| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.012987012987012988, |
| "eval_steps": 1000, |
| "global_step": 77000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0009090909090909091, |
| "grad_norm": 0.5637483596801758, |
| "learning_rate": 0.00066, |
| "loss": 7.38281005859375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0018181818181818182, |
| "grad_norm": 0.6073591709136963, |
| "learning_rate": 0.000999999509056267, |
| "loss": 5.783165283203125, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0027272727272727275, |
| "grad_norm": 0.480266273021698, |
| "learning_rate": 0.0009999954604635122, |
| "loss": 5.232196044921875, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0036363636363636364, |
| "grad_norm": 0.45949065685272217, |
| "learning_rate": 0.0009999873224161853, |
| "loss": 4.946490478515625, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.004545454545454545, |
| "grad_norm": 0.41542109847068787, |
| "learning_rate": 0.000999975094980847, |
| "loss": 4.719376831054688, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.005454545454545455, |
| "grad_norm": 0.40697741508483887, |
| "learning_rate": 0.0009999587782575051, |
| "loss": 4.591694030761719, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.006363636363636364, |
| "grad_norm": 0.3962944447994232, |
| "learning_rate": 0.0009999383723796143, |
| "loss": 4.466532592773437, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.007272727272727273, |
| "grad_norm": 0.6857792139053345, |
| "learning_rate": 0.0009999138775140734, |
| "loss": 4.349520874023438, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.008181818181818182, |
| "grad_norm": 0.4181463420391083, |
| "learning_rate": 0.000999885293861226, |
| "loss": 4.234326782226563, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "grad_norm": 0.3620698153972626, |
| "learning_rate": 0.0009998526216548572, |
| "loss": 4.120015869140625, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "eval_loss": 4.375123977661133, |
| "eval_runtime": 6.9666, |
| "eval_samples_per_second": 82.681, |
| "eval_steps_per_second": 20.67, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.3509594798088074, |
| "learning_rate": 0.0009998158611621922, |
| "loss": 3.993647155761719, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.01090909090909091, |
| "grad_norm": 0.3581515848636627, |
| "learning_rate": 0.0009997750126838946, |
| "loss": 3.9498220825195314, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.011818181818181818, |
| "grad_norm": 0.36733096837997437, |
| "learning_rate": 0.0009997300765540635, |
| "loss": 3.831287841796875, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.012727272727272728, |
| "grad_norm": 0.29147249460220337, |
| "learning_rate": 0.0009996810531402306, |
| "loss": 3.7590908813476562, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.013636363636363636, |
| "grad_norm": 0.29391637444496155, |
| "learning_rate": 0.0009996279428433578, |
| "loss": 3.722886047363281, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.014545454545454545, |
| "grad_norm": 0.3317511975765228, |
| "learning_rate": 0.000999570746097833, |
| "loss": 3.7012667846679688, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.015454545454545455, |
| "grad_norm": 0.32525742053985596, |
| "learning_rate": 0.0009995094633714677, |
| "loss": 3.6526870727539062, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.016363636363636365, |
| "grad_norm": 0.3586934208869934, |
| "learning_rate": 0.0009994440951654924, |
| "loss": 3.6262481689453123, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.017272727272727273, |
| "grad_norm": 0.30995482206344604, |
| "learning_rate": 0.0009993746420145523, |
| "loss": 3.594487609863281, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "grad_norm": 0.3067973852157593, |
| "learning_rate": 0.0009993011044867038, |
| "loss": 3.5707028198242186, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "eval_loss": 3.896928548812866, |
| "eval_runtime": 6.7872, |
| "eval_samples_per_second": 84.865, |
| "eval_steps_per_second": 21.216, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.019090909090909092, |
| "grad_norm": 0.2716964781284332, |
| "learning_rate": 0.000999223483183409, |
| "loss": 3.5685223388671874, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.2595560550689697, |
| "learning_rate": 0.000999141778739531, |
| "loss": 3.533115234375, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.02090909090909091, |
| "grad_norm": 0.2871851325035095, |
| "learning_rate": 0.0009990559918233294, |
| "loss": 3.51209716796875, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.02181818181818182, |
| "grad_norm": 0.2916632890701294, |
| "learning_rate": 0.0009989661231364542, |
| "loss": 3.4977175903320314, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.022727272727272728, |
| "grad_norm": 0.2674938440322876, |
| "learning_rate": 0.0009988721734139395, |
| "loss": 3.4819268798828125, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.023636363636363636, |
| "grad_norm": 0.28354012966156006, |
| "learning_rate": 0.0009987741434241983, |
| "loss": 3.4985772705078126, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.024545454545454544, |
| "grad_norm": 0.250453919172287, |
| "learning_rate": 0.000998672033969017, |
| "loss": 3.4824765014648436, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.025454545454545455, |
| "grad_norm": 0.25479111075401306, |
| "learning_rate": 0.0009985658458835465, |
| "loss": 3.43513916015625, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.026363636363636363, |
| "grad_norm": 0.5312749743461609, |
| "learning_rate": 0.0009984555800362977, |
| "loss": 3.4338519287109377, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "grad_norm": 0.24919964373111725, |
| "learning_rate": 0.0009983412373291332, |
| "loss": 3.394432373046875, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "eval_loss": 3.7320191860198975, |
| "eval_runtime": 6.8112, |
| "eval_samples_per_second": 84.566, |
| "eval_steps_per_second": 21.142, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.028181818181818183, |
| "grad_norm": 0.2345028668642044, |
| "learning_rate": 0.0009982228186972597, |
| "loss": 3.3772811889648438, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.02909090909090909, |
| "grad_norm": 0.2587430775165558, |
| "learning_rate": 0.0009981003251092215, |
| "loss": 3.368675537109375, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.25332900881767273, |
| "learning_rate": 0.0009979737575668917, |
| "loss": 3.3781060791015625, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.03090909090909091, |
| "grad_norm": 0.2273174375295639, |
| "learning_rate": 0.000997843117105464, |
| "loss": 3.328343505859375, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.031818181818181815, |
| "grad_norm": 0.2621140778064728, |
| "learning_rate": 0.0009977084047934448, |
| "loss": 3.3511767578125, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.03272727272727273, |
| "grad_norm": 0.22301150858402252, |
| "learning_rate": 0.0009975696217326435, |
| "loss": 3.3483154296875, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.03363636363636364, |
| "grad_norm": 0.22785483300685883, |
| "learning_rate": 0.0009974267690581644, |
| "loss": 3.351199951171875, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.034545454545454546, |
| "grad_norm": 0.24507705867290497, |
| "learning_rate": 0.0009972798479383977, |
| "loss": 3.311331787109375, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.035454545454545454, |
| "grad_norm": 0.22445634007453918, |
| "learning_rate": 0.0009971288595750083, |
| "loss": 3.2849237060546876, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "grad_norm": 0.2134762406349182, |
| "learning_rate": 0.0009969738052029277, |
| "loss": 3.2534124755859377, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "eval_loss": 3.6267645359039307, |
| "eval_runtime": 6.8001, |
| "eval_samples_per_second": 84.704, |
| "eval_steps_per_second": 21.176, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.03727272727272727, |
| "grad_norm": 0.2137739211320877, |
| "learning_rate": 0.000996814686090343, |
| "loss": 3.288787841796875, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.038181818181818185, |
| "grad_norm": 0.20396745204925537, |
| "learning_rate": 0.0009966515035386867, |
| "loss": 3.277693786621094, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.03909090909090909, |
| "grad_norm": 0.20048071444034576, |
| "learning_rate": 0.0009964842588826267, |
| "loss": 3.2614068603515625, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.2545357346534729, |
| "learning_rate": 0.0009963129534900535, |
| "loss": 3.241942138671875, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.04090909090909091, |
| "grad_norm": 0.21150407195091248, |
| "learning_rate": 0.0009961375887620715, |
| "loss": 3.254181213378906, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.04181818181818182, |
| "grad_norm": 0.25913697481155396, |
| "learning_rate": 0.0009959581661329855, |
| "loss": 3.256631164550781, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.042727272727272725, |
| "grad_norm": 0.21662315726280212, |
| "learning_rate": 0.000995774687070291, |
| "loss": 3.246457214355469, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.04363636363636364, |
| "grad_norm": 0.21578437089920044, |
| "learning_rate": 0.0009955871530746593, |
| "loss": 3.2591009521484375, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.04454545454545455, |
| "grad_norm": 0.2277086228132248, |
| "learning_rate": 0.0009953955656799285, |
| "loss": 3.2139767456054686, |
| "step": 4900 |
| }, |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 0.21145710349082947, |
| "learning_rate": 0.0009951999264530885, |
| "loss": 3.217757263183594, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.045454545454545456, |
| "eval_loss": 3.559657573699951, |
| "eval_runtime": 6.8094, |
| "eval_samples_per_second": 84.589, |
| "eval_steps_per_second": 21.147, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.046363636363636364, |
| "grad_norm": 0.2059008628129959, |
| "learning_rate": 0.0009950002369942693, |
| "loss": 3.2310595703125, |
| "step": 5100 |
| }, |
| { |
| "epoch": 0.04727272727272727, |
| "grad_norm": 0.31273841857910156, |
| "learning_rate": 0.0009947964989367275, |
| "loss": 3.236092529296875, |
| "step": 5200 |
| }, |
| { |
| "epoch": 0.04818181818181818, |
| "grad_norm": 0.20427817106246948, |
| "learning_rate": 0.0009945887139468335, |
| "loss": 3.20990966796875, |
| "step": 5300 |
| }, |
| { |
| "epoch": 0.04909090909090909, |
| "grad_norm": 0.21813584864139557, |
| "learning_rate": 0.0009943768837240572, |
| "loss": 3.23782470703125, |
| "step": 5400 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.21357640624046326, |
| "learning_rate": 0.0009941610100009546, |
| "loss": 3.2014178466796874, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.05090909090909091, |
| "grad_norm": 0.19788503646850586, |
| "learning_rate": 0.0009939410945431532, |
| "loss": 3.201743469238281, |
| "step": 5600 |
| }, |
| { |
| "epoch": 0.05181818181818182, |
| "grad_norm": 0.2109798789024353, |
| "learning_rate": 0.0009937171391493375, |
| "loss": 3.1780130004882814, |
| "step": 5700 |
| }, |
| { |
| "epoch": 0.05272727272727273, |
| "grad_norm": 0.1952320784330368, |
| "learning_rate": 0.0009934891456512356, |
| "loss": 3.1811758422851564, |
| "step": 5800 |
| }, |
| { |
| "epoch": 0.053636363636363635, |
| "grad_norm": 0.19197046756744385, |
| "learning_rate": 0.0009932571159136023, |
| "loss": 3.1767172241210937, |
| "step": 5900 |
| }, |
| { |
| "epoch": 0.05454545454545454, |
| "grad_norm": 0.20798423886299133, |
| "learning_rate": 0.0009930210518342049, |
| "loss": 3.1700228881835937, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.05454545454545454, |
| "eval_loss": 3.494601249694824, |
| "eval_runtime": 6.8416, |
| "eval_samples_per_second": 84.191, |
| "eval_steps_per_second": 21.048, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.05545454545454546, |
| "grad_norm": 0.18669773638248444, |
| "learning_rate": 0.0009927809553438077, |
| "loss": 3.1545779418945314, |
| "step": 6100 |
| }, |
| { |
| "epoch": 0.056363636363636366, |
| "grad_norm": 0.2077275514602661, |
| "learning_rate": 0.0009925368284061555, |
| "loss": 3.160372619628906, |
| "step": 6200 |
| }, |
| { |
| "epoch": 0.057272727272727274, |
| "grad_norm": 0.18006086349487305, |
| "learning_rate": 0.000992288673017959, |
| "loss": 3.1383782958984376, |
| "step": 6300 |
| }, |
| { |
| "epoch": 0.05818181818181818, |
| "grad_norm": 0.19835108518600464, |
| "learning_rate": 0.000992036491208877, |
| "loss": 3.15177001953125, |
| "step": 6400 |
| }, |
| { |
| "epoch": 0.05909090909090909, |
| "grad_norm": 0.19680027663707733, |
| "learning_rate": 0.0009917802850414998, |
| "loss": 3.16474365234375, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.28204840421676636, |
| "learning_rate": 0.0009915200566113338, |
| "loss": 3.1483929443359373, |
| "step": 6600 |
| }, |
| { |
| "epoch": 0.060909090909090906, |
| "grad_norm": 0.18320120871067047, |
| "learning_rate": 0.000991255808046783, |
| "loss": 3.150434875488281, |
| "step": 6700 |
| }, |
| { |
| "epoch": 0.06181818181818182, |
| "grad_norm": 0.19188480079174042, |
| "learning_rate": 0.000990987541509132, |
| "loss": 3.118103332519531, |
| "step": 6800 |
| }, |
| { |
| "epoch": 0.06272727272727273, |
| "grad_norm": 0.1749107539653778, |
| "learning_rate": 0.0009907152591925282, |
| "loss": 3.1161154174804686, |
| "step": 6900 |
| }, |
| { |
| "epoch": 0.06363636363636363, |
| "grad_norm": 0.17627771198749542, |
| "learning_rate": 0.0009904389633239644, |
| "loss": 3.140033874511719, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.06363636363636363, |
| "eval_loss": 3.460543632507324, |
| "eval_runtime": 6.8262, |
| "eval_samples_per_second": 84.381, |
| "eval_steps_per_second": 21.095, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.06454545454545454, |
| "grad_norm": 0.19298093020915985, |
| "learning_rate": 0.0009901586561632597, |
| "loss": 3.1127783203125, |
| "step": 7100 |
| }, |
| { |
| "epoch": 0.06545454545454546, |
| "grad_norm": 0.2005312442779541, |
| "learning_rate": 0.0009898743400030417, |
| "loss": 3.131772155761719, |
| "step": 7200 |
| }, |
| { |
| "epoch": 0.06636363636363636, |
| "grad_norm": 0.20932316780090332, |
| "learning_rate": 0.0009895860171687276, |
| "loss": 3.1065127563476564, |
| "step": 7300 |
| }, |
| { |
| "epoch": 0.06727272727272728, |
| "grad_norm": 0.1870882213115692, |
| "learning_rate": 0.0009892936900185053, |
| "loss": 3.1155380249023437, |
| "step": 7400 |
| }, |
| { |
| "epoch": 0.06818181818181818, |
| "grad_norm": 0.18347717821598053, |
| "learning_rate": 0.0009889973609433136, |
| "loss": 3.094842529296875, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.06909090909090909, |
| "grad_norm": 0.20144793391227722, |
| "learning_rate": 0.000988697032366823, |
| "loss": 3.1140432739257813, |
| "step": 7600 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.17255835235118866, |
| "learning_rate": 0.0009883927067454157, |
| "loss": 3.0936923217773438, |
| "step": 7700 |
| }, |
| { |
| "epoch": 0.07090909090909091, |
| "grad_norm": 0.19149735569953918, |
| "learning_rate": 0.0009880843865681666, |
| "loss": 3.0889437866210936, |
| "step": 7800 |
| }, |
| { |
| "epoch": 0.07181818181818182, |
| "grad_norm": 0.18358978629112244, |
| "learning_rate": 0.0009877720743568204, |
| "loss": 3.0625601196289063, |
| "step": 7900 |
| }, |
| { |
| "epoch": 0.07272727272727272, |
| "grad_norm": 0.16700264811515808, |
| "learning_rate": 0.0009874557726657744, |
| "loss": 3.0754776000976562, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.07272727272727272, |
| "eval_loss": 3.418283700942993, |
| "eval_runtime": 6.8139, |
| "eval_samples_per_second": 84.533, |
| "eval_steps_per_second": 21.133, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.07363636363636364, |
| "grad_norm": 0.18711890280246735, |
| "learning_rate": 0.0009871354840820543, |
| "loss": 3.0751129150390626, |
| "step": 8100 |
| }, |
| { |
| "epoch": 0.07454545454545454, |
| "grad_norm": 0.19081872701644897, |
| "learning_rate": 0.0009868112112252953, |
| "loss": 3.069129638671875, |
| "step": 8200 |
| }, |
| { |
| "epoch": 0.07545454545454545, |
| "grad_norm": 0.18380340933799744, |
| "learning_rate": 0.0009864829567477196, |
| "loss": 3.0967727661132813, |
| "step": 8300 |
| }, |
| { |
| "epoch": 0.07636363636363637, |
| "grad_norm": 0.1662234514951706, |
| "learning_rate": 0.0009861507233341154, |
| "loss": 3.0465274047851563, |
| "step": 8400 |
| }, |
| { |
| "epoch": 0.07727272727272727, |
| "grad_norm": 0.1769150197505951, |
| "learning_rate": 0.0009858145137018137, |
| "loss": 3.05833251953125, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.07818181818181819, |
| "grad_norm": 0.18805448710918427, |
| "learning_rate": 0.0009854743306006682, |
| "loss": 3.0252114868164064, |
| "step": 8600 |
| }, |
| { |
| "epoch": 0.07909090909090909, |
| "grad_norm": 0.18553867936134338, |
| "learning_rate": 0.0009851301768130304, |
| "loss": 3.0619546508789064, |
| "step": 8700 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.18448372185230255, |
| "learning_rate": 0.0009847820551537288, |
| "loss": 3.076944580078125, |
| "step": 8800 |
| }, |
| { |
| "epoch": 0.0809090909090909, |
| "grad_norm": 0.18073825538158417, |
| "learning_rate": 0.0009844299684700442, |
| "loss": 3.04953857421875, |
| "step": 8900 |
| }, |
| { |
| "epoch": 0.08181818181818182, |
| "grad_norm": 0.18676605820655823, |
| "learning_rate": 0.000984073919641688, |
| "loss": 3.052662658691406, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.08181818181818182, |
| "eval_loss": 3.390735626220703, |
| "eval_runtime": 6.8573, |
| "eval_samples_per_second": 83.999, |
| "eval_steps_per_second": 21.0, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.08272727272727273, |
| "grad_norm": 0.1843118667602539, |
| "learning_rate": 0.0009837139115807777, |
| "loss": 3.0578955078125, |
| "step": 9100 |
| }, |
| { |
| "epoch": 0.08363636363636363, |
| "grad_norm": 0.1908266246318817, |
| "learning_rate": 0.0009833499472318129, |
| "loss": 3.0461907958984376, |
| "step": 9200 |
| }, |
| { |
| "epoch": 0.08454545454545455, |
| "grad_norm": 0.17415334284305573, |
| "learning_rate": 0.0009829820295716525, |
| "loss": 3.0242233276367188, |
| "step": 9300 |
| }, |
| { |
| "epoch": 0.08545454545454545, |
| "grad_norm": 0.161512091755867, |
| "learning_rate": 0.0009826101616094885, |
| "loss": 3.06851806640625, |
| "step": 9400 |
| }, |
| { |
| "epoch": 0.08636363636363636, |
| "grad_norm": 0.17435242235660553, |
| "learning_rate": 0.000982234346386823, |
| "loss": 3.04041015625, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.08727272727272728, |
| "grad_norm": 0.17635726928710938, |
| "learning_rate": 0.0009818545869774427, |
| "loss": 3.0322161865234376, |
| "step": 9600 |
| }, |
| { |
| "epoch": 0.08818181818181818, |
| "grad_norm": 0.19083574414253235, |
| "learning_rate": 0.000981470886487393, |
| "loss": 3.0362371826171874, |
| "step": 9700 |
| }, |
| { |
| "epoch": 0.0890909090909091, |
| "grad_norm": 0.1669977903366089, |
| "learning_rate": 0.000981083248054954, |
| "loss": 3.0415472412109374, |
| "step": 9800 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.1624830961227417, |
| "learning_rate": 0.000980691674850614, |
| "loss": 3.03228271484375, |
| "step": 9900 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 0.20320835709571838, |
| "learning_rate": 0.000980296170077044, |
| "loss": 3.0213031005859374, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "eval_loss": 3.3655972480773926, |
| "eval_runtime": 6.8194, |
| "eval_samples_per_second": 84.465, |
| "eval_steps_per_second": 21.116, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.09181818181818181, |
| "grad_norm": 0.1716221123933792, |
| "learning_rate": 0.000979896736969071, |
| "loss": 3.018829345703125, |
| "step": 10100 |
| }, |
| { |
| "epoch": 0.09272727272727273, |
| "grad_norm": 0.18420584499835968, |
| "learning_rate": 0.0009794933787936513, |
| "loss": 3.0364111328125, |
| "step": 10200 |
| }, |
| { |
| "epoch": 0.09363636363636364, |
| "grad_norm": 0.16853921115398407, |
| "learning_rate": 0.000979086098849845, |
| "loss": 2.9975177001953126, |
| "step": 10300 |
| }, |
| { |
| "epoch": 0.09454545454545454, |
| "grad_norm": 0.17749086022377014, |
| "learning_rate": 0.000978674900468788, |
| "loss": 3.025662536621094, |
| "step": 10400 |
| }, |
| { |
| "epoch": 0.09545454545454546, |
| "grad_norm": 0.17817527055740356, |
| "learning_rate": 0.0009782597870136652, |
| "loss": 3.0068899536132814, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.09636363636363636, |
| "grad_norm": 0.16383598744869232, |
| "learning_rate": 0.0009778407618796824, |
| "loss": 2.9598651123046875, |
| "step": 10600 |
| }, |
| { |
| "epoch": 0.09727272727272727, |
| "grad_norm": 0.18420074880123138, |
| "learning_rate": 0.0009774178284940392, |
| "loss": 2.9876394653320313, |
| "step": 10700 |
| }, |
| { |
| "epoch": 0.09818181818181818, |
| "grad_norm": 0.16747510433197021, |
| "learning_rate": 0.0009769909903159007, |
| "loss": 3.0132855224609374, |
| "step": 10800 |
| }, |
| { |
| "epoch": 0.09909090909090909, |
| "grad_norm": 0.15621648728847504, |
| "learning_rate": 0.0009765602508363697, |
| "loss": 3.0095565795898436, |
| "step": 10900 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.1697891354560852, |
| "learning_rate": 0.0009761256135784568, |
| "loss": 3.0590411376953126, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 3.3478543758392334, |
| "eval_runtime": 6.8379, |
| "eval_samples_per_second": 84.236, |
| "eval_steps_per_second": 21.059, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.1009090909090909, |
| "grad_norm": 0.15818284451961517, |
| "learning_rate": 0.0009756870820970532, |
| "loss": 3.015447692871094, |
| "step": 11100 |
| }, |
| { |
| "epoch": 0.10181818181818182, |
| "grad_norm": 0.16059984266757965, |
| "learning_rate": 0.0009752446599789003, |
| "loss": 2.9939862060546876, |
| "step": 11200 |
| }, |
| { |
| "epoch": 0.10272727272727272, |
| "grad_norm": 0.16179029643535614, |
| "learning_rate": 0.0009747983508425615, |
| "loss": 2.989024963378906, |
| "step": 11300 |
| }, |
| { |
| "epoch": 0.10363636363636364, |
| "grad_norm": 0.16419965028762817, |
| "learning_rate": 0.0009743481583383919, |
| "loss": 2.9855859375, |
| "step": 11400 |
| }, |
| { |
| "epoch": 0.10454545454545454, |
| "grad_norm": 0.17154866456985474, |
| "learning_rate": 0.0009738940861485082, |
| "loss": 2.9723300170898437, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.10545454545454545, |
| "grad_norm": 0.16613702476024628, |
| "learning_rate": 0.0009734361379867597, |
| "loss": 3.022707214355469, |
| "step": 11600 |
| }, |
| { |
| "epoch": 0.10636363636363637, |
| "grad_norm": 0.16711774468421936, |
| "learning_rate": 0.0009729743175986965, |
| "loss": 2.99096923828125, |
| "step": 11700 |
| }, |
| { |
| "epoch": 0.10727272727272727, |
| "grad_norm": 0.16586251556873322, |
| "learning_rate": 0.00097250862876154, |
| "loss": 2.977761535644531, |
| "step": 11800 |
| }, |
| { |
| "epoch": 0.10818181818181818, |
| "grad_norm": 0.1719771921634674, |
| "learning_rate": 0.0009720390752841515, |
| "loss": 2.97351318359375, |
| "step": 11900 |
| }, |
| { |
| "epoch": 0.10909090909090909, |
| "grad_norm": 0.17710699141025543, |
| "learning_rate": 0.000971565661007001, |
| "loss": 2.976995849609375, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.10909090909090909, |
| "eval_loss": 3.324172019958496, |
| "eval_runtime": 6.855, |
| "eval_samples_per_second": 84.026, |
| "eval_steps_per_second": 21.006, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.16330398619174957, |
| "learning_rate": 0.0009710883898021361, |
| "loss": 2.98108154296875, |
| "step": 12100 |
| }, |
| { |
| "epoch": 0.11090909090909092, |
| "grad_norm": 0.16032378375530243, |
| "learning_rate": 0.0009706072655731501, |
| "loss": 2.975714111328125, |
| "step": 12200 |
| }, |
| { |
| "epoch": 0.11181818181818182, |
| "grad_norm": 0.15098635852336884, |
| "learning_rate": 0.00097012229225515, |
| "loss": 2.967715148925781, |
| "step": 12300 |
| }, |
| { |
| "epoch": 0.11272727272727273, |
| "grad_norm": 0.16129878163337708, |
| "learning_rate": 0.0009696334738147246, |
| "loss": 2.9537789916992185, |
| "step": 12400 |
| }, |
| { |
| "epoch": 0.11363636363636363, |
| "grad_norm": 0.1677810102701187, |
| "learning_rate": 0.0009691408142499116, |
| "loss": 2.9610797119140626, |
| "step": 12500 |
| }, |
| { |
| "epoch": 0.11454545454545455, |
| "grad_norm": 0.176312655210495, |
| "learning_rate": 0.0009686443175901656, |
| "loss": 3.0001925659179687, |
| "step": 12600 |
| }, |
| { |
| "epoch": 0.11545454545454545, |
| "grad_norm": 0.16458939015865326, |
| "learning_rate": 0.0009681439878963245, |
| "loss": 2.932486572265625, |
| "step": 12700 |
| }, |
| { |
| "epoch": 0.11636363636363636, |
| "grad_norm": 0.1687006801366806, |
| "learning_rate": 0.0009676398292605766, |
| "loss": 2.96806396484375, |
| "step": 12800 |
| }, |
| { |
| "epoch": 0.11727272727272728, |
| "grad_norm": 0.15523017942905426, |
| "learning_rate": 0.0009671318458064269, |
| "loss": 2.977980651855469, |
| "step": 12900 |
| }, |
| { |
| "epoch": 0.11818181818181818, |
| "grad_norm": 0.15686143934726715, |
| "learning_rate": 0.0009666200416886638, |
| "loss": 2.9614358520507813, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.11818181818181818, |
| "eval_loss": 3.310213565826416, |
| "eval_runtime": 6.7958, |
| "eval_samples_per_second": 84.758, |
| "eval_steps_per_second": 21.19, |
| "step": 13000 |
| }, |
| { |
| "epoch": 0.1190909090909091, |
| "grad_norm": 0.15569010376930237, |
| "learning_rate": 0.0009661044210933246, |
| "loss": 2.950162658691406, |
| "step": 13100 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.15551169216632843, |
| "learning_rate": 0.0009655849882376615, |
| "loss": 2.9463400268554687, |
| "step": 13200 |
| }, |
| { |
| "epoch": 0.12090909090909091, |
| "grad_norm": 0.1576288491487503, |
| "learning_rate": 0.0009650617473701073, |
| "loss": 2.9366680908203127, |
| "step": 13300 |
| }, |
| { |
| "epoch": 0.12181818181818181, |
| "grad_norm": 0.16019435226917267, |
| "learning_rate": 0.0009645347027702405, |
| "loss": 2.9609390258789063, |
| "step": 13400 |
| }, |
| { |
| "epoch": 0.12272727272727273, |
| "grad_norm": 0.19406898319721222, |
| "learning_rate": 0.0009640038587487499, |
| "loss": 2.9381414794921876, |
| "step": 13500 |
| }, |
| { |
| "epoch": 0.12363636363636364, |
| "grad_norm": 0.14867821335792542, |
| "learning_rate": 0.0009634692196474001, |
| "loss": 2.943419189453125, |
| "step": 13600 |
| }, |
| { |
| "epoch": 0.12454545454545454, |
| "grad_norm": 0.14702503383159637, |
| "learning_rate": 0.0009629307898389953, |
| "loss": 2.923211669921875, |
| "step": 13700 |
| }, |
| { |
| "epoch": 0.12545454545454546, |
| "grad_norm": 0.19858944416046143, |
| "learning_rate": 0.0009623885737273442, |
| "loss": 2.9624624633789063, |
| "step": 13800 |
| }, |
| { |
| "epoch": 0.12636363636363637, |
| "grad_norm": 0.15279068052768707, |
| "learning_rate": 0.0009618425757472229, |
| "loss": 2.9194540405273437, |
| "step": 13900 |
| }, |
| { |
| "epoch": 0.12727272727272726, |
| "grad_norm": 0.16745012998580933, |
| "learning_rate": 0.0009612928003643404, |
| "loss": 2.950616760253906, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.12727272727272726, |
| "eval_loss": 3.294524669647217, |
| "eval_runtime": 6.7865, |
| "eval_samples_per_second": 84.874, |
| "eval_steps_per_second": 21.218, |
| "step": 14000 |
| }, |
| { |
| "epoch": 0.12818181818181817, |
| "grad_norm": 0.15464717149734497, |
| "learning_rate": 0.0009607392520753, |
| "loss": 2.936573791503906, |
| "step": 14100 |
| }, |
| { |
| "epoch": 0.1290909090909091, |
| "grad_norm": 0.17451342940330505, |
| "learning_rate": 0.0009601819354075643, |
| "loss": 2.9196566772460937, |
| "step": 14200 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.15395045280456543, |
| "learning_rate": 0.0009596208549194167, |
| "loss": 2.9657086181640624, |
| "step": 14300 |
| }, |
| { |
| "epoch": 0.13090909090909092, |
| "grad_norm": 0.16990916430950165, |
| "learning_rate": 0.0009590560151999256, |
| "loss": 2.9283480834960938, |
| "step": 14400 |
| }, |
| { |
| "epoch": 0.1318181818181818, |
| "grad_norm": 0.14847813546657562, |
| "learning_rate": 0.0009584874208689055, |
| "loss": 2.9426678466796874, |
| "step": 14500 |
| }, |
| { |
| "epoch": 0.13272727272727272, |
| "grad_norm": 0.21499793231487274, |
| "learning_rate": 0.00095791507657688, |
| "loss": 2.9166836547851562, |
| "step": 14600 |
| }, |
| { |
| "epoch": 0.13363636363636364, |
| "grad_norm": 0.14092333614826202, |
| "learning_rate": 0.0009573389870050435, |
| "loss": 2.9289419555664065, |
| "step": 14700 |
| }, |
| { |
| "epoch": 0.13454545454545455, |
| "grad_norm": 0.15405072271823883, |
| "learning_rate": 0.0009567591568652231, |
| "loss": 2.9462161254882813, |
| "step": 14800 |
| }, |
| { |
| "epoch": 0.13545454545454547, |
| "grad_norm": 0.15389932692050934, |
| "learning_rate": 0.00095617559089984, |
| "loss": 2.9510357666015623, |
| "step": 14900 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 0.157777339220047, |
| "learning_rate": 0.0009555882938818703, |
| "loss": 2.9332815551757814, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "eval_loss": 3.2715365886688232, |
| "eval_runtime": 6.8421, |
| "eval_samples_per_second": 84.184, |
| "eval_steps_per_second": 21.046, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.13727272727272727, |
| "grad_norm": 0.15498115122318268, |
| "learning_rate": 0.0009549972706148067, |
| "loss": 2.9289910888671873, |
| "step": 15100 |
| }, |
| { |
| "epoch": 0.13818181818181818, |
| "grad_norm": 0.17162440717220306, |
| "learning_rate": 0.0009544025259326188, |
| "loss": 2.9223281860351564, |
| "step": 15200 |
| }, |
| { |
| "epoch": 0.1390909090909091, |
| "grad_norm": 0.16399726271629333, |
| "learning_rate": 0.0009538040646997133, |
| "loss": 2.910879821777344, |
| "step": 15300 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.20758388936519623, |
| "learning_rate": 0.0009532018918108949, |
| "loss": 2.9101876831054687, |
| "step": 15400 |
| }, |
| { |
| "epoch": 0.1409090909090909, |
| "grad_norm": 0.15389910340309143, |
| "learning_rate": 0.0009525960121913253, |
| "loss": 2.9736376953125, |
| "step": 15500 |
| }, |
| { |
| "epoch": 0.14181818181818182, |
| "grad_norm": 0.14939367771148682, |
| "learning_rate": 0.0009519864307964842, |
| "loss": 2.9354534912109376, |
| "step": 15600 |
| }, |
| { |
| "epoch": 0.14272727272727273, |
| "grad_norm": 0.18233561515808105, |
| "learning_rate": 0.0009513731526121277, |
| "loss": 2.9248681640625, |
| "step": 15700 |
| }, |
| { |
| "epoch": 0.14363636363636365, |
| "grad_norm": 0.16295863687992096, |
| "learning_rate": 0.0009507561826542477, |
| "loss": 2.92017578125, |
| "step": 15800 |
| }, |
| { |
| "epoch": 0.14454545454545453, |
| "grad_norm": 0.15371564030647278, |
| "learning_rate": 0.0009501355259690314, |
| "loss": 2.910662841796875, |
| "step": 15900 |
| }, |
| { |
| "epoch": 0.14545454545454545, |
| "grad_norm": 0.15596537292003632, |
| "learning_rate": 0.0009495111876328195, |
| "loss": 2.898775939941406, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.14545454545454545, |
| "eval_loss": 3.2674407958984375, |
| "eval_runtime": 6.8454, |
| "eval_samples_per_second": 84.143, |
| "eval_steps_per_second": 21.036, |
| "step": 16000 |
| }, |
| { |
| "epoch": 0.14636363636363636, |
| "grad_norm": 0.23435284197330475, |
| "learning_rate": 0.0009488831727520647, |
| "loss": 2.925650939941406, |
| "step": 16100 |
| }, |
| { |
| "epoch": 0.14727272727272728, |
| "grad_norm": 0.1385786384344101, |
| "learning_rate": 0.0009482514864632905, |
| "loss": 2.935544738769531, |
| "step": 16200 |
| }, |
| { |
| "epoch": 0.1481818181818182, |
| "grad_norm": 0.15425068140029907, |
| "learning_rate": 0.0009476161339330484, |
| "loss": 2.8958169555664064, |
| "step": 16300 |
| }, |
| { |
| "epoch": 0.14909090909090908, |
| "grad_norm": 0.16746921837329865, |
| "learning_rate": 0.0009469771203578765, |
| "loss": 2.886453857421875, |
| "step": 16400 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.15813444554805756, |
| "learning_rate": 0.000946334450964256, |
| "loss": 2.8945297241210937, |
| "step": 16500 |
| }, |
| { |
| "epoch": 0.1509090909090909, |
| "grad_norm": 0.16391652822494507, |
| "learning_rate": 0.0009456881310085692, |
| "loss": 2.871600341796875, |
| "step": 16600 |
| }, |
| { |
| "epoch": 0.15181818181818182, |
| "grad_norm": 0.14185769855976105, |
| "learning_rate": 0.0009450381657770563, |
| "loss": 2.8975213623046874, |
| "step": 16700 |
| }, |
| { |
| "epoch": 0.15272727272727274, |
| "grad_norm": 0.16267341375350952, |
| "learning_rate": 0.0009443845605857722, |
| "loss": 2.894129333496094, |
| "step": 16800 |
| }, |
| { |
| "epoch": 0.15363636363636363, |
| "grad_norm": 0.15159358084201813, |
| "learning_rate": 0.0009437273207805428, |
| "loss": 2.9036929321289064, |
| "step": 16900 |
| }, |
| { |
| "epoch": 0.15454545454545454, |
| "grad_norm": 0.19526581466197968, |
| "learning_rate": 0.0009430664517369216, |
| "loss": 2.9116668701171875, |
| "step": 17000 |
| }, |
| { |
| "epoch": 0.15454545454545454, |
| "eval_loss": 3.2496325969696045, |
| "eval_runtime": 6.8339, |
| "eval_samples_per_second": 84.285, |
| "eval_steps_per_second": 21.071, |
| "step": 17000 |
| }, |
| { |
| "epoch": 0.15545454545454546, |
| "grad_norm": 0.1410096138715744, |
| "learning_rate": 0.0009424019588601458, |
| "loss": 2.879241943359375, |
| "step": 17100 |
| }, |
| { |
| "epoch": 0.15636363636363637, |
| "grad_norm": 0.1442963033914566, |
| "learning_rate": 0.0009417338475850911, |
| "loss": 2.892339172363281, |
| "step": 17200 |
| }, |
| { |
| "epoch": 0.1572727272727273, |
| "grad_norm": 0.16006037592887878, |
| "learning_rate": 0.000941062123376229, |
| "loss": 2.8745999145507812, |
| "step": 17300 |
| }, |
| { |
| "epoch": 0.15818181818181817, |
| "grad_norm": 0.15137411653995514, |
| "learning_rate": 0.0009403867917275805, |
| "loss": 2.9007733154296873, |
| "step": 17400 |
| }, |
| { |
| "epoch": 0.1590909090909091, |
| "grad_norm": 0.15556079149246216, |
| "learning_rate": 0.0009397078581626718, |
| "loss": 2.8890725708007814, |
| "step": 17500 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.1370605081319809, |
| "learning_rate": 0.0009390253282344894, |
| "loss": 2.8879302978515624, |
| "step": 17600 |
| }, |
| { |
| "epoch": 0.16090909090909092, |
| "grad_norm": 0.15012328326702118, |
| "learning_rate": 0.0009383392075254342, |
| "loss": 2.870147399902344, |
| "step": 17700 |
| }, |
| { |
| "epoch": 0.1618181818181818, |
| "grad_norm": 0.15628907084465027, |
| "learning_rate": 0.0009376495016472762, |
| "loss": 2.899383239746094, |
| "step": 17800 |
| }, |
| { |
| "epoch": 0.16272727272727272, |
| "grad_norm": 0.172128364443779, |
| "learning_rate": 0.0009369562162411083, |
| "loss": 2.8812881469726563, |
| "step": 17900 |
| }, |
| { |
| "epoch": 0.16363636363636364, |
| "grad_norm": 0.15035715699195862, |
| "learning_rate": 0.0009362593569773001, |
| "loss": 2.893328857421875, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.16363636363636364, |
| "eval_loss": 3.241589069366455, |
| "eval_runtime": 6.7941, |
| "eval_samples_per_second": 84.779, |
| "eval_steps_per_second": 21.195, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.16454545454545455, |
| "grad_norm": 0.14139075577259064, |
| "learning_rate": 0.0009355589295554522, |
| "loss": 2.9356817626953124, |
| "step": 18100 |
| }, |
| { |
| "epoch": 0.16545454545454547, |
| "grad_norm": 0.22561536729335785, |
| "learning_rate": 0.0009348549397043489, |
| "loss": 2.8875466918945314, |
| "step": 18200 |
| }, |
| { |
| "epoch": 0.16636363636363635, |
| "grad_norm": 0.1523270159959793, |
| "learning_rate": 0.0009341473931819113, |
| "loss": 2.917890930175781, |
| "step": 18300 |
| }, |
| { |
| "epoch": 0.16727272727272727, |
| "grad_norm": 0.14544081687927246, |
| "learning_rate": 0.0009334362957751506, |
| "loss": 2.901419677734375, |
| "step": 18400 |
| }, |
| { |
| "epoch": 0.16818181818181818, |
| "grad_norm": 0.13483288884162903, |
| "learning_rate": 0.000932721653300121, |
| "loss": 2.9169821166992187, |
| "step": 18500 |
| }, |
| { |
| "epoch": 0.1690909090909091, |
| "grad_norm": 0.17061568796634674, |
| "learning_rate": 0.0009320034716018713, |
| "loss": 2.865706481933594, |
| "step": 18600 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.15831294655799866, |
| "learning_rate": 0.0009312817565543976, |
| "loss": 2.9071807861328125, |
| "step": 18700 |
| }, |
| { |
| "epoch": 0.1709090909090909, |
| "grad_norm": 0.1500754952430725, |
| "learning_rate": 0.0009305565140605957, |
| "loss": 2.8990237426757814, |
| "step": 18800 |
| }, |
| { |
| "epoch": 0.17181818181818181, |
| "grad_norm": 0.16387759149074554, |
| "learning_rate": 0.0009298277500522112, |
| "loss": 2.884671325683594, |
| "step": 18900 |
| }, |
| { |
| "epoch": 0.17272727272727273, |
| "grad_norm": 0.13598468899726868, |
| "learning_rate": 0.0009290954704897934, |
| "loss": 2.886610412597656, |
| "step": 19000 |
| }, |
| { |
| "epoch": 0.17272727272727273, |
| "eval_loss": 3.222428560256958, |
| "eval_runtime": 6.8544, |
| "eval_samples_per_second": 84.034, |
| "eval_steps_per_second": 21.008, |
| "step": 19000 |
| }, |
| { |
| "epoch": 0.17363636363636364, |
| "grad_norm": 0.17809490859508514, |
| "learning_rate": 0.0009283596813626444, |
| "loss": 2.8785455322265623, |
| "step": 19100 |
| }, |
| { |
| "epoch": 0.17454545454545456, |
| "grad_norm": 0.15393967926502228, |
| "learning_rate": 0.0009276203886887714, |
| "loss": 2.9021951293945314, |
| "step": 19200 |
| }, |
| { |
| "epoch": 0.17545454545454545, |
| "grad_norm": 0.1531384289264679, |
| "learning_rate": 0.0009268775985148369, |
| "loss": 2.900225830078125, |
| "step": 19300 |
| }, |
| { |
| "epoch": 0.17636363636363636, |
| "grad_norm": 0.1720549464225769, |
| "learning_rate": 0.0009261313169161094, |
| "loss": 2.8924365234375, |
| "step": 19400 |
| }, |
| { |
| "epoch": 0.17727272727272728, |
| "grad_norm": 0.17175054550170898, |
| "learning_rate": 0.0009253815499964135, |
| "loss": 2.8840255737304688, |
| "step": 19500 |
| }, |
| { |
| "epoch": 0.1781818181818182, |
| "grad_norm": 0.1715477555990219, |
| "learning_rate": 0.0009246283038880809, |
| "loss": 2.8627389526367186, |
| "step": 19600 |
| }, |
| { |
| "epoch": 0.17909090909090908, |
| "grad_norm": 0.17474284768104553, |
| "learning_rate": 0.0009238715847518984, |
| "loss": 2.887270812988281, |
| "step": 19700 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.15692177414894104, |
| "learning_rate": 0.0009231113987770599, |
| "loss": 2.890269775390625, |
| "step": 19800 |
| }, |
| { |
| "epoch": 0.1809090909090909, |
| "grad_norm": 0.15938249230384827, |
| "learning_rate": 0.0009223477521811132, |
| "loss": 2.9025338745117186, |
| "step": 19900 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 0.14352673292160034, |
| "learning_rate": 0.0009215806512099115, |
| "loss": 2.9029974365234374, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "eval_loss": 3.218810558319092, |
| "eval_runtime": 6.8249, |
| "eval_samples_per_second": 84.397, |
| "eval_steps_per_second": 21.099, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.18272727272727274, |
| "grad_norm": 0.1414630264043808, |
| "learning_rate": 0.000920810102137561, |
| "loss": 2.8807022094726564, |
| "step": 20100 |
| }, |
| { |
| "epoch": 0.18363636363636363, |
| "grad_norm": 0.1559121161699295, |
| "learning_rate": 0.0009200361112663695, |
| "loss": 2.845583190917969, |
| "step": 20200 |
| }, |
| { |
| "epoch": 0.18454545454545454, |
| "grad_norm": 0.13616813719272614, |
| "learning_rate": 0.0009192586849267957, |
| "loss": 2.8783746337890626, |
| "step": 20300 |
| }, |
| { |
| "epoch": 0.18545454545454546, |
| "grad_norm": 0.15556134283542633, |
| "learning_rate": 0.0009184778294773968, |
| "loss": 2.84674072265625, |
| "step": 20400 |
| }, |
| { |
| "epoch": 0.18636363636363637, |
| "grad_norm": 0.1401907503604889, |
| "learning_rate": 0.0009176935513047762, |
| "loss": 2.8818963623046874, |
| "step": 20500 |
| }, |
| { |
| "epoch": 0.18727272727272729, |
| "grad_norm": 0.1431131362915039, |
| "learning_rate": 0.0009169058568235323, |
| "loss": 2.8781854248046876, |
| "step": 20600 |
| }, |
| { |
| "epoch": 0.18818181818181817, |
| "grad_norm": 0.17515692114830017, |
| "learning_rate": 0.0009161147524762053, |
| "loss": 2.85051025390625, |
| "step": 20700 |
| }, |
| { |
| "epoch": 0.1890909090909091, |
| "grad_norm": 0.1567743867635727, |
| "learning_rate": 0.0009153202447332243, |
| "loss": 2.8653643798828123, |
| "step": 20800 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.14393377304077148, |
| "learning_rate": 0.000914522340092855, |
| "loss": 2.881787109375, |
| "step": 20900 |
| }, |
| { |
| "epoch": 0.19090909090909092, |
| "grad_norm": 0.1467711478471756, |
| "learning_rate": 0.0009137210450811462, |
| "loss": 2.9003524780273438, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.19090909090909092, |
| "eval_loss": 3.210813283920288, |
| "eval_runtime": 6.8446, |
| "eval_samples_per_second": 84.154, |
| "eval_steps_per_second": 21.038, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.1918181818181818, |
| "grad_norm": 0.14093157649040222, |
| "learning_rate": 0.0009129163662518766, |
| "loss": 2.834397277832031, |
| "step": 21100 |
| }, |
| { |
| "epoch": 0.19272727272727272, |
| "grad_norm": 0.14963804185390472, |
| "learning_rate": 0.000912108310186501, |
| "loss": 2.869900817871094, |
| "step": 21200 |
| }, |
| { |
| "epoch": 0.19363636363636363, |
| "grad_norm": 0.13998101651668549, |
| "learning_rate": 0.0009112968834940965, |
| "loss": 2.8689230346679686, |
| "step": 21300 |
| }, |
| { |
| "epoch": 0.19454545454545455, |
| "grad_norm": 0.13820187747478485, |
| "learning_rate": 0.0009104820928113083, |
| "loss": 2.840967102050781, |
| "step": 21400 |
| }, |
| { |
| "epoch": 0.19545454545454546, |
| "grad_norm": 0.1391438990831375, |
| "learning_rate": 0.0009096639448022963, |
| "loss": 2.839700927734375, |
| "step": 21500 |
| }, |
| { |
| "epoch": 0.19636363636363635, |
| "grad_norm": 0.15131688117980957, |
| "learning_rate": 0.0009088424461586793, |
| "loss": 2.8546661376953124, |
| "step": 21600 |
| }, |
| { |
| "epoch": 0.19727272727272727, |
| "grad_norm": 0.14853839576244354, |
| "learning_rate": 0.000908017603599481, |
| "loss": 2.8781912231445315, |
| "step": 21700 |
| }, |
| { |
| "epoch": 0.19818181818181818, |
| "grad_norm": 0.16618646681308746, |
| "learning_rate": 0.0009071894238710749, |
| "loss": 2.8425857543945314, |
| "step": 21800 |
| }, |
| { |
| "epoch": 0.1990909090909091, |
| "grad_norm": 0.13768044114112854, |
| "learning_rate": 0.0009063579137471296, |
| "loss": 2.8587716674804686, |
| "step": 21900 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.1462126523256302, |
| "learning_rate": 0.0009055230800285523, |
| "loss": 2.854002685546875, |
| "step": 22000 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 3.1955888271331787, |
| "eval_runtime": 6.8048, |
| "eval_samples_per_second": 84.646, |
| "eval_steps_per_second": 21.161, |
| "step": 22000 |
| }, |
| { |
| "epoch": 0.2009090909090909, |
| "grad_norm": 0.1481468826532364, |
| "learning_rate": 0.0009046849295434343, |
| "loss": 2.848748779296875, |
| "step": 22100 |
| }, |
| { |
| "epoch": 0.2018181818181818, |
| "grad_norm": 0.13478662073612213, |
| "learning_rate": 0.0009038434691469946, |
| "loss": 2.859345703125, |
| "step": 22200 |
| }, |
| { |
| "epoch": 0.20272727272727273, |
| "grad_norm": 0.1626402586698532, |
| "learning_rate": 0.0009029987057215234, |
| "loss": 2.879791259765625, |
| "step": 22300 |
| }, |
| { |
| "epoch": 0.20363636363636364, |
| "grad_norm": 0.1763114631175995, |
| "learning_rate": 0.0009021506461763272, |
| "loss": 2.8198529052734376, |
| "step": 22400 |
| }, |
| { |
| "epoch": 0.20454545454545456, |
| "grad_norm": 0.1592358946800232, |
| "learning_rate": 0.0009012992974476706, |
| "loss": 2.8292422485351563, |
| "step": 22500 |
| }, |
| { |
| "epoch": 0.20545454545454545, |
| "grad_norm": 0.16374371945858002, |
| "learning_rate": 0.0009004446664987209, |
| "loss": 2.839366149902344, |
| "step": 22600 |
| }, |
| { |
| "epoch": 0.20636363636363636, |
| "grad_norm": 0.16180269420146942, |
| "learning_rate": 0.0008995867603194905, |
| "loss": 2.824099426269531, |
| "step": 22700 |
| }, |
| { |
| "epoch": 0.20727272727272728, |
| "grad_norm": 0.1817290335893631, |
| "learning_rate": 0.0008987255859267796, |
| "loss": 2.852536926269531, |
| "step": 22800 |
| }, |
| { |
| "epoch": 0.2081818181818182, |
| "grad_norm": 0.1729678362607956, |
| "learning_rate": 0.0008978611503641194, |
| "loss": 2.87031005859375, |
| "step": 22900 |
| }, |
| { |
| "epoch": 0.20909090909090908, |
| "grad_norm": 0.13794034719467163, |
| "learning_rate": 0.000896993460701714, |
| "loss": 2.820664367675781, |
| "step": 23000 |
| }, |
| { |
| "epoch": 0.20909090909090908, |
| "eval_loss": 3.189971923828125, |
| "eval_runtime": 6.8545, |
| "eval_samples_per_second": 84.032, |
| "eval_steps_per_second": 21.008, |
| "step": 23000 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.14675737917423248, |
| "learning_rate": 0.0008961225240363826, |
| "loss": 2.834775390625, |
| "step": 23100 |
| }, |
| { |
| "epoch": 0.2109090909090909, |
| "grad_norm": 0.14198128879070282, |
| "learning_rate": 0.0008952483474915021, |
| "loss": 2.8415087890625, |
| "step": 23200 |
| }, |
| { |
| "epoch": 0.21181818181818182, |
| "grad_norm": 0.15185648202896118, |
| "learning_rate": 0.0008943709382169476, |
| "loss": 2.8519711303710937, |
| "step": 23300 |
| }, |
| { |
| "epoch": 0.21272727272727274, |
| "grad_norm": 0.15163777768611908, |
| "learning_rate": 0.0008934903033890352, |
| "loss": 2.8500375366210937, |
| "step": 23400 |
| }, |
| { |
| "epoch": 0.21363636363636362, |
| "grad_norm": 0.15410897135734558, |
| "learning_rate": 0.0008926064502104623, |
| "loss": 2.8353033447265625, |
| "step": 23500 |
| }, |
| { |
| "epoch": 0.21454545454545454, |
| "grad_norm": 0.22796989977359772, |
| "learning_rate": 0.0008917193859102497, |
| "loss": 2.8228555297851563, |
| "step": 23600 |
| }, |
| { |
| "epoch": 0.21545454545454545, |
| "grad_norm": 0.1605440229177475, |
| "learning_rate": 0.0008908291177436813, |
| "loss": 2.8567230224609377, |
| "step": 23700 |
| }, |
| { |
| "epoch": 0.21636363636363637, |
| "grad_norm": 0.16412964463233948, |
| "learning_rate": 0.0008899356529922459, |
| "loss": 2.8504483032226564, |
| "step": 23800 |
| }, |
| { |
| "epoch": 0.21727272727272728, |
| "grad_norm": 0.13510747253894806, |
| "learning_rate": 0.0008890389989635767, |
| "loss": 2.87345458984375, |
| "step": 23900 |
| }, |
| { |
| "epoch": 0.21818181818181817, |
| "grad_norm": 0.14522412419319153, |
| "learning_rate": 0.0008881391629913921, |
| "loss": 2.827217712402344, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.21818181818181817, |
| "eval_loss": 3.1835873126983643, |
| "eval_runtime": 6.8315, |
| "eval_samples_per_second": 84.315, |
| "eval_steps_per_second": 21.079, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.2190909090909091, |
| "grad_norm": 0.15911774337291718, |
| "learning_rate": 0.0008872361524354357, |
| "loss": 2.8208258056640627, |
| "step": 24100 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.14365383982658386, |
| "learning_rate": 0.0008863299746814158, |
| "loss": 2.82010986328125, |
| "step": 24200 |
| }, |
| { |
| "epoch": 0.22090909090909092, |
| "grad_norm": 0.16335056722164154, |
| "learning_rate": 0.0008854206371409452, |
| "loss": 2.863214416503906, |
| "step": 24300 |
| }, |
| { |
| "epoch": 0.22181818181818183, |
| "grad_norm": 0.15806064009666443, |
| "learning_rate": 0.0008845081472514806, |
| "loss": 2.8272698974609374, |
| "step": 24400 |
| }, |
| { |
| "epoch": 0.22272727272727272, |
| "grad_norm": 0.1631830632686615, |
| "learning_rate": 0.0008835925124762616, |
| "loss": 2.8286688232421877, |
| "step": 24500 |
| }, |
| { |
| "epoch": 0.22363636363636363, |
| "grad_norm": 0.142561137676239, |
| "learning_rate": 0.0008826737403042499, |
| "loss": 2.823035888671875, |
| "step": 24600 |
| }, |
| { |
| "epoch": 0.22454545454545455, |
| "grad_norm": 0.17523014545440674, |
| "learning_rate": 0.0008817518382500677, |
| "loss": 2.830491027832031, |
| "step": 24700 |
| }, |
| { |
| "epoch": 0.22545454545454546, |
| "grad_norm": 0.15598313510417938, |
| "learning_rate": 0.0008808268138539369, |
| "loss": 2.8227529907226563, |
| "step": 24800 |
| }, |
| { |
| "epoch": 0.22636363636363635, |
| "grad_norm": 0.1439158320426941, |
| "learning_rate": 0.0008798986746816162, |
| "loss": 2.8210317993164065, |
| "step": 24900 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 0.14227908849716187, |
| "learning_rate": 0.0008789674283243409, |
| "loss": 2.8191732788085937, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "eval_loss": 3.1780831813812256, |
| "eval_runtime": 6.8053, |
| "eval_samples_per_second": 84.639, |
| "eval_steps_per_second": 21.16, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.22818181818181818, |
| "grad_norm": 0.15105608105659485, |
| "learning_rate": 0.0008780330823987592, |
| "loss": 2.8317742919921876, |
| "step": 25100 |
| }, |
| { |
| "epoch": 0.2290909090909091, |
| "grad_norm": 0.16510829329490662, |
| "learning_rate": 0.0008770956445468713, |
| "loss": 2.8396697998046876, |
| "step": 25200 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.13736529648303986, |
| "learning_rate": 0.0008761551224359657, |
| "loss": 2.859419860839844, |
| "step": 25300 |
| }, |
| { |
| "epoch": 0.2309090909090909, |
| "grad_norm": 0.17783844470977783, |
| "learning_rate": 0.0008752115237585567, |
| "loss": 2.813878173828125, |
| "step": 25400 |
| }, |
| { |
| "epoch": 0.2318181818181818, |
| "grad_norm": 0.15228304266929626, |
| "learning_rate": 0.0008742648562323228, |
| "loss": 2.7972647094726564, |
| "step": 25500 |
| }, |
| { |
| "epoch": 0.23272727272727273, |
| "grad_norm": 0.17638841271400452, |
| "learning_rate": 0.0008733151276000417, |
| "loss": 2.84191650390625, |
| "step": 25600 |
| }, |
| { |
| "epoch": 0.23363636363636364, |
| "grad_norm": 0.15283086895942688, |
| "learning_rate": 0.0008723623456295282, |
| "loss": 2.8249298095703126, |
| "step": 25700 |
| }, |
| { |
| "epoch": 0.23454545454545456, |
| "grad_norm": 0.15044672787189484, |
| "learning_rate": 0.0008714065181135701, |
| "loss": 2.8220599365234373, |
| "step": 25800 |
| }, |
| { |
| "epoch": 0.23545454545454544, |
| "grad_norm": 0.149523064494133, |
| "learning_rate": 0.0008704476528698649, |
| "loss": 2.7989315795898437, |
| "step": 25900 |
| }, |
| { |
| "epoch": 0.23636363636363636, |
| "grad_norm": 0.15856775641441345, |
| "learning_rate": 0.0008694857577409556, |
| "loss": 2.7933050537109376, |
| "step": 26000 |
| }, |
| { |
| "epoch": 0.23636363636363636, |
| "eval_loss": 3.1705970764160156, |
| "eval_runtime": 6.8357, |
| "eval_samples_per_second": 84.264, |
| "eval_steps_per_second": 21.066, |
| "step": 26000 |
| }, |
| { |
| "epoch": 0.23727272727272727, |
| "grad_norm": 0.15482839941978455, |
| "learning_rate": 0.0008685208405941662, |
| "loss": 2.8198681640625, |
| "step": 26100 |
| }, |
| { |
| "epoch": 0.2381818181818182, |
| "grad_norm": 0.14043229818344116, |
| "learning_rate": 0.0008675529093215384, |
| "loss": 2.8507424926757814, |
| "step": 26200 |
| }, |
| { |
| "epoch": 0.2390909090909091, |
| "grad_norm": 0.13602057099342346, |
| "learning_rate": 0.0008665819718397658, |
| "loss": 2.841172180175781, |
| "step": 26300 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.1507735699415207, |
| "learning_rate": 0.0008656080360901299, |
| "loss": 2.8332550048828127, |
| "step": 26400 |
| }, |
| { |
| "epoch": 0.2409090909090909, |
| "grad_norm": 0.14570394158363342, |
| "learning_rate": 0.0008646311100384352, |
| "loss": 2.815726013183594, |
| "step": 26500 |
| }, |
| { |
| "epoch": 0.24181818181818182, |
| "grad_norm": 0.15119144320487976, |
| "learning_rate": 0.0008636512016749436, |
| "loss": 2.7973052978515627, |
| "step": 26600 |
| }, |
| { |
| "epoch": 0.24272727272727274, |
| "grad_norm": 0.1478470116853714, |
| "learning_rate": 0.0008626683190143092, |
| "loss": 2.8057537841796876, |
| "step": 26700 |
| }, |
| { |
| "epoch": 0.24363636363636362, |
| "grad_norm": 0.17405441403388977, |
| "learning_rate": 0.0008616824700955132, |
| "loss": 2.8201614379882813, |
| "step": 26800 |
| }, |
| { |
| "epoch": 0.24454545454545454, |
| "grad_norm": 0.1828102022409439, |
| "learning_rate": 0.0008606936629817973, |
| "loss": 2.817716064453125, |
| "step": 26900 |
| }, |
| { |
| "epoch": 0.24545454545454545, |
| "grad_norm": 0.1402510702610016, |
| "learning_rate": 0.0008597019057605986, |
| "loss": 2.8126416015625, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.24545454545454545, |
| "eval_loss": 3.1654067039489746, |
| "eval_runtime": 6.8224, |
| "eval_samples_per_second": 84.428, |
| "eval_steps_per_second": 21.107, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.24636363636363637, |
| "grad_norm": 0.15282770991325378, |
| "learning_rate": 0.000858707206543483, |
| "loss": 2.814878234863281, |
| "step": 27100 |
| }, |
| { |
| "epoch": 0.24727272727272728, |
| "grad_norm": 0.1374608278274536, |
| "learning_rate": 0.0008577095734660788, |
| "loss": 2.8010260009765626, |
| "step": 27200 |
| }, |
| { |
| "epoch": 0.24818181818181817, |
| "grad_norm": 0.14548851549625397, |
| "learning_rate": 0.0008567090146880105, |
| "loss": 2.828005676269531, |
| "step": 27300 |
| }, |
| { |
| "epoch": 0.24909090909090909, |
| "grad_norm": 0.1567397266626358, |
| "learning_rate": 0.0008557055383928316, |
| "loss": 2.78892578125, |
| "step": 27400 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.17172624170780182, |
| "learning_rate": 0.0008546991527879581, |
| "loss": 2.8362548828125, |
| "step": 27500 |
| }, |
| { |
| "epoch": 0.2509090909090909, |
| "grad_norm": 0.1834629327058792, |
| "learning_rate": 0.000853689866104601, |
| "loss": 2.799326171875, |
| "step": 27600 |
| }, |
| { |
| "epoch": 0.25181818181818183, |
| "grad_norm": 0.14964266121387482, |
| "learning_rate": 0.0008526776865976997, |
| "loss": 2.7806500244140624, |
| "step": 27700 |
| }, |
| { |
| "epoch": 0.25272727272727274, |
| "grad_norm": 0.1613718867301941, |
| "learning_rate": 0.0008516626225458535, |
| "loss": 2.8114141845703124, |
| "step": 27800 |
| }, |
| { |
| "epoch": 0.25363636363636366, |
| "grad_norm": 0.15746520459651947, |
| "learning_rate": 0.0008506446822512541, |
| "loss": 2.7960455322265627, |
| "step": 27900 |
| }, |
| { |
| "epoch": 0.2545454545454545, |
| "grad_norm": 0.14515548944473267, |
| "learning_rate": 0.0008496238740396188, |
| "loss": 2.848003234863281, |
| "step": 28000 |
| }, |
| { |
| "epoch": 0.2545454545454545, |
| "eval_loss": 3.1647140979766846, |
| "eval_runtime": 6.7942, |
| "eval_samples_per_second": 84.778, |
| "eval_steps_per_second": 21.195, |
| "step": 28000 |
| }, |
| { |
| "epoch": 0.25545454545454543, |
| "grad_norm": 0.1713736206293106, |
| "learning_rate": 0.0008486002062601203, |
| "loss": 2.8171258544921876, |
| "step": 28100 |
| }, |
| { |
| "epoch": 0.25636363636363635, |
| "grad_norm": 0.18038378655910492, |
| "learning_rate": 0.000847573687285321, |
| "loss": 2.8066680908203123, |
| "step": 28200 |
| }, |
| { |
| "epoch": 0.25727272727272726, |
| "grad_norm": 0.1601206362247467, |
| "learning_rate": 0.0008465443255111025, |
| "loss": 2.8091595458984373, |
| "step": 28300 |
| }, |
| { |
| "epoch": 0.2581818181818182, |
| "grad_norm": 0.15122343599796295, |
| "learning_rate": 0.0008455121293565974, |
| "loss": 2.8354150390625, |
| "step": 28400 |
| }, |
| { |
| "epoch": 0.2590909090909091, |
| "grad_norm": 0.1411023885011673, |
| "learning_rate": 0.000844477107264121, |
| "loss": 2.805926513671875, |
| "step": 28500 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.1714688241481781, |
| "learning_rate": 0.0008434392676991018, |
| "loss": 2.774625244140625, |
| "step": 28600 |
| }, |
| { |
| "epoch": 0.2609090909090909, |
| "grad_norm": 0.14336396753787994, |
| "learning_rate": 0.0008423986191500126, |
| "loss": 2.806527099609375, |
| "step": 28700 |
| }, |
| { |
| "epoch": 0.26181818181818184, |
| "grad_norm": 0.14724823832511902, |
| "learning_rate": 0.0008413551701283003, |
| "loss": 2.7858685302734374, |
| "step": 28800 |
| }, |
| { |
| "epoch": 0.26272727272727275, |
| "grad_norm": 0.1667833775281906, |
| "learning_rate": 0.0008403089291683173, |
| "loss": 2.788014221191406, |
| "step": 28900 |
| }, |
| { |
| "epoch": 0.2636363636363636, |
| "grad_norm": 0.13815470039844513, |
| "learning_rate": 0.0008392599048272509, |
| "loss": 2.7937637329101563, |
| "step": 29000 |
| }, |
| { |
| "epoch": 0.2636363636363636, |
| "eval_loss": 3.1548070907592773, |
| "eval_runtime": 6.8019, |
| "eval_samples_per_second": 84.682, |
| "eval_steps_per_second": 21.171, |
| "step": 29000 |
| }, |
| { |
| "epoch": 0.26454545454545453, |
| "grad_norm": 0.1442345827817917, |
| "learning_rate": 0.0008382081056850541, |
| "loss": 2.77263671875, |
| "step": 29100 |
| }, |
| { |
| "epoch": 0.26545454545454544, |
| "grad_norm": 0.14780735969543457, |
| "learning_rate": 0.0008371535403443743, |
| "loss": 2.8082760620117186, |
| "step": 29200 |
| }, |
| { |
| "epoch": 0.26636363636363636, |
| "grad_norm": 0.13575103878974915, |
| "learning_rate": 0.000836096217430484, |
| "loss": 2.7685586547851564, |
| "step": 29300 |
| }, |
| { |
| "epoch": 0.2672727272727273, |
| "grad_norm": 0.131728395819664, |
| "learning_rate": 0.0008350361455912099, |
| "loss": 2.771170349121094, |
| "step": 29400 |
| }, |
| { |
| "epoch": 0.2681818181818182, |
| "grad_norm": 0.18209482729434967, |
| "learning_rate": 0.0008339733334968619, |
| "loss": 2.7749264526367186, |
| "step": 29500 |
| }, |
| { |
| "epoch": 0.2690909090909091, |
| "grad_norm": 0.14567936956882477, |
| "learning_rate": 0.0008329077898401624, |
| "loss": 2.8004241943359376, |
| "step": 29600 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.1705045998096466, |
| "learning_rate": 0.0008318395233361753, |
| "loss": 2.8070437622070314, |
| "step": 29700 |
| }, |
| { |
| "epoch": 0.27090909090909093, |
| "grad_norm": 0.1700645238161087, |
| "learning_rate": 0.0008307685427222345, |
| "loss": 2.769403991699219, |
| "step": 29800 |
| }, |
| { |
| "epoch": 0.2718181818181818, |
| "grad_norm": 0.2213045209646225, |
| "learning_rate": 0.000829694856757873, |
| "loss": 2.75067138671875, |
| "step": 29900 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 0.1627679318189621, |
| "learning_rate": 0.0008286184742247502, |
| "loss": 2.782334899902344, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "eval_loss": 3.1495797634124756, |
| "eval_runtime": 6.8699, |
| "eval_samples_per_second": 83.844, |
| "eval_steps_per_second": 20.961, |
| "step": 30000 |
| }, |
| { |
| "epoch": 0.2736363636363636, |
| "grad_norm": 0.1445474475622177, |
| "learning_rate": 0.0008275394039265813, |
| "loss": 2.80556396484375, |
| "step": 30100 |
| }, |
| { |
| "epoch": 0.27454545454545454, |
| "grad_norm": 0.14685708284378052, |
| "learning_rate": 0.0008264576546890639, |
| "loss": 2.776888732910156, |
| "step": 30200 |
| }, |
| { |
| "epoch": 0.27545454545454545, |
| "grad_norm": 0.1347658634185791, |
| "learning_rate": 0.0008253732353598072, |
| "loss": 2.7627569580078126, |
| "step": 30300 |
| }, |
| { |
| "epoch": 0.27636363636363637, |
| "grad_norm": 0.13901016116142273, |
| "learning_rate": 0.0008242861548082591, |
| "loss": 2.780741882324219, |
| "step": 30400 |
| }, |
| { |
| "epoch": 0.2772727272727273, |
| "grad_norm": 0.13585121929645538, |
| "learning_rate": 0.0008231964219256331, |
| "loss": 2.804005432128906, |
| "step": 30500 |
| }, |
| { |
| "epoch": 0.2781818181818182, |
| "grad_norm": 0.15015123784542084, |
| "learning_rate": 0.0008221040456248367, |
| "loss": 2.7642987060546873, |
| "step": 30600 |
| }, |
| { |
| "epoch": 0.2790909090909091, |
| "grad_norm": 0.13883176445960999, |
| "learning_rate": 0.0008210090348403973, |
| "loss": 2.79775146484375, |
| "step": 30700 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.1524442732334137, |
| "learning_rate": 0.0008199113985283902, |
| "loss": 2.7866134643554688, |
| "step": 30800 |
| }, |
| { |
| "epoch": 0.2809090909090909, |
| "grad_norm": 0.14497579634189606, |
| "learning_rate": 0.0008188111456663641, |
| "loss": 2.770282897949219, |
| "step": 30900 |
| }, |
| { |
| "epoch": 0.2818181818181818, |
| "grad_norm": 0.1663127839565277, |
| "learning_rate": 0.0008177082852532691, |
| "loss": 2.7479037475585937, |
| "step": 31000 |
| }, |
| { |
| "epoch": 0.2818181818181818, |
| "eval_loss": 3.1455507278442383, |
| "eval_runtime": 6.8464, |
| "eval_samples_per_second": 84.131, |
| "eval_steps_per_second": 21.033, |
| "step": 31000 |
| }, |
| { |
| "epoch": 0.2827272727272727, |
| "grad_norm": 0.3059700131416321, |
| "learning_rate": 0.0008166028263093825, |
| "loss": 2.786407775878906, |
| "step": 31100 |
| }, |
| { |
| "epoch": 0.28363636363636363, |
| "grad_norm": 0.1757507622241974, |
| "learning_rate": 0.0008154947778762343, |
| "loss": 2.7669387817382813, |
| "step": 31200 |
| }, |
| { |
| "epoch": 0.28454545454545455, |
| "grad_norm": 0.1763867884874344, |
| "learning_rate": 0.0008143841490165344, |
| "loss": 2.763365478515625, |
| "step": 31300 |
| }, |
| { |
| "epoch": 0.28545454545454546, |
| "grad_norm": 0.1497093141078949, |
| "learning_rate": 0.0008132709488140977, |
| "loss": 2.7558905029296876, |
| "step": 31400 |
| }, |
| { |
| "epoch": 0.2863636363636364, |
| "grad_norm": 0.15906350314617157, |
| "learning_rate": 0.0008121551863737704, |
| "loss": 2.7421307373046875, |
| "step": 31500 |
| }, |
| { |
| "epoch": 0.2872727272727273, |
| "grad_norm": 0.14353445172309875, |
| "learning_rate": 0.0008110368708213548, |
| "loss": 2.7798092651367186, |
| "step": 31600 |
| }, |
| { |
| "epoch": 0.2881818181818182, |
| "grad_norm": 0.1670762598514557, |
| "learning_rate": 0.0008099160113035353, |
| "loss": 2.764653625488281, |
| "step": 31700 |
| }, |
| { |
| "epoch": 0.28909090909090907, |
| "grad_norm": 0.15554283559322357, |
| "learning_rate": 0.000808792616987803, |
| "loss": 2.76354736328125, |
| "step": 31800 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.14061635732650757, |
| "learning_rate": 0.0008076666970623821, |
| "loss": 2.764184875488281, |
| "step": 31900 |
| }, |
| { |
| "epoch": 0.2909090909090909, |
| "grad_norm": 0.18086077272891998, |
| "learning_rate": 0.0008065382607361523, |
| "loss": 2.7778125, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.2909090909090909, |
| "eval_loss": 3.1462559700012207, |
| "eval_runtime": 6.8321, |
| "eval_samples_per_second": 84.308, |
| "eval_steps_per_second": 21.077, |
| "step": 32000 |
| }, |
| { |
| "epoch": 0.0009090909090909091, |
| "grad_norm": 0.22038772702217102, |
| "learning_rate": 0.0008054073172385756, |
| "loss": 2.794765625, |
| "step": 32100 |
| }, |
| { |
| "epoch": 0.0018181818181818182, |
| "grad_norm": 0.15077297389507294, |
| "learning_rate": 0.0008042738758196204, |
| "loss": 2.7949072265625, |
| "step": 32200 |
| }, |
| { |
| "epoch": 0.0027272727272727275, |
| "grad_norm": 0.1514005959033966, |
| "learning_rate": 0.0008031379457496854, |
| "loss": 2.8156253051757814, |
| "step": 32300 |
| }, |
| { |
| "epoch": 0.0036363636363636364, |
| "grad_norm": 0.13997957110404968, |
| "learning_rate": 0.0008019995363195234, |
| "loss": 2.8109649658203124, |
| "step": 32400 |
| }, |
| { |
| "epoch": 0.004545454545454545, |
| "grad_norm": 0.14847084879875183, |
| "learning_rate": 0.0008008586568401662, |
| "loss": 2.7742608642578124, |
| "step": 32500 |
| }, |
| { |
| "epoch": 0.005454545454545455, |
| "grad_norm": 0.13216467201709747, |
| "learning_rate": 0.0007997153166428485, |
| "loss": 2.7673321533203126, |
| "step": 32600 |
| }, |
| { |
| "epoch": 0.006363636363636364, |
| "grad_norm": 0.16374439001083374, |
| "learning_rate": 0.0007985695250789306, |
| "loss": 2.78884521484375, |
| "step": 32700 |
| }, |
| { |
| "epoch": 0.007272727272727273, |
| "grad_norm": 0.1394331306219101, |
| "learning_rate": 0.0007974212915198225, |
| "loss": 2.779542236328125, |
| "step": 32800 |
| }, |
| { |
| "epoch": 0.008181818181818182, |
| "grad_norm": 0.1565932035446167, |
| "learning_rate": 0.0007962706253569077, |
| "loss": 2.815880126953125, |
| "step": 32900 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "grad_norm": 0.17284399271011353, |
| "learning_rate": 0.0007951175360014656, |
| "loss": 2.769788818359375, |
| "step": 33000 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "eval_loss": 3.1402082443237305, |
| "eval_runtime": 7.4554, |
| "eval_samples_per_second": 77.259, |
| "eval_steps_per_second": 19.315, |
| "step": 33000 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.15111324191093445, |
| "learning_rate": 0.0007939620328845948, |
| "loss": 2.7730609130859376, |
| "step": 33100 |
| }, |
| { |
| "epoch": 0.01090909090909091, |
| "grad_norm": 0.160688117146492, |
| "learning_rate": 0.0007928041254571361, |
| "loss": 2.787190246582031, |
| "step": 33200 |
| }, |
| { |
| "epoch": 0.011818181818181818, |
| "grad_norm": 0.17507240176200867, |
| "learning_rate": 0.0007916438231895952, |
| "loss": 2.766163330078125, |
| "step": 33300 |
| }, |
| { |
| "epoch": 0.012727272727272728, |
| "grad_norm": 0.15393611788749695, |
| "learning_rate": 0.0007904811355720652, |
| "loss": 2.7740924072265627, |
| "step": 33400 |
| }, |
| { |
| "epoch": 0.013636363636363636, |
| "grad_norm": 0.14618468284606934, |
| "learning_rate": 0.0007893160721141486, |
| "loss": 2.7595263671875, |
| "step": 33500 |
| }, |
| { |
| "epoch": 0.014545454545454545, |
| "grad_norm": 0.1701638251543045, |
| "learning_rate": 0.0007881486423448802, |
| "loss": 2.7771051025390623, |
| "step": 33600 |
| }, |
| { |
| "epoch": 0.015454545454545455, |
| "grad_norm": 0.15899600088596344, |
| "learning_rate": 0.0007869788558126487, |
| "loss": 2.754100646972656, |
| "step": 33700 |
| }, |
| { |
| "epoch": 0.016363636363636365, |
| "grad_norm": 0.14573192596435547, |
| "learning_rate": 0.0007858067220851188, |
| "loss": 2.7869033813476562, |
| "step": 33800 |
| }, |
| { |
| "epoch": 0.017272727272727273, |
| "grad_norm": 0.16796821355819702, |
| "learning_rate": 0.0007846322507491528, |
| "loss": 2.7748208618164063, |
| "step": 33900 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "grad_norm": 0.1425439566373825, |
| "learning_rate": 0.000783455451410732, |
| "loss": 2.773130187988281, |
| "step": 34000 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "eval_loss": 3.13128399848938, |
| "eval_runtime": 7.4414, |
| "eval_samples_per_second": 77.405, |
| "eval_steps_per_second": 19.351, |
| "step": 34000 |
| }, |
| { |
| "epoch": 0.019090909090909092, |
| "grad_norm": 0.15474802255630493, |
| "learning_rate": 0.000782276333694879, |
| "loss": 2.7699960327148436, |
| "step": 34100 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.1559676229953766, |
| "learning_rate": 0.0007810949072455778, |
| "loss": 2.7731719970703126, |
| "step": 34200 |
| }, |
| { |
| "epoch": 0.02090909090909091, |
| "grad_norm": 0.1522807478904724, |
| "learning_rate": 0.0007799111817256959, |
| "loss": 2.7761361694335935, |
| "step": 34300 |
| }, |
| { |
| "epoch": 0.02181818181818182, |
| "grad_norm": 0.15091344714164734, |
| "learning_rate": 0.0007787251668169043, |
| "loss": 2.7527685546875, |
| "step": 34400 |
| }, |
| { |
| "epoch": 0.022727272727272728, |
| "grad_norm": 0.15074443817138672, |
| "learning_rate": 0.0007775368722195997, |
| "loss": 2.7675704956054688, |
| "step": 34500 |
| }, |
| { |
| "epoch": 0.023636363636363636, |
| "grad_norm": 0.1461259126663208, |
| "learning_rate": 0.0007763463076528237, |
| "loss": 2.76167236328125, |
| "step": 34600 |
| }, |
| { |
| "epoch": 0.024545454545454544, |
| "grad_norm": 0.15030233561992645, |
| "learning_rate": 0.0007751534828541842, |
| "loss": 2.7275946044921877, |
| "step": 34700 |
| }, |
| { |
| "epoch": 0.025454545454545455, |
| "grad_norm": 0.14424681663513184, |
| "learning_rate": 0.0007739584075797753, |
| "loss": 2.736708679199219, |
| "step": 34800 |
| }, |
| { |
| "epoch": 0.026363636363636363, |
| "grad_norm": 0.15576180815696716, |
| "learning_rate": 0.0007727610916040981, |
| "loss": 2.7289297485351565, |
| "step": 34900 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "grad_norm": 0.1324995905160904, |
| "learning_rate": 0.0007715615447199798, |
| "loss": 2.7693435668945314, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "eval_loss": 3.1262025833129883, |
| "eval_runtime": 7.4365, |
| "eval_samples_per_second": 77.456, |
| "eval_steps_per_second": 19.364, |
| "step": 35000 |
| }, |
| { |
| "epoch": 0.028181818181818183, |
| "grad_norm": 0.1613311767578125, |
| "learning_rate": 0.0007703597767384945, |
| "loss": 2.7539468383789063, |
| "step": 35100 |
| }, |
| { |
| "epoch": 0.02909090909090909, |
| "grad_norm": 0.16793298721313477, |
| "learning_rate": 0.0007691557974888825, |
| "loss": 2.7785479736328127, |
| "step": 35200 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.14937831461429596, |
| "learning_rate": 0.0007679496168184705, |
| "loss": 2.7587347412109375, |
| "step": 35300 |
| }, |
| { |
| "epoch": 0.03090909090909091, |
| "grad_norm": 0.1619419902563095, |
| "learning_rate": 0.0007667412445925898, |
| "loss": 2.7732388305664064, |
| "step": 35400 |
| }, |
| { |
| "epoch": 0.031818181818181815, |
| "grad_norm": 0.15758360922336578, |
| "learning_rate": 0.000765530690694497, |
| "loss": 2.74038818359375, |
| "step": 35500 |
| }, |
| { |
| "epoch": 0.03272727272727273, |
| "grad_norm": 0.1523827463388443, |
| "learning_rate": 0.000764317965025292, |
| "loss": 2.7354312133789063, |
| "step": 35600 |
| }, |
| { |
| "epoch": 0.03363636363636364, |
| "grad_norm": 0.1685842126607895, |
| "learning_rate": 0.0007631030775038383, |
| "loss": 2.7525250244140627, |
| "step": 35700 |
| }, |
| { |
| "epoch": 0.034545454545454546, |
| "grad_norm": 0.1396898627281189, |
| "learning_rate": 0.0007618860380666808, |
| "loss": 2.737476501464844, |
| "step": 35800 |
| }, |
| { |
| "epoch": 0.035454545454545454, |
| "grad_norm": 0.15296360850334167, |
| "learning_rate": 0.0007606668566679644, |
| "loss": 2.747691955566406, |
| "step": 35900 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "grad_norm": 0.1561899036169052, |
| "learning_rate": 0.0007594455432793539, |
| "loss": 2.7320767211914063, |
| "step": 36000 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "eval_loss": 3.1245434284210205, |
| "eval_runtime": 7.4489, |
| "eval_samples_per_second": 77.327, |
| "eval_steps_per_second": 19.332, |
| "step": 36000 |
| }, |
| { |
| "epoch": 0.0009090909090909091, |
| "grad_norm": 0.20997287333011627, |
| "learning_rate": 0.0007582221078899511, |
| "loss": 2.71048828125, |
| "step": 36100 |
| }, |
| { |
| "epoch": 0.0018181818181818182, |
| "grad_norm": 0.1532030999660492, |
| "learning_rate": 0.0007569965605062139, |
| "loss": 2.7088739013671876, |
| "step": 36200 |
| }, |
| { |
| "epoch": 0.0027272727272727275, |
| "grad_norm": 0.14671523869037628, |
| "learning_rate": 0.000755768911151874, |
| "loss": 2.730252990722656, |
| "step": 36300 |
| }, |
| { |
| "epoch": 0.0036363636363636364, |
| "grad_norm": 0.1369636058807373, |
| "learning_rate": 0.0007545391698678547, |
| "loss": 2.7253591918945315, |
| "step": 36400 |
| }, |
| { |
| "epoch": 0.004545454545454545, |
| "grad_norm": 0.16328130662441254, |
| "learning_rate": 0.00075330734671219, |
| "loss": 2.6905337524414064, |
| "step": 36500 |
| }, |
| { |
| "epoch": 0.005454545454545455, |
| "grad_norm": 0.13856680691242218, |
| "learning_rate": 0.0007520734517599409, |
| "loss": 2.6842236328125, |
| "step": 36600 |
| }, |
| { |
| "epoch": 0.006363636363636364, |
| "grad_norm": 0.14775875210762024, |
| "learning_rate": 0.0007508374951031139, |
| "loss": 2.7059420776367187, |
| "step": 36700 |
| }, |
| { |
| "epoch": 0.007272727272727273, |
| "grad_norm": 0.14245547354221344, |
| "learning_rate": 0.0007495994868505774, |
| "loss": 2.6968829345703127, |
| "step": 36800 |
| }, |
| { |
| "epoch": 0.008181818181818182, |
| "grad_norm": 0.15311609208583832, |
| "learning_rate": 0.000748359437127981, |
| "loss": 2.7318048095703125, |
| "step": 36900 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "grad_norm": 0.1730499267578125, |
| "learning_rate": 0.0007471173560776705, |
| "loss": 2.6874020385742186, |
| "step": 37000 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "eval_loss": 3.13167405128479, |
| "eval_runtime": 7.5047, |
| "eval_samples_per_second": 76.752, |
| "eval_steps_per_second": 19.188, |
| "step": 37000 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 0.15705707669258118, |
| "learning_rate": 0.0007458732538586064, |
| "loss": 2.692235107421875, |
| "step": 37100 |
| }, |
| { |
| "epoch": 0.01090909090909091, |
| "grad_norm": 0.1563568264245987, |
| "learning_rate": 0.0007446271406462797, |
| "loss": 2.706945495605469, |
| "step": 37200 |
| }, |
| { |
| "epoch": 0.011818181818181818, |
| "grad_norm": 0.16822531819343567, |
| "learning_rate": 0.00074337902663263, |
| "loss": 2.685476989746094, |
| "step": 37300 |
| }, |
| { |
| "epoch": 0.012727272727272728, |
| "grad_norm": 0.14851588010787964, |
| "learning_rate": 0.000742128922025961, |
| "loss": 2.692755126953125, |
| "step": 37400 |
| }, |
| { |
| "epoch": 0.013636363636363636, |
| "grad_norm": 0.1650208979845047, |
| "learning_rate": 0.0007408768370508576, |
| "loss": 2.68127197265625, |
| "step": 37500 |
| }, |
| { |
| "epoch": 0.014545454545454545, |
| "grad_norm": 0.1679512858390808, |
| "learning_rate": 0.0007396227819481021, |
| "loss": 2.697837219238281, |
| "step": 37600 |
| }, |
| { |
| "epoch": 0.015454545454545455, |
| "grad_norm": 0.1745394617319107, |
| "learning_rate": 0.00073836676697459, |
| "loss": 2.6750924682617185, |
| "step": 37700 |
| }, |
| { |
| "epoch": 0.016363636363636365, |
| "grad_norm": 0.14067143201828003, |
| "learning_rate": 0.0007371088024032475, |
| "loss": 2.7095330810546874, |
| "step": 37800 |
| }, |
| { |
| "epoch": 0.017272727272727273, |
| "grad_norm": 0.16379132866859436, |
| "learning_rate": 0.0007358488985229455, |
| "loss": 2.6968374633789063, |
| "step": 37900 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "grad_norm": 0.15668943524360657, |
| "learning_rate": 0.000734587065638417, |
| "loss": 2.697041320800781, |
| "step": 38000 |
| }, |
| { |
| "epoch": 0.01818181818181818, |
| "eval_loss": 3.128469467163086, |
| "eval_runtime": 7.47, |
| "eval_samples_per_second": 77.109, |
| "eval_steps_per_second": 19.277, |
| "step": 38000 |
| }, |
| { |
| "epoch": 0.019090909090909092, |
| "grad_norm": 0.1642797887325287, |
| "learning_rate": 0.0007333233140701722, |
| "loss": 2.6924237060546874, |
| "step": 38100 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 0.16816826164722443, |
| "learning_rate": 0.0007320576541544144, |
| "loss": 2.69775634765625, |
| "step": 38200 |
| }, |
| { |
| "epoch": 0.02090909090909091, |
| "grad_norm": 0.1469792127609253, |
| "learning_rate": 0.000730790096242955, |
| "loss": 2.6987783813476565, |
| "step": 38300 |
| }, |
| { |
| "epoch": 0.02181818181818182, |
| "grad_norm": 0.15169106423854828, |
| "learning_rate": 0.0007295206507031289, |
| "loss": 2.6766021728515623, |
| "step": 38400 |
| }, |
| { |
| "epoch": 0.022727272727272728, |
| "grad_norm": 0.14681929349899292, |
| "learning_rate": 0.0007282493279177103, |
| "loss": 2.691963806152344, |
| "step": 38500 |
| }, |
| { |
| "epoch": 0.023636363636363636, |
| "grad_norm": 0.1452484130859375, |
| "learning_rate": 0.000726976138284827, |
| "loss": 2.6880203247070313, |
| "step": 38600 |
| }, |
| { |
| "epoch": 0.024545454545454544, |
| "grad_norm": 0.15825141966342926, |
| "learning_rate": 0.0007257010922178762, |
| "loss": 2.65422119140625, |
| "step": 38700 |
| }, |
| { |
| "epoch": 0.025454545454545455, |
| "grad_norm": 0.15018871426582336, |
| "learning_rate": 0.000724424200145438, |
| "loss": 2.663526611328125, |
| "step": 38800 |
| }, |
| { |
| "epoch": 0.026363636363636363, |
| "grad_norm": 0.16328509151935577, |
| "learning_rate": 0.0007231454725111919, |
| "loss": 2.6569583129882814, |
| "step": 38900 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "grad_norm": 0.14703254401683807, |
| "learning_rate": 0.0007218649197738298, |
| "loss": 2.69577392578125, |
| "step": 39000 |
| }, |
| { |
| "epoch": 0.02727272727272727, |
| "eval_loss": 3.1291093826293945, |
| "eval_runtime": 7.4103, |
| "eval_samples_per_second": 77.729, |
| "eval_steps_per_second": 19.432, |
| "step": 39000 |
| }, |
| { |
| "epoch": 0.028181818181818183, |
| "grad_norm": 0.1588928997516632, |
| "learning_rate": 0.0007205825524069714, |
| "loss": 2.6820574951171876, |
| "step": 39100 |
| }, |
| { |
| "epoch": 0.02909090909090909, |
| "grad_norm": 0.18345706164836884, |
| "learning_rate": 0.0007192983808990781, |
| "loss": 2.7058285522460936, |
| "step": 39200 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 0.1431887000799179, |
| "learning_rate": 0.0007180124157533671, |
| "loss": 2.6863577270507815, |
| "step": 39300 |
| }, |
| { |
| "epoch": 0.03090909090909091, |
| "grad_norm": 0.15360857546329498, |
| "learning_rate": 0.0007167246674877264, |
| "loss": 2.6997265625, |
| "step": 39400 |
| }, |
| { |
| "epoch": 0.031818181818181815, |
| "grad_norm": 0.15961426496505737, |
| "learning_rate": 0.0007154351466346273, |
| "loss": 2.66740966796875, |
| "step": 39500 |
| }, |
| { |
| "epoch": 0.03272727272727273, |
| "grad_norm": 0.15588298439979553, |
| "learning_rate": 0.0007141438637410398, |
| "loss": 2.6652230834960937, |
| "step": 39600 |
| }, |
| { |
| "epoch": 0.03363636363636364, |
| "grad_norm": 0.1670597940683365, |
| "learning_rate": 0.000712850829368345, |
| "loss": 2.681721496582031, |
| "step": 39700 |
| }, |
| { |
| "epoch": 0.034545454545454546, |
| "grad_norm": 0.15003304183483124, |
| "learning_rate": 0.0007115560540922497, |
| "loss": 2.6677728271484376, |
| "step": 39800 |
| }, |
| { |
| "epoch": 0.035454545454545454, |
| "grad_norm": 0.1557546705007553, |
| "learning_rate": 0.0007102595485026993, |
| "loss": 2.6783493041992186, |
| "step": 39900 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "grad_norm": 0.1732822060585022, |
| "learning_rate": 0.0007089613232037915, |
| "loss": 2.6648553466796874, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.03636363636363636, |
| "eval_loss": 3.129150867462158, |
| "eval_runtime": 7.5094, |
| "eval_samples_per_second": 76.703, |
| "eval_steps_per_second": 19.176, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.03727272727272727, |
| "grad_norm": 0.15226680040359497, |
| "learning_rate": 0.0007076613888136895, |
| "loss": 2.7523992919921874, |
| "step": 40100 |
| }, |
| { |
| "epoch": 0.038181818181818185, |
| "grad_norm": 0.16509854793548584, |
| "learning_rate": 0.0007063597559645352, |
| "loss": 2.7390933227539063, |
| "step": 40200 |
| }, |
| { |
| "epoch": 0.03909090909090909, |
| "grad_norm": 0.1810932159423828, |
| "learning_rate": 0.0007050564353023619, |
| "loss": 2.7575619506835936, |
| "step": 40300 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 0.14917488396167755, |
| "learning_rate": 0.0007037514374870077, |
| "loss": 2.700941162109375, |
| "step": 40400 |
| }, |
| { |
| "epoch": 0.04090909090909091, |
| "grad_norm": 0.1438620686531067, |
| "learning_rate": 0.0007024447731920284, |
| "loss": 2.7219302368164064, |
| "step": 40500 |
| }, |
| { |
| "epoch": 0.04181818181818182, |
| "grad_norm": 0.1588471382856369, |
| "learning_rate": 0.000701136453104609, |
| "loss": 2.7354092407226562, |
| "step": 40600 |
| }, |
| { |
| "epoch": 0.042727272727272725, |
| "grad_norm": 0.18232181668281555, |
| "learning_rate": 0.0006998264879254782, |
| "loss": 2.7257977294921876, |
| "step": 40700 |
| }, |
| { |
| "epoch": 0.04363636363636364, |
| "grad_norm": 0.15463081002235413, |
| "learning_rate": 0.0006985148883688194, |
| "loss": 2.7430325317382813, |
| "step": 40800 |
| }, |
| { |
| "epoch": 0.04454545454545455, |
| "grad_norm": 0.16292454302310944, |
| "learning_rate": 0.0006972016651621834, |
| "loss": 2.725971374511719, |
| "step": 40900 |
| }, |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 0.14817778766155243, |
| "learning_rate": 0.0006958868290464014, |
| "loss": 2.7598446655273436, |
| "step": 41000 |
| }, |
| { |
| "epoch": 0.045454545454545456, |
| "eval_loss": 3.1211743354797363, |
| "eval_runtime": 7.424, |
| "eval_samples_per_second": 77.586, |
| "eval_steps_per_second": 19.396, |
| "step": 41000 |
| }, |
| { |
| "epoch": 0.046363636363636364, |
| "grad_norm": 0.1458057463169098, |
| "learning_rate": 0.0006945703907754957, |
| "loss": 2.7241558837890625, |
| "step": 41100 |
| }, |
| { |
| "epoch": 0.04727272727272727, |
| "grad_norm": 0.1644594669342041, |
| "learning_rate": 0.0006932523611165934, |
| "loss": 2.737247314453125, |
| "step": 41200 |
| }, |
| { |
| "epoch": 0.04818181818181818, |
| "grad_norm": 0.1583612859249115, |
| "learning_rate": 0.000691932750849837, |
| "loss": 2.7208633422851562, |
| "step": 41300 |
| }, |
| { |
| "epoch": 0.04909090909090909, |
| "grad_norm": 0.15082280337810516, |
| "learning_rate": 0.000690611570768297, |
| "loss": 2.7353948974609374, |
| "step": 41400 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.16890287399291992, |
| "learning_rate": 0.0006892888316778836, |
| "loss": 2.7053826904296874, |
| "step": 41500 |
| }, |
| { |
| "epoch": 0.05090909090909091, |
| "grad_norm": 0.15229052305221558, |
| "learning_rate": 0.0006879645443972575, |
| "loss": 2.6989901733398436, |
| "step": 41600 |
| }, |
| { |
| "epoch": 0.05181818181818182, |
| "grad_norm": 0.15202166140079498, |
| "learning_rate": 0.0006866387197577427, |
| "loss": 2.7251095581054687, |
| "step": 41700 |
| }, |
| { |
| "epoch": 0.05272727272727273, |
| "grad_norm": 0.1463591307401657, |
| "learning_rate": 0.0006853113686032368, |
| "loss": 2.7278387451171877, |
| "step": 41800 |
| }, |
| { |
| "epoch": 0.053636363636363635, |
| "grad_norm": 0.14916226267814636, |
| "learning_rate": 0.0006839825017901229, |
| "loss": 2.71453369140625, |
| "step": 41900 |
| }, |
| { |
| "epoch": 0.05454545454545454, |
| "grad_norm": 0.15262916684150696, |
| "learning_rate": 0.0006826521301871804, |
| "loss": 2.712431640625, |
| "step": 42000 |
| }, |
| { |
| "epoch": 0.05454545454545454, |
| "eval_loss": 3.1164402961730957, |
| "eval_runtime": 7.416, |
| "eval_samples_per_second": 77.67, |
| "eval_steps_per_second": 19.418, |
| "step": 42000 |
| }, |
| { |
| "epoch": 0.05545454545454546, |
| "grad_norm": 0.14367501437664032, |
| "learning_rate": 0.0006813202646754969, |
| "loss": 2.770457458496094, |
| "step": 42100 |
| }, |
| { |
| "epoch": 0.056363636363636366, |
| "grad_norm": 0.16685152053833008, |
| "learning_rate": 0.000679986916148378, |
| "loss": 2.7458120727539064, |
| "step": 42200 |
| }, |
| { |
| "epoch": 0.057272727272727274, |
| "grad_norm": 0.1416223794221878, |
| "learning_rate": 0.0006786520955112592, |
| "loss": 2.737471923828125, |
| "step": 42300 |
| }, |
| { |
| "epoch": 0.05818181818181818, |
| "grad_norm": 0.19099284708499908, |
| "learning_rate": 0.0006773158136816167, |
| "loss": 2.7410955810546875, |
| "step": 42400 |
| }, |
| { |
| "epoch": 0.05909090909090909, |
| "grad_norm": 0.14040355384349823, |
| "learning_rate": 0.0006759780815888771, |
| "loss": 2.7524224853515626, |
| "step": 42500 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 0.14514034986495972, |
| "learning_rate": 0.0006746389101743291, |
| "loss": 2.7450900268554688, |
| "step": 42600 |
| }, |
| { |
| "epoch": 0.060909090909090906, |
| "grad_norm": 0.1578412503004074, |
| "learning_rate": 0.0006732983103910333, |
| "loss": 2.7615512084960936, |
| "step": 42700 |
| }, |
| { |
| "epoch": 0.06181818181818182, |
| "grad_norm": 0.18139956891536713, |
| "learning_rate": 0.0006719562932037332, |
| "loss": 2.709564514160156, |
| "step": 42800 |
| }, |
| { |
| "epoch": 0.06272727272727273, |
| "grad_norm": 0.15958115458488464, |
| "learning_rate": 0.000670612869588765, |
| "loss": 2.7086691284179687, |
| "step": 42900 |
| }, |
| { |
| "epoch": 0.06363636363636363, |
| "grad_norm": 0.18487316370010376, |
| "learning_rate": 0.0006692680505339684, |
| "loss": 2.7571722412109376, |
| "step": 43000 |
| }, |
| { |
| "epoch": 0.06363636363636363, |
| "eval_loss": 3.1164326667785645, |
| "eval_runtime": 7.4455, |
| "eval_samples_per_second": 77.362, |
| "eval_steps_per_second": 19.34, |
| "step": 43000 |
| }, |
| { |
| "epoch": 0.06454545454545454, |
| "grad_norm": 0.14378763735294342, |
| "learning_rate": 0.0006679218470385959, |
| "loss": 2.713703308105469, |
| "step": 43100 |
| }, |
| { |
| "epoch": 0.06545454545454546, |
| "grad_norm": 0.14831411838531494, |
| "learning_rate": 0.0006665742701132233, |
| "loss": 2.7057376098632813, |
| "step": 43200 |
| }, |
| { |
| "epoch": 0.06636363636363636, |
| "grad_norm": 0.14014075696468353, |
| "learning_rate": 0.0006652253307796605, |
| "loss": 2.732189025878906, |
| "step": 43300 |
| }, |
| { |
| "epoch": 0.06727272727272728, |
| "grad_norm": 0.1462206244468689, |
| "learning_rate": 0.0006638750400708597, |
| "loss": 2.735457763671875, |
| "step": 43400 |
| }, |
| { |
| "epoch": 0.06818181818181818, |
| "grad_norm": 0.15208710730075836, |
| "learning_rate": 0.0006625234090308261, |
| "loss": 2.7204766845703126, |
| "step": 43500 |
| }, |
| { |
| "epoch": 0.06909090909090909, |
| "grad_norm": 0.17330685257911682, |
| "learning_rate": 0.0006611704487145273, |
| "loss": 2.7174346923828123, |
| "step": 43600 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 0.14701761305332184, |
| "learning_rate": 0.000659816170187804, |
| "loss": 2.7171310424804687, |
| "step": 43700 |
| }, |
| { |
| "epoch": 0.07090909090909091, |
| "grad_norm": 0.15500852465629578, |
| "learning_rate": 0.0006584605845272769, |
| "loss": 2.7264663696289064, |
| "step": 43800 |
| }, |
| { |
| "epoch": 0.07181818181818182, |
| "grad_norm": 0.173856720328331, |
| "learning_rate": 0.0006571037028202593, |
| "loss": 2.7247988891601564, |
| "step": 43900 |
| }, |
| { |
| "epoch": 0.07272727272727272, |
| "grad_norm": 0.152163565158844, |
| "learning_rate": 0.0006557455361646638, |
| "loss": 2.7246688842773437, |
| "step": 44000 |
| }, |
| { |
| "epoch": 0.07272727272727272, |
| "eval_loss": 3.1064937114715576, |
| "eval_runtime": 7.4422, |
| "eval_samples_per_second": 77.396, |
| "eval_steps_per_second": 19.349, |
| "step": 44000 |
| }, |
| { |
| "epoch": 0.07363636363636364, |
| "grad_norm": 0.14658956229686737, |
| "learning_rate": 0.0006543860956689131, |
| "loss": 2.7102786254882814, |
| "step": 44100 |
| }, |
| { |
| "epoch": 0.07454545454545454, |
| "grad_norm": 0.1424274891614914, |
| "learning_rate": 0.0006530253924518484, |
| "loss": 2.682833557128906, |
| "step": 44200 |
| }, |
| { |
| "epoch": 0.07545454545454545, |
| "grad_norm": 0.1558665931224823, |
| "learning_rate": 0.0006516634376426387, |
| "loss": 2.7235848999023435, |
| "step": 44300 |
| }, |
| { |
| "epoch": 0.07636363636363637, |
| "grad_norm": 0.1660631000995636, |
| "learning_rate": 0.0006503002423806897, |
| "loss": 2.6941436767578124, |
| "step": 44400 |
| }, |
| { |
| "epoch": 0.07727272727272727, |
| "grad_norm": 0.15640541911125183, |
| "learning_rate": 0.0006489358178155531, |
| "loss": 2.7176858520507814, |
| "step": 44500 |
| }, |
| { |
| "epoch": 0.07818181818181819, |
| "grad_norm": 0.1507701575756073, |
| "learning_rate": 0.0006475701751068345, |
| "loss": 2.72189697265625, |
| "step": 44600 |
| }, |
| { |
| "epoch": 0.07909090909090909, |
| "grad_norm": 0.1533944010734558, |
| "learning_rate": 0.000646203325424103, |
| "loss": 2.6939328002929686, |
| "step": 44700 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.13101057708263397, |
| "learning_rate": 0.0006448352799467994, |
| "loss": 2.743724365234375, |
| "step": 44800 |
| }, |
| { |
| "epoch": 0.0809090909090909, |
| "grad_norm": 0.15205194056034088, |
| "learning_rate": 0.0006434660498641453, |
| "loss": 2.6808477783203126, |
| "step": 44900 |
| }, |
| { |
| "epoch": 0.08181818181818182, |
| "grad_norm": 0.16786165535449982, |
| "learning_rate": 0.0006420956463750505, |
| "loss": 2.7101092529296875, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.08181818181818182, |
| "eval_loss": 3.100367307662964, |
| "eval_runtime": 7.4121, |
| "eval_samples_per_second": 77.711, |
| "eval_steps_per_second": 19.428, |
| "step": 45000 |
| }, |
| { |
| "epoch": 0.08272727272727273, |
| "grad_norm": 0.1478699892759323, |
| "learning_rate": 0.0006407240806880225, |
| "loss": 2.717208251953125, |
| "step": 45100 |
| }, |
| { |
| "epoch": 0.08363636363636363, |
| "grad_norm": 0.1527082324028015, |
| "learning_rate": 0.0006393513640210743, |
| "loss": 2.7066421508789062, |
| "step": 45200 |
| }, |
| { |
| "epoch": 0.08454545454545455, |
| "grad_norm": 0.16474194824695587, |
| "learning_rate": 0.0006379775076016327, |
| "loss": 2.6989260864257814, |
| "step": 45300 |
| }, |
| { |
| "epoch": 0.08545454545454545, |
| "grad_norm": 0.17212653160095215, |
| "learning_rate": 0.0006366025226664465, |
| "loss": 2.72157958984375, |
| "step": 45400 |
| }, |
| { |
| "epoch": 0.08636363636363636, |
| "grad_norm": 0.1925841122865677, |
| "learning_rate": 0.0006352264204614946, |
| "loss": 2.7147427368164063, |
| "step": 45500 |
| }, |
| { |
| "epoch": 0.08727272727272728, |
| "grad_norm": 0.19100086390972137, |
| "learning_rate": 0.0006338492122418944, |
| "loss": 2.6837368774414063, |
| "step": 45600 |
| }, |
| { |
| "epoch": 0.08818181818181818, |
| "grad_norm": 0.15223105251789093, |
| "learning_rate": 0.0006324709092718088, |
| "loss": 2.6951806640625, |
| "step": 45700 |
| }, |
| { |
| "epoch": 0.0890909090909091, |
| "grad_norm": 0.16720791161060333, |
| "learning_rate": 0.000631091522824355, |
| "loss": 2.6881533813476564, |
| "step": 45800 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 0.28359341621398926, |
| "learning_rate": 0.0006297110641815118, |
| "loss": 2.695024108886719, |
| "step": 45900 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 0.16058634221553802, |
| "learning_rate": 0.0006283295446340276, |
| "loss": 2.694168701171875, |
| "step": 46000 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "eval_loss": 3.092599630355835, |
| "eval_runtime": 7.4402, |
| "eval_samples_per_second": 77.417, |
| "eval_steps_per_second": 19.354, |
| "step": 46000 |
| }, |
| { |
| "epoch": 0.09181818181818181, |
| "grad_norm": 0.14820711314678192, |
| "learning_rate": 0.0006269469754813277, |
| "loss": 2.678899841308594, |
| "step": 46100 |
| }, |
| { |
| "epoch": 0.09272727272727273, |
| "grad_norm": 0.14676456153392792, |
| "learning_rate": 0.0006255633680314226, |
| "loss": 2.6948358154296876, |
| "step": 46200 |
| }, |
| { |
| "epoch": 0.09363636363636364, |
| "grad_norm": 0.14033126831054688, |
| "learning_rate": 0.0006241787336008143, |
| "loss": 2.6942843627929687, |
| "step": 46300 |
| }, |
| { |
| "epoch": 0.09454545454545454, |
| "grad_norm": 0.15463101863861084, |
| "learning_rate": 0.000622793083514405, |
| "loss": 2.6831298828125, |
| "step": 46400 |
| }, |
| { |
| "epoch": 0.09545454545454546, |
| "grad_norm": 0.1568794697523117, |
| "learning_rate": 0.0006214064291054039, |
| "loss": 2.6844097900390627, |
| "step": 46500 |
| }, |
| { |
| "epoch": 0.09636363636363636, |
| "grad_norm": 0.15985362231731415, |
| "learning_rate": 0.0006200187817152341, |
| "loss": 2.6705093383789062, |
| "step": 46600 |
| }, |
| { |
| "epoch": 0.09727272727272727, |
| "grad_norm": 0.18481206893920898, |
| "learning_rate": 0.0006186301526934407, |
| "loss": 2.7399118041992185, |
| "step": 46700 |
| }, |
| { |
| "epoch": 0.09818181818181818, |
| "grad_norm": 0.17036649584770203, |
| "learning_rate": 0.0006172405533975973, |
| "loss": 2.7174920654296875, |
| "step": 46800 |
| }, |
| { |
| "epoch": 0.09909090909090909, |
| "grad_norm": 0.21465139091014862, |
| "learning_rate": 0.0006158499951932138, |
| "loss": 2.7115213012695314, |
| "step": 46900 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.16568434238433838, |
| "learning_rate": 0.0006144584894536423, |
| "loss": 2.7298922729492188, |
| "step": 47000 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 3.0938024520874023, |
| "eval_runtime": 7.4616, |
| "eval_samples_per_second": 77.195, |
| "eval_steps_per_second": 19.299, |
| "step": 47000 |
| }, |
| { |
| "epoch": 0.1009090909090909, |
| "grad_norm": 0.14605851471424103, |
| "learning_rate": 0.0006130660475599854, |
| "loss": 2.7149703979492186, |
| "step": 47100 |
| }, |
| { |
| "epoch": 0.10181818181818182, |
| "grad_norm": 0.21608054637908936, |
| "learning_rate": 0.0006116726809010022, |
| "loss": 2.7035641479492187, |
| "step": 47200 |
| }, |
| { |
| "epoch": 0.10272727272727272, |
| "grad_norm": 0.1545097827911377, |
| "learning_rate": 0.0006102784008730155, |
| "loss": 2.6880255126953125, |
| "step": 47300 |
| }, |
| { |
| "epoch": 0.10363636363636364, |
| "grad_norm": 0.14439067244529724, |
| "learning_rate": 0.0006088832188798183, |
| "loss": 2.6835076904296873, |
| "step": 47400 |
| }, |
| { |
| "epoch": 0.10454545454545454, |
| "grad_norm": 0.17214855551719666, |
| "learning_rate": 0.0006074871463325809, |
| "loss": 2.6864669799804686, |
| "step": 47500 |
| }, |
| { |
| "epoch": 0.10545454545454545, |
| "grad_norm": 0.15308986604213715, |
| "learning_rate": 0.0006060901946497581, |
| "loss": 2.6995504760742186, |
| "step": 47600 |
| }, |
| { |
| "epoch": 0.10636363636363637, |
| "grad_norm": 0.21875260770320892, |
| "learning_rate": 0.000604692375256994, |
| "loss": 2.6868545532226564, |
| "step": 47700 |
| }, |
| { |
| "epoch": 0.10727272727272727, |
| "grad_norm": 0.1660732924938202, |
| "learning_rate": 0.0006032936995870303, |
| "loss": 2.718809814453125, |
| "step": 47800 |
| }, |
| { |
| "epoch": 0.10818181818181818, |
| "grad_norm": 0.1624031513929367, |
| "learning_rate": 0.000601894179079612, |
| "loss": 2.718572692871094, |
| "step": 47900 |
| }, |
| { |
| "epoch": 0.10909090909090909, |
| "grad_norm": 0.17190197110176086, |
| "learning_rate": 0.0006004938251813943, |
| "loss": 2.7020748901367186, |
| "step": 48000 |
| }, |
| { |
| "epoch": 0.10909090909090909, |
| "eval_loss": 3.089716911315918, |
| "eval_runtime": 7.4415, |
| "eval_samples_per_second": 77.404, |
| "eval_steps_per_second": 19.351, |
| "step": 48000 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 0.1616736799478531, |
| "learning_rate": 0.0005990926493458485, |
| "loss": 2.7104031372070314, |
| "step": 48100 |
| }, |
| { |
| "epoch": 0.11090909090909092, |
| "grad_norm": 0.15068742632865906, |
| "learning_rate": 0.0005976906630331684, |
| "loss": 2.6817190551757815, |
| "step": 48200 |
| }, |
| { |
| "epoch": 0.11181818181818182, |
| "grad_norm": 0.1564316600561142, |
| "learning_rate": 0.0005962878777101768, |
| "loss": 2.699707336425781, |
| "step": 48300 |
| }, |
| { |
| "epoch": 0.11272727272727273, |
| "grad_norm": 0.1532757431268692, |
| "learning_rate": 0.0005948843048502316, |
| "loss": 2.7237933349609373, |
| "step": 48400 |
| }, |
| { |
| "epoch": 0.11363636363636363, |
| "grad_norm": 0.18864984810352325, |
| "learning_rate": 0.0005934799559331318, |
| "loss": 2.7044161987304687, |
| "step": 48500 |
| }, |
| { |
| "epoch": 0.11454545454545455, |
| "grad_norm": 0.1558079868555069, |
| "learning_rate": 0.0005920748424450241, |
| "loss": 2.7322943115234377, |
| "step": 48600 |
| }, |
| { |
| "epoch": 0.11545454545454545, |
| "grad_norm": 0.14599354565143585, |
| "learning_rate": 0.0005906689758783081, |
| "loss": 2.6957037353515627, |
| "step": 48700 |
| }, |
| { |
| "epoch": 0.11636363636363636, |
| "grad_norm": 0.16394606232643127, |
| "learning_rate": 0.0005892623677315435, |
| "loss": 2.735413818359375, |
| "step": 48800 |
| }, |
| { |
| "epoch": 0.11727272727272728, |
| "grad_norm": 0.16016560792922974, |
| "learning_rate": 0.0005878550295093547, |
| "loss": 2.743086853027344, |
| "step": 48900 |
| }, |
| { |
| "epoch": 0.11818181818181818, |
| "grad_norm": 0.1616428941488266, |
| "learning_rate": 0.0005864469727223377, |
| "loss": 2.6787353515625, |
| "step": 49000 |
| }, |
| { |
| "epoch": 0.11818181818181818, |
| "eval_loss": 3.087231159210205, |
| "eval_runtime": 7.451, |
| "eval_samples_per_second": 77.305, |
| "eval_steps_per_second": 19.326, |
| "step": 49000 |
| }, |
| { |
| "epoch": 0.1190909090909091, |
| "grad_norm": 0.1776418387889862, |
| "learning_rate": 0.0005850382088869656, |
| "loss": 2.6989129638671874, |
| "step": 49100 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 0.14982151985168457, |
| "learning_rate": 0.0005836287495254947, |
| "loss": 2.6925369262695313, |
| "step": 49200 |
| }, |
| { |
| "epoch": 0.12090909090909091, |
| "grad_norm": 0.15882854163646698, |
| "learning_rate": 0.0005822186061658693, |
| "loss": 2.7088381958007814, |
| "step": 49300 |
| }, |
| { |
| "epoch": 0.12181818181818181, |
| "grad_norm": 0.17874722182750702, |
| "learning_rate": 0.0005808077903416286, |
| "loss": 2.6966705322265625, |
| "step": 49400 |
| }, |
| { |
| "epoch": 0.12272727272727273, |
| "grad_norm": 0.17074082791805267, |
| "learning_rate": 0.0005793963135918122, |
| "loss": 2.7259332275390626, |
| "step": 49500 |
| }, |
| { |
| "epoch": 0.12363636363636364, |
| "grad_norm": 0.15236154198646545, |
| "learning_rate": 0.0005779841874608646, |
| "loss": 2.7060787963867186, |
| "step": 49600 |
| }, |
| { |
| "epoch": 0.12454545454545454, |
| "grad_norm": 0.15823383629322052, |
| "learning_rate": 0.0005765714234985422, |
| "loss": 2.681339111328125, |
| "step": 49700 |
| }, |
| { |
| "epoch": 0.12545454545454546, |
| "grad_norm": 0.21889136731624603, |
| "learning_rate": 0.0005751580332598178, |
| "loss": 2.693275146484375, |
| "step": 49800 |
| }, |
| { |
| "epoch": 0.12636363636363637, |
| "grad_norm": 0.1490192860364914, |
| "learning_rate": 0.000573744028304787, |
| "loss": 2.6937310791015623, |
| "step": 49900 |
| }, |
| { |
| "epoch": 0.12727272727272726, |
| "grad_norm": 0.1623009741306305, |
| "learning_rate": 0.0005723294201985724, |
| "loss": 2.678116760253906, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.12727272727272726, |
| "eval_loss": 3.082812786102295, |
| "eval_runtime": 7.4452, |
| "eval_samples_per_second": 77.366, |
| "eval_steps_per_second": 19.341, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.12818181818181817, |
| "grad_norm": 0.1424219161272049, |
| "learning_rate": 0.0005709142205112308, |
| "loss": 2.690723876953125, |
| "step": 50100 |
| }, |
| { |
| "epoch": 0.1290909090909091, |
| "grad_norm": 0.15792372822761536, |
| "learning_rate": 0.0005694984408176566, |
| "loss": 2.7299853515625, |
| "step": 50200 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 0.151839479804039, |
| "learning_rate": 0.0005680820926974884, |
| "loss": 2.665604248046875, |
| "step": 50300 |
| }, |
| { |
| "epoch": 0.13090909090909092, |
| "grad_norm": 0.1519307941198349, |
| "learning_rate": 0.0005666651877350139, |
| "loss": 2.6907989501953127, |
| "step": 50400 |
| }, |
| { |
| "epoch": 0.1318181818181818, |
| "grad_norm": 0.14843234419822693, |
| "learning_rate": 0.0005652477375190755, |
| "loss": 2.684622802734375, |
| "step": 50500 |
| }, |
| { |
| "epoch": 0.13272727272727272, |
| "grad_norm": 0.1492377370595932, |
| "learning_rate": 0.000563829753642975, |
| "loss": 2.68843994140625, |
| "step": 50600 |
| }, |
| { |
| "epoch": 0.13363636363636364, |
| "grad_norm": 0.1397194117307663, |
| "learning_rate": 0.0005624112477043789, |
| "loss": 2.6910018920898438, |
| "step": 50700 |
| }, |
| { |
| "epoch": 0.13454545454545455, |
| "grad_norm": 0.14176790416240692, |
| "learning_rate": 0.0005609922313052237, |
| "loss": 2.6935055541992186, |
| "step": 50800 |
| }, |
| { |
| "epoch": 0.13545454545454547, |
| "grad_norm": 0.16330276429653168, |
| "learning_rate": 0.0005595727160516208, |
| "loss": 2.6888656616210938, |
| "step": 50900 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 0.1529064178466797, |
| "learning_rate": 0.0005581527135537623, |
| "loss": 2.709434814453125, |
| "step": 51000 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "eval_loss": 3.07966685295105, |
| "eval_runtime": 7.3998, |
| "eval_samples_per_second": 77.84, |
| "eval_steps_per_second": 19.46, |
| "step": 51000 |
| }, |
| { |
| "epoch": 0.13727272727272727, |
| "grad_norm": 0.1499529331922531, |
| "learning_rate": 0.0005567322354258249, |
| "loss": 2.694036560058594, |
| "step": 51100 |
| }, |
| { |
| "epoch": 0.13818181818181818, |
| "grad_norm": 0.1941758096218109, |
| "learning_rate": 0.0005553112932858754, |
| "loss": 2.679619140625, |
| "step": 51200 |
| }, |
| { |
| "epoch": 0.1390909090909091, |
| "grad_norm": 0.1703883409500122, |
| "learning_rate": 0.0005538898987557763, |
| "loss": 2.7490829467773437, |
| "step": 51300 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 0.1707204133272171, |
| "learning_rate": 0.0005524680634610897, |
| "loss": 2.701058349609375, |
| "step": 51400 |
| }, |
| { |
| "epoch": 0.1409090909090909, |
| "grad_norm": 0.1748669594526291, |
| "learning_rate": 0.0005510457990309829, |
| "loss": 2.6962744140625, |
| "step": 51500 |
| }, |
| { |
| "epoch": 0.14181818181818182, |
| "grad_norm": 0.16774185001850128, |
| "learning_rate": 0.0005496231170981329, |
| "loss": 2.6645233154296877, |
| "step": 51600 |
| }, |
| { |
| "epoch": 0.14272727272727273, |
| "grad_norm": 0.15208636224269867, |
| "learning_rate": 0.000548200029298632, |
| "loss": 2.6871743774414063, |
| "step": 51700 |
| }, |
| { |
| "epoch": 0.14363636363636365, |
| "grad_norm": 0.17048777639865875, |
| "learning_rate": 0.0005467765472718914, |
| "loss": 2.6941012573242187, |
| "step": 51800 |
| }, |
| { |
| "epoch": 0.14454545454545453, |
| "grad_norm": 0.1853557974100113, |
| "learning_rate": 0.000545352682660547, |
| "loss": 2.669810791015625, |
| "step": 51900 |
| }, |
| { |
| "epoch": 0.14545454545454545, |
| "grad_norm": 0.18524755537509918, |
| "learning_rate": 0.0005439284471103641, |
| "loss": 2.714384765625, |
| "step": 52000 |
| }, |
| { |
| "epoch": 0.14545454545454545, |
| "eval_loss": 3.08223819732666, |
| "eval_runtime": 7.441, |
| "eval_samples_per_second": 77.409, |
| "eval_steps_per_second": 19.352, |
| "step": 52000 |
| }, |
| { |
| "epoch": 0.14636363636363636, |
| "grad_norm": 0.15897710621356964, |
| "learning_rate": 0.0005425038522701411, |
| "loss": 2.6896728515625, |
| "step": 52100 |
| }, |
| { |
| "epoch": 0.14727272727272728, |
| "grad_norm": 0.1507830172777176, |
| "learning_rate": 0.0005410789097916161, |
| "loss": 2.661712341308594, |
| "step": 52200 |
| }, |
| { |
| "epoch": 0.1481818181818182, |
| "grad_norm": 0.1556272655725479, |
| "learning_rate": 0.0005396536313293696, |
| "loss": 2.6831851196289063, |
| "step": 52300 |
| }, |
| { |
| "epoch": 0.14909090909090908, |
| "grad_norm": 0.15099219977855682, |
| "learning_rate": 0.0005382280285407307, |
| "loss": 2.6684881591796876, |
| "step": 52400 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.15491120517253876, |
| "learning_rate": 0.0005368021130856809, |
| "loss": 2.673580322265625, |
| "step": 52500 |
| }, |
| { |
| "epoch": 0.1509090909090909, |
| "grad_norm": 0.1487579345703125, |
| "learning_rate": 0.0005353758966267588, |
| "loss": 2.690845642089844, |
| "step": 52600 |
| }, |
| { |
| "epoch": 0.15181818181818182, |
| "grad_norm": 0.1554812639951706, |
| "learning_rate": 0.0005339493908289656, |
| "loss": 2.67916748046875, |
| "step": 52700 |
| }, |
| { |
| "epoch": 0.15272727272727274, |
| "grad_norm": 0.15371479094028473, |
| "learning_rate": 0.0005325226073596681, |
| "loss": 2.6689898681640627, |
| "step": 52800 |
| }, |
| { |
| "epoch": 0.15363636363636363, |
| "grad_norm": 0.21308736503124237, |
| "learning_rate": 0.0005310955578885049, |
| "loss": 2.696147766113281, |
| "step": 52900 |
| }, |
| { |
| "epoch": 0.15454545454545454, |
| "grad_norm": 0.15344563126564026, |
| "learning_rate": 0.0005296682540872898, |
| "loss": 2.6800167846679686, |
| "step": 53000 |
| }, |
| { |
| "epoch": 0.15454545454545454, |
| "eval_loss": 3.073288917541504, |
| "eval_runtime": 7.4514, |
| "eval_samples_per_second": 77.301, |
| "eval_steps_per_second": 19.325, |
| "step": 53000 |
| }, |
| { |
| "epoch": 0.15545454545454546, |
| "grad_norm": 0.14833194017410278, |
| "learning_rate": 0.000528240707629917, |
| "loss": 2.6591696166992187, |
| "step": 53100 |
| }, |
| { |
| "epoch": 0.15636363636363637, |
| "grad_norm": 0.200588196516037, |
| "learning_rate": 0.0005268129301922651, |
| "loss": 2.652269287109375, |
| "step": 53200 |
| }, |
| { |
| "epoch": 0.1572727272727273, |
| "grad_norm": 0.1412370204925537, |
| "learning_rate": 0.0005253849334521023, |
| "loss": 2.674943542480469, |
| "step": 53300 |
| }, |
| { |
| "epoch": 0.15818181818181817, |
| "grad_norm": 0.1481807678937912, |
| "learning_rate": 0.0005239567290889901, |
| "loss": 2.6497378540039063, |
| "step": 53400 |
| }, |
| { |
| "epoch": 0.1590909090909091, |
| "grad_norm": 0.1553225964307785, |
| "learning_rate": 0.0005225283287841883, |
| "loss": 2.655411682128906, |
| "step": 53500 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.1549694985151291, |
| "learning_rate": 0.0005210997442205594, |
| "loss": 2.654962158203125, |
| "step": 53600 |
| }, |
| { |
| "epoch": 0.16090909090909092, |
| "grad_norm": 0.1860799938440323, |
| "learning_rate": 0.0005196709870824726, |
| "loss": 2.6886834716796875, |
| "step": 53700 |
| }, |
| { |
| "epoch": 0.1618181818181818, |
| "grad_norm": 0.14446097612380981, |
| "learning_rate": 0.0005182420690557091, |
| "loss": 2.6884750366210937, |
| "step": 53800 |
| }, |
| { |
| "epoch": 0.16272727272727272, |
| "grad_norm": 0.14465349912643433, |
| "learning_rate": 0.0005168130018273655, |
| "loss": 2.677554931640625, |
| "step": 53900 |
| }, |
| { |
| "epoch": 0.16363636363636364, |
| "grad_norm": 0.14523738622665405, |
| "learning_rate": 0.0005153837970857591, |
| "loss": 2.66891357421875, |
| "step": 54000 |
| }, |
| { |
| "epoch": 0.16363636363636364, |
| "eval_loss": 3.070340394973755, |
| "eval_runtime": 7.4203, |
| "eval_samples_per_second": 77.625, |
| "eval_steps_per_second": 19.406, |
| "step": 54000 |
| }, |
| { |
| "epoch": 0.16454545454545455, |
| "grad_norm": 0.14817142486572266, |
| "learning_rate": 0.0005139544665203315, |
| "loss": 2.69839599609375, |
| "step": 54100 |
| }, |
| { |
| "epoch": 0.16545454545454547, |
| "grad_norm": 0.18234474956989288, |
| "learning_rate": 0.0005125250218215538, |
| "loss": 2.667855224609375, |
| "step": 54200 |
| }, |
| { |
| "epoch": 0.16636363636363635, |
| "grad_norm": 0.16814777255058289, |
| "learning_rate": 0.0005110954746808307, |
| "loss": 2.683269348144531, |
| "step": 54300 |
| }, |
| { |
| "epoch": 0.16727272727272727, |
| "grad_norm": 0.1632496416568756, |
| "learning_rate": 0.0005096658367904042, |
| "loss": 2.670632629394531, |
| "step": 54400 |
| }, |
| { |
| "epoch": 0.16818181818181818, |
| "grad_norm": 0.15290036797523499, |
| "learning_rate": 0.0005082361198432592, |
| "loss": 2.6895196533203123, |
| "step": 54500 |
| }, |
| { |
| "epoch": 0.1690909090909091, |
| "grad_norm": 0.15638327598571777, |
| "learning_rate": 0.0005068063355330264, |
| "loss": 2.676280212402344, |
| "step": 54600 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 0.14327116310596466, |
| "learning_rate": 0.0005053764955538885, |
| "loss": 2.693046875, |
| "step": 54700 |
| }, |
| { |
| "epoch": 0.1709090909090909, |
| "grad_norm": 0.1540258675813675, |
| "learning_rate": 0.0005039466116004827, |
| "loss": 2.6647442626953124, |
| "step": 54800 |
| }, |
| { |
| "epoch": 0.17181818181818181, |
| "grad_norm": 0.14872531592845917, |
| "learning_rate": 0.0005025166953678061, |
| "loss": 2.669239501953125, |
| "step": 54900 |
| }, |
| { |
| "epoch": 0.17272727272727273, |
| "grad_norm": 0.15456752479076385, |
| "learning_rate": 0.0005010867585511199, |
| "loss": 2.6779644775390623, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.17272727272727273, |
| "eval_loss": 3.070594072341919, |
| "eval_runtime": 7.4584, |
| "eval_samples_per_second": 77.229, |
| "eval_steps_per_second": 19.307, |
| "step": 55000 |
| }, |
| { |
| "epoch": 0.17363636363636364, |
| "grad_norm": 0.14803044497966766, |
| "learning_rate": 0.0004996568128458535, |
| "loss": 2.698114013671875, |
| "step": 55100 |
| }, |
| { |
| "epoch": 0.17454545454545456, |
| "grad_norm": 0.14924941956996918, |
| "learning_rate": 0.0004982268699475092, |
| "loss": 2.638841247558594, |
| "step": 55200 |
| }, |
| { |
| "epoch": 0.17545454545454545, |
| "grad_norm": 0.15640807151794434, |
| "learning_rate": 0.0004967969415515659, |
| "loss": 2.6517404174804686, |
| "step": 55300 |
| }, |
| { |
| "epoch": 0.17636363636363636, |
| "grad_norm": 0.18078777194023132, |
| "learning_rate": 0.0004953670393533846, |
| "loss": 2.6669937133789063, |
| "step": 55400 |
| }, |
| { |
| "epoch": 0.17727272727272728, |
| "grad_norm": 0.15050143003463745, |
| "learning_rate": 0.0004939371750481115, |
| "loss": 2.6495355224609374, |
| "step": 55500 |
| }, |
| { |
| "epoch": 0.1781818181818182, |
| "grad_norm": 0.15939530730247498, |
| "learning_rate": 0.0004925073603305833, |
| "loss": 2.673974609375, |
| "step": 55600 |
| }, |
| { |
| "epoch": 0.17909090909090908, |
| "grad_norm": 0.7551309466362, |
| "learning_rate": 0.0004910776068952304, |
| "loss": 2.6610736083984374, |
| "step": 55700 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 0.14220239222049713, |
| "learning_rate": 0.0004896479264359827, |
| "loss": 2.7120089721679688, |
| "step": 55800 |
| }, |
| { |
| "epoch": 0.1809090909090909, |
| "grad_norm": 0.17650385200977325, |
| "learning_rate": 0.0004882183306461728, |
| "loss": 2.6712158203125, |
| "step": 55900 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 0.15496277809143066, |
| "learning_rate": 0.00048678883121844096, |
| "loss": 2.6805792236328125, |
| "step": 56000 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "eval_loss": 3.068009614944458, |
| "eval_runtime": 7.4586, |
| "eval_samples_per_second": 77.227, |
| "eval_steps_per_second": 19.307, |
| "step": 56000 |
| }, |
| { |
| "epoch": 0.18272727272727274, |
| "grad_norm": 0.15831124782562256, |
| "learning_rate": 0.00048535943984463943, |
| "loss": 2.685963134765625, |
| "step": 56100 |
| }, |
| { |
| "epoch": 0.18363636363636363, |
| "grad_norm": 0.17237283289432526, |
| "learning_rate": 0.00048393016821573625, |
| "loss": 2.652848205566406, |
| "step": 56200 |
| }, |
| { |
| "epoch": 0.18454545454545454, |
| "grad_norm": 0.172745019197464, |
| "learning_rate": 0.00048250102802172067, |
| "loss": 2.6385073852539063, |
| "step": 56300 |
| }, |
| { |
| "epoch": 0.18545454545454546, |
| "grad_norm": 0.16651754081249237, |
| "learning_rate": 0.00048107203095150636, |
| "loss": 2.6532525634765625, |
| "step": 56400 |
| }, |
| { |
| "epoch": 0.18636363636363637, |
| "grad_norm": 0.16987019777297974, |
| "learning_rate": 0.00047964318869283683, |
| "loss": 2.690726623535156, |
| "step": 56500 |
| }, |
| { |
| "epoch": 0.18727272727272729, |
| "grad_norm": 0.15424904227256775, |
| "learning_rate": 0.000478214512932189, |
| "loss": 2.6622409057617187, |
| "step": 56600 |
| }, |
| { |
| "epoch": 0.18818181818181817, |
| "grad_norm": 0.1839853674173355, |
| "learning_rate": 0.0004767860153546783, |
| "loss": 2.683760681152344, |
| "step": 56700 |
| }, |
| { |
| "epoch": 0.1890909090909091, |
| "grad_norm": 0.15451455116271973, |
| "learning_rate": 0.0004753577076439628, |
| "loss": 2.6614370727539063, |
| "step": 56800 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.19505156576633453, |
| "learning_rate": 0.0004739296014821474, |
| "loss": 2.65382080078125, |
| "step": 56900 |
| }, |
| { |
| "epoch": 0.19090909090909092, |
| "grad_norm": 0.20561884343624115, |
| "learning_rate": 0.0004725017085496889, |
| "loss": 2.70877685546875, |
| "step": 57000 |
| }, |
| { |
| "epoch": 0.19090909090909092, |
| "eval_loss": 3.0625686645507812, |
| "eval_runtime": 7.4104, |
| "eval_samples_per_second": 77.728, |
| "eval_steps_per_second": 19.432, |
| "step": 57000 |
| }, |
| { |
| "epoch": 0.1918181818181818, |
| "grad_norm": 0.1769583523273468, |
| "learning_rate": 0.00047107404052529957, |
| "loss": 2.6674728393554688, |
| "step": 57100 |
| }, |
| { |
| "epoch": 0.19272727272727272, |
| "grad_norm": 0.15023104846477509, |
| "learning_rate": 0.0004696466090858528, |
| "loss": 2.6564959716796874, |
| "step": 57200 |
| }, |
| { |
| "epoch": 0.19363636363636363, |
| "grad_norm": 0.1738213300704956, |
| "learning_rate": 0.00046821942590628645, |
| "loss": 2.6518304443359373, |
| "step": 57300 |
| }, |
| { |
| "epoch": 0.19454545454545455, |
| "grad_norm": 0.15652106702327728, |
| "learning_rate": 0.00046679250265950815, |
| "loss": 2.6429074096679686, |
| "step": 57400 |
| }, |
| { |
| "epoch": 0.19545454545454546, |
| "grad_norm": 0.20546045899391174, |
| "learning_rate": 0.00046536585101629945, |
| "loss": 2.66235107421875, |
| "step": 57500 |
| }, |
| { |
| "epoch": 0.19636363636363635, |
| "grad_norm": 0.15202665328979492, |
| "learning_rate": 0.0004639394826452204, |
| "loss": 2.635772399902344, |
| "step": 57600 |
| }, |
| { |
| "epoch": 0.19727272727272727, |
| "grad_norm": 0.1581605225801468, |
| "learning_rate": 0.00046251340921251436, |
| "loss": 2.6710745239257814, |
| "step": 57700 |
| }, |
| { |
| "epoch": 0.19818181818181818, |
| "grad_norm": 0.19863693416118622, |
| "learning_rate": 0.000461087642382012, |
| "loss": 2.645235595703125, |
| "step": 57800 |
| }, |
| { |
| "epoch": 0.1990909090909091, |
| "grad_norm": 0.14989744126796722, |
| "learning_rate": 0.00045966219381503694, |
| "loss": 2.6374029541015624, |
| "step": 57900 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.18618331849575043, |
| "learning_rate": 0.000458237075170309, |
| "loss": 2.6277200317382814, |
| "step": 58000 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 3.0661063194274902, |
| "eval_runtime": 7.4551, |
| "eval_samples_per_second": 77.262, |
| "eval_steps_per_second": 19.316, |
| "step": 58000 |
| }, |
| { |
| "epoch": 0.2009090909090909, |
| "grad_norm": 0.16106659173965454, |
| "learning_rate": 0.00045681229810385005, |
| "loss": 2.6352557373046874, |
| "step": 58100 |
| }, |
| { |
| "epoch": 0.2018181818181818, |
| "grad_norm": 0.14770276844501495, |
| "learning_rate": 0.000455387874268888, |
| "loss": 2.627791442871094, |
| "step": 58200 |
| }, |
| { |
| "epoch": 0.20272727272727273, |
| "grad_norm": 0.17903557419776917, |
| "learning_rate": 0.0004539638153157621, |
| "loss": 2.638799133300781, |
| "step": 58300 |
| }, |
| { |
| "epoch": 0.20363636363636364, |
| "grad_norm": 0.16185429692268372, |
| "learning_rate": 0.0004525401328918264, |
| "loss": 2.635686340332031, |
| "step": 58400 |
| }, |
| { |
| "epoch": 0.20454545454545456, |
| "grad_norm": 0.17657916247844696, |
| "learning_rate": 0.00045111683864135617, |
| "loss": 2.6360543823242186, |
| "step": 58500 |
| }, |
| { |
| "epoch": 0.20545454545454545, |
| "grad_norm": 0.14804042875766754, |
| "learning_rate": 0.0004496939442054514, |
| "loss": 2.643255310058594, |
| "step": 58600 |
| }, |
| { |
| "epoch": 0.20636363636363636, |
| "grad_norm": 0.16301922500133514, |
| "learning_rate": 0.0004482714612219419, |
| "loss": 2.64661376953125, |
| "step": 58700 |
| }, |
| { |
| "epoch": 0.20727272727272728, |
| "grad_norm": 0.1726071685552597, |
| "learning_rate": 0.00044684940132529264, |
| "loss": 2.6665936279296876, |
| "step": 58800 |
| }, |
| { |
| "epoch": 0.2081818181818182, |
| "grad_norm": 0.16906021535396576, |
| "learning_rate": 0.0004454277761465076, |
| "loss": 2.65294921875, |
| "step": 58900 |
| }, |
| { |
| "epoch": 0.20909090909090908, |
| "grad_norm": 0.17039760947227478, |
| "learning_rate": 0.0004440065973130358, |
| "loss": 2.6539688110351562, |
| "step": 59000 |
| }, |
| { |
| "epoch": 0.20909090909090908, |
| "eval_loss": 3.057651996612549, |
| "eval_runtime": 7.4341, |
| "eval_samples_per_second": 77.481, |
| "eval_steps_per_second": 19.37, |
| "step": 59000 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.1761595457792282, |
| "learning_rate": 0.0004425858764486751, |
| "loss": 2.6766180419921874, |
| "step": 59100 |
| }, |
| { |
| "epoch": 0.2109090909090909, |
| "grad_norm": 0.16640876233577728, |
| "learning_rate": 0.00044116562517347796, |
| "loss": 2.6426458740234375, |
| "step": 59200 |
| }, |
| { |
| "epoch": 0.21181818181818182, |
| "grad_norm": 0.1541028618812561, |
| "learning_rate": 0.00043974585510365614, |
| "loss": 2.6716134643554685, |
| "step": 59300 |
| }, |
| { |
| "epoch": 0.21272727272727274, |
| "grad_norm": 0.16134560108184814, |
| "learning_rate": 0.0004383265778514852, |
| "loss": 2.6808517456054686, |
| "step": 59400 |
| }, |
| { |
| "epoch": 0.21363636363636362, |
| "grad_norm": 0.1456531435251236, |
| "learning_rate": 0.0004369078050252105, |
| "loss": 2.684778747558594, |
| "step": 59500 |
| }, |
| { |
| "epoch": 0.21454545454545454, |
| "grad_norm": 0.1792006641626358, |
| "learning_rate": 0.00043548954822895117, |
| "loss": 2.649779052734375, |
| "step": 59600 |
| }, |
| { |
| "epoch": 0.21545454545454545, |
| "grad_norm": 0.18216730654239655, |
| "learning_rate": 0.00043407181906260627, |
| "loss": 2.677138671875, |
| "step": 59700 |
| }, |
| { |
| "epoch": 0.21636363636363637, |
| "grad_norm": 0.1598980575799942, |
| "learning_rate": 0.0004326546291217589, |
| "loss": 2.6525616455078125, |
| "step": 59800 |
| }, |
| { |
| "epoch": 0.21727272727272728, |
| "grad_norm": 0.16436710953712463, |
| "learning_rate": 0.0004312379899975821, |
| "loss": 2.6850616455078127, |
| "step": 59900 |
| }, |
| { |
| "epoch": 0.21818181818181817, |
| "grad_norm": 0.175828754901886, |
| "learning_rate": 0.00042982191327674404, |
| "loss": 2.6756378173828126, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.21818181818181817, |
| "eval_loss": 3.0540809631347656, |
| "eval_runtime": 7.4118, |
| "eval_samples_per_second": 77.714, |
| "eval_steps_per_second": 19.429, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.2190909090909091, |
| "grad_norm": 0.16105052828788757, |
| "learning_rate": 0.0004284064105413123, |
| "loss": 2.6820413208007814, |
| "step": 60100 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 0.17260073125362396, |
| "learning_rate": 0.00042699149336866053, |
| "loss": 2.705378112792969, |
| "step": 60200 |
| }, |
| { |
| "epoch": 0.22090909090909092, |
| "grad_norm": 0.1929374486207962, |
| "learning_rate": 0.0004255771733313727, |
| "loss": 2.6583901977539064, |
| "step": 60300 |
| }, |
| { |
| "epoch": 0.22181818181818183, |
| "grad_norm": 0.15301187336444855, |
| "learning_rate": 0.00042416346199714895, |
| "loss": 2.6433419799804687, |
| "step": 60400 |
| }, |
| { |
| "epoch": 0.22272727272727272, |
| "grad_norm": 0.16559265553951263, |
| "learning_rate": 0.0004227503709287107, |
| "loss": 2.6537457275390626, |
| "step": 60500 |
| }, |
| { |
| "epoch": 0.22363636363636363, |
| "grad_norm": 0.16312868893146515, |
| "learning_rate": 0.0004213379116837065, |
| "loss": 2.642680969238281, |
| "step": 60600 |
| }, |
| { |
| "epoch": 0.22454545454545455, |
| "grad_norm": 0.1596183180809021, |
| "learning_rate": 0.00041992609581461714, |
| "loss": 2.6479568481445312, |
| "step": 60700 |
| }, |
| { |
| "epoch": 0.22545454545454546, |
| "grad_norm": 0.1691562980413437, |
| "learning_rate": 0.00041851493486866093, |
| "loss": 2.668114013671875, |
| "step": 60800 |
| }, |
| { |
| "epoch": 0.22636363636363635, |
| "grad_norm": 0.17783690989017487, |
| "learning_rate": 0.00041710444038770006, |
| "loss": 2.6744537353515625, |
| "step": 60900 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 0.14821407198905945, |
| "learning_rate": 0.00041569462390814507, |
| "loss": 2.6778204345703127, |
| "step": 61000 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "eval_loss": 3.0541512966156006, |
| "eval_runtime": 7.4401, |
| "eval_samples_per_second": 77.419, |
| "eval_steps_per_second": 19.355, |
| "step": 61000 |
| }, |
| { |
| "epoch": 0.22818181818181818, |
| "grad_norm": 0.15560130774974823, |
| "learning_rate": 0.00041428549696086213, |
| "loss": 2.6814599609375, |
| "step": 61100 |
| }, |
| { |
| "epoch": 0.2290909090909091, |
| "grad_norm": 0.16080529987812042, |
| "learning_rate": 0.0004128770710710768, |
| "loss": 2.6637908935546877, |
| "step": 61200 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 0.15518587827682495, |
| "learning_rate": 0.0004114693577582812, |
| "loss": 2.6588839721679687, |
| "step": 61300 |
| }, |
| { |
| "epoch": 0.2309090909090909, |
| "grad_norm": 0.16887351870536804, |
| "learning_rate": 0.000410062368536139, |
| "loss": 2.674110107421875, |
| "step": 61400 |
| }, |
| { |
| "epoch": 0.2318181818181818, |
| "grad_norm": 0.1643567532300949, |
| "learning_rate": 0.0004086561149123919, |
| "loss": 2.6627960205078125, |
| "step": 61500 |
| }, |
| { |
| "epoch": 0.23272727272727273, |
| "grad_norm": 0.17247343063354492, |
| "learning_rate": 0.0004072506083887647, |
| "loss": 2.680544738769531, |
| "step": 61600 |
| }, |
| { |
| "epoch": 0.23363636363636364, |
| "grad_norm": 0.17303307354450226, |
| "learning_rate": 0.0004058458604608721, |
| "loss": 2.6711715698242187, |
| "step": 61700 |
| }, |
| { |
| "epoch": 0.23454545454545456, |
| "grad_norm": 0.15602687001228333, |
| "learning_rate": 0.0004044418826181241, |
| "loss": 2.6567123413085936, |
| "step": 61800 |
| }, |
| { |
| "epoch": 0.23545454545454544, |
| "grad_norm": 0.17260140180587769, |
| "learning_rate": 0.0004030386863436319, |
| "loss": 2.6413006591796875, |
| "step": 61900 |
| }, |
| { |
| "epoch": 0.23636363636363636, |
| "grad_norm": 0.15273793041706085, |
| "learning_rate": 0.000401636283114115, |
| "loss": 2.6535302734375, |
| "step": 62000 |
| }, |
| { |
| "epoch": 0.23636363636363636, |
| "eval_loss": 3.0504443645477295, |
| "eval_runtime": 7.4706, |
| "eval_samples_per_second": 77.102, |
| "eval_steps_per_second": 19.276, |
| "step": 62000 |
| }, |
| { |
| "epoch": 0.23727272727272727, |
| "grad_norm": 0.1516442894935608, |
| "learning_rate": 0.0004002346843998058, |
| "loss": 2.65826416015625, |
| "step": 62100 |
| }, |
| { |
| "epoch": 0.2381818181818182, |
| "grad_norm": 0.16887111961841583, |
| "learning_rate": 0.0003988339016643571, |
| "loss": 2.65544189453125, |
| "step": 62200 |
| }, |
| { |
| "epoch": 0.2390909090909091, |
| "grad_norm": 0.17878231406211853, |
| "learning_rate": 0.00039743394636474735, |
| "loss": 2.6390304565429688, |
| "step": 62300 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.14858455955982208, |
| "learning_rate": 0.00039603482995118793, |
| "loss": 2.6456539916992186, |
| "step": 62400 |
| }, |
| { |
| "epoch": 0.2409090909090909, |
| "grad_norm": 0.16330905258655548, |
| "learning_rate": 0.0003946365638670289, |
| "loss": 2.6405880737304686, |
| "step": 62500 |
| }, |
| { |
| "epoch": 0.24181818181818182, |
| "grad_norm": 0.17122872173786163, |
| "learning_rate": 0.00039323915954866506, |
| "loss": 2.6345315551757813, |
| "step": 62600 |
| }, |
| { |
| "epoch": 0.24272727272727274, |
| "grad_norm": 0.15139397978782654, |
| "learning_rate": 0.00039184262842544346, |
| "loss": 2.617703857421875, |
| "step": 62700 |
| }, |
| { |
| "epoch": 0.24363636363636362, |
| "grad_norm": 0.14694419503211975, |
| "learning_rate": 0.0003904469819195686, |
| "loss": 2.6260647583007812, |
| "step": 62800 |
| }, |
| { |
| "epoch": 0.24454545454545454, |
| "grad_norm": 0.1512179970741272, |
| "learning_rate": 0.00038905223144601044, |
| "loss": 2.6326007080078124, |
| "step": 62900 |
| }, |
| { |
| "epoch": 0.24545454545454545, |
| "grad_norm": 0.1644383668899536, |
| "learning_rate": 0.00038765838841240964, |
| "loss": 2.655694885253906, |
| "step": 63000 |
| }, |
| { |
| "epoch": 0.24545454545454545, |
| "eval_loss": 3.050816774368286, |
| "eval_runtime": 7.4114, |
| "eval_samples_per_second": 77.718, |
| "eval_steps_per_second": 19.43, |
| "step": 63000 |
| }, |
| { |
| "epoch": 0.24636363636363637, |
| "grad_norm": 0.16079971194267273, |
| "learning_rate": 0.00038626546421898547, |
| "loss": 2.6361544799804686, |
| "step": 63100 |
| }, |
| { |
| "epoch": 0.24727272727272728, |
| "grad_norm": 0.16880013048648834, |
| "learning_rate": 0.0003848734702584417, |
| "loss": 2.6428652954101564, |
| "step": 63200 |
| }, |
| { |
| "epoch": 0.24818181818181817, |
| "grad_norm": 0.15799115598201752, |
| "learning_rate": 0.00038348241791587377, |
| "loss": 2.63120361328125, |
| "step": 63300 |
| }, |
| { |
| "epoch": 0.24909090909090909, |
| "grad_norm": 0.1738392412662506, |
| "learning_rate": 0.00038209231856867594, |
| "loss": 2.6429544067382813, |
| "step": 63400 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 0.16007262468338013, |
| "learning_rate": 0.0003807031835864474, |
| "loss": 2.6346502685546875, |
| "step": 63500 |
| }, |
| { |
| "epoch": 0.2509090909090909, |
| "grad_norm": 0.16581037640571594, |
| "learning_rate": 0.0003793150243309002, |
| "loss": 2.625074462890625, |
| "step": 63600 |
| }, |
| { |
| "epoch": 0.25181818181818183, |
| "grad_norm": 0.14953260123729706, |
| "learning_rate": 0.00037792785215576605, |
| "loss": 2.6320794677734374, |
| "step": 63700 |
| }, |
| { |
| "epoch": 0.25272727272727274, |
| "grad_norm": 0.15426383912563324, |
| "learning_rate": 0.0003765416784067028, |
| "loss": 2.6317816162109375, |
| "step": 63800 |
| }, |
| { |
| "epoch": 0.25363636363636366, |
| "grad_norm": 0.1912180483341217, |
| "learning_rate": 0.0003751565144212027, |
| "loss": 2.63588623046875, |
| "step": 63900 |
| }, |
| { |
| "epoch": 0.2545454545454545, |
| "grad_norm": 0.1402943879365921, |
| "learning_rate": 0.0003737723715284992, |
| "loss": 2.644476013183594, |
| "step": 64000 |
| }, |
| { |
| "epoch": 0.2545454545454545, |
| "eval_loss": 3.0472707748413086, |
| "eval_runtime": 7.4723, |
| "eval_samples_per_second": 77.085, |
| "eval_steps_per_second": 19.271, |
| "step": 64000 |
| }, |
| { |
| "epoch": 0.25545454545454543, |
| "grad_norm": 0.15801353752613068, |
| "learning_rate": 0.0003723892610494738, |
| "loss": 2.6523193359375, |
| "step": 64100 |
| }, |
| { |
| "epoch": 0.25636363636363635, |
| "grad_norm": 0.16160622239112854, |
| "learning_rate": 0.00037100719429656416, |
| "loss": 2.620086669921875, |
| "step": 64200 |
| }, |
| { |
| "epoch": 0.25727272727272726, |
| "grad_norm": 0.17042121291160583, |
| "learning_rate": 0.00036962618257367153, |
| "loss": 2.634929504394531, |
| "step": 64300 |
| }, |
| { |
| "epoch": 0.2581818181818182, |
| "grad_norm": 0.16742800176143646, |
| "learning_rate": 0.00036824623717606755, |
| "loss": 2.6305416870117186, |
| "step": 64400 |
| }, |
| { |
| "epoch": 0.2590909090909091, |
| "grad_norm": 0.15466608107089996, |
| "learning_rate": 0.000366867369390303, |
| "loss": 2.673544921875, |
| "step": 64500 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 0.16298887133598328, |
| "learning_rate": 0.00036548959049411447, |
| "loss": 2.629702453613281, |
| "step": 64600 |
| }, |
| { |
| "epoch": 0.2609090909090909, |
| "grad_norm": 0.1554904580116272, |
| "learning_rate": 0.00036411291175633275, |
| "loss": 2.664700927734375, |
| "step": 64700 |
| }, |
| { |
| "epoch": 0.26181818181818184, |
| "grad_norm": 0.16158753633499146, |
| "learning_rate": 0.0003627373444367902, |
| "loss": 2.632271423339844, |
| "step": 64800 |
| }, |
| { |
| "epoch": 0.26272727272727275, |
| "grad_norm": 0.1622844785451889, |
| "learning_rate": 0.00036136289978622925, |
| "loss": 2.626861877441406, |
| "step": 64900 |
| }, |
| { |
| "epoch": 0.2636363636363636, |
| "grad_norm": 0.16394828259944916, |
| "learning_rate": 0.0003599895890462101, |
| "loss": 2.648804016113281, |
| "step": 65000 |
| }, |
| { |
| "epoch": 0.2636363636363636, |
| "eval_loss": 3.0462276935577393, |
| "eval_runtime": 7.4377, |
| "eval_samples_per_second": 77.444, |
| "eval_steps_per_second": 19.361, |
| "step": 65000 |
| }, |
| { |
| "epoch": 0.26454545454545453, |
| "grad_norm": 0.15556195378303528, |
| "learning_rate": 0.000358617423449018, |
| "loss": 2.6247119140625, |
| "step": 65100 |
| }, |
| { |
| "epoch": 0.26545454545454544, |
| "grad_norm": 0.1603025197982788, |
| "learning_rate": 0.00035724641421757314, |
| "loss": 2.6453323364257812, |
| "step": 65200 |
| }, |
| { |
| "epoch": 0.26636363636363636, |
| "grad_norm": 0.17644956707954407, |
| "learning_rate": 0.0003558765725653368, |
| "loss": 2.67004638671875, |
| "step": 65300 |
| }, |
| { |
| "epoch": 0.2672727272727273, |
| "grad_norm": 0.17642109096050262, |
| "learning_rate": 0.0003545079096962215, |
| "loss": 2.6238552856445314, |
| "step": 65400 |
| }, |
| { |
| "epoch": 0.2681818181818182, |
| "grad_norm": 0.16550812125205994, |
| "learning_rate": 0.00035314043680449773, |
| "loss": 2.635771484375, |
| "step": 65500 |
| }, |
| { |
| "epoch": 0.2690909090909091, |
| "grad_norm": 0.18358127772808075, |
| "learning_rate": 0.0003517741650747038, |
| "loss": 2.673054504394531, |
| "step": 65600 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 0.14490514993667603, |
| "learning_rate": 0.0003504091056815537, |
| "loss": 2.6274179077148436, |
| "step": 65700 |
| }, |
| { |
| "epoch": 0.27090909090909093, |
| "grad_norm": 0.15338118374347687, |
| "learning_rate": 0.00034904526978984517, |
| "loss": 2.6343759155273436, |
| "step": 65800 |
| }, |
| { |
| "epoch": 0.2718181818181818, |
| "grad_norm": 0.1604444533586502, |
| "learning_rate": 0.00034768266855436967, |
| "loss": 2.643642578125, |
| "step": 65900 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 0.16554522514343262, |
| "learning_rate": 0.0003463213131198198, |
| "loss": 2.645709228515625, |
| "step": 66000 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "eval_loss": 3.0441606044769287, |
| "eval_runtime": 7.4053, |
| "eval_samples_per_second": 77.782, |
| "eval_steps_per_second": 19.445, |
| "step": 66000 |
| }, |
| { |
| "epoch": 0.2736363636363636, |
| "grad_norm": 0.16071894764900208, |
| "learning_rate": 0.00034496121462069916, |
| "loss": 2.6328436279296876, |
| "step": 66100 |
| }, |
| { |
| "epoch": 0.27454545454545454, |
| "grad_norm": 0.1610708087682724, |
| "learning_rate": 0.000343602384181231, |
| "loss": 2.650054626464844, |
| "step": 66200 |
| }, |
| { |
| "epoch": 0.27545454545454545, |
| "grad_norm": 0.1581074744462967, |
| "learning_rate": 0.00034224483291526666, |
| "loss": 2.6330722045898436, |
| "step": 66300 |
| }, |
| { |
| "epoch": 0.27636363636363637, |
| "grad_norm": 0.16902528703212738, |
| "learning_rate": 0.0003408885719261956, |
| "loss": 2.60602783203125, |
| "step": 66400 |
| }, |
| { |
| "epoch": 0.2772727272727273, |
| "grad_norm": 0.1647139936685562, |
| "learning_rate": 0.0003395336123068537, |
| "loss": 2.6406063842773437, |
| "step": 66500 |
| }, |
| { |
| "epoch": 0.2781818181818182, |
| "grad_norm": 0.16128414869308472, |
| "learning_rate": 0.0003381799651394335, |
| "loss": 2.6316217041015624, |
| "step": 66600 |
| }, |
| { |
| "epoch": 0.2790909090909091, |
| "grad_norm": 0.1957395374774933, |
| "learning_rate": 0.0003368276414953922, |
| "loss": 2.6092684936523436, |
| "step": 66700 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.14507023990154266, |
| "learning_rate": 0.0003354766524353632, |
| "loss": 2.602089538574219, |
| "step": 66800 |
| }, |
| { |
| "epoch": 0.2809090909090909, |
| "grad_norm": 0.17211727797985077, |
| "learning_rate": 0.0003341270090090631, |
| "loss": 2.65368896484375, |
| "step": 66900 |
| }, |
| { |
| "epoch": 0.2818181818181818, |
| "grad_norm": 0.15183623135089874, |
| "learning_rate": 0.0003327787222552032, |
| "loss": 2.647850341796875, |
| "step": 67000 |
| }, |
| { |
| "epoch": 0.2818181818181818, |
| "eval_loss": 3.037811279296875, |
| "eval_runtime": 7.4649, |
| "eval_samples_per_second": 77.161, |
| "eval_steps_per_second": 19.29, |
| "step": 67000 |
| }, |
| { |
| "epoch": 0.2827272727272727, |
| "grad_norm": 0.147422194480896, |
| "learning_rate": 0.0003314318032013985, |
| "loss": 2.63864501953125, |
| "step": 67100 |
| }, |
| { |
| "epoch": 0.28363636363636363, |
| "grad_norm": 0.15864703059196472, |
| "learning_rate": 0.00033008626286407756, |
| "loss": 2.6240463256835938, |
| "step": 67200 |
| }, |
| { |
| "epoch": 0.28454545454545455, |
| "grad_norm": 0.15877065062522888, |
| "learning_rate": 0.0003287421122483924, |
| "loss": 2.640238952636719, |
| "step": 67300 |
| }, |
| { |
| "epoch": 0.28545454545454546, |
| "grad_norm": 0.15702606737613678, |
| "learning_rate": 0.00032739936234812863, |
| "loss": 2.6432769775390623, |
| "step": 67400 |
| }, |
| { |
| "epoch": 0.2863636363636364, |
| "grad_norm": 0.17382535338401794, |
| "learning_rate": 0.0003260580241456155, |
| "loss": 2.6252288818359375, |
| "step": 67500 |
| }, |
| { |
| "epoch": 0.2872727272727273, |
| "grad_norm": 0.15588997304439545, |
| "learning_rate": 0.00032471810861163573, |
| "loss": 2.6104010009765624, |
| "step": 67600 |
| }, |
| { |
| "epoch": 0.2881818181818182, |
| "grad_norm": 0.17598041892051697, |
| "learning_rate": 0.0003233796267053365, |
| "loss": 2.6319580078125, |
| "step": 67700 |
| }, |
| { |
| "epoch": 0.28909090909090907, |
| "grad_norm": 0.15314966440200806, |
| "learning_rate": 0.0003220425893741388, |
| "loss": 2.6283184814453127, |
| "step": 67800 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.17279887199401855, |
| "learning_rate": 0.000320707007553649, |
| "loss": 2.6345831298828126, |
| "step": 67900 |
| }, |
| { |
| "epoch": 0.2909090909090909, |
| "grad_norm": 0.20019470155239105, |
| "learning_rate": 0.0003193728921675685, |
| "loss": 2.630293273925781, |
| "step": 68000 |
| }, |
| { |
| "epoch": 0.2909090909090909, |
| "eval_loss": 3.0448532104492188, |
| "eval_runtime": 7.4367, |
| "eval_samples_per_second": 77.454, |
| "eval_steps_per_second": 19.363, |
| "step": 68000 |
| }, |
| { |
| "epoch": 0.2918181818181818, |
| "grad_norm": 0.18501834571361542, |
| "learning_rate": 0.0003180402541276048, |
| "loss": 2.650793151855469, |
| "step": 68100 |
| }, |
| { |
| "epoch": 0.2927272727272727, |
| "grad_norm": 0.14561575651168823, |
| "learning_rate": 0.00031670910433338273, |
| "loss": 2.6040188598632814, |
| "step": 68200 |
| }, |
| { |
| "epoch": 0.29363636363636364, |
| "grad_norm": 0.16025520861148834, |
| "learning_rate": 0.00031537945367235393, |
| "loss": 2.6409112548828126, |
| "step": 68300 |
| }, |
| { |
| "epoch": 0.29454545454545455, |
| "grad_norm": 0.15475542843341827, |
| "learning_rate": 0.00031405131301970936, |
| "loss": 2.6054486083984374, |
| "step": 68400 |
| }, |
| { |
| "epoch": 0.29545454545454547, |
| "grad_norm": 0.15857645869255066, |
| "learning_rate": 0.0003127246932382891, |
| "loss": 2.616719055175781, |
| "step": 68500 |
| }, |
| { |
| "epoch": 0.2963636363636364, |
| "grad_norm": 0.19392845034599304, |
| "learning_rate": 0.0003113996051784945, |
| "loss": 2.60544921875, |
| "step": 68600 |
| }, |
| { |
| "epoch": 0.2972727272727273, |
| "grad_norm": 0.19967029988765717, |
| "learning_rate": 0.00031007605967819896, |
| "loss": 2.6308856201171875, |
| "step": 68700 |
| }, |
| { |
| "epoch": 0.29818181818181816, |
| "grad_norm": 0.19477345049381256, |
| "learning_rate": 0.00030875406756265887, |
| "loss": 2.6351129150390626, |
| "step": 68800 |
| }, |
| { |
| "epoch": 0.2990909090909091, |
| "grad_norm": 0.15118417143821716, |
| "learning_rate": 0.000307433639644426, |
| "loss": 2.614127197265625, |
| "step": 68900 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 0.15570956468582153, |
| "learning_rate": 0.0003061147867232582, |
| "loss": 2.608861389160156, |
| "step": 69000 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_loss": 3.0342400074005127, |
| "eval_runtime": 7.4253, |
| "eval_samples_per_second": 77.572, |
| "eval_steps_per_second": 19.393, |
| "step": 69000 |
| }, |
| { |
| "epoch": 0.3009090909090909, |
| "grad_norm": 0.1571355015039444, |
| "learning_rate": 0.0003047975195860318, |
| "loss": 2.606195983886719, |
| "step": 69100 |
| }, |
| { |
| "epoch": 0.3018181818181818, |
| "grad_norm": 0.15814636647701263, |
| "learning_rate": 0.0003034818490066527, |
| "loss": 2.5954779052734374, |
| "step": 69200 |
| }, |
| { |
| "epoch": 0.30272727272727273, |
| "grad_norm": 0.14323082566261292, |
| "learning_rate": 0.00030216778574596883, |
| "loss": 2.6024984741210937, |
| "step": 69300 |
| }, |
| { |
| "epoch": 0.30363636363636365, |
| "grad_norm": 0.17691482603549957, |
| "learning_rate": 0.00030085534055168184, |
| "loss": 2.602333984375, |
| "step": 69400 |
| }, |
| { |
| "epoch": 0.30454545454545456, |
| "grad_norm": 0.17705939710140228, |
| "learning_rate": 0.00029954452415825896, |
| "loss": 2.628582763671875, |
| "step": 69500 |
| }, |
| { |
| "epoch": 0.3054545454545455, |
| "grad_norm": 0.16018672287464142, |
| "learning_rate": 0.00029823534728684587, |
| "loss": 2.617008056640625, |
| "step": 69600 |
| }, |
| { |
| "epoch": 0.30636363636363634, |
| "grad_norm": 0.16868868470191956, |
| "learning_rate": 0.0002969278206451786, |
| "loss": 2.597875671386719, |
| "step": 69700 |
| }, |
| { |
| "epoch": 0.30727272727272725, |
| "grad_norm": 0.1678052544593811, |
| "learning_rate": 0.0002956219549274957, |
| "loss": 2.59896728515625, |
| "step": 69800 |
| }, |
| { |
| "epoch": 0.30818181818181817, |
| "grad_norm": 0.15835554897785187, |
| "learning_rate": 0.00029431776081445104, |
| "loss": 2.6005072021484374, |
| "step": 69900 |
| }, |
| { |
| "epoch": 0.3090909090909091, |
| "grad_norm": 0.148189514875412, |
| "learning_rate": 0.0002930152489730271, |
| "loss": 2.596640625, |
| "step": 70000 |
| }, |
| { |
| "epoch": 0.3090909090909091, |
| "eval_loss": 3.034733772277832, |
| "eval_runtime": 7.4478, |
| "eval_samples_per_second": 77.338, |
| "eval_steps_per_second": 19.335, |
| "step": 70000 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 0.1630752682685852, |
| "learning_rate": 0.0002917144300564461, |
| "loss": 2.6199655151367187, |
| "step": 70100 |
| }, |
| { |
| "epoch": 0.3109090909090909, |
| "grad_norm": 0.16336363554000854, |
| "learning_rate": 0.00029041531470408465, |
| "loss": 2.595935974121094, |
| "step": 70200 |
| }, |
| { |
| "epoch": 0.3118181818181818, |
| "grad_norm": 0.19114582240581512, |
| "learning_rate": 0.00028911791354138574, |
| "loss": 2.6245462036132814, |
| "step": 70300 |
| }, |
| { |
| "epoch": 0.31272727272727274, |
| "grad_norm": 0.15327058732509613, |
| "learning_rate": 0.0002878222371797716, |
| "loss": 2.606686706542969, |
| "step": 70400 |
| }, |
| { |
| "epoch": 0.31363636363636366, |
| "grad_norm": 0.16627787053585052, |
| "learning_rate": 0.00028652829621655793, |
| "loss": 2.6142779541015626, |
| "step": 70500 |
| }, |
| { |
| "epoch": 0.3145454545454546, |
| "grad_norm": 0.17076851427555084, |
| "learning_rate": 0.0002852361012348663, |
| "loss": 2.6306427001953123, |
| "step": 70600 |
| }, |
| { |
| "epoch": 0.31545454545454543, |
| "grad_norm": 0.15905171632766724, |
| "learning_rate": 0.0002839456628035381, |
| "loss": 2.646249084472656, |
| "step": 70700 |
| }, |
| { |
| "epoch": 0.31636363636363635, |
| "grad_norm": 0.15757545828819275, |
| "learning_rate": 0.000282656991477048, |
| "loss": 2.6342782592773437, |
| "step": 70800 |
| }, |
| { |
| "epoch": 0.31727272727272726, |
| "grad_norm": 0.1566353142261505, |
| "learning_rate": 0.000281370097795417, |
| "loss": 2.5926519775390626, |
| "step": 70900 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 0.1587604433298111, |
| "learning_rate": 0.0002800849922841273, |
| "loss": 2.62255615234375, |
| "step": 71000 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "eval_loss": 3.0347187519073486, |
| "eval_runtime": 7.4419, |
| "eval_samples_per_second": 77.4, |
| "eval_steps_per_second": 19.35, |
| "step": 71000 |
| }, |
| { |
| "epoch": 0.3190909090909091, |
| "grad_norm": 0.15599116683006287, |
| "learning_rate": 0.0002788016854540356, |
| "loss": 2.6368426513671874, |
| "step": 71100 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.15771758556365967, |
| "learning_rate": 0.0002775201878012872, |
| "loss": 2.6378125, |
| "step": 71200 |
| }, |
| { |
| "epoch": 0.3209090909090909, |
| "grad_norm": 0.16494904458522797, |
| "learning_rate": 0.0002762405098072303, |
| "loss": 2.6372637939453125, |
| "step": 71300 |
| }, |
| { |
| "epoch": 0.32181818181818184, |
| "grad_norm": 0.18344129621982574, |
| "learning_rate": 0.0002749626619383296, |
| "loss": 2.6274960327148436, |
| "step": 71400 |
| }, |
| { |
| "epoch": 0.32272727272727275, |
| "grad_norm": 0.19829513132572174, |
| "learning_rate": 0.00027368665464608174, |
| "loss": 2.652212829589844, |
| "step": 71500 |
| }, |
| { |
| "epoch": 0.3236363636363636, |
| "grad_norm": 0.170766219496727, |
| "learning_rate": 0.0002724124983669292, |
| "loss": 2.6236361694335937, |
| "step": 71600 |
| }, |
| { |
| "epoch": 0.3245454545454545, |
| "grad_norm": 0.15507978200912476, |
| "learning_rate": 0.0002711402035221751, |
| "loss": 2.612099304199219, |
| "step": 71700 |
| }, |
| { |
| "epoch": 0.32545454545454544, |
| "grad_norm": 0.17562313377857208, |
| "learning_rate": 0.00026986978051789804, |
| "loss": 2.651109313964844, |
| "step": 71800 |
| }, |
| { |
| "epoch": 0.32636363636363636, |
| "grad_norm": 0.16349823772907257, |
| "learning_rate": 0.0002686012397448662, |
| "loss": 2.652076416015625, |
| "step": 71900 |
| }, |
| { |
| "epoch": 0.32727272727272727, |
| "grad_norm": 0.1562015861272812, |
| "learning_rate": 0.00026733459157845385, |
| "loss": 2.6174331665039063, |
| "step": 72000 |
| }, |
| { |
| "epoch": 0.32727272727272727, |
| "eval_loss": 3.030982255935669, |
| "eval_runtime": 7.4103, |
| "eval_samples_per_second": 77.729, |
| "eval_steps_per_second": 19.432, |
| "step": 72000 |
| }, |
| { |
| "epoch": 0.3281818181818182, |
| "grad_norm": 0.15797623991966248, |
| "learning_rate": 0.0002660698463785552, |
| "loss": 2.619053955078125, |
| "step": 72100 |
| }, |
| { |
| "epoch": 0.3290909090909091, |
| "grad_norm": 0.1555212438106537, |
| "learning_rate": 0.0002648070144895005, |
| "loss": 2.632798156738281, |
| "step": 72200 |
| }, |
| { |
| "epoch": 0.33, |
| "grad_norm": 0.19114950299263, |
| "learning_rate": 0.00026354610623997046, |
| "loss": 2.6581826782226563, |
| "step": 72300 |
| }, |
| { |
| "epoch": 0.33090909090909093, |
| "grad_norm": 0.17001217603683472, |
| "learning_rate": 0.00026228713194291253, |
| "loss": 2.65262939453125, |
| "step": 72400 |
| }, |
| { |
| "epoch": 0.33181818181818185, |
| "grad_norm": 0.1753956377506256, |
| "learning_rate": 0.0002610301018954573, |
| "loss": 2.6327615356445313, |
| "step": 72500 |
| }, |
| { |
| "epoch": 0.3327272727272727, |
| "grad_norm": 0.19001173973083496, |
| "learning_rate": 0.00025977502637883234, |
| "loss": 2.6356915283203124, |
| "step": 72600 |
| }, |
| { |
| "epoch": 0.3336363636363636, |
| "grad_norm": 0.17613352835178375, |
| "learning_rate": 0.00025852191565827934, |
| "loss": 2.6278375244140624, |
| "step": 72700 |
| }, |
| { |
| "epoch": 0.33454545454545453, |
| "grad_norm": 0.16500087082386017, |
| "learning_rate": 0.0002572707799829701, |
| "loss": 2.6458389282226564, |
| "step": 72800 |
| }, |
| { |
| "epoch": 0.33545454545454545, |
| "grad_norm": 0.16459618508815765, |
| "learning_rate": 0.00025602162958592256, |
| "loss": 2.6154913330078124, |
| "step": 72900 |
| }, |
| { |
| "epoch": 0.33636363636363636, |
| "grad_norm": 0.16172908246517181, |
| "learning_rate": 0.0002547744746839172, |
| "loss": 2.617068176269531, |
| "step": 73000 |
| }, |
| { |
| "epoch": 0.33636363636363636, |
| "eval_loss": 3.033856153488159, |
| "eval_runtime": 7.4432, |
| "eval_samples_per_second": 77.386, |
| "eval_steps_per_second": 19.346, |
| "step": 73000 |
| }, |
| { |
| "epoch": 0.3372727272727273, |
| "grad_norm": 0.1543026864528656, |
| "learning_rate": 0.0002535293254774134, |
| "loss": 2.626250915527344, |
| "step": 73100 |
| }, |
| { |
| "epoch": 0.3381818181818182, |
| "grad_norm": 0.1827453225851059, |
| "learning_rate": 0.00025228619215046546, |
| "loss": 2.6261016845703127, |
| "step": 73200 |
| }, |
| { |
| "epoch": 0.3390909090909091, |
| "grad_norm": 0.1937389373779297, |
| "learning_rate": 0.0002510450848706404, |
| "loss": 2.6204208374023437, |
| "step": 73300 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 0.17227666079998016, |
| "learning_rate": 0.000249806013788934, |
| "loss": 2.6471063232421876, |
| "step": 73400 |
| }, |
| { |
| "epoch": 0.3409090909090909, |
| "grad_norm": 0.17451529204845428, |
| "learning_rate": 0.00024856898903968843, |
| "loss": 2.6337734985351564, |
| "step": 73500 |
| }, |
| { |
| "epoch": 0.3418181818181818, |
| "grad_norm": 0.24337761104106903, |
| "learning_rate": 0.00024733402074050815, |
| "loss": 2.6101370239257813, |
| "step": 73600 |
| }, |
| { |
| "epoch": 0.3427272727272727, |
| "grad_norm": 0.14900852739810944, |
| "learning_rate": 0.00024610111899217845, |
| "loss": 2.64669677734375, |
| "step": 73700 |
| }, |
| { |
| "epoch": 0.34363636363636363, |
| "grad_norm": 0.15780414640903473, |
| "learning_rate": 0.0002448702938785824, |
| "loss": 2.61236328125, |
| "step": 73800 |
| }, |
| { |
| "epoch": 0.34454545454545454, |
| "grad_norm": 0.194599449634552, |
| "learning_rate": 0.0002436415554666181, |
| "loss": 2.603551940917969, |
| "step": 73900 |
| }, |
| { |
| "epoch": 0.34545454545454546, |
| "grad_norm": 0.14722345769405365, |
| "learning_rate": 0.0002424149138061168, |
| "loss": 2.613863220214844, |
| "step": 74000 |
| }, |
| { |
| "epoch": 0.34545454545454546, |
| "eval_loss": 3.027711868286133, |
| "eval_runtime": 7.4441, |
| "eval_samples_per_second": 77.376, |
| "eval_steps_per_second": 19.344, |
| "step": 74000 |
| }, |
| { |
| "epoch": 0.3463636363636364, |
| "grad_norm": 0.1645086705684662, |
| "learning_rate": 0.00024119037892975998, |
| "loss": 2.59792724609375, |
| "step": 74100 |
| }, |
| { |
| "epoch": 0.3472727272727273, |
| "grad_norm": 0.1647663712501526, |
| "learning_rate": 0.00023996796085299821, |
| "loss": 2.611474609375, |
| "step": 74200 |
| }, |
| { |
| "epoch": 0.3481818181818182, |
| "grad_norm": 0.17553652822971344, |
| "learning_rate": 0.0002387476695739687, |
| "loss": 2.6507049560546876, |
| "step": 74300 |
| }, |
| { |
| "epoch": 0.3490909090909091, |
| "grad_norm": 0.15945149958133698, |
| "learning_rate": 0.00023752951507341352, |
| "loss": 2.643914794921875, |
| "step": 74400 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.16624271869659424, |
| "learning_rate": 0.00023631350731459827, |
| "loss": 2.641552734375, |
| "step": 74500 |
| }, |
| { |
| "epoch": 0.3509090909090909, |
| "grad_norm": 0.15819379687309265, |
| "learning_rate": 0.00023509965624322993, |
| "loss": 2.5745086669921875, |
| "step": 74600 |
| }, |
| { |
| "epoch": 0.3518181818181818, |
| "grad_norm": 0.17103050649166107, |
| "learning_rate": 0.00023388797178737635, |
| "loss": 2.5839889526367186, |
| "step": 74700 |
| }, |
| { |
| "epoch": 0.3527272727272727, |
| "grad_norm": 0.17305444180965424, |
| "learning_rate": 0.00023267846385738474, |
| "loss": 2.610628662109375, |
| "step": 74800 |
| }, |
| { |
| "epoch": 0.35363636363636364, |
| "grad_norm": 0.19914712011814117, |
| "learning_rate": 0.00023147114234580023, |
| "loss": 2.6196224975585936, |
| "step": 74900 |
| }, |
| { |
| "epoch": 0.35454545454545455, |
| "grad_norm": 0.15575388073921204, |
| "learning_rate": 0.00023026601712728567, |
| "loss": 2.590400390625, |
| "step": 75000 |
| }, |
| { |
| "epoch": 0.35454545454545455, |
| "eval_loss": 3.025919198989868, |
| "eval_runtime": 7.4339, |
| "eval_samples_per_second": 77.483, |
| "eval_steps_per_second": 19.371, |
| "step": 75000 |
| }, |
| { |
| "epoch": 0.35545454545454547, |
| "grad_norm": 0.16681872308254242, |
| "learning_rate": 0.00022906309805853986, |
| "loss": 2.60665771484375, |
| "step": 75100 |
| }, |
| { |
| "epoch": 0.3563636363636364, |
| "grad_norm": 0.18523137271404266, |
| "learning_rate": 0.00022786239497821808, |
| "loss": 2.613553771972656, |
| "step": 75200 |
| }, |
| { |
| "epoch": 0.3572727272727273, |
| "grad_norm": 0.18534353375434875, |
| "learning_rate": 0.0002266639177068509, |
| "loss": 2.6336288452148438, |
| "step": 75300 |
| }, |
| { |
| "epoch": 0.35818181818181816, |
| "grad_norm": 0.17340436577796936, |
| "learning_rate": 0.00022546767604676398, |
| "loss": 2.596582336425781, |
| "step": 75400 |
| }, |
| { |
| "epoch": 0.35909090909090907, |
| "grad_norm": 0.15971297025680542, |
| "learning_rate": 0.00022427367978199804, |
| "loss": 2.629716491699219, |
| "step": 75500 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 0.17461271584033966, |
| "learning_rate": 0.00022308193867822873, |
| "loss": 2.613475341796875, |
| "step": 75600 |
| }, |
| { |
| "epoch": 0.3609090909090909, |
| "grad_norm": 0.169435515999794, |
| "learning_rate": 0.00022189246248268673, |
| "loss": 2.597880859375, |
| "step": 75700 |
| }, |
| { |
| "epoch": 0.3618181818181818, |
| "grad_norm": 0.17688947916030884, |
| "learning_rate": 0.00022070526092407835, |
| "loss": 2.589518737792969, |
| "step": 75800 |
| }, |
| { |
| "epoch": 0.36272727272727273, |
| "grad_norm": 0.1569153070449829, |
| "learning_rate": 0.0002195203437125049, |
| "loss": 2.6041824340820314, |
| "step": 75900 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.1733204573392868, |
| "learning_rate": 0.00021833772053938495, |
| "loss": 2.594022521972656, |
| "step": 76000 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "eval_loss": 3.0241539478302, |
| "eval_runtime": 7.4745, |
| "eval_samples_per_second": 77.062, |
| "eval_steps_per_second": 19.266, |
| "step": 76000 |
| }, |
| { |
| "epoch": 0.0012987012987012987, |
| "grad_norm": 0.16393087804317474, |
| "learning_rate": 3.391192895308981e-07, |
| "loss": 2.6057958984375, |
| "step": 76100 |
| }, |
| { |
| "epoch": 0.0025974025974025974, |
| "grad_norm": 0.1581353396177292, |
| "learning_rate": 2.6802681023424534e-07, |
| "loss": 2.6045050048828124, |
| "step": 76200 |
| }, |
| { |
| "epoch": 0.003896103896103896, |
| "grad_norm": 0.16540294885635376, |
| "learning_rate": 2.0528552419035728e-07, |
| "loss": 2.6286279296875, |
| "step": 76300 |
| }, |
| { |
| "epoch": 0.005194805194805195, |
| "grad_norm": 0.1575717329978943, |
| "learning_rate": 1.508964798905832e-07, |
| "loss": 2.624171142578125, |
| "step": 76400 |
| }, |
| { |
| "epoch": 0.006493506493506494, |
| "grad_norm": 0.15712368488311768, |
| "learning_rate": 1.0486058624897821e-07, |
| "loss": 2.590557861328125, |
| "step": 76500 |
| }, |
| { |
| "epoch": 0.007792207792207792, |
| "grad_norm": 0.14502283930778503, |
| "learning_rate": 6.717861258720426e-08, |
| "loss": 2.5785467529296877, |
| "step": 76600 |
| }, |
| { |
| "epoch": 0.00909090909090909, |
| "grad_norm": 0.16336509585380554, |
| "learning_rate": 3.7851188621707e-08, |
| "loss": 2.6053866577148437, |
| "step": 76700 |
| }, |
| { |
| "epoch": 0.01038961038961039, |
| "grad_norm": 0.1576337367296219, |
| "learning_rate": 1.6878804453168694e-08, |
| "loss": 2.595892028808594, |
| "step": 76800 |
| }, |
| { |
| "epoch": 0.011688311688311689, |
| "grad_norm": 0.15049995481967926, |
| "learning_rate": 4.261810558348067e-09, |
| "loss": 2.629699401855469, |
| "step": 76900 |
| }, |
| { |
| "epoch": 0.012987012987012988, |
| "grad_norm": 0.1851549744606018, |
| "learning_rate": 4.177841961272577e-13, |
| "loss": 2.5818411254882814, |
| "step": 77000 |
| }, |
| { |
| "epoch": 0.012987012987012988, |
| "eval_loss": 3.022578001022339, |
| "eval_runtime": 7.458, |
| "eval_samples_per_second": 77.233, |
| "eval_steps_per_second": 19.308, |
| "step": 77000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 77000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 4000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.918422736699392e+18, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
