Step 1 | loss:0.01213599182665348 lr:1.4285714285714285e-05 tokens_per_second_per_gpu:3404.260116401829 Step 2 | loss:0.05323003977537155 lr:2.857142857142857e-05 tokens_per_second_per_gpu:2847.5748762569233 Step 3 | loss:0.006721426732838154 lr:4.2857142857142856e-05 tokens_per_second_per_gpu:3404.5310283094473 Step 4 | loss:0.03512277454137802 lr:5.714285714285714e-05 tokens_per_second_per_gpu:2151.1299929149804 Step 5 | loss:0.015561948530375957 lr:7.142857142857143e-05 tokens_per_second_per_gpu:7213.580199077777 Step 6 | loss:0.008180935867130756 lr:8.571428571428571e-05 tokens_per_second_per_gpu:7133.875309282848 Step 7 | loss:0.01505997683852911 lr:0.0001 tokens_per_second_per_gpu:2838.1605080364957 Step 8 | loss:0.017542490735650063 lr:9.994161134161634e-05 tokens_per_second_per_gpu:7064.647511922427 Step 9 | loss:0.01684839464724064 lr:9.976658173588244e-05 tokens_per_second_per_gpu:7195.1292634894635 Step 10 | loss:0.011541903018951416 lr:9.947531997255256e-05 tokens_per_second_per_gpu:1273.3526396091336 Step 11 | loss:0.0019745274912565947 lr:9.906850630697068e-05 tokens_per_second_per_gpu:7202.0862713139295 Step 12 | loss:0.04754862189292908 lr:9.85470908713026e-05 tokens_per_second_per_gpu:7090.606538899934 Step 13 | loss:0.00039215420838445425 lr:9.791229145545831e-05 tokens_per_second_per_gpu:7006.873846550338 Step 14 | loss:0.0008788838749751449 lr:9.716559066288715e-05 tokens_per_second_per_gpu:7192.817561967175 Step 15 | loss:0.0007529142312705517 lr:9.630873244788883e-05 tokens_per_second_per_gpu:7111.737477943987 Step 16 | loss:0.0001974945334950462 lr:9.534371804252728e-05 tokens_per_second_per_gpu:7091.69321172515 Step 17 | loss:0.0016645367722958326 lr:9.42728012826605e-05 tokens_per_second_per_gpu:7176.800912786511 Step 18 | loss:0.027435433119535446 lr:9.309848334400246e-05 tokens_per_second_per_gpu:7170.110091079389 Step 19 | loss:0.026739366352558136 lr:9.182350690051133e-05 tokens_per_second_per_gpu:7130.819955305939 Step 20 | loss:0.0015863939188420773 lr:9.045084971874738e-05 tokens_per_second_per_gpu:7076.8900804429095 Step 21 | loss:0.0016179593512788415 lr:8.898371770316111e-05 tokens_per_second_per_gpu:7177.145273038502 Step 22 | loss:0.02591816335916519 lr:8.742553740855506e-05 tokens_per_second_per_gpu:7038.516202651878 Step 23 | loss:0.000453911314252764 lr:8.577994803720606e-05 tokens_per_second_per_gpu:7076.675124899392 Step 24 | loss:0.01640825718641281 lr:8.405079293933986e-05 tokens_per_second_per_gpu:7111.868628736731 Step 25 | loss:0.0001911711151478812 lr:8.224211063680853e-05 tokens_per_second_per_gpu:6996.426639921837 Step 26 | loss:0.00019689431064762175 lr:8.035812539093557e-05 tokens_per_second_per_gpu:7129.771943389241 Step 27 | loss:0.0003955479769501835 lr:7.840323733655778e-05 tokens_per_second_per_gpu:6705.522398275781 Step 28 | loss:0.0016950565623119473 lr:7.638201220530665e-05 tokens_per_second_per_gpu:7164.835243901002 Step 29 | loss:0.0004549043078441173 lr:7.42991706621303e-05 tokens_per_second_per_gpu:7134.113817493094 Step 30 | loss:7.907362305559218e-05 lr:7.215957727996207e-05 tokens_per_second_per_gpu:7085.3284701406865 Step 31 | loss:0.022005649283528328 lr:6.996822917828477e-05 tokens_per_second_per_gpu:7106.993416514684 Step 32 | loss:0.00033388612791895866 lr:6.773024435212678e-05 tokens_per_second_per_gpu:7087.199547240821 Step 33 | loss:0.006230715196579695 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6889.225855285138 Step 34 | loss:0.019058911129832268 lr:6.313536890992935e-05 tokens_per_second_per_gpu:7226.036345262191 Step 35 | loss:0.0001418855244992301 lr:6.078920983839031e-05 tokens_per_second_per_gpu:7154.760936431576 Step 36 | loss:0.0005796361365355551 lr:5.841785206735192e-05 tokens_per_second_per_gpu:6891.661354772104 Step 37 | loss:4.626877125701867e-05 lr:5.602683401276615e-05 tokens_per_second_per_gpu:7002.617612685 Step 38 | loss:0.005331241525709629 lr:5.3621740008088126e-05 tokens_per_second_per_gpu:7010.927497097903 Step 39 | loss:0.00010369029769208282 lr:5.1208187261806615e-05 tokens_per_second_per_gpu:7168.5148320560575 Step 40 | loss:0.00034265266731381416 lr:4.87918127381934e-05 tokens_per_second_per_gpu:7162.935906194933 Step 41 | loss:0.00016875483561307192 lr:4.6378259991911886e-05 tokens_per_second_per_gpu:7134.073121948486 Step 42 | loss:6.131715053925291e-06 lr:4.397316598723385e-05 tokens_per_second_per_gpu:6997.651607723751 Step 43 | loss:0.00643449742347002 lr:4.1582147932648074e-05 tokens_per_second_per_gpu:7054.267604831181 Step 44 | loss:0.011971571482717991 lr:3.92107901616097e-05 tokens_per_second_per_gpu:6913.706728873295 Step 45 | loss:0.00011875088239321485 lr:3.6864631090070655e-05 tokens_per_second_per_gpu:7150.46483685172 Step 46 | loss:0.00037201965460553765 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:7209.474418950389 Step 47 | loss:6.80260345689021e-05 lr:3.226975564787322e-05 tokens_per_second_per_gpu:7069.455266192888 Step 48 | loss:0.00014731497503817081 lr:3.003177082171523e-05 tokens_per_second_per_gpu:7163.2810745656725 Step 49 | loss:0.00013455803855322301 lr:2.784042272003794e-05 tokens_per_second_per_gpu:7122.241765808404 Step 50 | loss:0.00018143688794225454 lr:2.57008293378697e-05 tokens_per_second_per_gpu:7232.54367922411 Step 51 | loss:0.00027479001437313855 lr:2.361798779469336e-05 tokens_per_second_per_gpu:6946.3745857220665 Step 52 | loss:9.438945198780857e-06 lr:2.1596762663442218e-05 tokens_per_second_per_gpu:7064.475268996893 Step 53 | loss:0.00028414305415935814 lr:1.9641874609064443e-05 tokens_per_second_per_gpu:7004.631675388433 Step 54 | loss:0.0002906432200688869 lr:1.7757889363191483e-05 tokens_per_second_per_gpu:7099.724473612669 Step 55 | loss:0.0006885308539494872 lr:1.5949207060660138e-05 tokens_per_second_per_gpu:7223.775075746081 Step 56 | loss:8.605341281509027e-05 lr:1.422005196279395e-05 tokens_per_second_per_gpu:6082.0778740205715 Step 57 | loss:0.0063959574326872826 lr:1.257446259144494e-05 tokens_per_second_per_gpu:7081.2743175992555 Step 58 | loss:0.005889782682061195 lr:1.1016282296838887e-05 tokens_per_second_per_gpu:7068.960681166967 Step 59 | loss:0.0003120407636743039 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7055.8604218274395 Step 60 | loss:0.000564471585676074 lr:8.176493099488663e-06 tokens_per_second_per_gpu:7272.444511517603 Step 61 | loss:8.206569327739999e-05 lr:6.901516655997536e-06 tokens_per_second_per_gpu:7210.362983854608 Step 62 | loss:0.0002453089982736856 lr:5.727198717339511e-06 tokens_per_second_per_gpu:6921.957697264826 Step 63 | loss:0.00021397467935457826 lr:4.65628195747273e-06 tokens_per_second_per_gpu:7103.90490201871 Step 64 | loss:2.379073293923284e-06 lr:3.691267552111183e-06 tokens_per_second_per_gpu:6993.683263965953 Step 65 | loss:0.0032244210597127676 lr:2.8344093371128424e-06 tokens_per_second_per_gpu:7137.559084787147 Step 66 | loss:0.0002484503202140331 lr:2.087708544541689e-06 tokens_per_second_per_gpu:7176.5653753533525 Step 67 | loss:5.681362836185144e-06 lr:1.4529091286973995e-06 tokens_per_second_per_gpu:7011.669433490256 Step 68 | loss:0.000574558274820447 lr:9.314936930293283e-07 tokens_per_second_per_gpu:7068.591725466086 Step 69 | loss:0.0002666613145265728 lr:5.246800274474439e-07 tokens_per_second_per_gpu:7109.388717623035 Step 70 | loss:7.340025331359357e-05 lr:2.334182641175686e-07 tokens_per_second_per_gpu:7215.015175796162 Step 71 | loss:0.005155441351234913 lr:5.838865838366792e-08 tokens_per_second_per_gpu:7187.734395899015 Step 72 | loss:0.004279113840311766 lr:0.0 tokens_per_second_per_gpu:7082.0875692297195