| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.21818181818181817, |
| "eval_steps": 1000, |
| "global_step": 24000, |
| "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 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 110000, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.97949943906304e+17, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
