate": 4.966561034301801e-06, "loss": 3.8593, "step": 2750464 }, { "epoch": 1.0, "learning_rate": 4.958175086791281e-06, "loss": 3.8558, "step": 2750976 }, { "epoch": 1.0, "learning_rate": 4.949789139280761e-06, "loss": 3.8458, "step": 2751488 }, { "epoch": 1.0, "learning_rate": 4.941419570573973e-06, "loss": 3.8568, "step": 2752000 }, { "epoch": 1.0, "learning_rate": 4.933033623063453e-06, "loss": 3.8597, "step": 2752512 }, { "epoch": 1.0, "learning_rate": 4.924647675552932e-06, "loss": 3.858, "step": 2753024 }, { "epoch": 1.0, "learning_rate": 4.9162617280424126e-06, "loss": 3.8613, "step": 2753536 }, { "epoch": 1.0, "learning_rate": 4.907908538139355e-06, "loss": 3.8501, "step": 2754048 }, { "epoch": 1.0, "learning_rate": 4.899522590628835e-06, "loss": 3.8609, "step": 2754560 }, { "epoch": 1.0, "learning_rate": 4.891136643118314e-06, "loss": 3.8491, "step": 2755072 }, { "epoch": 1.0, "learning_rate": 4.882750695607795e-06, "loss": 3.8478, "step": 2755584 }, { "epoch": 1.0, "learning_rate": 4.874364748097274e-06, "loss": 3.8493, "step": 2756096 }, { "epoch": 1.0, "learning_rate": 4.865978800586755e-06, "loss": 3.8599, "step": 2756608 }, { "epoch": 1.0, "learning_rate": 4.857592853076235e-06, "loss": 3.8545, "step": 2757120 }, { "epoch": 1.0, "learning_rate": 4.849206905565714e-06, "loss": 3.8717, "step": 2757632 }, { "epoch": 1.0, "learning_rate": 4.840820958055195e-06, "loss": 3.8594, "step": 2758144 }, { "epoch": 1.0, "learning_rate": 4.832435010544674e-06, "loss": 3.8662, "step": 2758656 }, { "epoch": 1.0, "learning_rate": 4.824049063034155e-06, "loss": 3.855, "step": 2759168 }, { "epoch": 1.0, "learning_rate": 4.815663115523634e-06, "loss": 3.8592, "step": 2759680 }, { "epoch": 1.0, "learning_rate": 4.807293546816845e-06, "loss": 3.8583, "step": 2760192 }, { "epoch": 1.0, "learning_rate": 4.798907599306325e-06, "loss": 3.8641, "step": 2760704 }, { "epoch": 1.0, "learning_rate": 4.790521651795804e-06, "loss": 3.8517, "step": 2761216 }, { "epoch": 1.0, "learning_rate": 4.782135704285285e-06, "loss": 3.8547, "step": 2761728 }, { "epoch": 1.0, "learning_rate": 4.773766135578496e-06, "loss": 3.8488, "step": 2762240 }, { "epoch": 1.0, "learning_rate": 4.765396566871708e-06, "loss": 3.8563, "step": 2762752 }, { "epoch": 1.01, "learning_rate": 4.757010619361188e-06, "loss": 3.8625, "step": 2763264 }, { "epoch": 1.01, "learning_rate": 4.7486246718506675e-06, "loss": 3.8629, "step": 2763776 }, { "epoch": 1.01, "learning_rate": 4.7402387243401475e-06, "loss": 3.8667, "step": 2764288 }, { "epoch": 1.01, "learning_rate": 4.7318527768296274e-06, "loss": 3.8546, "step": 2764800 }, { "epoch": 1.01, "learning_rate": 4.723483208122838e-06, "loss": 3.8566, "step": 2765312 }, { "epoch": 1.01, "learning_rate": 4.71511363941605e-06, "loss": 3.8663, "step": 2765824 }, { "epoch": 1.01, "learning_rate": 4.70672769190553e-06, "loss": 3.862, "step": 2766336 }, { "epoch": 1.01, "learning_rate": 4.69834174439501e-06, "loss": 3.8441, "step": 2766848 }, { "epoch": 1.01, "learning_rate": 4.68995579688449e-06, "loss": 3.8465, "step": 2767360 }, { "epoch": 1.01, "learning_rate": 4.68156984937397e-06, "loss": 3.8454, "step": 2767872 }, { "epoch": 1.01, "learning_rate": 4.67318390186345e-06, "loss": 3.8514, "step": 2768384 }, { "epoch": 1.01, "learning_rate": 4.66479795435293e-06, "loss": 3.8649, "step": 2768896 }, { "epoch": 1.01, "learning_rate": 4.6564120068424096e-06, "loss": 3.8537, "step": 2769408 }, { "epoch": 1.01, "learning_rate": 4.64804243813562e-06, "loss": 3.8487, "step": 2769920 }, { "epoch": 1.01, "learning_rate": 4.639656490625101e-06, "loss": 3.8593, "step": 2770432 }, { "epoch": 1.01, "learning_rate": 4.63127054311458e-06, "loss": 3.8544, "step": 2770944 }, { "epoch": 1.01, "learning_rate": 4.62288459560406e-06, "loss": 3.8548, "step": 2771456 }, { "epoch": 1.01, "learning_rate": 4.61449864809354e-06, "loss": 3.8493, "step": 2771968 }, { "epoch": 1.01, "learning_rate": 4.60611270058302e-06, "loss": 3.8305, "step": 2772480 }, { "epoch": 1.01, "learning_rate": 4.5977267530725e-06, "loss": 3.8795, "step": 2772992 }, { "epoch": 1.01, "learning_rate": 4.58934080556198e-06, "loss": 3.8627, "step": 2773504 }, { "epoch": 1.01, "learning_rate": 4.580971236855192e-06, "loss": 3.8583, "step": 2774016 }, { "epoch": 1.01, "learning_rate": 4.572585289344671e-06, "loss": 3.8542, "step": 2774528 }, { "epoch": 1.01, "learning_rate": 4.564199341834151e-06, "loss": 3.8542, "step": 2775040 }, { "epoch": 1.01, "learning_rate": 4.555829773127362e-06, "loss": 3.8482, "step": 2775552 }, { "epoch": 1.01, "learning_rate": 4.547460204420574e-06, "loss": 3.8587, "step": 2776064 }, { "epoch": 1.01, "learning_rate": 4.539074256910054e-06, "loss": 3.8496, "step": 2776576 }, { "epoch": 1.01, "learning_rate": 4.530688309399533e-06, "loss": 3.8588, "step": 2777088 }, { "epoch": 1.01, "learning_rate": 4.522302361889014e-06, "loss": 3.8695, "step": 2777600 }, { "epoch": 1.01, "learning_rate": 4.513916414378493e-06, "loss": 3.8501, "step": 2778112 }, { "epoch": 1.01, "learning_rate": 4.505530466867974e-06, "loss": 3.8425, "step": 2778624 }, { "epoch": 1.01, "learning_rate": 4.497144519357453e-06, "loss": 3.8654, "step": 2779136 }, { "epoch": 1.01, "learning_rate": 4.488758571846933e-06, "loss": 3.8358, "step": 2779648 }, { "epoch": 1.01, "learning_rate": 4.480372624336413e-06, "loss": 3.8499, "step": 2780160 }, { "epoch": 1.01, "learning_rate": 4.4720030556296245e-06, "loss": 3.8576, "step": 2780672 }, { "epoch": 1.01, "learning_rate": 4.463617108119104e-06, "loss": 3.858, "step": 2781184 }, { "epoch": 1.01, "learning_rate": 4.455231160608584e-06, "loss": 3.8519, "step": 2781696 }, { "epoch": 1.01, "learning_rate": 4.446845213098064e-06, "loss": 3.8492, "step": 2782208 }, { "epoch": 1.01, "learning_rate": 4.438459265587544e-06, "loss": 3.8364, "step": 2782720 }, { "epoch": 1.01, "learning_rate": 4.430089696880756e-06, "loss": 3.847, "step": 2783232 }, { "epoch": 1.01, "learning_rate": 4.421703749370235e-06, "loss": 3.8587, "step": 2783744 }, { "epoch": 1.01, "learning_rate": 4.413317801859715e-06, "loss": 3.8489, "step": 2784256 }, { "epoch": 1.01, "learning_rate": 4.404931854349195e-06, "loss": 3.8583, "step": 2784768 }, { "epoch": 1.01, "learning_rate": 4.396545906838675e-06, "loss": 3.8584, "step": 2785280 }, { "epoch": 1.01, "learning_rate": 4.388159959328155e-06, "loss": 3.8679, "step": 2785792 }, { "epoch": 1.01, "learning_rate": 4.3797903906213665e-06, "loss": 3.8494, "step": 2786304 }, { "epoch": 1.01, "learning_rate": 4.3714044431108464e-06, "loss": 3.8455, "step": 2786816 }, { "epoch": 1.01, "learning_rate": 4.363018495600326e-06, "loss": 3.8611, "step": 2787328 }, { "epoch": 1.01, "learning_rate": 4.3546325480898055e-06, "loss": 3.8481, "step": 2787840 }, { "epoch": 1.01, "learning_rate": 4.346246600579286e-06, "loss": 3.8652, "step": 2788352 }, { "epoch": 1.01, "learning_rate": 4.337860653068765e-06, "loss": 3.8521, "step": 2788864 }, { "epoch": 1.01, "learning_rate": 4.329474705558245e-06, "loss": 3.8534, "step": 2789376 }, { "epoch": 1.01, "learning_rate": 4.321088758047725e-06, "loss": 3.8594, "step": 2789888 }, { "epoch": 1.01, "learning_rate": 4.312702810537205e-06, "loss": 3.8413, "step": 2790400 }, { "epoch": 1.01, "learning_rate": 4.304333241830417e-06, "loss": 3.851, "step": 2790912 }, { "epoch": 1.01, "learning_rate": 4.295947294319896e-06, "loss": 3.8513, "step": 2791424 }, { "epoch": 1.01, "learning_rate": 4.287577725613108e-06, "loss": 3.8598, "step": 2791936 }, { "epoch": 1.01, "learning_rate": 4.279191778102588e-06, "loss": 3.8482, "step": 2792448 }, { "epoch": 1.01, "learning_rate": 4.270805830592068e-06, "loss": 3.8546, "step": 2792960 }, { "epoch": 1.02, "learning_rate": 4.2624198830815475e-06, "loss": 3.8479, "step": 2793472 }, { "epoch": 1.02, "learning_rate": 4.254050314374759e-06, "loss": 3.8498, "step": 2793984 }, { "epoch": 1.02, "learning_rate": 4.245664366864239e-06, "loss": 3.8426, "step": 2794496 }, { "epoch": 1.02, "learning_rate": 4.237278419353718e-06, "loss": 3.8552, "step": 2795008 }, { "epoch": 1.02, "learning_rate": 4.228892471843199e-06, "loss": 3.8626, "step": 2795520 }, { "epoch": 1.02, "learning_rate": 4.220506524332678e-06, "loss": 3.8557, "step": 2796032 }, { "epoch": 1.02, "learning_rate": 4.21213695562589e-06, "loss": 3.8593, "step": 2796544 }, { "epoch": 1.02, "learning_rate": 4.20375100811537e-06, "loss": 3.8462, "step": 2797056 }, { "epoch": 1.02, "learning_rate": 4.19536506060485e-06, "loss": 3.8511, "step": 2797568 }, { "epoch": 1.02, "learning_rate": 4.18697911309433e-06, "loss": 3.8538, "step": 2798080 }, { "epoch": 1.02, "learning_rate": 4.17859316558381e-06, "loss": 3.8601, "step": 2798592 }, { "epoch": 1.02, "learning_rate": 4.1702072180732896e-06, "loss": 3.8589, "step": 2799104 }, { "epoch": 1.02, "learning_rate": 4.1618376493665e-06, "loss": 3.8517, "step": 2799616 }, { "epoch": 1.02, "learning_rate": 4.153451701855981e-06, "loss": 3.8499, "step": 2800128 }, { "epoch": 1.02, "learning_rate": 4.14506575434546e-06, "loss": 3.8679, "step": 2800640 }, { "epoch": 1.02, "learning_rate": 4.136679806834941e-06, "loss": 3.8414, "step": 2801152 }, { "epoch": 1.02, "learning_rate": 4.12829385932442e-06, "loss": 3.8562, "step": 2801664 }, { "epoch": 1.02, "learning_rate": 4.119924290617632e-06, "loss": 3.847, "step": 2802176 }, { "epoch": 1.02, "learning_rate": 4.111538343107112e-06, "loss": 3.8561, "step": 2802688 }, { "epoch": 1.02, "learning_rate": 4.103152395596591e-06, "loss": 3.8477, "step": 2803200 }, { "epoch": 1.02, "learning_rate": 4.094766448086072e-06, "loss": 3.8562, "step": 2803712 }, { "epoch": 1.02, "learning_rate": 4.0863968793792825e-06, "loss": 3.8489, "step": 2804224 }, { "epoch": 1.02, "learning_rate": 4.078010931868763e-06, "loss": 3.8495, "step": 2804736 }, { "epoch": 1.02, "learning_rate": 4.069624984358242e-06, "loss": 3.8539, "step": 2805248 }, { "epoch": 1.02, "learning_rate": 4.061239036847723e-06, "loss": 3.8499, "step": 2805760 }, { "epoch": 1.02, "learning_rate": 4.052853089337202e-06, "loss": 3.8631, "step": 2806272 }, { "epoch": 1.02, "learning_rate": 4.044467141826682e-06, "loss": 3.8681, "step": 2806784 }, { "epoch": 1.02, "learning_rate": 4.036097573119894e-06, "loss": 3.856, "step": 2807296 }, { "epoch": 1.02, "learning_rate": 4.027711625609373e-06, "loss": 3.8556, "step": 2807808 }, { "epoch": 1.02, "learning_rate": 4.019325678098854e-06, "loss": 3.8463, "step": 2808320 }, { "epoch": 1.02, "learning_rate": 4.010939730588333e-06, "loss": 3.8502, "step": 2808832 }, { "epoch": 1.02, "learning_rate": 4.0025701618815445e-06, "loss": 3.8502, "step": 2809344 }, { "epoch": 1.02, "learning_rate": 3.9941842143710245e-06, "loss": 3.8661, "step": 2809856 }, { "epoch": 1.02, "learning_rate": 3.9857982668605045e-06, "loss": 3.836, "step": 2810368 }, { "epoch": 1.02, "learning_rate": 3.977412319349984e-06, "loss": 3.8564, "step": 2810880 }, { "epoch": 1.02, "learning_rate": 3.969026371839464e-06, "loss": 3.8548, "step": 2811392 }, { "epoch": 1.02, "learning_rate": 3.960640424328944e-06, "loss": 3.8596, "step": 2811904 }, { "epoch": 1.02, "learning_rate": 3.952270855622155e-06, "loss": 3.8502, "step": 2812416 }, { "epoch": 1.02, "learning_rate": 3.943884908111636e-06, "loss": 3.8531, "step": 2812928 }, { "epoch": 1.02, "learning_rate": 3.935498960601115e-06, "loss": 3.8476, "step": 2813440 }, { "epoch": 1.02, "learning_rate": 3.927113013090596e-06, "loss": 3.8638, "step": 2813952 }, { "epoch": 1.02, "learning_rate": 3.918727065580075e-06, "loss": 3.8613, "step": 2814464 }, { "epoch": 1.02, "learning_rate": 3.910341118069555e-06, "loss": 3.8639, "step": 2814976 }, { "epoch": 1.02, "learning_rate": 3.901955170559035e-06, "loss": 3.8468, "step": 2815488 }, { "epoch": 1.02, "learning_rate": 3.8935856018522465e-06, "loss": 3.863, "step": 2816000 }, { "epoch": 1.02, "learning_rate": 3.8851996543417264e-06, "loss": 3.8621, "step": 2816512 }, { "epoch": 1.02, "learning_rate": 3.876813706831206e-06, "loss": 3.851, "step": 2817024 }, { "epoch": 1.02, "learning_rate": 3.868427759320686e-06, "loss": 3.8554, "step": 2817536 }, { "epoch": 1.02, "learning_rate": 3.860041811810166e-06, "loss": 3.8631, "step": 2818048 }, { "epoch": 1.02, "learning_rate": 3.851655864299645e-06, "loss": 3.8547, "step": 2818560 }, { "epoch": 1.02, "learning_rate": 3.843269916789126e-06, "loss": 3.8776, "step": 2819072 }, { "epoch": 1.02, "learning_rate": 3.834900348082337e-06, "loss": 3.8487, "step": 2819584 }, { "epoch": 1.02, "learning_rate": 3.826514400571817e-06, "loss": 3.8609, "step": 2820096 }, { "epoch": 1.02, "learning_rate": 3.818128453061297e-06, "loss": 3.8517, "step": 2820608 }, { "epoch": 1.02, "learning_rate": 3.8097425055507773e-06, "loss": 3.8536, "step": 2821120 }, { "epoch": 1.02, "learning_rate": 3.801356558040257e-06, "loss": 3.8572, "step": 2821632 }, { "epoch": 1.02, "learning_rate": 3.7929706105297364e-06, "loss": 3.8526, "step": 2822144 }, { "epoch": 1.02, "learning_rate": 3.7845846630192167e-06, "loss": 3.8528, "step": 2822656 }, { "epoch": 1.02, "learning_rate": 3.7762150943124275e-06, "loss": 3.8428, "step": 2823168 }, { "epoch": 1.02, "learning_rate": 3.767829146801908e-06, "loss": 3.8554, "step": 2823680 }, { "epoch": 1.03, "eval_loss": 3.9831342697143555, "eval_runtime": 286.59, "eval_samples_per_second": 1331.487, "eval_steps_per_second": 41.61, "step": 2823840 }, { "epoch": 0.0, "learning_rate": 3.7594431992913874e-06, "loss": 3.8545, "step": 2824192 }, { "epoch": 0.0, "learning_rate": 3.751057251780867e-06, "loss": 3.8504, "step": 2824704 }, { "epoch": 0.0, "learning_rate": 3.7426713042703474e-06, "loss": 3.8629, "step": 2825216 }, { "epoch": 0.0, "learning_rate": 3.7342853567598273e-06, "loss": 3.8606, "step": 2825728 }, { "epoch": 0.0, "learning_rate": 3.7258994092493073e-06, "loss": 3.8669, "step": 2826240 }, { "epoch": 0.0, "learning_rate": 3.7175134617387872e-06, "loss": 3.8551, "step": 2826752 }, { "epoch": 0.0, "learning_rate": 3.7091275142282668e-06, "loss": 3.8575, "step": 2827264 }, { "epoch": 0.0, "learning_rate": 3.700741566717747e-06, "loss": 3.8445, "step": 2827776 }, { "epoch": 0.0, "learning_rate": 3.6923556192072267e-06, "loss": 3.8543, "step": 2828288 }, { "epoch": 0.0, "learning_rate": 3.683969671696707e-06, "loss": 3.8574, "step": 2828800 }, { "epoch": 0.0, "learning_rate": 3.6755837241861866e-06, "loss": 3.8566, "step": 2829312 }, { "epoch": 0.0, "learning_rate": 3.667197776675666e-06, "loss": 3.8532, "step": 2829824 }, { "epoch": 0.0, "learning_rate": 3.6588282079688777e-06, "loss": 3.8532, "step": 2830336 }, { "epoch": 0.0, "learning_rate": 3.6504422604583573e-06, "loss": 3.8545, "step": 2830848 }, { "epoch": 0.0, "learning_rate": 3.6420563129478377e-06, "loss": 3.8485, "step": 2831360 }, { "epoch": 0.0, "learning_rate": 3.633670365437317e-06, "loss": 3.8417, "step": 2831872 }, { "epoch": 0.0, "learning_rate": 3.625300796730529e-06, "loss": 3.8486, "step": 2832384 }, { "epoch": 0.0, "learning_rate": 3.6169148492200088e-06, "loss": 3.8563, "step": 2832896 }, { "epoch": 0.0, "learning_rate": 3.6085289017094887e-06, "loss": 3.8526, "step": 2833408 }, { "epoch": 0.0, "learning_rate": 3.6001429541989687e-06, "loss": 3.8702, "step": 2833920 }, { "epoch": 0.0, "learning_rate": 3.5917570066884482e-06, "loss": 3.8583, "step": 2834432 }, { "epoch": 0.0, "learning_rate": 3.5833710591779286e-06, "loss": 3.864, "step": 2834944 }, { "epoch": 0.0, "learning_rate": 3.574985111667408e-06, "loss": 3.8521, "step": 2835456 }, { "epoch": 0.0, "learning_rate": 3.5665991641568885e-06, "loss": 3.8554, "step": 2835968 }, { "epoch": 0.0, "learning_rate": 3.558213216646368e-06, "loss": 3.8536, "step": 2836480 }, { "epoch": 0.0, "learning_rate": 3.5498272691358476e-06, "loss": 3.8646, "step": 2836992 }, { "epoch": 0.0, "learning_rate": 3.5414577004290592e-06, "loss": 3.8501, "step": 2837504 }, { "epoch": 0.0, "learning_rate": 3.5330717529185387e-06, "loss": 3.8508, "step": 2838016 }, { "epoch": 0.0, "learning_rate": 3.524685805408019e-06, "loss": 3.8467, "step": 2838528 }, { "epoch": 0.0, "learning_rate": 3.5162998578974987e-06, "loss": 3.8552, "step": 2839040 }, { "epoch": 0.01, "learning_rate": 3.5079302891907107e-06, "loss": 3.8567, "step": 2839552 }, { "epoch": 0.01, "learning_rate": 3.4995443416801903e-06, "loss": 3.8603, "step": 2840064 }, { "epoch": 0.01, "learning_rate": 3.4911583941696706e-06, "loss": 3.8616, "step": 2840576 }, { "epoch": 0.01, "learning_rate": 3.48277244665915e-06, "loss": 3.8559, "step": 2841088 }, { "epoch": 0.01, "learning_rate": 3.474402877952362e-06, "loss": 3.8533, "step": 2841600 }, { "epoch": 0.01, "learning_rate": 3.4660333092455726e-06, "loss": 3.8637, "step": 2842112 }, { "epoch": 0.01, "learning_rate": 3.457647361735053e-06, "loss": 3.8589, "step": 2842624 }, { "epoch": 0.01, "learning_rate": 3.4492614142245325e-06, "loss": 3.8447, "step": 2843136 }, { "epoch": 0.01, "learning_rate": 3.440875466714012e-06, "loss": 3.8444, "step": 2843648 }, { "epoch": 0.01, "learning_rate": 3.4324895192034924e-06, "loss": 3.8435, "step": 2844160 }, { "epoch": 0.01, "learning_rate": 3.4241035716929724e-06, "loss": 3.8468, "step": 2844672 }, { "epoch": 0.01, "learning_rate": 3.4157176241824523e-06, "loss": 3.8633, "step": 2845184 }, { "epoch": 0.01, "learning_rate": 3.4073480554756635e-06, "loss": 3.8525, "step": 2845696 }, { "epoch": 0.01, "learning_rate": 3.398962107965144e-06, "loss": 3.8474, "step": 2846208 }, { "epoch": 0.01, "learning_rate": 3.3905761604546235e-06, "loss": 3.8583, "step": 2846720 }, { "epoch": 0.01, "learning_rate": 3.382190212944103e-06, "loss": 3.8498, "step": 2847232 }, { "epoch": 0.01, "learning_rate": 3.3738042654335834e-06, "loss": 3.855, "step": 2847744 }, { "epoch": 0.01, "learning_rate": 3.365418317923063e-06, "loss": 3.8465, "step": 2848256 }, { "epoch": 0.01, "learning_rate": 3.3570323704125433e-06, "loss": 3.8283, "step": 2848768 }, { "epoch": 0.01, "learning_rate": 3.348646422902023e-06, "loss": 3.8779, "step": 2849280 }, { "epoch": 0.01, "learning_rate": 3.3402604753915023e-06, "loss": 3.8571, "step": 2849792 }, { "epoch": 0.01, "learning_rate": 3.3318745278809827e-06, "loss": 3.8613, "step": 2850304 }, { "epoch": 0.01, "learning_rate": 3.323504959174194e-06, "loss": 3.8468, "step": 2850816 }, { "epoch": 0.01, "learning_rate": 3.315119011663674e-06, "loss": 3.8573, "step": 2851328 }, { "epoch": 0.01, "learning_rate": 3.306733064153154e-06, "loss": 3.847, "step": 2851840 }, { "epoch": 0.01, "learning_rate": 3.298347116642634e-06, "loss": 3.852, "step": 2852352 }, { "epoch": 0.01, "learning_rate": 3.2899611691321138e-06, "loss": 3.8518, "step": 2852864 }, { "epoch": 0.01, "learning_rate": 3.2815916004253254e-06, "loss": 3.8533, "step": 2853376 }, { "epoch": 0.01, "learning_rate": 3.273205652914805e-06, "loss": 3.8703, "step": 2853888 }, { "epoch": 0.01, "learning_rate": 3.2648197054042845e-06, "loss": 3.8466, "step": 2854400 }, { "epoch": 0.01, "learning_rate": 3.256433757893765e-06, "loss": 3.8385, "step": 2854912 }, { "epoch": 0.01, "learning_rate": 3.2480478103832444e-06, "loss": 3.863, "step": 2855424 }, { "epoch": 0.01, "learning_rate": 3.239678241676456e-06, "loss": 3.8343, "step": 2855936 }, { "epoch": 0.01, "learning_rate": 3.2312922941659355e-06, "loss": 3.8446, "step": 2856448 }, { "epoch": 0.01, "learning_rate": 3.222906346655416e-06, "loss": 3.8585, "step": 2856960 }, { "epoch": 0.01, "learning_rate": 3.2145203991448954e-06, "loss": 3.8569, "step": 2857472 }, { "epoch": 0.01, "learning_rate": 3.2061344516343754e-06, "loss": 3.8455, "step": 2857984 }, { "epoch": 0.01, "learning_rate": 3.1977485041238558e-06, "loss": 3.8529, "step": 2858496 }, { "epoch": 0.01, "learning_rate": 3.1893625566133353e-06, "loss": 3.8311, "step": 2859008 }, { "epoch": 0.01, "learning_rate": 3.180976609102815e-06, "loss": 3.8478, "step": 2859520 }, { "epoch": 0.01, "learning_rate": 3.1725906615922952e-06, "loss": 3.8546, "step": 2860032 }, { "epoch": 0.01, "learning_rate": 3.164221092885506e-06, "loss": 3.8434, "step": 2860544 }, { "epoch": 0.01, "learning_rate": 3.1558351453749864e-06, "loss": 3.8567, "step": 2861056 }, { "epoch": 0.01, "learning_rate": 3.147449197864466e-06, "loss": 3.8553, "step": 2861568 }, { "epoch": 0.01, "learning_rate": 3.1390632503539463e-06, "loss": 3.8685, "step": 2862080 }, { "epoch": 0.01, "learning_rate": 3.130693681647157e-06, "loss": 3.8458, "step": 2862592 }, { "epoch": 0.01, "learning_rate": 3.1223241129403687e-06, "loss": 3.8504, "step": 2863104 }, { "epoch": 0.01, "learning_rate": 3.1139545442335804e-06, "loss": 3.8592, "step": 2863616 }, { "epoch": 0.01, "learning_rate": 3.1055685967230603e-06, "loss": 3.845, "step": 2864128 }, { "epoch": 0.01, "learning_rate": 3.0971826492125403e-06, "loss": 3.859, "step": 2864640 }, { "epoch": 0.01, "learning_rate": 3.08879670170202e-06, "loss": 3.8521, "step": 2865152 }, { "epoch": 0.01, "learning_rate": 3.0804107541914998e-06, "loss": 3.8496, "step": 2865664 }, { "epoch": 0.01, "learning_rate": 3.0720248066809797e-06, "loss": 3.8591, "step": 2866176 }, { "epoch": 0.01, "learning_rate": 3.0636388591704597e-06, "loss": 3.8426, "step": 2866688 }, { "epoch": 0.01, "learning_rate": 3.0552529116599392e-06, "loss": 3.8438, "step": 2867200 }, { "epoch": 0.01, "learning_rate": 3.046866964149419e-06, "loss": 3.852, "step": 2867712 }, { "epoch": 0.01, "learning_rate": 3.038481016638899e-06, "loss": 3.8572, "step": 2868224 }, { "epoch": 0.01, "learning_rate": 3.030095069128379e-06, "loss": 3.8467, "step": 2868736 }, { "epoch": 0.01, "learning_rate": 3.0217255004215907e-06, "loss": 3.8509, "step": 2869248 }, { "epoch": 0.02, "learning_rate": 3.0133395529110707e-06, "loss": 3.8408, "step": 2869760 }, { "epoch": 0.02, "learning_rate": 3.0049536054005506e-06, "loss": 3.8498, "step": 2870272 }, { "epoch": 0.02, "learning_rate": 2.99656765789003e-06, "loss": 3.8419, "step": 2870784 }, { "epoch": 0.02, "learning_rate": 2.98818171037951e-06, "loss": 3.8525, "step": 2871296 }, { "epoch": 0.02, "learning_rate": 2.97979576286899e-06, "loss": 3.8663, "step": 2871808 }, { "epoch": 0.02, "learning_rate": 2.9714261941622013e-06, "loss": 3.852, "step": 2872320 }, { "epoch": 0.02, "learning_rate": 2.9630402466516812e-06, "loss": 3.8575, "step": 2872832 }, { "epoch": 0.02, "learning_rate": 2.954654299141161e-06, "loss": 3.845, "step": 2873344 }, { "epoch": 0.02, "learning_rate": 2.946268351630641e-06, "loss": 3.8483, "step": 2873856 }, { "epoch": 0.02, "learning_rate": 2.9378824041201207e-06, "loss": 3.8518, "step": 2874368 }, { "epoch": 0.02, "learning_rate": 2.9294964566096006e-06, "loss": 3.8596, "step": 2874880 }, { "epoch": 0.02, "learning_rate": 2.9211105090990806e-06, "loss": 3.8514, "step": 2875392 }, { "epoch": 0.02, "learning_rate": 2.9127245615885606e-06, "loss": 3.8572, "step": 2875904 }, { "epoch": 0.02, "learning_rate": 2.9043713716855035e-06, "loss": 3.8464, "step": 2876416 }, { "epoch": 0.02, "learning_rate": 2.8959854241749834e-06, "loss": 3.8609, "step": 2876928 }, { "epoch": 0.02, "learning_rate": 2.8875994766644634e-06, "loss": 3.8406, "step": 2877440 }, { "epoch": 0.02, "learning_rate": 2.8792135291539433e-06, "loss": 3.8539, "step": 2877952 }, { "epoch": 0.02, "learning_rate": 2.8708275816434233e-06, "loss": 3.842, "step": 2878464 }, { "epoch": 0.02, "learning_rate": 2.862441634132903e-06, "loss": 3.8585, "step": 2878976 }, { "epoch": 0.02, "learning_rate": 2.8540556866223828e-06, "loss": 3.8465, "step": 2879488 }, { "epoch": 0.02, "learning_rate": 2.8456697391118627e-06, "loss": 3.851, "step": 2880000 }, { "epoch": 0.02, "learning_rate": 2.837300170405074e-06, "loss": 3.8463, "step": 2880512 }, { "epoch": 0.02, "learning_rate": 2.828914222894554e-06, "loss": 3.8467, "step": 2881024 }, { "epoch": 0.02, "learning_rate": 2.8205446541877655e-06, "loss": 3.8484, "step": 2881536 }, { "epoch": 0.02, "learning_rate": 2.8121587066772455e-06, "loss": 3.8485, "step": 2882048 }, { "epoch": 0.02, "learning_rate": 2.8037727591667254e-06, "loss": 3.8582, "step": 2882560 }, { "epoch": 0.02, "learning_rate": 2.7953868116562054e-06, "loss": 3.8646, "step": 2883072 }, { "epoch": 0.02, "learning_rate": 2.7870172429494166e-06, "loss": 3.8561, "step": 2883584 }, { "epoch": 0.02, "learning_rate": 2.7786312954388966e-06, "loss": 3.8578, "step": 2884096 }, { "epoch": 0.02, "learning_rate": 2.770245347928376e-06, "loss": 3.8434, "step": 2884608 }, { "epoch": 0.02, "learning_rate": 2.761859400417856e-06, "loss": 3.8463, "step": 2885120 }, { "epoch": 0.02, "learning_rate": 2.753473452907336e-06, "loss": 3.851, "step": 2885632 }, { "epoch": 0.02, "learning_rate": 2.745087505396816e-06, "loss": 3.8595, "step": 2886144 }, { "epoch": 0.02, "learning_rate": 2.736717936690027e-06, "loss": 3.8338, "step": 2886656 }, { "epoch": 0.02, "learning_rate": 2.7283319891795076e-06, "loss": 3.8551, "step": 2887168 }, { "epoch": 0.02, "learning_rate": 2.719946041668987e-06, "loss": 3.8556, "step": 2887680 }, { "epoch": 0.02, "learning_rate": 2.711560094158467e-06, "loss": 3.8532, "step": 2888192 }, { "epoch": 0.02, "learning_rate": 2.703174146647947e-06, "loss": 3.8497, "step": 2888704 }, { "epoch": 0.02, "learning_rate": 2.694788199137427e-06, "loss": 3.8541, "step": 2889216 }, { "epoch": 0.02, "learning_rate": 2.686402251626907e-06, "loss": 3.8461, "step": 2889728 }, { "epoch": 0.02, "learning_rate": 2.6780163041163864e-06, "loss": 3.8604, "step": 2890240 }, { "epoch": 0.02, "learning_rate": 2.669646735409598e-06, "loss": 3.8571, "step": 2890752 }, { "epoch": 0.02, "learning_rate": 2.6612607878990776e-06, "loss": 3.8607, "step": 2891264 }, { "epoch": 0.02, "learning_rate": 2.6528912191922892e-06, "loss": 3.8428, "step": 2891776 }, { "epoch": 0.02, "learning_rate": 2.644505271681769e-06, "loss": 3.86, "step": 2892288 }, { "epoch": 0.02, "learning_rate": 2.636119324171249e-06, "loss": 3.8593, "step": 2892800 }, { "epoch": 0.02, "learning_rate": 2.627733376660729e-06, "loss": 3.8496, "step": 2893312 }, { "epoch": 0.02, "learning_rate": 2.619347429150209e-06, "loss": 3.8539, "step": 2893824 }, { "epoch": 0.02, "learning_rate": 2.610961481639689e-06, "loss": 3.8593, "step": 2894336 }, { "epoch": 0.02, "learning_rate": 2.6025755341291686e-06, "loss": 3.8566, "step": 2894848 }, { "epoch": 0.02, "learning_rate": 2.59420596542238e-06, "loss": 3.8686, "step": 2895360 }, { "epoch": 0.02, "learning_rate": 2.5858200179118597e-06, "loss": 3.8509, "step": 2895872 }, { "epoch": 0.02, "learning_rate": 2.5774340704013397e-06, "loss": 3.8567, "step": 2896384 }, { "epoch": 0.02, "learning_rate": 2.5690481228908196e-06, "loss": 3.8517, "step": 2896896 }, { "epoch": 0.02, "learning_rate": 2.5606621753802996e-06, "loss": 3.8536, "step": 2897408 }, { "epoch": 0.02, "learning_rate": 2.5522762278697795e-06, "loss": 3.849, "step": 2897920 }, { "epoch": 0.02, "learning_rate": 2.543890280359259e-06, "loss": 3.8483, "step": 2898432 }, { "epoch": 0.02, "learning_rate": 2.5355207116524707e-06, "loss": 3.8549, "step": 2898944 }, { "epoch": 0.02, "learning_rate": 2.5271511429456824e-06, "loss": 3.8393, "step": 2899456 }, { "epoch": 0.02, "learning_rate": 2.5187651954351623e-06, "loss": 3.8568, "step": 2899968 }, { "epoch": 0.03, "eval_loss": 3.9826278686523438, "eval_runtime": 282.3071, "eval_samples_per_second": 1351.687, "eval_steps_per_second": 42.241, "step": 2900160 }, { "epoch": 1.0, "learning_rate": 2.510379247924642e-06, "loss": 3.8547, "step": 2900480 }, { "epoch": 1.0, "learning_rate": 2.501993300414122e-06, "loss": 3.8492, "step": 2900992 }, { "epoch": 1.0, "learning_rate": 2.4936073529036018e-06, "loss": 3.8604, "step": 2901504 }, { "epoch": 1.0, "learning_rate": 2.485237784196813e-06, "loss": 3.8551, "step": 2902016 }, { "epoch": 1.0, "learning_rate": 2.476851836686293e-06, "loss": 3.8658, "step": 2902528 }, { "epoch": 1.0, "learning_rate": 2.468465889175773e-06, "loss": 3.8529, "step": 2903040 }, { "epoch": 1.0, "learning_rate": 2.4600799416652524e-06, "loss": 3.8549, "step": 2903552 }, { "epoch": 1.0, "learning_rate": 2.4516939941547324e-06, "loss": 3.8439, "step": 2904064 }, { "epoch": 1.0, "learning_rate": 2.4433080466442123e-06, "loss": 3.852, "step": 2904576 }, { "epoch": 1.0, "learning_rate": 2.434938477937424e-06, "loss": 3.8555, "step": 2905088 }, { "epoch": 1.0, "learning_rate": 2.426552530426904e-06, "loss": 3.8551, "step": 2905600 }, { "epoch": 1.0, "learning_rate": 2.418166582916384e-06, "loss": 3.8526, "step": 2906112 }, { "epoch": 1.0, "learning_rate": 2.409797014209595e-06, "loss": 3.8512, "step": 2906624 }, { "epoch": 1.0, "learning_rate": 2.401411066699075e-06, "loss": 3.8522, "step": 2907136 }, { "epoch": 1.0, "learning_rate": 2.393025119188555e-06, "loss": 3.851, "step": 2907648 }, { "epoch": 1.0, "learning_rate": 2.3846391716780345e-06, "loss": 3.8398, "step": 2908160 }, { "epoch": 1.0, "learning_rate": 2.3762532241675145e-06, "loss": 3.8479, "step": 2908672 }, { "epoch": 1.0, "learning_rate": 2.3678672766569944e-06, "loss": 3.8524, "step": 2909184 }, { "epoch": 1.0, "learning_rate": 2.3594813291464744e-06, "loss": 3.8531, "step": 2909696 }, { "epoch": 1.0, "learning_rate": 2.3510953816359544e-06, "loss": 3.8646, "step": 2910208 }, { "epoch": 1.0, "learning_rate": 2.342709434125434e-06, "loss": 3.8609, "step": 2910720 }, { "epoch": 1.0, "learning_rate": 2.3343234866149143e-06, "loss": 3.8624, "step": 2911232 }, { "epoch": 1.0, "learning_rate": 2.3259375391043942e-06, "loss": 3.8458, "step": 2911744 }, { "epoch": 1.0, "learning_rate": 2.317584349201337e-06, "loss": 3.8555, "step": 2912256 }, { "epoch": 1.0, "learning_rate": 2.3091984016908166e-06, "loss": 3.8529, "step": 2912768 }, { "epoch": 1.0, "learning_rate": 2.3008124541802966e-06, "loss": 3.862, "step": 2913280 }, { "epoch": 1.0, "learning_rate": 2.2924265066697766e-06, "loss": 3.8483, "step": 2913792 }, { "epoch": 1.0, "learning_rate": 2.2840405591592565e-06, "loss": 3.8516, "step": 2914304 }, { "epoch": 1.0, "learning_rate": 2.2756546116487365e-06, "loss": 3.8476, "step": 2914816 }, { "epoch": 1.0, "learning_rate": 2.267268664138216e-06, "loss": 3.8509, "step": 2915328 }, { "epoch": 1.01, "learning_rate": 2.258882716627696e-06, "loss": 3.8512, "step": 2915840 }, { "epoch": 1.01, "learning_rate": 2.250496769117176e-06, "loss": 3.8623, "step": 2916352 }, { "epoch": 1.01, "learning_rate": 2.2421272004103876e-06, "loss": 3.8592, "step": 2916864 }, { "epoch": 1.01, "learning_rate": 2.2337412528998675e-06, "loss": 3.8573, "step": 2917376 }, { "epoch": 1.01, "learning_rate": 2.2253553053893475e-06, "loss": 3.8508, "step": 2917888 }, { "epoch": 1.01, "learning_rate": 2.2169857366825587e-06, "loss": 3.8567, "step": 2918400 }, { "epoch": 1.01, "learning_rate": 2.2085997891720386e-06, "loss": 3.8575, "step": 2918912 }, { "epoch": 1.01, "learning_rate": 2.2002138416615186e-06, "loss": 3.8449, "step": 2919424 }, { "epoch": 1.01, "learning_rate": 2.191827894150998e-06, "loss": 3.8399, "step": 2919936 }, { "epoch": 1.01, "learning_rate": 2.183441946640478e-06, "loss": 3.8405, "step": 2920448 }, { "epoch": 1.01, "learning_rate": 2.175055999129958e-06, "loss": 3.8492, "step": 2920960 }, { "epoch": 1.01, "learning_rate": 2.166670051619438e-06, "loss": 3.8546, "step": 2921472 }, { "epoch": 1.01, "learning_rate": 2.1582841041089175e-06, "loss": 3.8524, "step": 2921984 }, { "epoch": 1.01, "learning_rate": 2.1498981565983975e-06, "loss": 3.8466, "step": 2922496 }, { "epoch": 1.01, "learning_rate": 2.1415122090878774e-06, "loss": 3.8513, "step": 2923008 }, { "epoch": 1.01, "learning_rate": 2.1331262615773574e-06, "loss": 3.8504, "step": 2923520 }, { "epoch": 1.01, "learning_rate": 2.1247403140668373e-06, "loss": 3.8543, "step": 2924032 }, { "epoch": 1.01, "learning_rate": 2.1163543665563173e-06, "loss": 3.844, "step": 2924544 }, { "epoch": 1.01, "learning_rate": 2.107984797849529e-06, "loss": 3.8272, "step": 2925056 }, { "epoch": 1.01, "learning_rate": 2.0995988503390085e-06, "loss": 3.8717, "step": 2925568 }, { "epoch": 1.01, "learning_rate": 2.09122928163222e-06, "loss": 3.8547, "step": 2926080 }, { "epoch": 1.01, "learning_rate": 2.0828433341216996e-06, "loss": 3.86, "step": 2926592 }, { "epoch": 1.01, "learning_rate": 2.0744573866111796e-06, "loss": 3.8481, "step": 2927104 }, { "epoch": 1.01, "learning_rate": 2.0660714391006595e-06, "loss": 3.8513, "step": 2927616 }, { "epoch": 1.01, "learning_rate": 2.0577018703938708e-06, "loss": 3.8453, "step": 2928128 }, { "epoch": 1.01, "learning_rate": 2.0493159228833507e-06, "loss": 3.8494, "step": 2928640 }, { "epoch": 1.01, "learning_rate": 2.0409299753728307e-06, "loss": 3.8528, "step": 2929152 }, { "epoch": 1.01, "learning_rate": 2.0325440278623106e-06, "loss": 3.8485, "step": 2929664 }, { "epoch": 1.01, "learning_rate": 2.0241580803517906e-06, "loss": 3.8681, "step": 2930176 }, { "epoch": 1.01, "learning_rate": 2.0157721328412705e-06, "loss": 3.8476, "step": 2930688 }, { "epoch": 1.01, "learning_rate": 2.0073861853307505e-06, "loss": 3.8369, "step": 2931200 }, { "epoch": 1.01, "learning_rate": 1.9990166166239617e-06, "loss": 3.8631, "step": 2931712 }, { "epoch": 1.01, "learning_rate": 1.990647047917173e-06, "loss": 3.8348, "step": 2932224 }, { "epoch": 1.01, "learning_rate": 1.982261100406653e-06, "loss": 3.8358, "step": 2932736 }, { "epoch": 1.01, "learning_rate": 1.973875152896133e-06, "loss": 3.8638, "step": 2933248 }, { "epoch": 1.01, "learning_rate": 1.965489205385613e-06, "loss": 3.8555, "step": 2933760 }, { "epoch": 1.01, "learning_rate": 1.9571032578750927e-06, "loss": 3.8432, "step": 2934272 }, { "epoch": 1.01, "learning_rate": 1.9487173103645723e-06, "loss": 3.8538, "step": 2934784 }, { "epoch": 1.01, "learning_rate": 1.9403313628540527e-06, "loss": 3.8302, "step": 2935296 }, { "epoch": 1.01, "learning_rate": 1.9319454153435326e-06, "loss": 3.8468, "step": 2935808 }, { "epoch": 1.01, "learning_rate": 1.923575846636744e-06, "loss": 3.8485, "step": 2936320 }, { "epoch": 1.01, "learning_rate": 1.9151898991262238e-06, "loss": 3.8436, "step": 2936832 }, { "epoch": 1.01, "learning_rate": 1.9068039516157037e-06, "loss": 3.8529, "step": 2937344 }, { "epoch": 1.01, "learning_rate": 1.8984180041051837e-06, "loss": 3.8523, "step": 2937856 }, { "epoch": 1.01, "learning_rate": 1.8900320565946632e-06, "loss": 3.8648, "step": 2938368 }, { "epoch": 1.01, "learning_rate": 1.8816461090841432e-06, "loss": 3.8469, "step": 2938880 }, { "epoch": 1.01, "learning_rate": 1.8732601615736231e-06, "loss": 3.8487, "step": 2939392 }, { "epoch": 1.01, "learning_rate": 1.8648905928668346e-06, "loss": 3.8557, "step": 2939904 }, { "epoch": 1.01, "learning_rate": 1.8565046453563145e-06, "loss": 3.8444, "step": 2940416 }, { "epoch": 1.01, "learning_rate": 1.8481186978457945e-06, "loss": 3.8546, "step": 2940928 }, { "epoch": 1.01, "learning_rate": 1.839732750335274e-06, "loss": 3.8507, "step": 2941440 }, { "epoch": 1.01, "learning_rate": 1.8313631816284856e-06, "loss": 3.8466, "step": 2941952 }, { "epoch": 1.01, "learning_rate": 1.8229772341179654e-06, "loss": 3.8618, "step": 2942464 }, { "epoch": 1.01, "learning_rate": 1.8145912866074453e-06, "loss": 3.8383, "step": 2942976 }, { "epoch": 1.01, "learning_rate": 1.8062053390969253e-06, "loss": 3.8425, "step": 2943488 }, { "epoch": 1.01, "learning_rate": 1.7978193915864053e-06, "loss": 3.8532, "step": 2944000 }, { "epoch": 1.01, "learning_rate": 1.7894334440758852e-06, "loss": 3.855, "step": 2944512 }, { "epoch": 1.01, "learning_rate": 1.7810474965653647e-06, "loss": 3.8474, "step": 2945024 }, { "epoch": 1.01, "learning_rate": 1.7726615490548447e-06, "loss": 3.8515, "step": 2945536 }, { "epoch": 1.02, "learning_rate": 1.7642919803480561e-06, "loss": 3.8367, "step": 2946048 }, { "epoch": 1.02, "learning_rate": 1.755906032837536e-06, "loss": 3.8475, "step": 2946560 }, { "epoch": 1.02, "learning_rate": 1.7475364641307473e-06, "loss": 3.8418, "step": 2947072 }, { "epoch": 1.02, "learning_rate": 1.7391505166202272e-06, "loss": 3.8507, "step": 2947584 }, { "epoch": 1.02, "learning_rate": 1.7307645691097072e-06, "loss": 3.8633, "step": 2948096 }, { "epoch": 1.02, "learning_rate": 1.7223786215991872e-06, "loss": 3.8494, "step": 2948608 }, { "epoch": 1.02, "learning_rate": 1.7139926740886671e-06, "loss": 3.8554, "step": 2949120 }, { "epoch": 1.02, "learning_rate": 1.7056067265781469e-06, "loss": 3.8418, "step": 2949632 }, { "epoch": 1.02, "learning_rate": 1.6972207790676268e-06, "loss": 3.845, "step": 2950144 }, { "epoch": 1.02, "learning_rate": 1.6888348315571068e-06, "loss": 3.8467, "step": 2950656 }, { "epoch": 1.02, "learning_rate": 1.680465262850318e-06, "loss": 3.8593, "step": 2951168 }, { "epoch": 1.02, "learning_rate": 1.672079315339798e-06, "loss": 3.853, "step": 2951680 }, { "epoch": 1.02, "learning_rate": 1.663693367829278e-06, "loss": 3.8549, "step": 2952192 }, { "epoch": 1.02, "learning_rate": 1.6553237991224893e-06, "loss": 3.8426, "step": 2952704 }, { "epoch": 1.02, "learning_rate": 1.6469378516119693e-06, "loss": 3.8575, "step": 2953216 }, { "epoch": 1.02, "learning_rate": 1.6385519041014492e-06, "loss": 3.8423, "step": 2953728 }, { "epoch": 1.02, "learning_rate": 1.6301659565909288e-06, "loss": 3.8514, "step": 2954240 }, { "epoch": 1.02, "learning_rate": 1.6217800090804087e-06, "loss": 3.8379, "step": 2954752 }, { "epoch": 1.02, "learning_rate": 1.6133940615698889e-06, "loss": 3.854, "step": 2955264 }, { "epoch": 1.02, "learning_rate": 1.6050081140593688e-06, "loss": 3.8447, "step": 2955776 }, { "epoch": 1.02, "learning_rate": 1.5966221665488488e-06, "loss": 3.8501, "step": 2956288 }, { "epoch": 1.02, "learning_rate": 1.5882362190383283e-06, "loss": 3.8405, "step": 2956800 }, { "epoch": 1.02, "learning_rate": 1.5798502715278083e-06, "loss": 3.8514, "step": 2957312 }, { "epoch": 1.02, "learning_rate": 1.5714643240172882e-06, "loss": 3.843, "step": 2957824 }, { "epoch": 1.02, "learning_rate": 1.5630947553104997e-06, "loss": 3.846, "step": 2958336 }, { "epoch": 1.02, "learning_rate": 1.5547088077999796e-06, "loss": 3.8602, "step": 2958848 }, { "epoch": 1.02, "learning_rate": 1.5463228602894594e-06, "loss": 3.8624, "step": 2959360 }, { "epoch": 1.02, "learning_rate": 1.5379369127789393e-06, "loss": 3.8562, "step": 2959872 }, { "epoch": 1.02, "learning_rate": 1.5295509652684193e-06, "loss": 3.8492, "step": 2960384 }, { "epoch": 1.02, "learning_rate": 1.521165017757899e-06, "loss": 3.8431, "step": 2960896 }, { "epoch": 1.02, "learning_rate": 1.512779070247379e-06, "loss": 3.8443, "step": 2961408 }, { "epoch": 1.02, "learning_rate": 1.5043931227368587e-06, "loss": 3.8509, "step": 2961920 }, { "epoch": 1.02, "learning_rate": 1.4960235540300704e-06, "loss": 3.8537, "step": 2962432 }, { "epoch": 1.02, "learning_rate": 1.48763760651955e-06, "loss": 3.8369, "step": 2962944 }, { "epoch": 1.02, "learning_rate": 1.47925165900903e-06, "loss": 3.8535, "step": 2963456 }, { "epoch": 1.02, "learning_rate": 1.4708657114985098e-06, "loss": 3.8536, "step": 2963968 }, { "epoch": 1.02, "learning_rate": 1.4624797639879898e-06, "loss": 3.8508, "step": 2964480 }, { "epoch": 1.02, "learning_rate": 1.4541265740849327e-06, "loss": 3.849, "step": 2964992 }, { "epoch": 1.02, "learning_rate": 1.4457406265744126e-06, "loss": 3.8485, "step": 2965504 }, { "epoch": 1.02, "learning_rate": 1.4373710578676238e-06, "loss": 3.8417, "step": 2966016 }, { "epoch": 1.02, "learning_rate": 1.4289851103571038e-06, "loss": 3.86, "step": 2966528 }, { "epoch": 1.02, "learning_rate": 1.4205991628465837e-06, "loss": 3.8569, "step": 2967040 }, { "epoch": 1.02, "learning_rate": 1.4122132153360637e-06, "loss": 3.8568, "step": 2967552 }, { "epoch": 1.02, "learning_rate": 1.4038272678255436e-06, "loss": 3.8417, "step": 2968064 }, { "epoch": 1.02, "learning_rate": 1.3954413203150234e-06, "loss": 3.86, "step": 2968576 }, { "epoch": 1.02, "learning_rate": 1.3870553728045033e-06, "loss": 3.8561, "step": 2969088 }, { "epoch": 1.02, "learning_rate": 1.378669425293983e-06, "loss": 3.8465, "step": 2969600 }, { "epoch": 1.02, "learning_rate": 1.3702998565871947e-06, "loss": 3.8544, "step": 2970112 }, { "epoch": 1.02, "learning_rate": 1.3619139090766745e-06, "loss": 3.8559, "step": 2970624 }, { "epoch": 1.02, "learning_rate": 1.3535279615661544e-06, "loss": 3.8536, "step": 2971136 }, { "epoch": 1.02, "learning_rate": 1.3451420140556342e-06, "loss": 3.8681, "step": 2971648 }, { "epoch": 1.02, "learning_rate": 1.3367560665451141e-06, "loss": 3.8475, "step": 2972160 }, { "epoch": 1.02, "learning_rate": 1.328370119034594e-06, "loss": 3.8563, "step": 2972672 }, { "epoch": 1.02, "learning_rate": 1.3199841715240738e-06, "loss": 3.8545, "step": 2973184 }, { "epoch": 1.02, "learning_rate": 1.3115982240135538e-06, "loss": 3.8524, "step": 2973696 }, { "epoch": 1.02, "learning_rate": 1.3032286553067652e-06, "loss": 3.8429, "step": 2974208 }, { "epoch": 1.02, "learning_rate": 1.2948427077962452e-06, "loss": 3.8435, "step": 2974720 }, { "epoch": 1.02, "learning_rate": 1.2864731390894564e-06, "loss": 3.849, "step": 2975232 }, { "epoch": 1.02, "learning_rate": 1.2780871915789363e-06, "loss": 3.8419, "step": 2975744 }, { "epoch": 1.02, "learning_rate": 1.2697012440684163e-06, "loss": 3.8537, "step": 2976256 }, { "epoch": 1.03, "eval_loss": 3.9823386669158936, "eval_runtime": 281.454, "eval_samples_per_second": 1355.785, "eval_steps_per_second": 42.369, "step": 2976480 }, { "epoch": 2.0, "learning_rate": 1.2613152965578962e-06, "loss": 3.8519, "step": 2976768 }, { "epoch": 2.0, "learning_rate": 1.2529293490473762e-06, "loss": 3.8484, "step": 2977280 }, { "epoch": 2.0, "learning_rate": 1.244543401536856e-06, "loss": 3.8551, "step": 2977792 }, { "epoch": 2.0, "learning_rate": 1.2361738328300674e-06, "loss": 3.8542, "step": 2978304 }, { "epoch": 2.0, "learning_rate": 1.2277878853195473e-06, "loss": 3.8629, "step": 2978816 }, { "epoch": 2.0, "learning_rate": 1.2194019378090273e-06, "loss": 3.8503, "step": 2979328 }, { "epoch": 2.0, "learning_rate": 1.211015990298507e-06, "loss": 3.8561, "step": 2979840 }, { "epoch": 2.0, "learning_rate": 1.202630042787987e-06, "loss": 3.8454, "step": 2980352 }, { "epoch": 2.0, "learning_rate": 1.1942440952774667e-06, "loss": 3.8445, "step": 2980864 }, { "epoch": 2.0, "learning_rate": 1.1858581477669467e-06, "loss": 3.8597, "step": 2981376 }, { "epoch": 2.0, "learning_rate": 1.1774722002564266e-06, "loss": 3.8507, "step": 2981888 }, { "epoch": 2.0, "learning_rate": 1.169102631549638e-06, "loss": 3.8483, "step": 2982400 }, { "epoch": 2.0, "learning_rate": 1.1607330628428493e-06, "loss": 3.8581, "step": 2982912 }, { "epoch": 2.0, "learning_rate": 1.1523471153323292e-06, "loss": 3.8446, "step": 2983424 }, { "epoch": 2.0, "learning_rate": 1.1439611678218092e-06, "loss": 3.8441, "step": 2983936 }, { "epoch": 2.0, "learning_rate": 1.135575220311289e-06, "loss": 3.8406, "step": 2984448 }, { "epoch": 2.0, "learning_rate": 1.1271892728007689e-06, "loss": 3.8457, "step": 2984960 }, { "epoch": 2.0, "learning_rate": 1.1188033252902488e-06, "loss": 3.8507, "step": 2985472 }, { "epoch": 2.0, "learning_rate": 1.1104173777797288e-06, "loss": 3.8442, "step": 2985984 }, { "epoch": 2.0, "learning_rate": 1.1020314302692088e-06, "loss": 3.864, "step": 2986496 }, { "epoch": 2.0, "learning_rate": 1.0936454827586885e-06, "loss": 3.8579, "step": 2987008 }, { "epoch": 2.0, "learning_rate": 1.0852595352481684e-06, "loss": 3.859, "step": 2987520 }, { "epoch": 2.0, "learning_rate": 1.0768735877376482e-06, "loss": 3.848, "step": 2988032 }, { "epoch": 2.0, "learning_rate": 1.0685040190308598e-06, "loss": 3.8477, "step": 2988544 }, { "epoch": 2.0, "learning_rate": 1.0601180715203396e-06, "loss": 3.8554, "step": 2989056 }, { "epoch": 2.0, "learning_rate": 1.0517321240098195e-06, "loss": 3.8563, "step": 2989568 }, { "epoch": 2.0, "learning_rate": 1.0433461764992993e-06, "loss": 3.8461, "step": 2990080 }, { "epoch": 2.0, "learning_rate": 1.0349602289887792e-06, "loss": 3.8511, "step": 2990592 }, { "epoch": 2.0, "learning_rate": 1.0265742814782592e-06, "loss": 3.8426, "step": 2991104 }, { "epoch": 2.0, "learning_rate": 1.018188333967739e-06, "loss": 3.8486, "step": 2991616 }, { "epoch": 2.01, "learning_rate": 1.0098023864572189e-06, "loss": 3.8503, "step": 2992128 }, { "epoch": 2.01, "learning_rate": 1.0014328177504303e-06, "loss": 3.8606, "step": 2992640 }, { "epoch": 2.01, "learning_rate": 9.930468702399103e-07, "loss": 3.858, "step": 2993152 }, { "epoch": 2.01, "learning_rate": 9.8466092272939e-07, "loss": 3.8575, "step": 2993664 }, { "epoch": 2.01, "learning_rate": 9.7627497521887e-07, "loss": 3.8517, "step": 2994176 }, { "epoch": 2.01, "learning_rate": 9.679217853158129e-07, "loss": 3.8549, "step": 2994688 }, { "epoch": 2.01, "learning_rate": 9.595358378052928e-07, "loss": 3.856, "step": 2995200 }, { "epoch": 2.01, "learning_rate": 9.511498902947726e-07, "loss": 3.8438, "step": 2995712 }, { "epoch": 2.01, "learning_rate": 9.427639427842525e-07, "loss": 3.8407, "step": 2996224 }, { "epoch": 2.01, "learning_rate": 9.343779952737325e-07, "loss": 3.8364, "step": 2996736 }, { "epoch": 2.01, "learning_rate": 9.259920477632123e-07, "loss": 3.8457, "step": 2997248 }, { "epoch": 2.01, "learning_rate": 9.176224790564237e-07, "loss": 3.8486, "step": 2997760 }, { "epoch": 2.01, "learning_rate": 9.092365315459036e-07, "loss": 3.8544, "step": 2998272 }, { "epoch": 2.01, "learning_rate": 9.008505840353836e-07, "loss": 3.8479, "step": 2998784 }, { "epoch": 2.01, "learning_rate": 8.924646365248633e-07, "loss": 3.8474, "step": 2999296 }, { "epoch": 2.01, "learning_rate": 8.840786890143434e-07, "loss": 3.8498, "step": 2999808 }, { "epoch": 2.01, "learning_rate": 8.756927415038231e-07, "loss": 3.8552, "step": 3000320 }, { "epoch": 2.01, "learning_rate": 8.673067939933031e-07, "loss": 3.8409, "step": 3000832 }, { "epoch": 2.01, "learning_rate": 8.58920846482783e-07, "loss": 3.8269, "step": 3001344 }, { "epoch": 2.01, "learning_rate": 8.505348989722629e-07, "loss": 3.8631, "step": 3001856 }, { "epoch": 2.01, "learning_rate": 8.421489514617428e-07, "loss": 3.8544, "step": 3002368 }, { "epoch": 2.01, "learning_rate": 8.337630039512226e-07, "loss": 3.8601, "step": 3002880 }, { "epoch": 2.01, "learning_rate": 8.253770564407025e-07, "loss": 3.8472, "step": 3003392 }, { "epoch": 2.01, "learning_rate": 8.169911089301825e-07, "loss": 3.8487, "step": 3003904 }, { "epoch": 2.01, "learning_rate": 8.086215402233938e-07, "loss": 3.8456, "step": 3004416 }, { "epoch": 2.01, "learning_rate": 8.002519715166051e-07, "loss": 3.8467, "step": 3004928 }, { "epoch": 2.01, "learning_rate": 7.918660240060851e-07, "loss": 3.8539, "step": 3005440 }, { "epoch": 2.01, "learning_rate": 7.83480076495565e-07, "loss": 3.8401, "step": 3005952 }, { "epoch": 2.01, "learning_rate": 7.750941289850449e-07, "loss": 3.8696, "step": 3006464 }, { "epoch": 2.01, "learning_rate": 7.667081814745247e-07, "loss": 3.8503, "step": 3006976 }, { "epoch": 2.01, "learning_rate": 7.583222339640047e-07, "loss": 3.832, "step": 3007488 }, { "epoch": 2.01, "learning_rate": 7.499362864534846e-07, "loss": 3.86, "step": 3008000 }, { "epoch": 2.01, "learning_rate": 7.415503389429645e-07, "loss": 3.8352, "step": 3008512 }, { "epoch": 2.01, "learning_rate": 7.331807702361759e-07, "loss": 3.8348, "step": 3009024 }, { "epoch": 2.01, "learning_rate": 7.247948227256558e-07, "loss": 3.8608, "step": 3009536 }, { "epoch": 2.01, "learning_rate": 7.164252540188671e-07, "loss": 3.8518, "step": 3010048 }, { "epoch": 2.01, "learning_rate": 7.08039306508347e-07, "loss": 3.8423, "step": 3010560 }, { "epoch": 2.01, "learning_rate": 6.996533589978269e-07, "loss": 3.8484, "step": 3011072 }, { "epoch": 2.01, "learning_rate": 6.912674114873067e-07, "loss": 3.8304, "step": 3011584 }, { "epoch": 2.01, "learning_rate": 6.828978427805182e-07, "loss": 3.8448, "step": 3012096 }, { "epoch": 2.01, "learning_rate": 6.74511895269998e-07, "loss": 3.8504, "step": 3012608 }, { "epoch": 2.01, "learning_rate": 6.66125947759478e-07, "loss": 3.8425, "step": 3013120 }, { "epoch": 2.01, "learning_rate": 6.577400002489579e-07, "loss": 3.8517, "step": 3013632 }, { "epoch": 2.01, "learning_rate": 6.493540527384378e-07, "loss": 3.8499, "step": 3014144 }, { "epoch": 2.01, "learning_rate": 6.409681052279176e-07, "loss": 3.8631, "step": 3014656 }, { "epoch": 2.01, "learning_rate": 6.32598536521129e-07, "loss": 3.8424, "step": 3015168 }, { "epoch": 2.01, "learning_rate": 6.242125890106089e-07, "loss": 3.8499, "step": 3015680 }, { "epoch": 2.01, "learning_rate": 6.158266415000889e-07, "loss": 3.8517, "step": 3016192 }, { "epoch": 2.01, "learning_rate": 6.074406939895687e-07, "loss": 3.8408, "step": 3016704 }, { "epoch": 2.01, "learning_rate": 5.990547464790486e-07, "loss": 3.854, "step": 3017216 }, { "epoch": 2.01, "learning_rate": 5.9068517777226e-07, "loss": 3.8491, "step": 3017728 }, { "epoch": 2.01, "learning_rate": 5.822992302617398e-07, "loss": 3.8416, "step": 3018240 }, { "epoch": 2.01, "learning_rate": 5.739132827512197e-07, "loss": 3.8608, "step": 3018752 }, { "epoch": 2.01, "learning_rate": 5.655273352406996e-07, "loss": 3.8355, "step": 3019264 }, { "epoch": 2.01, "learning_rate": 5.571741453376425e-07, "loss": 3.8389, "step": 3019776 }, { "epoch": 2.01, "learning_rate": 5.487881978271224e-07, "loss": 3.8513, "step": 3020288 }, { "epoch": 2.01, "learning_rate": 5.404022503166022e-07, "loss": 3.8502, "step": 3020800 }, { "epoch": 2.01, "learning_rate": 5.320163028060822e-07, "loss": 3.8455, "step": 3021312 }, { "epoch": 2.01, "learning_rate": 5.236303552955621e-07, "loss": 3.8528, "step": 3021824 }, { "epoch": 2.02, "learning_rate": 5.15244407785042e-07, "loss": 3.8365, "step": 3022336 }, { "epoch": 2.02, "learning_rate": 5.068748390782534e-07, "loss": 3.841, "step": 3022848 }, { "epoch": 2.02, "learning_rate": 4.984888915677333e-07, "loss": 3.8421, "step": 3023360 }, { "epoch": 2.02, "learning_rate": 4.901029440572131e-07, "loss": 3.8445, "step": 3023872 }, { "epoch": 2.02, "learning_rate": 4.817169965466931e-07, "loss": 3.8618, "step": 3024384 }, { "epoch": 2.02, "learning_rate": 4.733310490361729e-07, "loss": 3.8474, "step": 3024896 }, { "epoch": 2.02, "learning_rate": 4.649451015256529e-07, "loss": 3.855, "step": 3025408 }, { "epoch": 2.02, "learning_rate": 4.5655915401513273e-07, "loss": 3.8413, "step": 3025920 }, { "epoch": 2.02, "learning_rate": 4.4817320650461263e-07, "loss": 3.8448, "step": 3026432 }, { "epoch": 2.02, "learning_rate": 4.397872589940925e-07, "loss": 3.847, "step": 3026944 }, { "epoch": 2.02, "learning_rate": 4.314013114835724e-07, "loss": 3.8538, "step": 3027456 }, { "epoch": 2.02, "learning_rate": 4.230153639730523e-07, "loss": 3.8522, "step": 3027968 }, { "epoch": 2.02, "learning_rate": 4.1464579526626366e-07, "loss": 3.8526, "step": 3028480 }, { "epoch": 2.02, "learning_rate": 4.0625984775574356e-07, "loss": 3.846, "step": 3028992 }, { "epoch": 2.02, "learning_rate": 3.978739002452235e-07, "loss": 3.8493, "step": 3029504 }, { "epoch": 2.02, "learning_rate": 3.8948795273470337e-07, "loss": 3.8453, "step": 3030016 }, { "epoch": 2.02, "learning_rate": 3.8110200522418327e-07, "loss": 3.8476, "step": 3030528 }, { "epoch": 2.02, "learning_rate": 3.727160577136631e-07, "loss": 3.8363, "step": 3031040 }, { "epoch": 2.02, "learning_rate": 3.643301102031431e-07, "loss": 3.8568, "step": 3031552 }, { "epoch": 2.02, "learning_rate": 3.559441626926229e-07, "loss": 3.8406, "step": 3032064 }, { "epoch": 2.02, "learning_rate": 3.4757459398583435e-07, "loss": 3.8459, "step": 3032576 }, { "epoch": 2.02, "learning_rate": 3.3920502527904567e-07, "loss": 3.8372, "step": 3033088 }, { "epoch": 2.02, "learning_rate": 3.308190777685256e-07, "loss": 3.8486, "step": 3033600 }, { "epoch": 2.02, "learning_rate": 3.224331302580055e-07, "loss": 3.8434, "step": 3034112 }, { "epoch": 2.02, "learning_rate": 3.140471827474854e-07, "loss": 3.8452, "step": 3034624 }, { "epoch": 2.02, "learning_rate": 3.056612352369653e-07, "loss": 3.8542, "step": 3035136 }, { "epoch": 2.02, "learning_rate": 2.972752877264452e-07, "loss": 3.8626, "step": 3035648 }, { "epoch": 2.02, "learning_rate": 2.889057190196565e-07, "loss": 3.8611, "step": 3036160 }, { "epoch": 2.02, "learning_rate": 2.8051977150913646e-07, "loss": 3.8462, "step": 3036672 }, { "epoch": 2.02, "learning_rate": 2.721338239986163e-07, "loss": 3.8396, "step": 3037184 }, { "epoch": 2.02, "learning_rate": 2.6374787648809626e-07, "loss": 3.8411, "step": 3037696 }, { "epoch": 2.02, "learning_rate": 2.553619289775761e-07, "loss": 3.8491, "step": 3038208 }, { "epoch": 2.02, "learning_rate": 2.46975981467056e-07, "loss": 3.8525, "step": 3038720 }, { "epoch": 2.02, "learning_rate": 2.385900339565359e-07, "loss": 3.8345, "step": 3039232 }, { "epoch": 2.02, "learning_rate": 2.302204652497473e-07, "loss": 3.8526, "step": 3039744 }, { "epoch": 2.02, "learning_rate": 2.2183451773922717e-07, "loss": 3.8543, "step": 3040256 }, { "epoch": 2.02, "learning_rate": 2.1344857022870707e-07, "loss": 3.8457, "step": 3040768 }, { "epoch": 2.02, "learning_rate": 2.0506262271818697e-07, "loss": 3.8482, "step": 3041280 }, { "epoch": 2.02, "learning_rate": 1.9667667520766688e-07, "loss": 3.8532, "step": 3041792 }, { "epoch": 2.02, "learning_rate": 1.8830710650087822e-07, "loss": 3.8419, "step": 3042304 }, { "epoch": 2.02, "learning_rate": 1.799375377940896e-07, "loss": 3.8555, "step": 3042816 }, { "epoch": 2.02, "learning_rate": 1.715515902835695e-07, "loss": 3.8513, "step": 3043328 }, { "epoch": 2.02, "learning_rate": 1.631656427730494e-07, "loss": 3.8584, "step": 3043840 }, { "epoch": 2.02, "learning_rate": 1.547796952625293e-07, "loss": 3.8412, "step": 3044352 }, { "epoch": 2.02, "learning_rate": 1.4639374775200918e-07, "loss": 3.8572, "step": 3044864 }, { "epoch": 2.02, "learning_rate": 1.3800780024148908e-07, "loss": 3.8553, "step": 3045376 }, { "epoch": 2.02, "learning_rate": 1.2962185273096899e-07, "loss": 3.8471, "step": 3045888 }, { "epoch": 2.02, "learning_rate": 1.2123590522044886e-07, "loss": 3.8518, "step": 3046400 }, { "epoch": 2.02, "learning_rate": 1.1286633651366025e-07, "loss": 3.8497, "step": 3046912 }, { "epoch": 2.02, "learning_rate": 1.0448038900314015e-07, "loss": 3.8528, "step": 3047424 }, { "epoch": 2.02, "learning_rate": 9.609444149262004e-08, "loss": 3.8692, "step": 3047936 }, { "epoch": 2.02, "learning_rate": 8.770849398209994e-08, "loss": 3.8428, "step": 3048448 }, { "epoch": 2.02, "learning_rate": 7.932254647157983e-08, "loss": 3.856, "step": 3048960 }, { "epoch": 2.02, "learning_rate": 7.093659896105972e-08, "loss": 3.8509, "step": 3049472 }, { "epoch": 2.02, "learning_rate": 6.25670302542711e-08, "loss": 3.8508, "step": 3049984 }, { "epoch": 2.02, "learning_rate": 5.4181082743751004e-08, "loss": 3.8444, "step": 3050496 }, { "epoch": 2.02, "learning_rate": 4.5795135233230893e-08, "loss": 3.8408, "step": 3051008 }, { "epoch": 2.02, "learning_rate": 3.740918772271079e-08, "loss": 3.8515, "step": 3051520 }, { "epoch": 2.02, "learning_rate": 2.9039619015922166e-08, "loss": 3.8385, "step": 3052032 }, { "epoch": 2.02, "learning_rate": 2.065367150540206e-08, "loss": 3.8532, "step": 3052544 }, { "epoch": 2.02, "eval_loss": 3.9820053577423096, "eval_runtime": 282.2546, "eval_samples_per_second": 1351.939, "eval_steps_per_second": 42.249, "step": 3052726 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.2374818165235333e+18, "trial_name": null, "trial_params": null }