Invalid JSON: Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_metric": 3.302588701248169, | |
| "best_model_checkpoint": "/scratch/cl5625/exceptions/models/100M_495/checkpoint-90000", | |
| "epoch": 10.0, | |
| "eval_steps": 1000, | |
| "global_step": 92910, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005381552039608223, | |
| "grad_norm": 12.074577331542969, | |
| "learning_rate": 0.0003, | |
| "loss": 8.6374, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010763104079216447, | |
| "grad_norm": 1.3158553838729858, | |
| "learning_rate": 0.0006, | |
| "loss": 6.8912, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01614465611882467, | |
| "grad_norm": 2.628305196762085, | |
| "learning_rate": 0.0005996767589699385, | |
| "loss": 6.4839, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.021526208158432893, | |
| "grad_norm": 1.0599905252456665, | |
| "learning_rate": 0.0005993535179398771, | |
| "loss": 6.2264, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026907760198041114, | |
| "grad_norm": 1.638780951499939, | |
| "learning_rate": 0.0005990302769098158, | |
| "loss": 6.0419, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03228931223764934, | |
| "grad_norm": 1.9191187620162964, | |
| "learning_rate": 0.0005987070358797543, | |
| "loss": 5.955, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03767086427725756, | |
| "grad_norm": 1.12886643409729, | |
| "learning_rate": 0.0005983837948496929, | |
| "loss": 5.8538, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04305241631686579, | |
| "grad_norm": 1.3254728317260742, | |
| "learning_rate": 0.0005980605538196314, | |
| "loss": 5.7663, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.048433968356474004, | |
| "grad_norm": 2.3004322052001953, | |
| "learning_rate": 0.0005977373127895701, | |
| "loss": 5.6952, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.05381552039608223, | |
| "grad_norm": 1.495474934577942, | |
| "learning_rate": 0.0005974140717595086, | |
| "loss": 5.6341, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05919707243569045, | |
| "grad_norm": 0.9526841640472412, | |
| "learning_rate": 0.0005970908307294472, | |
| "loss": 5.5508, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.06457862447529868, | |
| "grad_norm": 1.1846691370010376, | |
| "learning_rate": 0.0005967675896993858, | |
| "loss": 5.4745, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0699601765149069, | |
| "grad_norm": 1.5218234062194824, | |
| "learning_rate": 0.0005964443486693243, | |
| "loss": 5.4167, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.07534172855451512, | |
| "grad_norm": 1.037400484085083, | |
| "learning_rate": 0.000596121107639263, | |
| "loss": 5.3214, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.08072328059412334, | |
| "grad_norm": 1.1252976655960083, | |
| "learning_rate": 0.0005957978666092015, | |
| "loss": 5.3002, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.08610483263373157, | |
| "grad_norm": 0.9828529953956604, | |
| "learning_rate": 0.0005954746255791401, | |
| "loss": 5.224, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.09148638467333979, | |
| "grad_norm": 1.4241634607315063, | |
| "learning_rate": 0.0005951513845490787, | |
| "loss": 5.2284, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.09686793671294801, | |
| "grad_norm": 1.0950024127960205, | |
| "learning_rate": 0.0005948281435190174, | |
| "loss": 5.1559, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.10224948875255624, | |
| "grad_norm": 0.8689674735069275, | |
| "learning_rate": 0.0005945049024889559, | |
| "loss": 5.1198, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.10763104079216446, | |
| "grad_norm": 0.8567312955856323, | |
| "learning_rate": 0.0005941816614588944, | |
| "loss": 5.0633, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10763104079216446, | |
| "eval_accuracy": 0.22941774764519313, | |
| "eval_loss": 4.999941825866699, | |
| "eval_runtime": 181.8712, | |
| "eval_samples_per_second": 99.032, | |
| "eval_steps_per_second": 6.191, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11301259283177269, | |
| "grad_norm": 1.0926947593688965, | |
| "learning_rate": 0.000593858420428833, | |
| "loss": 5.0126, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.1183941448713809, | |
| "grad_norm": 1.079075813293457, | |
| "learning_rate": 0.0005935351793987716, | |
| "loss": 4.9581, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.12377569691098914, | |
| "grad_norm": 1.9798409938812256, | |
| "learning_rate": 0.0005932119383687103, | |
| "loss": 4.9724, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.12915724895059735, | |
| "grad_norm": 1.3321768045425415, | |
| "learning_rate": 0.0005928886973386488, | |
| "loss": 4.9741, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.13453880099020557, | |
| "grad_norm": 1.1671667098999023, | |
| "learning_rate": 0.0005925654563085874, | |
| "loss": 4.9051, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.1399203530298138, | |
| "grad_norm": 0.8295050263404846, | |
| "learning_rate": 0.000592242215278526, | |
| "loss": 4.9002, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.14530190506942203, | |
| "grad_norm": 1.0559158325195312, | |
| "learning_rate": 0.0005919189742484645, | |
| "loss": 4.8626, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.15068345710903025, | |
| "grad_norm": 1.2337747812271118, | |
| "learning_rate": 0.0005915957332184032, | |
| "loss": 4.851, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.15606500914863847, | |
| "grad_norm": 1.0464680194854736, | |
| "learning_rate": 0.0005912724921883417, | |
| "loss": 4.8242, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.16144656118824668, | |
| "grad_norm": 0.8018038868904114, | |
| "learning_rate": 0.0005909492511582803, | |
| "loss": 4.7894, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1668281132278549, | |
| "grad_norm": 1.5508265495300293, | |
| "learning_rate": 0.0005906260101282189, | |
| "loss": 4.74, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.17220966526746315, | |
| "grad_norm": 0.9371482133865356, | |
| "learning_rate": 0.0005903027690981575, | |
| "loss": 4.7316, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.17759121730707136, | |
| "grad_norm": 1.0305496454238892, | |
| "learning_rate": 0.000589979528068096, | |
| "loss": 4.7221, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.18297276934667958, | |
| "grad_norm": 0.90619957447052, | |
| "learning_rate": 0.0005896562870380347, | |
| "loss": 4.7063, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.1883543213862878, | |
| "grad_norm": 1.0820300579071045, | |
| "learning_rate": 0.0005893330460079732, | |
| "loss": 4.668, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.19373587342589602, | |
| "grad_norm": 0.857718825340271, | |
| "learning_rate": 0.0005890098049779118, | |
| "loss": 4.6453, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.19911742546550426, | |
| "grad_norm": 0.9784050583839417, | |
| "learning_rate": 0.0005886865639478504, | |
| "loss": 4.6397, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.20449897750511248, | |
| "grad_norm": 0.9087166786193848, | |
| "learning_rate": 0.0005883633229177889, | |
| "loss": 4.6246, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.2098805295447207, | |
| "grad_norm": 0.9737820029258728, | |
| "learning_rate": 0.0005880400818877276, | |
| "loss": 4.6047, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.2152620815843289, | |
| "grad_norm": 0.8255292773246765, | |
| "learning_rate": 0.0005877168408576662, | |
| "loss": 4.5492, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2152620815843289, | |
| "eval_accuracy": 0.27245189692187455, | |
| "eval_loss": 4.491321563720703, | |
| "eval_runtime": 181.6962, | |
| "eval_samples_per_second": 99.127, | |
| "eval_steps_per_second": 6.197, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22064363362393713, | |
| "grad_norm": 0.7951588034629822, | |
| "learning_rate": 0.0005873935998276048, | |
| "loss": 4.5555, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.22602518566354537, | |
| "grad_norm": 0.8975157141685486, | |
| "learning_rate": 0.0005870703587975433, | |
| "loss": 4.5375, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.2314067377031536, | |
| "grad_norm": 1.0026023387908936, | |
| "learning_rate": 0.0005867471177674818, | |
| "loss": 4.5323, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.2367882897427618, | |
| "grad_norm": 0.803642988204956, | |
| "learning_rate": 0.0005864238767374205, | |
| "loss": 4.4924, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.24216984178237003, | |
| "grad_norm": 1.0086907148361206, | |
| "learning_rate": 0.0005861006357073591, | |
| "loss": 4.5072, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.24755139382197827, | |
| "grad_norm": 0.8211397528648376, | |
| "learning_rate": 0.0005857773946772977, | |
| "loss": 4.4681, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.2529329458615865, | |
| "grad_norm": 0.7603225111961365, | |
| "learning_rate": 0.0005854541536472362, | |
| "loss": 4.4691, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.2583144979011947, | |
| "grad_norm": 0.8533746004104614, | |
| "learning_rate": 0.0005851309126171749, | |
| "loss": 4.4473, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.2636960499408029, | |
| "grad_norm": 1.300952434539795, | |
| "learning_rate": 0.0005848076715871134, | |
| "loss": 4.4076, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.26907760198041114, | |
| "grad_norm": 0.7179780006408691, | |
| "learning_rate": 0.000584484430557052, | |
| "loss": 4.4134, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.27445915402001936, | |
| "grad_norm": 0.8938673734664917, | |
| "learning_rate": 0.0005841611895269906, | |
| "loss": 4.4109, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.2798407060596276, | |
| "grad_norm": 0.8200742602348328, | |
| "learning_rate": 0.0005838379484969291, | |
| "loss": 4.4013, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.2852222580992358, | |
| "grad_norm": 0.8515391945838928, | |
| "learning_rate": 0.0005835147074668678, | |
| "loss": 4.3763, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.29060381013884407, | |
| "grad_norm": 0.8918663859367371, | |
| "learning_rate": 0.0005831914664368063, | |
| "loss": 4.3774, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.2959853621784523, | |
| "grad_norm": 0.6826805472373962, | |
| "learning_rate": 0.0005828682254067449, | |
| "loss": 4.3631, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.3013669142180605, | |
| "grad_norm": 0.7818616628646851, | |
| "learning_rate": 0.0005825449843766835, | |
| "loss": 4.3313, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.3067484662576687, | |
| "grad_norm": 0.7908890843391418, | |
| "learning_rate": 0.0005822217433466221, | |
| "loss": 4.3407, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.31213001829727693, | |
| "grad_norm": 1.1532859802246094, | |
| "learning_rate": 0.0005818985023165607, | |
| "loss": 4.3188, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.31751157033688515, | |
| "grad_norm": 0.7944912910461426, | |
| "learning_rate": 0.0005815752612864992, | |
| "loss": 4.3062, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.32289312237649337, | |
| "grad_norm": 0.7332167029380798, | |
| "learning_rate": 0.0005812520202564378, | |
| "loss": 4.2863, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.32289312237649337, | |
| "eval_accuracy": 0.29881217403454574, | |
| "eval_loss": 4.233547687530518, | |
| "eval_runtime": 181.7872, | |
| "eval_samples_per_second": 99.077, | |
| "eval_steps_per_second": 6.194, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3282746744161016, | |
| "grad_norm": 0.6582856774330139, | |
| "learning_rate": 0.0005809287792263764, | |
| "loss": 4.3131, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.3336562264557098, | |
| "grad_norm": 0.7379726767539978, | |
| "learning_rate": 0.0005806055381963151, | |
| "loss": 4.2889, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.3390377784953181, | |
| "grad_norm": 0.7286725640296936, | |
| "learning_rate": 0.0005802822971662536, | |
| "loss": 4.287, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.3444193305349263, | |
| "grad_norm": 0.7306691408157349, | |
| "learning_rate": 0.0005799590561361922, | |
| "loss": 4.2596, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.3498008825745345, | |
| "grad_norm": 0.6126540303230286, | |
| "learning_rate": 0.0005796358151061307, | |
| "loss": 4.2404, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.35518243461414273, | |
| "grad_norm": 0.7405567765235901, | |
| "learning_rate": 0.0005793125740760694, | |
| "loss": 4.253, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.36056398665375095, | |
| "grad_norm": 0.8209679126739502, | |
| "learning_rate": 0.0005789893330460079, | |
| "loss": 4.2517, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.36594553869335916, | |
| "grad_norm": 0.7422078847885132, | |
| "learning_rate": 0.0005786660920159465, | |
| "loss": 4.2362, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.3713270907329674, | |
| "grad_norm": 0.6978297233581543, | |
| "learning_rate": 0.0005783428509858851, | |
| "loss": 4.2293, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.3767086427725756, | |
| "grad_norm": 0.7036471962928772, | |
| "learning_rate": 0.0005780196099558237, | |
| "loss": 4.2389, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.3820901948121838, | |
| "grad_norm": 0.8010238409042358, | |
| "learning_rate": 0.0005776963689257623, | |
| "loss": 4.2198, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.38747174685179203, | |
| "grad_norm": 0.6499230265617371, | |
| "learning_rate": 0.0005773731278957008, | |
| "loss": 4.1941, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.3928532988914003, | |
| "grad_norm": 0.7018994688987732, | |
| "learning_rate": 0.0005770498868656394, | |
| "loss": 4.2102, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.3982348509310085, | |
| "grad_norm": 0.6573231816291809, | |
| "learning_rate": 0.000576726645835578, | |
| "loss": 4.1892, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.40361640297061674, | |
| "grad_norm": 0.6301137804985046, | |
| "learning_rate": 0.0005764034048055167, | |
| "loss": 4.1782, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.40899795501022496, | |
| "grad_norm": 0.6420815587043762, | |
| "learning_rate": 0.0005760801637754552, | |
| "loss": 4.1881, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.4143795070498332, | |
| "grad_norm": 0.7286609411239624, | |
| "learning_rate": 0.0005757569227453937, | |
| "loss": 4.1681, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.4197610590894414, | |
| "grad_norm": 0.7999758720397949, | |
| "learning_rate": 0.0005754336817153324, | |
| "loss": 4.1663, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.4251426111290496, | |
| "grad_norm": 0.681491494178772, | |
| "learning_rate": 0.0005751104406852709, | |
| "loss": 4.1526, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.4305241631686578, | |
| "grad_norm": 0.8898637890815735, | |
| "learning_rate": 0.0005747871996552096, | |
| "loss": 4.1472, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4305241631686578, | |
| "eval_accuracy": 0.31332352777238437, | |
| "eval_loss": 4.088411808013916, | |
| "eval_runtime": 182.0558, | |
| "eval_samples_per_second": 98.931, | |
| "eval_steps_per_second": 6.185, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.43590571520826604, | |
| "grad_norm": 1.0454559326171875, | |
| "learning_rate": 0.0005744639586251481, | |
| "loss": 4.174, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.44128726724787426, | |
| "grad_norm": 0.7238677144050598, | |
| "learning_rate": 0.0005741407175950867, | |
| "loss": 4.1417, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.44666881928748253, | |
| "grad_norm": 0.6636929512023926, | |
| "learning_rate": 0.0005738174765650253, | |
| "loss": 4.14, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.45205037132709075, | |
| "grad_norm": 0.553901195526123, | |
| "learning_rate": 0.0005734942355349638, | |
| "loss": 4.1244, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.45743192336669897, | |
| "grad_norm": 0.7060267925262451, | |
| "learning_rate": 0.0005731709945049025, | |
| "loss": 4.1363, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.4628134754063072, | |
| "grad_norm": 0.6566117405891418, | |
| "learning_rate": 0.000572847753474841, | |
| "loss": 4.1328, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.4681950274459154, | |
| "grad_norm": 0.663583517074585, | |
| "learning_rate": 0.0005725245124447796, | |
| "loss": 4.1281, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.4735765794855236, | |
| "grad_norm": 0.797214925289154, | |
| "learning_rate": 0.0005722012714147182, | |
| "loss": 4.1199, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.47895813152513184, | |
| "grad_norm": 0.6216398477554321, | |
| "learning_rate": 0.0005718780303846568, | |
| "loss": 4.1097, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.48433968356474005, | |
| "grad_norm": 0.7291539907455444, | |
| "learning_rate": 0.0005715547893545953, | |
| "loss": 4.0946, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.48972123560434827, | |
| "grad_norm": 0.6444728374481201, | |
| "learning_rate": 0.000571231548324534, | |
| "loss": 4.0871, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.49510278764395654, | |
| "grad_norm": 0.6845434308052063, | |
| "learning_rate": 0.0005709083072944725, | |
| "loss": 4.0885, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.5004843396835648, | |
| "grad_norm": 0.7555699944496155, | |
| "learning_rate": 0.0005705850662644111, | |
| "loss": 4.0955, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.505865891723173, | |
| "grad_norm": 0.7021520733833313, | |
| "learning_rate": 0.0005702618252343497, | |
| "loss": 4.0961, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.5112474437627812, | |
| "grad_norm": 0.5818867087364197, | |
| "learning_rate": 0.0005699385842042882, | |
| "loss": 4.0799, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.5166289958023894, | |
| "grad_norm": 0.665334939956665, | |
| "learning_rate": 0.0005696153431742269, | |
| "loss": 4.0524, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.5220105478419976, | |
| "grad_norm": 0.6017621755599976, | |
| "learning_rate": 0.0005692921021441655, | |
| "loss": 4.0778, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.5273920998816058, | |
| "grad_norm": 0.6869152188301086, | |
| "learning_rate": 0.0005689688611141041, | |
| "loss": 4.0557, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.5327736519212141, | |
| "grad_norm": 0.7289915680885315, | |
| "learning_rate": 0.0005686456200840426, | |
| "loss": 4.0789, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.5381552039608223, | |
| "grad_norm": 0.6597164869308472, | |
| "learning_rate": 0.0005683223790539811, | |
| "loss": 4.062, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5381552039608223, | |
| "eval_accuracy": 0.32235986249325127, | |
| "eval_loss": 3.9826269149780273, | |
| "eval_runtime": 181.7213, | |
| "eval_samples_per_second": 99.113, | |
| "eval_steps_per_second": 6.196, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5435367560004305, | |
| "grad_norm": 0.6261274218559265, | |
| "learning_rate": 0.0005679991380239198, | |
| "loss": 4.0553, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.5489183080400387, | |
| "grad_norm": 0.649811863899231, | |
| "learning_rate": 0.0005676823618144596, | |
| "loss": 4.0688, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.5542998600796469, | |
| "grad_norm": 0.6599764823913574, | |
| "learning_rate": 0.0005673591207843981, | |
| "loss": 4.0458, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.5596814121192552, | |
| "grad_norm": 0.5525273680686951, | |
| "learning_rate": 0.0005670358797543368, | |
| "loss": 4.032, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.5650629641588634, | |
| "grad_norm": 0.5733092427253723, | |
| "learning_rate": 0.0005667126387242753, | |
| "loss": 4.0628, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.5704445161984716, | |
| "grad_norm": 0.6523923277854919, | |
| "learning_rate": 0.000566389397694214, | |
| "loss": 4.0207, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.5758260682380799, | |
| "grad_norm": 0.5884820222854614, | |
| "learning_rate": 0.0005660661566641525, | |
| "loss": 4.0289, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.5812076202776881, | |
| "grad_norm": 0.6992023587226868, | |
| "learning_rate": 0.0005657429156340911, | |
| "loss": 4.0149, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.5865891723172963, | |
| "grad_norm": 0.6001935601234436, | |
| "learning_rate": 0.0005654196746040297, | |
| "loss": 4.0226, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.5919707243569046, | |
| "grad_norm": 0.7079454660415649, | |
| "learning_rate": 0.0005650964335739684, | |
| "loss": 4.0292, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.5973522763965128, | |
| "grad_norm": 0.6667420864105225, | |
| "learning_rate": 0.0005647731925439069, | |
| "loss": 3.9974, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.602733828436121, | |
| "grad_norm": 0.589589536190033, | |
| "learning_rate": 0.0005644499515138454, | |
| "loss": 4.0047, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.6081153804757292, | |
| "grad_norm": 0.6412240266799927, | |
| "learning_rate": 0.000564126710483784, | |
| "loss": 3.9956, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.6134969325153374, | |
| "grad_norm": 0.6452463269233704, | |
| "learning_rate": 0.0005638034694537226, | |
| "loss": 3.9969, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.6188784845549457, | |
| "grad_norm": 0.634573221206665, | |
| "learning_rate": 0.0005634802284236612, | |
| "loss": 3.9971, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.6242600365945539, | |
| "grad_norm": 0.6738696694374084, | |
| "learning_rate": 0.0005631569873935998, | |
| "loss": 3.9907, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.6296415886341621, | |
| "grad_norm": 0.6989587545394897, | |
| "learning_rate": 0.0005628337463635384, | |
| "loss": 4.0001, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.6350231406737703, | |
| "grad_norm": 0.7382339239120483, | |
| "learning_rate": 0.0005625105053334769, | |
| "loss": 3.9866, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.6404046927133785, | |
| "grad_norm": 0.6265085339546204, | |
| "learning_rate": 0.0005621872643034155, | |
| "loss": 3.965, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.6457862447529867, | |
| "grad_norm": 0.675687313079834, | |
| "learning_rate": 0.0005618640232733541, | |
| "loss": 3.9919, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6457862447529867, | |
| "eval_accuracy": 0.3284569192929609, | |
| "eval_loss": 3.910811424255371, | |
| "eval_runtime": 181.5773, | |
| "eval_samples_per_second": 99.192, | |
| "eval_steps_per_second": 6.201, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.651167796792595, | |
| "grad_norm": 0.6309311389923096, | |
| "learning_rate": 0.0005615407822432927, | |
| "loss": 3.9811, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.6565493488322032, | |
| "grad_norm": 0.5584713220596313, | |
| "learning_rate": 0.0005612175412132313, | |
| "loss": 3.9619, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.6619309008718114, | |
| "grad_norm": 0.5973617434501648, | |
| "learning_rate": 0.0005608943001831699, | |
| "loss": 3.9528, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.6673124529114196, | |
| "grad_norm": 0.6784116625785828, | |
| "learning_rate": 0.0005605710591531085, | |
| "loss": 3.9584, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.6726940049510278, | |
| "grad_norm": 0.5735004544258118, | |
| "learning_rate": 0.000560247818123047, | |
| "loss": 3.9522, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.6780755569906362, | |
| "grad_norm": 0.6804719567298889, | |
| "learning_rate": 0.0005599245770929855, | |
| "loss": 3.9563, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.6834571090302444, | |
| "grad_norm": 0.6392138004302979, | |
| "learning_rate": 0.0005596013360629242, | |
| "loss": 3.9444, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.6888386610698526, | |
| "grad_norm": 0.5223947763442993, | |
| "learning_rate": 0.0005592780950328628, | |
| "loss": 3.9685, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.6942202131094608, | |
| "grad_norm": 0.6110231280326843, | |
| "learning_rate": 0.0005589548540028014, | |
| "loss": 3.9501, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.699601765149069, | |
| "grad_norm": 0.6495262980461121, | |
| "learning_rate": 0.0005586316129727399, | |
| "loss": 3.9733, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.7049833171886772, | |
| "grad_norm": 0.5392972230911255, | |
| "learning_rate": 0.0005583083719426786, | |
| "loss": 3.9475, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.7103648692282855, | |
| "grad_norm": 0.5373910665512085, | |
| "learning_rate": 0.0005579851309126171, | |
| "loss": 3.9475, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.7157464212678937, | |
| "grad_norm": 0.5609496235847473, | |
| "learning_rate": 0.0005576618898825558, | |
| "loss": 3.9292, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.7211279733075019, | |
| "grad_norm": 0.5721986293792725, | |
| "learning_rate": 0.0005573386488524943, | |
| "loss": 3.9432, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.7265095253471101, | |
| "grad_norm": 0.5666886568069458, | |
| "learning_rate": 0.0005570154078224328, | |
| "loss": 3.9348, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.7318910773867183, | |
| "grad_norm": 0.5143133997917175, | |
| "learning_rate": 0.0005566921667923715, | |
| "loss": 3.9322, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.7372726294263265, | |
| "grad_norm": 0.5764801502227783, | |
| "learning_rate": 0.00055636892576231, | |
| "loss": 3.9196, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.7426541814659348, | |
| "grad_norm": 0.6438068151473999, | |
| "learning_rate": 0.0005560456847322487, | |
| "loss": 3.9207, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.748035733505543, | |
| "grad_norm": 0.547141432762146, | |
| "learning_rate": 0.0005557224437021872, | |
| "loss": 3.9211, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.7534172855451512, | |
| "grad_norm": 0.5400163531303406, | |
| "learning_rate": 0.0005553992026721258, | |
| "loss": 3.912, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.7534172855451512, | |
| "eval_accuracy": 0.3342374702304669, | |
| "eval_loss": 3.858619451522827, | |
| "eval_runtime": 181.854, | |
| "eval_samples_per_second": 99.041, | |
| "eval_steps_per_second": 6.192, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.7587988375847594, | |
| "grad_norm": 0.6468452215194702, | |
| "learning_rate": 0.0005550759616420644, | |
| "loss": 3.9213, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.7641803896243676, | |
| "grad_norm": 0.8306963443756104, | |
| "learning_rate": 0.000554752720612003, | |
| "loss": 3.9261, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.7695619416639758, | |
| "grad_norm": 0.5487331748008728, | |
| "learning_rate": 0.0005544294795819415, | |
| "loss": 3.9015, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.7749434937035841, | |
| "grad_norm": 0.5448126196861267, | |
| "learning_rate": 0.0005541062385518801, | |
| "loss": 3.9063, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.7803250457431924, | |
| "grad_norm": 0.5569677948951721, | |
| "learning_rate": 0.0005537829975218188, | |
| "loss": 3.9022, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.7857065977828006, | |
| "grad_norm": 0.5910586714744568, | |
| "learning_rate": 0.0005534597564917573, | |
| "loss": 3.9111, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.7910881498224088, | |
| "grad_norm": 0.75867760181427, | |
| "learning_rate": 0.0005531365154616959, | |
| "loss": 3.9149, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.796469701862017, | |
| "grad_norm": 0.5806201696395874, | |
| "learning_rate": 0.0005528132744316344, | |
| "loss": 3.8975, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.8018512539016253, | |
| "grad_norm": 0.5979334115982056, | |
| "learning_rate": 0.0005524900334015731, | |
| "loss": 3.9194, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.8072328059412335, | |
| "grad_norm": 0.6362331509590149, | |
| "learning_rate": 0.0005521667923715117, | |
| "loss": 3.8981, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8126143579808417, | |
| "grad_norm": 0.5838714838027954, | |
| "learning_rate": 0.0005518435513414502, | |
| "loss": 3.8961, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.8179959100204499, | |
| "grad_norm": 0.7832590937614441, | |
| "learning_rate": 0.0005515203103113888, | |
| "loss": 3.8931, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.8233774620600581, | |
| "grad_norm": 0.5615019798278809, | |
| "learning_rate": 0.0005511970692813274, | |
| "loss": 3.8981, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.8287590140996663, | |
| "grad_norm": 0.6099148392677307, | |
| "learning_rate": 0.000550873828251266, | |
| "loss": 3.8941, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.8341405661392746, | |
| "grad_norm": 0.5140008330345154, | |
| "learning_rate": 0.0005505505872212045, | |
| "loss": 3.8796, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.8395221181788828, | |
| "grad_norm": 0.6559896469116211, | |
| "learning_rate": 0.0005502273461911432, | |
| "loss": 3.8723, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.844903670218491, | |
| "grad_norm": 0.557579517364502, | |
| "learning_rate": 0.0005499041051610817, | |
| "loss": 3.8736, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.8502852222580992, | |
| "grad_norm": 0.6086620688438416, | |
| "learning_rate": 0.0005495808641310204, | |
| "loss": 3.9014, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.8556667742977074, | |
| "grad_norm": 0.6662868857383728, | |
| "learning_rate": 0.0005492576231009589, | |
| "loss": 3.8747, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.8610483263373157, | |
| "grad_norm": 1.007802963256836, | |
| "learning_rate": 0.0005489343820708974, | |
| "loss": 3.862, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.8610483263373157, | |
| "eval_accuracy": 0.33844711771595115, | |
| "eval_loss": 3.811176061630249, | |
| "eval_runtime": 181.8668, | |
| "eval_samples_per_second": 99.034, | |
| "eval_steps_per_second": 6.191, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.8664298783769239, | |
| "grad_norm": 0.5262889266014099, | |
| "learning_rate": 0.0005486111410408361, | |
| "loss": 3.8806, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.8718114304165321, | |
| "grad_norm": 0.5448309183120728, | |
| "learning_rate": 0.0005482879000107746, | |
| "loss": 3.8702, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.5762999057769775, | |
| "learning_rate": 0.0005479646589807133, | |
| "loss": 3.8735, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.8825745344957485, | |
| "grad_norm": 1.141692876815796, | |
| "learning_rate": 0.0005476414179506518, | |
| "loss": 3.8806, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.8879560865353568, | |
| "grad_norm": 0.5628105998039246, | |
| "learning_rate": 0.0005473181769205904, | |
| "loss": 3.8622, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.8933376385749651, | |
| "grad_norm": 0.5854573249816895, | |
| "learning_rate": 0.000546994935890529, | |
| "loss": 3.8763, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.8987191906145733, | |
| "grad_norm": 0.5357927083969116, | |
| "learning_rate": 0.0005466716948604677, | |
| "loss": 3.8505, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.9041007426541815, | |
| "grad_norm": 0.6378769874572754, | |
| "learning_rate": 0.0005463484538304062, | |
| "loss": 3.845, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.9094822946937897, | |
| "grad_norm": 0.6226728558540344, | |
| "learning_rate": 0.0005460252128003447, | |
| "loss": 3.8583, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.9148638467333979, | |
| "grad_norm": 0.5731797218322754, | |
| "learning_rate": 0.0005457019717702833, | |
| "loss": 3.8498, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.9202453987730062, | |
| "grad_norm": 0.6198984384536743, | |
| "learning_rate": 0.0005453787307402219, | |
| "loss": 3.8389, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.9256269508126144, | |
| "grad_norm": 0.600885272026062, | |
| "learning_rate": 0.0005450554897101605, | |
| "loss": 3.8547, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.9310085028522226, | |
| "grad_norm": 0.5399230122566223, | |
| "learning_rate": 0.0005447322486800991, | |
| "loss": 3.8578, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.9363900548918308, | |
| "grad_norm": 0.5042197108268738, | |
| "learning_rate": 0.0005444090076500377, | |
| "loss": 3.8613, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.941771606931439, | |
| "grad_norm": 0.5343637466430664, | |
| "learning_rate": 0.0005440857666199763, | |
| "loss": 3.8458, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.9471531589710472, | |
| "grad_norm": 0.5491181015968323, | |
| "learning_rate": 0.0005437625255899148, | |
| "loss": 3.8335, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.9525347110106555, | |
| "grad_norm": 0.5667814612388611, | |
| "learning_rate": 0.0005434392845598534, | |
| "loss": 3.845, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.9579162630502637, | |
| "grad_norm": 0.5124309659004211, | |
| "learning_rate": 0.000543116043529792, | |
| "loss": 3.8512, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.9632978150898719, | |
| "grad_norm": 0.5880436301231384, | |
| "learning_rate": 0.0005427928024997306, | |
| "loss": 3.8386, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.9686793671294801, | |
| "grad_norm": 0.5593850016593933, | |
| "learning_rate": 0.0005424695614696692, | |
| "loss": 3.8266, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.9686793671294801, | |
| "eval_accuracy": 0.34156187005092886, | |
| "eval_loss": 3.7744014263153076, | |
| "eval_runtime": 179.4219, | |
| "eval_samples_per_second": 100.384, | |
| "eval_steps_per_second": 6.276, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.9740609191690883, | |
| "grad_norm": 0.6109694838523865, | |
| "learning_rate": 0.0005421463204396078, | |
| "loss": 3.8173, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.9794424712086965, | |
| "grad_norm": 0.5747610330581665, | |
| "learning_rate": 0.0005418295442301476, | |
| "loss": 3.8562, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.9848240232483048, | |
| "grad_norm": 0.536498486995697, | |
| "learning_rate": 0.0005415063032000861, | |
| "loss": 3.8285, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.9902055752879131, | |
| "grad_norm": 0.5872951745986938, | |
| "learning_rate": 0.0005411830621700248, | |
| "loss": 3.8311, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.9955871273275213, | |
| "grad_norm": 0.6314157843589783, | |
| "learning_rate": 0.0005408598211399633, | |
| "loss": 3.8067, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 1.0009686793671295, | |
| "grad_norm": 0.5174910426139832, | |
| "learning_rate": 0.0005405365801099019, | |
| "loss": 3.8005, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.0063502314067376, | |
| "grad_norm": 0.5861645936965942, | |
| "learning_rate": 0.0005402133390798405, | |
| "loss": 3.7532, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 1.011731783446346, | |
| "grad_norm": 0.6189785003662109, | |
| "learning_rate": 0.000539890098049779, | |
| "loss": 3.7568, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.017113335485954, | |
| "grad_norm": 0.5914862751960754, | |
| "learning_rate": 0.0005395668570197177, | |
| "loss": 3.7533, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 1.0224948875255624, | |
| "grad_norm": 0.618517279624939, | |
| "learning_rate": 0.0005392436159896562, | |
| "loss": 3.7495, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.0278764395651705, | |
| "grad_norm": 0.5718392133712769, | |
| "learning_rate": 0.0005389203749595948, | |
| "loss": 3.7624, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 1.0332579916047788, | |
| "grad_norm": 0.5652843713760376, | |
| "learning_rate": 0.0005385971339295334, | |
| "loss": 3.7637, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.0386395436443872, | |
| "grad_norm": 0.6264984011650085, | |
| "learning_rate": 0.000538273892899472, | |
| "loss": 3.7699, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 1.0440210956839953, | |
| "grad_norm": 0.5926131010055542, | |
| "learning_rate": 0.0005379506518694106, | |
| "loss": 3.7665, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.0494026477236036, | |
| "grad_norm": 0.539849579334259, | |
| "learning_rate": 0.0005376274108393491, | |
| "loss": 3.7516, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 1.0547841997632117, | |
| "grad_norm": 0.626375138759613, | |
| "learning_rate": 0.0005373041698092877, | |
| "loss": 3.7572, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.06016575180282, | |
| "grad_norm": 0.5491912364959717, | |
| "learning_rate": 0.0005369809287792263, | |
| "loss": 3.7701, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 1.0655473038424281, | |
| "grad_norm": 0.5011469721794128, | |
| "learning_rate": 0.000536657687749165, | |
| "loss": 3.7628, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.0709288558820365, | |
| "grad_norm": 0.6251816153526306, | |
| "learning_rate": 0.0005363344467191035, | |
| "loss": 3.7487, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 1.0763104079216446, | |
| "grad_norm": 0.702565610408783, | |
| "learning_rate": 0.000536011205689042, | |
| "loss": 3.7541, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.0763104079216446, | |
| "eval_accuracy": 0.34536037500892314, | |
| "eval_loss": 3.741765022277832, | |
| "eval_runtime": 180.285, | |
| "eval_samples_per_second": 99.903, | |
| "eval_steps_per_second": 6.246, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.081691959961253, | |
| "grad_norm": 0.5714436769485474, | |
| "learning_rate": 0.0005356879646589807, | |
| "loss": 3.7614, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 1.087073512000861, | |
| "grad_norm": 0.5856513977050781, | |
| "learning_rate": 0.0005353647236289192, | |
| "loss": 3.7646, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.0924550640404693, | |
| "grad_norm": 0.5325464606285095, | |
| "learning_rate": 0.0005350414825988579, | |
| "loss": 3.77, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 1.0978366160800774, | |
| "grad_norm": 0.6802165508270264, | |
| "learning_rate": 0.0005347182415687964, | |
| "loss": 3.745, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.1032181681196858, | |
| "grad_norm": 0.5991120934486389, | |
| "learning_rate": 0.000534395000538735, | |
| "loss": 3.7629, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 1.1085997201592939, | |
| "grad_norm": 0.5548239350318909, | |
| "learning_rate": 0.0005340717595086736, | |
| "loss": 3.7561, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.1139812721989022, | |
| "grad_norm": 0.5725270509719849, | |
| "learning_rate": 0.0005337485184786122, | |
| "loss": 3.7547, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 1.1193628242385103, | |
| "grad_norm": 0.6069482564926147, | |
| "learning_rate": 0.0005334252774485507, | |
| "loss": 3.755, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.1247443762781186, | |
| "grad_norm": 0.5790407657623291, | |
| "learning_rate": 0.0005331020364184894, | |
| "loss": 3.742, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 1.1301259283177267, | |
| "grad_norm": 0.5913881659507751, | |
| "learning_rate": 0.0005327787953884279, | |
| "loss": 3.7511, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.135507480357335, | |
| "grad_norm": 0.6094677448272705, | |
| "learning_rate": 0.0005324555543583665, | |
| "loss": 3.7278, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 1.1408890323969434, | |
| "grad_norm": 0.5710995197296143, | |
| "learning_rate": 0.0005321323133283051, | |
| "loss": 3.7383, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.1462705844365515, | |
| "grad_norm": 0.532470703125, | |
| "learning_rate": 0.0005318090722982436, | |
| "loss": 3.7373, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 1.1516521364761596, | |
| "grad_norm": 0.5976846218109131, | |
| "learning_rate": 0.0005314858312681823, | |
| "loss": 3.7609, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.157033688515768, | |
| "grad_norm": 0.5880893468856812, | |
| "learning_rate": 0.0005311625902381209, | |
| "loss": 3.7448, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 1.1624152405553763, | |
| "grad_norm": 0.6322693228721619, | |
| "learning_rate": 0.0005308393492080595, | |
| "loss": 3.7477, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.1677967925949844, | |
| "grad_norm": 0.5472283363342285, | |
| "learning_rate": 0.000530516108177998, | |
| "loss": 3.737, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 1.1731783446345927, | |
| "grad_norm": 0.5412709712982178, | |
| "learning_rate": 0.0005301928671479365, | |
| "loss": 3.7412, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.1785598966742008, | |
| "grad_norm": 0.5746583342552185, | |
| "learning_rate": 0.0005298696261178752, | |
| "loss": 3.7427, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 1.1839414487138091, | |
| "grad_norm": 0.543925940990448, | |
| "learning_rate": 0.0005295463850878138, | |
| "loss": 3.7349, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.1839414487138091, | |
| "eval_accuracy": 0.34741369728284116, | |
| "eval_loss": 3.7178292274475098, | |
| "eval_runtime": 179.9682, | |
| "eval_samples_per_second": 100.079, | |
| "eval_steps_per_second": 6.257, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.1893230007534172, | |
| "grad_norm": 0.6048632860183716, | |
| "learning_rate": 0.0005292231440577524, | |
| "loss": 3.7374, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 1.1947045527930256, | |
| "grad_norm": 0.5460487008094788, | |
| "learning_rate": 0.0005288999030276909, | |
| "loss": 3.7464, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.2000861048326337, | |
| "grad_norm": 0.6168481111526489, | |
| "learning_rate": 0.0005285766619976295, | |
| "loss": 3.7319, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 1.205467656872242, | |
| "grad_norm": 0.5460136532783508, | |
| "learning_rate": 0.0005282534209675681, | |
| "loss": 3.7478, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.21084920891185, | |
| "grad_norm": 0.5822840332984924, | |
| "learning_rate": 0.0005279301799375066, | |
| "loss": 3.7287, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 1.2162307609514584, | |
| "grad_norm": 0.528600811958313, | |
| "learning_rate": 0.0005276069389074453, | |
| "loss": 3.7461, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.2216123129910665, | |
| "grad_norm": 0.5433237552642822, | |
| "learning_rate": 0.0005272836978773838, | |
| "loss": 3.738, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 1.2269938650306749, | |
| "grad_norm": 0.5144934058189392, | |
| "learning_rate": 0.0005269604568473225, | |
| "loss": 3.6953, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.232375417070283, | |
| "grad_norm": 0.5954382419586182, | |
| "learning_rate": 0.000526637215817261, | |
| "loss": 3.7262, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 1.2377569691098913, | |
| "grad_norm": 0.6082680225372314, | |
| "learning_rate": 0.0005263139747871996, | |
| "loss": 3.7328, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.2431385211494996, | |
| "grad_norm": 0.510694682598114, | |
| "learning_rate": 0.0005259907337571381, | |
| "loss": 3.7532, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 1.2485200731891077, | |
| "grad_norm": 0.5158873796463013, | |
| "learning_rate": 0.0005256674927270768, | |
| "loss": 3.7257, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.2539016252287158, | |
| "grad_norm": 0.559540331363678, | |
| "learning_rate": 0.0005253442516970154, | |
| "loss": 3.7084, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 1.2592831772683242, | |
| "grad_norm": 0.6382985711097717, | |
| "learning_rate": 0.000525021010666954, | |
| "loss": 3.7259, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.2646647293079325, | |
| "grad_norm": 0.6098189353942871, | |
| "learning_rate": 0.0005246977696368925, | |
| "loss": 3.7354, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 1.2700462813475406, | |
| "grad_norm": 0.5487571358680725, | |
| "learning_rate": 0.0005243745286068311, | |
| "loss": 3.7322, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.275427833387149, | |
| "grad_norm": 0.5637610554695129, | |
| "learning_rate": 0.0005240577523973709, | |
| "loss": 3.7314, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 1.280809385426757, | |
| "grad_norm": 0.5707816481590271, | |
| "learning_rate": 0.0005237345113673095, | |
| "loss": 3.7303, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.2861909374663654, | |
| "grad_norm": 0.5442221164703369, | |
| "learning_rate": 0.0005234112703372481, | |
| "loss": 3.7523, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 1.2915724895059735, | |
| "grad_norm": 0.7692139148712158, | |
| "learning_rate": 0.0005230880293071867, | |
| "loss": 3.7312, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.2915724895059735, | |
| "eval_accuracy": 0.3501756536910853, | |
| "eval_loss": 3.6950345039367676, | |
| "eval_runtime": 182.9419, | |
| "eval_samples_per_second": 98.452, | |
| "eval_steps_per_second": 6.155, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.2969540415455818, | |
| "grad_norm": 0.5720347762107849, | |
| "learning_rate": 0.0005227647882771253, | |
| "loss": 3.7174, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 1.30233559358519, | |
| "grad_norm": 0.5530905723571777, | |
| "learning_rate": 0.0005224415472470639, | |
| "loss": 3.7105, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.3077171456247982, | |
| "grad_norm": 0.5424105525016785, | |
| "learning_rate": 0.0005221183062170024, | |
| "loss": 3.7247, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 1.3130986976644063, | |
| "grad_norm": 0.5885405540466309, | |
| "learning_rate": 0.0005217950651869409, | |
| "loss": 3.7127, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.3184802497040147, | |
| "grad_norm": 0.5528365969657898, | |
| "learning_rate": 0.0005214718241568796, | |
| "loss": 3.7347, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 1.3238618017436228, | |
| "grad_norm": 0.5199754238128662, | |
| "learning_rate": 0.0005211485831268182, | |
| "loss": 3.7388, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.329243353783231, | |
| "grad_norm": 0.581535279750824, | |
| "learning_rate": 0.0005208253420967568, | |
| "loss": 3.7209, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 1.3346249058228392, | |
| "grad_norm": 0.614345371723175, | |
| "learning_rate": 0.0005205021010666953, | |
| "loss": 3.7146, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.3400064578624475, | |
| "grad_norm": 0.6020660400390625, | |
| "learning_rate": 0.0005201788600366339, | |
| "loss": 3.7209, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 1.3453880099020559, | |
| "grad_norm": 0.5743170976638794, | |
| "learning_rate": 0.0005198556190065725, | |
| "loss": 3.7123, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.350769561941664, | |
| "grad_norm": 0.5332421660423279, | |
| "learning_rate": 0.0005195323779765112, | |
| "loss": 3.7184, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 1.356151113981272, | |
| "grad_norm": 0.5720219612121582, | |
| "learning_rate": 0.0005192091369464497, | |
| "loss": 3.7093, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.3615326660208804, | |
| "grad_norm": 0.5706057548522949, | |
| "learning_rate": 0.0005188858959163882, | |
| "loss": 3.7122, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 1.3669142180604887, | |
| "grad_norm": 0.5560119152069092, | |
| "learning_rate": 0.0005185626548863269, | |
| "loss": 3.7149, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.3722957701000968, | |
| "grad_norm": 0.6042450666427612, | |
| "learning_rate": 0.0005182394138562654, | |
| "loss": 3.7158, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 1.3776773221397052, | |
| "grad_norm": 0.6797989010810852, | |
| "learning_rate": 0.0005179161728262041, | |
| "loss": 3.7213, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.3830588741793133, | |
| "grad_norm": 0.6140666007995605, | |
| "learning_rate": 0.0005175929317961426, | |
| "loss": 3.7106, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 1.3884404262189216, | |
| "grad_norm": 0.5921536684036255, | |
| "learning_rate": 0.0005172696907660812, | |
| "loss": 3.7036, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.3938219782585297, | |
| "grad_norm": 0.547536313533783, | |
| "learning_rate": 0.0005169464497360198, | |
| "loss": 3.7023, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 1.399203530298138, | |
| "grad_norm": 0.5648983716964722, | |
| "learning_rate": 0.0005166232087059583, | |
| "loss": 3.7127, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.399203530298138, | |
| "eval_accuracy": 0.35228004282227615, | |
| "eval_loss": 3.673454761505127, | |
| "eval_runtime": 182.9372, | |
| "eval_samples_per_second": 98.455, | |
| "eval_steps_per_second": 6.155, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.4045850823377461, | |
| "grad_norm": 0.5507751107215881, | |
| "learning_rate": 0.0005162999676758969, | |
| "loss": 3.7025, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 1.4099666343773545, | |
| "grad_norm": 0.5451176166534424, | |
| "learning_rate": 0.0005159767266458355, | |
| "loss": 3.7267, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.4153481864169626, | |
| "grad_norm": 0.6242395043373108, | |
| "learning_rate": 0.0005156534856157741, | |
| "loss": 3.6888, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 1.420729738456571, | |
| "grad_norm": 0.5988582372665405, | |
| "learning_rate": 0.0005153302445857127, | |
| "loss": 3.7165, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.426111290496179, | |
| "grad_norm": 0.5528572201728821, | |
| "learning_rate": 0.0005150070035556513, | |
| "loss": 3.6995, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 1.4314928425357873, | |
| "grad_norm": 0.581158459186554, | |
| "learning_rate": 0.0005146837625255898, | |
| "loss": 3.7006, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.4368743945753955, | |
| "grad_norm": 0.5531030297279358, | |
| "learning_rate": 0.0005143605214955285, | |
| "loss": 3.6895, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 1.4422559466150038, | |
| "grad_norm": 0.5417513847351074, | |
| "learning_rate": 0.0005140372804654671, | |
| "loss": 3.6885, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.447637498654612, | |
| "grad_norm": 0.5422365665435791, | |
| "learning_rate": 0.0005137140394354056, | |
| "loss": 3.7015, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 1.4530190506942202, | |
| "grad_norm": 0.5661604404449463, | |
| "learning_rate": 0.0005133907984053442, | |
| "loss": 3.6965, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.4584006027338283, | |
| "grad_norm": 0.581283688545227, | |
| "learning_rate": 0.0005130675573752827, | |
| "loss": 3.7015, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 1.4637821547734367, | |
| "grad_norm": 0.5587770938873291, | |
| "learning_rate": 0.0005127443163452214, | |
| "loss": 3.7007, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.469163706813045, | |
| "grad_norm": 0.5291188955307007, | |
| "learning_rate": 0.00051242107531516, | |
| "loss": 3.6855, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 1.474545258852653, | |
| "grad_norm": 0.5866516828536987, | |
| "learning_rate": 0.0005120978342850986, | |
| "loss": 3.6982, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.4799268108922612, | |
| "grad_norm": 0.6090840697288513, | |
| "learning_rate": 0.0005117745932550371, | |
| "loss": 3.7063, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 1.4853083629318695, | |
| "grad_norm": 0.5599469542503357, | |
| "learning_rate": 0.0005114513522249758, | |
| "loss": 3.6826, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.4906899149714778, | |
| "grad_norm": 0.5345983505249023, | |
| "learning_rate": 0.0005111281111949143, | |
| "loss": 3.7033, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 1.496071467011086, | |
| "grad_norm": 0.582324206829071, | |
| "learning_rate": 0.0005108048701648528, | |
| "loss": 3.706, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.501453019050694, | |
| "grad_norm": 0.5937202572822571, | |
| "learning_rate": 0.0005104880939553926, | |
| "loss": 3.6788, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 1.5068345710903024, | |
| "grad_norm": 0.5526854395866394, | |
| "learning_rate": 0.0005101648529253313, | |
| "loss": 3.6974, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.5068345710903024, | |
| "eval_accuracy": 0.3537209974204718, | |
| "eval_loss": 3.6525895595550537, | |
| "eval_runtime": 183.0004, | |
| "eval_samples_per_second": 98.421, | |
| "eval_steps_per_second": 6.153, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.5122161231299107, | |
| "grad_norm": 0.530371904373169, | |
| "learning_rate": 0.0005098416118952699, | |
| "loss": 3.7083, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 1.5175976751695188, | |
| "grad_norm": 0.5713452100753784, | |
| "learning_rate": 0.0005095183708652085, | |
| "loss": 3.681, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.5229792272091272, | |
| "grad_norm": 0.5218368768692017, | |
| "learning_rate": 0.000509195129835147, | |
| "loss": 3.6881, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 1.5283607792487355, | |
| "grad_norm": 0.5329176783561707, | |
| "learning_rate": 0.0005088718888050856, | |
| "loss": 3.6926, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.5337423312883436, | |
| "grad_norm": 0.5380780100822449, | |
| "learning_rate": 0.0005085486477750242, | |
| "loss": 3.705, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 1.5391238833279517, | |
| "grad_norm": 0.5449959635734558, | |
| "learning_rate": 0.0005082254067449629, | |
| "loss": 3.6826, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.54450543536756, | |
| "grad_norm": 0.6050571203231812, | |
| "learning_rate": 0.0005079021657149014, | |
| "loss": 3.6679, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 1.5498869874071683, | |
| "grad_norm": 0.5612210631370544, | |
| "learning_rate": 0.0005075789246848399, | |
| "loss": 3.6984, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.5552685394467765, | |
| "grad_norm": 0.5346029996871948, | |
| "learning_rate": 0.0005072556836547785, | |
| "loss": 3.6831, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 1.5606500914863846, | |
| "grad_norm": 0.5634347200393677, | |
| "learning_rate": 0.0005069324426247171, | |
| "loss": 3.6772, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.566031643525993, | |
| "grad_norm": 0.5833031535148621, | |
| "learning_rate": 0.0005066092015946557, | |
| "loss": 3.6852, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 1.5714131955656012, | |
| "grad_norm": 0.5364494919776917, | |
| "learning_rate": 0.0005062859605645943, | |
| "loss": 3.6904, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.5767947476052093, | |
| "grad_norm": 0.592128336429596, | |
| "learning_rate": 0.0005059627195345329, | |
| "loss": 3.6875, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 1.5821762996448174, | |
| "grad_norm": 0.5206913352012634, | |
| "learning_rate": 0.0005056394785044715, | |
| "loss": 3.6847, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.5875578516844258, | |
| "grad_norm": 0.5297030806541443, | |
| "learning_rate": 0.00050531623747441, | |
| "loss": 3.677, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 1.592939403724034, | |
| "grad_norm": 0.6701345443725586, | |
| "learning_rate": 0.0005049929964443486, | |
| "loss": 3.6901, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.5983209557636422, | |
| "grad_norm": 0.5313422083854675, | |
| "learning_rate": 0.0005046697554142871, | |
| "loss": 3.6859, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 1.6037025078032503, | |
| "grad_norm": 0.5316382646560669, | |
| "learning_rate": 0.0005043465143842258, | |
| "loss": 3.6802, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.6090840598428586, | |
| "grad_norm": 0.6596531271934509, | |
| "learning_rate": 0.0005040232733541644, | |
| "loss": 3.6445, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 1.614465611882467, | |
| "grad_norm": 0.6033098101615906, | |
| "learning_rate": 0.000503700032324103, | |
| "loss": 3.6788, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.614465611882467, | |
| "eval_accuracy": 0.35575758714966643, | |
| "eval_loss": 3.6347877979278564, | |
| "eval_runtime": 183.0426, | |
| "eval_samples_per_second": 98.398, | |
| "eval_steps_per_second": 6.152, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.619847163922075, | |
| "grad_norm": 0.5396302342414856, | |
| "learning_rate": 0.0005033767912940415, | |
| "loss": 3.663, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 1.6252287159616834, | |
| "grad_norm": 0.6209707856178284, | |
| "learning_rate": 0.0005030535502639802, | |
| "loss": 3.6696, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.6306102680012917, | |
| "grad_norm": 0.5924604535102844, | |
| "learning_rate": 0.0005027303092339187, | |
| "loss": 3.6585, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 1.6359918200408998, | |
| "grad_norm": 0.5263779163360596, | |
| "learning_rate": 0.0005024070682038573, | |
| "loss": 3.6734, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.641373372080508, | |
| "grad_norm": 0.5559638142585754, | |
| "learning_rate": 0.0005020838271737959, | |
| "loss": 3.6798, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 1.6467549241201163, | |
| "grad_norm": 0.5919946432113647, | |
| "learning_rate": 0.0005017605861437344, | |
| "loss": 3.6702, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.6521364761597246, | |
| "grad_norm": 0.4996275007724762, | |
| "learning_rate": 0.0005014373451136731, | |
| "loss": 3.673, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 1.6575180281993327, | |
| "grad_norm": 0.5767028331756592, | |
| "learning_rate": 0.0005011141040836116, | |
| "loss": 3.6692, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.6628995802389408, | |
| "grad_norm": 0.5547932386398315, | |
| "learning_rate": 0.0005007908630535503, | |
| "loss": 3.665, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 1.6682811322785491, | |
| "grad_norm": 0.5808051228523254, | |
| "learning_rate": 0.0005004676220234888, | |
| "loss": 3.6697, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.6736626843181575, | |
| "grad_norm": 0.6720907688140869, | |
| "learning_rate": 0.0005001443809934273, | |
| "loss": 3.666, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 1.6790442363577656, | |
| "grad_norm": 0.5560029149055481, | |
| "learning_rate": 0.000499821139963366, | |
| "loss": 3.66, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.6844257883973737, | |
| "grad_norm": 0.5708025693893433, | |
| "learning_rate": 0.0004994978989333045, | |
| "loss": 3.6729, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 1.689807340436982, | |
| "grad_norm": 0.6271914839744568, | |
| "learning_rate": 0.0004991746579032431, | |
| "loss": 3.6725, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.6951888924765903, | |
| "grad_norm": 0.5649659037590027, | |
| "learning_rate": 0.0004988514168731817, | |
| "loss": 3.6506, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 1.7005704445161984, | |
| "grad_norm": 0.5502942204475403, | |
| "learning_rate": 0.0004985281758431204, | |
| "loss": 3.68, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.7059519965558065, | |
| "grad_norm": 0.6230396628379822, | |
| "learning_rate": 0.0004982049348130589, | |
| "loss": 3.6764, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 1.7113335485954149, | |
| "grad_norm": 0.5738170742988586, | |
| "learning_rate": 0.0004978816937829975, | |
| "loss": 3.6683, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.7167151006350232, | |
| "grad_norm": 0.5674835443496704, | |
| "learning_rate": 0.000497558452752936, | |
| "loss": 3.6641, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 1.7220966526746313, | |
| "grad_norm": 0.5687111616134644, | |
| "learning_rate": 0.0004972416765434759, | |
| "loss": 3.653, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.7220966526746313, | |
| "eval_accuracy": 0.35766868279343533, | |
| "eval_loss": 3.6169068813323975, | |
| "eval_runtime": 182.8519, | |
| "eval_samples_per_second": 98.5, | |
| "eval_steps_per_second": 6.158, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.7274782047142396, | |
| "grad_norm": 0.5726053714752197, | |
| "learning_rate": 0.0004969184355134145, | |
| "loss": 3.6704, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 1.732859756753848, | |
| "grad_norm": 0.5218805074691772, | |
| "learning_rate": 0.0004965951944833531, | |
| "loss": 3.6687, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.738241308793456, | |
| "grad_norm": 0.5829153060913086, | |
| "learning_rate": 0.0004962719534532916, | |
| "loss": 3.6701, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 1.7436228608330642, | |
| "grad_norm": 0.6053098440170288, | |
| "learning_rate": 0.0004959487124232302, | |
| "loss": 3.6489, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.7490044128726725, | |
| "grad_norm": 0.5329374670982361, | |
| "learning_rate": 0.0004956254713931688, | |
| "loss": 3.6494, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "grad_norm": 0.5787749886512756, | |
| "learning_rate": 0.0004953022303631074, | |
| "loss": 3.6523, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.759767516951889, | |
| "grad_norm": 0.5446376800537109, | |
| "learning_rate": 0.0004949789893330459, | |
| "loss": 3.6551, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 1.765149068991497, | |
| "grad_norm": 0.6261696815490723, | |
| "learning_rate": 0.0004946557483029846, | |
| "loss": 3.6529, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.7705306210311054, | |
| "grad_norm": 0.5923592448234558, | |
| "learning_rate": 0.0004943325072729231, | |
| "loss": 3.6742, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 1.7759121730707137, | |
| "grad_norm": 0.5514686703681946, | |
| "learning_rate": 0.0004940092662428617, | |
| "loss": 3.6655, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.7812937251103218, | |
| "grad_norm": 0.5481582283973694, | |
| "learning_rate": 0.0004936860252128003, | |
| "loss": 3.6613, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 1.78667527714993, | |
| "grad_norm": 0.5708692073822021, | |
| "learning_rate": 0.0004933627841827388, | |
| "loss": 3.6644, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.7920568291895382, | |
| "grad_norm": 0.5547276139259338, | |
| "learning_rate": 0.0004930395431526775, | |
| "loss": 3.6443, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 1.7974383812291466, | |
| "grad_norm": 0.60475754737854, | |
| "learning_rate": 0.0004927163021226161, | |
| "loss": 3.666, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.8028199332687547, | |
| "grad_norm": 0.568871796131134, | |
| "learning_rate": 0.0004923930610925547, | |
| "loss": 3.6573, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 1.8082014853083628, | |
| "grad_norm": 0.5564674139022827, | |
| "learning_rate": 0.0004920698200624932, | |
| "loss": 3.6515, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.813583037347971, | |
| "grad_norm": 0.5341878533363342, | |
| "learning_rate": 0.0004917465790324317, | |
| "loss": 3.6652, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 1.8189645893875794, | |
| "grad_norm": 0.58695387840271, | |
| "learning_rate": 0.0004914233380023704, | |
| "loss": 3.6546, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.8243461414271875, | |
| "grad_norm": 0.5584468245506287, | |
| "learning_rate": 0.0004911000969723089, | |
| "loss": 3.631, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 1.8297276934667959, | |
| "grad_norm": 0.5749080777168274, | |
| "learning_rate": 0.0004907768559422476, | |
| "loss": 3.6484, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.8297276934667959, | |
| "eval_accuracy": 0.35881909956961505, | |
| "eval_loss": 3.601506233215332, | |
| "eval_runtime": 182.9699, | |
| "eval_samples_per_second": 98.437, | |
| "eval_steps_per_second": 6.154, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.8351092455064042, | |
| "grad_norm": 0.5957604050636292, | |
| "learning_rate": 0.0004904536149121861, | |
| "loss": 3.6388, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 1.8404907975460123, | |
| "grad_norm": 0.5906072854995728, | |
| "learning_rate": 0.0004901303738821248, | |
| "loss": 3.6523, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.8458723495856204, | |
| "grad_norm": 0.6116198301315308, | |
| "learning_rate": 0.0004898071328520633, | |
| "loss": 3.6424, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 1.8512539016252287, | |
| "grad_norm": 0.5727099776268005, | |
| "learning_rate": 0.0004894838918220019, | |
| "loss": 3.6625, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.856635453664837, | |
| "grad_norm": 0.5920504331588745, | |
| "learning_rate": 0.0004891606507919405, | |
| "loss": 3.6366, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 1.8620170057044452, | |
| "grad_norm": 0.6015959978103638, | |
| "learning_rate": 0.000488837409761879, | |
| "loss": 3.6506, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.8673985577440533, | |
| "grad_norm": 0.5476948022842407, | |
| "learning_rate": 0.0004885141687318177, | |
| "loss": 3.654, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 1.8727801097836616, | |
| "grad_norm": 0.5550304651260376, | |
| "learning_rate": 0.00048819092770175623, | |
| "loss": 3.6382, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.87816166182327, | |
| "grad_norm": 0.5779985189437866, | |
| "learning_rate": 0.0004878676866716948, | |
| "loss": 3.6562, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 1.883543213862878, | |
| "grad_norm": 0.5878141522407532, | |
| "learning_rate": 0.00048754444564163337, | |
| "loss": 3.6424, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.8889247659024861, | |
| "grad_norm": 0.5703890323638916, | |
| "learning_rate": 0.000487221204611572, | |
| "loss": 3.6491, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 1.8943063179420945, | |
| "grad_norm": 0.5712037086486816, | |
| "learning_rate": 0.00048689796358151056, | |
| "loss": 3.6276, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.8996878699817028, | |
| "grad_norm": 0.5311342477798462, | |
| "learning_rate": 0.00048657472255144915, | |
| "loss": 3.6438, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 1.905069422021311, | |
| "grad_norm": 0.5727416276931763, | |
| "learning_rate": 0.00048625148152138775, | |
| "loss": 3.6264, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.910450974060919, | |
| "grad_norm": 0.6044231653213501, | |
| "learning_rate": 0.0004859282404913263, | |
| "loss": 3.6242, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 1.9158325261005273, | |
| "grad_norm": 0.5727190971374512, | |
| "learning_rate": 0.0004856049994612649, | |
| "loss": 3.6462, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.9212140781401357, | |
| "grad_norm": 0.5734631419181824, | |
| "learning_rate": 0.00048528175843120353, | |
| "loss": 3.6472, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 1.9265956301797438, | |
| "grad_norm": 0.5388041734695435, | |
| "learning_rate": 0.0004849585174011421, | |
| "loss": 3.6489, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.931977182219352, | |
| "grad_norm": 0.5606278777122498, | |
| "learning_rate": 0.00048463527637108067, | |
| "loss": 3.6294, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 1.9373587342589604, | |
| "grad_norm": 0.5878045558929443, | |
| "learning_rate": 0.0004843120353410192, | |
| "loss": 3.6472, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.9373587342589604, | |
| "eval_accuracy": 0.36079995036736084, | |
| "eval_loss": 3.5877466201782227, | |
| "eval_runtime": 182.9553, | |
| "eval_samples_per_second": 98.445, | |
| "eval_steps_per_second": 6.155, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.9427402862985685, | |
| "grad_norm": 0.5944440960884094, | |
| "learning_rate": 0.00048399525913155907, | |
| "loss": 3.6349, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 1.9481218383381766, | |
| "grad_norm": 0.6114388704299927, | |
| "learning_rate": 0.0004836720181014976, | |
| "loss": 3.6319, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.953503390377785, | |
| "grad_norm": 0.5699650645256042, | |
| "learning_rate": 0.0004833487770714362, | |
| "loss": 3.6309, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 1.9588849424173933, | |
| "grad_norm": 0.5740841031074524, | |
| "learning_rate": 0.00048302553604137485, | |
| "loss": 3.6278, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.9642664944570014, | |
| "grad_norm": 0.6211947798728943, | |
| "learning_rate": 0.0004827022950113134, | |
| "loss": 3.6346, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 1.9696480464966095, | |
| "grad_norm": 0.5401277542114258, | |
| "learning_rate": 0.000482379053981252, | |
| "loss": 3.6603, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.9750295985362178, | |
| "grad_norm": 0.5557017922401428, | |
| "learning_rate": 0.0004820558129511906, | |
| "loss": 3.629, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 1.9804111505758262, | |
| "grad_norm": 0.592074453830719, | |
| "learning_rate": 0.0004817325719211291, | |
| "loss": 3.6235, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.9857927026154343, | |
| "grad_norm": 0.600532591342926, | |
| "learning_rate": 0.0004814093308910677, | |
| "loss": 3.6253, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 1.9911742546550424, | |
| "grad_norm": 0.4943503141403198, | |
| "learning_rate": 0.00048108608986100637, | |
| "loss": 3.6225, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.9965558066946507, | |
| "grad_norm": 0.5403441190719604, | |
| "learning_rate": 0.0004807628488309449, | |
| "loss": 3.6333, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 2.001937358734259, | |
| "grad_norm": 0.5593751668930054, | |
| "learning_rate": 0.0004804396078008835, | |
| "loss": 3.5902, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.007318910773867, | |
| "grad_norm": 0.5596261024475098, | |
| "learning_rate": 0.00048011636677082204, | |
| "loss": 3.5438, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 2.0127004628134753, | |
| "grad_norm": 0.5620816946029663, | |
| "learning_rate": 0.00047979312574076064, | |
| "loss": 3.5367, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.018082014853084, | |
| "grad_norm": 0.6553834080696106, | |
| "learning_rate": 0.0004794698847106992, | |
| "loss": 3.5336, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 2.023463566892692, | |
| "grad_norm": 0.5942727327346802, | |
| "learning_rate": 0.0004791466436806378, | |
| "loss": 3.5532, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.0288451189323, | |
| "grad_norm": 0.563507616519928, | |
| "learning_rate": 0.0004788234026505764, | |
| "loss": 3.565, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 2.034226670971908, | |
| "grad_norm": 0.5451712608337402, | |
| "learning_rate": 0.00047850016162051496, | |
| "loss": 3.55, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.0396082230115167, | |
| "grad_norm": 0.6260777711868286, | |
| "learning_rate": 0.00047817692059045356, | |
| "loss": 3.5395, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 2.044989775051125, | |
| "grad_norm": 0.6237614750862122, | |
| "learning_rate": 0.00047785367956039215, | |
| "loss": 3.5601, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.044989775051125, | |
| "eval_accuracy": 0.36222699739591624, | |
| "eval_loss": 3.5780997276306152, | |
| "eval_runtime": 182.9631, | |
| "eval_samples_per_second": 98.441, | |
| "eval_steps_per_second": 6.154, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.050371327090733, | |
| "grad_norm": 0.5645211935043335, | |
| "learning_rate": 0.00047753043853033075, | |
| "loss": 3.5712, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 2.055752879130341, | |
| "grad_norm": 0.550080418586731, | |
| "learning_rate": 0.00047720719750026934, | |
| "loss": 3.5519, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.0611344311699495, | |
| "grad_norm": 0.5775645971298218, | |
| "learning_rate": 0.00047688395647020793, | |
| "loss": 3.5345, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 2.0665159832095576, | |
| "grad_norm": 0.6265087127685547, | |
| "learning_rate": 0.0004765607154401465, | |
| "loss": 3.5604, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.0718975352491658, | |
| "grad_norm": 0.645406186580658, | |
| "learning_rate": 0.00047623747441008507, | |
| "loss": 3.5486, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 2.0772790872887743, | |
| "grad_norm": 0.5847898721694946, | |
| "learning_rate": 0.0004759142333800236, | |
| "loss": 3.5457, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.0826606393283824, | |
| "grad_norm": 0.5650346875190735, | |
| "learning_rate": 0.00047559099234996226, | |
| "loss": 3.5555, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 2.0880421913679905, | |
| "grad_norm": 0.599783182144165, | |
| "learning_rate": 0.00047526775131990085, | |
| "loss": 3.5459, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.0934237434075986, | |
| "grad_norm": 0.5775169730186462, | |
| "learning_rate": 0.0004749445102898394, | |
| "loss": 3.5612, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 2.098805295447207, | |
| "grad_norm": 0.6146634817123413, | |
| "learning_rate": 0.000474621269259778, | |
| "loss": 3.5666, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.1041868474868153, | |
| "grad_norm": 0.6270310878753662, | |
| "learning_rate": 0.0004742980282297166, | |
| "loss": 3.5408, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 2.1095683995264234, | |
| "grad_norm": 0.517265796661377, | |
| "learning_rate": 0.0004739747871996551, | |
| "loss": 3.5576, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.1149499515660315, | |
| "grad_norm": 0.6480297446250916, | |
| "learning_rate": 0.00047365154616959377, | |
| "loss": 3.542, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 2.12033150360564, | |
| "grad_norm": 0.5682874321937561, | |
| "learning_rate": 0.00047332830513953237, | |
| "loss": 3.5669, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.125713055645248, | |
| "grad_norm": 0.6224113702774048, | |
| "learning_rate": 0.0004730050641094709, | |
| "loss": 3.5485, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 2.1310946076848563, | |
| "grad_norm": 0.554499089717865, | |
| "learning_rate": 0.0004726818230794095, | |
| "loss": 3.5338, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.1364761597244644, | |
| "grad_norm": 0.6027452349662781, | |
| "learning_rate": 0.0004723650468699493, | |
| "loss": 3.5481, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 2.141857711764073, | |
| "grad_norm": 0.6047434210777283, | |
| "learning_rate": 0.0004720418058398879, | |
| "loss": 3.5465, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.147239263803681, | |
| "grad_norm": 0.5787104964256287, | |
| "learning_rate": 0.00047171856480982644, | |
| "loss": 3.5562, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 2.152620815843289, | |
| "grad_norm": 0.5642232298851013, | |
| "learning_rate": 0.0004713953237797651, | |
| "loss": 3.5694, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.152620815843289, | |
| "eval_accuracy": 0.36314848253747084, | |
| "eval_loss": 3.5687355995178223, | |
| "eval_runtime": 179.7649, | |
| "eval_samples_per_second": 100.192, | |
| "eval_steps_per_second": 6.264, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.1580023678828972, | |
| "grad_norm": 0.6349261999130249, | |
| "learning_rate": 0.0004710720827497037, | |
| "loss": 3.5747, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 2.163383919922506, | |
| "grad_norm": 0.5958331823348999, | |
| "learning_rate": 0.00047074884171964223, | |
| "loss": 3.5547, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.168765471962114, | |
| "grad_norm": 0.6347177028656006, | |
| "learning_rate": 0.0004704256006895808, | |
| "loss": 3.561, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 2.174147024001722, | |
| "grad_norm": 0.6787843108177185, | |
| "learning_rate": 0.00047010235965951936, | |
| "loss": 3.5584, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.1795285760413305, | |
| "grad_norm": 0.5568081140518188, | |
| "learning_rate": 0.00046977911862945796, | |
| "loss": 3.5667, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 2.1849101280809387, | |
| "grad_norm": 0.6003414988517761, | |
| "learning_rate": 0.0004694558775993966, | |
| "loss": 3.5515, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.1902916801205468, | |
| "grad_norm": 0.5988909602165222, | |
| "learning_rate": 0.00046913263656933515, | |
| "loss": 3.5563, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 2.195673232160155, | |
| "grad_norm": 0.6274018287658691, | |
| "learning_rate": 0.00046880939553927374, | |
| "loss": 3.55, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.2010547841997634, | |
| "grad_norm": 0.5922993421554565, | |
| "learning_rate": 0.00046848615450921234, | |
| "loss": 3.5385, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 2.2064363362393715, | |
| "grad_norm": 0.6406957507133484, | |
| "learning_rate": 0.0004681629134791509, | |
| "loss": 3.5292, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.2118178882789796, | |
| "grad_norm": 0.5569520592689514, | |
| "learning_rate": 0.00046783967244908947, | |
| "loss": 3.5393, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 2.2171994403185877, | |
| "grad_norm": 0.5793364644050598, | |
| "learning_rate": 0.0004675164314190281, | |
| "loss": 3.5537, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.2225809923581963, | |
| "grad_norm": 0.5888959765434265, | |
| "learning_rate": 0.00046719319038896666, | |
| "loss": 3.5403, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 2.2279625443978044, | |
| "grad_norm": 0.5922018885612488, | |
| "learning_rate": 0.00046686994935890526, | |
| "loss": 3.547, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.2333440964374125, | |
| "grad_norm": 0.6159331798553467, | |
| "learning_rate": 0.0004665467083288438, | |
| "loss": 3.5509, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 2.2387256484770206, | |
| "grad_norm": 0.6433561444282532, | |
| "learning_rate": 0.0004662234672987824, | |
| "loss": 3.5546, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.244107200516629, | |
| "grad_norm": 0.5780196189880371, | |
| "learning_rate": 0.00046590022626872104, | |
| "loss": 3.5505, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 2.2494887525562373, | |
| "grad_norm": 0.6302474141120911, | |
| "learning_rate": 0.0004655769852386596, | |
| "loss": 3.5528, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.2548703045958454, | |
| "grad_norm": 0.6163661479949951, | |
| "learning_rate": 0.0004652537442085982, | |
| "loss": 3.5506, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 2.2602518566354535, | |
| "grad_norm": 0.5856783390045166, | |
| "learning_rate": 0.00046493050317853677, | |
| "loss": 3.5485, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.2602518566354535, | |
| "eval_accuracy": 0.364305092528256, | |
| "eval_loss": 3.5584065914154053, | |
| "eval_runtime": 179.7572, | |
| "eval_samples_per_second": 100.196, | |
| "eval_steps_per_second": 6.264, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.265633408675062, | |
| "grad_norm": 0.5490982532501221, | |
| "learning_rate": 0.0004646072621484753, | |
| "loss": 3.5765, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 2.27101496071467, | |
| "grad_norm": 0.6259151697158813, | |
| "learning_rate": 0.0004642840211184139, | |
| "loss": 3.5557, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.2763965127542782, | |
| "grad_norm": 0.6125593185424805, | |
| "learning_rate": 0.00046396078008835255, | |
| "loss": 3.562, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 2.281778064793887, | |
| "grad_norm": 0.596523642539978, | |
| "learning_rate": 0.0004636375390582911, | |
| "loss": 3.544, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.287159616833495, | |
| "grad_norm": 0.6259929537773132, | |
| "learning_rate": 0.0004633142980282297, | |
| "loss": 3.5504, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 2.292541168873103, | |
| "grad_norm": 0.5609055161476135, | |
| "learning_rate": 0.00046299105699816823, | |
| "loss": 3.5574, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.297922720912711, | |
| "grad_norm": 0.6183776259422302, | |
| "learning_rate": 0.0004626678159681068, | |
| "loss": 3.5536, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 2.303304272952319, | |
| "grad_norm": 0.531791090965271, | |
| "learning_rate": 0.0004623445749380454, | |
| "loss": 3.5414, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.3086858249919278, | |
| "grad_norm": 0.558052122592926, | |
| "learning_rate": 0.000462021333907984, | |
| "loss": 3.538, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 2.314067377031536, | |
| "grad_norm": 0.5366657972335815, | |
| "learning_rate": 0.0004616980928779226, | |
| "loss": 3.5508, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.319448929071144, | |
| "grad_norm": 0.5605040192604065, | |
| "learning_rate": 0.0004613748518478612, | |
| "loss": 3.5527, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 2.3248304811107525, | |
| "grad_norm": 0.5950835347175598, | |
| "learning_rate": 0.00046105161081779974, | |
| "loss": 3.553, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.3302120331503606, | |
| "grad_norm": 0.5673235058784485, | |
| "learning_rate": 0.00046072836978773834, | |
| "loss": 3.5484, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 2.3355935851899687, | |
| "grad_norm": 0.5962451100349426, | |
| "learning_rate": 0.000460405128757677, | |
| "loss": 3.5665, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.340975137229577, | |
| "grad_norm": 0.5817105770111084, | |
| "learning_rate": 0.0004600818877276155, | |
| "loss": 3.5456, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 2.3463566892691854, | |
| "grad_norm": 0.5566921234130859, | |
| "learning_rate": 0.0004597586466975541, | |
| "loss": 3.5419, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.3517382413087935, | |
| "grad_norm": 0.5889357924461365, | |
| "learning_rate": 0.00045943540566749266, | |
| "loss": 3.553, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 2.3571197933484016, | |
| "grad_norm": 0.5869264006614685, | |
| "learning_rate": 0.00045911216463743126, | |
| "loss": 3.549, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.3625013453880097, | |
| "grad_norm": 0.5697734951972961, | |
| "learning_rate": 0.00045878892360736985, | |
| "loss": 3.5583, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 2.3678828974276183, | |
| "grad_norm": 0.6061686873435974, | |
| "learning_rate": 0.00045846568257730845, | |
| "loss": 3.5613, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.3678828974276183, | |
| "eval_accuracy": 0.36498678074640406, | |
| "eval_loss": 3.547973871231079, | |
| "eval_runtime": 180.0761, | |
| "eval_samples_per_second": 100.019, | |
| "eval_steps_per_second": 6.253, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.3732644494672264, | |
| "grad_norm": 0.5746018290519714, | |
| "learning_rate": 0.00045814244154724704, | |
| "loss": 3.5496, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 2.3786460015068345, | |
| "grad_norm": 0.6272563338279724, | |
| "learning_rate": 0.00045781920051718563, | |
| "loss": 3.5636, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.384027553546443, | |
| "grad_norm": 0.5796659588813782, | |
| "learning_rate": 0.0004574959594871242, | |
| "loss": 3.5412, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 2.389409105586051, | |
| "grad_norm": 0.5960429906845093, | |
| "learning_rate": 0.00045717271845706277, | |
| "loss": 3.5478, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.3947906576256592, | |
| "grad_norm": 0.6166843175888062, | |
| "learning_rate": 0.0004568494774270013, | |
| "loss": 3.5584, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 2.4001722096652673, | |
| "grad_norm": 0.5762814879417419, | |
| "learning_rate": 0.00045652623639693996, | |
| "loss": 3.537, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.4055537617048754, | |
| "grad_norm": 0.5935600399971008, | |
| "learning_rate": 0.00045620299536687855, | |
| "loss": 3.5506, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 2.410935313744484, | |
| "grad_norm": 0.5715270042419434, | |
| "learning_rate": 0.0004558797543368171, | |
| "loss": 3.5349, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 2.416316865784092, | |
| "grad_norm": 0.5746564269065857, | |
| "learning_rate": 0.0004555565133067557, | |
| "loss": 3.5393, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 2.4216984178237, | |
| "grad_norm": 0.6002961993217468, | |
| "learning_rate": 0.0004552332722766943, | |
| "loss": 3.5703, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.4270799698633088, | |
| "grad_norm": 0.6364290118217468, | |
| "learning_rate": 0.0004549100312466328, | |
| "loss": 3.535, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 2.432461521902917, | |
| "grad_norm": 0.5654012560844421, | |
| "learning_rate": 0.0004545867902165715, | |
| "loss": 3.5494, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 2.437843073942525, | |
| "grad_norm": 0.6237375736236572, | |
| "learning_rate": 0.00045426354918651007, | |
| "loss": 3.5464, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 2.443224625982133, | |
| "grad_norm": 0.5933444499969482, | |
| "learning_rate": 0.0004539467729770499, | |
| "loss": 3.5417, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 2.4486061780217416, | |
| "grad_norm": 0.5668746829032898, | |
| "learning_rate": 0.0004536235319469884, | |
| "loss": 3.5352, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 2.4539877300613497, | |
| "grad_norm": 0.6203579902648926, | |
| "learning_rate": 0.000453300290916927, | |
| "loss": 3.574, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 2.459369282100958, | |
| "grad_norm": 0.5573844909667969, | |
| "learning_rate": 0.0004529770498868656, | |
| "loss": 3.5529, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 2.464750834140566, | |
| "grad_norm": 0.6508901715278625, | |
| "learning_rate": 0.00045265380885680414, | |
| "loss": 3.531, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 2.4701323861801745, | |
| "grad_norm": 0.5782315135002136, | |
| "learning_rate": 0.0004523305678267428, | |
| "loss": 3.5689, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 2.4755139382197826, | |
| "grad_norm": 0.6106559038162231, | |
| "learning_rate": 0.0004520073267966814, | |
| "loss": 3.5521, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.4755139382197826, | |
| "eval_accuracy": 0.3663403784227969, | |
| "eval_loss": 3.5380020141601562, | |
| "eval_runtime": 179.612, | |
| "eval_samples_per_second": 100.277, | |
| "eval_steps_per_second": 6.269, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.4808954902593907, | |
| "grad_norm": 0.5985417366027832, | |
| "learning_rate": 0.00045168408576661993, | |
| "loss": 3.5309, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 2.4862770422989993, | |
| "grad_norm": 0.5568486452102661, | |
| "learning_rate": 0.0004513608447365585, | |
| "loss": 3.5504, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 2.4916585943386074, | |
| "grad_norm": 0.607467770576477, | |
| "learning_rate": 0.00045103760370649706, | |
| "loss": 3.5585, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 2.4970401463782155, | |
| "grad_norm": 0.6122623085975647, | |
| "learning_rate": 0.00045071436267643566, | |
| "loss": 3.55, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 2.5024216984178236, | |
| "grad_norm": 0.6299822330474854, | |
| "learning_rate": 0.0004503911216463743, | |
| "loss": 3.5361, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 2.5078032504574317, | |
| "grad_norm": 0.5975040793418884, | |
| "learning_rate": 0.00045006788061631285, | |
| "loss": 3.5452, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 2.5131848024970402, | |
| "grad_norm": 0.6091236472129822, | |
| "learning_rate": 0.00044974463958625144, | |
| "loss": 3.5612, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 2.5185663545366483, | |
| "grad_norm": 0.5954560041427612, | |
| "learning_rate": 0.00044942139855619004, | |
| "loss": 3.5283, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 2.5239479065762565, | |
| "grad_norm": 0.5859009623527527, | |
| "learning_rate": 0.0004490981575261286, | |
| "loss": 3.537, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 2.529329458615865, | |
| "grad_norm": 0.5438385009765625, | |
| "learning_rate": 0.0004487749164960672, | |
| "loss": 3.5416, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.534711010655473, | |
| "grad_norm": 0.5849915146827698, | |
| "learning_rate": 0.0004484516754660058, | |
| "loss": 3.544, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 2.540092562695081, | |
| "grad_norm": 0.6110696792602539, | |
| "learning_rate": 0.00044812843443594436, | |
| "loss": 3.5456, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 2.5454741147346893, | |
| "grad_norm": 0.6262888312339783, | |
| "learning_rate": 0.00044780519340588296, | |
| "loss": 3.5357, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 2.550855666774298, | |
| "grad_norm": 0.6227126717567444, | |
| "learning_rate": 0.0004474819523758215, | |
| "loss": 3.5471, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 2.556237218813906, | |
| "grad_norm": 0.607038140296936, | |
| "learning_rate": 0.0004471587113457601, | |
| "loss": 3.5478, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 2.561618770853514, | |
| "grad_norm": 0.5638023614883423, | |
| "learning_rate": 0.00044683547031569874, | |
| "loss": 3.5658, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 2.567000322893122, | |
| "grad_norm": 0.6163343787193298, | |
| "learning_rate": 0.0004465122292856373, | |
| "loss": 3.5602, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 2.5723818749327307, | |
| "grad_norm": 0.5720522999763489, | |
| "learning_rate": 0.0004461889882555759, | |
| "loss": 3.5562, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 2.577763426972339, | |
| "grad_norm": 0.636634111404419, | |
| "learning_rate": 0.00044586574722551447, | |
| "loss": 3.5685, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 2.583144979011947, | |
| "grad_norm": 0.5891180634498596, | |
| "learning_rate": 0.000445542506195453, | |
| "loss": 3.5455, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.583144979011947, | |
| "eval_accuracy": 0.36704879525134726, | |
| "eval_loss": 3.526322364807129, | |
| "eval_runtime": 179.7285, | |
| "eval_samples_per_second": 100.212, | |
| "eval_steps_per_second": 6.265, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.5885265310515555, | |
| "grad_norm": 0.6043258905410767, | |
| "learning_rate": 0.0004452192651653916, | |
| "loss": 3.5164, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 2.5939080830911636, | |
| "grad_norm": 0.6400256752967834, | |
| "learning_rate": 0.00044489602413533025, | |
| "loss": 3.5409, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 2.5992896351307717, | |
| "grad_norm": 0.6273722648620605, | |
| "learning_rate": 0.0004445727831052688, | |
| "loss": 3.5391, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 2.60467118717038, | |
| "grad_norm": 0.6210452318191528, | |
| "learning_rate": 0.0004442495420752074, | |
| "loss": 3.5436, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 2.610052739209988, | |
| "grad_norm": 0.5660796761512756, | |
| "learning_rate": 0.00044392630104514593, | |
| "loss": 3.5256, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 2.6154342912495965, | |
| "grad_norm": 0.5474342107772827, | |
| "learning_rate": 0.0004436030600150845, | |
| "loss": 3.526, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 2.6208158432892046, | |
| "grad_norm": 0.5688294768333435, | |
| "learning_rate": 0.0004432798189850231, | |
| "loss": 3.5341, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 2.6261973953288127, | |
| "grad_norm": 0.5909520387649536, | |
| "learning_rate": 0.0004429565779549617, | |
| "loss": 3.5394, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.5881052613258362, | |
| "learning_rate": 0.0004426333369249003, | |
| "loss": 3.544, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 2.6369604994080293, | |
| "grad_norm": 0.5401953458786011, | |
| "learning_rate": 0.0004423100958948389, | |
| "loss": 3.5518, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.6423420514476375, | |
| "grad_norm": 0.6648808121681213, | |
| "learning_rate": 0.00044198685486477744, | |
| "loss": 3.5483, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 2.6477236034872456, | |
| "grad_norm": 0.5619612336158752, | |
| "learning_rate": 0.00044166361383471604, | |
| "loss": 3.5388, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.653105155526854, | |
| "grad_norm": 0.5457707643508911, | |
| "learning_rate": 0.0004413403728046547, | |
| "loss": 3.5491, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 2.658486707566462, | |
| "grad_norm": 0.6164374947547913, | |
| "learning_rate": 0.0004410171317745932, | |
| "loss": 3.5383, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.6638682596060703, | |
| "grad_norm": 0.5915449261665344, | |
| "learning_rate": 0.0004406938907445318, | |
| "loss": 3.5412, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 2.6692498116456784, | |
| "grad_norm": 0.6016857028007507, | |
| "learning_rate": 0.00044037064971447036, | |
| "loss": 3.5451, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.674631363685287, | |
| "grad_norm": 0.5480591058731079, | |
| "learning_rate": 0.00044004740868440896, | |
| "loss": 3.538, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 2.680012915724895, | |
| "grad_norm": 0.5656848549842834, | |
| "learning_rate": 0.00043972416765434755, | |
| "loss": 3.5566, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.685394467764503, | |
| "grad_norm": 0.6277399063110352, | |
| "learning_rate": 0.00043940092662428615, | |
| "loss": 3.5456, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 2.6907760198041117, | |
| "grad_norm": 0.6056678295135498, | |
| "learning_rate": 0.00043907768559422474, | |
| "loss": 3.5473, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.6907760198041117, | |
| "eval_accuracy": 0.36839630836602244, | |
| "eval_loss": 3.5200185775756836, | |
| "eval_runtime": 179.6896, | |
| "eval_samples_per_second": 100.234, | |
| "eval_steps_per_second": 6.266, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.69615757184372, | |
| "grad_norm": 0.635338544845581, | |
| "learning_rate": 0.00043875444456416334, | |
| "loss": 3.5616, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 2.701539123883328, | |
| "grad_norm": 0.6054742932319641, | |
| "learning_rate": 0.0004384312035341019, | |
| "loss": 3.5651, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.706920675922936, | |
| "grad_norm": 0.6213764548301697, | |
| "learning_rate": 0.00043810796250404047, | |
| "loss": 3.5406, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 2.712302227962544, | |
| "grad_norm": 0.5552936792373657, | |
| "learning_rate": 0.000437784721473979, | |
| "loss": 3.5186, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.7176837800021527, | |
| "grad_norm": 0.588412344455719, | |
| "learning_rate": 0.00043746148044391766, | |
| "loss": 3.5416, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 2.723065332041761, | |
| "grad_norm": 0.5414818525314331, | |
| "learning_rate": 0.00043713823941385625, | |
| "loss": 3.5289, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.728446884081369, | |
| "grad_norm": 0.6171042919158936, | |
| "learning_rate": 0.0004368149983837948, | |
| "loss": 3.548, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 2.7338284361209775, | |
| "grad_norm": 0.6250415444374084, | |
| "learning_rate": 0.0004364917573537334, | |
| "loss": 3.5393, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.7392099881605856, | |
| "grad_norm": 0.6534850597381592, | |
| "learning_rate": 0.00043616851632367193, | |
| "loss": 3.5351, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 2.7445915402001937, | |
| "grad_norm": 0.6056131720542908, | |
| "learning_rate": 0.0004358452752936106, | |
| "loss": 3.5331, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.749973092239802, | |
| "grad_norm": 0.6097458004951477, | |
| "learning_rate": 0.0004355220342635492, | |
| "loss": 3.5229, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 2.7553546442794103, | |
| "grad_norm": 0.5821205377578735, | |
| "learning_rate": 0.00043519879323348777, | |
| "loss": 3.5547, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.7607361963190185, | |
| "grad_norm": 0.572923481464386, | |
| "learning_rate": 0.0004348755522034263, | |
| "loss": 3.5459, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 2.7661177483586266, | |
| "grad_norm": 0.5959768295288086, | |
| "learning_rate": 0.0004345523111733649, | |
| "loss": 3.53, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.7714993003982347, | |
| "grad_norm": 0.6123167872428894, | |
| "learning_rate": 0.00043422907014330344, | |
| "loss": 3.5332, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 2.776880852437843, | |
| "grad_norm": 0.5567452311515808, | |
| "learning_rate": 0.0004339058291132421, | |
| "loss": 3.5329, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.7822624044774513, | |
| "grad_norm": 0.6061723232269287, | |
| "learning_rate": 0.0004335825880831807, | |
| "loss": 3.5429, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 2.7876439565170594, | |
| "grad_norm": 0.5593557357788086, | |
| "learning_rate": 0.00043325934705311923, | |
| "loss": 3.5072, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.793025508556668, | |
| "grad_norm": 0.5608957409858704, | |
| "learning_rate": 0.0004329361060230578, | |
| "loss": 3.5159, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 2.798407060596276, | |
| "grad_norm": 0.5900284051895142, | |
| "learning_rate": 0.00043261286499299636, | |
| "loss": 3.5301, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.798407060596276, | |
| "eval_accuracy": 0.36886427635383945, | |
| "eval_loss": 3.5095598697662354, | |
| "eval_runtime": 180.5366, | |
| "eval_samples_per_second": 99.764, | |
| "eval_steps_per_second": 6.237, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.803788612635884, | |
| "grad_norm": 0.5952501893043518, | |
| "learning_rate": 0.00043228962396293496, | |
| "loss": 3.5283, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 2.8091701646754923, | |
| "grad_norm": 0.5934816598892212, | |
| "learning_rate": 0.00043197284775347476, | |
| "loss": 3.5287, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.8145517167151004, | |
| "grad_norm": 0.6665016412734985, | |
| "learning_rate": 0.00043164960672341336, | |
| "loss": 3.5178, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 2.819933268754709, | |
| "grad_norm": 0.5784537196159363, | |
| "learning_rate": 0.000431326365693352, | |
| "loss": 3.5368, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.825314820794317, | |
| "grad_norm": 0.5916054248809814, | |
| "learning_rate": 0.00043100312466329055, | |
| "loss": 3.5361, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 2.830696372833925, | |
| "grad_norm": 0.5684788227081299, | |
| "learning_rate": 0.00043067988363322914, | |
| "loss": 3.5204, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.8360779248735337, | |
| "grad_norm": 0.5924267172813416, | |
| "learning_rate": 0.00043035664260316774, | |
| "loss": 3.5382, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 2.841459476913142, | |
| "grad_norm": 0.6063621640205383, | |
| "learning_rate": 0.0004300334015731063, | |
| "loss": 3.5343, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 2.84684102895275, | |
| "grad_norm": 0.6259608268737793, | |
| "learning_rate": 0.0004297101605430449, | |
| "loss": 3.5212, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 2.852222580992358, | |
| "grad_norm": 0.5912953019142151, | |
| "learning_rate": 0.0004293869195129835, | |
| "loss": 3.5333, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.857604133031966, | |
| "grad_norm": 0.6470860838890076, | |
| "learning_rate": 0.00042906367848292206, | |
| "loss": 3.5356, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 2.8629856850715747, | |
| "grad_norm": 0.6130536198616028, | |
| "learning_rate": 0.00042874043745286066, | |
| "loss": 3.5259, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 2.868367237111183, | |
| "grad_norm": 0.5800825357437134, | |
| "learning_rate": 0.0004284171964227992, | |
| "loss": 3.5425, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 2.873748789150791, | |
| "grad_norm": 0.5847500562667847, | |
| "learning_rate": 0.0004280939553927378, | |
| "loss": 3.5086, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 2.8791303411903995, | |
| "grad_norm": 0.6748270988464355, | |
| "learning_rate": 0.00042777071436267644, | |
| "loss": 3.5213, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 2.8845118932300076, | |
| "grad_norm": 0.576877772808075, | |
| "learning_rate": 0.000427447473332615, | |
| "loss": 3.5173, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 2.8898934452696157, | |
| "grad_norm": 0.5994119644165039, | |
| "learning_rate": 0.0004271242323025536, | |
| "loss": 3.5184, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 2.895274997309224, | |
| "grad_norm": 0.5870147943496704, | |
| "learning_rate": 0.00042680099127249217, | |
| "loss": 3.5404, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 2.9006565493488323, | |
| "grad_norm": 0.5605146884918213, | |
| "learning_rate": 0.0004264777502424307, | |
| "loss": 3.5338, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 2.9060381013884404, | |
| "grad_norm": 0.6184528470039368, | |
| "learning_rate": 0.0004261545092123693, | |
| "loss": 3.5226, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.9060381013884404, | |
| "eval_accuracy": 0.3700053489816671, | |
| "eval_loss": 3.502581834793091, | |
| "eval_runtime": 180.637, | |
| "eval_samples_per_second": 99.708, | |
| "eval_steps_per_second": 6.233, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.9114196534280485, | |
| "grad_norm": 0.6496872305870056, | |
| "learning_rate": 0.00042583126818230795, | |
| "loss": 3.5242, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 2.9168012054676566, | |
| "grad_norm": 0.6035163402557373, | |
| "learning_rate": 0.0004255080271522465, | |
| "loss": 3.5265, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 2.922182757507265, | |
| "grad_norm": 0.5869918465614319, | |
| "learning_rate": 0.0004251847861221851, | |
| "loss": 3.5208, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 2.9275643095468733, | |
| "grad_norm": 0.6070534586906433, | |
| "learning_rate": 0.00042486154509212363, | |
| "loss": 3.4932, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 2.9329458615864814, | |
| "grad_norm": 0.6247556805610657, | |
| "learning_rate": 0.0004245383040620622, | |
| "loss": 3.5168, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 2.93832741362609, | |
| "grad_norm": 0.606638491153717, | |
| "learning_rate": 0.0004242150630320009, | |
| "loss": 3.5379, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 2.943708965665698, | |
| "grad_norm": 0.5896838307380676, | |
| "learning_rate": 0.0004238918220019394, | |
| "loss": 3.5439, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 2.949090517705306, | |
| "grad_norm": 0.7161862850189209, | |
| "learning_rate": 0.000423568580971878, | |
| "loss": 3.524, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 2.9544720697449143, | |
| "grad_norm": 0.5472960472106934, | |
| "learning_rate": 0.00042324533994181655, | |
| "loss": 3.5082, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 2.9598536217845224, | |
| "grad_norm": 0.6270456910133362, | |
| "learning_rate": 0.00042292209891175514, | |
| "loss": 3.5133, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.965235173824131, | |
| "grad_norm": 0.6163716912269592, | |
| "learning_rate": 0.00042259885788169374, | |
| "loss": 3.5185, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 2.970616725863739, | |
| "grad_norm": 0.5813859105110168, | |
| "learning_rate": 0.00042227561685163233, | |
| "loss": 3.5219, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 2.975998277903347, | |
| "grad_norm": 0.6137823462486267, | |
| "learning_rate": 0.00042195237582157093, | |
| "loss": 3.5238, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 2.9813798299429557, | |
| "grad_norm": 0.573917031288147, | |
| "learning_rate": 0.0004216291347915095, | |
| "loss": 3.531, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 2.986761381982564, | |
| "grad_norm": 0.6336318254470825, | |
| "learning_rate": 0.00042130589376144806, | |
| "loss": 3.5142, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 2.992142934022172, | |
| "grad_norm": 0.5717305541038513, | |
| "learning_rate": 0.00042098265273138666, | |
| "loss": 3.5073, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 2.9975244860617805, | |
| "grad_norm": 0.6153519749641418, | |
| "learning_rate": 0.0004206594117013252, | |
| "loss": 3.5313, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 3.0029060381013886, | |
| "grad_norm": 0.5966550707817078, | |
| "learning_rate": 0.00042033617067126385, | |
| "loss": 3.4862, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 3.0082875901409967, | |
| "grad_norm": 0.5811104774475098, | |
| "learning_rate": 0.00042001292964120244, | |
| "loss": 3.4131, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 3.0136691421806048, | |
| "grad_norm": 0.5833897590637207, | |
| "learning_rate": 0.000419689688611141, | |
| "loss": 3.4297, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.0136691421806048, | |
| "eval_accuracy": 0.3707112667937978, | |
| "eval_loss": 3.4965574741363525, | |
| "eval_runtime": 180.5598, | |
| "eval_samples_per_second": 99.751, | |
| "eval_steps_per_second": 6.236, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.0190506942202133, | |
| "grad_norm": 0.6142577528953552, | |
| "learning_rate": 0.0004193664475810796, | |
| "loss": 3.4263, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 3.0244322462598214, | |
| "grad_norm": 0.60226970911026, | |
| "learning_rate": 0.00041904320655101817, | |
| "loss": 3.4323, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 3.0298137982994295, | |
| "grad_norm": 0.6177240014076233, | |
| "learning_rate": 0.0004187199655209567, | |
| "loss": 3.4357, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 3.0351953503390376, | |
| "grad_norm": 0.5931535363197327, | |
| "learning_rate": 0.00041839672449089536, | |
| "loss": 3.4589, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 3.040576902378646, | |
| "grad_norm": 0.608650803565979, | |
| "learning_rate": 0.00041807348346083395, | |
| "loss": 3.4432, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 3.0459584544182543, | |
| "grad_norm": 0.6467320322990417, | |
| "learning_rate": 0.0004177502424307725, | |
| "loss": 3.4356, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 3.0513400064578624, | |
| "grad_norm": 0.6208910346031189, | |
| "learning_rate": 0.0004174270014007111, | |
| "loss": 3.4335, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 3.0567215584974705, | |
| "grad_norm": 0.6012397408485413, | |
| "learning_rate": 0.00041710376037064963, | |
| "loss": 3.4368, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 3.062103110537079, | |
| "grad_norm": 0.5883954763412476, | |
| "learning_rate": 0.0004167805193405883, | |
| "loss": 3.4407, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 3.067484662576687, | |
| "grad_norm": 0.5667783617973328, | |
| "learning_rate": 0.0004164572783105269, | |
| "loss": 3.4358, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.0728662146162953, | |
| "grad_norm": 0.6078146696090698, | |
| "learning_rate": 0.0004161340372804654, | |
| "loss": 3.4422, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 3.0782477666559034, | |
| "grad_norm": 0.6011075377464294, | |
| "learning_rate": 0.000415810796250404, | |
| "loss": 3.4444, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 3.083629318695512, | |
| "grad_norm": 0.6752050518989563, | |
| "learning_rate": 0.0004154875552203426, | |
| "loss": 3.4557, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 3.08901087073512, | |
| "grad_norm": 0.6102807521820068, | |
| "learning_rate": 0.00041516431419028114, | |
| "loss": 3.4272, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 3.094392422774728, | |
| "grad_norm": 0.6542812585830688, | |
| "learning_rate": 0.0004148410731602198, | |
| "loss": 3.4495, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 3.0997739748143363, | |
| "grad_norm": 0.6202298998832703, | |
| "learning_rate": 0.0004145178321301584, | |
| "loss": 3.4493, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 3.105155526853945, | |
| "grad_norm": 0.6084877848625183, | |
| "learning_rate": 0.00041419459110009693, | |
| "loss": 3.4437, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 3.110537078893553, | |
| "grad_norm": 0.8142428398132324, | |
| "learning_rate": 0.0004138713500700355, | |
| "loss": 3.4456, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 3.115918630933161, | |
| "grad_norm": 0.6456471681594849, | |
| "learning_rate": 0.00041354810903997406, | |
| "loss": 3.4468, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 3.121300182972769, | |
| "grad_norm": 0.6340752840042114, | |
| "learning_rate": 0.00041322486800991266, | |
| "loss": 3.4224, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.121300182972769, | |
| "eval_accuracy": 0.37119194716948906, | |
| "eval_loss": 3.4933841228485107, | |
| "eval_runtime": 180.305, | |
| "eval_samples_per_second": 99.892, | |
| "eval_steps_per_second": 6.245, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.1266817350123777, | |
| "grad_norm": 0.6109960675239563, | |
| "learning_rate": 0.0004129016269798513, | |
| "loss": 3.4461, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 3.132063287051986, | |
| "grad_norm": 0.5882677435874939, | |
| "learning_rate": 0.00041257838594978985, | |
| "loss": 3.4344, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.137444839091594, | |
| "grad_norm": 0.5873978734016418, | |
| "learning_rate": 0.00041225514491972844, | |
| "loss": 3.4492, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 3.1428263911312024, | |
| "grad_norm": 0.6426523923873901, | |
| "learning_rate": 0.00041193190388966704, | |
| "loss": 3.4381, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.1482079431708105, | |
| "grad_norm": 0.5868753790855408, | |
| "learning_rate": 0.0004116086628596056, | |
| "loss": 3.4539, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 3.1535894952104186, | |
| "grad_norm": 0.6552289128303528, | |
| "learning_rate": 0.0004112854218295442, | |
| "loss": 3.4576, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.1589710472500268, | |
| "grad_norm": 0.6329394578933716, | |
| "learning_rate": 0.0004109621807994828, | |
| "loss": 3.4514, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 3.1643525992896353, | |
| "grad_norm": 0.6486338376998901, | |
| "learning_rate": 0.00041063893976942136, | |
| "loss": 3.4588, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.1697341513292434, | |
| "grad_norm": 0.5754224061965942, | |
| "learning_rate": 0.00041031569873935996, | |
| "loss": 3.4392, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 3.1751157033688515, | |
| "grad_norm": 0.6380184888839722, | |
| "learning_rate": 0.0004099924577092985, | |
| "loss": 3.4547, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.1804972554084596, | |
| "grad_norm": 0.6305249333381653, | |
| "learning_rate": 0.0004096692166792371, | |
| "loss": 3.4568, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 3.185878807448068, | |
| "grad_norm": 0.6137855648994446, | |
| "learning_rate": 0.00040934597564917574, | |
| "loss": 3.4612, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.1912603594876763, | |
| "grad_norm": 0.5795332789421082, | |
| "learning_rate": 0.0004090227346191143, | |
| "loss": 3.4387, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 3.1966419115272844, | |
| "grad_norm": 0.6044164299964905, | |
| "learning_rate": 0.0004086994935890529, | |
| "loss": 3.4696, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.2020234635668925, | |
| "grad_norm": 0.60833340883255, | |
| "learning_rate": 0.00040837625255899147, | |
| "loss": 3.4597, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 3.207405015606501, | |
| "grad_norm": 0.6233122944831848, | |
| "learning_rate": 0.00040805301152893, | |
| "loss": 3.4374, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.212786567646109, | |
| "grad_norm": 0.6239629983901978, | |
| "learning_rate": 0.0004077297704988686, | |
| "loss": 3.4452, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 3.2181681196857173, | |
| "grad_norm": 0.6396247148513794, | |
| "learning_rate": 0.00040740652946880725, | |
| "loss": 3.4325, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 3.2235496717253254, | |
| "grad_norm": 0.58219975233078, | |
| "learning_rate": 0.0004070832884387458, | |
| "loss": 3.466, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 3.228931223764934, | |
| "grad_norm": 0.6302553415298462, | |
| "learning_rate": 0.0004067600474086844, | |
| "loss": 3.456, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.228931223764934, | |
| "eval_accuracy": 0.3716267760265226, | |
| "eval_loss": 3.489248275756836, | |
| "eval_runtime": 180.7912, | |
| "eval_samples_per_second": 99.623, | |
| "eval_steps_per_second": 6.228, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.234312775804542, | |
| "grad_norm": 0.6658568382263184, | |
| "learning_rate": 0.00040643680637862293, | |
| "loss": 3.4516, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 3.23969432784415, | |
| "grad_norm": 0.6323238611221313, | |
| "learning_rate": 0.0004061135653485615, | |
| "loss": 3.457, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 3.2450758798837587, | |
| "grad_norm": 0.5995866060256958, | |
| "learning_rate": 0.00040579678913910133, | |
| "loss": 3.4326, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 3.250457431923367, | |
| "grad_norm": 0.6197038888931274, | |
| "learning_rate": 0.0004054735481090399, | |
| "loss": 3.4274, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 3.255838983962975, | |
| "grad_norm": 0.5652536749839783, | |
| "learning_rate": 0.0004051503070789786, | |
| "loss": 3.4548, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 3.261220536002583, | |
| "grad_norm": 0.6363932490348816, | |
| "learning_rate": 0.0004048270660489171, | |
| "loss": 3.4593, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 3.2666020880421915, | |
| "grad_norm": 0.6436594128608704, | |
| "learning_rate": 0.0004045038250188557, | |
| "loss": 3.4508, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 3.2719836400817996, | |
| "grad_norm": 0.627250075340271, | |
| "learning_rate": 0.00040418058398879425, | |
| "loss": 3.4444, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 3.2773651921214078, | |
| "grad_norm": 0.659887433052063, | |
| "learning_rate": 0.00040385734295873284, | |
| "loss": 3.4687, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 3.282746744161016, | |
| "grad_norm": 0.5804165005683899, | |
| "learning_rate": 0.00040353410192867144, | |
| "loss": 3.4656, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.2881282962006244, | |
| "grad_norm": 0.6306347846984863, | |
| "learning_rate": 0.00040321086089861003, | |
| "loss": 3.4417, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 3.2935098482402325, | |
| "grad_norm": 0.6350857019424438, | |
| "learning_rate": 0.00040288761986854863, | |
| "loss": 3.4682, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 3.2988914002798406, | |
| "grad_norm": 0.7076759338378906, | |
| "learning_rate": 0.0004025643788384872, | |
| "loss": 3.4531, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 3.304272952319449, | |
| "grad_norm": 0.6139525175094604, | |
| "learning_rate": 0.00040224113780842576, | |
| "loss": 3.4659, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 3.3096545043590573, | |
| "grad_norm": 0.6305450201034546, | |
| "learning_rate": 0.00040191789677836436, | |
| "loss": 3.4443, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 3.3150360563986654, | |
| "grad_norm": 0.5848320722579956, | |
| "learning_rate": 0.0004015946557483029, | |
| "loss": 3.453, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 3.3204176084382735, | |
| "grad_norm": 0.6427562236785889, | |
| "learning_rate": 0.00040127141471824155, | |
| "loss": 3.4731, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 3.3257991604778816, | |
| "grad_norm": 0.6468438506126404, | |
| "learning_rate": 0.00040094817368818014, | |
| "loss": 3.4487, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 3.33118071251749, | |
| "grad_norm": 0.6019175052642822, | |
| "learning_rate": 0.0004006249326581187, | |
| "loss": 3.4629, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 3.3365622645570983, | |
| "grad_norm": 0.6581705212593079, | |
| "learning_rate": 0.0004003016916280573, | |
| "loss": 3.4661, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.3365622645570983, | |
| "eval_accuracy": 0.37244656206508286, | |
| "eval_loss": 3.4832379817962646, | |
| "eval_runtime": 180.6125, | |
| "eval_samples_per_second": 99.722, | |
| "eval_steps_per_second": 6.234, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.3419438165967064, | |
| "grad_norm": 0.65335613489151, | |
| "learning_rate": 0.00039997845059799587, | |
| "loss": 3.4359, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 3.347325368636315, | |
| "grad_norm": 0.6507302522659302, | |
| "learning_rate": 0.00039965520956793447, | |
| "loss": 3.4525, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 3.352706920675923, | |
| "grad_norm": 0.5894781351089478, | |
| "learning_rate": 0.00039933196853787306, | |
| "loss": 3.4516, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 3.358088472715531, | |
| "grad_norm": 0.6025640964508057, | |
| "learning_rate": 0.00039900872750781166, | |
| "loss": 3.4648, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 3.3634700247551392, | |
| "grad_norm": 0.6366141438484192, | |
| "learning_rate": 0.0003986854864777502, | |
| "loss": 3.4504, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 3.368851576794748, | |
| "grad_norm": 0.6077277064323425, | |
| "learning_rate": 0.0003983622454476888, | |
| "loss": 3.4439, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 3.374233128834356, | |
| "grad_norm": 0.6532594561576843, | |
| "learning_rate": 0.00039803900441762733, | |
| "loss": 3.4624, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 3.379614680873964, | |
| "grad_norm": 0.6048536896705627, | |
| "learning_rate": 0.000397715763387566, | |
| "loss": 3.4589, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 3.384996232913572, | |
| "grad_norm": 0.6351385712623596, | |
| "learning_rate": 0.0003973925223575046, | |
| "loss": 3.4395, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 3.3903777849531807, | |
| "grad_norm": 0.6504836082458496, | |
| "learning_rate": 0.0003970692813274431, | |
| "loss": 3.4588, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.3957593369927888, | |
| "grad_norm": 0.6237932443618774, | |
| "learning_rate": 0.0003967460402973817, | |
| "loss": 3.4532, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 3.401140889032397, | |
| "grad_norm": 0.5831241011619568, | |
| "learning_rate": 0.0003964227992673203, | |
| "loss": 3.447, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 3.4065224410720054, | |
| "grad_norm": 0.6177220344543457, | |
| "learning_rate": 0.00039609955823725884, | |
| "loss": 3.4438, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 3.4119039931116135, | |
| "grad_norm": 0.6046972870826721, | |
| "learning_rate": 0.0003957763172071975, | |
| "loss": 3.4752, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 3.4172855451512216, | |
| "grad_norm": 0.6035352349281311, | |
| "learning_rate": 0.0003954530761771361, | |
| "loss": 3.4588, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 3.4226670971908297, | |
| "grad_norm": 0.5911862850189209, | |
| "learning_rate": 0.00039512983514707463, | |
| "loss": 3.4505, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 3.428048649230438, | |
| "grad_norm": 0.5918540358543396, | |
| "learning_rate": 0.0003948065941170132, | |
| "loss": 3.4555, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 3.4334302012700464, | |
| "grad_norm": 0.6266008019447327, | |
| "learning_rate": 0.00039448335308695176, | |
| "loss": 3.4768, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 3.4388117533096545, | |
| "grad_norm": 0.6207110285758972, | |
| "learning_rate": 0.00039416011205689036, | |
| "loss": 3.4568, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 3.4441933053492626, | |
| "grad_norm": 0.6404582858085632, | |
| "learning_rate": 0.000393836871026829, | |
| "loss": 3.4577, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.4441933053492626, | |
| "eval_accuracy": 0.37327199805380945, | |
| "eval_loss": 3.4748642444610596, | |
| "eval_runtime": 180.6631, | |
| "eval_samples_per_second": 99.694, | |
| "eval_steps_per_second": 6.233, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.449574857388871, | |
| "grad_norm": 0.6518675088882446, | |
| "learning_rate": 0.00039351362999676755, | |
| "loss": 3.4445, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 3.4549564094284793, | |
| "grad_norm": 0.6538469195365906, | |
| "learning_rate": 0.00039319038896670614, | |
| "loss": 3.4755, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 3.4603379614680874, | |
| "grad_norm": 0.5812484622001648, | |
| "learning_rate": 0.00039287361275724595, | |
| "loss": 3.4689, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 3.4657195135076955, | |
| "grad_norm": 0.6309418678283691, | |
| "learning_rate": 0.00039255037172718454, | |
| "loss": 3.4447, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 3.471101065547304, | |
| "grad_norm": 0.6192950010299683, | |
| "learning_rate": 0.0003922271306971231, | |
| "loss": 3.4599, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 3.476482617586912, | |
| "grad_norm": 0.6055722832679749, | |
| "learning_rate": 0.0003919038896670617, | |
| "loss": 3.462, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 3.4818641696265202, | |
| "grad_norm": 0.6457564234733582, | |
| "learning_rate": 0.00039158064863700033, | |
| "loss": 3.4393, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 3.4872457216661283, | |
| "grad_norm": 0.6618093848228455, | |
| "learning_rate": 0.00039125740760693887, | |
| "loss": 3.4606, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 3.492627273705737, | |
| "grad_norm": 0.5980201363563538, | |
| "learning_rate": 0.00039093416657687746, | |
| "loss": 3.4392, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 3.498008825745345, | |
| "grad_norm": 0.6752046346664429, | |
| "learning_rate": 0.00039061092554681606, | |
| "loss": 3.4676, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.503390377784953, | |
| "grad_norm": 0.6271814703941345, | |
| "learning_rate": 0.0003902876845167546, | |
| "loss": 3.4844, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "grad_norm": 0.6477372050285339, | |
| "learning_rate": 0.0003899644434866932, | |
| "loss": 3.457, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 3.5141534818641698, | |
| "grad_norm": 0.613669753074646, | |
| "learning_rate": 0.00038964120245663184, | |
| "loss": 3.4533, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 3.519535033903778, | |
| "grad_norm": 0.5857597589492798, | |
| "learning_rate": 0.0003893179614265704, | |
| "loss": 3.4571, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 3.524916585943386, | |
| "grad_norm": 0.6374267339706421, | |
| "learning_rate": 0.000388994720396509, | |
| "loss": 3.455, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 3.530298137982994, | |
| "grad_norm": 0.6730107665061951, | |
| "learning_rate": 0.0003886714793664475, | |
| "loss": 3.4661, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 3.5356796900226026, | |
| "grad_norm": 0.6586828827857971, | |
| "learning_rate": 0.0003883482383363861, | |
| "loss": 3.4606, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 3.5410612420622107, | |
| "grad_norm": 0.6340796947479248, | |
| "learning_rate": 0.00038802499730632476, | |
| "loss": 3.4729, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 3.546442794101819, | |
| "grad_norm": 0.6165903806686401, | |
| "learning_rate": 0.0003877017562762633, | |
| "loss": 3.4466, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 3.5518243461414274, | |
| "grad_norm": 0.6035377383232117, | |
| "learning_rate": 0.0003873785152462019, | |
| "loss": 3.4654, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.5518243461414274, | |
| "eval_accuracy": 0.3737836445025279, | |
| "eval_loss": 3.466870069503784, | |
| "eval_runtime": 180.8094, | |
| "eval_samples_per_second": 99.613, | |
| "eval_steps_per_second": 6.228, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.5572058981810355, | |
| "grad_norm": 0.6327840089797974, | |
| "learning_rate": 0.0003870552742161405, | |
| "loss": 3.4539, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 3.5625874502206436, | |
| "grad_norm": 0.6125268936157227, | |
| "learning_rate": 0.00038673203318607903, | |
| "loss": 3.4392, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 3.5679690022602517, | |
| "grad_norm": 0.6121278405189514, | |
| "learning_rate": 0.0003864087921560176, | |
| "loss": 3.452, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 3.57335055429986, | |
| "grad_norm": 0.5984029769897461, | |
| "learning_rate": 0.0003860855511259563, | |
| "loss": 3.4638, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 3.5787321063394684, | |
| "grad_norm": 0.6518922448158264, | |
| "learning_rate": 0.0003857623100958948, | |
| "loss": 3.4674, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 3.5841136583790765, | |
| "grad_norm": 0.6262392401695251, | |
| "learning_rate": 0.0003854390690658334, | |
| "loss": 3.4391, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 3.5894952104186846, | |
| "grad_norm": 0.5916134715080261, | |
| "learning_rate": 0.00038511582803577195, | |
| "loss": 3.4595, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 3.594876762458293, | |
| "grad_norm": 0.6136584877967834, | |
| "learning_rate": 0.00038479258700571054, | |
| "loss": 3.4431, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 3.6002583144979012, | |
| "grad_norm": 0.6699656248092651, | |
| "learning_rate": 0.00038446934597564914, | |
| "loss": 3.4583, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 3.6056398665375093, | |
| "grad_norm": 0.5867238640785217, | |
| "learning_rate": 0.00038414610494558773, | |
| "loss": 3.4409, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.611021418577118, | |
| "grad_norm": 0.6047042012214661, | |
| "learning_rate": 0.00038382286391552633, | |
| "loss": 3.4538, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 3.616402970616726, | |
| "grad_norm": 0.6440869569778442, | |
| "learning_rate": 0.0003834996228854649, | |
| "loss": 3.4487, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 3.621784522656334, | |
| "grad_norm": 0.5783991813659668, | |
| "learning_rate": 0.00038317638185540346, | |
| "loss": 3.4664, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 3.627166074695942, | |
| "grad_norm": 0.611685574054718, | |
| "learning_rate": 0.00038285314082534206, | |
| "loss": 3.4513, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 3.6325476267355503, | |
| "grad_norm": 0.6536784172058105, | |
| "learning_rate": 0.0003825298997952806, | |
| "loss": 3.4523, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 3.637929178775159, | |
| "grad_norm": 0.557302713394165, | |
| "learning_rate": 0.00038220665876521925, | |
| "loss": 3.4496, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 3.643310730814767, | |
| "grad_norm": 0.6502556204795837, | |
| "learning_rate": 0.00038188341773515784, | |
| "loss": 3.4551, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 3.648692282854375, | |
| "grad_norm": 0.6656308770179749, | |
| "learning_rate": 0.0003815601767050964, | |
| "loss": 3.4679, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 3.6540738348939836, | |
| "grad_norm": 0.6328909993171692, | |
| "learning_rate": 0.000381236935675035, | |
| "loss": 3.4338, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 3.6594553869335917, | |
| "grad_norm": 0.5742416977882385, | |
| "learning_rate": 0.0003809136946449735, | |
| "loss": 3.4522, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.6594553869335917, | |
| "eval_accuracy": 0.3745204197347979, | |
| "eval_loss": 3.4621152877807617, | |
| "eval_runtime": 180.7271, | |
| "eval_samples_per_second": 99.659, | |
| "eval_steps_per_second": 6.23, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.6648369389732, | |
| "grad_norm": 0.6359716653823853, | |
| "learning_rate": 0.00038059045361491217, | |
| "loss": 3.4588, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 3.670218491012808, | |
| "grad_norm": 0.5943437814712524, | |
| "learning_rate": 0.00038026721258485076, | |
| "loss": 3.4557, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 3.675600043052416, | |
| "grad_norm": 0.6035296320915222, | |
| "learning_rate": 0.0003799439715547893, | |
| "loss": 3.4482, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 3.6809815950920246, | |
| "grad_norm": 0.6305634379386902, | |
| "learning_rate": 0.00037962719534532916, | |
| "loss": 3.4752, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 3.6863631471316327, | |
| "grad_norm": 0.5965917706489563, | |
| "learning_rate": 0.0003793039543152677, | |
| "loss": 3.4266, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 3.691744699171241, | |
| "grad_norm": 0.6232327818870544, | |
| "learning_rate": 0.0003789807132852063, | |
| "loss": 3.4366, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 3.6971262512108494, | |
| "grad_norm": 0.6077519655227661, | |
| "learning_rate": 0.0003786574722551449, | |
| "loss": 3.4553, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 3.7025078032504575, | |
| "grad_norm": 0.6324222087860107, | |
| "learning_rate": 0.00037833423122508343, | |
| "loss": 3.4602, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 3.7078893552900656, | |
| "grad_norm": 0.6138796210289001, | |
| "learning_rate": 0.0003780109901950221, | |
| "loss": 3.4462, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 3.713270907329674, | |
| "grad_norm": 0.6130177974700928, | |
| "learning_rate": 0.0003776877491649607, | |
| "loss": 3.4534, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.7186524593692822, | |
| "grad_norm": 0.585455596446991, | |
| "learning_rate": 0.0003773645081348992, | |
| "loss": 3.4594, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 3.7240340114088903, | |
| "grad_norm": 0.6451506614685059, | |
| "learning_rate": 0.0003770412671048378, | |
| "loss": 3.4623, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 3.7294155634484984, | |
| "grad_norm": 0.6334204077720642, | |
| "learning_rate": 0.00037671802607477635, | |
| "loss": 3.4552, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 3.7347971154881066, | |
| "grad_norm": 0.6382574439048767, | |
| "learning_rate": 0.000376394785044715, | |
| "loss": 3.4504, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 3.740178667527715, | |
| "grad_norm": 0.6397031545639038, | |
| "learning_rate": 0.0003760715440146536, | |
| "loss": 3.4533, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 3.745560219567323, | |
| "grad_norm": 0.644877016544342, | |
| "learning_rate": 0.00037574830298459214, | |
| "loss": 3.4596, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 3.7509417716069313, | |
| "grad_norm": 0.6290867924690247, | |
| "learning_rate": 0.00037542506195453073, | |
| "loss": 3.4531, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 3.75632332364654, | |
| "grad_norm": 0.6182779669761658, | |
| "learning_rate": 0.0003751018209244693, | |
| "loss": 3.4488, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 3.761704875686148, | |
| "grad_norm": 0.6078924536705017, | |
| "learning_rate": 0.00037477857989440787, | |
| "loss": 3.4599, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 3.767086427725756, | |
| "grad_norm": 0.6303339004516602, | |
| "learning_rate": 0.0003744553388643465, | |
| "loss": 3.4511, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.767086427725756, | |
| "eval_accuracy": 0.37501337788681216, | |
| "eval_loss": 3.45632266998291, | |
| "eval_runtime": 180.682, | |
| "eval_samples_per_second": 99.683, | |
| "eval_steps_per_second": 6.232, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.772467979765364, | |
| "grad_norm": 0.6259037852287292, | |
| "learning_rate": 0.0003741320978342851, | |
| "loss": 3.4522, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 3.7778495318049723, | |
| "grad_norm": 0.6218352913856506, | |
| "learning_rate": 0.00037380885680422365, | |
| "loss": 3.452, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 3.783231083844581, | |
| "grad_norm": 0.6394650936126709, | |
| "learning_rate": 0.00037348561577416224, | |
| "loss": 3.4425, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 3.788612635884189, | |
| "grad_norm": 0.6433684825897217, | |
| "learning_rate": 0.0003731623747441008, | |
| "loss": 3.4432, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 3.793994187923797, | |
| "grad_norm": 0.5973502397537231, | |
| "learning_rate": 0.0003728391337140394, | |
| "loss": 3.4626, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 3.7993757399634056, | |
| "grad_norm": 0.6366912126541138, | |
| "learning_rate": 0.00037251589268397803, | |
| "loss": 3.4434, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 3.8047572920030137, | |
| "grad_norm": 0.6271637082099915, | |
| "learning_rate": 0.00037219265165391657, | |
| "loss": 3.4478, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 3.810138844042622, | |
| "grad_norm": 0.6246579885482788, | |
| "learning_rate": 0.00037186941062385516, | |
| "loss": 3.4664, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 3.8155203960822304, | |
| "grad_norm": 0.6329902410507202, | |
| "learning_rate": 0.0003715461695937937, | |
| "loss": 3.4509, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 3.8209019481218385, | |
| "grad_norm": 0.6158545613288879, | |
| "learning_rate": 0.0003712229285637323, | |
| "loss": 3.4538, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.8262835001614466, | |
| "grad_norm": 0.6100180149078369, | |
| "learning_rate": 0.0003708996875336709, | |
| "loss": 3.4539, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 3.8316650522010547, | |
| "grad_norm": 0.6152170896530151, | |
| "learning_rate": 0.0003705764465036095, | |
| "loss": 3.4498, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 3.837046604240663, | |
| "grad_norm": 0.6338374018669128, | |
| "learning_rate": 0.0003702532054735481, | |
| "loss": 3.4563, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 3.8424281562802713, | |
| "grad_norm": 0.6253648996353149, | |
| "learning_rate": 0.0003699299644434867, | |
| "loss": 3.452, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 3.8478097083198795, | |
| "grad_norm": 0.6302428245544434, | |
| "learning_rate": 0.0003696067234134252, | |
| "loss": 3.456, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 3.8531912603594876, | |
| "grad_norm": 0.6266033053398132, | |
| "learning_rate": 0.0003692834823833638, | |
| "loss": 3.4385, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 3.858572812399096, | |
| "grad_norm": 0.613212525844574, | |
| "learning_rate": 0.00036896024135330246, | |
| "loss": 3.4627, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 3.863954364438704, | |
| "grad_norm": 0.6388803720474243, | |
| "learning_rate": 0.000368637000323241, | |
| "loss": 3.4467, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 3.8693359164783123, | |
| "grad_norm": 0.6624432802200317, | |
| "learning_rate": 0.0003683137592931796, | |
| "loss": 3.4508, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 3.8747174685179204, | |
| "grad_norm": 0.6262862086296082, | |
| "learning_rate": 0.00036799051826311814, | |
| "loss": 3.4455, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.8747174685179204, | |
| "eval_accuracy": 0.37557652580435463, | |
| "eval_loss": 3.453572988510132, | |
| "eval_runtime": 180.586, | |
| "eval_samples_per_second": 99.736, | |
| "eval_steps_per_second": 6.235, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.8800990205575285, | |
| "grad_norm": 0.6518728137016296, | |
| "learning_rate": 0.00036766727723305673, | |
| "loss": 3.4398, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 3.885480572597137, | |
| "grad_norm": 0.6276541352272034, | |
| "learning_rate": 0.0003673440362029953, | |
| "loss": 3.4572, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 3.890862124636745, | |
| "grad_norm": 0.6711607575416565, | |
| "learning_rate": 0.0003670207951729339, | |
| "loss": 3.4699, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 3.8962436766763533, | |
| "grad_norm": 0.610508382320404, | |
| "learning_rate": 0.0003667040189634737, | |
| "loss": 3.4665, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 3.901625228715962, | |
| "grad_norm": 0.6061813235282898, | |
| "learning_rate": 0.0003663807779334123, | |
| "loss": 3.4368, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 3.90700678075557, | |
| "grad_norm": 0.6153860092163086, | |
| "learning_rate": 0.0003660575369033509, | |
| "loss": 3.4408, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 3.912388332795178, | |
| "grad_norm": 0.6401193141937256, | |
| "learning_rate": 0.0003657342958732895, | |
| "loss": 3.4316, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 3.9177698848347866, | |
| "grad_norm": 0.6334563493728638, | |
| "learning_rate": 0.00036541105484322805, | |
| "loss": 3.4479, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 3.9231514368743947, | |
| "grad_norm": 0.6796964406967163, | |
| "learning_rate": 0.00036508781381316665, | |
| "loss": 3.4225, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 3.928532988914003, | |
| "grad_norm": 0.5866906046867371, | |
| "learning_rate": 0.0003647645727831053, | |
| "loss": 3.4297, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.933914540953611, | |
| "grad_norm": 0.6415225267410278, | |
| "learning_rate": 0.00036444133175304384, | |
| "loss": 3.4563, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 3.939296092993219, | |
| "grad_norm": 0.6429531574249268, | |
| "learning_rate": 0.00036411809072298243, | |
| "loss": 3.4365, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 3.9446776450328276, | |
| "grad_norm": 0.590459942817688, | |
| "learning_rate": 0.00036379484969292097, | |
| "loss": 3.4546, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 3.9500591970724357, | |
| "grad_norm": 0.5942658185958862, | |
| "learning_rate": 0.00036347160866285956, | |
| "loss": 3.438, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 3.955440749112044, | |
| "grad_norm": 0.6288406848907471, | |
| "learning_rate": 0.0003631483676327981, | |
| "loss": 3.4517, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 3.9608223011516523, | |
| "grad_norm": 0.6701431274414062, | |
| "learning_rate": 0.00036282512660273675, | |
| "loss": 3.4485, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 3.9662038531912605, | |
| "grad_norm": 0.7019712328910828, | |
| "learning_rate": 0.00036250188557267535, | |
| "loss": 3.4408, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 3.9715854052308686, | |
| "grad_norm": 0.6082743406295776, | |
| "learning_rate": 0.0003621786445426139, | |
| "loss": 3.4446, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 3.9769669572704767, | |
| "grad_norm": 0.6317737102508545, | |
| "learning_rate": 0.0003618554035125525, | |
| "loss": 3.4349, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 3.9823485093100848, | |
| "grad_norm": 0.619764506816864, | |
| "learning_rate": 0.0003615321624824911, | |
| "loss": 3.4402, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.9823485093100848, | |
| "eval_accuracy": 0.3760329765860633, | |
| "eval_loss": 3.4432144165039062, | |
| "eval_runtime": 180.6742, | |
| "eval_samples_per_second": 99.688, | |
| "eval_steps_per_second": 6.232, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.9877300613496933, | |
| "grad_norm": 0.649409830570221, | |
| "learning_rate": 0.0003612089214524296, | |
| "loss": 3.4344, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 3.9931116133893014, | |
| "grad_norm": 0.6841443777084351, | |
| "learning_rate": 0.00036088568042236827, | |
| "loss": 3.4393, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 3.9984931654289095, | |
| "grad_norm": 0.6146060824394226, | |
| "learning_rate": 0.00036056243939230686, | |
| "loss": 3.4337, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 4.003874717468518, | |
| "grad_norm": 0.6463866829872131, | |
| "learning_rate": 0.0003602391983622454, | |
| "loss": 3.3701, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 4.009256269508126, | |
| "grad_norm": 0.6479421257972717, | |
| "learning_rate": 0.000359915957332184, | |
| "loss": 3.3524, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 4.014637821547734, | |
| "grad_norm": 0.7297543883323669, | |
| "learning_rate": 0.00035959271630212254, | |
| "loss": 3.3483, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 4.020019373587343, | |
| "grad_norm": 0.6528753638267517, | |
| "learning_rate": 0.00035926947527206113, | |
| "loss": 3.3525, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 4.0254009256269505, | |
| "grad_norm": 0.6073748469352722, | |
| "learning_rate": 0.0003589462342419998, | |
| "loss": 3.3627, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 4.030782477666559, | |
| "grad_norm": 0.6415776610374451, | |
| "learning_rate": 0.0003586229932119383, | |
| "loss": 3.3607, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 4.036164029706168, | |
| "grad_norm": 0.629884660243988, | |
| "learning_rate": 0.0003582997521818769, | |
| "loss": 3.3572, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 4.041545581745775, | |
| "grad_norm": 0.6344863772392273, | |
| "learning_rate": 0.0003579765111518155, | |
| "loss": 3.3406, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 4.046927133785384, | |
| "grad_norm": 0.5791500806808472, | |
| "learning_rate": 0.00035765327012175405, | |
| "loss": 3.3334, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 4.0523086858249915, | |
| "grad_norm": 0.6291230320930481, | |
| "learning_rate": 0.0003573300290916927, | |
| "loss": 3.364, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 4.0576902378646, | |
| "grad_norm": 0.6606059670448303, | |
| "learning_rate": 0.0003570067880616313, | |
| "loss": 3.3702, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 4.063071789904209, | |
| "grad_norm": 0.66637122631073, | |
| "learning_rate": 0.00035668354703156984, | |
| "loss": 3.375, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 4.068453341943816, | |
| "grad_norm": 0.6079049110412598, | |
| "learning_rate": 0.00035636030600150843, | |
| "loss": 3.3491, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 4.073834893983425, | |
| "grad_norm": 0.6581602692604065, | |
| "learning_rate": 0.00035603706497144697, | |
| "loss": 3.3601, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 4.079216446023033, | |
| "grad_norm": 0.5903530716896057, | |
| "learning_rate": 0.00035571382394138557, | |
| "loss": 3.3685, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 4.084597998062641, | |
| "grad_norm": 0.6376979947090149, | |
| "learning_rate": 0.0003553905829113242, | |
| "loss": 3.3583, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 4.08997955010225, | |
| "grad_norm": 0.6378331184387207, | |
| "learning_rate": 0.00035506734188126275, | |
| "loss": 3.3602, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.08997955010225, | |
| "eval_accuracy": 0.37666750945089983, | |
| "eval_loss": 3.4465579986572266, | |
| "eval_runtime": 180.5241, | |
| "eval_samples_per_second": 99.771, | |
| "eval_steps_per_second": 6.237, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.095361102141858, | |
| "grad_norm": 0.6897552013397217, | |
| "learning_rate": 0.00035474410085120135, | |
| "loss": 3.3881, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 4.100742654181466, | |
| "grad_norm": 0.624983549118042, | |
| "learning_rate": 0.00035442085982113994, | |
| "loss": 3.384, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 4.106124206221074, | |
| "grad_norm": 0.6599211692810059, | |
| "learning_rate": 0.0003540976187910785, | |
| "loss": 3.3793, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 4.111505758260682, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.0003537808425816183, | |
| "loss": 3.3838, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 4.1168873103002905, | |
| "grad_norm": 0.6250761151313782, | |
| "learning_rate": 0.0003534576015515569, | |
| "loss": 3.372, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 4.122268862339899, | |
| "grad_norm": 0.6939108967781067, | |
| "learning_rate": 0.00035313436052149553, | |
| "loss": 3.3702, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 4.127650414379507, | |
| "grad_norm": 0.6383840441703796, | |
| "learning_rate": 0.0003528111194914341, | |
| "loss": 3.3634, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 4.133031966419115, | |
| "grad_norm": 0.631736159324646, | |
| "learning_rate": 0.00035248787846137267, | |
| "loss": 3.3815, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 4.138413518458724, | |
| "grad_norm": 0.9963732957839966, | |
| "learning_rate": 0.00035216463743131126, | |
| "loss": 3.3576, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 4.1437950704983315, | |
| "grad_norm": 0.6733307838439941, | |
| "learning_rate": 0.0003518413964012498, | |
| "loss": 3.3926, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.14917662253794, | |
| "grad_norm": 0.5962156653404236, | |
| "learning_rate": 0.0003515181553711884, | |
| "loss": 3.3779, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 4.154558174577549, | |
| "grad_norm": 0.6685757637023926, | |
| "learning_rate": 0.00035119491434112705, | |
| "loss": 3.3795, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 4.159939726617156, | |
| "grad_norm": 0.6577488780021667, | |
| "learning_rate": 0.0003508716733110656, | |
| "loss": 3.3678, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 4.165321278656765, | |
| "grad_norm": 0.7001060247421265, | |
| "learning_rate": 0.0003505484322810042, | |
| "loss": 3.3803, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 4.1707028306963725, | |
| "grad_norm": 0.6563752889633179, | |
| "learning_rate": 0.0003502251912509427, | |
| "loss": 3.3882, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 4.176084382735981, | |
| "grad_norm": 0.6249417066574097, | |
| "learning_rate": 0.0003499019502208813, | |
| "loss": 3.3791, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 4.18146593477559, | |
| "grad_norm": 0.6289679408073425, | |
| "learning_rate": 0.0003495787091908199, | |
| "loss": 3.3752, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 4.186847486815197, | |
| "grad_norm": 0.6969509720802307, | |
| "learning_rate": 0.0003492554681607585, | |
| "loss": 3.3764, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 4.192229038854806, | |
| "grad_norm": 0.663133442401886, | |
| "learning_rate": 0.0003489322271306971, | |
| "loss": 3.3928, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 4.197610590894414, | |
| "grad_norm": 0.7347210645675659, | |
| "learning_rate": 0.0003486089861006357, | |
| "loss": 3.3807, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.197610590894414, | |
| "eval_accuracy": 0.37702878030288295, | |
| "eval_loss": 3.4417600631713867, | |
| "eval_runtime": 180.8436, | |
| "eval_samples_per_second": 99.594, | |
| "eval_steps_per_second": 6.226, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.202992142934022, | |
| "grad_norm": 0.72121262550354, | |
| "learning_rate": 0.00034828574507057424, | |
| "loss": 3.3713, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 4.208373694973631, | |
| "grad_norm": 0.6440616250038147, | |
| "learning_rate": 0.00034796250404051283, | |
| "loss": 3.3781, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 4.213755247013238, | |
| "grad_norm": 0.6587533950805664, | |
| "learning_rate": 0.00034763926301045137, | |
| "loss": 3.3838, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 4.219136799052847, | |
| "grad_norm": 0.6770883798599243, | |
| "learning_rate": 0.00034731602198039, | |
| "loss": 3.3788, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 4.224518351092455, | |
| "grad_norm": 0.6280528903007507, | |
| "learning_rate": 0.0003469927809503286, | |
| "loss": 3.3621, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 4.229899903132063, | |
| "grad_norm": 0.7106229662895203, | |
| "learning_rate": 0.00034666953992026716, | |
| "loss": 3.3894, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 4.2352814551716715, | |
| "grad_norm": 0.6384456157684326, | |
| "learning_rate": 0.00034634629889020575, | |
| "loss": 3.3686, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 4.24066300721128, | |
| "grad_norm": 0.6792171001434326, | |
| "learning_rate": 0.00034602305786014435, | |
| "loss": 3.3783, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 4.246044559250888, | |
| "grad_norm": 0.6978849768638611, | |
| "learning_rate": 0.00034569981683008294, | |
| "loss": 3.3816, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 4.251426111290496, | |
| "grad_norm": 0.6810808181762695, | |
| "learning_rate": 0.00034537657580002154, | |
| "loss": 3.3828, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.256807663330104, | |
| "grad_norm": 0.6624694466590881, | |
| "learning_rate": 0.00034505333476996013, | |
| "loss": 3.3848, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 4.2621892153697125, | |
| "grad_norm": 0.6291442513465881, | |
| "learning_rate": 0.00034473009373989867, | |
| "loss": 3.3908, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 4.267570767409321, | |
| "grad_norm": 0.6254659295082092, | |
| "learning_rate": 0.00034440685270983727, | |
| "loss": 3.3732, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 4.272952319448929, | |
| "grad_norm": 0.6378159523010254, | |
| "learning_rate": 0.0003440836116797758, | |
| "loss": 3.3713, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 4.278333871488537, | |
| "grad_norm": 0.6168226003646851, | |
| "learning_rate": 0.00034376037064971445, | |
| "loss": 3.3812, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 4.283715423528146, | |
| "grad_norm": 0.6415433287620544, | |
| "learning_rate": 0.00034343712961965305, | |
| "loss": 3.3846, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 4.2890969755677535, | |
| "grad_norm": 0.6528810262680054, | |
| "learning_rate": 0.0003431138885895916, | |
| "loss": 3.377, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 4.294478527607362, | |
| "grad_norm": 0.6433749794960022, | |
| "learning_rate": 0.0003427906475595302, | |
| "loss": 3.3652, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 4.299860079646971, | |
| "grad_norm": 0.6395750641822815, | |
| "learning_rate": 0.0003424674065294688, | |
| "loss": 3.381, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 4.305241631686578, | |
| "grad_norm": 0.6627628207206726, | |
| "learning_rate": 0.0003421441654994073, | |
| "loss": 3.3776, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.305241631686578, | |
| "eval_accuracy": 0.37774751915577576, | |
| "eval_loss": 3.4375598430633545, | |
| "eval_runtime": 180.6158, | |
| "eval_samples_per_second": 99.72, | |
| "eval_steps_per_second": 6.234, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.310623183726187, | |
| "grad_norm": 0.6349745392799377, | |
| "learning_rate": 0.00034182092446934597, | |
| "loss": 3.3783, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 4.3160047357657945, | |
| "grad_norm": 0.6404194831848145, | |
| "learning_rate": 0.00034149768343928456, | |
| "loss": 3.3909, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 4.321386287805403, | |
| "grad_norm": 0.6430397033691406, | |
| "learning_rate": 0.0003411744424092231, | |
| "loss": 3.3771, | |
| "step": 40150 | |
| }, | |
| { | |
| "epoch": 4.326767839845012, | |
| "grad_norm": 0.660280704498291, | |
| "learning_rate": 0.0003408512013791617, | |
| "loss": 3.3799, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 4.332149391884619, | |
| "grad_norm": 0.6253730654716492, | |
| "learning_rate": 0.0003405344251697015, | |
| "loss": 3.3712, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 4.337530943924228, | |
| "grad_norm": 0.6870384216308594, | |
| "learning_rate": 0.0003402111841396401, | |
| "loss": 3.381, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 4.342912495963836, | |
| "grad_norm": 0.665998637676239, | |
| "learning_rate": 0.00033988794310957864, | |
| "loss": 3.3787, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 4.348294048003444, | |
| "grad_norm": 0.6889680027961731, | |
| "learning_rate": 0.0003395647020795173, | |
| "loss": 3.3795, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 4.3536756000430525, | |
| "grad_norm": 0.7430781722068787, | |
| "learning_rate": 0.0003392414610494559, | |
| "loss": 3.3779, | |
| "step": 40450 | |
| }, | |
| { | |
| "epoch": 4.359057152082661, | |
| "grad_norm": 0.629690945148468, | |
| "learning_rate": 0.0003389182200193944, | |
| "loss": 3.3751, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.364438704122269, | |
| "grad_norm": 0.6800459027290344, | |
| "learning_rate": 0.000338594978989333, | |
| "loss": 3.3752, | |
| "step": 40550 | |
| }, | |
| { | |
| "epoch": 4.369820256161877, | |
| "grad_norm": 0.6480296850204468, | |
| "learning_rate": 0.00033827173795927156, | |
| "loss": 3.3933, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 4.375201808201485, | |
| "grad_norm": 0.6850379705429077, | |
| "learning_rate": 0.00033794849692921015, | |
| "loss": 3.3732, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 4.3805833602410935, | |
| "grad_norm": 0.6677266359329224, | |
| "learning_rate": 0.0003376252558991488, | |
| "loss": 3.3851, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 4.385964912280702, | |
| "grad_norm": 0.6740007996559143, | |
| "learning_rate": 0.00033730201486908734, | |
| "loss": 3.3816, | |
| "step": 40750 | |
| }, | |
| { | |
| "epoch": 4.39134646432031, | |
| "grad_norm": 0.6995536684989929, | |
| "learning_rate": 0.00033697877383902594, | |
| "loss": 3.3898, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 4.396728016359918, | |
| "grad_norm": 0.6835097074508667, | |
| "learning_rate": 0.00033665553280896453, | |
| "loss": 3.3867, | |
| "step": 40850 | |
| }, | |
| { | |
| "epoch": 4.402109568399527, | |
| "grad_norm": 0.6530295014381409, | |
| "learning_rate": 0.00033633229177890307, | |
| "loss": 3.3737, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 4.4074911204391345, | |
| "grad_norm": 0.6370556354522705, | |
| "learning_rate": 0.00033600905074884167, | |
| "loss": 3.3841, | |
| "step": 40950 | |
| }, | |
| { | |
| "epoch": 4.412872672478743, | |
| "grad_norm": 0.6709283590316772, | |
| "learning_rate": 0.0003356858097187803, | |
| "loss": 3.3871, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.412872672478743, | |
| "eval_accuracy": 0.37784802307700416, | |
| "eval_loss": 3.4330832958221436, | |
| "eval_runtime": 180.4989, | |
| "eval_samples_per_second": 99.785, | |
| "eval_steps_per_second": 6.238, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.418254224518351, | |
| "grad_norm": 0.6717859506607056, | |
| "learning_rate": 0.00033536256868871886, | |
| "loss": 3.3859, | |
| "step": 41050 | |
| }, | |
| { | |
| "epoch": 4.423635776557959, | |
| "grad_norm": 0.6793646216392517, | |
| "learning_rate": 0.00033503932765865745, | |
| "loss": 3.3893, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 4.429017328597568, | |
| "grad_norm": 0.6531360149383545, | |
| "learning_rate": 0.000334716086628596, | |
| "loss": 3.4012, | |
| "step": 41150 | |
| }, | |
| { | |
| "epoch": 4.4343988806371755, | |
| "grad_norm": 0.655354917049408, | |
| "learning_rate": 0.0003343928455985346, | |
| "loss": 3.3705, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 4.439780432676784, | |
| "grad_norm": 0.6870447993278503, | |
| "learning_rate": 0.00033406960456847324, | |
| "loss": 3.3836, | |
| "step": 41250 | |
| }, | |
| { | |
| "epoch": 4.445161984716393, | |
| "grad_norm": 0.6646298170089722, | |
| "learning_rate": 0.0003337463635384118, | |
| "loss": 3.3703, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 4.450543536756, | |
| "grad_norm": 0.7067282795906067, | |
| "learning_rate": 0.00033342312250835037, | |
| "loss": 3.3779, | |
| "step": 41350 | |
| }, | |
| { | |
| "epoch": 4.455925088795609, | |
| "grad_norm": 0.6601843237876892, | |
| "learning_rate": 0.00033309988147828896, | |
| "loss": 3.3896, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 4.461306640835216, | |
| "grad_norm": 0.6824533343315125, | |
| "learning_rate": 0.0003327766404482275, | |
| "loss": 3.3798, | |
| "step": 41450 | |
| }, | |
| { | |
| "epoch": 4.466688192874825, | |
| "grad_norm": 0.6678142547607422, | |
| "learning_rate": 0.0003324533994181661, | |
| "loss": 3.385, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.4720697449144335, | |
| "grad_norm": 0.6664413213729858, | |
| "learning_rate": 0.00033213015838810475, | |
| "loss": 3.4065, | |
| "step": 41550 | |
| }, | |
| { | |
| "epoch": 4.477451296954041, | |
| "grad_norm": 0.6379727721214294, | |
| "learning_rate": 0.0003318069173580433, | |
| "loss": 3.3982, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 4.48283284899365, | |
| "grad_norm": 0.7035315036773682, | |
| "learning_rate": 0.0003314836763279819, | |
| "loss": 3.3971, | |
| "step": 41650 | |
| }, | |
| { | |
| "epoch": 4.488214401033258, | |
| "grad_norm": 0.6721235513687134, | |
| "learning_rate": 0.0003311604352979204, | |
| "loss": 3.3991, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 4.493595953072866, | |
| "grad_norm": 0.6236030459403992, | |
| "learning_rate": 0.000330837194267859, | |
| "loss": 3.3777, | |
| "step": 41750 | |
| }, | |
| { | |
| "epoch": 4.4989775051124745, | |
| "grad_norm": 0.6594476103782654, | |
| "learning_rate": 0.0003305139532377976, | |
| "loss": 3.392, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 4.504359057152083, | |
| "grad_norm": 0.6631010174751282, | |
| "learning_rate": 0.0003301907122077362, | |
| "loss": 3.3953, | |
| "step": 41850 | |
| }, | |
| { | |
| "epoch": 4.509740609191691, | |
| "grad_norm": 0.6775970458984375, | |
| "learning_rate": 0.0003298674711776748, | |
| "loss": 3.3798, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 4.515122161231299, | |
| "grad_norm": 0.6755871772766113, | |
| "learning_rate": 0.0003295442301476134, | |
| "loss": 3.376, | |
| "step": 41950 | |
| }, | |
| { | |
| "epoch": 4.520503713270907, | |
| "grad_norm": 0.660190761089325, | |
| "learning_rate": 0.00032922098911755194, | |
| "loss": 3.3824, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.520503713270907, | |
| "eval_accuracy": 0.37855622259977895, | |
| "eval_loss": 3.42791485786438, | |
| "eval_runtime": 180.7657, | |
| "eval_samples_per_second": 99.637, | |
| "eval_steps_per_second": 6.229, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.5258852653105155, | |
| "grad_norm": 0.6533682942390442, | |
| "learning_rate": 0.00032889774808749053, | |
| "loss": 3.3913, | |
| "step": 42050 | |
| }, | |
| { | |
| "epoch": 4.531266817350124, | |
| "grad_norm": 0.6714156270027161, | |
| "learning_rate": 0.0003285745070574292, | |
| "loss": 3.3873, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 4.536648369389732, | |
| "grad_norm": 0.6406194567680359, | |
| "learning_rate": 0.0003282512660273677, | |
| "loss": 3.3876, | |
| "step": 42150 | |
| }, | |
| { | |
| "epoch": 4.54202992142934, | |
| "grad_norm": 0.672727108001709, | |
| "learning_rate": 0.0003279280249973063, | |
| "loss": 3.3871, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 4.547411473468949, | |
| "grad_norm": 0.6561397314071655, | |
| "learning_rate": 0.00032760478396724486, | |
| "loss": 3.3847, | |
| "step": 42250 | |
| }, | |
| { | |
| "epoch": 4.5527930255085565, | |
| "grad_norm": 0.7014278173446655, | |
| "learning_rate": 0.0003272880077577847, | |
| "loss": 3.4011, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 4.558174577548165, | |
| "grad_norm": 0.6329679489135742, | |
| "learning_rate": 0.00032696476672772326, | |
| "loss": 3.3918, | |
| "step": 42350 | |
| }, | |
| { | |
| "epoch": 4.563556129587774, | |
| "grad_norm": 0.6573483943939209, | |
| "learning_rate": 0.00032664152569766185, | |
| "loss": 3.4036, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 4.568937681627381, | |
| "grad_norm": 0.6461696624755859, | |
| "learning_rate": 0.0003263182846676004, | |
| "loss": 3.3831, | |
| "step": 42450 | |
| }, | |
| { | |
| "epoch": 4.57431923366699, | |
| "grad_norm": 0.6436484456062317, | |
| "learning_rate": 0.00032599504363753904, | |
| "loss": 3.4091, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 4.579700785706597, | |
| "grad_norm": 0.683167040348053, | |
| "learning_rate": 0.00032567180260747764, | |
| "loss": 3.3936, | |
| "step": 42550 | |
| }, | |
| { | |
| "epoch": 4.585082337746206, | |
| "grad_norm": 0.6897136569023132, | |
| "learning_rate": 0.0003253485615774162, | |
| "loss": 3.3839, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 4.5904638897858145, | |
| "grad_norm": 0.7163823246955872, | |
| "learning_rate": 0.00032502532054735477, | |
| "loss": 3.3933, | |
| "step": 42650 | |
| }, | |
| { | |
| "epoch": 4.595845441825422, | |
| "grad_norm": 0.6382591724395752, | |
| "learning_rate": 0.00032470207951729337, | |
| "loss": 3.3879, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 4.601226993865031, | |
| "grad_norm": 0.6253649592399597, | |
| "learning_rate": 0.0003243788384872319, | |
| "loss": 3.3937, | |
| "step": 42750 | |
| }, | |
| { | |
| "epoch": 4.606608545904638, | |
| "grad_norm": 0.6715789437294006, | |
| "learning_rate": 0.00032405559745717056, | |
| "loss": 3.3917, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 4.611990097944247, | |
| "grad_norm": 0.7270500659942627, | |
| "learning_rate": 0.00032373235642710915, | |
| "loss": 3.3983, | |
| "step": 42850 | |
| }, | |
| { | |
| "epoch": 4.6173716499838555, | |
| "grad_norm": 0.6829226613044739, | |
| "learning_rate": 0.0003234091153970477, | |
| "loss": 3.4023, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 4.622753202023463, | |
| "grad_norm": 0.7018654942512512, | |
| "learning_rate": 0.0003230858743669863, | |
| "loss": 3.3912, | |
| "step": 42950 | |
| }, | |
| { | |
| "epoch": 4.628134754063072, | |
| "grad_norm": 0.6380162239074707, | |
| "learning_rate": 0.0003227626333369248, | |
| "loss": 3.3943, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.628134754063072, | |
| "eval_accuracy": 0.37904103178520715, | |
| "eval_loss": 3.421799421310425, | |
| "eval_runtime": 180.2956, | |
| "eval_samples_per_second": 99.897, | |
| "eval_steps_per_second": 6.245, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.63351630610268, | |
| "grad_norm": 0.6637802124023438, | |
| "learning_rate": 0.0003224393923068635, | |
| "loss": 3.3806, | |
| "step": 43050 | |
| }, | |
| { | |
| "epoch": 4.638897858142288, | |
| "grad_norm": 0.6968106031417847, | |
| "learning_rate": 0.00032211615127680207, | |
| "loss": 3.3677, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 4.6442794101818965, | |
| "grad_norm": 0.6918413043022156, | |
| "learning_rate": 0.0003217929102467406, | |
| "loss": 3.3913, | |
| "step": 43150 | |
| }, | |
| { | |
| "epoch": 4.649660962221505, | |
| "grad_norm": 0.637776255607605, | |
| "learning_rate": 0.0003214696692166792, | |
| "loss": 3.3909, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 4.655042514261113, | |
| "grad_norm": 0.666828453540802, | |
| "learning_rate": 0.0003211464281866178, | |
| "loss": 3.3732, | |
| "step": 43250 | |
| }, | |
| { | |
| "epoch": 4.660424066300721, | |
| "grad_norm": 0.6439411640167236, | |
| "learning_rate": 0.00032082318715655634, | |
| "loss": 3.3776, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 4.665805618340329, | |
| "grad_norm": 0.6902055740356445, | |
| "learning_rate": 0.000320499946126495, | |
| "loss": 3.3948, | |
| "step": 43350 | |
| }, | |
| { | |
| "epoch": 4.6711871703799375, | |
| "grad_norm": 0.7745203375816345, | |
| "learning_rate": 0.0003201767050964336, | |
| "loss": 3.3795, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 4.676568722419546, | |
| "grad_norm": 0.671711266040802, | |
| "learning_rate": 0.0003198534640663721, | |
| "loss": 3.3798, | |
| "step": 43450 | |
| }, | |
| { | |
| "epoch": 4.681950274459154, | |
| "grad_norm": 0.6714461445808411, | |
| "learning_rate": 0.00031953668785691193, | |
| "loss": 3.3852, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 4.687331826498762, | |
| "grad_norm": 0.6817046999931335, | |
| "learning_rate": 0.0003192134468268505, | |
| "loss": 3.3894, | |
| "step": 43550 | |
| }, | |
| { | |
| "epoch": 4.692713378538371, | |
| "grad_norm": 0.6941414475440979, | |
| "learning_rate": 0.0003188902057967891, | |
| "loss": 3.4095, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 4.6980949305779784, | |
| "grad_norm": 0.7007185220718384, | |
| "learning_rate": 0.00031856696476672766, | |
| "loss": 3.3747, | |
| "step": 43650 | |
| }, | |
| { | |
| "epoch": 4.703476482617587, | |
| "grad_norm": 0.7390422821044922, | |
| "learning_rate": 0.0003182437237366663, | |
| "loss": 3.3933, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 4.7088580346571955, | |
| "grad_norm": 0.6899697780609131, | |
| "learning_rate": 0.0003179204827066049, | |
| "loss": 3.3846, | |
| "step": 43750 | |
| }, | |
| { | |
| "epoch": 4.714239586696803, | |
| "grad_norm": 0.6393377184867859, | |
| "learning_rate": 0.00031759724167654344, | |
| "loss": 3.3877, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 4.719621138736412, | |
| "grad_norm": 0.6704504489898682, | |
| "learning_rate": 0.00031727400064648204, | |
| "loss": 3.3905, | |
| "step": 43850 | |
| }, | |
| { | |
| "epoch": 4.725002690776019, | |
| "grad_norm": 0.6651193499565125, | |
| "learning_rate": 0.0003169507596164206, | |
| "loss": 3.3773, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 4.730384242815628, | |
| "grad_norm": 0.6523035168647766, | |
| "learning_rate": 0.0003166275185863592, | |
| "loss": 3.4, | |
| "step": 43950 | |
| }, | |
| { | |
| "epoch": 4.7357657948552365, | |
| "grad_norm": 0.6419060230255127, | |
| "learning_rate": 0.0003163042775562978, | |
| "loss": 3.3728, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.7357657948552365, | |
| "eval_accuracy": 0.37933276478898903, | |
| "eval_loss": 3.417551040649414, | |
| "eval_runtime": 180.8101, | |
| "eval_samples_per_second": 99.613, | |
| "eval_steps_per_second": 6.228, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.741147346894844, | |
| "grad_norm": 0.6831957697868347, | |
| "learning_rate": 0.00031598103652623636, | |
| "loss": 3.3938, | |
| "step": 44050 | |
| }, | |
| { | |
| "epoch": 4.746528898934453, | |
| "grad_norm": 0.6325632929801941, | |
| "learning_rate": 0.00031565779549617496, | |
| "loss": 3.4015, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 4.751910450974061, | |
| "grad_norm": 0.687362790107727, | |
| "learning_rate": 0.00031533455446611355, | |
| "loss": 3.3946, | |
| "step": 44150 | |
| }, | |
| { | |
| "epoch": 4.757292003013669, | |
| "grad_norm": 0.6923133134841919, | |
| "learning_rate": 0.0003150113134360521, | |
| "loss": 3.3823, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 4.7626735550532775, | |
| "grad_norm": 0.709951639175415, | |
| "learning_rate": 0.0003146880724059907, | |
| "loss": 3.3947, | |
| "step": 44250 | |
| }, | |
| { | |
| "epoch": 4.768055107092886, | |
| "grad_norm": 0.6787405610084534, | |
| "learning_rate": 0.00031436483137592934, | |
| "loss": 3.3734, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 4.773436659132494, | |
| "grad_norm": 0.7011154890060425, | |
| "learning_rate": 0.0003140415903458679, | |
| "loss": 3.3932, | |
| "step": 44350 | |
| }, | |
| { | |
| "epoch": 4.778818211172102, | |
| "grad_norm": 0.7104355096817017, | |
| "learning_rate": 0.00031371834931580647, | |
| "loss": 3.3876, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 4.78419976321171, | |
| "grad_norm": 0.65087890625, | |
| "learning_rate": 0.000313395108285745, | |
| "loss": 3.3826, | |
| "step": 44450 | |
| }, | |
| { | |
| "epoch": 4.7895813152513185, | |
| "grad_norm": 0.7193938493728638, | |
| "learning_rate": 0.0003130718672556836, | |
| "loss": 3.3899, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 4.794962867290927, | |
| "grad_norm": 0.6938375234603882, | |
| "learning_rate": 0.0003127486262256222, | |
| "loss": 3.367, | |
| "step": 44550 | |
| }, | |
| { | |
| "epoch": 4.800344419330535, | |
| "grad_norm": 0.6607935428619385, | |
| "learning_rate": 0.0003124253851955608, | |
| "loss": 3.3828, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 4.805725971370143, | |
| "grad_norm": 0.7184892296791077, | |
| "learning_rate": 0.0003121021441654994, | |
| "loss": 3.4025, | |
| "step": 44650 | |
| }, | |
| { | |
| "epoch": 4.811107523409751, | |
| "grad_norm": 0.6583475470542908, | |
| "learning_rate": 0.000311778903135438, | |
| "loss": 3.4065, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 4.8164890754493594, | |
| "grad_norm": 0.746714174747467, | |
| "learning_rate": 0.0003114556621053765, | |
| "loss": 3.4003, | |
| "step": 44750 | |
| }, | |
| { | |
| "epoch": 4.821870627488968, | |
| "grad_norm": 0.667801558971405, | |
| "learning_rate": 0.0003111324210753151, | |
| "loss": 3.3777, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 4.827252179528576, | |
| "grad_norm": 0.6681658029556274, | |
| "learning_rate": 0.00031080918004525377, | |
| "loss": 3.3846, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 4.832633731568184, | |
| "grad_norm": 0.6859903931617737, | |
| "learning_rate": 0.0003104859390151923, | |
| "loss": 3.3843, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 4.838015283607793, | |
| "grad_norm": 0.6311453580856323, | |
| "learning_rate": 0.0003101626979851309, | |
| "loss": 3.3754, | |
| "step": 44950 | |
| }, | |
| { | |
| "epoch": 4.8433968356474, | |
| "grad_norm": 0.6764549016952515, | |
| "learning_rate": 0.00030983945695506945, | |
| "loss": 3.3897, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.8433968356474, | |
| "eval_accuracy": 0.3799441545887211, | |
| "eval_loss": 3.4145073890686035, | |
| "eval_runtime": 180.8088, | |
| "eval_samples_per_second": 99.614, | |
| "eval_steps_per_second": 6.228, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.848778387687009, | |
| "grad_norm": 0.7071652412414551, | |
| "learning_rate": 0.00030951621592500804, | |
| "loss": 3.3874, | |
| "step": 45050 | |
| }, | |
| { | |
| "epoch": 4.8541599397266175, | |
| "grad_norm": 0.6975886821746826, | |
| "learning_rate": 0.00030919297489494663, | |
| "loss": 3.381, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 4.859541491766225, | |
| "grad_norm": 0.6888333559036255, | |
| "learning_rate": 0.00030886973386488523, | |
| "loss": 3.3775, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 4.864923043805834, | |
| "grad_norm": 0.6672408580780029, | |
| "learning_rate": 0.0003085464928348238, | |
| "loss": 3.4037, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 4.870304595845441, | |
| "grad_norm": 0.710537850856781, | |
| "learning_rate": 0.0003082232518047624, | |
| "loss": 3.391, | |
| "step": 45250 | |
| }, | |
| { | |
| "epoch": 4.87568614788505, | |
| "grad_norm": 0.6636947393417358, | |
| "learning_rate": 0.00030790001077470096, | |
| "loss": 3.3911, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 4.8810676999246585, | |
| "grad_norm": 0.6961594223976135, | |
| "learning_rate": 0.00030757676974463955, | |
| "loss": 3.3829, | |
| "step": 45350 | |
| }, | |
| { | |
| "epoch": 4.886449251964266, | |
| "grad_norm": 0.8008875846862793, | |
| "learning_rate": 0.0003072535287145781, | |
| "loss": 3.3904, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 4.891830804003875, | |
| "grad_norm": 0.6139016151428223, | |
| "learning_rate": 0.00030693028768451674, | |
| "loss": 3.3811, | |
| "step": 45450 | |
| }, | |
| { | |
| "epoch": 4.897212356043483, | |
| "grad_norm": 0.6992993354797363, | |
| "learning_rate": 0.00030660704665445534, | |
| "loss": 3.3865, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 4.902593908083091, | |
| "grad_norm": 0.6530194282531738, | |
| "learning_rate": 0.0003062838056243939, | |
| "loss": 3.3902, | |
| "step": 45550 | |
| }, | |
| { | |
| "epoch": 4.9079754601226995, | |
| "grad_norm": 0.6725596189498901, | |
| "learning_rate": 0.00030596056459433247, | |
| "loss": 3.3907, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 4.913357012162308, | |
| "grad_norm": 0.670534610748291, | |
| "learning_rate": 0.00030563732356427107, | |
| "loss": 3.3845, | |
| "step": 45650 | |
| }, | |
| { | |
| "epoch": 4.918738564201916, | |
| "grad_norm": 0.6930390000343323, | |
| "learning_rate": 0.00030531408253420966, | |
| "loss": 3.3919, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 4.924120116241524, | |
| "grad_norm": 0.7007985711097717, | |
| "learning_rate": 0.00030499084150414826, | |
| "loss": 3.375, | |
| "step": 45750 | |
| }, | |
| { | |
| "epoch": 4.929501668281132, | |
| "grad_norm": 0.6509608030319214, | |
| "learning_rate": 0.00030466760047408685, | |
| "loss": 3.3936, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 4.9348832203207404, | |
| "grad_norm": 0.7178775668144226, | |
| "learning_rate": 0.0003043443594440254, | |
| "loss": 3.3867, | |
| "step": 45850 | |
| }, | |
| { | |
| "epoch": 4.940264772360349, | |
| "grad_norm": 0.7314358949661255, | |
| "learning_rate": 0.000304021118413964, | |
| "loss": 3.3853, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 4.945646324399957, | |
| "grad_norm": 0.7417964339256287, | |
| "learning_rate": 0.0003036978773839025, | |
| "loss": 3.3955, | |
| "step": 45950 | |
| }, | |
| { | |
| "epoch": 4.951027876439565, | |
| "grad_norm": 0.6962642669677734, | |
| "learning_rate": 0.0003033746363538412, | |
| "loss": 3.3879, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.951027876439565, | |
| "eval_accuracy": 0.3806199755509272, | |
| "eval_loss": 3.4076614379882812, | |
| "eval_runtime": 180.463, | |
| "eval_samples_per_second": 99.804, | |
| "eval_steps_per_second": 6.24, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.956409428479174, | |
| "grad_norm": 0.6814647912979126, | |
| "learning_rate": 0.00030305139532377977, | |
| "loss": 3.3941, | |
| "step": 46050 | |
| }, | |
| { | |
| "epoch": 4.961790980518781, | |
| "grad_norm": 0.6750015020370483, | |
| "learning_rate": 0.0003027281542937183, | |
| "loss": 3.3918, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 4.96717253255839, | |
| "grad_norm": 0.6892281174659729, | |
| "learning_rate": 0.0003024049132636569, | |
| "loss": 3.3945, | |
| "step": 46150 | |
| }, | |
| { | |
| "epoch": 4.9725540845979985, | |
| "grad_norm": 0.6996626257896423, | |
| "learning_rate": 0.0003020816722335955, | |
| "loss": 3.3739, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 4.977935636637606, | |
| "grad_norm": 0.6532090902328491, | |
| "learning_rate": 0.00030175843120353404, | |
| "loss": 3.4021, | |
| "step": 46250 | |
| }, | |
| { | |
| "epoch": 4.983317188677215, | |
| "grad_norm": 0.6986241936683655, | |
| "learning_rate": 0.0003014351901734727, | |
| "loss": 3.3769, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 4.988698740716822, | |
| "grad_norm": 0.6778721213340759, | |
| "learning_rate": 0.0003011119491434113, | |
| "loss": 3.3806, | |
| "step": 46350 | |
| }, | |
| { | |
| "epoch": 4.994080292756431, | |
| "grad_norm": 0.7227446436882019, | |
| "learning_rate": 0.0003007887081133498, | |
| "loss": 3.386, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 4.9994618447960395, | |
| "grad_norm": 0.6771180629730225, | |
| "learning_rate": 0.0003004654670832884, | |
| "loss": 3.3777, | |
| "step": 46450 | |
| }, | |
| { | |
| "epoch": 5.004843396835647, | |
| "grad_norm": 0.6935259699821472, | |
| "learning_rate": 0.00030014222605322696, | |
| "loss": 3.3098, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 5.010224948875256, | |
| "grad_norm": 0.7119801640510559, | |
| "learning_rate": 0.00029981898502316555, | |
| "loss": 3.3013, | |
| "step": 46550 | |
| }, | |
| { | |
| "epoch": 5.015606500914864, | |
| "grad_norm": 0.7470939755439758, | |
| "learning_rate": 0.00029949574399310415, | |
| "loss": 3.2987, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 5.020988052954472, | |
| "grad_norm": 0.7172041535377502, | |
| "learning_rate": 0.00029917250296304274, | |
| "loss": 3.2962, | |
| "step": 46650 | |
| }, | |
| { | |
| "epoch": 5.0263696049940805, | |
| "grad_norm": 0.708893895149231, | |
| "learning_rate": 0.00029884926193298134, | |
| "loss": 3.2944, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 5.031751157033688, | |
| "grad_norm": 0.6856112480163574, | |
| "learning_rate": 0.0002985260209029199, | |
| "loss": 3.2975, | |
| "step": 46750 | |
| }, | |
| { | |
| "epoch": 5.037132709073297, | |
| "grad_norm": 0.6789200305938721, | |
| "learning_rate": 0.00029820277987285853, | |
| "loss": 3.2961, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 5.042514261112905, | |
| "grad_norm": 0.6745328307151794, | |
| "learning_rate": 0.00029787953884279707, | |
| "loss": 3.294, | |
| "step": 46850 | |
| }, | |
| { | |
| "epoch": 5.047895813152513, | |
| "grad_norm": 0.695334792137146, | |
| "learning_rate": 0.00029756276263333693, | |
| "loss": 3.3119, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 5.0532773651921215, | |
| "grad_norm": 0.6939895153045654, | |
| "learning_rate": 0.00029723952160327547, | |
| "loss": 3.2977, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 5.05865891723173, | |
| "grad_norm": 0.7092863917350769, | |
| "learning_rate": 0.00029691628057321406, | |
| "loss": 3.3093, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 5.05865891723173, | |
| "eval_accuracy": 0.3807579647184516, | |
| "eval_loss": 3.4131321907043457, | |
| "eval_runtime": 180.5823, | |
| "eval_samples_per_second": 99.738, | |
| "eval_steps_per_second": 6.235, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 5.064040469271338, | |
| "grad_norm": 0.7017537355422974, | |
| "learning_rate": 0.00029659303954315266, | |
| "loss": 3.3113, | |
| "step": 47050 | |
| }, | |
| { | |
| "epoch": 5.069422021310946, | |
| "grad_norm": 0.7066820859909058, | |
| "learning_rate": 0.00029626979851309125, | |
| "loss": 3.3025, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 5.074803573350554, | |
| "grad_norm": 0.7007570862770081, | |
| "learning_rate": 0.00029594655748302985, | |
| "loss": 3.3077, | |
| "step": 47150 | |
| }, | |
| { | |
| "epoch": 5.080185125390162, | |
| "grad_norm": 0.7130218744277954, | |
| "learning_rate": 0.0002956233164529684, | |
| "loss": 3.2919, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 5.085566677429771, | |
| "grad_norm": 0.7107332944869995, | |
| "learning_rate": 0.000295300075422907, | |
| "loss": 3.3093, | |
| "step": 47250 | |
| }, | |
| { | |
| "epoch": 5.090948229469379, | |
| "grad_norm": 0.6778996586799622, | |
| "learning_rate": 0.0002949768343928456, | |
| "loss": 3.3089, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 5.096329781508987, | |
| "grad_norm": 0.7302454113960266, | |
| "learning_rate": 0.00029465359336278417, | |
| "loss": 3.321, | |
| "step": 47350 | |
| }, | |
| { | |
| "epoch": 5.101711333548596, | |
| "grad_norm": 0.7293109893798828, | |
| "learning_rate": 0.0002943303523327227, | |
| "loss": 3.3307, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 5.107092885588203, | |
| "grad_norm": 0.7125155329704285, | |
| "learning_rate": 0.00029400711130266136, | |
| "loss": 3.3088, | |
| "step": 47450 | |
| }, | |
| { | |
| "epoch": 5.112474437627812, | |
| "grad_norm": 0.7028940916061401, | |
| "learning_rate": 0.0002936838702725999, | |
| "loss": 3.3038, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 5.1178559896674205, | |
| "grad_norm": 0.6821138858795166, | |
| "learning_rate": 0.0002933606292425385, | |
| "loss": 3.3197, | |
| "step": 47550 | |
| }, | |
| { | |
| "epoch": 5.123237541707028, | |
| "grad_norm": 0.6831609010696411, | |
| "learning_rate": 0.0002930373882124771, | |
| "loss": 3.3003, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 5.128619093746637, | |
| "grad_norm": 0.6890237331390381, | |
| "learning_rate": 0.0002927141471824157, | |
| "loss": 3.3091, | |
| "step": 47650 | |
| }, | |
| { | |
| "epoch": 5.134000645786244, | |
| "grad_norm": 0.7032915949821472, | |
| "learning_rate": 0.0002923909061523542, | |
| "loss": 3.3137, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 5.139382197825853, | |
| "grad_norm": 0.6753126382827759, | |
| "learning_rate": 0.0002920676651222928, | |
| "loss": 3.3034, | |
| "step": 47750 | |
| }, | |
| { | |
| "epoch": 5.1447637498654615, | |
| "grad_norm": 0.7659389972686768, | |
| "learning_rate": 0.0002917444240922314, | |
| "loss": 3.3154, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 5.150145301905069, | |
| "grad_norm": 0.688945472240448, | |
| "learning_rate": 0.00029142118306216996, | |
| "loss": 3.3108, | |
| "step": 47850 | |
| }, | |
| { | |
| "epoch": 5.155526853944678, | |
| "grad_norm": 0.6884469389915466, | |
| "learning_rate": 0.0002910979420321086, | |
| "loss": 3.3065, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 5.160908405984286, | |
| "grad_norm": 0.6957643032073975, | |
| "learning_rate": 0.00029077470100204715, | |
| "loss": 3.31, | |
| "step": 47950 | |
| }, | |
| { | |
| "epoch": 5.166289958023894, | |
| "grad_norm": 0.7388163805007935, | |
| "learning_rate": 0.00029045145997198574, | |
| "loss": 3.2902, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.166289958023894, | |
| "eval_accuracy": 0.3809007346130398, | |
| "eval_loss": 3.4100382328033447, | |
| "eval_runtime": 180.4717, | |
| "eval_samples_per_second": 99.8, | |
| "eval_steps_per_second": 6.239, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.1716715100635025, | |
| "grad_norm": 0.7176282405853271, | |
| "learning_rate": 0.00029012821894192433, | |
| "loss": 3.315, | |
| "step": 48050 | |
| }, | |
| { | |
| "epoch": 5.17705306210311, | |
| "grad_norm": 0.6990656852722168, | |
| "learning_rate": 0.00028980497791186293, | |
| "loss": 3.3085, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 5.182434614142719, | |
| "grad_norm": 0.7440829277038574, | |
| "learning_rate": 0.0002894817368818015, | |
| "loss": 3.3026, | |
| "step": 48150 | |
| }, | |
| { | |
| "epoch": 5.187816166182327, | |
| "grad_norm": 0.7810512781143188, | |
| "learning_rate": 0.00028915849585174006, | |
| "loss": 3.3067, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 5.193197718221935, | |
| "grad_norm": 0.7514436841011047, | |
| "learning_rate": 0.00028883525482167866, | |
| "loss": 3.3155, | |
| "step": 48250 | |
| }, | |
| { | |
| "epoch": 5.198579270261543, | |
| "grad_norm": 0.7587404251098633, | |
| "learning_rate": 0.00028851201379161725, | |
| "loss": 3.326, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 5.203960822301152, | |
| "grad_norm": 0.728809654712677, | |
| "learning_rate": 0.00028818877276155585, | |
| "loss": 3.3046, | |
| "step": 48350 | |
| }, | |
| { | |
| "epoch": 5.20934237434076, | |
| "grad_norm": 0.6925315260887146, | |
| "learning_rate": 0.0002878655317314944, | |
| "loss": 3.3156, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 5.214723926380368, | |
| "grad_norm": 0.761146605014801, | |
| "learning_rate": 0.00028754229070143304, | |
| "loss": 3.3213, | |
| "step": 48450 | |
| }, | |
| { | |
| "epoch": 5.220105478419977, | |
| "grad_norm": 0.7084577679634094, | |
| "learning_rate": 0.0002872190496713716, | |
| "loss": 3.3169, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 5.225487030459584, | |
| "grad_norm": 0.6968151926994324, | |
| "learning_rate": 0.0002868958086413102, | |
| "loss": 3.307, | |
| "step": 48550 | |
| }, | |
| { | |
| "epoch": 5.230868582499193, | |
| "grad_norm": 0.6933405995368958, | |
| "learning_rate": 0.00028657256761124877, | |
| "loss": 3.3176, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 5.236250134538801, | |
| "grad_norm": 0.7592040300369263, | |
| "learning_rate": 0.00028624932658118736, | |
| "loss": 3.3159, | |
| "step": 48650 | |
| }, | |
| { | |
| "epoch": 5.241631686578409, | |
| "grad_norm": 0.6854032874107361, | |
| "learning_rate": 0.0002859260855511259, | |
| "loss": 3.3186, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 5.247013238618018, | |
| "grad_norm": 0.7083324193954468, | |
| "learning_rate": 0.0002856028445210645, | |
| "loss": 3.316, | |
| "step": 48750 | |
| }, | |
| { | |
| "epoch": 5.252394790657625, | |
| "grad_norm": 0.7232556939125061, | |
| "learning_rate": 0.0002852796034910031, | |
| "loss": 3.3182, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 5.257776342697234, | |
| "grad_norm": 0.6980643272399902, | |
| "learning_rate": 0.0002849563624609417, | |
| "loss": 3.318, | |
| "step": 48850 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "grad_norm": 0.6944864988327026, | |
| "learning_rate": 0.0002846331214308803, | |
| "loss": 3.3329, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 5.26853944677645, | |
| "grad_norm": 0.749697744846344, | |
| "learning_rate": 0.0002843098804008188, | |
| "loss": 3.34, | |
| "step": 48950 | |
| }, | |
| { | |
| "epoch": 5.273920998816059, | |
| "grad_norm": 0.706950843334198, | |
| "learning_rate": 0.00028398663937075747, | |
| "loss": 3.3097, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.273920998816059, | |
| "eval_accuracy": 0.3812864523647812, | |
| "eval_loss": 3.405521869659424, | |
| "eval_runtime": 181.1668, | |
| "eval_samples_per_second": 99.417, | |
| "eval_steps_per_second": 6.215, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.279302550855666, | |
| "grad_norm": 0.7286232709884644, | |
| "learning_rate": 0.000283663398340696, | |
| "loss": 3.3282, | |
| "step": 49050 | |
| }, | |
| { | |
| "epoch": 5.284684102895275, | |
| "grad_norm": 0.7539182305335999, | |
| "learning_rate": 0.0002833401573106346, | |
| "loss": 3.3236, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 5.2900656549348835, | |
| "grad_norm": 0.6944497227668762, | |
| "learning_rate": 0.0002830169162805732, | |
| "loss": 3.333, | |
| "step": 49150 | |
| }, | |
| { | |
| "epoch": 5.295447206974491, | |
| "grad_norm": 0.684943675994873, | |
| "learning_rate": 0.0002826936752505118, | |
| "loss": 3.3295, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 5.3008287590141, | |
| "grad_norm": 0.762440025806427, | |
| "learning_rate": 0.00028237043422045034, | |
| "loss": 3.3233, | |
| "step": 49250 | |
| }, | |
| { | |
| "epoch": 5.306210311053708, | |
| "grad_norm": 0.7036476135253906, | |
| "learning_rate": 0.00028205365801099014, | |
| "loss": 3.3298, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 5.311591863093316, | |
| "grad_norm": 0.7563344836235046, | |
| "learning_rate": 0.00028173041698092874, | |
| "loss": 3.3374, | |
| "step": 49350 | |
| }, | |
| { | |
| "epoch": 5.316973415132924, | |
| "grad_norm": 0.7168316841125488, | |
| "learning_rate": 0.00028140717595086733, | |
| "loss": 3.3358, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 5.322354967172533, | |
| "grad_norm": 0.7628238201141357, | |
| "learning_rate": 0.0002810839349208059, | |
| "loss": 3.3199, | |
| "step": 49450 | |
| }, | |
| { | |
| "epoch": 5.327736519212141, | |
| "grad_norm": 0.7322455644607544, | |
| "learning_rate": 0.00028076069389074447, | |
| "loss": 3.327, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 5.333118071251749, | |
| "grad_norm": 0.6967852115631104, | |
| "learning_rate": 0.0002804374528606831, | |
| "loss": 3.3419, | |
| "step": 49550 | |
| }, | |
| { | |
| "epoch": 5.338499623291357, | |
| "grad_norm": 0.7441530227661133, | |
| "learning_rate": 0.00028011421183062166, | |
| "loss": 3.3185, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 5.343881175330965, | |
| "grad_norm": 0.7443904280662537, | |
| "learning_rate": 0.00027979097080056025, | |
| "loss": 3.3199, | |
| "step": 49650 | |
| }, | |
| { | |
| "epoch": 5.349262727370574, | |
| "grad_norm": 0.7386976480484009, | |
| "learning_rate": 0.00027946772977049885, | |
| "loss": 3.318, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 5.354644279410182, | |
| "grad_norm": 0.7359290719032288, | |
| "learning_rate": 0.00027914448874043744, | |
| "loss": 3.3406, | |
| "step": 49750 | |
| }, | |
| { | |
| "epoch": 5.36002583144979, | |
| "grad_norm": 0.730819046497345, | |
| "learning_rate": 0.00027882124771037603, | |
| "loss": 3.3092, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 5.365407383489399, | |
| "grad_norm": 0.7585179209709167, | |
| "learning_rate": 0.0002784980066803146, | |
| "loss": 3.326, | |
| "step": 49850 | |
| }, | |
| { | |
| "epoch": 5.370788935529006, | |
| "grad_norm": 0.7162631750106812, | |
| "learning_rate": 0.00027817476565025317, | |
| "loss": 3.3382, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 5.376170487568615, | |
| "grad_norm": 0.7122279405593872, | |
| "learning_rate": 0.00027785152462019176, | |
| "loss": 3.3342, | |
| "step": 49950 | |
| }, | |
| { | |
| "epoch": 5.3815520396082235, | |
| "grad_norm": 0.7170236706733704, | |
| "learning_rate": 0.00027752828359013036, | |
| "loss": 3.3242, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.3815520396082235, | |
| "eval_accuracy": 0.38197922317748634, | |
| "eval_loss": 3.400938034057617, | |
| "eval_runtime": 180.5748, | |
| "eval_samples_per_second": 99.743, | |
| "eval_steps_per_second": 6.236, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.386933591647831, | |
| "grad_norm": 0.6691011786460876, | |
| "learning_rate": 0.0002772050425600689, | |
| "loss": 3.3201, | |
| "step": 50050 | |
| }, | |
| { | |
| "epoch": 5.39231514368744, | |
| "grad_norm": 0.7036200761795044, | |
| "learning_rate": 0.00027688180153000755, | |
| "loss": 3.3223, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 5.397696695727047, | |
| "grad_norm": 0.6968643069267273, | |
| "learning_rate": 0.0002765585604999461, | |
| "loss": 3.34, | |
| "step": 50150 | |
| }, | |
| { | |
| "epoch": 5.403078247766656, | |
| "grad_norm": 0.7583166360855103, | |
| "learning_rate": 0.0002762353194698847, | |
| "loss": 3.3211, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 5.4084597998062645, | |
| "grad_norm": 0.7078987956047058, | |
| "learning_rate": 0.0002759120784398233, | |
| "loss": 3.3302, | |
| "step": 50250 | |
| }, | |
| { | |
| "epoch": 5.413841351845872, | |
| "grad_norm": 0.764525294303894, | |
| "learning_rate": 0.00027558883740976187, | |
| "loss": 3.344, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 5.419222903885481, | |
| "grad_norm": 0.7484478950500488, | |
| "learning_rate": 0.0002752655963797004, | |
| "loss": 3.3345, | |
| "step": 50350 | |
| }, | |
| { | |
| "epoch": 5.424604455925088, | |
| "grad_norm": 0.7260310053825378, | |
| "learning_rate": 0.000274942355349639, | |
| "loss": 3.3208, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 5.429986007964697, | |
| "grad_norm": 0.6879717707633972, | |
| "learning_rate": 0.0002746191143195776, | |
| "loss": 3.3432, | |
| "step": 50450 | |
| }, | |
| { | |
| "epoch": 5.435367560004305, | |
| "grad_norm": 0.7341870665550232, | |
| "learning_rate": 0.0002742958732895162, | |
| "loss": 3.3261, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 5.440749112043913, | |
| "grad_norm": 0.70168536901474, | |
| "learning_rate": 0.0002739726322594548, | |
| "loss": 3.3284, | |
| "step": 50550 | |
| }, | |
| { | |
| "epoch": 5.446130664083522, | |
| "grad_norm": 0.745499312877655, | |
| "learning_rate": 0.00027364939122939333, | |
| "loss": 3.3374, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 5.45151221612313, | |
| "grad_norm": 0.7081572413444519, | |
| "learning_rate": 0.0002733261501993319, | |
| "loss": 3.3199, | |
| "step": 50650 | |
| }, | |
| { | |
| "epoch": 5.456893768162738, | |
| "grad_norm": 0.7260119915008545, | |
| "learning_rate": 0.0002730029091692705, | |
| "loss": 3.3515, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 5.462275320202346, | |
| "grad_norm": 0.7278617024421692, | |
| "learning_rate": 0.0002726796681392091, | |
| "loss": 3.331, | |
| "step": 50750 | |
| }, | |
| { | |
| "epoch": 5.467656872241955, | |
| "grad_norm": 0.7048456072807312, | |
| "learning_rate": 0.0002723564271091477, | |
| "loss": 3.3106, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 5.473038424281563, | |
| "grad_norm": 0.7255328893661499, | |
| "learning_rate": 0.0002720331860790863, | |
| "loss": 3.3247, | |
| "step": 50850 | |
| }, | |
| { | |
| "epoch": 5.478419976321171, | |
| "grad_norm": 0.7401384115219116, | |
| "learning_rate": 0.00027170994504902485, | |
| "loss": 3.3402, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 5.483801528360779, | |
| "grad_norm": 0.786148190498352, | |
| "learning_rate": 0.00027138670401896344, | |
| "loss": 3.3437, | |
| "step": 50950 | |
| }, | |
| { | |
| "epoch": 5.489183080400387, | |
| "grad_norm": 0.7473777532577515, | |
| "learning_rate": 0.00027106346298890204, | |
| "loss": 3.3597, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.489183080400387, | |
| "eval_accuracy": 0.38263559527277363, | |
| "eval_loss": 3.3964664936065674, | |
| "eval_runtime": 180.3564, | |
| "eval_samples_per_second": 99.863, | |
| "eval_steps_per_second": 6.243, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.494564632439996, | |
| "grad_norm": 0.7068842649459839, | |
| "learning_rate": 0.00027074022195884063, | |
| "loss": 3.3147, | |
| "step": 51050 | |
| }, | |
| { | |
| "epoch": 5.499946184479604, | |
| "grad_norm": 0.7448179125785828, | |
| "learning_rate": 0.0002704169809287792, | |
| "loss": 3.3439, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 5.505327736519212, | |
| "grad_norm": 0.7172561287879944, | |
| "learning_rate": 0.00027009373989871776, | |
| "loss": 3.3419, | |
| "step": 51150 | |
| }, | |
| { | |
| "epoch": 5.510709288558821, | |
| "grad_norm": 0.7486968040466309, | |
| "learning_rate": 0.00026977049886865636, | |
| "loss": 3.3319, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 5.516090840598428, | |
| "grad_norm": 0.7076429128646851, | |
| "learning_rate": 0.00026944725783859495, | |
| "loss": 3.3312, | |
| "step": 51250 | |
| }, | |
| { | |
| "epoch": 5.521472392638037, | |
| "grad_norm": 0.7071561813354492, | |
| "learning_rate": 0.00026912401680853355, | |
| "loss": 3.3152, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 5.5268539446776455, | |
| "grad_norm": 0.7227540612220764, | |
| "learning_rate": 0.0002688007757784721, | |
| "loss": 3.3266, | |
| "step": 51350 | |
| }, | |
| { | |
| "epoch": 5.532235496717253, | |
| "grad_norm": 0.7778589129447937, | |
| "learning_rate": 0.00026847753474841074, | |
| "loss": 3.345, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 5.537617048756862, | |
| "grad_norm": 0.7239121794700623, | |
| "learning_rate": 0.0002681542937183493, | |
| "loss": 3.3364, | |
| "step": 51450 | |
| }, | |
| { | |
| "epoch": 5.542998600796469, | |
| "grad_norm": 0.7021813988685608, | |
| "learning_rate": 0.0002678310526882879, | |
| "loss": 3.3266, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 5.548380152836078, | |
| "grad_norm": 0.7057538628578186, | |
| "learning_rate": 0.00026750781165822647, | |
| "loss": 3.315, | |
| "step": 51550 | |
| }, | |
| { | |
| "epoch": 5.553761704875686, | |
| "grad_norm": 0.7174096703529358, | |
| "learning_rate": 0.00026718457062816506, | |
| "loss": 3.3249, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 5.559143256915294, | |
| "grad_norm": 0.7189500331878662, | |
| "learning_rate": 0.00026686132959810366, | |
| "loss": 3.3414, | |
| "step": 51650 | |
| }, | |
| { | |
| "epoch": 5.564524808954903, | |
| "grad_norm": 0.7119573354721069, | |
| "learning_rate": 0.0002665380885680422, | |
| "loss": 3.3625, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 5.569906360994511, | |
| "grad_norm": 0.7115148901939392, | |
| "learning_rate": 0.0002662148475379808, | |
| "loss": 3.3203, | |
| "step": 51750 | |
| }, | |
| { | |
| "epoch": 5.575287913034119, | |
| "grad_norm": 0.7708024382591248, | |
| "learning_rate": 0.0002658916065079194, | |
| "loss": 3.3362, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 5.580669465073727, | |
| "grad_norm": 0.7303184866905212, | |
| "learning_rate": 0.000265568365477858, | |
| "loss": 3.334, | |
| "step": 51850 | |
| }, | |
| { | |
| "epoch": 5.586051017113336, | |
| "grad_norm": 0.7622580528259277, | |
| "learning_rate": 0.0002652451244477965, | |
| "loss": 3.32, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 5.591432569152944, | |
| "grad_norm": 0.7121456265449524, | |
| "learning_rate": 0.00026492188341773517, | |
| "loss": 3.316, | |
| "step": 51950 | |
| }, | |
| { | |
| "epoch": 5.596814121192552, | |
| "grad_norm": 0.7205502390861511, | |
| "learning_rate": 0.0002645986423876737, | |
| "loss": 3.3013, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.596814121192552, | |
| "eval_accuracy": 0.38279140351389956, | |
| "eval_loss": 3.3938612937927246, | |
| "eval_runtime": 180.5356, | |
| "eval_samples_per_second": 99.764, | |
| "eval_steps_per_second": 6.237, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.60219567323216, | |
| "grad_norm": 0.7592937350273132, | |
| "learning_rate": 0.0002642754013576123, | |
| "loss": 3.3312, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 5.607577225271768, | |
| "grad_norm": 0.7347540855407715, | |
| "learning_rate": 0.0002639521603275509, | |
| "loss": 3.3274, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 5.612958777311377, | |
| "grad_norm": 0.717491626739502, | |
| "learning_rate": 0.0002636289192974895, | |
| "loss": 3.3496, | |
| "step": 52150 | |
| }, | |
| { | |
| "epoch": 5.618340329350985, | |
| "grad_norm": 0.7288353443145752, | |
| "learning_rate": 0.00026330567826742804, | |
| "loss": 3.3103, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 5.623721881390593, | |
| "grad_norm": 0.6995804309844971, | |
| "learning_rate": 0.00026298243723736663, | |
| "loss": 3.3326, | |
| "step": 52250 | |
| }, | |
| { | |
| "epoch": 5.629103433430201, | |
| "grad_norm": 0.7089316844940186, | |
| "learning_rate": 0.0002626591962073052, | |
| "loss": 3.3313, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 5.634484985469809, | |
| "grad_norm": 0.7350379824638367, | |
| "learning_rate": 0.0002623359551772438, | |
| "loss": 3.3358, | |
| "step": 52350 | |
| }, | |
| { | |
| "epoch": 5.639866537509418, | |
| "grad_norm": 0.7242736220359802, | |
| "learning_rate": 0.0002620127141471824, | |
| "loss": 3.3154, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 5.645248089549026, | |
| "grad_norm": 0.7510601282119751, | |
| "learning_rate": 0.00026168947311712095, | |
| "loss": 3.3391, | |
| "step": 52450 | |
| }, | |
| { | |
| "epoch": 5.650629641588634, | |
| "grad_norm": 0.7219720482826233, | |
| "learning_rate": 0.00026136623208705955, | |
| "loss": 3.3203, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 5.656011193628243, | |
| "grad_norm": 0.7292102575302124, | |
| "learning_rate": 0.00026104299105699814, | |
| "loss": 3.3382, | |
| "step": 52550 | |
| }, | |
| { | |
| "epoch": 5.66139274566785, | |
| "grad_norm": 0.7652955651283264, | |
| "learning_rate": 0.00026071975002693674, | |
| "loss": 3.3266, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 5.666774297707459, | |
| "grad_norm": 0.7515937685966492, | |
| "learning_rate": 0.00026039650899687533, | |
| "loss": 3.3376, | |
| "step": 52650 | |
| }, | |
| { | |
| "epoch": 5.672155849747067, | |
| "grad_norm": 0.7084229588508606, | |
| "learning_rate": 0.00026007326796681393, | |
| "loss": 3.3164, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 5.677537401786675, | |
| "grad_norm": 0.717211127281189, | |
| "learning_rate": 0.00025975002693675247, | |
| "loss": 3.3411, | |
| "step": 52750 | |
| }, | |
| { | |
| "epoch": 5.682918953826284, | |
| "grad_norm": 0.7143423557281494, | |
| "learning_rate": 0.00025942678590669106, | |
| "loss": 3.3249, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 5.688300505865891, | |
| "grad_norm": 0.7390002012252808, | |
| "learning_rate": 0.00025910354487662966, | |
| "loss": 3.3317, | |
| "step": 52850 | |
| }, | |
| { | |
| "epoch": 5.6936820579055, | |
| "grad_norm": 0.7596791386604309, | |
| "learning_rate": 0.00025878676866716946, | |
| "loss": 3.3377, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 5.699063609945108, | |
| "grad_norm": 0.7708361744880676, | |
| "learning_rate": 0.00025846352763710806, | |
| "loss": 3.3309, | |
| "step": 52950 | |
| }, | |
| { | |
| "epoch": 5.704445161984716, | |
| "grad_norm": 0.7448739409446716, | |
| "learning_rate": 0.0002581402866070466, | |
| "loss": 3.3461, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.704445161984716, | |
| "eval_accuracy": 0.382959815490012, | |
| "eval_loss": 3.3894808292388916, | |
| "eval_runtime": 180.4953, | |
| "eval_samples_per_second": 99.787, | |
| "eval_steps_per_second": 6.238, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.709826714024325, | |
| "grad_norm": 0.7527272701263428, | |
| "learning_rate": 0.00025781704557698525, | |
| "loss": 3.3118, | |
| "step": 53050 | |
| }, | |
| { | |
| "epoch": 5.715208266063933, | |
| "grad_norm": 0.7586866021156311, | |
| "learning_rate": 0.0002574938045469238, | |
| "loss": 3.323, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 5.720589818103541, | |
| "grad_norm": 0.7504985928535461, | |
| "learning_rate": 0.0002571705635168624, | |
| "loss": 3.3293, | |
| "step": 53150 | |
| }, | |
| { | |
| "epoch": 5.725971370143149, | |
| "grad_norm": 0.7618194222450256, | |
| "learning_rate": 0.000256847322486801, | |
| "loss": 3.344, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 5.731352922182758, | |
| "grad_norm": 0.7982940673828125, | |
| "learning_rate": 0.0002565240814567396, | |
| "loss": 3.3382, | |
| "step": 53250 | |
| }, | |
| { | |
| "epoch": 5.736734474222366, | |
| "grad_norm": 0.7086600661277771, | |
| "learning_rate": 0.0002562008404266781, | |
| "loss": 3.3341, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 5.742116026261974, | |
| "grad_norm": 0.71695476770401, | |
| "learning_rate": 0.0002558775993966167, | |
| "loss": 3.3213, | |
| "step": 53350 | |
| }, | |
| { | |
| "epoch": 5.747497578301582, | |
| "grad_norm": 0.7411425709724426, | |
| "learning_rate": 0.0002555543583665553, | |
| "loss": 3.3474, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 5.75287913034119, | |
| "grad_norm": 0.7171765565872192, | |
| "learning_rate": 0.0002552311173364939, | |
| "loss": 3.3428, | |
| "step": 53450 | |
| }, | |
| { | |
| "epoch": 5.758260682380799, | |
| "grad_norm": 0.7351555228233337, | |
| "learning_rate": 0.0002549078763064325, | |
| "loss": 3.3225, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 5.763642234420407, | |
| "grad_norm": 0.7267298102378845, | |
| "learning_rate": 0.00025458463527637103, | |
| "loss": 3.3269, | |
| "step": 53550 | |
| }, | |
| { | |
| "epoch": 5.769023786460015, | |
| "grad_norm": 0.6977094411849976, | |
| "learning_rate": 0.0002542613942463097, | |
| "loss": 3.3547, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 5.774405338499624, | |
| "grad_norm": 0.7931075096130371, | |
| "learning_rate": 0.0002539381532162482, | |
| "loss": 3.3261, | |
| "step": 53650 | |
| }, | |
| { | |
| "epoch": 5.779786890539231, | |
| "grad_norm": 0.7646996378898621, | |
| "learning_rate": 0.0002536149121861868, | |
| "loss": 3.3383, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 5.78516844257884, | |
| "grad_norm": 0.7829656004905701, | |
| "learning_rate": 0.0002532916711561254, | |
| "loss": 3.3332, | |
| "step": 53750 | |
| }, | |
| { | |
| "epoch": 5.790549994618448, | |
| "grad_norm": 0.7650371789932251, | |
| "learning_rate": 0.000252968430126064, | |
| "loss": 3.3414, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 5.795931546658056, | |
| "grad_norm": 0.7446619272232056, | |
| "learning_rate": 0.00025264518909600255, | |
| "loss": 3.3277, | |
| "step": 53850 | |
| }, | |
| { | |
| "epoch": 5.801313098697665, | |
| "grad_norm": 0.7219211459159851, | |
| "learning_rate": 0.00025232194806594114, | |
| "loss": 3.3408, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 5.806694650737272, | |
| "grad_norm": 0.7577422857284546, | |
| "learning_rate": 0.00025199870703587974, | |
| "loss": 3.345, | |
| "step": 53950 | |
| }, | |
| { | |
| "epoch": 5.812076202776881, | |
| "grad_norm": 0.7506514191627502, | |
| "learning_rate": 0.00025167546600581833, | |
| "loss": 3.3376, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.812076202776881, | |
| "eval_accuracy": 0.3836133626102161, | |
| "eval_loss": 3.3827064037323, | |
| "eval_runtime": 180.6271, | |
| "eval_samples_per_second": 99.714, | |
| "eval_steps_per_second": 6.234, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.817457754816489, | |
| "grad_norm": 0.7082645297050476, | |
| "learning_rate": 0.0002513522249757569, | |
| "loss": 3.3294, | |
| "step": 54050 | |
| }, | |
| { | |
| "epoch": 5.822839306856097, | |
| "grad_norm": 0.8100736141204834, | |
| "learning_rate": 0.00025102898394569547, | |
| "loss": 3.3329, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 5.828220858895706, | |
| "grad_norm": 0.7404306530952454, | |
| "learning_rate": 0.00025070574291563406, | |
| "loss": 3.3335, | |
| "step": 54150 | |
| }, | |
| { | |
| "epoch": 5.833602410935313, | |
| "grad_norm": 0.7143645286560059, | |
| "learning_rate": 0.00025038250188557265, | |
| "loss": 3.3362, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 5.838983962974922, | |
| "grad_norm": 0.7716860175132751, | |
| "learning_rate": 0.00025005926085551125, | |
| "loss": 3.3455, | |
| "step": 54250 | |
| }, | |
| { | |
| "epoch": 5.84436551501453, | |
| "grad_norm": 0.769177258014679, | |
| "learning_rate": 0.0002497360198254498, | |
| "loss": 3.3358, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 5.849747067054138, | |
| "grad_norm": 0.7687222957611084, | |
| "learning_rate": 0.00024941277879538844, | |
| "loss": 3.3366, | |
| "step": 54350 | |
| }, | |
| { | |
| "epoch": 5.855128619093747, | |
| "grad_norm": 0.7368986010551453, | |
| "learning_rate": 0.000249089537765327, | |
| "loss": 3.332, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 5.860510171133355, | |
| "grad_norm": 0.7428856492042542, | |
| "learning_rate": 0.0002487662967352656, | |
| "loss": 3.3448, | |
| "step": 54450 | |
| }, | |
| { | |
| "epoch": 5.865891723172963, | |
| "grad_norm": 0.7492393255233765, | |
| "learning_rate": 0.00024844305570520417, | |
| "loss": 3.3396, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 5.871273275212571, | |
| "grad_norm": 0.8640391826629639, | |
| "learning_rate": 0.00024811981467514276, | |
| "loss": 3.3256, | |
| "step": 54550 | |
| }, | |
| { | |
| "epoch": 5.87665482725218, | |
| "grad_norm": 0.7381857633590698, | |
| "learning_rate": 0.00024779657364508136, | |
| "loss": 3.3202, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 5.882036379291788, | |
| "grad_norm": 0.7371327877044678, | |
| "learning_rate": 0.0002474733326150199, | |
| "loss": 3.3164, | |
| "step": 54650 | |
| }, | |
| { | |
| "epoch": 5.887417931331396, | |
| "grad_norm": 0.7317863702774048, | |
| "learning_rate": 0.0002471500915849585, | |
| "loss": 3.314, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 5.892799483371004, | |
| "grad_norm": 0.7320008277893066, | |
| "learning_rate": 0.0002468268505548971, | |
| "loss": 3.3218, | |
| "step": 54750 | |
| }, | |
| { | |
| "epoch": 5.898181035410612, | |
| "grad_norm": 0.7335460186004639, | |
| "learning_rate": 0.0002465036095248357, | |
| "loss": 3.339, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 5.903562587450221, | |
| "grad_norm": 0.7588884234428406, | |
| "learning_rate": 0.0002461803684947742, | |
| "loss": 3.3418, | |
| "step": 54850 | |
| }, | |
| { | |
| "epoch": 5.9089441394898286, | |
| "grad_norm": 0.7557958364486694, | |
| "learning_rate": 0.0002458571274647128, | |
| "loss": 3.3497, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 5.914325691529437, | |
| "grad_norm": 0.7636759281158447, | |
| "learning_rate": 0.0002455338864346514, | |
| "loss": 3.3302, | |
| "step": 54950 | |
| }, | |
| { | |
| "epoch": 5.919707243569046, | |
| "grad_norm": 0.7415563464164734, | |
| "learning_rate": 0.00024521064540459, | |
| "loss": 3.3454, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.919707243569046, | |
| "eval_accuracy": 0.38400386108902135, | |
| "eval_loss": 3.3798177242279053, | |
| "eval_runtime": 180.4085, | |
| "eval_samples_per_second": 99.835, | |
| "eval_steps_per_second": 6.241, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.925088795608653, | |
| "grad_norm": 0.7452832460403442, | |
| "learning_rate": 0.0002448874043745286, | |
| "loss": 3.3509, | |
| "step": 55050 | |
| }, | |
| { | |
| "epoch": 5.930470347648262, | |
| "grad_norm": 0.8210157752037048, | |
| "learning_rate": 0.00024456416334446714, | |
| "loss": 3.3223, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 5.93585189968787, | |
| "grad_norm": 0.734848141670227, | |
| "learning_rate": 0.000244247387135007, | |
| "loss": 3.3249, | |
| "step": 55150 | |
| }, | |
| { | |
| "epoch": 5.941233451727478, | |
| "grad_norm": 0.8083829283714294, | |
| "learning_rate": 0.00024392414610494557, | |
| "loss": 3.329, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 5.946615003767087, | |
| "grad_norm": 0.7373672723770142, | |
| "learning_rate": 0.00024360090507488414, | |
| "loss": 3.339, | |
| "step": 55250 | |
| }, | |
| { | |
| "epoch": 5.951996555806694, | |
| "grad_norm": 0.7348290681838989, | |
| "learning_rate": 0.00024327766404482273, | |
| "loss": 3.3362, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 5.957378107846303, | |
| "grad_norm": 0.7888813018798828, | |
| "learning_rate": 0.0002429544230147613, | |
| "loss": 3.3275, | |
| "step": 55350 | |
| }, | |
| { | |
| "epoch": 5.962759659885911, | |
| "grad_norm": 0.7368828058242798, | |
| "learning_rate": 0.00024263118198469992, | |
| "loss": 3.3428, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 5.968141211925519, | |
| "grad_norm": 0.726843535900116, | |
| "learning_rate": 0.0002423079409546385, | |
| "loss": 3.357, | |
| "step": 55450 | |
| }, | |
| { | |
| "epoch": 5.973522763965128, | |
| "grad_norm": 0.7297669053077698, | |
| "learning_rate": 0.00024198469992457706, | |
| "loss": 3.3171, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 5.978904316004736, | |
| "grad_norm": 0.7472332119941711, | |
| "learning_rate": 0.00024166145889451568, | |
| "loss": 3.3452, | |
| "step": 55550 | |
| }, | |
| { | |
| "epoch": 5.984285868044344, | |
| "grad_norm": 0.7742068767547607, | |
| "learning_rate": 0.00024133821786445425, | |
| "loss": 3.35, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 5.989667420083952, | |
| "grad_norm": 0.7965028882026672, | |
| "learning_rate": 0.0002410149768343928, | |
| "loss": 3.3454, | |
| "step": 55650 | |
| }, | |
| { | |
| "epoch": 5.995048972123561, | |
| "grad_norm": 0.7538635730743408, | |
| "learning_rate": 0.0002406917358043314, | |
| "loss": 3.3523, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 6.000430524163169, | |
| "grad_norm": 0.7462757229804993, | |
| "learning_rate": 0.00024036849477427, | |
| "loss": 3.3303, | |
| "step": 55750 | |
| }, | |
| { | |
| "epoch": 6.005812076202777, | |
| "grad_norm": 0.7339770793914795, | |
| "learning_rate": 0.00024004525374420857, | |
| "loss": 3.2492, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 6.011193628242385, | |
| "grad_norm": 0.7494232654571533, | |
| "learning_rate": 0.00023972201271414716, | |
| "loss": 3.2566, | |
| "step": 55850 | |
| }, | |
| { | |
| "epoch": 6.016575180281993, | |
| "grad_norm": 0.7096470594406128, | |
| "learning_rate": 0.00023939877168408573, | |
| "loss": 3.2373, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 6.021956732321602, | |
| "grad_norm": 0.7256503701210022, | |
| "learning_rate": 0.00023907553065402433, | |
| "loss": 3.2391, | |
| "step": 55950 | |
| }, | |
| { | |
| "epoch": 6.0273382843612096, | |
| "grad_norm": 0.7260343432426453, | |
| "learning_rate": 0.00023875228962396292, | |
| "loss": 3.2501, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.0273382843612096, | |
| "eval_accuracy": 0.3840860026722091, | |
| "eval_loss": 3.3830971717834473, | |
| "eval_runtime": 180.8499, | |
| "eval_samples_per_second": 99.591, | |
| "eval_steps_per_second": 6.226, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.032719836400818, | |
| "grad_norm": 0.8156185746192932, | |
| "learning_rate": 0.0002384290485939015, | |
| "loss": 3.2535, | |
| "step": 56050 | |
| }, | |
| { | |
| "epoch": 6.038101388440427, | |
| "grad_norm": 0.7497657537460327, | |
| "learning_rate": 0.00023810580756384006, | |
| "loss": 3.2479, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 6.043482940480034, | |
| "grad_norm": 0.7156153321266174, | |
| "learning_rate": 0.00023778256653377868, | |
| "loss": 3.2614, | |
| "step": 56150 | |
| }, | |
| { | |
| "epoch": 6.048864492519643, | |
| "grad_norm": 0.7490081787109375, | |
| "learning_rate": 0.00023745932550371725, | |
| "loss": 3.2544, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 6.0542460445592505, | |
| "grad_norm": 0.7716811299324036, | |
| "learning_rate": 0.00023713608447365584, | |
| "loss": 3.2517, | |
| "step": 56250 | |
| }, | |
| { | |
| "epoch": 6.059627596598859, | |
| "grad_norm": 0.805608868598938, | |
| "learning_rate": 0.00023681284344359444, | |
| "loss": 3.2538, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 6.065009148638468, | |
| "grad_norm": 0.8110917210578918, | |
| "learning_rate": 0.000236489602413533, | |
| "loss": 3.246, | |
| "step": 56350 | |
| }, | |
| { | |
| "epoch": 6.070390700678075, | |
| "grad_norm": 0.8059680461883545, | |
| "learning_rate": 0.0002361663613834716, | |
| "loss": 3.2608, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 6.075772252717684, | |
| "grad_norm": 0.7581197619438171, | |
| "learning_rate": 0.00023584312035341017, | |
| "loss": 3.2681, | |
| "step": 56450 | |
| }, | |
| { | |
| "epoch": 6.081153804757292, | |
| "grad_norm": 0.7696651816368103, | |
| "learning_rate": 0.00023551987932334876, | |
| "loss": 3.2486, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 6.0865353567969, | |
| "grad_norm": 0.7502686977386475, | |
| "learning_rate": 0.00023519663829328735, | |
| "loss": 3.2639, | |
| "step": 56550 | |
| }, | |
| { | |
| "epoch": 6.091916908836509, | |
| "grad_norm": 0.7801194190979004, | |
| "learning_rate": 0.00023487339726322592, | |
| "loss": 3.2652, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 6.097298460876116, | |
| "grad_norm": 0.7480630874633789, | |
| "learning_rate": 0.0002345501562331645, | |
| "loss": 3.2495, | |
| "step": 56650 | |
| }, | |
| { | |
| "epoch": 6.102680012915725, | |
| "grad_norm": 0.7701714038848877, | |
| "learning_rate": 0.0002342269152031031, | |
| "loss": 3.27, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 6.108061564955333, | |
| "grad_norm": 0.7400213479995728, | |
| "learning_rate": 0.00023390367417304168, | |
| "loss": 3.2617, | |
| "step": 56750 | |
| }, | |
| { | |
| "epoch": 6.113443116994941, | |
| "grad_norm": 0.7020822763442993, | |
| "learning_rate": 0.00023358043314298025, | |
| "loss": 3.2603, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 6.11882466903455, | |
| "grad_norm": 0.7655128240585327, | |
| "learning_rate": 0.00023325719211291887, | |
| "loss": 3.2421, | |
| "step": 56850 | |
| }, | |
| { | |
| "epoch": 6.124206221074158, | |
| "grad_norm": 0.7835574150085449, | |
| "learning_rate": 0.00023293395108285744, | |
| "loss": 3.2615, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 6.129587773113766, | |
| "grad_norm": 0.7708025574684143, | |
| "learning_rate": 0.000232610710052796, | |
| "loss": 3.2681, | |
| "step": 56950 | |
| }, | |
| { | |
| "epoch": 6.134969325153374, | |
| "grad_norm": 0.7812603116035461, | |
| "learning_rate": 0.0002322874690227346, | |
| "loss": 3.2706, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.134969325153374, | |
| "eval_accuracy": 0.3842589780696098, | |
| "eval_loss": 3.382967472076416, | |
| "eval_runtime": 180.3604, | |
| "eval_samples_per_second": 99.861, | |
| "eval_steps_per_second": 6.243, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.140350877192983, | |
| "grad_norm": 0.7508556842803955, | |
| "learning_rate": 0.0002319642279926732, | |
| "loss": 3.2406, | |
| "step": 57050 | |
| }, | |
| { | |
| "epoch": 6.1457324292325906, | |
| "grad_norm": 0.7822660207748413, | |
| "learning_rate": 0.00023164098696261176, | |
| "loss": 3.2669, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 6.151113981272199, | |
| "grad_norm": 0.7589568495750427, | |
| "learning_rate": 0.00023131774593255036, | |
| "loss": 3.2541, | |
| "step": 57150 | |
| }, | |
| { | |
| "epoch": 6.156495533311807, | |
| "grad_norm": 0.8089141845703125, | |
| "learning_rate": 0.00023099450490248892, | |
| "loss": 3.2655, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 6.161877085351415, | |
| "grad_norm": 0.7813968658447266, | |
| "learning_rate": 0.00023067126387242754, | |
| "loss": 3.2779, | |
| "step": 57250 | |
| }, | |
| { | |
| "epoch": 6.167258637391024, | |
| "grad_norm": 0.7517101168632507, | |
| "learning_rate": 0.0002303480228423661, | |
| "loss": 3.261, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 6.1726401894306315, | |
| "grad_norm": 0.7565500140190125, | |
| "learning_rate": 0.00023002478181230468, | |
| "loss": 3.2513, | |
| "step": 57350 | |
| }, | |
| { | |
| "epoch": 6.17802174147024, | |
| "grad_norm": 0.722113311290741, | |
| "learning_rate": 0.00022970154078224327, | |
| "loss": 3.2755, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 6.183403293509849, | |
| "grad_norm": 0.805997371673584, | |
| "learning_rate": 0.00022937829975218187, | |
| "loss": 3.2674, | |
| "step": 57450 | |
| }, | |
| { | |
| "epoch": 6.188784845549456, | |
| "grad_norm": 0.7368705868721008, | |
| "learning_rate": 0.00022905505872212044, | |
| "loss": 3.2627, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 6.194166397589065, | |
| "grad_norm": 0.7440856099128723, | |
| "learning_rate": 0.00022873181769205903, | |
| "loss": 3.2576, | |
| "step": 57550 | |
| }, | |
| { | |
| "epoch": 6.1995479496286725, | |
| "grad_norm": 0.8116312623023987, | |
| "learning_rate": 0.0002284085766619976, | |
| "loss": 3.2743, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 6.204929501668281, | |
| "grad_norm": 0.7270071506500244, | |
| "learning_rate": 0.0002280853356319362, | |
| "loss": 3.2859, | |
| "step": 57650 | |
| }, | |
| { | |
| "epoch": 6.21031105370789, | |
| "grad_norm": 0.7267986536026001, | |
| "learning_rate": 0.0002277620946018748, | |
| "loss": 3.2578, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 6.215692605747497, | |
| "grad_norm": 0.7756433486938477, | |
| "learning_rate": 0.00022743885357181336, | |
| "loss": 3.2718, | |
| "step": 57750 | |
| }, | |
| { | |
| "epoch": 6.221074157787106, | |
| "grad_norm": 0.7905489206314087, | |
| "learning_rate": 0.00022711561254175192, | |
| "loss": 3.2755, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 6.226455709826714, | |
| "grad_norm": 0.8063260912895203, | |
| "learning_rate": 0.00022679237151169054, | |
| "loss": 3.2735, | |
| "step": 57850 | |
| }, | |
| { | |
| "epoch": 6.231837261866322, | |
| "grad_norm": 0.7980824708938599, | |
| "learning_rate": 0.0002264691304816291, | |
| "loss": 3.2635, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 6.237218813905931, | |
| "grad_norm": 0.7567322254180908, | |
| "learning_rate": 0.00022614588945156768, | |
| "loss": 3.2738, | |
| "step": 57950 | |
| }, | |
| { | |
| "epoch": 6.242600365945538, | |
| "grad_norm": 0.7856761813163757, | |
| "learning_rate": 0.0002258226484215063, | |
| "loss": 3.28, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.242600365945538, | |
| "eval_accuracy": 0.3846668610104653, | |
| "eval_loss": 3.3798773288726807, | |
| "eval_runtime": 180.5316, | |
| "eval_samples_per_second": 99.766, | |
| "eval_steps_per_second": 6.237, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.247981917985147, | |
| "grad_norm": 0.7729969024658203, | |
| "learning_rate": 0.00022549940739144487, | |
| "loss": 3.2857, | |
| "step": 58050 | |
| }, | |
| { | |
| "epoch": 6.253363470024755, | |
| "grad_norm": 0.8097330927848816, | |
| "learning_rate": 0.00022517616636138344, | |
| "loss": 3.2717, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 6.258745022064363, | |
| "grad_norm": 0.8649580478668213, | |
| "learning_rate": 0.00022485292533132203, | |
| "loss": 3.2832, | |
| "step": 58150 | |
| }, | |
| { | |
| "epoch": 6.264126574103972, | |
| "grad_norm": 0.771740734577179, | |
| "learning_rate": 0.00022452968430126063, | |
| "loss": 3.2734, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 6.26950812614358, | |
| "grad_norm": 0.7663628458976746, | |
| "learning_rate": 0.00022420644327119922, | |
| "loss": 3.2736, | |
| "step": 58250 | |
| }, | |
| { | |
| "epoch": 6.274889678183188, | |
| "grad_norm": 0.7669972777366638, | |
| "learning_rate": 0.0002238832022411378, | |
| "loss": 3.2712, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 6.280271230222796, | |
| "grad_norm": 0.7995150089263916, | |
| "learning_rate": 0.00022355996121107636, | |
| "loss": 3.2764, | |
| "step": 58350 | |
| }, | |
| { | |
| "epoch": 6.285652782262405, | |
| "grad_norm": 0.7507680654525757, | |
| "learning_rate": 0.00022323672018101498, | |
| "loss": 3.2882, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 6.2910343343020125, | |
| "grad_norm": 0.8180110454559326, | |
| "learning_rate": 0.00022291347915095355, | |
| "loss": 3.2764, | |
| "step": 58450 | |
| }, | |
| { | |
| "epoch": 6.296415886341621, | |
| "grad_norm": 0.7749719619750977, | |
| "learning_rate": 0.0002225902381208921, | |
| "loss": 3.272, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 6.301797438381229, | |
| "grad_norm": 0.7502884864807129, | |
| "learning_rate": 0.00022226699709083073, | |
| "loss": 3.2762, | |
| "step": 58550 | |
| }, | |
| { | |
| "epoch": 6.307178990420837, | |
| "grad_norm": 0.8392398357391357, | |
| "learning_rate": 0.00022195022088137051, | |
| "loss": 3.2646, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 6.312560542460446, | |
| "grad_norm": 0.7521066665649414, | |
| "learning_rate": 0.0002216269798513091, | |
| "loss": 3.2673, | |
| "step": 58650 | |
| }, | |
| { | |
| "epoch": 6.3179420945000535, | |
| "grad_norm": 0.7701011300086975, | |
| "learning_rate": 0.00022130373882124768, | |
| "loss": 3.2645, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 6.323323646539662, | |
| "grad_norm": 0.8215457797050476, | |
| "learning_rate": 0.00022098049779118627, | |
| "loss": 3.2603, | |
| "step": 58750 | |
| }, | |
| { | |
| "epoch": 6.328705198579271, | |
| "grad_norm": 0.7722597122192383, | |
| "learning_rate": 0.00022065725676112487, | |
| "loss": 3.2791, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 6.334086750618878, | |
| "grad_norm": 0.7506366968154907, | |
| "learning_rate": 0.00022033401573106343, | |
| "loss": 3.2869, | |
| "step": 58850 | |
| }, | |
| { | |
| "epoch": 6.339468302658487, | |
| "grad_norm": 0.7620330452919006, | |
| "learning_rate": 0.000220010774701002, | |
| "loss": 3.274, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 6.344849854698095, | |
| "grad_norm": 0.7641044855117798, | |
| "learning_rate": 0.00021968753367094062, | |
| "loss": 3.2703, | |
| "step": 58950 | |
| }, | |
| { | |
| "epoch": 6.350231406737703, | |
| "grad_norm": 0.7357539534568787, | |
| "learning_rate": 0.0002193642926408792, | |
| "loss": 3.277, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.350231406737703, | |
| "eval_accuracy": 0.3850675728607251, | |
| "eval_loss": 3.3782007694244385, | |
| "eval_runtime": 180.5172, | |
| "eval_samples_per_second": 99.774, | |
| "eval_steps_per_second": 6.238, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.355612958777312, | |
| "grad_norm": 0.793239951133728, | |
| "learning_rate": 0.00021904105161081778, | |
| "loss": 3.2845, | |
| "step": 59050 | |
| }, | |
| { | |
| "epoch": 6.360994510816919, | |
| "grad_norm": 0.7626572251319885, | |
| "learning_rate": 0.00021871781058075638, | |
| "loss": 3.2751, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 6.366376062856528, | |
| "grad_norm": 0.7418571710586548, | |
| "learning_rate": 0.00021839456955069495, | |
| "loss": 3.285, | |
| "step": 59150 | |
| }, | |
| { | |
| "epoch": 6.371757614896136, | |
| "grad_norm": 0.7725799679756165, | |
| "learning_rate": 0.00021807132852063354, | |
| "loss": 3.2829, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 6.377139166935744, | |
| "grad_norm": 0.731188952922821, | |
| "learning_rate": 0.0002177480874905721, | |
| "loss": 3.2764, | |
| "step": 59250 | |
| }, | |
| { | |
| "epoch": 6.382520718975353, | |
| "grad_norm": 0.7765207290649414, | |
| "learning_rate": 0.0002174248464605107, | |
| "loss": 3.2717, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 6.387902271014961, | |
| "grad_norm": 0.7506345510482788, | |
| "learning_rate": 0.0002171016054304493, | |
| "loss": 3.2679, | |
| "step": 59350 | |
| }, | |
| { | |
| "epoch": 6.393283823054569, | |
| "grad_norm": 0.7452055215835571, | |
| "learning_rate": 0.00021677836440038787, | |
| "loss": 3.2577, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 6.398665375094177, | |
| "grad_norm": 0.8073831796646118, | |
| "learning_rate": 0.00021645512337032643, | |
| "loss": 3.2606, | |
| "step": 59450 | |
| }, | |
| { | |
| "epoch": 6.404046927133785, | |
| "grad_norm": 0.7789980173110962, | |
| "learning_rate": 0.00021613188234026506, | |
| "loss": 3.2712, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 6.4094284791733935, | |
| "grad_norm": 0.8396959900856018, | |
| "learning_rate": 0.00021580864131020362, | |
| "loss": 3.2768, | |
| "step": 59550 | |
| }, | |
| { | |
| "epoch": 6.414810031213002, | |
| "grad_norm": 0.797767162322998, | |
| "learning_rate": 0.0002154854002801422, | |
| "loss": 3.2813, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 6.42019158325261, | |
| "grad_norm": 0.802899956703186, | |
| "learning_rate": 0.0002151621592500808, | |
| "loss": 3.2889, | |
| "step": 59650 | |
| }, | |
| { | |
| "epoch": 6.425573135292218, | |
| "grad_norm": 0.8054869771003723, | |
| "learning_rate": 0.00021483891822001938, | |
| "loss": 3.2716, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 6.430954687331827, | |
| "grad_norm": 0.7798833250999451, | |
| "learning_rate": 0.00021451567718995795, | |
| "loss": 3.2781, | |
| "step": 59750 | |
| }, | |
| { | |
| "epoch": 6.4363362393714345, | |
| "grad_norm": 0.7423691153526306, | |
| "learning_rate": 0.00021419243615989654, | |
| "loss": 3.2763, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 6.441717791411043, | |
| "grad_norm": 0.8051731586456299, | |
| "learning_rate": 0.00021386919512983514, | |
| "loss": 3.2666, | |
| "step": 59850 | |
| }, | |
| { | |
| "epoch": 6.447099343450651, | |
| "grad_norm": 0.8098742365837097, | |
| "learning_rate": 0.0002135459540997737, | |
| "loss": 3.2656, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 6.452480895490259, | |
| "grad_norm": 0.8203098177909851, | |
| "learning_rate": 0.0002132227130697123, | |
| "loss": 3.2729, | |
| "step": 59950 | |
| }, | |
| { | |
| "epoch": 6.457862447529868, | |
| "grad_norm": 0.736182689666748, | |
| "learning_rate": 0.00021289947203965087, | |
| "loss": 3.2727, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.457862447529868, | |
| "eval_accuracy": 0.385509246849691, | |
| "eval_loss": 3.372286558151245, | |
| "eval_runtime": 180.8685, | |
| "eval_samples_per_second": 99.581, | |
| "eval_steps_per_second": 6.226, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.4632439995694755, | |
| "grad_norm": 0.7694886326789856, | |
| "learning_rate": 0.0002125762310095895, | |
| "loss": 3.2795, | |
| "step": 60050 | |
| }, | |
| { | |
| "epoch": 6.468625551609084, | |
| "grad_norm": 0.7625947594642639, | |
| "learning_rate": 0.00021225298997952806, | |
| "loss": 3.2678, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 6.474007103648693, | |
| "grad_norm": 0.7633724808692932, | |
| "learning_rate": 0.00021192974894946662, | |
| "loss": 3.2773, | |
| "step": 60150 | |
| }, | |
| { | |
| "epoch": 6.4793886556883, | |
| "grad_norm": 0.7859768271446228, | |
| "learning_rate": 0.00021160650791940524, | |
| "loss": 3.2929, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 6.484770207727909, | |
| "grad_norm": 0.7822881937026978, | |
| "learning_rate": 0.0002112832668893438, | |
| "loss": 3.2923, | |
| "step": 60250 | |
| }, | |
| { | |
| "epoch": 6.490151759767517, | |
| "grad_norm": 0.7258760929107666, | |
| "learning_rate": 0.00021096002585928238, | |
| "loss": 3.2784, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 6.495533311807125, | |
| "grad_norm": 0.7965183854103088, | |
| "learning_rate": 0.00021063678482922097, | |
| "loss": 3.2617, | |
| "step": 60350 | |
| }, | |
| { | |
| "epoch": 6.500914863846734, | |
| "grad_norm": 0.8430307507514954, | |
| "learning_rate": 0.00021031354379915957, | |
| "loss": 3.2637, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 6.506296415886341, | |
| "grad_norm": 0.7958040833473206, | |
| "learning_rate": 0.00020999030276909814, | |
| "loss": 3.2915, | |
| "step": 60450 | |
| }, | |
| { | |
| "epoch": 6.51167796792595, | |
| "grad_norm": 0.7817371487617493, | |
| "learning_rate": 0.00020966706173903673, | |
| "loss": 3.2911, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 6.517059519965558, | |
| "grad_norm": 0.7723913192749023, | |
| "learning_rate": 0.0002093438207089753, | |
| "loss": 3.2695, | |
| "step": 60550 | |
| }, | |
| { | |
| "epoch": 6.522441072005166, | |
| "grad_norm": 0.7523823380470276, | |
| "learning_rate": 0.00020902057967891387, | |
| "loss": 3.2835, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 6.5278226240447745, | |
| "grad_norm": 0.7971324920654297, | |
| "learning_rate": 0.0002086973386488525, | |
| "loss": 3.2922, | |
| "step": 60650 | |
| }, | |
| { | |
| "epoch": 6.533204176084383, | |
| "grad_norm": 0.8252760767936707, | |
| "learning_rate": 0.00020837409761879106, | |
| "loss": 3.2898, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 6.538585728123991, | |
| "grad_norm": 0.7614521980285645, | |
| "learning_rate": 0.00020805085658872962, | |
| "loss": 3.2906, | |
| "step": 60750 | |
| }, | |
| { | |
| "epoch": 6.543967280163599, | |
| "grad_norm": 0.8246181011199951, | |
| "learning_rate": 0.00020772761555866825, | |
| "loss": 3.2725, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 6.549348832203208, | |
| "grad_norm": 0.7531991004943848, | |
| "learning_rate": 0.0002074043745286068, | |
| "loss": 3.274, | |
| "step": 60850 | |
| }, | |
| { | |
| "epoch": 6.5547303842428155, | |
| "grad_norm": 0.8107429146766663, | |
| "learning_rate": 0.00020708113349854538, | |
| "loss": 3.2757, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 6.560111936282424, | |
| "grad_norm": 0.8336337208747864, | |
| "learning_rate": 0.00020675789246848397, | |
| "loss": 3.2756, | |
| "step": 60950 | |
| }, | |
| { | |
| "epoch": 6.565493488322032, | |
| "grad_norm": 0.8028927445411682, | |
| "learning_rate": 0.00020643465143842257, | |
| "loss": 3.2838, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.565493488322032, | |
| "eval_accuracy": 0.3859593957639064, | |
| "eval_loss": 3.3682973384857178, | |
| "eval_runtime": 180.3806, | |
| "eval_samples_per_second": 99.85, | |
| "eval_steps_per_second": 6.242, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.57087504036164, | |
| "grad_norm": 0.8147567510604858, | |
| "learning_rate": 0.00020611141040836116, | |
| "loss": 3.2949, | |
| "step": 61050 | |
| }, | |
| { | |
| "epoch": 6.576256592401249, | |
| "grad_norm": 0.8347201347351074, | |
| "learning_rate": 0.00020578816937829973, | |
| "loss": 3.2929, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 6.5816381444408565, | |
| "grad_norm": 0.8149718046188354, | |
| "learning_rate": 0.0002054649283482383, | |
| "loss": 3.2933, | |
| "step": 61150 | |
| }, | |
| { | |
| "epoch": 6.587019696480465, | |
| "grad_norm": 0.7641071677207947, | |
| "learning_rate": 0.00020514168731817692, | |
| "loss": 3.2689, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 6.592401248520073, | |
| "grad_norm": 0.8402169942855835, | |
| "learning_rate": 0.0002048184462881155, | |
| "loss": 3.2796, | |
| "step": 61250 | |
| }, | |
| { | |
| "epoch": 6.597782800559681, | |
| "grad_norm": 0.7858189940452576, | |
| "learning_rate": 0.00020449520525805406, | |
| "loss": 3.29, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 6.60316435259929, | |
| "grad_norm": 0.7707937359809875, | |
| "learning_rate": 0.00020417196422799268, | |
| "loss": 3.2823, | |
| "step": 61350 | |
| }, | |
| { | |
| "epoch": 6.608545904638898, | |
| "grad_norm": 0.7980074882507324, | |
| "learning_rate": 0.00020384872319793125, | |
| "loss": 3.2965, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 6.613927456678506, | |
| "grad_norm": 0.771574854850769, | |
| "learning_rate": 0.0002035254821678698, | |
| "loss": 3.2852, | |
| "step": 61450 | |
| }, | |
| { | |
| "epoch": 6.619309008718115, | |
| "grad_norm": 0.7880848050117493, | |
| "learning_rate": 0.0002032022411378084, | |
| "loss": 3.2822, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 6.624690560757722, | |
| "grad_norm": 0.7877942323684692, | |
| "learning_rate": 0.000202879000107747, | |
| "loss": 3.264, | |
| "step": 61550 | |
| }, | |
| { | |
| "epoch": 6.630072112797331, | |
| "grad_norm": 0.7295520901679993, | |
| "learning_rate": 0.00020255575907768557, | |
| "loss": 3.2691, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 6.635453664836939, | |
| "grad_norm": 0.8145275712013245, | |
| "learning_rate": 0.00020223251804762416, | |
| "loss": 3.2715, | |
| "step": 61650 | |
| }, | |
| { | |
| "epoch": 6.640835216876547, | |
| "grad_norm": 0.8078879714012146, | |
| "learning_rate": 0.00020190927701756273, | |
| "loss": 3.2752, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 6.6462167689161555, | |
| "grad_norm": 1.0516327619552612, | |
| "learning_rate": 0.00020158603598750133, | |
| "loss": 3.2702, | |
| "step": 61750 | |
| }, | |
| { | |
| "epoch": 6.651598320955763, | |
| "grad_norm": 0.8313896059989929, | |
| "learning_rate": 0.00020126279495743992, | |
| "loss": 3.2767, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 6.656979872995372, | |
| "grad_norm": 0.812926709651947, | |
| "learning_rate": 0.0002009395539273785, | |
| "loss": 3.2784, | |
| "step": 61850 | |
| }, | |
| { | |
| "epoch": 6.66236142503498, | |
| "grad_norm": 0.7894045114517212, | |
| "learning_rate": 0.00020061631289731706, | |
| "loss": 3.2954, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 6.667742977074588, | |
| "grad_norm": 0.7732223272323608, | |
| "learning_rate": 0.00020029307186725568, | |
| "loss": 3.2946, | |
| "step": 61950 | |
| }, | |
| { | |
| "epoch": 6.6731245291141965, | |
| "grad_norm": 0.7833398580551147, | |
| "learning_rate": 0.00019996983083719425, | |
| "loss": 3.2802, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.6731245291141965, | |
| "eval_accuracy": 0.38636662678743505, | |
| "eval_loss": 3.3642148971557617, | |
| "eval_runtime": 180.6181, | |
| "eval_samples_per_second": 99.719, | |
| "eval_steps_per_second": 6.234, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.678506081153805, | |
| "grad_norm": 0.7945963740348816, | |
| "learning_rate": 0.00019964658980713284, | |
| "loss": 3.306, | |
| "step": 62050 | |
| }, | |
| { | |
| "epoch": 6.683887633193413, | |
| "grad_norm": 0.7843768000602722, | |
| "learning_rate": 0.00019932334877707144, | |
| "loss": 3.2765, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 6.689269185233021, | |
| "grad_norm": 0.8199366927146912, | |
| "learning_rate": 0.00019900657256761124, | |
| "loss": 3.2743, | |
| "step": 62150 | |
| }, | |
| { | |
| "epoch": 6.69465073727263, | |
| "grad_norm": 0.7921463251113892, | |
| "learning_rate": 0.0001986833315375498, | |
| "loss": 3.284, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 6.7000322893122375, | |
| "grad_norm": 0.7658042311668396, | |
| "learning_rate": 0.00019836009050748838, | |
| "loss": 3.2779, | |
| "step": 62250 | |
| }, | |
| { | |
| "epoch": 6.705413841351846, | |
| "grad_norm": 0.7855052947998047, | |
| "learning_rate": 0.000198036849477427, | |
| "loss": 3.2939, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 6.710795393391454, | |
| "grad_norm": 0.778864860534668, | |
| "learning_rate": 0.00019771360844736557, | |
| "loss": 3.2865, | |
| "step": 62350 | |
| }, | |
| { | |
| "epoch": 6.716176945431062, | |
| "grad_norm": 0.7535867691040039, | |
| "learning_rate": 0.00019739036741730413, | |
| "loss": 3.281, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 6.721558497470671, | |
| "grad_norm": 0.8026406168937683, | |
| "learning_rate": 0.00019706712638724276, | |
| "loss": 3.2898, | |
| "step": 62450 | |
| }, | |
| { | |
| "epoch": 6.7269400495102785, | |
| "grad_norm": 0.826941192150116, | |
| "learning_rate": 0.00019674388535718132, | |
| "loss": 3.2813, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 6.732321601549887, | |
| "grad_norm": 0.8191684484481812, | |
| "learning_rate": 0.0001964206443271199, | |
| "loss": 3.279, | |
| "step": 62550 | |
| }, | |
| { | |
| "epoch": 6.737703153589496, | |
| "grad_norm": 0.7996468544006348, | |
| "learning_rate": 0.00019609740329705849, | |
| "loss": 3.2748, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 6.743084705629103, | |
| "grad_norm": 0.8293940424919128, | |
| "learning_rate": 0.00019577416226699708, | |
| "loss": 3.2804, | |
| "step": 62650 | |
| }, | |
| { | |
| "epoch": 6.748466257668712, | |
| "grad_norm": 0.7844554781913757, | |
| "learning_rate": 0.00019545092123693565, | |
| "loss": 3.2701, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 6.75384780970832, | |
| "grad_norm": 0.7604687809944153, | |
| "learning_rate": 0.00019512768020687424, | |
| "loss": 3.2818, | |
| "step": 62750 | |
| }, | |
| { | |
| "epoch": 6.759229361747928, | |
| "grad_norm": 0.8484272956848145, | |
| "learning_rate": 0.0001948044391768128, | |
| "loss": 3.2771, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 6.7646109137875365, | |
| "grad_norm": 0.7642599940299988, | |
| "learning_rate": 0.00019448119814675143, | |
| "loss": 3.2808, | |
| "step": 62850 | |
| }, | |
| { | |
| "epoch": 6.769992465827144, | |
| "grad_norm": 0.7840580344200134, | |
| "learning_rate": 0.00019415795711669, | |
| "loss": 3.2957, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 6.775374017866753, | |
| "grad_norm": 0.8181833028793335, | |
| "learning_rate": 0.00019383471608662857, | |
| "loss": 3.2691, | |
| "step": 62950 | |
| }, | |
| { | |
| "epoch": 6.780755569906361, | |
| "grad_norm": 0.8215237259864807, | |
| "learning_rate": 0.0001935114750565672, | |
| "loss": 3.2696, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.780755569906361, | |
| "eval_accuracy": 0.38650168232698845, | |
| "eval_loss": 3.359816312789917, | |
| "eval_runtime": 180.6996, | |
| "eval_samples_per_second": 99.674, | |
| "eval_steps_per_second": 6.231, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.786137121945969, | |
| "grad_norm": 0.7587153911590576, | |
| "learning_rate": 0.00019318823402650576, | |
| "loss": 3.2695, | |
| "step": 63050 | |
| }, | |
| { | |
| "epoch": 6.7915186739855775, | |
| "grad_norm": 0.7708876729011536, | |
| "learning_rate": 0.00019286499299644432, | |
| "loss": 3.2752, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 6.796900226025185, | |
| "grad_norm": 0.8366973400115967, | |
| "learning_rate": 0.00019254175196638292, | |
| "loss": 3.293, | |
| "step": 63150 | |
| }, | |
| { | |
| "epoch": 6.802281778064794, | |
| "grad_norm": 0.8045485019683838, | |
| "learning_rate": 0.0001922185109363215, | |
| "loss": 3.2756, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 6.807663330104402, | |
| "grad_norm": 0.7623797059059143, | |
| "learning_rate": 0.00019189526990626008, | |
| "loss": 3.2853, | |
| "step": 63250 | |
| }, | |
| { | |
| "epoch": 6.813044882144011, | |
| "grad_norm": 0.7878138422966003, | |
| "learning_rate": 0.00019157202887619867, | |
| "loss": 3.2875, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 6.8184264341836185, | |
| "grad_norm": 0.7722912430763245, | |
| "learning_rate": 0.00019124878784613724, | |
| "loss": 3.2808, | |
| "step": 63350 | |
| }, | |
| { | |
| "epoch": 6.823807986223227, | |
| "grad_norm": 0.7824761271476746, | |
| "learning_rate": 0.00019092554681607584, | |
| "loss": 3.2744, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 6.829189538262835, | |
| "grad_norm": 0.8032478094100952, | |
| "learning_rate": 0.00019060230578601443, | |
| "loss": 3.2716, | |
| "step": 63450 | |
| }, | |
| { | |
| "epoch": 6.834571090302443, | |
| "grad_norm": 0.7636817097663879, | |
| "learning_rate": 0.000190279064755953, | |
| "loss": 3.2809, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 6.839952642342052, | |
| "grad_norm": 0.8288126587867737, | |
| "learning_rate": 0.00018995582372589157, | |
| "loss": 3.2843, | |
| "step": 63550 | |
| }, | |
| { | |
| "epoch": 6.8453341943816595, | |
| "grad_norm": 0.7764488458633423, | |
| "learning_rate": 0.0001896325826958302, | |
| "loss": 3.2944, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 6.850715746421268, | |
| "grad_norm": 0.8440558910369873, | |
| "learning_rate": 0.00018930934166576876, | |
| "loss": 3.282, | |
| "step": 63650 | |
| }, | |
| { | |
| "epoch": 6.856097298460876, | |
| "grad_norm": 0.8410781025886536, | |
| "learning_rate": 0.00018898610063570732, | |
| "loss": 3.2914, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 6.861478850500484, | |
| "grad_norm": 0.7732300758361816, | |
| "learning_rate": 0.00018866285960564595, | |
| "loss": 3.2623, | |
| "step": 63750 | |
| }, | |
| { | |
| "epoch": 6.866860402540093, | |
| "grad_norm": 0.7925925850868225, | |
| "learning_rate": 0.0001883396185755845, | |
| "loss": 3.2792, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 6.8722419545797, | |
| "grad_norm": 0.7949431538581848, | |
| "learning_rate": 0.0001880163775455231, | |
| "loss": 3.2922, | |
| "step": 63850 | |
| }, | |
| { | |
| "epoch": 6.877623506619309, | |
| "grad_norm": 0.7886269092559814, | |
| "learning_rate": 0.00018769313651546168, | |
| "loss": 3.28, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 6.8830050586589175, | |
| "grad_norm": 0.8459096550941467, | |
| "learning_rate": 0.00018736989548540027, | |
| "loss": 3.2812, | |
| "step": 63950 | |
| }, | |
| { | |
| "epoch": 6.888386610698525, | |
| "grad_norm": 0.798220694065094, | |
| "learning_rate": 0.00018704665445533886, | |
| "loss": 3.2895, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.888386610698525, | |
| "eval_accuracy": 0.3871914108588348, | |
| "eval_loss": 3.3550844192504883, | |
| "eval_runtime": 180.8293, | |
| "eval_samples_per_second": 99.602, | |
| "eval_steps_per_second": 6.227, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.893768162738134, | |
| "grad_norm": 0.788962185382843, | |
| "learning_rate": 0.00018672341342527743, | |
| "loss": 3.2834, | |
| "step": 64050 | |
| }, | |
| { | |
| "epoch": 6.899149714777742, | |
| "grad_norm": 0.7914458513259888, | |
| "learning_rate": 0.000186400172395216, | |
| "loss": 3.2871, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 6.90453126681735, | |
| "grad_norm": 0.8202913403511047, | |
| "learning_rate": 0.00018607693136515462, | |
| "loss": 3.2844, | |
| "step": 64150 | |
| }, | |
| { | |
| "epoch": 6.9099128188569585, | |
| "grad_norm": 0.8197557330131531, | |
| "learning_rate": 0.0001857536903350932, | |
| "loss": 3.2812, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 6.915294370896566, | |
| "grad_norm": 0.8909661769866943, | |
| "learning_rate": 0.00018543044930503176, | |
| "loss": 3.2823, | |
| "step": 64250 | |
| }, | |
| { | |
| "epoch": 6.920675922936175, | |
| "grad_norm": 0.8012292385101318, | |
| "learning_rate": 0.00018510720827497035, | |
| "loss": 3.2831, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 6.926057474975783, | |
| "grad_norm": 0.8419049978256226, | |
| "learning_rate": 0.00018478396724490895, | |
| "loss": 3.2819, | |
| "step": 64350 | |
| }, | |
| { | |
| "epoch": 6.931439027015391, | |
| "grad_norm": 0.8665248155593872, | |
| "learning_rate": 0.0001844607262148475, | |
| "loss": 3.2778, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 6.9368205790549995, | |
| "grad_norm": 0.8091945052146912, | |
| "learning_rate": 0.0001841374851847861, | |
| "loss": 3.2969, | |
| "step": 64450 | |
| }, | |
| { | |
| "epoch": 6.942202131094608, | |
| "grad_norm": 0.7917461395263672, | |
| "learning_rate": 0.00018381424415472468, | |
| "loss": 3.2777, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 6.947583683134216, | |
| "grad_norm": 0.8483121395111084, | |
| "learning_rate": 0.00018349100312466327, | |
| "loss": 3.2774, | |
| "step": 64550 | |
| }, | |
| { | |
| "epoch": 6.952965235173824, | |
| "grad_norm": 0.8231863379478455, | |
| "learning_rate": 0.00018316776209460186, | |
| "loss": 3.2817, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 6.958346787213433, | |
| "grad_norm": 0.7838043570518494, | |
| "learning_rate": 0.00018284452106454043, | |
| "loss": 3.2871, | |
| "step": 64650 | |
| }, | |
| { | |
| "epoch": 6.9637283392530405, | |
| "grad_norm": 0.8054148554801941, | |
| "learning_rate": 0.000182521280034479, | |
| "loss": 3.2853, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 6.969109891292649, | |
| "grad_norm": 0.8586058020591736, | |
| "learning_rate": 0.00018219803900441762, | |
| "loss": 3.2725, | |
| "step": 64750 | |
| }, | |
| { | |
| "epoch": 6.974491443332257, | |
| "grad_norm": 0.8905388712882996, | |
| "learning_rate": 0.0001818747979743562, | |
| "loss": 3.2941, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 6.979872995371865, | |
| "grad_norm": 0.8023561835289001, | |
| "learning_rate": 0.00018155155694429478, | |
| "loss": 3.2772, | |
| "step": 64850 | |
| }, | |
| { | |
| "epoch": 6.985254547411474, | |
| "grad_norm": 0.8267327547073364, | |
| "learning_rate": 0.00018122831591423338, | |
| "loss": 3.3077, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 6.990636099451081, | |
| "grad_norm": 0.8111370801925659, | |
| "learning_rate": 0.00018090507488417195, | |
| "loss": 3.2822, | |
| "step": 64950 | |
| }, | |
| { | |
| "epoch": 6.99601765149069, | |
| "grad_norm": 0.7818148732185364, | |
| "learning_rate": 0.00018058829867471175, | |
| "loss": 3.2834, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 6.99601765149069, | |
| "eval_accuracy": 0.38743957405460305, | |
| "eval_loss": 3.350639581680298, | |
| "eval_runtime": 180.6606, | |
| "eval_samples_per_second": 99.695, | |
| "eval_steps_per_second": 6.233, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 7.0013992035302985, | |
| "grad_norm": 0.8154913783073425, | |
| "learning_rate": 0.00018026505764465035, | |
| "loss": 3.2506, | |
| "step": 65050 | |
| }, | |
| { | |
| "epoch": 7.006780755569906, | |
| "grad_norm": 0.776719868183136, | |
| "learning_rate": 0.00017994181661458894, | |
| "loss": 3.1834, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 7.012162307609515, | |
| "grad_norm": 0.7705662846565247, | |
| "learning_rate": 0.0001796185755845275, | |
| "loss": 3.2001, | |
| "step": 65150 | |
| }, | |
| { | |
| "epoch": 7.017543859649122, | |
| "grad_norm": 0.8426011800765991, | |
| "learning_rate": 0.00017929533455446608, | |
| "loss": 3.1784, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 7.022925411688731, | |
| "grad_norm": 0.8200896978378296, | |
| "learning_rate": 0.0001789720935244047, | |
| "loss": 3.1967, | |
| "step": 65250 | |
| }, | |
| { | |
| "epoch": 7.0283069637283395, | |
| "grad_norm": 0.8123102188110352, | |
| "learning_rate": 0.00017864885249434327, | |
| "loss": 3.201, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 7.033688515767947, | |
| "grad_norm": 0.8369794487953186, | |
| "learning_rate": 0.00017832561146428183, | |
| "loss": 3.1928, | |
| "step": 65350 | |
| }, | |
| { | |
| "epoch": 7.039070067807556, | |
| "grad_norm": 0.7779251933097839, | |
| "learning_rate": 0.00017800237043422046, | |
| "loss": 3.1874, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 7.044451619847164, | |
| "grad_norm": 0.8082521557807922, | |
| "learning_rate": 0.00017767912940415902, | |
| "loss": 3.1967, | |
| "step": 65450 | |
| }, | |
| { | |
| "epoch": 7.049833171886772, | |
| "grad_norm": 0.8156419992446899, | |
| "learning_rate": 0.0001773558883740976, | |
| "loss": 3.1956, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 7.0552147239263805, | |
| "grad_norm": 0.8252975344657898, | |
| "learning_rate": 0.00017703264734403619, | |
| "loss": 3.2095, | |
| "step": 65550 | |
| }, | |
| { | |
| "epoch": 7.060596275965988, | |
| "grad_norm": 0.7841750383377075, | |
| "learning_rate": 0.00017670940631397475, | |
| "loss": 3.1895, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 7.065977828005597, | |
| "grad_norm": 0.8294128179550171, | |
| "learning_rate": 0.00017638616528391337, | |
| "loss": 3.212, | |
| "step": 65650 | |
| }, | |
| { | |
| "epoch": 7.071359380045205, | |
| "grad_norm": 0.8671795129776001, | |
| "learning_rate": 0.00017606292425385194, | |
| "loss": 3.2094, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 7.076740932084813, | |
| "grad_norm": 0.7949682474136353, | |
| "learning_rate": 0.0001757396832237905, | |
| "loss": 3.2189, | |
| "step": 65750 | |
| }, | |
| { | |
| "epoch": 7.0821224841244215, | |
| "grad_norm": 0.8465704917907715, | |
| "learning_rate": 0.00017541644219372913, | |
| "loss": 3.2139, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 7.08750403616403, | |
| "grad_norm": 0.8210230469703674, | |
| "learning_rate": 0.0001750932011636677, | |
| "loss": 3.2113, | |
| "step": 65850 | |
| }, | |
| { | |
| "epoch": 7.092885588203638, | |
| "grad_norm": 0.8009158372879028, | |
| "learning_rate": 0.00017476996013360627, | |
| "loss": 3.2013, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 7.098267140243246, | |
| "grad_norm": 0.8548141717910767, | |
| "learning_rate": 0.00017444671910354486, | |
| "loss": 3.2163, | |
| "step": 65950 | |
| }, | |
| { | |
| "epoch": 7.103648692282855, | |
| "grad_norm": 0.8232263922691345, | |
| "learning_rate": 0.00017412347807348346, | |
| "loss": 3.2163, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.103648692282855, | |
| "eval_accuracy": 0.3872667073100902, | |
| "eval_loss": 3.3580427169799805, | |
| "eval_runtime": 180.5751, | |
| "eval_samples_per_second": 99.742, | |
| "eval_steps_per_second": 6.236, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.109030244322462, | |
| "grad_norm": 0.7871417999267578, | |
| "learning_rate": 0.00017380023704342202, | |
| "loss": 3.217, | |
| "step": 66050 | |
| }, | |
| { | |
| "epoch": 7.114411796362071, | |
| "grad_norm": 0.8225372433662415, | |
| "learning_rate": 0.00017347699601336062, | |
| "loss": 3.2348, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 7.119793348401679, | |
| "grad_norm": 0.8037530779838562, | |
| "learning_rate": 0.00017315375498329919, | |
| "loss": 3.2072, | |
| "step": 66150 | |
| }, | |
| { | |
| "epoch": 7.125174900441287, | |
| "grad_norm": 1.7943295240402222, | |
| "learning_rate": 0.00017283051395323778, | |
| "loss": 3.2096, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 7.130556452480896, | |
| "grad_norm": 0.8043410181999207, | |
| "learning_rate": 0.00017250727292317638, | |
| "loss": 3.2008, | |
| "step": 66250 | |
| }, | |
| { | |
| "epoch": 7.135938004520503, | |
| "grad_norm": 0.8701448440551758, | |
| "learning_rate": 0.00017218403189311494, | |
| "loss": 3.2097, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 7.141319556560112, | |
| "grad_norm": 0.8197288513183594, | |
| "learning_rate": 0.0001718607908630535, | |
| "loss": 3.1995, | |
| "step": 66350 | |
| }, | |
| { | |
| "epoch": 7.1467011085997205, | |
| "grad_norm": 0.8066554665565491, | |
| "learning_rate": 0.00017153754983299213, | |
| "loss": 3.2064, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 7.152082660639328, | |
| "grad_norm": 0.7715657353401184, | |
| "learning_rate": 0.0001712143088029307, | |
| "loss": 3.2109, | |
| "step": 66450 | |
| }, | |
| { | |
| "epoch": 7.157464212678937, | |
| "grad_norm": 0.8049308061599731, | |
| "learning_rate": 0.00017089106777286927, | |
| "loss": 3.2056, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 7.162845764718545, | |
| "grad_norm": 0.8044945001602173, | |
| "learning_rate": 0.0001705678267428079, | |
| "loss": 3.2161, | |
| "step": 66550 | |
| }, | |
| { | |
| "epoch": 7.168227316758153, | |
| "grad_norm": 0.8120958805084229, | |
| "learning_rate": 0.00017024458571274646, | |
| "loss": 3.2157, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 7.1736088687977615, | |
| "grad_norm": 0.8076058030128479, | |
| "learning_rate": 0.00016992134468268505, | |
| "loss": 3.2389, | |
| "step": 66650 | |
| }, | |
| { | |
| "epoch": 7.178990420837369, | |
| "grad_norm": 0.8148431181907654, | |
| "learning_rate": 0.00016959810365262362, | |
| "loss": 3.2187, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 7.184371972876978, | |
| "grad_norm": 0.8567858338356018, | |
| "learning_rate": 0.0001692748626225622, | |
| "loss": 3.2188, | |
| "step": 66750 | |
| }, | |
| { | |
| "epoch": 7.189753524916586, | |
| "grad_norm": 0.8196995854377747, | |
| "learning_rate": 0.0001689516215925008, | |
| "loss": 3.2203, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 7.195135076956194, | |
| "grad_norm": 0.8134042620658875, | |
| "learning_rate": 0.00016862838056243938, | |
| "loss": 3.2023, | |
| "step": 66850 | |
| }, | |
| { | |
| "epoch": 7.2005166289958025, | |
| "grad_norm": 0.8222635984420776, | |
| "learning_rate": 0.00016830513953237794, | |
| "loss": 3.2136, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 7.205898181035411, | |
| "grad_norm": 0.8523157835006714, | |
| "learning_rate": 0.00016798189850231657, | |
| "loss": 3.2292, | |
| "step": 66950 | |
| }, | |
| { | |
| "epoch": 7.211279733075019, | |
| "grad_norm": 0.8117284178733826, | |
| "learning_rate": 0.00016765865747225513, | |
| "loss": 3.2243, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 7.211279733075019, | |
| "eval_accuracy": 0.38720662226312885, | |
| "eval_loss": 3.3582334518432617, | |
| "eval_runtime": 180.7195, | |
| "eval_samples_per_second": 99.663, | |
| "eval_steps_per_second": 6.231, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 7.216661285114627, | |
| "grad_norm": 0.849255383014679, | |
| "learning_rate": 0.0001673354164421937, | |
| "loss": 3.2088, | |
| "step": 67050 | |
| }, | |
| { | |
| "epoch": 7.222042837154235, | |
| "grad_norm": 0.8112828135490417, | |
| "learning_rate": 0.00016701217541213232, | |
| "loss": 3.2221, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 7.2274243891938434, | |
| "grad_norm": 0.8703665733337402, | |
| "learning_rate": 0.0001666889343820709, | |
| "loss": 3.2114, | |
| "step": 67150 | |
| }, | |
| { | |
| "epoch": 7.232805941233452, | |
| "grad_norm": 0.7933388352394104, | |
| "learning_rate": 0.00016636569335200946, | |
| "loss": 3.2238, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 7.23818749327306, | |
| "grad_norm": 0.8398449420928955, | |
| "learning_rate": 0.00016604245232194805, | |
| "loss": 3.2391, | |
| "step": 67250 | |
| }, | |
| { | |
| "epoch": 7.243569045312668, | |
| "grad_norm": 0.8231996297836304, | |
| "learning_rate": 0.00016571921129188665, | |
| "loss": 3.2372, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 7.248950597352277, | |
| "grad_norm": 0.8363311886787415, | |
| "learning_rate": 0.00016539597026182521, | |
| "loss": 3.2078, | |
| "step": 67350 | |
| }, | |
| { | |
| "epoch": 7.254332149391884, | |
| "grad_norm": 0.8070518970489502, | |
| "learning_rate": 0.0001650727292317638, | |
| "loss": 3.2155, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 7.259713701431493, | |
| "grad_norm": 0.8043374419212341, | |
| "learning_rate": 0.00016474948820170238, | |
| "loss": 3.229, | |
| "step": 67450 | |
| }, | |
| { | |
| "epoch": 7.265095253471101, | |
| "grad_norm": 0.8224925398826599, | |
| "learning_rate": 0.00016442624717164094, | |
| "loss": 3.2222, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 7.270476805510709, | |
| "grad_norm": 0.8394501209259033, | |
| "learning_rate": 0.00016410300614157957, | |
| "loss": 3.2113, | |
| "step": 67550 | |
| }, | |
| { | |
| "epoch": 7.275858357550318, | |
| "grad_norm": 0.8679465055465698, | |
| "learning_rate": 0.00016377976511151813, | |
| "loss": 3.2274, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 7.281239909589925, | |
| "grad_norm": 0.8839657306671143, | |
| "learning_rate": 0.00016345652408145675, | |
| "loss": 3.2073, | |
| "step": 67650 | |
| }, | |
| { | |
| "epoch": 7.286621461629534, | |
| "grad_norm": 0.9003349542617798, | |
| "learning_rate": 0.00016313328305139532, | |
| "loss": 3.2276, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 7.2920030136691425, | |
| "grad_norm": 0.8355953097343445, | |
| "learning_rate": 0.0001628100420213339, | |
| "loss": 3.229, | |
| "step": 67750 | |
| }, | |
| { | |
| "epoch": 7.29738456570875, | |
| "grad_norm": 0.8046534657478333, | |
| "learning_rate": 0.00016248680099127248, | |
| "loss": 3.2386, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 7.302766117748359, | |
| "grad_norm": 0.8797202110290527, | |
| "learning_rate": 0.00016216355996121105, | |
| "loss": 3.2217, | |
| "step": 67850 | |
| }, | |
| { | |
| "epoch": 7.308147669787967, | |
| "grad_norm": 0.9474117755889893, | |
| "learning_rate": 0.00016184031893114965, | |
| "loss": 3.2168, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 7.313529221827575, | |
| "grad_norm": 0.8707678318023682, | |
| "learning_rate": 0.00016151707790108824, | |
| "loss": 3.2345, | |
| "step": 67950 | |
| }, | |
| { | |
| "epoch": 7.3189107738671835, | |
| "grad_norm": 0.8038205504417419, | |
| "learning_rate": 0.0001611938368710268, | |
| "loss": 3.222, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 7.3189107738671835, | |
| "eval_accuracy": 0.387976102014631, | |
| "eval_loss": 3.352640390396118, | |
| "eval_runtime": 180.5346, | |
| "eval_samples_per_second": 99.765, | |
| "eval_steps_per_second": 6.237, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 7.324292325906791, | |
| "grad_norm": 0.8763945698738098, | |
| "learning_rate": 0.00016087059584096538, | |
| "loss": 3.2126, | |
| "step": 68050 | |
| }, | |
| { | |
| "epoch": 7.3296738779464, | |
| "grad_norm": 0.8443440198898315, | |
| "learning_rate": 0.000160547354810904, | |
| "loss": 3.2391, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 7.335055429986008, | |
| "grad_norm": 0.8131680488586426, | |
| "learning_rate": 0.00016023057860144378, | |
| "loss": 3.2449, | |
| "step": 68150 | |
| }, | |
| { | |
| "epoch": 7.340436982025616, | |
| "grad_norm": 0.8589426279067993, | |
| "learning_rate": 0.0001599073375713824, | |
| "loss": 3.2291, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 7.3458185340652244, | |
| "grad_norm": 0.8745540380477905, | |
| "learning_rate": 0.00015958409654132097, | |
| "loss": 3.2265, | |
| "step": 68250 | |
| }, | |
| { | |
| "epoch": 7.351200086104833, | |
| "grad_norm": 0.838469386100769, | |
| "learning_rate": 0.00015926085551125953, | |
| "loss": 3.2466, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 7.356581638144441, | |
| "grad_norm": 0.8351563811302185, | |
| "learning_rate": 0.00015893761448119813, | |
| "loss": 3.2189, | |
| "step": 68350 | |
| }, | |
| { | |
| "epoch": 7.361963190184049, | |
| "grad_norm": 0.8260790705680847, | |
| "learning_rate": 0.00015861437345113672, | |
| "loss": 3.2165, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 7.367344742223658, | |
| "grad_norm": 0.8453501462936401, | |
| "learning_rate": 0.00015829759724167653, | |
| "loss": 3.2279, | |
| "step": 68450 | |
| }, | |
| { | |
| "epoch": 7.372726294263265, | |
| "grad_norm": 0.8862749934196472, | |
| "learning_rate": 0.0001579743562116151, | |
| "loss": 3.2315, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 7.378107846302874, | |
| "grad_norm": 0.7972759008407593, | |
| "learning_rate": 0.00015765111518155372, | |
| "loss": 3.2317, | |
| "step": 68550 | |
| }, | |
| { | |
| "epoch": 7.383489398342482, | |
| "grad_norm": 0.8577588796615601, | |
| "learning_rate": 0.0001573278741514923, | |
| "loss": 3.2332, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 7.38887095038209, | |
| "grad_norm": 0.8090537190437317, | |
| "learning_rate": 0.00015700463312143085, | |
| "loss": 3.2207, | |
| "step": 68650 | |
| }, | |
| { | |
| "epoch": 7.394252502421699, | |
| "grad_norm": 0.8941483497619629, | |
| "learning_rate": 0.00015668139209136945, | |
| "loss": 3.2325, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 7.399634054461306, | |
| "grad_norm": 0.8350239396095276, | |
| "learning_rate": 0.00015635815106130804, | |
| "loss": 3.2347, | |
| "step": 68750 | |
| }, | |
| { | |
| "epoch": 7.405015606500915, | |
| "grad_norm": 0.834892749786377, | |
| "learning_rate": 0.0001560349100312466, | |
| "loss": 3.2314, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 7.4103971585405235, | |
| "grad_norm": 0.8487468957901001, | |
| "learning_rate": 0.0001557116690011852, | |
| "loss": 3.2407, | |
| "step": 68850 | |
| }, | |
| { | |
| "epoch": 7.415778710580131, | |
| "grad_norm": 0.8758741021156311, | |
| "learning_rate": 0.00015538842797112377, | |
| "loss": 3.2153, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 7.42116026261974, | |
| "grad_norm": 0.879677951335907, | |
| "learning_rate": 0.00015506518694106237, | |
| "loss": 3.2249, | |
| "step": 68950 | |
| }, | |
| { | |
| "epoch": 7.426541814659347, | |
| "grad_norm": 0.8545063138008118, | |
| "learning_rate": 0.00015474194591100096, | |
| "loss": 3.2349, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 7.426541814659347, | |
| "eval_accuracy": 0.3882562091594167, | |
| "eval_loss": 3.3482072353363037, | |
| "eval_runtime": 180.8861, | |
| "eval_samples_per_second": 99.571, | |
| "eval_steps_per_second": 6.225, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 7.431923366698956, | |
| "grad_norm": 0.8772327303886414, | |
| "learning_rate": 0.00015441870488093953, | |
| "loss": 3.2284, | |
| "step": 69050 | |
| }, | |
| { | |
| "epoch": 7.4373049187385645, | |
| "grad_norm": 0.9024936556816101, | |
| "learning_rate": 0.0001540954638508781, | |
| "loss": 3.218, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 7.442686470778172, | |
| "grad_norm": 0.8099319338798523, | |
| "learning_rate": 0.00015377222282081672, | |
| "loss": 3.2183, | |
| "step": 69150 | |
| }, | |
| { | |
| "epoch": 7.448068022817781, | |
| "grad_norm": 0.793427050113678, | |
| "learning_rate": 0.0001534489817907553, | |
| "loss": 3.2307, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 7.453449574857389, | |
| "grad_norm": 0.8657283186912537, | |
| "learning_rate": 0.00015312574076069388, | |
| "loss": 3.2321, | |
| "step": 69250 | |
| }, | |
| { | |
| "epoch": 7.458831126896997, | |
| "grad_norm": 0.8640968799591064, | |
| "learning_rate": 0.00015280249973063248, | |
| "loss": 3.2242, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 7.4642126789366054, | |
| "grad_norm": 0.8989497423171997, | |
| "learning_rate": 0.00015247925870057104, | |
| "loss": 3.2395, | |
| "step": 69350 | |
| }, | |
| { | |
| "epoch": 7.469594230976213, | |
| "grad_norm": 0.8708150386810303, | |
| "learning_rate": 0.00015215601767050964, | |
| "loss": 3.2317, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 7.474975783015822, | |
| "grad_norm": 0.8274281024932861, | |
| "learning_rate": 0.0001518327766404482, | |
| "loss": 3.2348, | |
| "step": 69450 | |
| }, | |
| { | |
| "epoch": 7.48035733505543, | |
| "grad_norm": 0.841109573841095, | |
| "learning_rate": 0.0001515095356103868, | |
| "loss": 3.2263, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 7.485738887095038, | |
| "grad_norm": 0.8123463988304138, | |
| "learning_rate": 0.0001511862945803254, | |
| "loss": 3.2116, | |
| "step": 69550 | |
| }, | |
| { | |
| "epoch": 7.491120439134646, | |
| "grad_norm": 0.8069713115692139, | |
| "learning_rate": 0.00015086305355026396, | |
| "loss": 3.201, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 7.496501991174255, | |
| "grad_norm": 0.8293700218200684, | |
| "learning_rate": 0.00015053981252020253, | |
| "loss": 3.2439, | |
| "step": 69650 | |
| }, | |
| { | |
| "epoch": 7.501883543213863, | |
| "grad_norm": 0.8899844884872437, | |
| "learning_rate": 0.00015021657149014115, | |
| "loss": 3.2287, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 7.507265095253471, | |
| "grad_norm": 0.8449057936668396, | |
| "learning_rate": 0.00014989333046007972, | |
| "loss": 3.2416, | |
| "step": 69750 | |
| }, | |
| { | |
| "epoch": 7.51264664729308, | |
| "grad_norm": 0.8326901197433472, | |
| "learning_rate": 0.00014957008943001832, | |
| "loss": 3.2332, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 7.518028199332687, | |
| "grad_norm": 0.8048696517944336, | |
| "learning_rate": 0.00014924684839995688, | |
| "loss": 3.2153, | |
| "step": 69850 | |
| }, | |
| { | |
| "epoch": 7.523409751372296, | |
| "grad_norm": 0.8521336913108826, | |
| "learning_rate": 0.00014892360736989548, | |
| "loss": 3.2298, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 7.528791303411904, | |
| "grad_norm": 0.8536204695701599, | |
| "learning_rate": 0.00014860036633983407, | |
| "loss": 3.2237, | |
| "step": 69950 | |
| }, | |
| { | |
| "epoch": 7.534172855451512, | |
| "grad_norm": 0.8090736865997314, | |
| "learning_rate": 0.00014827712530977264, | |
| "loss": 3.2364, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 7.534172855451512, | |
| "eval_accuracy": 0.38876535659171535, | |
| "eval_loss": 3.3461689949035645, | |
| "eval_runtime": 180.6754, | |
| "eval_samples_per_second": 99.687, | |
| "eval_steps_per_second": 6.232, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 7.539554407491121, | |
| "grad_norm": 0.8323525786399841, | |
| "learning_rate": 0.00014795388427971123, | |
| "loss": 3.2362, | |
| "step": 70050 | |
| }, | |
| { | |
| "epoch": 7.544935959530728, | |
| "grad_norm": 0.8688218593597412, | |
| "learning_rate": 0.0001476306432496498, | |
| "loss": 3.237, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 7.550317511570337, | |
| "grad_norm": 0.8065937161445618, | |
| "learning_rate": 0.0001473074022195884, | |
| "loss": 3.2411, | |
| "step": 70150 | |
| }, | |
| { | |
| "epoch": 7.5556990636099455, | |
| "grad_norm": 0.8267635703086853, | |
| "learning_rate": 0.00014698416118952696, | |
| "loss": 3.2375, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 7.561080615649553, | |
| "grad_norm": 0.8378524780273438, | |
| "learning_rate": 0.00014666092015946556, | |
| "loss": 3.2159, | |
| "step": 70250 | |
| }, | |
| { | |
| "epoch": 7.566462167689162, | |
| "grad_norm": 0.8994044661521912, | |
| "learning_rate": 0.00014633767912940415, | |
| "loss": 3.2369, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 7.57184371972877, | |
| "grad_norm": 0.8720497488975525, | |
| "learning_rate": 0.00014601443809934272, | |
| "loss": 3.2369, | |
| "step": 70350 | |
| }, | |
| { | |
| "epoch": 7.577225271768378, | |
| "grad_norm": 0.8321914076805115, | |
| "learning_rate": 0.00014569119706928132, | |
| "loss": 3.2346, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 7.5826068238079865, | |
| "grad_norm": 0.844092607498169, | |
| "learning_rate": 0.0001453679560392199, | |
| "loss": 3.2344, | |
| "step": 70450 | |
| }, | |
| { | |
| "epoch": 7.587988375847594, | |
| "grad_norm": 0.8993640542030334, | |
| "learning_rate": 0.00014504471500915848, | |
| "loss": 3.2362, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 7.593369927887203, | |
| "grad_norm": 0.8442127108573914, | |
| "learning_rate": 0.00014472147397909707, | |
| "loss": 3.2303, | |
| "step": 70550 | |
| }, | |
| { | |
| "epoch": 7.598751479926811, | |
| "grad_norm": 0.8459310531616211, | |
| "learning_rate": 0.00014439823294903564, | |
| "loss": 3.2299, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 7.604133031966419, | |
| "grad_norm": 0.9453602433204651, | |
| "learning_rate": 0.00014407499191897423, | |
| "loss": 3.2242, | |
| "step": 70650 | |
| }, | |
| { | |
| "epoch": 7.609514584006027, | |
| "grad_norm": 0.8440732955932617, | |
| "learning_rate": 0.0001437517508889128, | |
| "loss": 3.2356, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 7.614896136045635, | |
| "grad_norm": 0.8589253425598145, | |
| "learning_rate": 0.0001434285098588514, | |
| "loss": 3.2333, | |
| "step": 70750 | |
| }, | |
| { | |
| "epoch": 7.620277688085244, | |
| "grad_norm": 0.8273172974586487, | |
| "learning_rate": 0.00014310526882879, | |
| "loss": 3.2155, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 7.625659240124852, | |
| "grad_norm": 0.8450290560722351, | |
| "learning_rate": 0.00014278202779872856, | |
| "loss": 3.2351, | |
| "step": 70850 | |
| }, | |
| { | |
| "epoch": 7.63104079216446, | |
| "grad_norm": 0.8752638697624207, | |
| "learning_rate": 0.00014245878676866715, | |
| "loss": 3.2436, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 7.636422344204068, | |
| "grad_norm": 0.8159819841384888, | |
| "learning_rate": 0.00014213554573860575, | |
| "loss": 3.2332, | |
| "step": 70950 | |
| }, | |
| { | |
| "epoch": 7.641803896243677, | |
| "grad_norm": 0.8391739130020142, | |
| "learning_rate": 0.00014181230470854434, | |
| "loss": 3.2297, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 7.641803896243677, | |
| "eval_accuracy": 0.3891160881135805, | |
| "eval_loss": 3.3415868282318115, | |
| "eval_runtime": 180.8754, | |
| "eval_samples_per_second": 99.577, | |
| "eval_steps_per_second": 6.225, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 7.647185448283285, | |
| "grad_norm": 0.8811625838279724, | |
| "learning_rate": 0.0001414890636784829, | |
| "loss": 3.2345, | |
| "step": 71050 | |
| }, | |
| { | |
| "epoch": 7.652567000322893, | |
| "grad_norm": 0.8388746976852417, | |
| "learning_rate": 0.0001411658226484215, | |
| "loss": 3.227, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 7.657948552362502, | |
| "grad_norm": 0.8501401543617249, | |
| "learning_rate": 0.00014084258161836007, | |
| "loss": 3.2577, | |
| "step": 71150 | |
| }, | |
| { | |
| "epoch": 7.663330104402109, | |
| "grad_norm": 0.8466740846633911, | |
| "learning_rate": 0.00014051934058829867, | |
| "loss": 3.2052, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 7.668711656441718, | |
| "grad_norm": 0.8789371252059937, | |
| "learning_rate": 0.00014019609955823723, | |
| "loss": 3.2209, | |
| "step": 71250 | |
| }, | |
| { | |
| "epoch": 7.674093208481326, | |
| "grad_norm": 0.8286100625991821, | |
| "learning_rate": 0.00013987285852817583, | |
| "loss": 3.2018, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 7.679474760520934, | |
| "grad_norm": 0.8479146361351013, | |
| "learning_rate": 0.0001395496174981144, | |
| "loss": 3.2163, | |
| "step": 71350 | |
| }, | |
| { | |
| "epoch": 7.684856312560543, | |
| "grad_norm": 0.9216192960739136, | |
| "learning_rate": 0.000139226376468053, | |
| "loss": 3.226, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 7.69023786460015, | |
| "grad_norm": 0.9375202655792236, | |
| "learning_rate": 0.00013890313543799159, | |
| "loss": 3.2309, | |
| "step": 71450 | |
| }, | |
| { | |
| "epoch": 7.695619416639759, | |
| "grad_norm": 0.8177657127380371, | |
| "learning_rate": 0.00013857989440793018, | |
| "loss": 3.219, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 7.7010009686793675, | |
| "grad_norm": 0.846137285232544, | |
| "learning_rate": 0.00013825665337786875, | |
| "loss": 3.2353, | |
| "step": 71550 | |
| }, | |
| { | |
| "epoch": 7.706382520718975, | |
| "grad_norm": 0.8408653140068054, | |
| "learning_rate": 0.00013793341234780734, | |
| "loss": 3.244, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 7.711764072758584, | |
| "grad_norm": 0.8572009801864624, | |
| "learning_rate": 0.00013761017131774594, | |
| "loss": 3.2277, | |
| "step": 71650 | |
| }, | |
| { | |
| "epoch": 7.717145624798192, | |
| "grad_norm": 0.8709561824798584, | |
| "learning_rate": 0.0001372869302876845, | |
| "loss": 3.2533, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 7.7225271768378, | |
| "grad_norm": 0.8801485896110535, | |
| "learning_rate": 0.0001369636892576231, | |
| "loss": 3.2471, | |
| "step": 71750 | |
| }, | |
| { | |
| "epoch": 7.727908728877408, | |
| "grad_norm": 0.8573904633522034, | |
| "learning_rate": 0.00013664044822756167, | |
| "loss": 3.2491, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 7.733290280917016, | |
| "grad_norm": 0.8685466051101685, | |
| "learning_rate": 0.00013631720719750026, | |
| "loss": 3.2406, | |
| "step": 71850 | |
| }, | |
| { | |
| "epoch": 7.738671832956625, | |
| "grad_norm": 0.8761990070343018, | |
| "learning_rate": 0.00013599396616743883, | |
| "loss": 3.2162, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 7.744053384996233, | |
| "grad_norm": 0.8514412641525269, | |
| "learning_rate": 0.00013567072513737742, | |
| "loss": 3.2311, | |
| "step": 71950 | |
| }, | |
| { | |
| "epoch": 7.749434937035841, | |
| "grad_norm": 0.8694790005683899, | |
| "learning_rate": 0.00013534748410731602, | |
| "loss": 3.2361, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 7.749434937035841, | |
| "eval_accuracy": 0.38934903990505476, | |
| "eval_loss": 3.3384485244750977, | |
| "eval_runtime": 180.5632, | |
| "eval_samples_per_second": 99.749, | |
| "eval_steps_per_second": 6.236, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 7.754816489075449, | |
| "grad_norm": 0.9411042928695679, | |
| "learning_rate": 0.0001350242430772546, | |
| "loss": 3.245, | |
| "step": 72050 | |
| }, | |
| { | |
| "epoch": 7.760198041115058, | |
| "grad_norm": 0.9091503024101257, | |
| "learning_rate": 0.00013470100204719318, | |
| "loss": 3.2592, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 7.765579593154666, | |
| "grad_norm": 0.8613893389701843, | |
| "learning_rate": 0.00013437776101713178, | |
| "loss": 3.2299, | |
| "step": 72150 | |
| }, | |
| { | |
| "epoch": 7.770961145194274, | |
| "grad_norm": 0.8697505593299866, | |
| "learning_rate": 0.00013405451998707034, | |
| "loss": 3.231, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 7.776342697233883, | |
| "grad_norm": 0.8704033493995667, | |
| "learning_rate": 0.00013373127895700894, | |
| "loss": 3.2344, | |
| "step": 72250 | |
| }, | |
| { | |
| "epoch": 7.78172424927349, | |
| "grad_norm": 0.8434908986091614, | |
| "learning_rate": 0.00013340803792694753, | |
| "loss": 3.2269, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 7.787105801313099, | |
| "grad_norm": 0.8213037252426147, | |
| "learning_rate": 0.0001330847968968861, | |
| "loss": 3.2196, | |
| "step": 72350 | |
| }, | |
| { | |
| "epoch": 7.792487353352707, | |
| "grad_norm": 0.8428940176963806, | |
| "learning_rate": 0.00013276155586682467, | |
| "loss": 3.2337, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 7.797868905392315, | |
| "grad_norm": 0.8586910367012024, | |
| "learning_rate": 0.00013243831483676326, | |
| "loss": 3.2219, | |
| "step": 72450 | |
| }, | |
| { | |
| "epoch": 7.803250457431924, | |
| "grad_norm": 0.9171772003173828, | |
| "learning_rate": 0.00013211507380670186, | |
| "loss": 3.2315, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 7.808632009471531, | |
| "grad_norm": 0.9385636448860168, | |
| "learning_rate": 0.00013179183277664042, | |
| "loss": 3.233, | |
| "step": 72550 | |
| }, | |
| { | |
| "epoch": 7.81401356151114, | |
| "grad_norm": 0.8959430456161499, | |
| "learning_rate": 0.00013146859174657902, | |
| "loss": 3.2515, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 7.819395113550748, | |
| "grad_norm": 0.8392729759216309, | |
| "learning_rate": 0.00013114535071651761, | |
| "loss": 3.2207, | |
| "step": 72650 | |
| }, | |
| { | |
| "epoch": 7.824776665590356, | |
| "grad_norm": 0.8786283135414124, | |
| "learning_rate": 0.00013082210968645618, | |
| "loss": 3.232, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 7.830158217629965, | |
| "grad_norm": 0.8381286263465881, | |
| "learning_rate": 0.00013049886865639478, | |
| "loss": 3.2142, | |
| "step": 72750 | |
| }, | |
| { | |
| "epoch": 7.835539769669572, | |
| "grad_norm": 0.8869178891181946, | |
| "learning_rate": 0.00013017562762633337, | |
| "loss": 3.2404, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 7.840921321709181, | |
| "grad_norm": 0.8395768404006958, | |
| "learning_rate": 0.00012985238659627194, | |
| "loss": 3.2477, | |
| "step": 72850 | |
| }, | |
| { | |
| "epoch": 7.846302873748789, | |
| "grad_norm": 0.8443187475204468, | |
| "learning_rate": 0.00012952914556621053, | |
| "loss": 3.2534, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 7.851684425788397, | |
| "grad_norm": 0.8238486051559448, | |
| "learning_rate": 0.0001292059045361491, | |
| "loss": 3.2415, | |
| "step": 72950 | |
| }, | |
| { | |
| "epoch": 7.857065977828006, | |
| "grad_norm": 0.8638015985488892, | |
| "learning_rate": 0.0001288826635060877, | |
| "loss": 3.2416, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 7.857065977828006, | |
| "eval_accuracy": 0.3898458009081426, | |
| "eval_loss": 3.3356986045837402, | |
| "eval_runtime": 180.5467, | |
| "eval_samples_per_second": 99.758, | |
| "eval_steps_per_second": 6.237, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 7.862447529867614, | |
| "grad_norm": 0.8598248958587646, | |
| "learning_rate": 0.00012855942247602626, | |
| "loss": 3.2224, | |
| "step": 73050 | |
| }, | |
| { | |
| "epoch": 7.867829081907222, | |
| "grad_norm": 0.8552663326263428, | |
| "learning_rate": 0.00012823618144596486, | |
| "loss": 3.2338, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 7.87321063394683, | |
| "grad_norm": 0.8366514444351196, | |
| "learning_rate": 0.00012791294041590345, | |
| "loss": 3.2301, | |
| "step": 73150 | |
| }, | |
| { | |
| "epoch": 7.878592185986438, | |
| "grad_norm": 0.870034396648407, | |
| "learning_rate": 0.00012758969938584202, | |
| "loss": 3.2463, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 7.883973738026047, | |
| "grad_norm": 0.9482511878013611, | |
| "learning_rate": 0.00012726645835578061, | |
| "loss": 3.2368, | |
| "step": 73250 | |
| }, | |
| { | |
| "epoch": 7.889355290065655, | |
| "grad_norm": 0.8701103329658508, | |
| "learning_rate": 0.00012694968214632045, | |
| "loss": 3.2315, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 7.894736842105263, | |
| "grad_norm": 0.8550585508346558, | |
| "learning_rate": 0.00012662644111625902, | |
| "loss": 3.2292, | |
| "step": 73350 | |
| }, | |
| { | |
| "epoch": 7.900118394144871, | |
| "grad_norm": 0.84943026304245, | |
| "learning_rate": 0.0001263032000861976, | |
| "loss": 3.2401, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 7.90549994618448, | |
| "grad_norm": 0.8325279355049133, | |
| "learning_rate": 0.00012597995905613618, | |
| "loss": 3.2095, | |
| "step": 73450 | |
| }, | |
| { | |
| "epoch": 7.910881498224088, | |
| "grad_norm": 0.8745725750923157, | |
| "learning_rate": 0.00012565671802607477, | |
| "loss": 3.2367, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 7.916263050263696, | |
| "grad_norm": 0.8808631896972656, | |
| "learning_rate": 0.00012533347699601334, | |
| "loss": 3.2522, | |
| "step": 73550 | |
| }, | |
| { | |
| "epoch": 7.921644602303305, | |
| "grad_norm": 0.8490099906921387, | |
| "learning_rate": 0.00012501023596595193, | |
| "loss": 3.2407, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 7.927026154342912, | |
| "grad_norm": 0.8633183836936951, | |
| "learning_rate": 0.0001246869949358905, | |
| "loss": 3.2352, | |
| "step": 73650 | |
| }, | |
| { | |
| "epoch": 7.932407706382521, | |
| "grad_norm": 0.8482357263565063, | |
| "learning_rate": 0.0001243637539058291, | |
| "loss": 3.2172, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 7.937789258422129, | |
| "grad_norm": 0.8842774033546448, | |
| "learning_rate": 0.0001240405128757677, | |
| "loss": 3.2256, | |
| "step": 73750 | |
| }, | |
| { | |
| "epoch": 7.943170810461737, | |
| "grad_norm": 0.9809737205505371, | |
| "learning_rate": 0.00012371727184570629, | |
| "loss": 3.231, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 7.948552362501346, | |
| "grad_norm": 0.8404791355133057, | |
| "learning_rate": 0.00012339403081564485, | |
| "loss": 3.2285, | |
| "step": 73850 | |
| }, | |
| { | |
| "epoch": 7.953933914540953, | |
| "grad_norm": 0.8805235624313354, | |
| "learning_rate": 0.00012307078978558345, | |
| "loss": 3.2412, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 7.959315466580562, | |
| "grad_norm": 0.8662030100822449, | |
| "learning_rate": 0.00012274754875552202, | |
| "loss": 3.2325, | |
| "step": 73950 | |
| }, | |
| { | |
| "epoch": 7.96469701862017, | |
| "grad_norm": 0.8386152386665344, | |
| "learning_rate": 0.0001224243077254606, | |
| "loss": 3.2293, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 7.96469701862017, | |
| "eval_accuracy": 0.3901281897635724, | |
| "eval_loss": 3.3309998512268066, | |
| "eval_runtime": 180.7262, | |
| "eval_samples_per_second": 99.659, | |
| "eval_steps_per_second": 6.23, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 7.970078570659778, | |
| "grad_norm": 0.8542754650115967, | |
| "learning_rate": 0.00012210106669539918, | |
| "loss": 3.2285, | |
| "step": 74050 | |
| }, | |
| { | |
| "epoch": 7.975460122699387, | |
| "grad_norm": 0.9284147024154663, | |
| "learning_rate": 0.00012177782566533779, | |
| "loss": 3.2351, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 7.980841674738995, | |
| "grad_norm": 0.8983561396598816, | |
| "learning_rate": 0.00012145458463527635, | |
| "loss": 3.2408, | |
| "step": 74150 | |
| }, | |
| { | |
| "epoch": 7.986223226778603, | |
| "grad_norm": 0.8538508415222168, | |
| "learning_rate": 0.00012113134360521495, | |
| "loss": 3.238, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 7.991604778818211, | |
| "grad_norm": 0.8690817356109619, | |
| "learning_rate": 0.00012080810257515353, | |
| "loss": 3.2251, | |
| "step": 74250 | |
| }, | |
| { | |
| "epoch": 7.996986330857819, | |
| "grad_norm": 0.8762375712394714, | |
| "learning_rate": 0.00012048486154509212, | |
| "loss": 3.2278, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 8.002367882897428, | |
| "grad_norm": 0.823405385017395, | |
| "learning_rate": 0.00012016162051503069, | |
| "loss": 3.1888, | |
| "step": 74350 | |
| }, | |
| { | |
| "epoch": 8.007749434937036, | |
| "grad_norm": 0.8836029171943665, | |
| "learning_rate": 0.00011983837948496929, | |
| "loss": 3.1696, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 8.013130986976645, | |
| "grad_norm": 0.8643078207969666, | |
| "learning_rate": 0.00011951513845490787, | |
| "loss": 3.1547, | |
| "step": 74450 | |
| }, | |
| { | |
| "epoch": 8.018512539016251, | |
| "grad_norm": 0.8536393046379089, | |
| "learning_rate": 0.00011919189742484645, | |
| "loss": 3.1705, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 8.02389409105586, | |
| "grad_norm": 0.8264943957328796, | |
| "learning_rate": 0.00011886865639478503, | |
| "loss": 3.1485, | |
| "step": 74550 | |
| }, | |
| { | |
| "epoch": 8.029275643095469, | |
| "grad_norm": 0.88083416223526, | |
| "learning_rate": 0.00011854541536472362, | |
| "loss": 3.1529, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 8.034657195135077, | |
| "grad_norm": 0.8759968876838684, | |
| "learning_rate": 0.00011822217433466219, | |
| "loss": 3.176, | |
| "step": 74650 | |
| }, | |
| { | |
| "epoch": 8.040038747174686, | |
| "grad_norm": 0.8657451868057251, | |
| "learning_rate": 0.00011789893330460079, | |
| "loss": 3.1421, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 8.045420299214294, | |
| "grad_norm": 0.8699697256088257, | |
| "learning_rate": 0.00011757569227453937, | |
| "loss": 3.1628, | |
| "step": 74750 | |
| }, | |
| { | |
| "epoch": 8.050801851253901, | |
| "grad_norm": 0.859023928642273, | |
| "learning_rate": 0.00011725245124447796, | |
| "loss": 3.17, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 8.05618340329351, | |
| "grad_norm": 0.8847795724868774, | |
| "learning_rate": 0.00011692921021441653, | |
| "loss": 3.1528, | |
| "step": 74850 | |
| }, | |
| { | |
| "epoch": 8.061564955333118, | |
| "grad_norm": 0.8535637259483337, | |
| "learning_rate": 0.00011660596918435512, | |
| "loss": 3.175, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 8.066946507372727, | |
| "grad_norm": 0.8353862166404724, | |
| "learning_rate": 0.00011628272815429372, | |
| "loss": 3.168, | |
| "step": 74950 | |
| }, | |
| { | |
| "epoch": 8.072328059412335, | |
| "grad_norm": 0.8807953000068665, | |
| "learning_rate": 0.00011595948712423229, | |
| "loss": 3.1452, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 8.072328059412335, | |
| "eval_accuracy": 0.3901538318450966, | |
| "eval_loss": 3.3356988430023193, | |
| "eval_runtime": 180.8043, | |
| "eval_samples_per_second": 99.616, | |
| "eval_steps_per_second": 6.228, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 8.077709611451942, | |
| "grad_norm": 0.8582302927970886, | |
| "learning_rate": 0.00011563624609417088, | |
| "loss": 3.1795, | |
| "step": 75050 | |
| }, | |
| { | |
| "epoch": 8.08309116349155, | |
| "grad_norm": 0.8993620872497559, | |
| "learning_rate": 0.00011531300506410946, | |
| "loss": 3.172, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 8.088472715531159, | |
| "grad_norm": 0.863032877445221, | |
| "learning_rate": 0.00011498976403404804, | |
| "loss": 3.1669, | |
| "step": 75150 | |
| }, | |
| { | |
| "epoch": 8.093854267570768, | |
| "grad_norm": 0.8714480996131897, | |
| "learning_rate": 0.00011466652300398663, | |
| "loss": 3.1687, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 8.099235819610376, | |
| "grad_norm": 0.8861761093139648, | |
| "learning_rate": 0.00011434328197392522, | |
| "loss": 3.1669, | |
| "step": 75250 | |
| }, | |
| { | |
| "epoch": 8.104617371649983, | |
| "grad_norm": 0.8841901421546936, | |
| "learning_rate": 0.0001140200409438638, | |
| "loss": 3.1596, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 8.109998923689592, | |
| "grad_norm": 0.9461728930473328, | |
| "learning_rate": 0.00011370326473440361, | |
| "loss": 3.1537, | |
| "step": 75350 | |
| }, | |
| { | |
| "epoch": 8.1153804757292, | |
| "grad_norm": 0.8345040082931519, | |
| "learning_rate": 0.0001133800237043422, | |
| "loss": 3.1692, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 8.120762027768809, | |
| "grad_norm": 0.8404425382614136, | |
| "learning_rate": 0.00011305678267428077, | |
| "loss": 3.1557, | |
| "step": 75450 | |
| }, | |
| { | |
| "epoch": 8.126143579808417, | |
| "grad_norm": 0.9137583374977112, | |
| "learning_rate": 0.00011273354164421936, | |
| "loss": 3.1746, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 8.131525131848026, | |
| "grad_norm": 0.892432689666748, | |
| "learning_rate": 0.00011241030061415795, | |
| "loss": 3.1794, | |
| "step": 75550 | |
| }, | |
| { | |
| "epoch": 8.136906683887632, | |
| "grad_norm": 0.8653923273086548, | |
| "learning_rate": 0.00011208705958409654, | |
| "loss": 3.1651, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 8.142288235927241, | |
| "grad_norm": 0.8782545328140259, | |
| "learning_rate": 0.00011176381855403511, | |
| "loss": 3.1522, | |
| "step": 75650 | |
| }, | |
| { | |
| "epoch": 8.14766978796685, | |
| "grad_norm": 0.9366098642349243, | |
| "learning_rate": 0.0001114405775239737, | |
| "loss": 3.1548, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 8.153051340006458, | |
| "grad_norm": 0.8603706359863281, | |
| "learning_rate": 0.00011111733649391228, | |
| "loss": 3.1867, | |
| "step": 75750 | |
| }, | |
| { | |
| "epoch": 8.158432892046067, | |
| "grad_norm": 0.8969858288764954, | |
| "learning_rate": 0.00011079409546385086, | |
| "loss": 3.1751, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 8.163814444085673, | |
| "grad_norm": 0.8933687806129456, | |
| "learning_rate": 0.00011047085443378945, | |
| "loss": 3.1702, | |
| "step": 75850 | |
| }, | |
| { | |
| "epoch": 8.169195996125282, | |
| "grad_norm": 0.8683410286903381, | |
| "learning_rate": 0.00011014761340372804, | |
| "loss": 3.1628, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 8.17457754816489, | |
| "grad_norm": 0.8602153658866882, | |
| "learning_rate": 0.00010982437237366661, | |
| "loss": 3.1739, | |
| "step": 75950 | |
| }, | |
| { | |
| "epoch": 8.1799591002045, | |
| "grad_norm": 0.8595947623252869, | |
| "learning_rate": 0.0001095011313436052, | |
| "loss": 3.1608, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 8.1799591002045, | |
| "eval_accuracy": 0.39043980624582436, | |
| "eval_loss": 3.3351192474365234, | |
| "eval_runtime": 179.5075, | |
| "eval_samples_per_second": 100.336, | |
| "eval_steps_per_second": 6.273, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 8.185340652244108, | |
| "grad_norm": 0.8788470029830933, | |
| "learning_rate": 0.0001091778903135438, | |
| "loss": 3.1627, | |
| "step": 76050 | |
| }, | |
| { | |
| "epoch": 8.190722204283716, | |
| "grad_norm": 0.9367756843566895, | |
| "learning_rate": 0.00010885464928348238, | |
| "loss": 3.1624, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 8.196103756323323, | |
| "grad_norm": 0.902297854423523, | |
| "learning_rate": 0.00010853140825342096, | |
| "loss": 3.1812, | |
| "step": 76150 | |
| }, | |
| { | |
| "epoch": 8.201485308362932, | |
| "grad_norm": 0.8547227382659912, | |
| "learning_rate": 0.00010820816722335954, | |
| "loss": 3.1807, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 8.20686686040254, | |
| "grad_norm": 0.8972384929656982, | |
| "learning_rate": 0.00010788492619329814, | |
| "loss": 3.1558, | |
| "step": 76250 | |
| }, | |
| { | |
| "epoch": 8.212248412442149, | |
| "grad_norm": 0.8367764353752136, | |
| "learning_rate": 0.0001075616851632367, | |
| "loss": 3.1766, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 8.217629964481757, | |
| "grad_norm": 0.9024211764335632, | |
| "learning_rate": 0.0001072384441331753, | |
| "loss": 3.1712, | |
| "step": 76350 | |
| }, | |
| { | |
| "epoch": 8.223011516521364, | |
| "grad_norm": 0.9114934802055359, | |
| "learning_rate": 0.00010691520310311388, | |
| "loss": 3.1711, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 8.228393068560973, | |
| "grad_norm": 0.8747788071632385, | |
| "learning_rate": 0.00010659196207305246, | |
| "loss": 3.1774, | |
| "step": 76450 | |
| }, | |
| { | |
| "epoch": 8.233774620600581, | |
| "grad_norm": 0.8949354887008667, | |
| "learning_rate": 0.00010626872104299104, | |
| "loss": 3.1705, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 8.23915617264019, | |
| "grad_norm": 0.8727163076400757, | |
| "learning_rate": 0.00010594548001292964, | |
| "loss": 3.1873, | |
| "step": 76550 | |
| }, | |
| { | |
| "epoch": 8.244537724679798, | |
| "grad_norm": 0.9465581178665161, | |
| "learning_rate": 0.00010562223898286823, | |
| "loss": 3.1834, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 8.249919276719407, | |
| "grad_norm": 0.8704432249069214, | |
| "learning_rate": 0.0001052989979528068, | |
| "loss": 3.1673, | |
| "step": 76650 | |
| }, | |
| { | |
| "epoch": 8.255300828759013, | |
| "grad_norm": 0.8336291909217834, | |
| "learning_rate": 0.00010497575692274539, | |
| "loss": 3.1781, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 8.260682380798622, | |
| "grad_norm": 0.8544026613235474, | |
| "learning_rate": 0.00010465251589268397, | |
| "loss": 3.1756, | |
| "step": 76750 | |
| }, | |
| { | |
| "epoch": 8.26606393283823, | |
| "grad_norm": 0.8753527402877808, | |
| "learning_rate": 0.00010432927486262254, | |
| "loss": 3.1786, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 8.27144548487784, | |
| "grad_norm": 0.8853304386138916, | |
| "learning_rate": 0.00010400603383256114, | |
| "loss": 3.186, | |
| "step": 76850 | |
| }, | |
| { | |
| "epoch": 8.276827036917448, | |
| "grad_norm": 0.8864724040031433, | |
| "learning_rate": 0.00010368279280249973, | |
| "loss": 3.173, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 8.282208588957054, | |
| "grad_norm": 0.8877735733985901, | |
| "learning_rate": 0.0001033595517724383, | |
| "loss": 3.1759, | |
| "step": 76950 | |
| }, | |
| { | |
| "epoch": 8.287590140996663, | |
| "grad_norm": 0.8727827072143555, | |
| "learning_rate": 0.00010303631074237689, | |
| "loss": 3.184, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 8.287590140996663, | |
| "eval_accuracy": 0.3906263632542018, | |
| "eval_loss": 3.3312065601348877, | |
| "eval_runtime": 179.6044, | |
| "eval_samples_per_second": 100.281, | |
| "eval_steps_per_second": 6.269, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 8.292971693036272, | |
| "grad_norm": 0.9259955883026123, | |
| "learning_rate": 0.00010271306971231547, | |
| "loss": 3.1869, | |
| "step": 77050 | |
| }, | |
| { | |
| "epoch": 8.29835324507588, | |
| "grad_norm": 0.8535556793212891, | |
| "learning_rate": 0.00010238982868225407, | |
| "loss": 3.1768, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 8.303734797115489, | |
| "grad_norm": 0.8989574909210205, | |
| "learning_rate": 0.00010206658765219264, | |
| "loss": 3.1815, | |
| "step": 77150 | |
| }, | |
| { | |
| "epoch": 8.309116349155097, | |
| "grad_norm": 0.8857195377349854, | |
| "learning_rate": 0.00010174334662213123, | |
| "loss": 3.1588, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 8.314497901194704, | |
| "grad_norm": 0.8919908404350281, | |
| "learning_rate": 0.00010142010559206981, | |
| "loss": 3.1797, | |
| "step": 77250 | |
| }, | |
| { | |
| "epoch": 8.319879453234313, | |
| "grad_norm": 0.8413748145103455, | |
| "learning_rate": 0.00010109686456200839, | |
| "loss": 3.1667, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 8.325261005273921, | |
| "grad_norm": 0.9747196435928345, | |
| "learning_rate": 0.00010077362353194697, | |
| "loss": 3.1803, | |
| "step": 77350 | |
| }, | |
| { | |
| "epoch": 8.33064255731353, | |
| "grad_norm": 0.9089459180831909, | |
| "learning_rate": 0.00010045038250188557, | |
| "loss": 3.1852, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 8.336024109353138, | |
| "grad_norm": 0.8968145847320557, | |
| "learning_rate": 0.00010012714147182414, | |
| "loss": 3.1821, | |
| "step": 77450 | |
| }, | |
| { | |
| "epoch": 8.341405661392745, | |
| "grad_norm": 0.8776057958602905, | |
| "learning_rate": 9.980390044176273e-05, | |
| "loss": 3.1656, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 8.346787213432354, | |
| "grad_norm": 0.9172366261482239, | |
| "learning_rate": 9.948065941170133e-05, | |
| "loss": 3.1746, | |
| "step": 77550 | |
| }, | |
| { | |
| "epoch": 8.352168765471962, | |
| "grad_norm": 0.9139503240585327, | |
| "learning_rate": 9.91574183816399e-05, | |
| "loss": 3.1718, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 8.35755031751157, | |
| "grad_norm": 0.8708044290542603, | |
| "learning_rate": 9.883417735157849e-05, | |
| "loss": 3.1651, | |
| "step": 77650 | |
| }, | |
| { | |
| "epoch": 8.36293186955118, | |
| "grad_norm": 0.8740552067756653, | |
| "learning_rate": 9.851093632151707e-05, | |
| "loss": 3.1701, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 8.368313421590786, | |
| "grad_norm": 0.8782268762588501, | |
| "learning_rate": 9.818769529145566e-05, | |
| "loss": 3.1765, | |
| "step": 77750 | |
| }, | |
| { | |
| "epoch": 8.373694973630395, | |
| "grad_norm": 0.9119528532028198, | |
| "learning_rate": 9.786445426139423e-05, | |
| "loss": 3.1792, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 8.379076525670003, | |
| "grad_norm": 0.8632680177688599, | |
| "learning_rate": 9.754121323133283e-05, | |
| "loss": 3.1724, | |
| "step": 77850 | |
| }, | |
| { | |
| "epoch": 8.384458077709612, | |
| "grad_norm": 0.8710095882415771, | |
| "learning_rate": 9.72179722012714e-05, | |
| "loss": 3.184, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 8.38983962974922, | |
| "grad_norm": 1.0001767873764038, | |
| "learning_rate": 9.689473117120999e-05, | |
| "loss": 3.1691, | |
| "step": 77950 | |
| }, | |
| { | |
| "epoch": 8.395221181788829, | |
| "grad_norm": 0.8792982697486877, | |
| "learning_rate": 9.657149014114857e-05, | |
| "loss": 3.1742, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 8.395221181788829, | |
| "eval_accuracy": 0.3911284482487925, | |
| "eval_loss": 3.327723264694214, | |
| "eval_runtime": 179.8658, | |
| "eval_samples_per_second": 100.136, | |
| "eval_steps_per_second": 6.26, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 8.400602733828435, | |
| "grad_norm": 0.8982104063034058, | |
| "learning_rate": 9.624824911108716e-05, | |
| "loss": 3.1786, | |
| "step": 78050 | |
| }, | |
| { | |
| "epoch": 8.405984285868044, | |
| "grad_norm": 0.9011202454566956, | |
| "learning_rate": 9.592500808102574e-05, | |
| "loss": 3.1867, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 8.411365837907653, | |
| "grad_norm": 0.9007724523544312, | |
| "learning_rate": 9.560176705096433e-05, | |
| "loss": 3.1988, | |
| "step": 78150 | |
| }, | |
| { | |
| "epoch": 8.416747389947261, | |
| "grad_norm": 0.8967268466949463, | |
| "learning_rate": 9.52785260209029e-05, | |
| "loss": 3.1872, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 8.42212894198687, | |
| "grad_norm": 0.9627910256385803, | |
| "learning_rate": 9.49552849908415e-05, | |
| "loss": 3.175, | |
| "step": 78250 | |
| }, | |
| { | |
| "epoch": 8.427510494026476, | |
| "grad_norm": 0.873896062374115, | |
| "learning_rate": 9.463204396078007e-05, | |
| "loss": 3.1978, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 8.432892046066085, | |
| "grad_norm": 0.8684766888618469, | |
| "learning_rate": 9.430880293071866e-05, | |
| "loss": 3.1839, | |
| "step": 78350 | |
| }, | |
| { | |
| "epoch": 8.438273598105694, | |
| "grad_norm": 0.8813990950584412, | |
| "learning_rate": 9.398556190065726e-05, | |
| "loss": 3.1705, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 8.443655150145302, | |
| "grad_norm": 0.9459818005561829, | |
| "learning_rate": 9.366232087059583e-05, | |
| "loss": 3.1823, | |
| "step": 78450 | |
| }, | |
| { | |
| "epoch": 8.44903670218491, | |
| "grad_norm": 0.8727448582649231, | |
| "learning_rate": 9.333907984053442e-05, | |
| "loss": 3.156, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 8.45441825422452, | |
| "grad_norm": 0.8859150409698486, | |
| "learning_rate": 9.3015838810473e-05, | |
| "loss": 3.1686, | |
| "step": 78550 | |
| }, | |
| { | |
| "epoch": 8.459799806264126, | |
| "grad_norm": 0.903968334197998, | |
| "learning_rate": 9.269906260101281e-05, | |
| "loss": 3.1785, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 8.465181358303735, | |
| "grad_norm": 0.9025602340698242, | |
| "learning_rate": 9.23758215709514e-05, | |
| "loss": 3.1681, | |
| "step": 78650 | |
| }, | |
| { | |
| "epoch": 8.470562910343343, | |
| "grad_norm": 0.8712466359138489, | |
| "learning_rate": 9.205258054088998e-05, | |
| "loss": 3.1776, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 8.475944462382952, | |
| "grad_norm": 0.8721148371696472, | |
| "learning_rate": 9.172933951082856e-05, | |
| "loss": 3.1735, | |
| "step": 78750 | |
| }, | |
| { | |
| "epoch": 8.48132601442256, | |
| "grad_norm": 0.8949872851371765, | |
| "learning_rate": 9.140609848076715e-05, | |
| "loss": 3.1736, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 8.486707566462167, | |
| "grad_norm": 0.9402435421943665, | |
| "learning_rate": 9.108285745070574e-05, | |
| "loss": 3.1829, | |
| "step": 78850 | |
| }, | |
| { | |
| "epoch": 8.492089118501776, | |
| "grad_norm": 0.9432632327079773, | |
| "learning_rate": 9.075961642064432e-05, | |
| "loss": 3.1734, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 8.497470670541384, | |
| "grad_norm": 0.9873622059822083, | |
| "learning_rate": 9.04363753905829e-05, | |
| "loss": 3.1805, | |
| "step": 78950 | |
| }, | |
| { | |
| "epoch": 8.502852222580993, | |
| "grad_norm": 0.8836618065834045, | |
| "learning_rate": 9.011313436052148e-05, | |
| "loss": 3.1759, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 8.502852222580993, | |
| "eval_accuracy": 0.39123579730195324, | |
| "eval_loss": 3.325312852859497, | |
| "eval_runtime": 179.5604, | |
| "eval_samples_per_second": 100.306, | |
| "eval_steps_per_second": 6.271, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 8.508233774620601, | |
| "grad_norm": 0.8848540186882019, | |
| "learning_rate": 8.978989333046008e-05, | |
| "loss": 3.197, | |
| "step": 79050 | |
| }, | |
| { | |
| "epoch": 8.513615326660208, | |
| "grad_norm": 0.8550401329994202, | |
| "learning_rate": 8.946665230039865e-05, | |
| "loss": 3.1957, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 8.518996878699816, | |
| "grad_norm": 0.9009631872177124, | |
| "learning_rate": 8.914341127033724e-05, | |
| "loss": 3.176, | |
| "step": 79150 | |
| }, | |
| { | |
| "epoch": 8.524378430739425, | |
| "grad_norm": 0.9329746961593628, | |
| "learning_rate": 8.882017024027582e-05, | |
| "loss": 3.166, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 8.529759982779034, | |
| "grad_norm": 0.9039963483810425, | |
| "learning_rate": 8.84969292102144e-05, | |
| "loss": 3.1773, | |
| "step": 79250 | |
| }, | |
| { | |
| "epoch": 8.535141534818642, | |
| "grad_norm": 0.8915432691574097, | |
| "learning_rate": 8.817368818015298e-05, | |
| "loss": 3.1771, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 8.54052308685825, | |
| "grad_norm": 0.8851172924041748, | |
| "learning_rate": 8.785044715009158e-05, | |
| "loss": 3.1684, | |
| "step": 79350 | |
| }, | |
| { | |
| "epoch": 8.545904638897857, | |
| "grad_norm": 0.8741281032562256, | |
| "learning_rate": 8.752720612003017e-05, | |
| "loss": 3.174, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 8.551286190937466, | |
| "grad_norm": 0.8948149681091309, | |
| "learning_rate": 8.720396508996874e-05, | |
| "loss": 3.1767, | |
| "step": 79450 | |
| }, | |
| { | |
| "epoch": 8.556667742977075, | |
| "grad_norm": 0.8773640990257263, | |
| "learning_rate": 8.688072405990734e-05, | |
| "loss": 3.1672, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 8.562049295016683, | |
| "grad_norm": 0.9167670607566833, | |
| "learning_rate": 8.655748302984592e-05, | |
| "loss": 3.1816, | |
| "step": 79550 | |
| }, | |
| { | |
| "epoch": 8.567430847056292, | |
| "grad_norm": 0.9075756669044495, | |
| "learning_rate": 8.62342419997845e-05, | |
| "loss": 3.181, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 8.572812399095898, | |
| "grad_norm": 0.8566796183586121, | |
| "learning_rate": 8.591100096972308e-05, | |
| "loss": 3.1908, | |
| "step": 79650 | |
| }, | |
| { | |
| "epoch": 8.578193951135507, | |
| "grad_norm": 0.8454053401947021, | |
| "learning_rate": 8.558775993966167e-05, | |
| "loss": 3.1871, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 8.583575503175116, | |
| "grad_norm": 0.9006174206733704, | |
| "learning_rate": 8.526451890960024e-05, | |
| "loss": 3.1881, | |
| "step": 79750 | |
| }, | |
| { | |
| "epoch": 8.588957055214724, | |
| "grad_norm": 0.9350295662879944, | |
| "learning_rate": 8.494127787953884e-05, | |
| "loss": 3.1843, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 8.594338607254333, | |
| "grad_norm": 0.9077459573745728, | |
| "learning_rate": 8.461803684947742e-05, | |
| "loss": 3.1737, | |
| "step": 79850 | |
| }, | |
| { | |
| "epoch": 8.599720159293941, | |
| "grad_norm": 0.8846340775489807, | |
| "learning_rate": 8.429479581941601e-05, | |
| "loss": 3.1663, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 8.605101711333548, | |
| "grad_norm": 0.9019478559494019, | |
| "learning_rate": 8.397155478935458e-05, | |
| "loss": 3.1775, | |
| "step": 79950 | |
| }, | |
| { | |
| "epoch": 8.610483263373157, | |
| "grad_norm": 0.8935966491699219, | |
| "learning_rate": 8.364831375929317e-05, | |
| "loss": 3.1707, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 8.610483263373157, | |
| "eval_accuracy": 0.3917088719754975, | |
| "eval_loss": 3.32266902923584, | |
| "eval_runtime": 179.6899, | |
| "eval_samples_per_second": 100.234, | |
| "eval_steps_per_second": 6.266, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 8.615864815412765, | |
| "grad_norm": 0.946051299571991, | |
| "learning_rate": 8.332507272923177e-05, | |
| "loss": 3.1791, | |
| "step": 80050 | |
| }, | |
| { | |
| "epoch": 8.621246367452374, | |
| "grad_norm": 0.9058233499526978, | |
| "learning_rate": 8.300183169917034e-05, | |
| "loss": 3.177, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 8.626627919491982, | |
| "grad_norm": 0.8954179286956787, | |
| "learning_rate": 8.267859066910892e-05, | |
| "loss": 3.1708, | |
| "step": 80150 | |
| }, | |
| { | |
| "epoch": 8.632009471531589, | |
| "grad_norm": 0.9015591740608215, | |
| "learning_rate": 8.235534963904751e-05, | |
| "loss": 3.1996, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 8.637391023571197, | |
| "grad_norm": 0.8927049040794373, | |
| "learning_rate": 8.203210860898608e-05, | |
| "loss": 3.1693, | |
| "step": 80250 | |
| }, | |
| { | |
| "epoch": 8.642772575610806, | |
| "grad_norm": 0.901568591594696, | |
| "learning_rate": 8.170886757892467e-05, | |
| "loss": 3.1794, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 8.648154127650415, | |
| "grad_norm": 0.9400429725646973, | |
| "learning_rate": 8.138562654886327e-05, | |
| "loss": 3.1847, | |
| "step": 80350 | |
| }, | |
| { | |
| "epoch": 8.653535679690023, | |
| "grad_norm": 0.9230552911758423, | |
| "learning_rate": 8.106238551880185e-05, | |
| "loss": 3.1876, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 8.658917231729632, | |
| "grad_norm": 0.8878161311149597, | |
| "learning_rate": 8.073914448874043e-05, | |
| "loss": 3.2039, | |
| "step": 80450 | |
| }, | |
| { | |
| "epoch": 8.664298783769238, | |
| "grad_norm": 0.9797596335411072, | |
| "learning_rate": 8.041590345867901e-05, | |
| "loss": 3.2002, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 8.669680335808847, | |
| "grad_norm": 0.8710808753967285, | |
| "learning_rate": 8.00926624286176e-05, | |
| "loss": 3.1984, | |
| "step": 80550 | |
| }, | |
| { | |
| "epoch": 8.675061887848456, | |
| "grad_norm": 0.8963496088981628, | |
| "learning_rate": 7.976942139855617e-05, | |
| "loss": 3.1836, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 8.680443439888064, | |
| "grad_norm": 0.9148070812225342, | |
| "learning_rate": 7.944618036849477e-05, | |
| "loss": 3.1782, | |
| "step": 80650 | |
| }, | |
| { | |
| "epoch": 8.685824991927673, | |
| "grad_norm": 0.9107878804206848, | |
| "learning_rate": 7.912293933843335e-05, | |
| "loss": 3.1832, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 8.69120654396728, | |
| "grad_norm": 0.931254506111145, | |
| "learning_rate": 7.879969830837193e-05, | |
| "loss": 3.172, | |
| "step": 80750 | |
| }, | |
| { | |
| "epoch": 8.696588096006888, | |
| "grad_norm": 0.8768410682678223, | |
| "learning_rate": 7.847645727831051e-05, | |
| "loss": 3.1846, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 8.701969648046497, | |
| "grad_norm": 0.8722245693206787, | |
| "learning_rate": 7.815321624824911e-05, | |
| "loss": 3.1826, | |
| "step": 80850 | |
| }, | |
| { | |
| "epoch": 8.707351200086105, | |
| "grad_norm": 0.9657986760139465, | |
| "learning_rate": 7.78299752181877e-05, | |
| "loss": 3.1677, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 8.712732752125714, | |
| "grad_norm": 0.8934928774833679, | |
| "learning_rate": 7.750673418812627e-05, | |
| "loss": 3.1852, | |
| "step": 80950 | |
| }, | |
| { | |
| "epoch": 8.718114304165322, | |
| "grad_norm": 0.9235027432441711, | |
| "learning_rate": 7.718349315806486e-05, | |
| "loss": 3.1837, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 8.718114304165322, | |
| "eval_accuracy": 0.39210328195826405, | |
| "eval_loss": 3.3185155391693115, | |
| "eval_runtime": 179.7373, | |
| "eval_samples_per_second": 100.207, | |
| "eval_steps_per_second": 6.265, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 8.723495856204929, | |
| "grad_norm": 0.8857280611991882, | |
| "learning_rate": 7.686025212800344e-05, | |
| "loss": 3.1725, | |
| "step": 81050 | |
| }, | |
| { | |
| "epoch": 8.728877408244538, | |
| "grad_norm": 0.9040824770927429, | |
| "learning_rate": 7.653701109794203e-05, | |
| "loss": 3.198, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 8.734258960284146, | |
| "grad_norm": 0.8779809474945068, | |
| "learning_rate": 7.621377006788061e-05, | |
| "loss": 3.1761, | |
| "step": 81150 | |
| }, | |
| { | |
| "epoch": 8.739640512323755, | |
| "grad_norm": 0.9397569894790649, | |
| "learning_rate": 7.58905290378192e-05, | |
| "loss": 3.1935, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 8.745022064363363, | |
| "grad_norm": 0.9214434623718262, | |
| "learning_rate": 7.556728800775777e-05, | |
| "loss": 3.1911, | |
| "step": 81250 | |
| }, | |
| { | |
| "epoch": 8.75040361640297, | |
| "grad_norm": 0.8609477281570435, | |
| "learning_rate": 7.524404697769636e-05, | |
| "loss": 3.1853, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 8.755785168442578, | |
| "grad_norm": 0.9056183695793152, | |
| "learning_rate": 7.492080594763495e-05, | |
| "loss": 3.1735, | |
| "step": 81350 | |
| }, | |
| { | |
| "epoch": 8.761166720482187, | |
| "grad_norm": 0.8735660314559937, | |
| "learning_rate": 7.459756491757353e-05, | |
| "loss": 3.176, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 8.766548272521796, | |
| "grad_norm": 0.846092700958252, | |
| "learning_rate": 7.427432388751212e-05, | |
| "loss": 3.1834, | |
| "step": 81450 | |
| }, | |
| { | |
| "epoch": 8.771929824561404, | |
| "grad_norm": 0.9211810827255249, | |
| "learning_rate": 7.39510828574507e-05, | |
| "loss": 3.1885, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 8.777311376601011, | |
| "grad_norm": 0.9464531540870667, | |
| "learning_rate": 7.362784182738928e-05, | |
| "loss": 3.1756, | |
| "step": 81550 | |
| }, | |
| { | |
| "epoch": 8.78269292864062, | |
| "grad_norm": 0.9161049127578735, | |
| "learning_rate": 7.330460079732786e-05, | |
| "loss": 3.1791, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 8.788074480680228, | |
| "grad_norm": 0.8961696624755859, | |
| "learning_rate": 7.298135976726645e-05, | |
| "loss": 3.1933, | |
| "step": 81650 | |
| }, | |
| { | |
| "epoch": 8.793456032719837, | |
| "grad_norm": 0.942209780216217, | |
| "learning_rate": 7.265811873720504e-05, | |
| "loss": 3.167, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 8.798837584759445, | |
| "grad_norm": 0.8983950018882751, | |
| "learning_rate": 7.233487770714362e-05, | |
| "loss": 3.1915, | |
| "step": 81750 | |
| }, | |
| { | |
| "epoch": 8.804219136799054, | |
| "grad_norm": 0.969327986240387, | |
| "learning_rate": 7.20116366770822e-05, | |
| "loss": 3.1829, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 8.80960068883866, | |
| "grad_norm": 0.8701090812683105, | |
| "learning_rate": 7.16883956470208e-05, | |
| "loss": 3.1765, | |
| "step": 81850 | |
| }, | |
| { | |
| "epoch": 8.814982240878269, | |
| "grad_norm": 0.9157487154006958, | |
| "learning_rate": 7.136515461695938e-05, | |
| "loss": 3.1855, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 8.820363792917878, | |
| "grad_norm": 0.9211909174919128, | |
| "learning_rate": 7.104191358689796e-05, | |
| "loss": 3.1932, | |
| "step": 81950 | |
| }, | |
| { | |
| "epoch": 8.825745344957486, | |
| "grad_norm": 0.9057191610336304, | |
| "learning_rate": 7.071867255683654e-05, | |
| "loss": 3.1755, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 8.825745344957486, | |
| "eval_accuracy": 0.39230526767671114, | |
| "eval_loss": 3.315615653991699, | |
| "eval_runtime": 179.8786, | |
| "eval_samples_per_second": 100.129, | |
| "eval_steps_per_second": 6.26, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 8.831126896997095, | |
| "grad_norm": 0.8885180354118347, | |
| "learning_rate": 7.039543152677512e-05, | |
| "loss": 3.1984, | |
| "step": 82050 | |
| }, | |
| { | |
| "epoch": 8.836508449036701, | |
| "grad_norm": 0.8651913404464722, | |
| "learning_rate": 7.007219049671372e-05, | |
| "loss": 3.19, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 8.84189000107631, | |
| "grad_norm": 0.8910512924194336, | |
| "learning_rate": 6.97489494666523e-05, | |
| "loss": 3.1838, | |
| "step": 82150 | |
| }, | |
| { | |
| "epoch": 8.847271553115919, | |
| "grad_norm": 0.9161734580993652, | |
| "learning_rate": 6.942570843659088e-05, | |
| "loss": 3.161, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 8.852653105155527, | |
| "grad_norm": 0.9313191175460815, | |
| "learning_rate": 6.910246740652946e-05, | |
| "loss": 3.2002, | |
| "step": 82250 | |
| }, | |
| { | |
| "epoch": 8.858034657195136, | |
| "grad_norm": 0.9104998707771301, | |
| "learning_rate": 6.877922637646804e-05, | |
| "loss": 3.173, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 8.863416209234742, | |
| "grad_norm": 0.9300284385681152, | |
| "learning_rate": 6.845598534640663e-05, | |
| "loss": 3.1875, | |
| "step": 82350 | |
| }, | |
| { | |
| "epoch": 8.868797761274351, | |
| "grad_norm": 0.9142300486564636, | |
| "learning_rate": 6.813274431634522e-05, | |
| "loss": 3.1742, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 8.87417931331396, | |
| "grad_norm": 0.9559773206710815, | |
| "learning_rate": 6.78095032862838e-05, | |
| "loss": 3.1745, | |
| "step": 82450 | |
| }, | |
| { | |
| "epoch": 8.879560865353568, | |
| "grad_norm": 0.9085149168968201, | |
| "learning_rate": 6.748626225622238e-05, | |
| "loss": 3.1852, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 8.884942417393177, | |
| "grad_norm": 0.8920027017593384, | |
| "learning_rate": 6.716302122616096e-05, | |
| "loss": 3.1765, | |
| "step": 82550 | |
| }, | |
| { | |
| "epoch": 8.890323969432785, | |
| "grad_norm": 0.8755592703819275, | |
| "learning_rate": 6.684624501670078e-05, | |
| "loss": 3.1659, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 8.895705521472392, | |
| "grad_norm": 0.8625423908233643, | |
| "learning_rate": 6.652300398663936e-05, | |
| "loss": 3.1941, | |
| "step": 82650 | |
| }, | |
| { | |
| "epoch": 8.901087073512, | |
| "grad_norm": 0.9189068675041199, | |
| "learning_rate": 6.619976295657794e-05, | |
| "loss": 3.1668, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 8.906468625551609, | |
| "grad_norm": 0.8962160348892212, | |
| "learning_rate": 6.587652192651654e-05, | |
| "loss": 3.1717, | |
| "step": 82750 | |
| }, | |
| { | |
| "epoch": 8.911850177591218, | |
| "grad_norm": 0.9272757768630981, | |
| "learning_rate": 6.555328089645512e-05, | |
| "loss": 3.1858, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 8.917231729630826, | |
| "grad_norm": 0.8833206295967102, | |
| "learning_rate": 6.52300398663937e-05, | |
| "loss": 3.188, | |
| "step": 82850 | |
| }, | |
| { | |
| "epoch": 8.922613281670433, | |
| "grad_norm": 0.9083338379859924, | |
| "learning_rate": 6.490679883633229e-05, | |
| "loss": 3.1798, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 8.927994833710041, | |
| "grad_norm": 0.9264318346977234, | |
| "learning_rate": 6.458355780627087e-05, | |
| "loss": 3.1807, | |
| "step": 82950 | |
| }, | |
| { | |
| "epoch": 8.93337638574965, | |
| "grad_norm": 0.9590030908584595, | |
| "learning_rate": 6.426031677620946e-05, | |
| "loss": 3.1712, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 8.93337638574965, | |
| "eval_accuracy": 0.39272173419570405, | |
| "eval_loss": 3.3121018409729004, | |
| "eval_runtime": 179.6448, | |
| "eval_samples_per_second": 100.259, | |
| "eval_steps_per_second": 6.268, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 8.938757937789259, | |
| "grad_norm": 0.8892170786857605, | |
| "learning_rate": 6.393707574614804e-05, | |
| "loss": 3.1905, | |
| "step": 83050 | |
| }, | |
| { | |
| "epoch": 8.944139489828867, | |
| "grad_norm": 0.8800289034843445, | |
| "learning_rate": 6.361383471608662e-05, | |
| "loss": 3.176, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 8.949521041868476, | |
| "grad_norm": 0.9177758097648621, | |
| "learning_rate": 6.329059368602521e-05, | |
| "loss": 3.1671, | |
| "step": 83150 | |
| }, | |
| { | |
| "epoch": 8.954902593908082, | |
| "grad_norm": 0.9445570707321167, | |
| "learning_rate": 6.29673526559638e-05, | |
| "loss": 3.1747, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 8.960284145947691, | |
| "grad_norm": 0.91263747215271, | |
| "learning_rate": 6.264411162590237e-05, | |
| "loss": 3.1787, | |
| "step": 83250 | |
| }, | |
| { | |
| "epoch": 8.9656656979873, | |
| "grad_norm": 0.9258759021759033, | |
| "learning_rate": 6.232087059584096e-05, | |
| "loss": 3.1714, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 8.971047250026908, | |
| "grad_norm": 0.9283280372619629, | |
| "learning_rate": 6.199762956577954e-05, | |
| "loss": 3.1852, | |
| "step": 83350 | |
| }, | |
| { | |
| "epoch": 8.976428802066517, | |
| "grad_norm": 0.9237959980964661, | |
| "learning_rate": 6.167438853571813e-05, | |
| "loss": 3.1738, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 8.981810354106123, | |
| "grad_norm": 0.9457531571388245, | |
| "learning_rate": 6.135114750565671e-05, | |
| "loss": 3.1898, | |
| "step": 83450 | |
| }, | |
| { | |
| "epoch": 8.987191906145732, | |
| "grad_norm": 0.8861507773399353, | |
| "learning_rate": 6.10279064755953e-05, | |
| "loss": 3.1828, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 8.99257345818534, | |
| "grad_norm": 0.9238635897636414, | |
| "learning_rate": 6.070466544553388e-05, | |
| "loss": 3.1701, | |
| "step": 83550 | |
| }, | |
| { | |
| "epoch": 8.997955010224949, | |
| "grad_norm": 0.9327380061149597, | |
| "learning_rate": 6.038142441547246e-05, | |
| "loss": 3.1951, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 9.003336562264558, | |
| "grad_norm": 0.9319394826889038, | |
| "learning_rate": 6.005818338541105e-05, | |
| "loss": 3.1399, | |
| "step": 83650 | |
| }, | |
| { | |
| "epoch": 9.008718114304166, | |
| "grad_norm": 0.8817294239997864, | |
| "learning_rate": 5.973494235534963e-05, | |
| "loss": 3.1182, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 9.014099666343773, | |
| "grad_norm": 0.9379280209541321, | |
| "learning_rate": 5.941170132528822e-05, | |
| "loss": 3.1158, | |
| "step": 83750 | |
| }, | |
| { | |
| "epoch": 9.019481218383381, | |
| "grad_norm": 0.8813740015029907, | |
| "learning_rate": 5.90884602952268e-05, | |
| "loss": 3.1219, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 9.02486277042299, | |
| "grad_norm": 0.9050074815750122, | |
| "learning_rate": 5.876521926516538e-05, | |
| "loss": 3.101, | |
| "step": 83850 | |
| }, | |
| { | |
| "epoch": 9.030244322462599, | |
| "grad_norm": 0.9405961036682129, | |
| "learning_rate": 5.844197823510397e-05, | |
| "loss": 3.1274, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 9.035625874502207, | |
| "grad_norm": 0.9838739633560181, | |
| "learning_rate": 5.811873720504255e-05, | |
| "loss": 3.1278, | |
| "step": 83950 | |
| }, | |
| { | |
| "epoch": 9.041007426541814, | |
| "grad_norm": 0.9542596340179443, | |
| "learning_rate": 5.7795496174981145e-05, | |
| "loss": 3.1222, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 9.041007426541814, | |
| "eval_accuracy": 0.3926494800253074, | |
| "eval_loss": 3.314357280731201, | |
| "eval_runtime": 179.6808, | |
| "eval_samples_per_second": 100.239, | |
| "eval_steps_per_second": 6.267, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 9.046388978581422, | |
| "grad_norm": 0.9362724423408508, | |
| "learning_rate": 5.7472255144919726e-05, | |
| "loss": 3.1182, | |
| "step": 84050 | |
| }, | |
| { | |
| "epoch": 9.051770530621031, | |
| "grad_norm": 0.9181835651397705, | |
| "learning_rate": 5.714901411485831e-05, | |
| "loss": 3.1153, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 9.05715208266064, | |
| "grad_norm": 0.9418762922286987, | |
| "learning_rate": 5.6825773084796895e-05, | |
| "loss": 3.1096, | |
| "step": 84150 | |
| }, | |
| { | |
| "epoch": 9.062533634700248, | |
| "grad_norm": 0.9246426224708557, | |
| "learning_rate": 5.6502532054735476e-05, | |
| "loss": 3.1255, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 9.067915186739857, | |
| "grad_norm": 0.9008504152297974, | |
| "learning_rate": 5.6179291024674064e-05, | |
| "loss": 3.1114, | |
| "step": 84250 | |
| }, | |
| { | |
| "epoch": 9.073296738779463, | |
| "grad_norm": 0.8827772736549377, | |
| "learning_rate": 5.5856049994612645e-05, | |
| "loss": 3.1209, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 9.078678290819072, | |
| "grad_norm": 0.8775843381881714, | |
| "learning_rate": 5.5532808964551227e-05, | |
| "loss": 3.1176, | |
| "step": 84350 | |
| }, | |
| { | |
| "epoch": 9.08405984285868, | |
| "grad_norm": 0.9226499795913696, | |
| "learning_rate": 5.5209567934489814e-05, | |
| "loss": 3.1154, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 9.089441394898289, | |
| "grad_norm": 0.8536249399185181, | |
| "learning_rate": 5.4886326904428396e-05, | |
| "loss": 3.1195, | |
| "step": 84450 | |
| }, | |
| { | |
| "epoch": 9.094822946937898, | |
| "grad_norm": 0.8758836984634399, | |
| "learning_rate": 5.4563085874366983e-05, | |
| "loss": 3.1041, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 9.100204498977504, | |
| "grad_norm": 0.9015653729438782, | |
| "learning_rate": 5.4239844844305565e-05, | |
| "loss": 3.1224, | |
| "step": 84550 | |
| }, | |
| { | |
| "epoch": 9.105586051017113, | |
| "grad_norm": 0.9079980850219727, | |
| "learning_rate": 5.392306863484538e-05, | |
| "loss": 3.1171, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 9.110967603056721, | |
| "grad_norm": 0.9092751145362854, | |
| "learning_rate": 5.359982760478396e-05, | |
| "loss": 3.1239, | |
| "step": 84650 | |
| }, | |
| { | |
| "epoch": 9.11634915509633, | |
| "grad_norm": 0.9043470621109009, | |
| "learning_rate": 5.327658657472255e-05, | |
| "loss": 3.1177, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 9.121730707135939, | |
| "grad_norm": 0.924089252948761, | |
| "learning_rate": 5.295334554466113e-05, | |
| "loss": 3.1266, | |
| "step": 84750 | |
| }, | |
| { | |
| "epoch": 9.127112259175545, | |
| "grad_norm": 0.8986655473709106, | |
| "learning_rate": 5.2630104514599716e-05, | |
| "loss": 3.1482, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 9.132493811215154, | |
| "grad_norm": 0.898731529712677, | |
| "learning_rate": 5.23068634845383e-05, | |
| "loss": 3.1273, | |
| "step": 84850 | |
| }, | |
| { | |
| "epoch": 9.137875363254762, | |
| "grad_norm": 0.9368207454681396, | |
| "learning_rate": 5.198362245447688e-05, | |
| "loss": 3.1113, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 9.143256915294371, | |
| "grad_norm": 0.9111401438713074, | |
| "learning_rate": 5.166038142441547e-05, | |
| "loss": 3.1205, | |
| "step": 84950 | |
| }, | |
| { | |
| "epoch": 9.14863846733398, | |
| "grad_norm": 0.8901679515838623, | |
| "learning_rate": 5.1337140394354054e-05, | |
| "loss": 3.1353, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 9.14863846733398, | |
| "eval_accuracy": 0.39298576071309327, | |
| "eval_loss": 3.314081907272339, | |
| "eval_runtime": 179.6507, | |
| "eval_samples_per_second": 100.256, | |
| "eval_steps_per_second": 6.268, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 9.154020019373588, | |
| "grad_norm": 0.9217543601989746, | |
| "learning_rate": 5.101389936429264e-05, | |
| "loss": 3.1371, | |
| "step": 85050 | |
| }, | |
| { | |
| "epoch": 9.159401571413195, | |
| "grad_norm": 0.8988335728645325, | |
| "learning_rate": 5.069065833423122e-05, | |
| "loss": 3.1121, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 9.164783123452803, | |
| "grad_norm": 0.960673451423645, | |
| "learning_rate": 5.0367417304169804e-05, | |
| "loss": 3.1377, | |
| "step": 85150 | |
| }, | |
| { | |
| "epoch": 9.170164675492412, | |
| "grad_norm": 0.912464439868927, | |
| "learning_rate": 5.004417627410839e-05, | |
| "loss": 3.1354, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 9.17554622753202, | |
| "grad_norm": 0.8949055075645447, | |
| "learning_rate": 4.972093524404697e-05, | |
| "loss": 3.1273, | |
| "step": 85250 | |
| }, | |
| { | |
| "epoch": 9.180927779571629, | |
| "grad_norm": 0.9239495396614075, | |
| "learning_rate": 4.939769421398556e-05, | |
| "loss": 3.1125, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 9.186309331611236, | |
| "grad_norm": 0.9031249284744263, | |
| "learning_rate": 4.907445318392414e-05, | |
| "loss": 3.1272, | |
| "step": 85350 | |
| }, | |
| { | |
| "epoch": 9.191690883650844, | |
| "grad_norm": 0.9332590103149414, | |
| "learning_rate": 4.875121215386272e-05, | |
| "loss": 3.1247, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 9.197072435690453, | |
| "grad_norm": 0.9094883799552917, | |
| "learning_rate": 4.842797112380131e-05, | |
| "loss": 3.1337, | |
| "step": 85450 | |
| }, | |
| { | |
| "epoch": 9.202453987730062, | |
| "grad_norm": 0.9142782092094421, | |
| "learning_rate": 4.810473009373989e-05, | |
| "loss": 3.1185, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 9.20783553976967, | |
| "grad_norm": 0.8732017874717712, | |
| "learning_rate": 4.778148906367848e-05, | |
| "loss": 3.107, | |
| "step": 85550 | |
| }, | |
| { | |
| "epoch": 9.213217091809279, | |
| "grad_norm": 0.8603156208992004, | |
| "learning_rate": 4.745824803361706e-05, | |
| "loss": 3.1289, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 9.218598643848885, | |
| "grad_norm": 0.9196754693984985, | |
| "learning_rate": 4.713500700355564e-05, | |
| "loss": 3.1223, | |
| "step": 85650 | |
| }, | |
| { | |
| "epoch": 9.223980195888494, | |
| "grad_norm": 0.8952550292015076, | |
| "learning_rate": 4.681176597349424e-05, | |
| "loss": 3.0968, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 9.229361747928102, | |
| "grad_norm": 0.9112910628318787, | |
| "learning_rate": 4.648852494343282e-05, | |
| "loss": 3.1297, | |
| "step": 85750 | |
| }, | |
| { | |
| "epoch": 9.234743299967711, | |
| "grad_norm": 0.8979288339614868, | |
| "learning_rate": 4.6165283913371406e-05, | |
| "loss": 3.1185, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 9.24012485200732, | |
| "grad_norm": 0.9608327150344849, | |
| "learning_rate": 4.584204288330999e-05, | |
| "loss": 3.1162, | |
| "step": 85850 | |
| }, | |
| { | |
| "epoch": 9.245506404046926, | |
| "grad_norm": 0.8818651437759399, | |
| "learning_rate": 4.551880185324857e-05, | |
| "loss": 3.1501, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 9.250887956086535, | |
| "grad_norm": 0.9698681235313416, | |
| "learning_rate": 4.5195560823187156e-05, | |
| "loss": 3.1213, | |
| "step": 85950 | |
| }, | |
| { | |
| "epoch": 9.256269508126143, | |
| "grad_norm": 0.958239734172821, | |
| "learning_rate": 4.487231979312574e-05, | |
| "loss": 3.139, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 9.256269508126143, | |
| "eval_accuracy": 0.3931503698381322, | |
| "eval_loss": 3.3128864765167236, | |
| "eval_runtime": 179.9322, | |
| "eval_samples_per_second": 100.099, | |
| "eval_steps_per_second": 6.258, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 9.261651060165752, | |
| "grad_norm": 0.9176580905914307, | |
| "learning_rate": 4.4549078763064325e-05, | |
| "loss": 3.1481, | |
| "step": 86050 | |
| }, | |
| { | |
| "epoch": 9.26703261220536, | |
| "grad_norm": 0.9287602305412292, | |
| "learning_rate": 4.4225837733002906e-05, | |
| "loss": 3.1331, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 9.272414164244967, | |
| "grad_norm": 0.9146842360496521, | |
| "learning_rate": 4.390259670294149e-05, | |
| "loss": 3.1283, | |
| "step": 86150 | |
| }, | |
| { | |
| "epoch": 9.277795716284576, | |
| "grad_norm": 0.9413586258888245, | |
| "learning_rate": 4.3579355672880075e-05, | |
| "loss": 3.1207, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 9.283177268324184, | |
| "grad_norm": 0.9226080775260925, | |
| "learning_rate": 4.3256114642818656e-05, | |
| "loss": 3.1259, | |
| "step": 86250 | |
| }, | |
| { | |
| "epoch": 9.288558820363793, | |
| "grad_norm": 0.9166672229766846, | |
| "learning_rate": 4.2932873612757244e-05, | |
| "loss": 3.146, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 9.293940372403402, | |
| "grad_norm": 0.9550894498825073, | |
| "learning_rate": 4.2609632582695825e-05, | |
| "loss": 3.1108, | |
| "step": 86350 | |
| }, | |
| { | |
| "epoch": 9.29932192444301, | |
| "grad_norm": 0.9045702219009399, | |
| "learning_rate": 4.2286391552634406e-05, | |
| "loss": 3.1302, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 9.304703476482617, | |
| "grad_norm": 0.9491354823112488, | |
| "learning_rate": 4.1963150522572994e-05, | |
| "loss": 3.1328, | |
| "step": 86450 | |
| }, | |
| { | |
| "epoch": 9.310085028522225, | |
| "grad_norm": 0.9591734409332275, | |
| "learning_rate": 4.1639909492511575e-05, | |
| "loss": 3.1423, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 9.315466580561834, | |
| "grad_norm": 0.9250282049179077, | |
| "learning_rate": 4.131666846245017e-05, | |
| "loss": 3.126, | |
| "step": 86550 | |
| }, | |
| { | |
| "epoch": 9.320848132601443, | |
| "grad_norm": 0.8863346576690674, | |
| "learning_rate": 4.099989225298998e-05, | |
| "loss": 3.1328, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 9.326229684641051, | |
| "grad_norm": 0.92470782995224, | |
| "learning_rate": 4.0676651222928564e-05, | |
| "loss": 3.1243, | |
| "step": 86650 | |
| }, | |
| { | |
| "epoch": 9.331611236680658, | |
| "grad_norm": 0.8946364521980286, | |
| "learning_rate": 4.035341019286714e-05, | |
| "loss": 3.1377, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 9.336992788720266, | |
| "grad_norm": 0.871094286441803, | |
| "learning_rate": 4.003016916280573e-05, | |
| "loss": 3.1324, | |
| "step": 86750 | |
| }, | |
| { | |
| "epoch": 9.342374340759875, | |
| "grad_norm": 0.9345404505729675, | |
| "learning_rate": 3.9706928132744314e-05, | |
| "loss": 3.1413, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 9.347755892799483, | |
| "grad_norm": 0.8760411143302917, | |
| "learning_rate": 3.93836871026829e-05, | |
| "loss": 3.1308, | |
| "step": 86850 | |
| }, | |
| { | |
| "epoch": 9.353137444839092, | |
| "grad_norm": 0.9380771517753601, | |
| "learning_rate": 3.906044607262148e-05, | |
| "loss": 3.1174, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 9.3585189968787, | |
| "grad_norm": 0.8624494075775146, | |
| "learning_rate": 3.8737205042560064e-05, | |
| "loss": 3.13, | |
| "step": 86950 | |
| }, | |
| { | |
| "epoch": 9.363900548918307, | |
| "grad_norm": 0.9666469693183899, | |
| "learning_rate": 3.841396401249865e-05, | |
| "loss": 3.1295, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 9.363900548918307, | |
| "eval_accuracy": 0.3934488393209586, | |
| "eval_loss": 3.3093247413635254, | |
| "eval_runtime": 179.5385, | |
| "eval_samples_per_second": 100.318, | |
| "eval_steps_per_second": 6.272, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 9.369282100957916, | |
| "grad_norm": 0.91963791847229, | |
| "learning_rate": 3.809072298243723e-05, | |
| "loss": 3.1292, | |
| "step": 87050 | |
| }, | |
| { | |
| "epoch": 9.374663652997524, | |
| "grad_norm": 0.9316657185554504, | |
| "learning_rate": 3.776748195237582e-05, | |
| "loss": 3.1515, | |
| "step": 87100 | |
| }, | |
| { | |
| "epoch": 9.380045205037133, | |
| "grad_norm": 0.9758146405220032, | |
| "learning_rate": 3.74442409223144e-05, | |
| "loss": 3.1249, | |
| "step": 87150 | |
| }, | |
| { | |
| "epoch": 9.385426757076742, | |
| "grad_norm": 0.904312789440155, | |
| "learning_rate": 3.712099989225299e-05, | |
| "loss": 3.1384, | |
| "step": 87200 | |
| }, | |
| { | |
| "epoch": 9.390808309116348, | |
| "grad_norm": 0.9568246006965637, | |
| "learning_rate": 3.679775886219157e-05, | |
| "loss": 3.1241, | |
| "step": 87250 | |
| }, | |
| { | |
| "epoch": 9.396189861155957, | |
| "grad_norm": 0.9116389155387878, | |
| "learning_rate": 3.647451783213015e-05, | |
| "loss": 3.1473, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 9.401571413195565, | |
| "grad_norm": 0.9002155065536499, | |
| "learning_rate": 3.615127680206874e-05, | |
| "loss": 3.1357, | |
| "step": 87350 | |
| }, | |
| { | |
| "epoch": 9.406952965235174, | |
| "grad_norm": 0.984461784362793, | |
| "learning_rate": 3.582803577200732e-05, | |
| "loss": 3.1345, | |
| "step": 87400 | |
| }, | |
| { | |
| "epoch": 9.412334517274783, | |
| "grad_norm": 0.9499680995941162, | |
| "learning_rate": 3.550479474194591e-05, | |
| "loss": 3.1226, | |
| "step": 87450 | |
| }, | |
| { | |
| "epoch": 9.417716069314391, | |
| "grad_norm": 0.9205060005187988, | |
| "learning_rate": 3.518155371188449e-05, | |
| "loss": 3.127, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 9.423097621353998, | |
| "grad_norm": 0.9197761416435242, | |
| "learning_rate": 3.485831268182308e-05, | |
| "loss": 3.1202, | |
| "step": 87550 | |
| }, | |
| { | |
| "epoch": 9.428479173393606, | |
| "grad_norm": 0.9335700273513794, | |
| "learning_rate": 3.453507165176166e-05, | |
| "loss": 3.1419, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 9.433860725433215, | |
| "grad_norm": 1.0131042003631592, | |
| "learning_rate": 3.421183062170025e-05, | |
| "loss": 3.1274, | |
| "step": 87650 | |
| }, | |
| { | |
| "epoch": 9.439242277472824, | |
| "grad_norm": 0.9497924447059631, | |
| "learning_rate": 3.388858959163883e-05, | |
| "loss": 3.1297, | |
| "step": 87700 | |
| }, | |
| { | |
| "epoch": 9.444623829512432, | |
| "grad_norm": 0.935814380645752, | |
| "learning_rate": 3.3565348561577416e-05, | |
| "loss": 3.128, | |
| "step": 87750 | |
| }, | |
| { | |
| "epoch": 9.450005381552039, | |
| "grad_norm": 0.9703516960144043, | |
| "learning_rate": 3.3242107531516e-05, | |
| "loss": 3.1104, | |
| "step": 87800 | |
| }, | |
| { | |
| "epoch": 9.455386933591647, | |
| "grad_norm": 0.935706377029419, | |
| "learning_rate": 3.291886650145458e-05, | |
| "loss": 3.1187, | |
| "step": 87850 | |
| }, | |
| { | |
| "epoch": 9.460768485631256, | |
| "grad_norm": 0.9084662795066833, | |
| "learning_rate": 3.2595625471393166e-05, | |
| "loss": 3.1274, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 9.466150037670864, | |
| "grad_norm": 0.9186142683029175, | |
| "learning_rate": 3.2272384441331754e-05, | |
| "loss": 3.1346, | |
| "step": 87950 | |
| }, | |
| { | |
| "epoch": 9.471531589710473, | |
| "grad_norm": 0.9566908478736877, | |
| "learning_rate": 3.1949143411270335e-05, | |
| "loss": 3.1359, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 9.471531589710473, | |
| "eval_accuracy": 0.3937906613060229, | |
| "eval_loss": 3.3066892623901367, | |
| "eval_runtime": 179.5664, | |
| "eval_samples_per_second": 100.303, | |
| "eval_steps_per_second": 6.271, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 9.476913141750082, | |
| "grad_norm": 0.9515846967697144, | |
| "learning_rate": 3.1625902381208916e-05, | |
| "loss": 3.1377, | |
| "step": 88050 | |
| }, | |
| { | |
| "epoch": 9.482294693789688, | |
| "grad_norm": 0.9604725241661072, | |
| "learning_rate": 3.1302661351147504e-05, | |
| "loss": 3.147, | |
| "step": 88100 | |
| }, | |
| { | |
| "epoch": 9.487676245829297, | |
| "grad_norm": 0.9489278197288513, | |
| "learning_rate": 3.0979420321086085e-05, | |
| "loss": 3.1266, | |
| "step": 88150 | |
| }, | |
| { | |
| "epoch": 9.493057797868905, | |
| "grad_norm": 0.8774126172065735, | |
| "learning_rate": 3.065617929102467e-05, | |
| "loss": 3.1176, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 9.498439349908514, | |
| "grad_norm": 0.8997475504875183, | |
| "learning_rate": 3.0332938260963258e-05, | |
| "loss": 3.1124, | |
| "step": 88250 | |
| }, | |
| { | |
| "epoch": 9.503820901948123, | |
| "grad_norm": 0.9679112434387207, | |
| "learning_rate": 3.000969723090184e-05, | |
| "loss": 3.1337, | |
| "step": 88300 | |
| }, | |
| { | |
| "epoch": 9.50920245398773, | |
| "grad_norm": 0.8895472288131714, | |
| "learning_rate": 2.9686456200840423e-05, | |
| "loss": 3.1079, | |
| "step": 88350 | |
| }, | |
| { | |
| "epoch": 9.514584006027338, | |
| "grad_norm": 0.8873099684715271, | |
| "learning_rate": 2.9363215170779008e-05, | |
| "loss": 3.1358, | |
| "step": 88400 | |
| }, | |
| { | |
| "epoch": 9.519965558066946, | |
| "grad_norm": 0.9306134581565857, | |
| "learning_rate": 2.9039974140717592e-05, | |
| "loss": 3.1186, | |
| "step": 88450 | |
| }, | |
| { | |
| "epoch": 9.525347110106555, | |
| "grad_norm": 0.9422151446342468, | |
| "learning_rate": 2.871673311065618e-05, | |
| "loss": 3.1145, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 9.530728662146164, | |
| "grad_norm": 0.8907070755958557, | |
| "learning_rate": 2.839349208059476e-05, | |
| "loss": 3.1338, | |
| "step": 88550 | |
| }, | |
| { | |
| "epoch": 9.536110214185772, | |
| "grad_norm": 0.9752025008201599, | |
| "learning_rate": 2.8070251050533346e-05, | |
| "loss": 3.1358, | |
| "step": 88600 | |
| }, | |
| { | |
| "epoch": 9.541491766225379, | |
| "grad_norm": 0.9604821801185608, | |
| "learning_rate": 2.775347484107316e-05, | |
| "loss": 3.155, | |
| "step": 88650 | |
| }, | |
| { | |
| "epoch": 9.546873318264987, | |
| "grad_norm": 0.9035794734954834, | |
| "learning_rate": 2.7430233811011744e-05, | |
| "loss": 3.1376, | |
| "step": 88700 | |
| }, | |
| { | |
| "epoch": 9.552254870304596, | |
| "grad_norm": 0.909589946269989, | |
| "learning_rate": 2.7106992780950328e-05, | |
| "loss": 3.1384, | |
| "step": 88750 | |
| }, | |
| { | |
| "epoch": 9.557636422344205, | |
| "grad_norm": 0.9262523651123047, | |
| "learning_rate": 2.678375175088891e-05, | |
| "loss": 3.1124, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 9.563017974383813, | |
| "grad_norm": 0.8929489850997925, | |
| "learning_rate": 2.6466975541428722e-05, | |
| "loss": 3.13, | |
| "step": 88850 | |
| }, | |
| { | |
| "epoch": 9.56839952642342, | |
| "grad_norm": 0.9192137718200684, | |
| "learning_rate": 2.6143734511367307e-05, | |
| "loss": 3.1142, | |
| "step": 88900 | |
| }, | |
| { | |
| "epoch": 9.573781078463028, | |
| "grad_norm": 0.9199954271316528, | |
| "learning_rate": 2.582049348130589e-05, | |
| "loss": 3.1292, | |
| "step": 88950 | |
| }, | |
| { | |
| "epoch": 9.579162630502637, | |
| "grad_norm": 0.9602384567260742, | |
| "learning_rate": 2.5497252451244476e-05, | |
| "loss": 3.1312, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 9.579162630502637, | |
| "eval_accuracy": 0.39399927485062675, | |
| "eval_loss": 3.3048999309539795, | |
| "eval_runtime": 179.8132, | |
| "eval_samples_per_second": 100.165, | |
| "eval_steps_per_second": 6.262, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 9.584544182542245, | |
| "grad_norm": 0.9000515937805176, | |
| "learning_rate": 2.517401142118306e-05, | |
| "loss": 3.1282, | |
| "step": 89050 | |
| }, | |
| { | |
| "epoch": 9.589925734581854, | |
| "grad_norm": 0.9287469387054443, | |
| "learning_rate": 2.485077039112164e-05, | |
| "loss": 3.1414, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 9.59530728662146, | |
| "grad_norm": 0.8891144394874573, | |
| "learning_rate": 2.4527529361060226e-05, | |
| "loss": 3.1132, | |
| "step": 89150 | |
| }, | |
| { | |
| "epoch": 9.60068883866107, | |
| "grad_norm": 0.9419028759002686, | |
| "learning_rate": 2.4204288330998814e-05, | |
| "loss": 3.1305, | |
| "step": 89200 | |
| }, | |
| { | |
| "epoch": 9.606070390700678, | |
| "grad_norm": 0.9434340000152588, | |
| "learning_rate": 2.38810473009374e-05, | |
| "loss": 3.1396, | |
| "step": 89250 | |
| }, | |
| { | |
| "epoch": 9.611451942740286, | |
| "grad_norm": 0.9384384155273438, | |
| "learning_rate": 2.3557806270875983e-05, | |
| "loss": 3.1392, | |
| "step": 89300 | |
| }, | |
| { | |
| "epoch": 9.616833494779895, | |
| "grad_norm": 0.9376377463340759, | |
| "learning_rate": 2.3234565240814564e-05, | |
| "loss": 3.1508, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 9.622215046819504, | |
| "grad_norm": 0.9515202641487122, | |
| "learning_rate": 2.291132421075315e-05, | |
| "loss": 3.1305, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 9.62759659885911, | |
| "grad_norm": 0.8941816091537476, | |
| "learning_rate": 2.2588083180691733e-05, | |
| "loss": 3.1137, | |
| "step": 89450 | |
| }, | |
| { | |
| "epoch": 9.632978150898719, | |
| "grad_norm": 0.9425456523895264, | |
| "learning_rate": 2.2264842150630318e-05, | |
| "loss": 3.1185, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 9.638359702938327, | |
| "grad_norm": 0.9340146780014038, | |
| "learning_rate": 2.1941601120568905e-05, | |
| "loss": 3.1293, | |
| "step": 89550 | |
| }, | |
| { | |
| "epoch": 9.643741254977936, | |
| "grad_norm": 0.9706893563270569, | |
| "learning_rate": 2.1618360090507483e-05, | |
| "loss": 3.1119, | |
| "step": 89600 | |
| }, | |
| { | |
| "epoch": 9.649122807017545, | |
| "grad_norm": 0.8813906311988831, | |
| "learning_rate": 2.1301583881047296e-05, | |
| "loss": 3.144, | |
| "step": 89650 | |
| }, | |
| { | |
| "epoch": 9.654504359057151, | |
| "grad_norm": 0.8951605558395386, | |
| "learning_rate": 2.097834285098588e-05, | |
| "loss": 3.1292, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 9.65988591109676, | |
| "grad_norm": 0.9236047863960266, | |
| "learning_rate": 2.065510182092447e-05, | |
| "loss": 3.1305, | |
| "step": 89750 | |
| }, | |
| { | |
| "epoch": 9.665267463136368, | |
| "grad_norm": 0.8858392238616943, | |
| "learning_rate": 2.0331860790863053e-05, | |
| "loss": 3.1305, | |
| "step": 89800 | |
| }, | |
| { | |
| "epoch": 9.670649015175977, | |
| "grad_norm": 0.931576669216156, | |
| "learning_rate": 2.0008619760801638e-05, | |
| "loss": 3.1385, | |
| "step": 89850 | |
| }, | |
| { | |
| "epoch": 9.676030567215586, | |
| "grad_norm": 0.9866983890533447, | |
| "learning_rate": 1.968537873074022e-05, | |
| "loss": 3.1275, | |
| "step": 89900 | |
| }, | |
| { | |
| "epoch": 9.681412119255192, | |
| "grad_norm": 0.9134666323661804, | |
| "learning_rate": 1.9362137700678803e-05, | |
| "loss": 3.1039, | |
| "step": 89950 | |
| }, | |
| { | |
| "epoch": 9.6867936712948, | |
| "grad_norm": 0.9204062819480896, | |
| "learning_rate": 1.9038896670617388e-05, | |
| "loss": 3.1326, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 9.6867936712948, | |
| "eval_accuracy": 0.3943079577049077, | |
| "eval_loss": 3.302588701248169, | |
| "eval_runtime": 179.7361, | |
| "eval_samples_per_second": 100.208, | |
| "eval_steps_per_second": 6.265, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 9.69217522333441, | |
| "grad_norm": 0.8718501329421997, | |
| "learning_rate": 1.8715655640555972e-05, | |
| "loss": 3.1206, | |
| "step": 90050 | |
| }, | |
| { | |
| "epoch": 9.697556775374018, | |
| "grad_norm": 0.9207223653793335, | |
| "learning_rate": 1.8392414610494557e-05, | |
| "loss": 3.1523, | |
| "step": 90100 | |
| }, | |
| { | |
| "epoch": 9.702938327413626, | |
| "grad_norm": 0.9116508364677429, | |
| "learning_rate": 1.806917358043314e-05, | |
| "loss": 3.1253, | |
| "step": 90150 | |
| }, | |
| { | |
| "epoch": 9.708319879453235, | |
| "grad_norm": 0.9184285402297974, | |
| "learning_rate": 1.7745932550371726e-05, | |
| "loss": 3.1539, | |
| "step": 90200 | |
| }, | |
| { | |
| "epoch": 9.713701431492842, | |
| "grad_norm": 0.9284878373146057, | |
| "learning_rate": 1.742269152031031e-05, | |
| "loss": 3.1282, | |
| "step": 90250 | |
| }, | |
| { | |
| "epoch": 9.71908298353245, | |
| "grad_norm": 0.9029609560966492, | |
| "learning_rate": 1.7099450490248895e-05, | |
| "loss": 3.128, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 9.724464535572059, | |
| "grad_norm": 0.9100344777107239, | |
| "learning_rate": 1.677620946018748e-05, | |
| "loss": 3.1314, | |
| "step": 90350 | |
| }, | |
| { | |
| "epoch": 9.729846087611667, | |
| "grad_norm": 0.9491696953773499, | |
| "learning_rate": 1.6452968430126064e-05, | |
| "loss": 3.1323, | |
| "step": 90400 | |
| }, | |
| { | |
| "epoch": 9.735227639651276, | |
| "grad_norm": 0.9546681046485901, | |
| "learning_rate": 1.6129727400064645e-05, | |
| "loss": 3.1522, | |
| "step": 90450 | |
| }, | |
| { | |
| "epoch": 9.740609191690883, | |
| "grad_norm": 0.967365026473999, | |
| "learning_rate": 1.580648637000323e-05, | |
| "loss": 3.1408, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 9.745990743730491, | |
| "grad_norm": 0.9326353669166565, | |
| "learning_rate": 1.5483245339941817e-05, | |
| "loss": 3.1218, | |
| "step": 90550 | |
| }, | |
| { | |
| "epoch": 9.7513722957701, | |
| "grad_norm": 0.9593531489372253, | |
| "learning_rate": 1.5160004309880398e-05, | |
| "loss": 3.1252, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 9.756753847809708, | |
| "grad_norm": 0.9383837580680847, | |
| "learning_rate": 1.4836763279818985e-05, | |
| "loss": 3.1253, | |
| "step": 90650 | |
| }, | |
| { | |
| "epoch": 9.762135399849317, | |
| "grad_norm": 0.9309119582176208, | |
| "learning_rate": 1.4513522249757567e-05, | |
| "loss": 3.1303, | |
| "step": 90700 | |
| }, | |
| { | |
| "epoch": 9.767516951888926, | |
| "grad_norm": 0.8812274932861328, | |
| "learning_rate": 1.4190281219696152e-05, | |
| "loss": 3.1207, | |
| "step": 90750 | |
| }, | |
| { | |
| "epoch": 9.772898503928532, | |
| "grad_norm": 0.9175823330879211, | |
| "learning_rate": 1.3867040189634736e-05, | |
| "loss": 3.1227, | |
| "step": 90800 | |
| }, | |
| { | |
| "epoch": 9.77828005596814, | |
| "grad_norm": 0.9752672910690308, | |
| "learning_rate": 1.3543799159573321e-05, | |
| "loss": 3.1246, | |
| "step": 90850 | |
| }, | |
| { | |
| "epoch": 9.78366160800775, | |
| "grad_norm": 0.9278659820556641, | |
| "learning_rate": 1.3220558129511905e-05, | |
| "loss": 3.1261, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 9.789043160047358, | |
| "grad_norm": 0.9404040575027466, | |
| "learning_rate": 1.2897317099450488e-05, | |
| "loss": 3.1244, | |
| "step": 90950 | |
| }, | |
| { | |
| "epoch": 9.794424712086967, | |
| "grad_norm": 0.9082286953926086, | |
| "learning_rate": 1.2574076069389073e-05, | |
| "loss": 3.1159, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 9.794424712086967, | |
| "eval_accuracy": 0.394532651876908, | |
| "eval_loss": 3.3007988929748535, | |
| "eval_runtime": 180.0492, | |
| "eval_samples_per_second": 100.034, | |
| "eval_steps_per_second": 6.254, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 9.799806264126573, | |
| "grad_norm": 0.9126229286193848, | |
| "learning_rate": 1.2250835039327659e-05, | |
| "loss": 3.1382, | |
| "step": 91050 | |
| }, | |
| { | |
| "epoch": 9.805187816166182, | |
| "grad_norm": 0.9428226351737976, | |
| "learning_rate": 1.1927594009266242e-05, | |
| "loss": 3.149, | |
| "step": 91100 | |
| }, | |
| { | |
| "epoch": 9.81056936820579, | |
| "grad_norm": 0.933461606502533, | |
| "learning_rate": 1.1604352979204826e-05, | |
| "loss": 3.1239, | |
| "step": 91150 | |
| }, | |
| { | |
| "epoch": 9.815950920245399, | |
| "grad_norm": 0.9387831687927246, | |
| "learning_rate": 1.1281111949143409e-05, | |
| "loss": 3.1187, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 9.821332472285007, | |
| "grad_norm": 0.9336826205253601, | |
| "learning_rate": 1.0957870919081995e-05, | |
| "loss": 3.138, | |
| "step": 91250 | |
| }, | |
| { | |
| "epoch": 9.826714024324616, | |
| "grad_norm": 0.943970799446106, | |
| "learning_rate": 1.063462988902058e-05, | |
| "loss": 3.1231, | |
| "step": 91300 | |
| }, | |
| { | |
| "epoch": 9.832095576364223, | |
| "grad_norm": 0.9266682267189026, | |
| "learning_rate": 1.0311388858959162e-05, | |
| "loss": 3.1375, | |
| "step": 91350 | |
| }, | |
| { | |
| "epoch": 9.837477128403831, | |
| "grad_norm": 0.9433984756469727, | |
| "learning_rate": 9.988147828897747e-06, | |
| "loss": 3.1164, | |
| "step": 91400 | |
| }, | |
| { | |
| "epoch": 9.84285868044344, | |
| "grad_norm": 0.9360959529876709, | |
| "learning_rate": 9.66490679883633e-06, | |
| "loss": 3.1196, | |
| "step": 91450 | |
| }, | |
| { | |
| "epoch": 9.848240232483048, | |
| "grad_norm": 0.9291725158691406, | |
| "learning_rate": 9.341665768774916e-06, | |
| "loss": 3.1343, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 9.853621784522657, | |
| "grad_norm": 1.001280426979065, | |
| "learning_rate": 9.018424738713499e-06, | |
| "loss": 3.1302, | |
| "step": 91550 | |
| }, | |
| { | |
| "epoch": 9.859003336562264, | |
| "grad_norm": 0.9111364483833313, | |
| "learning_rate": 8.695183708652085e-06, | |
| "loss": 3.1544, | |
| "step": 91600 | |
| }, | |
| { | |
| "epoch": 9.864384888601872, | |
| "grad_norm": 0.9523101449012756, | |
| "learning_rate": 8.37194267859067e-06, | |
| "loss": 3.1224, | |
| "step": 91650 | |
| }, | |
| { | |
| "epoch": 9.869766440641481, | |
| "grad_norm": 0.9617007374763489, | |
| "learning_rate": 8.048701648529252e-06, | |
| "loss": 3.1031, | |
| "step": 91700 | |
| }, | |
| { | |
| "epoch": 9.87514799268109, | |
| "grad_norm": 0.9206680655479431, | |
| "learning_rate": 7.725460618467837e-06, | |
| "loss": 3.143, | |
| "step": 91750 | |
| }, | |
| { | |
| "epoch": 9.880529544720698, | |
| "grad_norm": 0.911401629447937, | |
| "learning_rate": 7.40221958840642e-06, | |
| "loss": 3.1169, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 9.885911096760307, | |
| "grad_norm": 0.9321516752243042, | |
| "learning_rate": 7.078978558345006e-06, | |
| "loss": 3.1209, | |
| "step": 91850 | |
| }, | |
| { | |
| "epoch": 9.891292648799913, | |
| "grad_norm": 0.9269621968269348, | |
| "learning_rate": 6.75573752828359e-06, | |
| "loss": 3.1273, | |
| "step": 91900 | |
| }, | |
| { | |
| "epoch": 9.896674200839522, | |
| "grad_norm": 0.9078811407089233, | |
| "learning_rate": 6.432496498222174e-06, | |
| "loss": 3.12, | |
| "step": 91950 | |
| }, | |
| { | |
| "epoch": 9.90205575287913, | |
| "grad_norm": 0.9647493362426758, | |
| "learning_rate": 6.1092554681607575e-06, | |
| "loss": 3.1335, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 9.90205575287913, | |
| "eval_accuracy": 0.39470041193569355, | |
| "eval_loss": 3.298912763595581, | |
| "eval_runtime": 179.4924, | |
| "eval_samples_per_second": 100.344, | |
| "eval_steps_per_second": 6.273, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 9.907437304918739, | |
| "grad_norm": 0.8831244111061096, | |
| "learning_rate": 5.786014438099342e-06, | |
| "loss": 3.1265, | |
| "step": 92050 | |
| }, | |
| { | |
| "epoch": 9.912818856958348, | |
| "grad_norm": 0.9248406887054443, | |
| "learning_rate": 5.4627734080379264e-06, | |
| "loss": 3.1265, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 9.918200408997954, | |
| "grad_norm": 0.8974929451942444, | |
| "learning_rate": 5.139532377976511e-06, | |
| "loss": 3.1342, | |
| "step": 92150 | |
| }, | |
| { | |
| "epoch": 9.923581961037563, | |
| "grad_norm": 0.8904796838760376, | |
| "learning_rate": 4.816291347915095e-06, | |
| "loss": 3.141, | |
| "step": 92200 | |
| }, | |
| { | |
| "epoch": 9.928963513077171, | |
| "grad_norm": 0.9588956236839294, | |
| "learning_rate": 4.493050317853679e-06, | |
| "loss": 3.132, | |
| "step": 92250 | |
| }, | |
| { | |
| "epoch": 9.93434506511678, | |
| "grad_norm": 0.8969722390174866, | |
| "learning_rate": 4.169809287792264e-06, | |
| "loss": 3.1247, | |
| "step": 92300 | |
| }, | |
| { | |
| "epoch": 9.939726617156388, | |
| "grad_norm": 0.9294554591178894, | |
| "learning_rate": 3.846568257730847e-06, | |
| "loss": 3.1151, | |
| "step": 92350 | |
| }, | |
| { | |
| "epoch": 9.945108169195997, | |
| "grad_norm": 0.9306110143661499, | |
| "learning_rate": 3.523327227669432e-06, | |
| "loss": 3.1447, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 9.950489721235604, | |
| "grad_norm": 0.9280375838279724, | |
| "learning_rate": 3.2000861976080162e-06, | |
| "loss": 3.1198, | |
| "step": 92450 | |
| }, | |
| { | |
| "epoch": 9.955871273275212, | |
| "grad_norm": 0.9354221820831299, | |
| "learning_rate": 2.8768451675466007e-06, | |
| "loss": 3.1236, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 9.961252825314821, | |
| "grad_norm": 0.933273434638977, | |
| "learning_rate": 2.5536041374851848e-06, | |
| "loss": 3.119, | |
| "step": 92550 | |
| }, | |
| { | |
| "epoch": 9.96663437735443, | |
| "grad_norm": 0.9233914613723755, | |
| "learning_rate": 2.230363107423769e-06, | |
| "loss": 3.1258, | |
| "step": 92600 | |
| }, | |
| { | |
| "epoch": 9.972015929394038, | |
| "grad_norm": 0.8901816010475159, | |
| "learning_rate": 1.9071220773623531e-06, | |
| "loss": 3.1333, | |
| "step": 92650 | |
| }, | |
| { | |
| "epoch": 9.977397481433645, | |
| "grad_norm": 0.904162585735321, | |
| "learning_rate": 1.5838810473009372e-06, | |
| "loss": 3.1192, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 9.982779033473253, | |
| "grad_norm": 0.9620854258537292, | |
| "learning_rate": 1.2606400172395215e-06, | |
| "loss": 3.1128, | |
| "step": 92750 | |
| }, | |
| { | |
| "epoch": 9.988160585512862, | |
| "grad_norm": 0.962112545967102, | |
| "learning_rate": 9.373989871781058e-07, | |
| "loss": 3.1307, | |
| "step": 92800 | |
| }, | |
| { | |
| "epoch": 9.99354213755247, | |
| "grad_norm": 0.9469469785690308, | |
| "learning_rate": 6.1415795711669e-07, | |
| "loss": 3.139, | |
| "step": 92850 | |
| }, | |
| { | |
| "epoch": 9.998923689592079, | |
| "grad_norm": 0.9218598008155823, | |
| "learning_rate": 2.909169270552742e-07, | |
| "loss": 3.1296, | |
| "step": 92900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 92910, | |
| "total_flos": 7.7683166281728e+17, | |
| "train_loss": 3.452293256932703, | |
| "train_runtime": 79255.5774, | |
| "train_samples_per_second": 37.512, | |
| "train_steps_per_second": 1.172 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 92910, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.7683166281728e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |