diff --git "a/train.log" "b/train.log" new file mode 100644--- /dev/null +++ "b/train.log" @@ -0,0 +1,5146 @@ +type train | step 1 | loss 7052.1274 11972.1328 21960.0371 32676.7305 38345.8594 43423.1641 48731.6875 58731.4570 71870.0938 97071.4141 168062.1406 675061.3750 | lr 6.7e-07 | norm 525494.5000 | dt 47.753 +type train | step 2 | loss 7011.0342 11889.8115 22103.3789 32499.4395 38379.4297 43270.7812 48479.3359 58491.0000 71782.1953 97117.2812 167240.3594 654517.2500 | lr 1.3e-06 | norm 504417.7812 | dt 9.141 +type train | step 3 | loss 6981.8921 11847.8652 21932.7441 32593.7246 38462.7930 43174.9375 48583.2773 58293.6523 71582.2812 97160.5234 167538.1875 670959.0625 | lr 2.0e-06 | norm 523884.3750 | dt 9.162 +type train | step 4 | loss 6998.1875 11890.3096 21852.2539 32498.7031 38568.1406 43172.8828 48365.2148 58248.5703 71795.5547 97757.0781 168569.0469 678931.6875 | lr 2.7e-06 | norm 539840.3125 | dt 9.167 +type train | step 5 | loss 6895.6567 11737.7812 21832.5508 32281.1484 38118.6055 43083.6172 48652.5703 58389.6250 71953.2031 97435.4141 166170.5781 704435.0000 | lr 3.3e-06 | norm 559649.0000 | dt 9.154 +type train | step 6 | loss 6967.6270 11848.1357 21962.3535 32590.1465 38235.7578 43476.3359 48707.6797 59032.2812 72184.9766 97603.9062 167383.7812 687392.9375 | lr 4.0e-06 | norm 527603.0625 | dt 9.151 +type train | step 7 | loss 6922.7217 11714.0801 21770.3184 31993.9199 38066.4727 42823.4609 48255.4922 57785.0859 71319.7656 96423.8906 165195.8906 672880.0625 | lr 4.7e-06 | norm 524346.0625 | dt 9.199 +type train | step 8 | loss 6944.4854 11780.6348 21951.7871 32500.0488 38171.5469 43184.3711 48504.1680 58220.6250 71497.4375 96332.7422 166756.4062 669066.8125 | lr 5.3e-06 | norm 516393.6562 | dt 9.188 +type train | step 9 | loss 6890.3306 11692.3232 21833.7383 32228.2539 37988.0234 42874.6172 48262.4609 58022.4297 71367.8359 96777.1250 167199.6250 674751.0625 | lr 6.0e-06 | norm 525206.0625 | dt 9.193 +type train | step 10 | loss 6886.3237 11671.4248 21746.4492 32254.3027 38068.4961 42687.0742 48067.0703 57686.7109 70794.9453 95914.5625 165821.7344 671346.9375 | lr 6.7e-06 | norm 523084.2500 | dt 9.225 +type train | step 11 | loss 6896.4893 11715.1172 21656.0605 32085.7559 37913.6055 42577.6797 47846.7734 57773.2383 70571.7266 95292.5781 164547.3750 672588.6250 | lr 7.3e-06 | norm 517300.9375 | dt 9.200 +type train | step 12 | loss 6929.7461 11736.9238 21602.2754 31954.8203 37696.6562 42621.3906 48135.3867 57619.9570 70453.6094 95146.3438 164112.2500 675154.6250 | lr 8.0e-06 | norm 520880.3750 | dt 9.207 +type train | step 13 | loss 6854.8276 11618.7412 21489.7812 31865.0977 37743.9883 42611.2148 48095.6094 57547.1758 70417.2031 95831.8438 165079.8125 655649.0625 | lr 8.7e-06 | norm 499831.5625 | dt 9.202 +type train | step 14 | loss 6866.7720 11632.8750 21541.8359 31924.5273 37871.5781 42584.8594 47941.3438 57540.3008 70590.6094 95610.1172 164683.9375 660845.9375 | lr 9.3e-06 | norm 508597.5625 | dt 9.199 +type train | step 15 | loss 6833.7852 11573.1592 21557.0781 31846.6504 37844.6641 42547.2969 47736.8125 57663.8086 70406.7734 95358.5000 164505.7031 663498.0625 | lr 1.0e-05 | norm 512526.5938 | dt 9.199 +type train | step 16 | loss 6812.0454 11526.2178 21402.7578 31428.7109 37201.5703 42082.8398 47279.1953 57062.0156 70097.5859 94715.5859 162728.9531 658015.3750 | lr 1.1e-05 | norm 499809.3750 | dt 9.219 +type train | step 17 | loss 6754.4082 11410.9189 21139.8477 31286.3047 37561.9492 41949.5781 47543.2461 57010.8203 70061.8594 95554.2812 164832.5156 647216.4375 | lr 1.1e-05 | norm 495690.0000 | dt 9.215 +type train | step 18 | loss 6887.1558 11685.9150 21357.6875 31699.7031 37743.5859 42675.5547 48144.3398 58010.6797 70802.2734 95093.8750 163261.7812 668846.7500 | lr 1.2e-05 | norm 516303.3750 | dt 9.203 +type train | step 19 | loss 6821.6157 11559.8311 21282.1152 31302.1582 37202.8711 41886.5977 47628.9570 57342.0234 69913.2344 94329.7266 163125.8594 670018.8750 | lr 1.3e-05 | norm 510183.2812 | dt 9.199 +type train | step 20 | loss 6780.0337 11484.3359 21055.0430 31386.9609 37386.2500 41842.3828 47493.4922 57089.7461 69880.0547 95295.9688 163398.9531 655974.0000 | lr 1.3e-05 | norm 508884.0312 | dt 9.216 +type train | step 21 | loss 6806.2056 11495.8994 21093.9102 31294.7051 37028.2188 41749.0117 46941.6836 56975.5391 69402.7500 93550.7500 161375.0625 649383.5000 | lr 1.4e-05 | norm 494806.7500 | dt 9.215 +type train | step 22 | loss 6795.1133 11475.4268 20996.4453 30971.6270 36940.9102 41826.6680 47189.6133 57149.2266 69660.0078 94841.2266 163459.5000 679415.1250 | lr 1.5e-05 | norm 515126.3125 | dt 9.202 +type train | step 23 | loss 6829.2896 11583.9717 21156.4980 31242.4590 37035.9336 41643.7930 46976.5117 56564.1406 68681.6250 92508.8359 158939.0781 642136.7500 | lr 1.5e-05 | norm 486093.6250 | dt 9.216 +type train | step 24 | loss 6892.2578 11680.2646 21201.9883 31505.3750 37195.5117 41979.5781 47872.4102 57336.7617 69652.0547 93295.1406 159445.2656 640723.7500 | lr 1.6e-05 | norm 477181.5000 | dt 9.222 +type train | step 25 | loss 6736.6592 11349.2822 20684.7109 30888.8750 36733.6719 41423.9531 46601.8008 56383.2227 68728.5625 93093.8672 161084.1562 661293.3750 | lr 1.7e-05 | norm 523773.0000 | dt 9.186 +type train | step 26 | loss 6663.9873 11215.5107 20535.5312 30690.2930 36583.6367 40986.5820 46798.9180 55977.1953 68394.7344 92864.9531 160059.5469 658434.1875 | lr 1.7e-05 | norm 514728.5312 | dt 9.220 +type train | step 27 | loss 6682.8789 11255.3369 20573.3516 30615.7520 36265.0312 41013.9961 46381.2852 55997.6250 68408.6953 92846.6797 159356.7500 624672.7500 | lr 1.8e-05 | norm 479725.3438 | dt 9.214 +type train | step 28 | loss 6688.3208 11326.7930 20763.6367 30955.2910 37002.7812 41221.6758 47070.8008 56060.2188 68436.6094 92830.9141 158906.1562 625876.6875 | lr 1.9e-05 | norm 474397.2812 | dt 9.210 +type train | step 29 | loss 6634.7080 11187.1455 20555.6406 30698.4219 36280.7578 40999.2109 46608.4375 55382.5078 67587.6953 92075.7891 158117.9219 647945.7500 | lr 1.9e-05 | norm 505749.1875 | dt 9.215 +type train | step 30 | loss 6662.9688 11248.5635 20605.7227 30691.3223 36769.8438 41238.2773 46525.9844 55865.1094 68299.9219 92876.2656 158675.0000 642622.0625 | lr 2.0e-05 | norm 496516.5625 | dt 9.211 +type train | step 31 | loss 6699.7314 11334.5068 20599.7461 30641.4707 36520.8789 41180.8867 46719.8125 55874.7656 67922.5391 91682.2578 156797.2031 618792.5000 | lr 2.1e-05 | norm 469245.2188 | dt 9.226 +type train | step 32 | loss 6665.3076 11274.9844 20538.6191 30487.5000 36228.5078 40828.5352 46528.8320 55533.2656 68006.4297 91824.9688 157890.2812 634520.7500 | lr 2.1e-05 | norm 483629.0625 | dt 9.223 +type train | step 33 | loss 6641.4307 11231.5254 20497.2812 30395.7793 36426.1641 40790.6484 45992.6914 55081.4844 67755.2734 92132.4766 157478.6406 622748.6875 | lr 2.2e-05 | norm 471366.8750 | dt 9.208 +type train | step 34 | loss 6558.4658 11092.7490 20291.5547 30296.9766 36166.8594 40530.0234 46245.2812 55136.1875 67735.6484 92192.4844 159020.4219 643005.0000 | lr 2.3e-05 | norm 492254.5312 | dt 9.209 +type train | step 35 | loss 6603.2515 11163.2295 20337.1934 30045.9316 35708.6641 40238.8711 45997.5078 54979.3398 67180.0938 91279.7891 156226.2188 637209.0625 | lr 2.3e-05 | norm 483379.7188 | dt 9.212 +type train | step 36 | loss 6545.5176 11088.2012 20252.4668 30106.9883 35402.7930 40467.2266 45623.9688 54700.4414 66907.5156 90294.1406 155998.5625 633457.9375 | lr 2.4e-05 | norm 488922.0625 | dt 9.215 +type train | step 37 | loss 6451.0352 10910.2197 19975.4570 29898.3750 35459.3125 40157.6953 45321.6016 54468.3945 67118.1250 91093.9688 157238.9062 632357.6250 | lr 2.5e-05 | norm 475804.4062 | dt 9.216 +type train | step 38 | loss 6595.0000 11156.8594 20291.5156 30082.2793 35622.1875 40190.9844 45633.6914 54792.4180 67034.6250 90373.0312 156049.2344 630391.8125 | lr 2.5e-05 | norm 498599.0938 | dt 9.205 +type train | step 39 | loss 6549.3154 11046.1963 20090.1406 29874.3164 34969.6875 39868.1719 45101.1289 54449.8281 66550.1328 90420.1562 155566.1562 633639.3125 | lr 2.6e-05 | norm 494089.2812 | dt 9.214 +type train | step 40 | loss 6516.6445 11035.3311 20000.4160 29816.7637 34899.2500 39834.7383 44947.2773 54168.9023 65818.5312 89613.1641 155066.8125 613877.4375 | lr 2.7e-05 | norm 468270.0312 | dt 9.228 +type train | step 41 | loss 6529.8530 11028.2471 20015.0645 29770.2598 34878.9023 39792.4648 45122.9219 54314.1797 66333.3359 89609.4141 154140.0312 600892.3125 | lr 2.7e-05 | norm 441543.9062 | dt 9.224 +type train | step 42 | loss 6486.9160 10979.3525 19963.5488 29841.6055 34903.2773 39959.4180 44952.2188 54130.3320 66211.7969 89815.9609 154112.9219 597365.4375 | lr 2.8e-05 | norm 441021.5938 | dt 9.219 +type train | step 43 | loss 6458.2700 10946.0703 19818.2363 29550.1758 34711.0039 39516.5234 44398.8633 53319.7305 65687.1562 88810.0391 152704.8438 623334.2500 | lr 2.9e-05 | norm 477300.5312 | dt 9.210 +type train | step 44 | loss 6445.1812 10904.2754 19832.1797 29705.4512 34646.5781 39719.9844 44484.2852 53708.3750 65975.8828 89480.8594 154047.7969 604219.6875 | lr 2.9e-05 | norm 452038.5625 | dt 9.228 +type train | step 45 | loss 6403.3086 10833.8486 19688.5176 29485.4707 34402.4570 39242.2812 44284.8398 53467.9141 65510.1367 88820.0078 153522.0469 608465.8125 | lr 3.0e-05 | norm 463380.5312 | dt 9.205 +type train | step 46 | loss 6359.8096 10734.1348 19706.8457 29439.9297 34515.2539 39282.1211 44236.6406 53484.8633 65844.7188 89377.6406 153884.1875 595674.7500 | lr 3.1e-05 | norm 439356.2188 | dt 9.230 +type train | step 47 | loss 6399.2056 10810.4756 19715.5469 29284.4258 34284.7969 39205.8086 44286.0352 53413.7109 65583.0000 88959.6719 152474.6719 589792.7500 | lr 3.1e-05 | norm 438512.5625 | dt 9.237 +type train | step 48 | loss 6410.8721 10818.9502 19617.7754 29285.9512 34221.5977 38857.2969 44240.4922 53317.1641 65561.0547 88261.2734 151370.4375 597405.8750 | lr 3.2e-05 | norm 451223.9062 | dt 9.236 +type train | step 49 | loss 6389.1123 10829.7979 19559.8828 29100.4980 34119.8281 39057.9102 44275.5078 53358.7266 65024.6484 87626.3438 150108.1875 591163.5625 | lr 3.3e-05 | norm 432460.4688 | dt 9.243 +type train | step 50 | loss 6309.5410 10676.7422 19375.5527 28936.0996 34028.4648 38620.6602 43865.5469 52935.4961 64726.4688 88191.3750 151381.2812 590235.8750 | lr 3.3e-05 | norm 437416.2188 | dt 9.242 +type train | step 51 | loss 6265.2144 10598.5195 19140.2676 28550.0801 33603.8477 37954.1719 43342.6133 51792.8281 63134.2656 84957.9531 147235.2812 626207.5625 | lr 3.4e-05 | norm 487567.8750 | dt 9.222 +type train | step 52 | loss 6064.9521 10261.1973 18919.5781 28317.6875 33214.9453 37652.0781 43023.5234 51796.7617 63868.1836 87324.0000 151271.8594 690767.5625 | lr 3.5e-05 | norm 605568.3125 | dt 9.239 +type train | step 53 | loss 6186.4414 10478.7002 19118.4160 28466.3828 33639.9102 38069.5469 43438.7773 52138.3398 64078.1172 87367.7656 149528.0938 572339.6250 | lr 3.5e-05 | norm 425736.2188 | dt 9.273 +type train | step 54 | loss 6178.1265 10458.5127 19089.4355 28280.1172 33375.5938 37614.9180 43049.1250 51870.4141 63420.3477 86721.1250 148239.9531 571325.8750 | lr 3.6e-05 | norm 423898.5625 | dt 9.298 +type train | step 55 | loss 6239.6426 10528.7578 19068.5996 28300.7148 33437.9180 37698.9297 43027.2656 51580.1836 63326.4609 85952.6641 147276.9375 574098.5000 | lr 3.7e-05 | norm 452544.4375 | dt 9.268 +type train | step 56 | loss 6151.6396 10389.7139 18841.1543 28086.8164 32976.5469 37480.2500 42560.7617 51082.4766 62351.5703 84961.0625 145397.3125 590660.0000 | lr 3.7e-05 | norm 457854.5000 | dt 9.253 +type train | step 57 | loss 6093.0234 10305.7666 18845.0840 28063.2480 33076.5742 37769.8828 42611.8594 51245.6016 62983.2500 85870.4688 147528.2812 572644.6250 | lr 3.8e-05 | norm 435641.7500 | dt 9.241 +type train | step 58 | loss 6109.0806 10362.5039 18863.4551 28107.0293 32967.8789 37752.3906 42548.4922 51325.1719 62592.7461 85062.4219 145893.8438 571272.3125 | lr 3.9e-05 | norm 429141.4375 | dt 9.253 +type train | step 59 | loss 6095.8955 10311.9307 18810.5996 27931.7129 32670.5742 37457.7812 42345.3945 51058.4297 62505.6367 84912.4766 146290.0000 555075.1875 | lr 3.9e-05 | norm 404987.0625 | dt 9.269 +type train | step 60 | loss 6091.7949 10323.8477 18765.9375 27920.5938 32637.5684 37336.7891 42069.1992 50721.3438 62227.4766 84299.0781 145001.0156 550316.2500 | lr 4.0e-05 | norm 396736.7500 | dt 9.263 +type train | step 61 | loss 6006.0303 10174.2188 18594.2559 27859.2188 32423.1055 37279.8008 41854.6602 50599.1172 62194.6641 84526.5312 145957.2812 575499.6875 | lr 4.1e-05 | norm 438788.1875 | dt 9.250 +type train | step 62 | loss 5960.9707 10058.6074 18385.4180 27503.4785 32057.3555 36711.1484 41387.0859 50183.7812 61742.9609 83629.9141 144614.5938 578707.6250 | lr 4.1e-05 | norm 457509.4375 | dt 9.249 +type train | step 63 | loss 6033.0356 10221.6348 18658.3516 27788.0938 32478.0449 37030.6602 41909.4570 50596.9844 61888.4883 83879.5781 143962.4375 545232.3125 | lr 4.2e-05 | norm 401983.4062 | dt 9.265 +type train | step 64 | loss 6007.2549 10183.9678 18496.9453 27704.5293 32277.1191 37011.0078 41819.3828 50562.2617 61874.3281 83252.4688 142797.7969 550708.2500 | lr 4.3e-05 | norm 401713.6875 | dt 9.258 +type train | step 65 | loss 5899.0610 9999.4219 18227.8340 27252.4629 32040.5996 36360.6289 41120.2773 49656.4414 60973.4844 82772.8828 141701.3594 551633.6250 | lr 4.3e-05 | norm 409910.8125 | dt 9.257 +type train | step 66 | loss 5922.4634 10014.9521 18245.7676 27324.6211 32006.6992 36331.4531 41295.7344 49715.2852 60991.0234 82999.5234 142008.0938 541684.0625 | lr 4.4e-05 | norm 398697.0312 | dt 9.274 +type train | step 67 | loss 5828.0366 9872.9297 18077.4590 27018.5996 31754.9668 35968.6836 41166.8125 49410.5898 60936.9961 82730.2578 141912.8125 530932.3125 | lr 4.5e-05 | norm 388963.4375 | dt 9.251 +type train | step 68 | loss 5839.6484 9915.4248 18126.3145 26952.5605 31634.9395 35779.4023 40771.6406 49455.3789 60584.3867 82673.8359 141723.0938 535827.8750 | lr 4.5e-05 | norm 389321.3750 | dt 9.256 +type train | step 69 | loss 5825.8145 9857.4023 18079.6133 26910.8984 31629.3613 35800.6953 40746.3984 48993.3359 59879.0469 81271.1562 139208.6094 538878.0625 | lr 4.6e-05 | norm 377025.8125 | dt 9.260 +type train | step 70 | loss 5800.7793 9797.7188 17956.3027 26642.2441 31402.3398 35607.4102 40593.1953 48753.1562 59822.9688 81962.4688 140604.7344 548934.9375 | lr 4.7e-05 | norm 409762.6875 | dt 9.230 +type train | step 71 | loss 5704.4883 9606.6660 17704.0566 26333.9727 31214.2500 35495.0938 40224.8711 48159.8359 59224.5156 80616.8750 137781.4219 514114.5625 | lr 4.7e-05 | norm 377629.0312 | dt 9.236 +type train | step 72 | loss 5764.8291 9778.8320 17862.2031 26542.5391 31286.7793 35631.6289 40222.5391 48442.8867 59489.6641 80810.1016 138473.9688 513253.2188 | lr 4.8e-05 | norm 357971.9375 | dt 9.264 +type train | step 73 | loss 5705.6235 9674.7578 17720.6641 26473.2793 30928.9980 35309.0117 39838.5898 47974.8125 59035.0820 80370.5625 138234.6562 522804.0625 | lr 4.9e-05 | norm 369636.8125 | dt 9.265 +type train | step 74 | loss 5696.9351 9664.5508 17573.3535 26355.1055 30666.9941 35158.2734 39771.4961 47902.3125 59071.6055 80420.9531 138535.9531 529360.8125 | lr 4.9e-05 | norm 387460.7812 | dt 9.260 +type train | step 75 | loss 5692.2104 9655.4307 17641.3555 26332.0898 30588.8145 35073.6250 39599.1016 47681.3672 58534.9062 79981.3828 136630.8438 506093.4062 | lr 5.0e-05 | norm 358582.1250 | dt 9.299 +type train | step 76 | loss 5636.8247 9546.9453 17551.3691 26269.9160 30430.9258 34830.3242 39357.7812 47385.0977 58341.7461 79679.1016 136506.9219 516124.5000 | lr 5.1e-05 | norm 370510.7812 | dt 9.273 +type train | step 77 | loss 5546.4775 9451.2529 17425.1328 26080.9375 30388.9648 34759.2109 39445.4141 47765.0391 58828.2188 80101.4531 138097.0469 521443.5000 | lr 5.1e-05 | norm 355115.2188 | dt 9.257 +type train | step 78 | loss 5579.9429 9477.5928 17330.1914 25852.5000 30479.8730 34408.1680 39205.9414 47223.4453 57782.1562 78551.0312 135450.5781 508132.8438 | lr 5.2e-05 | norm 363223.1562 | dt 9.272 +type train | step 79 | loss 5529.8105 9389.2334 17270.8438 25801.4551 30429.3203 34322.9414 39246.8711 47251.9023 58054.7539 79065.6406 135246.0938 506255.5625 | lr 5.3e-05 | norm 356004.3750 | dt 9.257 +type train | step 80 | loss 5487.9395 9326.8877 17064.6719 25443.0195 29929.6758 34056.3164 38993.4219 47207.8320 58194.2773 79095.7969 135217.0312 512195.9375 | lr 5.3e-05 | norm 360067.3438 | dt 9.248 +type train | step 81 | loss 5467.3252 9291.6289 17036.6797 25283.4883 29852.0078 33807.1250 38511.7266 46207.7891 56636.0078 77066.8984 132195.4844 489725.9688 | lr 5.4e-05 | norm 350183.8438 | dt 9.278 +type train | step 82 | loss 5527.6182 9390.9941 17107.2500 25530.5664 29993.3184 33951.3281 38542.8750 46217.5234 56890.1211 77069.2969 131763.5781 486270.1562 | lr 5.5e-05 | norm 336188.5938 | dt 9.284 +type train | step 83 | loss 5448.6973 9214.4629 16883.1113 25367.9258 29653.4590 33532.4570 38217.4062 45508.7227 56218.5078 76520.7812 130427.2188 475446.5938 | lr 5.5e-05 | norm 328524.8750 | dt 9.272 +type train | step 84 | loss 5398.1777 9164.4502 16752.0840 25125.5078 29440.7480 33413.6406 37918.8164 45679.7617 56301.9297 76702.1250 131586.2188 491999.3125 | lr 5.6e-05 | norm 351344.7188 | dt 9.257 +type train | step 85 | loss 5389.3818 9159.7480 16806.4121 25234.8672 29331.8438 33354.3242 37756.8047 45456.8125 55568.6562 76079.6797 130149.8359 478699.4375 | lr 5.7e-05 | norm 337035.9375 | dt 9.275 +type train | step 86 | loss 5319.0273 9024.1172 16664.1074 24936.5781 28882.5664 32974.0625 37389.3711 45021.4180 55166.8359 75858.4141 129769.4453 482533.8750 | lr 5.7e-05 | norm 339019.1250 | dt 9.270 +type train | step 87 | loss 5290.2358 8972.3252 16452.1699 24829.2500 28804.6250 32948.9883 37556.6250 45243.3594 55572.1641 75462.3359 129606.2812 499368.2188 | lr 5.8e-05 | norm 351886.0000 | dt 9.247 +type train | step 88 | loss 5284.2065 8997.0527 16569.3926 24987.3848 28935.0078 32829.3125 37481.4727 45179.9727 55285.5547 74905.7969 128001.8750 480221.5000 | lr 5.9e-05 | norm 331319.7812 | dt 9.302 +type train | step 89 | loss 5269.5674 8953.5732 16445.0879 24558.3613 28650.3965 32488.0566 37343.2656 44936.6367 54986.6406 74646.9062 128182.9844 471844.8438 | lr 5.9e-05 | norm 330649.7500 | dt 9.274 +type train | step 90 | loss 5224.9922 8883.4414 16419.8848 24459.2344 28776.6426 32409.0293 37078.5898 44558.5234 54650.8945 74480.7344 127316.4922 464882.1250 | lr 6.0e-05 | norm 320403.0938 | dt 9.271 +type train | step 91 | loss 5197.7148 8849.9570 16230.6855 24217.9766 28489.9004 32264.5742 36778.2461 44256.2188 54238.7422 73643.9219 126606.5391 472533.5625 | lr 6.1e-05 | norm 324935.6875 | dt 9.285 +type train | step 92 | loss 5085.9194 8662.7646 16055.7100 24066.3730 28380.5312 31967.3066 36408.7461 43606.2695 53959.2812 73803.6250 126903.4297 469081.1250 | lr 6.1e-05 | norm 325885.6875 | dt 9.252 +type train | step 93 | loss 5294.7344 9018.7881 16266.9971 24360.1621 28650.1055 32358.5156 36774.9258 43939.8633 53471.5703 71562.6953 121824.4062 446324.0938 | lr 6.2e-05 | norm 296564.0625 | dt 9.273 +type train | step 94 | loss 5123.0947 8689.9062 15939.3623 23924.7422 27911.7930 31694.1738 36069.8516 43398.3281 53234.7422 72523.3984 124366.5859 473335.4375 | lr 6.3e-05 | norm 331452.5312 | dt 9.268 +type train | step 95 | loss 5101.6816 8661.8135 15946.0840 24064.5391 27989.0078 31720.5996 36054.2188 43280.8477 52995.2344 72151.7656 123153.6641 443149.4062 | lr 6.3e-05 | norm 301247.8438 | dt 9.285 +type train | step 96 | loss 5092.0229 8634.3809 15921.8662 23952.6680 27780.9336 31548.2305 35913.1133 43050.2188 52389.9180 71398.2031 122358.9453 442634.3125 | lr 6.4e-05 | norm 304062.4375 | dt 9.261 +type train | step 97 | loss 5028.6387 8535.9258 15804.1523 23806.0332 27539.7266 31227.5664 35660.7656 43009.0820 52556.0859 72024.5156 123436.8203 440297.0938 | lr 6.5e-05 | norm 306235.1875 | dt 9.288 +type train | step 98 | loss 4967.4360 8472.7656 15657.8896 23437.2090 27271.0078 30964.5547 35401.5898 42630.8516 52556.8633 71664.8047 122017.8047 454357.1875 | lr 6.5e-05 | norm 309354.0312 | dt 9.269 +type train | step 99 | loss 5044.9282 8598.6924 15795.8555 23466.4805 27497.9141 31227.1484 35515.1953 42542.5938 51787.9453 68773.3438 117800.5938 490528.5000 | lr 6.6e-05 | norm 375444.3438 | dt 9.280 +type train | step 100 | loss 4911.4971 8366.5273 15473.3320 23227.7988 27219.7129 30852.8594 35138.9844 42088.4805 51867.4492 70159.2031 120916.6953 470580.8438 | lr 6.7e-05 | norm 326826.9062 | dt 9.261 +type train | step 101 | loss 4919.3657 8363.2988 15413.2031 23263.7637 27327.5000 30732.7793 34954.3984 41774.0312 51507.1875 69997.3594 119327.8281 422512.5000 | lr 6.7e-05 | norm 281289.0938 | dt 9.284 +type train | step 102 | loss 4894.4429 8339.1533 15468.7549 23352.7891 27276.8027 30650.5410 34865.0508 41540.9258 51248.0469 69652.9219 118748.6641 416140.7812 | lr 6.8e-05 | norm 280169.6562 | dt 9.304 +type train | step 103 | loss 4744.8779 8062.3281 15044.0020 22954.3906 26647.4707 30059.0098 34157.0352 40637.7148 50298.1914 68852.8125 118176.1875 432891.2500 | lr 6.9e-05 | norm 312073.3438 | dt 9.258 +type train | step 104 | loss 4695.4902 7970.3379 14937.6660 22791.0781 26436.1055 29951.8848 34062.3359 40818.6875 50377.2383 69299.4531 119291.7500 433161.5000 | lr 6.9e-05 | norm 321603.5000 | dt 9.237 +type train | step 105 | loss 4727.1460 8032.1104 15010.9775 22819.9277 26401.7852 30024.8984 34150.3242 40817.1211 50161.1016 68819.1250 118061.2031 422610.1250 | lr 7.0e-05 | norm 295682.1875 | dt 9.288 +type train | step 106 | loss 4792.6416 8164.2241 15179.6230 22878.5020 26584.8691 29914.8086 34355.1094 41383.3320 50571.4336 68749.6719 117196.8750 406628.6250 | lr 7.1e-05 | norm 258642.8906 | dt 9.297 +type train | step 107 | loss 4729.1006 8054.6982 14984.1484 22407.7070 26196.1523 29405.8535 33953.4414 40401.9180 49694.6484 67873.0156 115513.4062 406389.9375 | lr 7.1e-05 | norm 266823.6562 | dt 9.322 +type train | step 108 | loss 4767.8730 8129.7695 15110.2988 22516.1270 26147.1641 29592.6777 34010.6250 40466.9375 49771.5352 67628.3281 115192.9688 407871.8125 | lr 7.2e-05 | norm 269537.5000 | dt 9.322 +type train | step 109 | loss 4633.5615 7901.5557 14726.2314 22302.8984 26018.7949 29351.9824 33490.4375 39975.1875 49242.6055 66919.2109 114036.2734 401493.5000 | lr 7.3e-05 | norm 260712.7188 | dt 9.307 +type train | step 110 | loss 4654.7744 7932.8379 14791.3027 22253.1504 26097.7324 29487.7695 33511.1680 39851.8047 48968.5352 66423.9609 113194.3203 396221.3125 | lr 7.3e-05 | norm 255338.6562 | dt 9.316 +type train | step 111 | loss 4577.9009 7812.5034 14578.4531 22061.6836 25725.7383 29072.3242 33097.8594 39467.1680 48531.7812 66359.7656 113786.7656 411678.8125 | lr 7.4e-05 | norm 265050.7500 | dt 9.258 +type train | step 112 | loss 4585.9980 7816.8291 14573.0254 22164.2832 25779.9297 29134.2305 33136.2227 39660.9453 48492.2617 66547.6094 113345.9375 399603.7500 | lr 7.5e-05 | norm 258191.5781 | dt 9.274 +type train | step 113 | loss 4565.1011 7778.5342 14457.9912 22075.9863 25460.8672 28710.3770 32659.2852 39044.6367 47995.7148 65594.6484 111661.7812 380618.9688 | lr 7.5e-05 | norm 248913.2812 | dt 9.276 +type train | step 114 | loss 4515.8965 7682.5161 14363.6445 21841.5352 25382.8711 28595.6055 32892.7227 39168.6641 48037.6797 65293.4219 110999.1172 381637.5312 | lr 7.6e-05 | norm 241731.9375 | dt 9.270 +type train | step 115 | loss 4474.6641 7592.3291 14182.6719 21474.9355 24989.1875 28121.8320 32471.6230 38577.7578 47357.1875 64661.1719 110815.2422 387674.4688 | lr 7.7e-05 | norm 254843.9219 | dt 9.261 +type train | step 116 | loss 4491.7969 7674.6040 14248.4570 21537.0254 25112.1758 28326.5918 32513.3125 38602.7305 47231.4766 64105.7461 109193.5156 373286.5625 | lr 7.7e-05 | norm 231445.5156 | dt 9.297 +type train | step 117 | loss 4432.7217 7552.5684 14109.8506 21406.0137 25042.8516 28185.6562 32172.1523 38210.2656 47207.0547 64045.1445 109006.5703 370541.1562 | lr 7.8e-05 | norm 233348.2812 | dt 9.290 +type train | step 118 | loss 4370.3398 7435.5947 13918.6494 21363.3457 24738.1055 27946.5156 31838.8184 37942.1445 46801.6719 63955.3750 108462.7812 376794.9062 | lr 7.9e-05 | norm 243583.1406 | dt 9.265 +type train | step 119 | loss 4465.3721 7574.3447 14058.0205 21422.8398 24753.5527 28000.6270 31920.5605 38021.7031 46388.1406 63176.0273 107724.7578 370773.6562 | lr 7.9e-05 | norm 236611.6562 | dt 9.300 +type train | step 120 | loss 4406.0137 7495.6401 13922.4189 21260.3105 24585.1895 27393.7070 31368.5996 37141.0977 45534.6055 62369.5039 106531.4844 361560.1875 | lr 8.0e-05 | norm 228091.0312 | dt 9.298 +type train | step 121 | loss 4343.2671 7392.0791 13895.7715 21123.9883 24505.4727 27437.3750 31550.3652 37652.2109 45960.0312 62827.1445 106863.0391 358571.6562 | lr 8.1e-05 | norm 221760.7812 | dt 9.285 +type train | step 122 | loss 4256.7529 7268.3584 13685.9727 20772.4648 24341.0449 27001.1719 31227.5117 37040.9805 45368.8867 61822.2148 105928.4297 354279.0625 | lr 8.1e-05 | norm 221831.0156 | dt 9.287 +type train | step 123 | loss 4290.6572 7327.8872 13626.2744 20727.4766 24214.9043 27074.4355 31318.9707 37173.6055 45499.2227 61999.1406 105189.3828 353112.2500 | lr 8.2e-05 | norm 216655.6562 | dt 9.348 +type train | step 124 | loss 4185.6045 7131.4810 13515.5859 20565.5508 23916.8398 27016.3477 30896.8750 36492.8984 45020.5273 61394.1016 103395.8125 344163.9375 | lr 8.3e-05 | norm 208211.4375 | dt 9.328 +type train | step 125 | loss 4182.4561 7111.4678 13407.0137 20417.3965 23752.4492 26758.8711 30550.5410 36186.8359 44801.3477 61082.8672 103646.4141 356531.8125 | lr 8.3e-05 | norm 221974.9688 | dt 9.363 +type train | step 126 | loss 4152.4932 7075.6543 13367.2881 20596.2656 23867.9375 26708.5586 30535.7168 36022.1055 44315.9453 60868.9336 103337.5703 344440.8438 | lr 8.4e-05 | norm 213614.5938 | dt 9.335 +type train | step 127 | loss 4173.8149 7124.8770 13364.1377 20668.3789 23887.9219 26600.1016 30433.2383 36188.8906 44159.9180 60518.0781 103292.4844 350869.2188 | lr 8.5e-05 | norm 216271.2031 | dt 9.350 +type train | step 128 | loss 4147.5303 7076.0039 13299.3262 20407.0664 23518.9180 26243.0781 30306.3945 35977.6562 43953.4023 60040.9961 102772.8125 337849.8750 | lr 8.5e-05 | norm 206587.0469 | dt 9.336 +type train | step 129 | loss 4086.5481 6968.4658 13139.5137 20081.0781 23328.0020 26011.5508 30408.3594 35949.9375 43835.8203 59576.7305 101316.6250 344158.3750 | lr 8.6e-05 | norm 209435.2812 | dt 9.341 +type train | step 130 | loss 4059.2080 6928.1294 13003.8184 20041.0977 23068.2305 25762.5938 29872.5078 35332.8906 43185.5078 58931.6328 101019.0625 342820.8750 | lr 8.7e-05 | norm 212980.6562 | dt 9.333 +type train | step 131 | loss 4032.7920 6864.2305 12959.5283 19961.5742 23063.8906 25829.2871 29715.0762 35387.4922 43171.4062 59054.5625 100335.5781 330798.2500 | lr 8.7e-05 | norm 198603.2344 | dt 9.346 +type train | step 132 | loss 4028.9229 6861.5967 12994.9092 19808.4355 22916.2383 25831.0488 29528.9023 34874.9531 42892.8672 58353.8945 99103.8438 337091.5938 | lr 8.8e-05 | norm 199558.8906 | dt 9.367 +type train | step 133 | loss 3925.3806 6699.0859 12759.1426 19748.3359 22797.4590 25571.5605 29316.9258 34471.1836 42341.3828 57510.6133 98126.2969 321484.3125 | lr 8.9e-05 | norm 186185.9062 | dt 9.367 +type train | step 134 | loss 3942.1494 6717.7134 12803.3330 19845.0938 22793.8164 25263.5566 29206.9609 34385.2969 42384.6758 57656.9609 98599.1250 325633.8750 | lr 8.9e-05 | norm 194538.3281 | dt 9.362 +type train | step 135 | loss 3899.1045 6678.2031 12728.9453 19597.3145 22598.8105 25198.7910 29183.8672 34543.7812 42050.3164 57057.8555 97621.8125 323675.8125 | lr 9.0e-05 | norm 189737.0938 | dt 9.362 +type train | step 136 | loss 3893.6489 6623.7490 12630.4854 19416.4961 22648.7598 24900.9258 29055.8066 34350.0430 41991.2461 56757.3711 96833.9141 313949.6875 | lr 9.1e-05 | norm 183349.4062 | dt 9.369 +type train | step 137 | loss 3889.9033 6652.0601 12624.4404 19541.1133 22404.4648 24980.4297 28918.2207 34389.2461 42203.1641 57692.6250 97443.3359 329926.4688 | lr 9.1e-05 | norm 189889.3750 | dt 9.345 +type train | step 138 | loss 3818.9048 6520.3872 12422.9219 19332.9043 22026.2148 24824.9570 28504.4766 33752.5547 41477.3672 56417.3516 95856.8359 306015.7188 | lr 9.2e-05 | norm 177743.2031 | dt 9.358 +type train | step 139 | loss 3803.7122 6486.2461 12351.0449 19230.5117 22004.9453 24682.9336 28216.8613 33340.0195 40972.3828 55814.5312 95071.4531 309183.6875 | lr 9.3e-05 | norm 177893.4375 | dt 9.378 +type train | step 140 | loss 3760.6411 6425.0181 12299.0830 19133.7070 21999.4375 24481.1289 28213.3359 33125.0352 40706.1875 55521.3672 94893.6719 306884.7188 | lr 9.3e-05 | norm 177001.5781 | dt 9.411 +type train | step 141 | loss 3687.7568 6316.3516 12181.3926 19014.8242 21919.9883 24176.0898 28188.1758 33172.4102 40693.2891 54985.1992 94453.2188 306868.2812 | lr 9.4e-05 | norm 171055.8594 | dt 9.393 +type train | step 142 | loss 3677.8120 6219.0562 12024.0801 18831.9824 21479.7695 23867.1367 27812.4316 32958.9961 40242.7109 54330.0938 93289.9844 329037.0938 | lr 9.5e-05 | norm 215005.4688 | dt 9.293 +type train | step 143 | loss 3642.7410 6200.0713 11941.0938 18613.7012 21448.3066 23732.5078 27702.4453 32771.6680 40017.3984 53939.9922 92137.7891 316625.1562 | lr 9.5e-05 | norm 188140.5312 | dt 9.328 +type train | step 144 | loss 3692.3237 6287.2017 12031.3027 18765.5469 21566.3379 23784.6328 27640.4629 32600.0801 39825.7383 53833.7461 92161.2344 292528.5938 | lr 9.6e-05 | norm 161003.2500 | dt 9.435 +type train | step 145 | loss 3626.6929 6189.3101 11845.6885 18673.5566 21290.9570 23585.3320 27287.3750 32160.8105 39374.5859 53662.2656 91168.1250 290349.3438 | lr 9.7e-05 | norm 163609.8594 | dt 9.381 +type train | step 146 | loss 3607.7410 6149.5874 11901.4316 18544.7344 21133.1855 23664.6230 27250.8457 32199.4297 39438.0859 53625.9219 91148.0781 289559.4375 | lr 9.7e-05 | norm 164205.1562 | dt 9.377 +type train | step 1 | loss 7092.9990 11875.2012 21794.5879 32899.0391 37999.3203 42446.4766 49534.2891 57137.8320 71687.8906 98173.5781 166356.6094 672612.8125 | lr 6.7e-07 | norm 546114.1875 | dt 47.650 +type train | step 2 | loss 7052.1982 11765.7676 21695.8672 32570.9141 37762.6172 42181.1875 49225.2383 56928.3398 71430.9219 97611.2266 165732.5000 653476.5000 | lr 1.3e-06 | norm 524757.5000 | dt 9.300 +type train | step 3 | loss 7023.4775 11745.6230 21692.7188 32588.8672 37885.6328 42377.0938 49173.5625 56713.0977 71328.2344 98088.1094 165844.1562 666265.1250 | lr 2.0e-06 | norm 540414.3750 | dt 9.171 +type train | step 4 | loss 7038.5864 11773.7344 21675.3145 32610.9492 37784.0156 42081.6680 49177.9375 56715.4922 71476.7891 98438.6875 167708.6250 674657.1875 | lr 2.7e-06 | norm 559213.5000 | dt 9.162 +type train | step 5 | loss 6936.6807 11611.7217 21588.5312 32530.1562 37505.9141 42307.5547 49489.0312 57152.2266 71546.9922 97903.3828 164995.9219 707666.7500 | lr 3.3e-06 | norm 591530.0000 | dt 9.160 +type train | step 6 | loss 7004.5771 11737.9775 21706.3066 32666.1406 37705.0391 42473.7969 49597.1133 57364.9922 71819.0625 98565.8203 165907.5938 685935.1875 | lr 4.0e-06 | norm 540453.3750 | dt 9.154 +type train | step 7 | loss 6961.5576 11616.1699 21497.9336 32460.4668 37354.0664 41796.7578 48890.2969 56254.2344 70990.6328 97380.3281 164182.6094 669202.9375 | lr 4.7e-06 | norm 540507.0625 | dt 9.209 +type train | step 8 | loss 6983.7178 11672.9658 21593.7812 32508.1133 37421.2266 42128.4023 49433.6523 56829.7617 71168.1641 97248.4922 165613.6094 663520.7500 | lr 5.3e-06 | norm 525074.9375 | dt 9.184 +type train | step 9 | loss 6924.2632 11577.2998 21460.6602 32315.0312 37458.8672 41896.1016 49131.0820 56461.4258 70995.6250 97649.3828 166049.1719 670986.6875 | lr 6.0e-06 | norm 544044.6875 | dt 9.188 +type train | step 10 | loss 6922.3462 11565.7559 21385.5918 32357.7715 37502.1406 41726.4766 48931.6758 56026.2891 70532.7656 96969.7891 164848.2188 667042.6875 | lr 6.7e-06 | norm 539164.8750 | dt 9.183 +type train | step 11 | loss 6936.0176 11597.7100 21379.6309 32410.2227 37160.9023 41747.6211 48763.3984 56065.0273 70327.6406 96252.5859 163867.6875 670725.6250 | lr 7.3e-06 | norm 533016.1250 | dt 9.200 +type train | step 12 | loss 6972.7212 11638.6914 21333.1035 32364.6934 37163.7656 41841.0195 48865.3242 56139.7500 70242.0234 96192.6328 162962.5781 670968.1875 | lr 8.0e-06 | norm 538326.1250 | dt 9.212 +type train | step 13 | loss 6893.2480 11515.7012 21326.2090 32183.8125 37069.6484 41805.3281 48682.8516 55887.9883 70359.6797 96765.4062 164067.2812 653902.8750 | lr 8.7e-06 | norm 520321.7812 | dt 9.206 +type train | step 14 | loss 6894.9922 11520.2109 21317.8906 32332.9453 36961.8047 41543.9961 48538.7500 56100.5664 70302.4297 96359.3984 163623.2969 657883.5625 | lr 9.3e-06 | norm 525316.1875 | dt 9.206 +type train | step 15 | loss 6872.2407 11467.9238 21224.9570 32219.5820 37222.0000 41775.4922 48714.6328 56243.1406 70158.6406 96488.5469 163359.3594 658795.5000 | lr 1.0e-05 | norm 523027.9688 | dt 9.195 +type train | step 16 | loss 6841.4546 11430.4043 21051.0762 31761.5918 36625.0195 41190.5156 48159.8594 55464.9375 69777.3438 95456.6016 161636.9844 652460.0625 | lr 1.1e-05 | norm 516516.0000 | dt 9.191 +type train | step 17 | loss 6793.5840 11312.8838 21016.6719 31927.7402 36706.9688 41284.4297 48078.7188 55544.2188 69949.8281 96145.5469 163754.1250 645360.4375 | lr 1.1e-05 | norm 515245.4375 | dt 9.210 +type train | step 18 | loss 6928.7808 11576.7480 21241.1523 32190.5273 37126.5820 41889.7578 48531.7344 56833.9727 70397.9531 95701.4297 162473.1875 665574.8750 | lr 1.2e-05 | norm 526797.6875 | dt 9.213 +type train | step 19 | loss 6860.7266 11466.0352 21012.8047 31721.5781 36589.9570 41204.7227 47780.4258 55588.7891 69658.8750 95136.0156 162083.5781 662866.5625 | lr 1.3e-05 | norm 518809.7812 | dt 9.195 +type train | step 20 | loss 6820.3818 11371.9414 21046.8887 31853.2441 36569.1133 41091.5898 47751.3555 55638.6484 69694.7891 95781.1250 162955.1875 653606.5625 | lr 1.3e-05 | norm 528307.2500 | dt 9.202 +type train | step 21 | loss 6841.7871 11410.2197 21047.3105 31753.3652 36444.4883 41093.5742 47328.8008 55450.1680 69234.5703 94338.4375 160763.4375 647271.8125 | lr 1.4e-05 | norm 516163.3438 | dt 9.215 +type train | step 22 | loss 6828.2930 11381.8516 20950.6875 31698.3281 36354.1172 41004.6875 47329.3203 55631.1172 69621.3125 95666.5078 163337.4062 681824.3125 | lr 1.5e-05 | norm 550272.0625 | dt 9.193 +type train | step 23 | loss 6868.8267 11484.4824 21028.9473 31696.9219 36434.8789 40980.6172 47149.7148 55274.1094 68465.4297 93500.9688 158266.1719 635918.6875 | lr 1.5e-05 | norm 500123.3125 | dt 9.200 +type train | step 24 | loss 6932.1089 11582.7598 21205.0078 32066.2402 36684.0117 41317.5977 47534.4766 56047.7578 69429.8516 94020.3750 158664.9844 634228.7500 | lr 1.6e-05 | norm 489937.2188 | dt 9.222 +type train | step 25 | loss 6766.7710 11266.9160 20822.0352 31648.0215 35983.1836 40621.8945 46855.8828 55173.2852 68737.4922 93988.0703 160965.0469 659776.3750 | lr 1.7e-05 | norm 555465.9375 | dt 9.183 +type train | step 26 | loss 6695.7524 11114.2715 20514.3555 31202.3242 35767.5273 40308.7305 46456.5859 54685.3008 68305.8438 93672.0391 160244.0938 654388.8750 | lr 1.7e-05 | norm 542715.5625 | dt 9.208 +type train | step 27 | loss 6712.0322 11157.3174 20600.2188 31148.5508 35995.6445 40206.4102 46797.6875 54534.1094 68411.7891 93529.3047 158748.9062 622687.7500 | lr 1.8e-05 | norm 501525.7500 | dt 9.206 +type train | step 28 | loss 6721.9019 11234.6133 20739.9785 31645.3184 36180.9922 40535.0078 47039.7188 54892.2578 68576.6797 93362.8281 158533.2031 624202.1875 | lr 1.9e-05 | norm 493286.6875 | dt 9.214 +type train | step 29 | loss 6663.2598 11073.0117 20540.7188 31140.8730 35721.5508 40189.4219 46545.2422 54199.8359 67872.8047 92746.0234 158017.1875 645024.5000 | lr 1.9e-05 | norm 526069.2500 | dt 9.208 +type train | step 30 | loss 6693.4336 11143.8906 20618.7207 31136.3223 36011.5039 40534.5586 46771.9219 54818.2266 68411.7812 93387.4219 158702.6094 642904.6875 | lr 2.0e-05 | norm 526462.0625 | dt 9.224 +type train | step 31 | loss 6739.3672 11242.8223 20642.0391 31298.0078 35812.1836 40547.2539 46528.9375 54776.7344 68114.1875 92260.5703 156014.2031 612678.6250 | lr 2.1e-05 | norm 477267.6562 | dt 9.223 +type train | step 32 | loss 6703.0781 11173.1943 20486.7500 30919.1426 35558.7344 40006.8438 46618.2148 54292.3281 68269.1250 92519.3125 157427.1562 630002.9375 | lr 2.1e-05 | norm 501276.4688 | dt 9.219 +type train | step 33 | loss 6671.7202 11146.8633 20507.0957 30923.7109 35573.2773 40075.8516 46564.2773 54058.5156 67940.5938 92924.8438 157296.0938 617859.7500 | lr 2.2e-05 | norm 486945.5625 | dt 9.219 +type train | step 34 | loss 6600.1123 11002.4346 20286.0430 30848.6289 35144.2109 40043.4297 45958.6367 54145.7891 67885.9375 92932.0703 158936.5625 640503.4375 | lr 2.3e-05 | norm 519026.8125 | dt 9.211 +type train | step 35 | loss 6638.2163 11049.3037 20301.3594 30619.1699 35097.2500 39715.4414 45971.0039 53829.6719 67434.0781 91912.5000 155789.1719 637032.1250 | lr 2.3e-05 | norm 515390.9375 | dt 9.204 +type train | step 36 | loss 6580.0220 10995.7021 20230.0723 30601.6875 35155.2539 39571.1172 45974.9570 53388.2227 66846.1484 91002.3828 155454.4844 629068.6875 | lr 2.4e-05 | norm 505133.5938 | dt 9.220 +type train | step 37 | loss 6484.8955 10813.2705 20043.0254 30262.9219 34929.9336 39555.4844 45398.8281 53274.3672 66791.3828 91998.6406 157150.7500 631124.7500 | lr 2.5e-05 | norm 495424.8750 | dt 9.219 +type train | step 38 | loss 6630.4795 11072.0615 20231.3516 30490.2148 35128.5625 39662.6367 45638.0000 53590.6719 67021.3438 91239.5156 155820.8750 623438.2500 | lr 2.5e-05 | norm 501838.1875 | dt 9.218 +type train | step 39 | loss 6587.3511 10955.1152 20115.0566 30136.5586 34666.9141 39235.3828 45294.6797 52978.2148 66678.0703 91288.0000 155334.3906 624565.6875 | lr 2.6e-05 | norm 505548.8125 | dt 9.228 +type train | step 40 | loss 6544.2432 10933.7559 20026.9844 30076.8340 34701.5547 39107.6641 45370.7500 52906.9102 66052.1484 90210.6250 154331.0156 610199.7500 | lr 2.7e-05 | norm 478517.3125 | dt 9.239 +type train | step 41 | loss 6567.3838 10920.2891 20031.6719 29932.9121 34568.4609 39095.0625 45573.0938 53021.5352 66346.9844 90178.1250 153229.8594 596554.5625 | lr 2.7e-05 | norm 453525.6562 | dt 9.217 +type train | step 42 | loss 6514.3691 10889.6084 20002.0820 29999.8887 34617.4102 39024.0703 45622.6328 52797.6172 66428.9453 90609.7266 153481.4531 595059.3750 | lr 2.8e-05 | norm 461534.2812 | dt 9.223 +type train | step 43 | loss 6493.9385 10845.8145 19855.5156 29911.5508 34679.7656 38849.7500 45137.2031 52090.6016 65688.6562 89635.8828 152761.6406 621814.3750 | lr 2.9e-05 | norm 510606.6562 | dt 9.205 +type train | step 44 | loss 6480.6421 10806.2891 19887.9160 29944.6191 34497.7109 38877.6250 45269.3359 52524.9648 65887.6016 90070.0781 153422.0156 598246.9375 | lr 2.9e-05 | norm 463013.9062 | dt 9.240 +type train | step 45 | loss 6430.6807 10735.2168 19713.3516 29648.7637 34224.0195 38625.8984 44907.2930 52088.6602 65330.3594 89376.7812 153037.2812 606726.8750 | lr 3.0e-05 | norm 482166.8125 | dt 9.208 +type train | step 46 | loss 6391.7764 10627.9883 19632.8320 29756.9414 34255.4180 38472.7266 44742.2930 52151.1367 65672.1328 90200.5391 153773.5781 595380.6250 | lr 3.1e-05 | norm 462858.4062 | dt 9.220 +type train | step 47 | loss 6429.6602 10705.5449 19650.1992 29621.5820 34030.6133 38409.5039 44509.1250 52027.4336 65387.9297 89614.6406 152668.3281 586875.6250 | lr 3.1e-05 | norm 452895.5312 | dt 9.222 +type train | step 48 | loss 6441.1826 10727.1104 19680.9316 29625.4688 34017.2656 38214.2695 44312.8398 51920.9375 65316.7695 89103.2266 151256.5312 593888.8125 | lr 3.2e-05 | norm 459138.7188 | dt 9.221 +type train | step 49 | loss 6421.7959 10726.7051 19634.5039 29613.5742 34043.6172 38284.9805 44321.6133 51984.9492 64979.2969 88559.9219 150007.6562 586456.3125 | lr 3.3e-05 | norm 446757.3750 | dt 9.219 +type train | step 50 | loss 6334.7539 10575.7979 19447.9766 29295.6602 33818.8867 37957.0625 43933.3008 51718.4336 64715.2109 88850.7656 150915.7344 586240.3750 | lr 3.3e-05 | norm 454458.5938 | dt 9.223 +type train | step 51 | loss 6286.6187 10465.5107 19244.6816 29073.8105 33471.7266 37366.7383 43296.3086 50788.8359 63267.8906 86002.9219 147030.1562 627581.6250 | lr 3.4e-05 | norm 523915.4375 | dt 9.194 +type train | step 52 | loss 6091.1660 10147.1465 18917.9941 28733.0645 33020.4492 37105.5469 42900.3828 50730.0859 63832.4688 88044.7344 151637.7812 691238.0625 | lr 3.5e-05 | norm 651916.7500 | dt 9.157 +type train | step 53 | loss 6219.1221 10390.2861 19125.2773 29052.8242 33388.4531 37432.8398 43330.4258 50991.7227 64256.3945 87865.5781 149272.7656 567872.3125 | lr 3.5e-05 | norm 440282.8750 | dt 9.231 +type train | step 54 | loss 6213.4966 10358.5039 19029.7344 28784.1367 32992.9805 37214.2344 42922.6719 50413.3789 63714.1172 87324.3125 147709.0156 564707.7500 | lr 3.6e-05 | norm 432406.9688 | dt 9.227 +type train | step 55 | loss 6272.3730 10434.5010 19065.0293 28854.5391 32974.4141 37184.6172 43021.3359 50590.3203 63448.1133 86460.4922 146824.3125 571082.2500 | lr 3.7e-05 | norm 468513.4375 | dt 9.215 +type train | step 56 | loss 6179.8633 10297.6943 18932.6367 28356.3809 32751.7539 36870.6055 42552.4492 49869.3086 62508.5586 85642.2656 144992.7500 589836.8750 | lr 3.7e-05 | norm 476536.9062 | dt 9.229 +type train | step 57 | loss 6114.9316 10207.3184 18872.7617 28429.2520 32693.8887 37036.3672 42839.0664 50093.5430 63170.3945 86673.5781 147364.3281 569797.8125 | lr 3.8e-05 | norm 454141.9375 | dt 9.235 +type train | step 58 | loss 6148.1709 10266.7803 18880.8867 28499.7461 32711.7070 36999.3320 42976.4336 50170.9141 62862.6094 85745.0859 145470.1094 566416.5625 | lr 3.9e-05 | norm 444361.5938 | dt 9.226 +type train | step 59 | loss 6121.9287 10225.7666 18812.3516 28257.8320 32580.2285 36797.8672 42864.7891 49811.9727 62696.0391 85648.7266 145651.6406 548235.6250 | lr 3.9e-05 | norm 412749.6562 | dt 9.232 +type train | step 60 | loss 6123.3174 10225.8223 18769.9199 28184.2266 32428.3594 36688.8125 42580.2344 49622.7656 62482.3984 85131.1250 144691.0469 545628.3750 | lr 4.0e-05 | norm 405980.0625 | dt 9.235 +type train | step 61 | loss 6038.0107 10080.4004 18620.9336 28099.1641 32351.3359 36551.0898 42230.3008 49458.1953 62286.6562 85302.6875 145536.5156 570780.0625 | lr 4.1e-05 | norm 447997.9375 | dt 9.214 +type train | step 62 | loss 5985.7310 9956.1895 18407.4668 27773.9141 31868.9512 35990.2617 41809.9062 48914.3867 61611.1875 84707.0000 144562.9062 572317.5000 | lr 4.1e-05 | norm 466083.0625 | dt 9.218 +type train | step 63 | loss 6058.8604 10131.7900 18575.1113 28037.4219 32290.5000 36365.3125 42089.5195 49338.3242 61917.1211 84770.0938 143687.4531 538334.3125 | lr 4.2e-05 | norm 406386.0312 | dt 9.233 +type train | step 64 | loss 6040.8125 10091.7227 18482.1699 27943.8379 32293.6543 36402.2852 42028.5000 49356.5586 61864.8633 84209.1328 142368.1562 545367.8125 | lr 4.3e-05 | norm 411246.0312 | dt 9.235 +type train | step 65 | loss 5931.4629 9903.4258 18270.8984 27588.7598 31868.7656 35749.6875 41474.1328 48711.3906 61027.3164 83446.8438 141400.3594 546095.8750 | lr 4.3e-05 | norm 422904.6250 | dt 9.219 +type train | step 66 | loss 5949.4004 9928.0098 18279.0371 27610.9902 31835.4668 35838.1836 41398.2812 48634.5391 60930.6875 83578.7500 141685.5938 538121.6250 | lr 4.4e-05 | norm 413965.2188 | dt 9.230 +type train | step 67 | loss 5853.5928 9776.8516 18090.6445 27443.0488 31577.8984 35498.6172 41108.2656 48284.4922 60837.4141 83127.9766 141382.3125 525826.2500 | lr 4.5e-05 | norm 397388.3750 | dt 9.229 +type train | step 68 | loss 5867.3535 9821.0039 18094.0977 27385.7734 31450.9375 35442.1016 40904.8750 48458.0781 60577.1875 82992.2578 141161.7031 529486.6250 | lr 4.5e-05 | norm 395855.6562 | dt 9.222 +type train | step 69 | loss 5849.5977 9763.8516 18008.2754 27240.0566 31481.6035 35512.9375 40928.1406 48002.5742 59823.6953 81770.4219 138742.8438 533453.6250 | lr 4.6e-05 | norm 382518.2812 | dt 9.240 +type train | step 70 | loss 5827.4375 9708.4131 17933.2734 27027.2695 31179.1191 35201.2422 40657.7773 47764.1836 59983.4414 82642.2891 140457.3438 543564.8750 | lr 4.7e-05 | norm 425205.9688 | dt 9.222 +type train | step 71 | loss 5730.9775 9515.8457 17749.6074 26768.8809 30920.5176 34948.5625 40482.3320 47182.6289 59182.1719 81530.5156 137639.5000 508464.4688 | lr 4.7e-05 | norm 387564.8750 | dt 9.215 +type train | step 72 | loss 5793.9458 9684.9121 17835.2148 26857.3164 30902.3203 35044.0859 40577.3438 47503.1953 59601.4492 81760.3125 138472.8281 506928.0938 | lr 4.8e-05 | norm 363830.6875 | dt 9.238 +type train | step 73 | loss 5729.5000 9574.5098 17683.9043 26622.9902 30752.3203 34687.0508 40227.6406 46998.7773 59171.5742 81129.0703 137886.9688 518891.9375 | lr 4.9e-05 | norm 387440.1250 | dt 9.233 +type train | step 74 | loss 5729.6064 9566.3564 17605.5762 26430.4863 30461.9121 34482.7188 40022.0977 47007.2266 59241.3125 81016.1016 138293.7344 520961.6875 | lr 4.9e-05 | norm 389713.1562 | dt 9.213 +type train | step 75 | loss 5718.0850 9572.7812 17576.9004 26423.6348 30463.2012 34446.2617 39892.7734 46774.2969 58738.0469 80637.5938 136591.1562 500935.5625 | lr 5.0e-05 | norm 365802.6875 | dt 9.243 +type train | step 76 | loss 5657.4316 9445.0684 17493.2930 26413.8887 30567.9160 34208.1797 39564.5000 46418.5078 58362.2109 80271.9219 136201.9062 510482.4062 | lr 5.1e-05 | norm 387949.9688 | dt 9.233 +type train | step 77 | loss 5566.0430 9354.3076 17347.4766 26312.5879 30419.0410 34328.8203 39703.8281 46780.1016 58698.6797 80774.2266 137626.1562 516984.1875 | lr 5.1e-05 | norm 365490.2812 | dt 9.212 +type train | step 78 | loss 5603.3525 9377.5479 17265.3340 26233.4629 30177.4961 33978.4492 39289.3828 46261.2891 57845.2031 79222.5781 134709.1875 502241.8125 | lr 5.2e-05 | norm 370972.3750 | dt 9.230 +type train | step 79 | loss 5558.7764 9290.4717 17129.8633 26168.1973 30168.0312 33906.8047 39328.2461 46381.7266 58123.9141 79502.8750 134825.5000 501124.7812 | lr 5.3e-05 | norm 369671.4688 | dt 9.227 +type train | step 80 | loss 5514.1548 9221.9424 17025.8867 26006.4824 29718.0703 33633.2344 39153.9688 46452.0586 58276.3398 79742.3047 134840.4375 509801.0938 | lr 5.3e-05 | norm 387879.5625 | dt 9.228 +type train | step 81 | loss 5489.7075 9190.1875 16987.6270 25822.6758 29735.8066 33558.8828 38752.3438 45436.3672 56744.4375 77680.7109 132142.6562 483021.8750 | lr 5.4e-05 | norm 357185.6250 | dt 9.235 +type train | step 82 | loss 5553.9648 9298.3008 17095.7520 25876.1367 29604.4023 33544.8984 38740.9492 45422.7461 56833.0586 77601.3828 131408.6562 481492.4062 | lr 5.5e-05 | norm 346741.5312 | dt 9.263 +type train | step 83 | loss 5470.8262 9119.8740 16866.2910 25449.9902 29324.2734 33163.5469 38362.2656 44781.4023 56435.4453 77151.1484 130401.9453 470926.1250 | lr 5.5e-05 | norm 340879.1875 | dt 9.253 +type train | step 84 | loss 5416.9512 9053.5996 16689.3027 25203.7871 29108.8320 33053.1133 38136.0703 44950.3672 56577.4688 77205.6172 131461.0625 484070.2500 | lr 5.6e-05 | norm 363692.2500 | dt 9.232 +type train | step 85 | loss 5414.5479 9067.5342 16723.5684 25204.2969 29132.1445 32924.5508 38027.5039 44733.9414 56008.8633 76483.4453 130453.3828 473274.0000 | lr 5.7e-05 | norm 347584.2812 | dt 9.247 +type train | step 86 | loss 5338.1538 8928.6963 16549.9199 25018.7773 28783.5469 32516.4258 37672.6055 44180.0977 55530.2500 76379.4297 129403.0938 476984.6562 | lr 5.7e-05 | norm 359469.8438 | dt 9.231 +type train | step 87 | loss 5312.3335 8875.7129 16429.6875 24971.7734 28764.0312 32559.3203 37659.3789 44653.7383 55683.0078 76117.1797 128917.7031 495294.0938 | lr 5.8e-05 | norm 370403.4062 | dt 9.227 +type train | step 88 | loss 5305.1909 8901.9639 16477.6816 25024.3965 28944.5098 32474.0781 37666.9531 44388.0938 55373.1953 75584.9453 127475.2578 473589.6562 | lr 5.9e-05 | norm 342228.0312 | dt 9.246 +type train | step 89 | loss 5289.3740 8870.0518 16289.9463 24889.4023 28513.7695 32248.2598 37447.4648 44098.3359 55092.9492 75340.4531 127789.6172 464441.2812 | lr 5.9e-05 | norm 338719.3438 | dt 9.251 +type train | step 90 | loss 5248.3394 8790.0000 16246.0127 24727.3301 28482.2305 32178.2188 37295.0859 43880.6562 54816.3047 75004.8594 127273.9453 460015.6250 | lr 6.0e-05 | norm 332217.6250 | dt 9.249 +type train | step 91 | loss 5216.9976 8759.1748 16168.5869 24547.3945 28297.1387 31949.5273 36895.6992 43540.4453 54077.0586 74480.9219 126413.9922 466925.6562 | lr 6.1e-05 | norm 334048.9062 | dt 9.240 +type train | step 92 | loss 5109.4648 8565.0986 15992.8223 24303.1934 27974.2344 31680.2461 36634.2188 42931.5977 54019.1602 74356.6094 127020.7266 462199.6250 | lr 6.1e-05 | norm 336374.0312 | dt 9.231 +type train | step 93 | loss 5318.6997 8938.1777 16231.8955 24632.5957 28320.1348 32041.5566 37115.6719 43388.5586 53402.5078 72339.2734 121303.1328 439887.7812 | lr 6.2e-05 | norm 299784.5625 | dt 9.245 +type train | step 94 | loss 5141.2095 8596.8848 15943.7861 24055.9141 27628.8828 31376.8398 36243.0234 42766.1758 53399.6172 73207.9141 124193.4453 468852.6875 | lr 6.3e-05 | norm 343960.0625 | dt 9.241 +type train | step 95 | loss 5123.8770 8577.4863 15879.6309 24007.7871 27705.8691 31439.2871 36254.2852 42589.2969 53294.7812 72638.8203 123095.7031 436722.5000 | lr 6.3e-05 | norm 309633.0000 | dt 9.250 +type train | step 96 | loss 5108.7993 8545.4463 15821.0381 23927.8281 27527.4102 31267.6035 35991.9102 42576.4570 52696.8398 71937.6094 122223.9062 436386.3750 | lr 6.4e-05 | norm 311549.7500 | dt 9.247 +type train | step 97 | loss 5044.8228 8446.4043 15683.0342 23937.4414 27534.1250 30997.5098 35838.8984 42329.7734 52720.4375 72768.7656 123011.1797 434703.6250 | lr 6.5e-05 | norm 312901.7812 | dt 9.248 +type train | step 98 | loss 4983.7085 8376.0811 15527.3545 23671.0586 27149.6484 30752.1230 35630.7227 42246.2148 52521.5664 72194.7109 121898.0703 450276.2500 | lr 6.5e-05 | norm 325181.3438 | dt 9.230 +type train | step 99 | loss 5072.2456 8492.3662 15579.1807 23810.7461 27311.5781 30944.5195 35652.9297 41991.4531 51874.3516 69258.7500 117273.8203 486277.6875 | lr 6.6e-05 | norm 403750.6250 | dt 9.235 +type train | step 100 | loss 4933.7285 8267.4512 15373.6543 23465.0000 26956.8242 30555.1523 35463.4531 41644.5781 51832.6406 70786.5938 120889.5781 466183.7812 | lr 6.7e-05 | norm 335819.5625 | dt 9.248 +type train | step 101 | loss 4940.4580 8276.4248 15370.0664 23420.2480 26917.2363 30415.1328 35203.6602 41322.5703 51452.8867 70618.9766 119841.5000 415186.2500 | lr 6.7e-05 | norm 290131.5312 | dt 9.263 +type train | step 102 | loss 4917.2705 8247.8154 15316.3711 23280.3125 26938.3652 30443.2207 35139.2891 40971.2148 51326.6758 70178.4219 118746.5781 410016.0625 | lr 6.8e-05 | norm 282376.6875 | dt 9.273 +type train | step 103 | loss 4763.9673 7970.5303 15013.7285 22797.8398 26364.6211 29909.1719 34363.0156 40347.6875 50596.0586 69410.9531 118304.1641 424748.8438 | lr 6.9e-05 | norm 316999.8125 | dt 9.223 +type train | step 104 | loss 4715.0479 7872.9395 14884.7891 22673.6094 26192.8535 29684.9609 34324.3359 40538.7812 50650.6328 69681.3672 119735.9766 426959.7500 | lr 6.9e-05 | norm 338345.0938 | dt 9.226 +type train | step 105 | loss 4745.3359 7939.9961 14946.2490 22820.3398 26369.0176 29537.6699 34253.7188 40527.2812 50376.7734 69047.8594 118050.0156 416605.0312 | lr 7.0e-05 | norm 306915.6562 | dt 9.233 +type train | step 106 | loss 4811.2827 8081.2935 14975.3213 22968.4395 26505.4492 29868.9941 34608.7930 40873.9297 50687.8750 69247.8906 116944.8984 400183.2188 | lr 7.1e-05 | norm 257163.4844 | dt 9.271 +type train | step 107 | loss 4747.5869 7967.2383 14791.1768 22634.0391 25966.1504 29365.8633 33867.0078 40062.1445 49894.5898 68239.1328 115606.2656 399743.5000 | lr 7.1e-05 | norm 274970.7188 | dt 9.266 +type train | step 108 | loss 4782.4463 8039.3506 14873.0869 22698.5469 26089.1113 29312.7520 34103.3477 40071.2148 49780.8359 68096.3359 115059.0703 400357.3750 | lr 7.2e-05 | norm 272153.5938 | dt 9.253 +type train | step 109 | loss 4646.9722 7812.5195 14614.5449 22378.4102 25731.7324 29054.9727 33793.8047 39633.9062 49225.6680 67423.3203 114217.8906 396181.5625 | lr 7.3e-05 | norm 263339.7812 | dt 9.252 +type train | step 110 | loss 4668.9844 7846.0557 14657.8633 22465.5684 25824.3984 29095.0078 33572.6445 39600.7031 49121.0117 66937.8281 113327.0625 389575.4375 | lr 7.3e-05 | norm 251631.1250 | dt 9.285 +type train | step 111 | loss 4593.6899 7726.4995 14477.8574 22002.3203 25363.7969 28713.3711 33293.0703 39117.5273 48914.6328 66889.2422 113520.4609 405099.9375 | lr 7.4e-05 | norm 281300.7812 | dt 9.260 +type train | step 112 | loss 4600.6489 7738.6968 14481.0801 21942.5234 25495.8848 28747.3145 33249.5820 39426.1914 49052.3242 66869.4531 113155.8906 393700.6250 | lr 7.5e-05 | norm 261981.6094 | dt 9.282 +type train | step 113 | loss 4580.4214 7692.8984 14424.0215 21870.4863 25353.4512 28627.9629 32903.5977 38906.0547 48474.9414 66033.5312 111647.7031 373845.2188 | lr 7.5e-05 | norm 246396.6250 | dt 9.273 +type train | step 114 | loss 4531.0068 7601.9893 14284.9355 21822.0801 25257.7441 28540.2500 32868.3633 39002.6875 48175.8594 65914.0625 110954.9766 376359.9688 | lr 7.6e-05 | norm 248163.2344 | dt 9.271 +type train | step 115 | loss 4489.1855 7509.0361 14061.5996 21627.2949 24854.3672 28084.1816 32502.3750 38366.8008 47434.2266 65355.4961 110621.6953 379828.5625 | lr 7.7e-05 | norm 256997.0938 | dt 9.260 +type train | step 116 | loss 4508.3125 7583.9985 14102.7754 21721.8887 24997.2090 28197.2617 32513.5625 38287.2930 47393.5352 64584.7852 109135.6875 367479.6250 | lr 7.7e-05 | norm 232030.2656 | dt 9.274 +type train | step 117 | loss 4447.8350 7467.8384 14030.8604 21495.3359 24795.4746 28055.6523 32421.4258 37954.5156 47285.2227 64430.3359 109127.8359 364331.5312 | lr 7.8e-05 | norm 231329.0625 | dt 9.294 +type train | step 118 | loss 4386.1763 7351.4736 13832.0391 21371.6680 24539.7109 27684.1133 31984.9629 37743.7461 46943.0859 64337.4766 108488.5938 370102.3750 | lr 7.9e-05 | norm 244869.6719 | dt 9.260 +type train | step 119 | loss 4479.9727 7494.6758 13915.7764 21311.4199 24521.6660 27812.3789 32035.4785 37717.3828 46798.2656 63732.0273 107758.5312 363634.0625 | lr 7.9e-05 | norm 231386.1250 | dt 9.271 +type train | step 120 | loss 4421.4761 7423.4082 13844.9316 21001.8125 24347.4570 27420.5000 31477.9766 37000.2969 45828.1250 62678.2422 106297.2344 355319.0938 | lr 8.0e-05 | norm 225664.7656 | dt 9.306 +type train | step 121 | loss 4355.7192 7310.5464 13776.2549 20959.6348 24237.1602 27329.6133 31515.9375 37379.2109 46504.6797 63273.4570 106730.6641 351597.1562 | lr 8.1e-05 | norm 222603.7344 | dt 9.278 +type train | step 122 | loss 4270.3345 7183.8135 13537.2227 20762.8457 24044.3301 27113.7969 31242.3965 36883.1133 45651.8945 62378.8516 106017.2188 347227.5000 | lr 8.1e-05 | norm 225162.2656 | dt 9.271 +type train | step 123 | loss 4301.8438 7239.7700 13503.1055 20752.5156 23932.3281 27136.2051 31369.0996 37025.1953 45541.1328 62359.9688 105189.8125 347401.0938 | lr 8.2e-05 | norm 212974.7500 | dt 9.287 +type train | step 124 | loss 4193.4932 7052.9219 13393.9639 20546.2148 23822.5684 26960.7441 31024.1016 36313.3906 45138.8086 61798.3242 103633.1797 338100.2188 | lr 8.3e-05 | norm 209142.7188 | dt 9.296 +type train | step 125 | loss 4193.3857 7026.4473 13273.1270 20481.9297 23630.2266 26607.4609 30603.4551 36141.7227 44830.4922 61635.2969 103711.4453 348535.5625 | lr 8.3e-05 | norm 225234.7031 | dt 9.288 +type train | step 126 | loss 4160.1826 6993.7173 13264.7666 20371.0215 23644.9375 26685.3379 30638.7656 36071.2539 44818.3984 61262.5039 103277.0312 337018.1875 | lr 8.4e-05 | norm 213511.8906 | dt 9.285 +type train | step 127 | loss 4184.7339 7045.0342 13287.4697 20324.0625 23481.8379 26742.3652 30562.7715 36116.4297 44576.2070 61158.3359 103125.5391 346373.0000 | lr 8.5e-05 | norm 215619.2812 | dt 9.276 +type train | step 128 | loss 4162.9194 6991.6157 13141.6074 20105.0195 23412.2773 26240.2793 30268.6797 35804.8633 44286.5156 60690.4219 102662.5625 330534.7500 | lr 8.5e-05 | norm 207326.7656 | dt 9.297 +type train | step 129 | loss 4097.4419 6882.8364 13033.8281 20017.9453 23079.2656 26202.9668 30142.6445 35669.4922 44059.4727 60217.6328 101307.0000 337475.1562 | lr 8.6e-05 | norm 209139.5156 | dt 9.284 +type train | step 130 | loss 4067.2490 6851.6602 12933.9434 19856.7051 22904.6875 25781.1816 29853.3945 35165.9023 43308.7891 59365.9141 101016.2344 335944.3750 | lr 8.7e-05 | norm 208723.4375 | dt 9.274 +type train | step 131 | loss 4038.2236 6789.2002 12874.3750 19844.9258 23008.2207 25865.7344 29883.6797 35047.7891 43389.2188 59608.9102 100301.3359 321959.9062 | lr 8.7e-05 | norm 196350.7031 | dt 9.276 +type train | step 132 | loss 4038.3633 6780.4233 12741.6260 19714.3809 22895.5059 25653.2520 29587.7500 34864.8867 43008.4336 58877.0078 98913.1250 330373.0938 | lr 8.8e-05 | norm 198860.9219 | dt 9.283 +type train | step 133 | loss 3934.2881 6618.9399 12672.2480 19624.3828 22678.7617 25629.2695 29364.0098 34542.4414 42666.1055 58194.1094 97895.1016 314416.0625 | lr 8.9e-05 | norm 187004.3594 | dt 9.300 +type train | step 134 | loss 3947.8313 6640.7627 12626.7871 19511.6230 22599.0469 25415.4238 29070.7148 34481.4062 42564.1797 58400.4570 98534.2266 317441.5938 | lr 8.9e-05 | norm 192497.1875 | dt 9.294 +type train | step 135 | loss 3904.7622 6587.8701 12577.3564 19349.5000 22381.7402 25191.7793 28891.6582 34284.8906 42111.2539 57861.8164 97544.3438 317609.1875 | lr 9.0e-05 | norm 187550.2812 | dt 9.294 +type train | step 136 | loss 3900.8320 6549.1904 12539.3643 19232.1562 22233.6211 25288.5352 28968.1758 34168.6016 42012.1914 57324.4219 96780.9766 306957.5625 | lr 9.1e-05 | norm 182510.2969 | dt 9.304 +type train | step 137 | loss 3894.4868 6571.4385 12494.5820 19296.6426 22231.3242 25272.7207 29039.5215 34112.0312 42325.0781 58134.0703 97394.3438 321120.7188 | lr 9.1e-05 | norm 193686.0156 | dt 9.293 +type train | step 138 | loss 3822.9658 6435.7080 12307.7275 19064.1445 22086.2832 24835.8379 28631.7461 33424.8828 41588.0820 56881.3711 95747.4766 300684.8125 | lr 9.2e-05 | norm 173457.3281 | dt 9.305 +type train | step 139 | loss 3809.6357 6407.1558 12242.5059 18950.8105 22103.1484 24633.3027 28408.8633 33287.1250 41128.7656 56270.3438 94848.6641 302896.1875 | lr 9.3e-05 | norm 176038.5312 | dt 9.326 +type train | step 140 | loss 3761.5378 6341.3877 12206.5234 18891.9062 21795.9316 24590.6699 28276.0273 33316.4180 40967.7109 56193.1211 94453.3203 299920.6562 | lr 9.3e-05 | norm 174283.5156 | dt 9.295 +type train | step 141 | loss 3691.8684 6240.4067 12053.2061 18782.3359 21616.8691 24352.1348 28064.4902 33086.4492 40652.4844 55843.9766 94345.0859 299349.0000 | lr 9.4e-05 | norm 170441.2500 | dt 9.293 +type train | step 142 | loss 3674.2505 6143.3413 11885.2471 18430.2461 21140.9082 24173.3496 27747.4004 32707.4180 40306.4141 55089.3750 93125.2656 322864.4375 | lr 9.5e-05 | norm 222213.4062 | dt 9.238 +type train | step 143 | loss 3641.7158 6119.0161 11847.6357 18312.1973 21117.9395 24117.7812 27618.0430 32502.5000 40030.9219 54611.0273 92141.4844 309301.4062 | lr 9.5e-05 | norm 191983.4844 | dt 9.253 +type train | step 144 | loss 3695.0781 6205.7754 11912.6494 18422.5762 21371.3477 24121.4609 27667.0234 32404.2812 39890.0547 54392.0898 91853.7344 287598.9375 | lr 9.6e-05 | norm 157427.8750 | dt 9.310 +type train | step 145 | loss 3631.7202 6117.2388 11793.3887 18203.1660 21316.8145 23720.6133 27388.7246 32033.5605 39589.8086 54332.3477 90921.3516 284094.6250 | lr 9.7e-05 | norm 161582.7500 | dt 9.325 +type train | step 146 | loss 3608.9382 6075.7183 11764.0957 18160.5098 21153.6719 23716.2695 27318.7910 32055.7285 39597.9375 54352.0391 90755.5938 284431.9375 | lr 9.7e-05 | norm 160287.5938 | dt 9.329 +type train | step 147 | loss 3620.5645 6089.5381 11687.6895 18189.0566 21004.4648 23565.5215 27189.8301 31866.7070 39319.3516 53915.6992 90258.4531 282053.9375 | lr 9.8e-05 | norm 155694.4531 | dt 9.315 +type train | step 148 | loss 3558.4922 5984.7363 11539.6709 18096.7344 20651.0547 23165.1582 26850.5312 31318.5938 38551.9844 52832.1641 89182.4375 272528.3750 | lr 9.9e-05 | norm 153297.8125 | dt 9.300 +type train | step 149 | loss 3587.0671 6043.7231 11589.7490 17946.4453 20638.0391 23368.7695 26723.1484 31167.9082 38380.3945 52260.1797 87445.7969 276397.0625 | lr 9.9e-05 | norm 149274.1719 | dt 9.329 +type train | step 150 | loss 3524.3301 5938.1650 11493.8955 17787.9922 20715.6250 23489.3223 26801.5762 31134.2930 38484.3555 52663.3984 87895.5312 268884.9688 | lr 1.0e-04 | norm 142832.4844 | dt 9.338 +type train | step 151 | loss 3510.9583 5901.7764 11403.2910 17583.7266 20454.4980 22874.0078 26338.2891 30723.4453 37787.3281 51554.0547 86265.1250 269176.3125 | lr 1.0e-04 | norm 142723.1406 | dt 9.336 +type train | step 152 | loss 3489.6138 5867.3867 11377.9844 17670.0625 20510.0039 22870.5977 26335.8379 30788.2988 37869.3477 51894.0156 85932.4531 264911.0312 | lr 1.0e-04 | norm 142060.3281 | dt 9.326 +type train | step 153 | loss 3425.7305 5796.9658 11221.1865 17596.8867 20331.8320 22506.0859 26007.5977 30454.2832 37793.7266 51745.8125 86566.3359 281453.5938 | lr 1.0e-04 | norm 167792.1094 | dt 9.320 +type train | step 154 | loss 3365.5476 5689.6489 11137.9912 17463.2227 19925.5762 22453.7578 26090.1523 30612.1387 37890.6445 51768.2109 85882.7266 279173.5000 | lr 1.0e-04 | norm 160868.8906 | dt 9.285 +type train | step 155 | loss 3386.2349 5689.2148 11130.8320 17213.6602 19821.8574 22276.6973 25696.2559 29999.7402 36815.7734 50172.4570 84088.2500 261418.5000 | lr 1.0e-04 | norm 138085.7031 | dt 9.307 +type train | step 156 | loss 3363.4180 5672.7354 11055.3477 17125.2324 19786.4531 22437.4395 25669.2695 29999.6797 36985.1133 50940.9922 85256.7344 261846.2344 | lr 1.0e-04 | norm 141461.3594 | dt 9.297 +type train | step 157 | loss 3328.9272 5601.9600 11005.0674 16918.7188 19710.9316 22170.7363 25456.0391 29812.9688 36261.0117 49713.3438 82803.5234 258320.4688 | lr 1.0e-04 | norm 132018.0156 | dt 9.328 +type train | step 158 | loss 3313.3149 5594.9702 10960.6992 16954.4141 19781.4727 22032.9316 25287.4004 29512.6113 36291.7734 49983.5039 83589.6484 250421.3906 | lr 1.1e-04 | norm 131821.2500 | dt 9.313 +type train | step 159 | loss 3321.2810 5621.4551 10942.2568 17004.5312 19748.4961 22010.0234 25232.1211 29543.1270 36193.2617 49300.2969 82720.0156 250770.8125 | lr 1.1e-04 | norm 127694.8828 | dt 9.324 +type train | step 160 | loss 3275.5801 5504.9233 10791.0283 16866.3730 19229.2852 21586.3047 24965.9121 29049.0059 35790.1172 48813.1055 81837.1562 250915.3438 | lr 1.1e-04 | norm 131963.6562 | dt 9.316 +type train | step 161 | loss 3294.3406 5548.0879 10807.0586 16841.0078 19303.7344 21770.6973 25051.1973 29183.8945 35872.6328 49228.4766 82316.1562 250893.8281 | lr 1.1e-04 | norm 127008.1484 | dt 9.312 +type train | step 162 | loss 3259.1938 5478.8857 10735.3750 16624.7305 19186.2461 21684.9902 24827.1934 28740.5176 34986.1172 48077.1484 79942.4219 242848.6562 | lr 1.1e-04 | norm 119725.1797 | dt 9.327 +type train | step 163 | loss 3179.6885 5342.0156 10545.2158 16184.2822 18916.7461 21197.8770 24508.4141 28297.6074 34774.5586 47880.3867 79818.3516 245823.4531 | lr 1.1e-04 | norm 129928.8516 | dt 9.327 +type train | step 164 | loss 3199.9814 5404.2285 10568.8809 16563.4199 19047.7129 21332.6680 24449.8242 28462.3789 34812.5000 47828.5547 79817.9922 238770.0000 | lr 1.1e-04 | norm 122164.1172 | dt 9.340 +type train | step 165 | loss 3166.7000 5337.8584 10531.8252 16434.3164 18907.5312 21118.2070 24268.3027 28340.4648 34562.8906 47327.2695 78736.7031 240654.5938 | lr 1.1e-04 | norm 123953.3750 | dt 9.347 +type train | step 166 | loss 3149.9661 5320.2612 10466.1924 16323.6387 18745.3965 21017.2520 24069.9102 28150.8691 34504.6758 47469.0234 79566.4062 238017.6875 | lr 1.1e-04 | norm 118543.6719 | dt 9.343 +type train | step 167 | loss 3094.7214 5210.0132 10303.9062 16137.9238 18400.9902 20898.3594 23746.2715 27622.5547 33948.3672 46471.6602 77267.0938 228425.0312 | lr 1.1e-04 | norm 113111.9062 | dt 9.355 +type train | step 168 | loss 3116.4932 5262.2173 10376.2930 16025.5479 18404.7988 20873.1289 23918.6895 27671.5430 33860.9336 46506.5586 77585.6094 230392.2812 | lr 1.1e-04 | norm 116951.9375 | dt 9.334 +type train | step 169 | loss 3078.0564 5181.5054 10302.6738 15844.9131 18382.6543 20611.8145 23619.3418 27375.8965 33455.6836 46030.2383 76543.0625 230773.9375 | lr 1.1e-04 | norm 115692.8281 | dt 9.347 +type train | step 170 | loss 3064.7151 5170.1890 10218.5215 16015.2207 18307.0352 20647.4648 23648.1523 27526.4434 33340.5430 45659.4102 76159.9062 231689.2188 | lr 1.1e-04 | norm 112772.8906 | dt 9.329 +type train | step 171 | loss 3028.7476 5125.2734 10275.7471 15960.9043 18161.6973 20582.0957 23475.0176 27348.1816 33382.8633 45824.5508 76092.6875 222889.2344 | lr 1.1e-04 | norm 105468.1484 | dt 9.358 +type train | step 172 | loss 2981.2861 5036.4946 10140.7656 15631.1221 17912.2363 20234.8184 23231.9766 27124.2988 33146.8945 45699.1289 76208.7344 221721.0469 | lr 1.1e-04 | norm 109554.0078 | dt 9.337 +type train | step 173 | loss 2972.6343 4998.1250 10017.8604 15441.5078 17690.5391 19915.2988 22995.4961 26675.9023 32521.0352 44714.7344 74463.1406 216738.3906 | lr 1.2e-04 | norm 105999.3984 | dt 9.346 +type train | step 174 | loss 3049.4934 5128.4971 10107.9482 15519.1699 17803.0781 20076.9258 23108.0723 26899.4590 32548.1895 44569.7070 73939.5469 220429.0625 | lr 1.2e-04 | norm 105064.4766 | dt 9.354 +type train | step 175 | loss 2894.3923 4891.4438 9831.7158 15242.0352 17545.7695 19901.0762 22683.6895 26572.8125 32405.6738 44557.2773 73835.9688 218342.3438 | lr 1.2e-04 | norm 105428.9297 | dt 9.344 +type train | step 176 | loss 2896.9995 4905.8896 9845.9863 15324.6484 17443.1328 19966.9082 22774.0508 26502.0508 32429.3262 44615.0000 74379.7188 218274.6406 | lr 1.2e-04 | norm 103286.2969 | dt 9.354 +type train | step 177 | loss 2897.0701 4888.3438 9863.1475 15294.6729 17367.0234 19755.9707 22544.3633 26352.7031 31919.1191 43788.1055 72646.1719 211656.2500 | lr 1.2e-04 | norm 100602.1094 | dt 9.347 +type train | step 178 | loss 2842.2866 4817.9097 9788.2715 15054.6299 17158.0059 19527.1328 22485.8828 26235.0371 31891.2266 43854.8125 72728.6016 209744.0312 | lr 1.2e-04 | norm 97112.5391 | dt 9.347 +type train | step 179 | loss 2905.8201 4904.5366 9759.3633 15130.5713 17117.8359 19459.5039 22433.4375 26160.9590 31747.8008 43479.2305 72490.4375 218400.3438 | lr 1.2e-04 | norm 107166.8281 | dt 9.355 +type train | step 180 | loss 2836.6433 4800.5957 9677.6387 14966.2861 17115.2344 19377.9492 22076.3359 25700.1621 31186.2109 42639.3984 70702.5625 205345.4531 | lr 1.2e-04 | norm 97166.5938 | dt 9.699 +type train | step 181 | loss 2791.6973 4723.7612 9567.1934 14761.0273 16891.8926 19289.3633 21998.8535 25652.3984 31131.9160 42702.7266 70650.2188 205706.1719 | lr 1.2e-04 | norm 96865.3281 | dt 9.351 +type train | step 182 | loss 2793.8809 4719.0625 9526.5469 14823.3975 16840.3242 19164.3027 21840.3887 25568.3652 30966.7578 42430.2109 69769.2188 199605.0000 | lr 1.2e-04 | norm 93654.9922 | dt 9.347 +type train | step 183 | loss 2785.4238 4721.1973 9509.5684 14678.5410 16701.4805 19092.5508 21822.1172 25419.4102 30718.0918 42296.5820 69753.4766 207883.0625 | lr 1.2e-04 | norm 92985.5000 | dt 9.357 +type train | step 184 | loss 2757.0127 4640.2246 9404.4863 14575.3789 16514.8496 18719.2363 21534.1055 25022.5098 30120.9180 41432.6602 68422.5703 196481.8906 | lr 1.2e-04 | norm 95960.0859 | dt 9.362 +type train | step 185 | loss 2718.6538 4598.5449 9322.0957 14513.6719 16400.5605 18663.5996 21354.2031 24896.1445 30224.8711 41737.9414 69044.2422 196743.3750 | lr 1.2e-04 | norm 94475.6719 | dt 9.363 +type train | step 186 | loss 2789.1953 4703.0049 9398.1719 14438.6689 16442.0312 18728.9355 21324.3770 24937.3711 30056.7637 41040.5469 67716.7422 193842.4375 | lr 1.2e-04 | norm 89423.1797 | dt 9.363 +type train | step 187 | loss 2732.5740 4615.8018 9348.9287 14376.6387 16407.0000 18738.3242 21290.4629 24794.4883 29924.1094 41143.1016 67559.9766 188005.8125 | lr 1.2e-04 | norm 87513.5625 | dt 9.369 +type train | step 188 | loss 2673.5435 4542.8633 9210.3281 14228.9434 16237.0908 18511.6406 21078.3828 24613.8691 29833.2324 41335.5039 68147.9688 192212.1406 | lr 1.3e-04 | norm 90845.8203 | dt 9.374 +type train | step 189 | loss 2651.5659 4491.7480 9169.4346 14202.0459 16105.0957 18295.7676 21048.2363 24453.1738 29647.9941 40974.7227 67678.8984 188382.7812 | lr 1.3e-04 | norm 91662.5391 | dt 9.347 +type train | step 190 | loss 2612.5479 4424.4238 9084.2871 14071.7168 15908.3184 18165.7578 20711.2832 24160.5898 29405.9375 40496.9688 67104.3281 187040.2188 | lr 1.3e-04 | norm 90877.2578 | dt 9.377 +type train | step 191 | loss 2623.7085 4449.7256 9072.6221 14011.6348 15935.2949 18210.4492 20655.5352 24275.0859 29443.1699 40579.3828 67312.6094 188263.0781 | lr 1.3e-04 | norm 91881.0938 | dt 9.371 +type train | step 192 | loss 2599.4934 4403.9858 9015.0039 13952.4238 15859.6357 18109.9688 20612.8926 23987.0566 29056.9141 40086.8828 65821.4531 184869.4688 | lr 1.3e-04 | norm 94635.5156 | dt 9.371 +type train | step 193 | loss 2589.4329 4397.1587 8989.3926 13901.0488 15897.6309 18042.0098 20488.7012 23953.1250 28982.3672 40158.6797 66096.2109 180699.8125 | lr 1.3e-04 | norm 88149.4922 | dt 9.380 +type train | step 194 | loss 2574.0247 4367.5845 8930.0791 13772.5010 15670.7197 17760.4844 20353.1152 23773.5234 28706.1992 39547.3477 65165.8320 175762.3438 | lr 1.3e-04 | norm 85996.7109 | dt 9.387 +type train | step 195 | loss 2524.5830 4281.5527 8801.4316 13673.1699 15541.3818 17675.5977 20247.4727 23635.7070 28582.3496 39253.2031 64872.5391 178529.7188 | lr 1.3e-04 | norm 89336.3672 | dt 9.362 +type train | step 196 | loss 2532.3879 4302.0532 8852.8350 13631.4424 15496.1914 17648.3066 20114.5508 23584.2363 28440.7656 39279.0391 65091.2969 179918.9531 | lr 1.3e-04 | norm 88940.9531 | dt 9.360 +type train | step 197 | loss 2482.8408 4243.5723 8765.0859 13613.0508 15550.7178 17736.7090 20147.4316 23706.9395 28806.7188 39872.8516 65721.0625 185673.3750 | lr 1.3e-04 | norm 91706.5156 | dt 9.364 +type train | step 198 | loss 2491.7910 4235.7388 8725.4893 13489.8770 15445.8428 17522.7969 19870.4609 23149.6348 28069.4531 38757.1172 63805.4922 170045.6719 | lr 1.3e-04 | norm 87362.9375 | dt 9.380 +type train | step 199 | loss 2488.6589 4227.4302 8625.4336 13404.6748 15256.8633 17312.0391 19776.5215 23110.5195 27816.4297 38382.7383 63288.6094 169353.3594 | lr 1.3e-04 | norm 86033.4688 | dt 9.386 +type train | step 200 | loss 2495.8789 4235.9980 8606.5488 13342.6562 15172.6133 17318.9297 19678.6484 22950.6367 27633.5254 38011.7070 62811.0742 170230.9688 | lr 1.3e-04 | norm 88479.2969 | dt 9.390 +type train | step 201 | loss 2465.2832 4194.8125 8604.4336 13333.2090 15114.2090 17278.6172 19605.7148 22905.4355 27603.3105 37992.1133 62524.8008 165585.1406 | lr 1.3e-04 | norm 85717.9141 | dt 9.385 +type train | step 202 | loss 2530.8364 4290.4312 8738.8086 13441.8311 15324.2529 17502.3574 19799.1465 23132.8418 27695.8164 37988.8086 62135.0547 163189.5938 | lr 1.3e-04 | norm 82613.9453 | dt 9.416 +type train | step 203 | loss 2409.8049 4115.3086 8488.9678 13144.6992 14963.3828 17036.3223 19328.8613 22580.1797 27195.1172 37379.6367 61622.5195 170379.5938 | lr 1.4e-04 | norm 92917.3125 | dt 9.385 +type train | step 204 | loss 2428.6458 4141.0244 8461.0996 13053.2031 14872.1094 16938.5215 19357.9199 22716.0098 27362.6230 37674.4102 62188.8164 167045.9688 | lr 1.4e-04 | norm 87975.0234 | dt 9.342 +type train | step 205 | loss 2482.3748 4222.2222 8549.0186 13156.5771 14904.9805 17008.0898 19326.6953 22590.1855 27037.0508 37155.2617 61414.6367 163158.5156 | lr 1.4e-04 | norm 86238.0469 | dt 9.369 +type train | step 206 | loss 2390.7307 4078.7422 8437.1572 12988.4785 14788.3262 16829.8262 19076.5020 22383.0430 26912.8320 37069.5742 61063.1680 156432.5156 | lr 1.4e-04 | norm 85351.8125 | dt 9.417 +type train | step 207 | loss 2394.0691 4081.3323 8413.6104 13001.4580 14751.9707 16819.7910 19043.0020 22318.1973 26772.4336 36820.9492 60381.7188 158137.1875 | lr 1.4e-04 | norm 86626.6406 | dt 9.402 +type train | step 208 | loss 2416.6292 4129.7461 8423.0332 12965.8047 14824.9824 16877.4512 19163.7617 22450.0977 26766.4688 36729.4375 60106.1250 157896.0156 | lr 1.4e-04 | norm 84841.7734 | dt 9.418 +type train | step 209 | loss 2314.7700 3971.3489 8251.4492 12784.6035 14495.3984 16504.3477 18854.3320 22205.9883 26636.3809 36679.5781 60255.5586 155882.8750 | lr 1.4e-04 | norm 89608.0938 | dt 9.364 +type train | step 210 | loss 2312.1479 3973.4875 8233.7871 12744.5781 14484.4688 16516.7246 18760.4531 21930.1484 26446.1152 36440.3789 59955.8359 149839.0000 | lr 1.4e-04 | norm 88996.0703 | dt 9.403 +type train | step 211 | loss 2301.0171 3956.5151 8211.2148 12679.1211 14389.3193 16355.4004 18589.5156 21674.3828 26159.4297 35945.6328 58130.2500 146196.1719 | lr 1.4e-04 | norm 90184.0938 | dt 9.393 +type train | step 212 | loss 2272.8472 3903.6226 8139.6938 12609.8184 14335.4180 16345.7920 18560.4805 21634.3750 26072.4531 35892.6406 58737.5117 144766.3125 | lr 1.4e-04 | norm 87546.8438 | dt 9.409 +type train | step 213 | loss 2242.9653 3862.8137 8080.8159 12529.2295 14210.7637 16179.2061 18437.4844 21559.3613 26029.4453 35836.2891 58960.8438 145389.4219 | lr 1.4e-04 | norm 92207.5312 | dt 9.393 +type train | step 214 | loss 2265.7122 3905.4219 8107.5659 12523.9727 14267.6445 16288.6377 18571.8652 21771.3535 26070.7246 35875.1406 58890.0352 147115.0156 | lr 1.4e-04 | norm 88003.3984 | dt 9.412 +type train | step 215 | loss 2226.9180 3850.3398 8006.1890 12429.4238 14048.0684 16073.1172 18300.8438 21403.9414 25691.4453 35468.3750 58043.2969 142037.3281 | lr 1.4e-04 | norm 91443.1641 | dt 9.383 +type train | step 216 | loss 2230.0347 3844.2288 7999.1147 12407.0820 14084.0020 16054.8174 18255.4980 21412.5215 25690.5879 35374.2578 57953.9258 139773.7500 | lr 1.4e-04 | norm 90466.2109 | dt 9.417 +type train | step 217 | loss 2268.7158 3894.0278 8062.6797 12456.4062 14135.6113 16093.3096 18238.5176 21285.7441 25442.3379 34942.3203 57367.4688 137233.1406 | lr 1.4e-04 | norm 93166.1953 | dt 9.419 +type train | step 218 | loss 2203.8606 3798.4434 7918.6509 12240.1982 13913.4961 15828.0957 17988.6523 21056.9492 25365.9688 34904.0391 57257.8750 137423.5156 | lr 1.5e-04 | norm 91674.6094 | dt 9.429 +type train | step 219 | loss 2207.5051 3818.6328 7965.9634 12245.3604 13975.1680 15909.0410 18088.9414 21182.5039 25470.7129 35045.5000 57242.7461 135409.9844 | lr 1.5e-04 | norm 90144.7109 | dt 9.423 +type train | step 220 | loss 2193.7412 3808.7539 7879.4692 12215.7607 13870.7920 15798.4219 17984.1328 21029.0078 25300.0352 34956.0430 57344.1055 132856.8281 | lr 1.5e-04 | norm 92678.3359 | dt 9.400 +type train | step 221 | loss 2180.0479 3797.7883 7896.7466 12157.2832 13817.4795 15759.1787 18053.9961 21226.3633 25392.3164 34986.6875 57566.5625 146308.7188 | lr 1.5e-04 | norm 104405.3828 | dt 9.369 +type train | step 222 | loss 2149.8538 3736.3606 7847.0420 12129.5156 13790.1963 15781.6123 17918.7832 20959.9922 25182.8672 34697.7188 56756.4375 132334.3594 | lr 1.5e-04 | norm 93138.1797 | dt 9.400 +type train | step 223 | loss 2165.7153 3751.1062 7825.9688 12089.3242 13772.6719 15765.8760 17897.2012 20974.3965 24993.3594 34382.5430 55882.0742 134082.0312 | lr 1.5e-04 | norm 92593.0625 | dt 9.405 +type train | step 224 | loss 2100.6880 3653.3872 7688.0718 11928.2900 13592.6680 15432.7793 17544.0879 20559.2422 24674.5898 34114.8398 55813.7812 125478.2188 | lr 1.5e-04 | norm 94486.1953 | dt 9.416 +type train | step 225 | loss 2082.0337 3640.8049 7653.7773 11863.8027 13463.7363 15414.0664 17554.9121 20615.6367 24774.4980 34253.0625 55917.0781 128732.0547 | lr 1.5e-04 | norm 96422.4766 | dt 9.377 +type train | step 226 | loss 2077.9404 3623.2415 7617.0981 11804.7188 13435.4531 15407.8066 17543.2500 20598.7266 24740.9277 34136.6797 55899.5156 130739.7812 | lr 1.5e-04 | norm 96244.2969 | dt 9.387 +type train | step 227 | loss 2032.5072 3555.7485 7582.1206 11793.7949 13412.3965 15232.2383 17382.1133 20326.2070 24460.4492 33839.5273 55011.8008 121052.9453 | lr 1.5e-04 | norm 95766.1562 | dt 9.379 +type train | step 228 | loss 2018.3933 3540.7876 7519.7949 11731.5195 13318.9160 15187.8447 17287.9668 20263.8828 24343.7441 33683.2812 55091.0234 122390.5625 | lr 1.5e-04 | norm 99541.5625 | dt 9.375 +type train | step 229 | loss 2000.4154 3534.4180 7519.2578 11673.0615 13355.1914 15230.0547 17318.8223 20358.2461 24502.7773 34068.0078 55594.1445 124658.3359 | lr 1.5e-04 | norm 101927.8594 | dt 9.356 +type train | step 230 | loss 1969.3613 3481.1235 7443.0181 11577.6035 13219.3965 15017.5879 17149.7344 20052.4121 24078.0527 33434.1094 54865.6562 122466.6094 | lr 1.5e-04 | norm 103655.2344 | dt 9.402 +type train | step 231 | loss 1964.3005 3475.3027 7385.6992 11526.8418 13159.7090 14908.9883 17004.9688 19891.5586 23949.0840 33122.7383 54057.3945 119619.8359 | lr 1.5e-04 | norm 101761.4531 | dt 9.395 +type train | step 232 | loss 1968.6991 3466.1299 7403.9487 11534.1396 13158.9385 14969.2510 17000.0352 19906.3984 23886.9746 33092.8438 54191.0547 114475.7500 | lr 1.5e-04 | norm 97211.6719 | dt 9.389 +type train | step 233 | loss 1919.8881 3396.5239 7322.0845 11420.4355 13036.9180 14868.3721 16911.2773 19820.8828 23811.9238 33014.0664 53986.8555 114677.2422 | lr 1.6e-04 | norm 99216.1094 | dt 9.372 +type train | step 234 | loss 1943.3037 3426.3362 7339.1304 11420.0918 13029.7500 14870.1123 16879.5156 19828.5781 23852.7344 32935.0469 53788.7891 114518.8438 | lr 1.6e-04 | norm 93972.2500 | dt 9.398 +type train | step 235 | loss 1942.2017 3427.8071 7349.2842 11405.8389 13094.5508 14826.3770 16907.4043 19799.4238 23747.6250 32862.3945 53309.6758 112114.8828 | lr 1.6e-04 | norm 96716.8672 | dt 9.392 +type train | step 236 | loss 1945.0255 3438.1436 7307.4351 11342.6748 13020.3418 14786.4102 16845.4160 19782.0527 23694.7598 32711.3691 53175.8281 111767.5469 | lr 1.6e-04 | norm 97130.6328 | dt 9.408 +type train | step 237 | loss 1814.1501 3243.6646 7115.0659 11178.8174 12744.4941 14535.6045 16545.4395 19372.2246 23211.5742 32233.3711 52625.2812 110498.6328 | lr 1.6e-04 | norm 104681.5938 | dt 9.342 +type train | step 238 | loss 1848.6881 3325.9954 7157.5244 11229.7139 12783.7734 14651.4307 16616.7227 19574.4180 23530.4160 32698.2578 53373.7695 113491.3750 | lr 1.6e-04 | norm 105941.2422 | dt 9.346 +type train | step 239 | loss 1846.0436 3297.8831 7154.2104 11170.5342 12743.9102 14539.0898 16604.0352 19422.1719 23406.9434 32410.7891 52673.1641 108034.8906 | lr 1.6e-04 | norm 96279.0234 | dt 9.382 +type train | step 240 | loss 1834.4027 3269.7805 7086.4756 11151.0078 12699.0156 14463.3457 16589.6953 19500.2715 23450.6133 32614.4941 52667.2461 107683.3906 | lr 1.6e-04 | norm 96022.0156 | dt 9.378 +type train | step 241 | loss 1854.8389 3295.9219 7099.8047 11114.4844 12695.3545 14424.0078 16472.7988 19323.5020 23205.0977 32211.0996 52523.0820 105147.4453 | lr 1.6e-04 | norm 98255.7344 | dt 9.377 +type train | step 242 | loss 1838.8064 3273.9912 7094.7456 11074.9287 12664.5986 14441.7070 16505.8008 19339.2344 23167.0020 32029.0078 51906.1836 102578.2266 | lr 1.6e-04 | norm 93966.1875 | dt 9.386 +type train | step 243 | loss 1828.1810 3252.4966 7041.8877 10988.5557 12526.8271 14327.4053 16320.2988 19153.0762 22950.8184 31827.2207 51825.5352 101251.8281 | lr 1.6e-04 | norm 97521.2188 | dt 9.371 +type train | step 244 | loss 1828.7478 3255.2727 7038.7710 10997.2949 12541.0820 14327.6445 16346.6240 19134.1738 22883.7969 31731.5996 51569.0156 101181.7188 | lr 1.6e-04 | norm 92148.4766 | dt 9.371 +type train | step 245 | loss 1786.4304 3194.9688 6954.1616 10887.6133 12413.1904 14182.6543 16219.3135 18960.6719 22881.7129 31721.9355 51324.6484 100612.3750 | lr 1.6e-04 | norm 95304.8125 | dt 9.373 +type train | step 246 | loss 1778.9303 3187.1602 6927.7754 10857.2236 12409.8770 14233.4492 16176.7754 18961.4668 22721.5195 31505.5352 50773.2266 98098.7344 | lr 1.6e-04 | norm 91883.4609 | dt 9.369 +type train | step 247 | loss 1760.0647 3162.3726 6923.6450 10824.4883 12350.6611 14170.5459 16155.3887 18987.9590 22681.7617 31497.0762 51059.5312 98221.7188 | lr 1.6e-04 | norm 97668.5312 | dt 9.365 +type train | step 248 | loss 1742.6624 3132.2844 6860.3237 10742.8994 12281.4746 14031.8125 16099.9336 18825.4180 22616.2578 31434.2148 50884.6758 96517.6562 | lr 1.7e-04 | norm 96599.2188 | dt 9.354 +type train | step 249 | loss 1737.0084 3117.1697 6831.4033 10689.2607 12201.7871 13964.7383 15990.0811 18686.0742 22418.9746 31154.7812 50054.8555 94464.6094 | lr 1.7e-04 | norm 97309.9531 | dt 9.338 +type train | step 250 | loss 1733.2194 3107.9399 6808.7173 10633.4219 12193.6807 13931.7637 15936.3721 18683.6465 22352.6328 31016.6250 50022.5859 93083.8359 | lr 1.7e-04 | norm 94685.2188 | dt 9.328 +type train | step 251 | loss 1617.4113 3026.2644 6705.2944 10522.8418 12067.1426 13916.5801 15866.3145 18906.4805 22741.7930 31991.3262 52256.0547 112620.6953 | lr 1.7e-04 | norm 113612.7344 | dt 9.943 +type train | step 252 | loss 1636.7070 3025.9592 6701.1113 10520.1572 12056.3594 13892.5000 15898.8262 18811.9883 22583.8281 31748.2520 51531.3438 106454.2656 | lr 1.7e-04 | norm 112781.2812 | dt 9.941 +type train | step 253 | loss 1692.1337 3044.4944 6711.5898 10507.6973 12008.8730 13746.2881 15702.9336 18423.8789 22111.8867 30734.8223 49492.9141 90520.5625 | lr 1.7e-04 | norm 94023.8438 | dt 10.004 +type train | step 254 | loss 1692.2938 3038.6484 6632.4585 10382.3926 11909.9082 13687.7803 15595.4014 18485.4648 22151.7188 30729.1348 49621.0195 91951.5469 | lr 1.7e-04 | norm 96555.9609 | dt 9.996 +type train | step 255 | loss 1676.8132 3012.6919 6598.6113 10325.2422 11808.6494 13505.7236 15423.2598 18104.9785 21744.0547 30164.5879 48393.3984 87151.1953 | lr 1.7e-04 | norm 94257.7031 | dt 9.993 +type train | step 256 | loss 1637.2386 2978.1362 6593.1714 10321.4941 11863.1426 13645.4854 15589.7842 18297.1230 22028.5371 30621.6367 48923.4062 90027.4688 | lr 1.7e-04 | norm 84515.2500 | dt 9.998 +type train | step 257 | loss 1654.6837 3000.7544 6580.2388 10314.0713 11831.6484 13613.7314 15508.5723 18280.3008 21788.5078 30229.5723 48397.1836 86344.7266 | lr 1.7e-04 | norm 87099.8594 | dt 10.012 +type train | step 258 | loss 1637.5005 2971.1384 6563.7266 10264.3271 11796.6436 13488.6104 15315.0059 18012.6094 21547.0371 29911.1328 47791.7930 84382.7109 | lr 1.7e-04 | norm 87271.6719 | dt 10.019 +type train | step 259 | loss 1642.1278 2974.1067 6520.1006 10216.7930 11726.8467 13417.7812 15273.5391 17935.5547 21470.2109 29714.9297 47431.4062 82801.6328 | lr 1.7e-04 | norm 87172.6016 | dt 10.012 +type train | step 260 | loss 1623.6284 2944.0781 6472.0874 10153.9336 11644.2207 13315.0742 15223.5762 17871.0840 21419.3496 29767.7129 47332.1523 80984.6797 | lr 1.7e-04 | norm 85337.6641 | dt 10.019 +type train | step 261 | loss 1640.0105 2964.9417 6509.7964 10149.5762 11666.0605 13393.1182 15294.4229 18046.1562 21476.2246 29778.4414 47486.9453 83777.1719 | lr 1.7e-04 | norm 82317.4297 | dt 10.001 +type train | step 262 | loss 1631.5454 2956.1111 6483.1777 10157.5693 11675.2207 13330.6396 15218.8369 17854.5508 21412.5469 29537.7383 46975.6094 79521.5781 | lr 1.7e-04 | norm 79801.5234 | dt 9.996 +type train | step 263 | loss 1576.0228 2864.8167 6398.4961 9984.9277 11529.0703 13132.0459 15025.5273 17741.5781 21290.3438 29550.4609 46853.1133 79150.0781 | lr 1.8e-04 | norm 83703.3750 | dt 9.968 +type train | step 264 | loss 1622.2460 2954.0151 6446.7305 10028.0752 11571.3115 13303.1865 15212.7285 17946.4375 21459.0605 29720.1367 47095.0391 83876.3516 | lr 1.8e-04 | norm 75429.8516 | dt 9.986 +type train | step 265 | loss 1606.4395 2913.4790 6393.0195 9998.6953 11513.3154 13203.8008 15072.6582 17694.9551 21110.5020 29044.4043 46093.5742 77571.1719 | lr 1.8e-04 | norm 80916.5000 | dt 9.990 +type train | step 266 | loss 1560.7660 2850.9670 6325.4204 9889.5029 11407.8613 13020.3203 14925.4971 17449.4668 20922.9180 28918.9219 45844.1953 76305.6719 | lr 1.8e-04 | norm 78854.5547 | dt 9.980 +type train | step 267 | loss 1624.6880 2931.0449 6407.8125 9984.4199 11478.5459 13163.6738 15014.2959 17582.6855 20947.4199 28801.2852 45525.8711 74275.9844 | lr 1.8e-04 | norm 80979.4609 | dt 9.987 +type train | step 268 | loss 1536.7119 2795.3677 6227.5005 9719.6855 11190.7852 12805.1396 14646.4727 17208.5801 20649.9336 28612.4141 44976.0938 72362.1641 | lr 1.8e-04 | norm 77415.2656 | dt 9.978 +type train | step 269 | loss 1494.6780 2748.8254 6171.6631 9659.2012 11098.5752 12685.0254 14604.9561 17090.3984 20613.6621 28736.1484 45338.1680 74557.2031 | lr 1.8e-04 | norm 74319.3594 | dt 9.962 +type train | step 270 | loss 1564.0210 2844.9727 6233.5884 9734.0625 11220.2207 12883.9277 14805.7510 17454.9531 21075.5664 29063.0703 45396.6641 76620.1641 | lr 1.8e-04 | norm 67687.1641 | dt 9.972 +type train | step 271 | loss 1587.5709 2875.7129 6249.8770 9731.6387 11205.6084 12899.5635 14717.4990 17209.1191 20573.4121 28230.2871 44755.1055 72261.4688 | lr 1.8e-04 | norm 74683.2812 | dt 9.958 +type train | step 272 | loss 1456.3959 2675.0408 6013.2090 9435.7402 10867.4453 12490.0498 14359.4541 16830.1465 20296.6172 28293.7754 44743.3906 73489.9766 | lr 1.8e-04 | norm 80641.4609 | dt 9.927 +type train | step 273 | loss 1491.9990 2738.9851 6075.7075 9454.9531 10934.3398 12574.8496 14422.6035 16936.1895 20409.7676 28274.5312 44555.1367 72700.1406 | lr 1.8e-04 | norm 72155.5391 | dt 9.936 +type train | step 274 | loss 1484.8734 2729.4294 6067.2241 9397.7197 10916.3809 12525.8037 14372.2363 16786.0430 20289.0781 28083.1855 43880.7852 70233.7734 | lr 1.8e-04 | norm 69157.8125 | dt 9.950 +type train | step 275 | loss 1491.2526 2729.3115 6023.7690 9327.1855 10837.0117 12546.1201 14380.0791 16926.0391 20308.1836 28215.4238 44208.9219 72303.9062 | lr 1.8e-04 | norm 73943.7109 | dt 9.925 +type train | step 276 | loss 1449.0692 2670.1970 5980.8667 9310.5430 10816.8613 12413.7607 14244.2275 16661.4883 20088.3965 27720.4590 43190.3281 69389.5781 | lr 1.8e-04 | norm 66264.9062 | dt 9.919 +type train | step 277 | loss 1412.4506 2618.9360 5902.7681 9207.1123 10693.2949 12261.4883 14122.2510 16522.4473 19880.7520 27607.4883 43087.3555 69200.4375 | lr 1.8e-04 | norm 65458.8594 | dt 9.909 +type train | step 278 | loss 1434.1166 2641.6008 5927.3350 9151.3105 10659.5996 12213.5635 14066.2695 16527.6543 19817.2539 27499.0352 43058.2227 69331.8828 | lr 1.9e-04 | norm 67289.1719 | dt 9.898 +type train | step 279 | loss 1423.2051 2635.2896 5889.2070 9078.0381 10611.6299 12155.7920 14005.7324 16342.3281 19789.9512 27455.6836 42737.9844 67214.9219 | lr 1.9e-04 | norm 64462.4023 | dt 9.903 +type train | step 280 | loss 1415.9342 2619.7651 5834.6538 9020.3193 10581.5811 12066.3066 13959.6807 16315.1680 19663.5703 27225.4199 42383.9492 67962.9766 | lr 1.9e-04 | norm 61816.4062 | dt 9.893 +type train | step 281 | loss 1401.6495 2599.2856 5808.0913 8931.4951 10492.8525 11979.5947 13849.7686 16258.7500 19630.7168 27202.1016 42076.9805 65789.8281 | lr 1.9e-04 | norm 60362.6523 | dt 9.896 +type train | step 282 | loss 1396.8173 2590.1416 5790.8521 8869.2480 10484.6914 11890.9717 13751.2715 16139.6816 19464.1191 27022.3594 41927.4766 65015.8242 | lr 1.9e-04 | norm 60958.1016 | dt 9.896 +type train | step 283 | loss 1390.1224 2575.9666 5761.3838 8821.3828 10452.2021 11870.7871 13697.2529 16115.9043 19447.3359 26998.8223 41692.2656 64790.4492 | lr 1.9e-04 | norm 58849.8984 | dt 9.892 +type train | step 284 | loss 1373.9561 2554.3020 5719.0757 8746.5625 10390.4111 11822.9629 13666.6768 16023.3604 19355.0723 26732.9121 41185.4297 64521.7773 | lr 1.9e-04 | norm 57555.4570 | dt 9.896 +type train | step 285 | loss 1366.1309 2540.8018 5664.5903 8659.3408 10292.2764 11662.7979 13501.0303 15892.2461 19151.7715 26424.0391 40675.3594 63091.0625 | lr 1.9e-04 | norm 59705.3203 | dt 9.884 +type train | step 286 | loss 1343.2661 2503.7107 5579.3335 8558.6504 10234.4502 11618.4541 13461.0781 15871.2002 19068.7695 26296.4492 40154.5938 63197.4883 | lr 1.9e-04 | norm 58794.7891 | dt 9.877 +type train | step 287 | loss 1363.5056 2532.9609 5594.5244 8537.4961 10197.5010 11508.5762 13379.4180 15749.7070 19003.0234 26210.2031 40193.7109 61836.5117 | lr 1.9e-04 | norm 55540.9961 | dt 9.884 +type train | step 288 | loss 1340.1108 2498.7886 5544.3438 8435.1055 10136.1816 11451.6572 13270.4316 15656.4082 18849.1523 25962.5859 39832.2773 60805.6523 | lr 1.9e-04 | norm 56047.2891 | dt 9.881 +type train | step 289 | loss 1379.7759 2554.5085 5582.7139 8473.6533 10209.9033 11484.0234 13273.6270 15709.3066 18792.9180 25910.6641 39735.9648 60086.8555 | lr 1.9e-04 | norm 55626.0156 | dt 9.888 +type train | step 290 | loss 1327.4313 2476.9050 5492.4614 8310.5439 10020.2646 11323.9238 13088.7939 15547.3809 18795.4844 26006.1250 40064.7031 62484.0742 | lr 1.9e-04 | norm 53856.7617 | dt 9.877 +type train | step 291 | loss 1286.1758 2412.3887 5396.1357 8168.3623 9903.2607 11179.4512 12971.4355 15364.4502 18596.9258 25702.6445 39543.3398 61500.6133 | lr 1.9e-04 | norm 54823.7578 | dt 9.857 +type train | step 292 | loss 1324.2048 2466.3242 5442.1602 8175.1997 9917.5205 11168.1104 12972.7900 15379.6475 18463.7812 25336.0605 38793.3867 58311.4648 | lr 1.9e-04 | norm 56278.9336 | dt 9.866 +type train | step 293 | loss 1304.7196 2454.2466 5415.4482 8123.7100 9898.0830 11073.0742 12940.3525 15410.1797 18560.9707 25632.8008 39891.5938 63261.6484 | lr 2.0e-04 | norm 57349.4648 | dt 9.862 +type train | step 294 | loss 1300.2185 2451.9661 5406.1812 8101.8008 9873.9336 11061.7275 12957.4473 15489.5195 18629.6191 25916.0137 40659.2227 65491.0703 | lr 2.0e-04 | norm 62446.0820 | dt 9.848 +type train | step 295 | loss 1290.0074 2415.5735 5328.4844 7876.9756 9676.0889 10891.3174 12737.8457 15222.6631 18371.3633 25416.8906 39027.1992 61040.3164 | lr 2.0e-04 | norm 52848.9336 | dt 9.847 +type train | step 296 | loss 1275.9355 2390.8442 5330.3042 7800.2280 9584.5186 10723.8760 12528.9629 14895.9590 17983.0332 24756.5664 37991.3477 57533.6016 | lr 2.0e-04 | norm 52963.6562 | dt 9.860 +type train | step 297 | loss 1255.5948 2371.2803 5244.0986 7716.5117 9511.1006 10710.6250 12552.2422 14848.5244 18011.1172 24826.6289 37963.3984 57880.7422 | lr 2.0e-04 | norm 50254.1953 | dt 9.862 +type train | step 298 | loss 1278.7435 2400.4478 5257.4312 7706.8818 9489.1357 10684.9229 12577.5410 14885.0635 17996.6211 24792.8125 38012.4023 58651.3789 | lr 2.0e-04 | norm 48572.5273 | dt 9.850 +type train | step 299 | loss 1219.6700 2313.2344 5150.8257 7559.9438 9372.4365 10537.5137 12365.5225 14593.7627 17771.1328 24500.9180 37336.3555 57159.0234 | lr 2.0e-04 | norm 52890.8125 | dt 9.864 +type train | step 300 | loss 1335.5986 2492.0288 5314.8096 7729.0049 9505.0020 10772.2246 12569.7930 15017.3906 18117.7852 24671.0703 37717.3125 59212.1016 | lr 2.0e-04 | norm 54966.5039 | dt 9.866 +type train | step 301 | loss 1344.7289 2500.7019 5291.6567 7689.7490 9455.3760 10704.2051 12477.2881 14928.6699 17936.6055 24453.6523 37487.4922 58656.9922 | lr 2.0e-04 | norm 61647.0898 | dt 9.866 +type train | step 302 | loss 1340.1515 2496.3982 5264.2031 7642.0430 9367.2705 10661.8252 12411.4404 14791.5371 17774.7305 24138.5840 36883.9766 57219.7344 | lr 2.0e-04 | norm 61576.6602 | dt 9.886 +type train | step 303 | loss 1340.0542 2494.4070 5263.7041 7579.0615 9252.8896 10607.6758 12346.8799 14786.3584 17756.4082 24203.2188 36875.6953 57082.4961 | lr 2.0e-04 | norm 57429.7109 | dt 9.867 +type train | step 304 | loss 1344.2340 2504.3916 5209.9683 7521.5117 9191.9844 10588.8076 12295.2617 14775.3477 17620.1875 23961.0117 36302.1719 56153.0625 | lr 2.0e-04 | norm 55884.1641 | dt 9.845 +type train | step 305 | loss 1232.7598 2324.8936 5027.7866 7261.4609 8976.9150 10199.3975 11937.8770 14199.5732 17217.3945 23777.9180 36198.0703 54945.5859 | lr 2.0e-04 | norm 47693.9609 | dt 9.865 +type train | step 306 | loss 1231.2145 2324.7593 4993.3433 7222.2915 8902.3730 10205.9170 11940.5488 14251.3330 17288.6875 23910.8574 36344.0312 59084.0352 | lr 2.0e-04 | norm 48285.1992 | dt 9.847 +type train | step 307 | loss 1205.2084 2284.8281 4911.9072 7114.3901 8766.6514 10012.2266 11691.8408 13937.9297 17027.4238 23765.1367 36221.1953 55846.7500 | lr 2.0e-04 | norm 51324.0781 | dt 9.836 +type train | step 308 | loss 1181.1926 2245.5015 4851.5137 7036.0527 8653.6738 9965.5947 11615.4229 13848.9219 16909.7559 23470.2520 35792.3242 55515.3398 | lr 2.1e-04 | norm 55290.6406 | dt 9.828 +type train | step 309 | loss 1193.8281 2265.5383 4853.0693 7018.5439 8619.1582 9894.7236 11473.7744 13707.7461 16818.7695 23427.0898 35783.0898 54739.8281 | lr 2.1e-04 | norm 50292.1445 | dt 9.828 +type train | step 310 | loss 1197.4529 2265.9541 4831.5269 6981.7607 8558.3262 9845.3018 11441.9102 13730.4941 16752.8047 23231.2578 35420.4023 54620.2617 | lr 2.1e-04 | norm 49473.4766 | dt 9.811 +type train | step 311 | loss 1171.9829 2219.7202 4753.3687 6885.1875 8422.1992 9717.5879 11295.9688 13545.1328 16601.8262 23075.1016 35168.4180 53769.0391 | lr 2.1e-04 | norm 49654.6445 | dt 9.828 +type train | step 312 | loss 1836.2866 3424.5205 6199.8589 8523.2607 10194.8291 11812.2051 13727.3164 16504.9570 19759.5840 26042.2402 37012.5625 53783.6523 | lr 2.1e-04 | norm 78725.8203 | dt 9.831 +type train | step 313 | loss 1548.0865 2922.0100 5564.5029 7806.4722 9460.6123 10914.1318 12700.0195 15322.7734 18569.8809 24967.3574 36409.4141 54075.0391 | lr 2.1e-04 | norm 59848.9141 | dt 9.854 +type train | step 314 | loss 1110.1372 2127.1240 4595.5972 6693.0703 8246.7666 9498.7500 11081.5645 13339.5957 16544.9961 23120.3164 35519.9844 55663.1406 | lr 2.1e-04 | norm 56592.5508 | dt 9.824 +type train | step 315 | loss 1163.2161 2214.2290 4673.7783 6742.0557 8282.0430 9510.0234 11070.8652 13254.3662 16349.9756 22641.5098 34464.6094 52077.8281 | lr 2.1e-04 | norm 46437.9141 | dt 9.839 +type train | step 316 | loss 1133.7893 2168.5103 4606.7188 6644.1040 8166.5723 9375.2227 10985.4238 13186.1719 16372.7549 22738.6094 34576.4688 53148.4219 | lr 2.1e-04 | norm 47367.4180 | dt 9.849 +type train | step 317 | loss 1135.0471 2176.0862 4599.5552 6595.0137 8120.8511 9287.1436 10902.4082 13066.3379 16179.2764 22468.4707 34139.2422 52438.5547 | lr 2.1e-04 | norm 48121.3516 | dt 9.823 +type train | step 318 | loss 1149.6989 2190.0847 4603.8770 6585.8311 8115.4624 9252.0547 10860.9688 12986.5137 16086.6582 22254.2422 33845.1914 50596.0195 | lr 2.1e-04 | norm 43889.9453 | dt 9.871 +type train | step 319 | loss 1124.3610 2150.8591 4545.1416 6511.3457 8044.1035 9161.7041 10804.6191 12943.6641 16068.3613 22266.5117 33728.3164 51100.2461 | lr 2.1e-04 | norm 45428.8203 | dt 9.853 +type train | step 320 | loss 1125.0646 2150.2600 4502.3232 6470.2974 7968.3208 9051.2715 10680.3320 12806.4307 15909.2148 22138.8203 33923.7188 52137.7773 | lr 2.1e-04 | norm 45486.8281 | dt 9.845 +type train | step 321 | loss 1111.1779 2128.1082 4472.7100 6401.8076 7901.1343 8964.2979 10575.7148 12693.7617 15791.4707 21940.0527 33390.6328 50640.2578 | lr 2.1e-04 | norm 44045.6016 | dt 9.844 +type train | step 322 | loss 1120.9958 2142.4321 4471.1436 6401.3848 7879.2417 8931.9619 10543.1973 12662.4102 15748.5977 21857.4648 33229.6719 50197.3516 | lr 2.1e-04 | norm 42896.1992 | dt 9.839 +type train | step 323 | loss 1100.1655 2109.1831 4415.8994 6330.1353 7797.3975 8844.7705 10443.2715 12600.8779 15643.2920 21722.8379 33013.3242 50079.1992 | lr 2.2e-04 | norm 43479.9688 | dt 9.854 +type train | step 324 | loss 1126.7374 2151.3982 4441.5962 6360.5542 7807.0483 8872.4521 10476.1602 12660.6406 15667.3408 21681.1992 33043.9336 51110.6094 | lr 2.2e-04 | norm 46354.9648 | dt 9.825 +type train | step 325 | loss 1124.0469 2148.1270 4413.1172 6327.0806 7767.2266 8815.8535 10425.0078 12616.8154 15648.9580 21750.3223 33115.9727 51267.3281 | lr 2.2e-04 | norm 43292.0156 | dt 9.842 +type train | step 326 | loss 1086.5569 2083.9248 4311.9292 6209.4751 7628.7080 8651.8926 10239.6787 12372.2666 15363.4980 21380.3594 32373.8438 49289.6055 | lr 2.2e-04 | norm 43176.2383 | dt 9.833 +type train | step 327 | loss 1099.4658 2106.9668 4318.2363 6186.8496 7587.5820 8607.0596 10193.4395 12364.4121 15299.4004 21360.1152 32632.0137 49465.5547 | lr 2.2e-04 | norm 43029.5703 | dt 9.842 +type train | step 328 | loss 1087.6155 2087.3892 4287.4116 6163.4932 7554.6714 8591.8838 10196.4521 12351.3926 15318.4648 21292.6484 32346.2441 49629.7812 | lr 2.2e-04 | norm 42369.0039 | dt 9.846 +type train | step 329 | loss 1070.5522 2055.3069 4231.1816 6077.6050 7409.5415 8462.8447 10048.3467 12219.1416 15210.6445 21289.0020 32333.5957 49366.8594 | lr 2.2e-04 | norm 41886.2656 | dt 9.839 +type train | step 330 | loss 1071.0148 2055.8601 4205.8896 6036.3726 7329.3140 8409.7822 9990.6318 12162.6113 15094.7061 21119.1816 32137.0254 49139.7617 | lr 2.2e-04 | norm 41216.7266 | dt 9.837 +type train | step 331 | loss 1071.5120 2052.6582 4167.6748 5992.9507 7252.9399 8362.7432 9924.4766 12095.1172 14988.0723 20953.8711 31888.7168 49004.5078 | lr 2.2e-04 | norm 40076.1484 | dt 9.832 +type train | step 332 | loss 1086.1321 2079.2764 4161.3247 6017.7051 7260.1113 8383.1211 9941.6631 12114.2197 14988.7500 20872.1367 31633.5410 48357.3594 | lr 2.2e-04 | norm 40752.6172 | dt 9.819 +type train | step 333 | loss 1039.2487 2002.9089 4076.9001 5894.8979 7128.6772 8257.0635 9818.5293 11958.9346 14891.5332 20843.2539 31449.5898 48163.0273 | lr 2.2e-04 | norm 40202.4453 | dt 9.856 +type train | step 334 | loss 1038.3112 1997.7483 4026.4746 5845.2339 7041.9409 8175.2231 9733.3232 11856.1299 14748.3271 20657.1016 31440.6270 48343.5820 | lr 2.2e-04 | norm 40659.2500 | dt 9.832 +type train | step 335 | loss 1048.2960 2015.3197 4021.9219 5846.6299 7024.6660 8169.3481 9707.4629 11849.7031 14664.6846 20544.7441 31268.0195 48984.6055 | lr 2.2e-04 | norm 40962.5391 | dt 9.823 +type train | step 336 | loss 1042.2562 2006.2988 3989.0898 5791.2012 6959.5635 8096.0015 9641.7676 11750.5693 14607.5996 20443.3008 31054.7207 47729.4844 | lr 2.2e-04 | norm 38816.3086 | dt 9.838 +type train | step 337 | loss 1026.4340 1973.9865 3930.4441 5720.5708 6869.2979 8015.4604 9542.3691 11641.9482 14419.6514 20194.5820 30776.4922 47711.8320 | lr 2.2e-04 | norm 42543.8359 | dt 9.810 +type train | step 338 | loss 1018.2385 1968.5532 3903.7769 5685.9858 6837.0400 7960.8213 9465.9922 11512.0146 14293.9365 20047.8789 30532.5137 47756.4922 | lr 2.3e-04 | norm 42161.7070 | dt 9.836 +type train | step 339 | loss 1052.1791 2021.9402 3954.2104 5739.0933 6888.6318 8055.1899 9623.3105 11826.9766 14679.1377 20465.4531 30967.1543 48137.0547 | lr 2.3e-04 | norm 38081.1719 | dt 9.845 +type train | step 340 | loss 1031.8070 1986.8896 3900.1907 5669.3779 6820.2334 7957.4893 9487.0078 11580.6289 14428.5479 20118.0566 30417.5781 47450.8672 | lr 2.3e-04 | norm 38513.1523 | dt 9.851 +type train | step 341 | loss 1007.8290 1938.7701 3833.9148 5582.9180 6725.2153 7867.2427 9383.4375 11467.6348 14267.2568 20020.7109 30543.7773 48178.0469 | lr 2.3e-04 | norm 39104.7930 | dt 9.835 +type train | step 342 | loss 988.3149 1910.1119 3773.8276 5489.7202 6625.3262 7750.7437 9244.5771 11277.3271 14095.3682 19770.7891 30059.6074 47088.3828 | lr 2.3e-04 | norm 38211.1367 | dt 9.817 +type train | step 343 | loss 1024.3412 1974.6178 3857.1406 5585.2441 6723.9722 7871.9404 9432.3369 11556.7373 14378.5088 20030.3867 30289.0469 48022.8906 | lr 2.3e-04 | norm 39933.3984 | dt 9.847 +type train | step 344 | loss 978.7471 1889.0627 3733.8049 5413.9961 6521.1392 7604.0654 9091.7803 11075.2637 13869.9443 19496.2344 29643.0039 47087.9062 | lr 2.3e-04 | norm 41971.1797 | dt 9.808 +type train | step 345 | loss 980.6149 1903.0491 3747.5488 5420.6196 6536.3291 7639.2505 9153.2266 11173.5801 14073.6523 19816.6602 30239.4668 48094.8477 | lr 2.3e-04 | norm 39003.5352 | dt 9.837 +type train | step 346 | loss 970.0038 1873.9030 3691.4712 5336.3979 6437.3970 7503.1216 8979.4580 10952.9932 13807.5986 19398.1426 29530.6836 45616.7031 | lr 2.3e-04 | norm 38381.1523 | dt 9.819 +type train | step 347 | loss 1000.2186 1918.3235 3714.9919 5350.8276 6433.4927 7539.9033 9020.0605 11036.8438 13825.8975 19350.6641 29441.0469 46764.5625 | lr 2.3e-04 | norm 37309.0820 | dt 9.824 +type train | step 348 | loss 963.7605 1869.8004 3667.5063 5286.6548 6377.0723 7448.4404 8926.3604 10893.9062 13746.5596 19341.7383 29554.7520 46290.6680 | lr 2.3e-04 | norm 37689.9609 | dt 9.828 +type train | step 349 | loss 972.5652 1878.9208 3662.5503 5269.8223 6348.4814 7420.0894 8882.2012 10815.6748 13633.1592 19112.3418 29098.2930 45028.7734 | lr 2.3e-04 | norm 35937.6250 | dt 9.830 +type train | step 350 | loss 953.2859 1845.7655 3600.3770 5194.8047 6277.8203 7353.1396 8820.3447 10796.9121 13551.7842 19044.1992 28861.6172 45556.5742 | lr 2.3e-04 | norm 37718.0508 | dt 9.823 +type train | step 351 | loss 946.3491 1828.9869 3561.2073 5126.5684 6188.1904 7260.1826 8725.9248 10705.8838 13502.0957 19122.3887 29083.0996 45967.6289 | lr 2.3e-04 | norm 37342.9219 | dt 9.818 +type train | step 352 | loss 1030.5479 1981.9360 3753.4910 5367.7158 6457.9736 7597.3472 9135.6396 11196.6846 13939.4766 19599.4453 29669.3125 48248.6836 | lr 2.3e-04 | norm 52385.5234 | dt 9.844 +type train | step 353 | loss 962.0031 1856.7026 3570.7280 5133.5879 6204.9302 7289.0278 8752.3057 10707.1084 13463.1377 18906.0430 28661.9297 44846.3750 | lr 2.4e-04 | norm 34559.7891 | dt 9.846 +type train | step 354 | loss 932.5591 1796.5282 3473.9180 5001.9634 6055.2324 7118.0630 8561.0156 10510.6074 13255.3457 18613.0469 28370.4902 44215.2539 | lr 2.4e-04 | norm 36868.1992 | dt 9.822 +type train | step 355 | loss 944.1174 1818.3193 3473.7441 5013.3657 6043.1211 7104.9902 8546.4844 10516.9883 13212.9521 18579.0547 28370.1875 44569.2539 | lr 2.4e-04 | norm 35648.6797 | dt 9.821 +type train | step 356 | loss 933.4724 1806.0310 3448.1553 4952.7002 5996.9639 7032.5317 8452.0645 10367.7920 13111.7891 18498.2773 28228.6074 44033.0156 | lr 2.4e-04 | norm 35175.1367 | dt 9.828 +type train | step 357 | loss 945.7487 1826.1215 3464.6958 5004.6567 6057.3491 7133.8926 8535.5693 10456.1523 13148.7158 18518.1484 28383.7031 45590.5273 | lr 2.4e-04 | norm 37514.8594 | dt 9.826 +type train | step 358 | loss 915.0636 1765.7451 3361.3418 4857.5771 5887.8022 6911.3916 8319.5908 10208.1445 12931.9922 18245.6875 27715.5938 43322.6523 | lr 2.4e-04 | norm 36609.2305 | dt 9.826 +type train | step 359 | loss 897.6227 1731.0024 3314.2227 4806.6738 5818.9111 6858.4541 8277.0654 10171.7939 12881.5020 18198.5176 27789.6055 43578.8867 | lr 2.4e-04 | norm 34137.4805 | dt 9.818 +type train | step 360 | loss 906.6049 1754.8218 3310.2871 4786.5210 5791.8511 6822.7241 8215.6025 10107.9219 12780.1133 18097.8359 27797.4199 43960.2031 | lr 2.4e-04 | norm 37647.7461 | dt 9.829 +type train | step 361 | loss 884.8926 1716.5161 3255.6077 4718.9834 5721.8223 6757.0444 8170.0225 10084.3262 12806.5684 18176.6426 28012.6016 44689.2852 | lr 2.4e-04 | norm 36815.2461 | dt 9.823 +type train | step 362 | loss 850.0650 1674.7157 3204.9714 4625.9146 5634.1348 6593.0103 7999.4756 9872.2852 12748.6875 18423.1211 28649.8086 45649.1641 | lr 2.4e-04 | norm 64003.7969 | dt 9.825 +type train | step 363 | loss 888.3126 1719.0315 3240.7859 4690.7373 5697.7656 6696.7871 8100.0166 10003.6484 12732.3105 18135.5586 28013.8301 44437.3750 | lr 2.4e-04 | norm 36153.3516 | dt 9.829 +type train | step 364 | loss 980.4031 1879.2712 3390.0840 4844.5420 5860.1274 6929.2505 8359.3652 10342.8164 12947.9346 18103.3750 27350.2422 43083.3281 | lr 2.4e-04 | norm 35805.9375 | dt 9.835 +type train | step 365 | loss 918.5457 1769.1331 3264.4988 4686.9282 5694.9756 6723.2524 8122.9927 10016.6875 12632.1904 17868.1445 27333.7383 44096.5469 | lr 2.4e-04 | norm 36685.2344 | dt 9.824 +type train | step 366 | loss 866.6854 1680.3240 3148.3806 4538.1978 5531.5342 6523.4443 7906.3525 9764.7344 12428.1133 17598.4551 26937.8008 42808.1016 | lr 2.4e-04 | norm 34544.3242 | dt 9.827 +type train | step 367 | loss 854.4107 1663.3567 3126.4297 4546.6411 5560.9907 6582.3945 7980.4878 9837.7393 12510.6973 17829.7070 27341.6777 44594.3047 | lr 2.4e-04 | norm 42603.4883 | dt 9.826 +type train | step 368 | loss 875.9450 1690.4137 3121.9277 4482.3252 5452.1968 6432.8916 7783.0093 9623.2715 12224.2812 17264.8828 26471.3750 42121.8164 | lr 2.5e-04 | norm 34696.6602 | dt 9.816 +type train | step 369 | loss 893.3572 1722.1719 3155.2314 4519.0405 5488.7314 6474.0557 7825.1382 9664.4561 12278.0928 17402.9355 26734.0371 42660.5234 | lr 2.5e-04 | norm 35853.6094 | dt 9.816 +type train | step 370 | loss 861.6616 1660.0234 3072.2786 4421.7148 5384.2817 6400.5347 7765.1055 9650.9277 12261.0762 17425.7832 26791.2480 43738.2539 | lr 2.5e-04 | norm 33510.0547 | dt 9.812 +type train | step 371 | loss 877.8807 1690.9363 3078.1953 4427.5811 5375.0298 6394.5259 7754.8252 9657.8975 12265.9307 17448.0234 26866.5527 44028.8164 | lr 2.5e-04 | norm 35360.7461 | dt 9.812 +type train | step 372 | loss 853.8229 1649.2473 3033.1064 4364.4414 5325.9365 6325.6436 7677.7236 9535.0020 12163.9277 17316.2559 26602.5781 42522.6875 | lr 2.5e-04 | norm 31720.7520 | dt 9.824 +type train | step 373 | loss 837.3693 1615.0028 2976.7251 4283.2314 5226.6592 6210.3843 7538.6577 9343.3945 11922.5410 16993.6484 26231.4902 42136.6445 | lr 2.5e-04 | norm 31246.9648 | dt 9.829 +type train | step 374 | loss 848.5089 1640.2013 2983.4199 4287.4702 5244.3638 6231.6992 7562.7329 9396.5898 11990.5156 17082.2070 26334.7715 43350.8750 | lr 2.5e-04 | norm 34102.5586 | dt 9.814 +type train | step 375 | loss 848.7986 1645.5922 2990.0232 4279.8271 5225.7974 6213.9561 7575.4160 9438.9590 12054.0293 17133.7637 26374.7891 43269.5781 | lr 2.5e-04 | norm 32322.4238 | dt 9.817 +type train | step 376 | loss 879.8740 1692.3192 3028.9182 4333.6978 5293.1304 6310.6108 7641.3325 9511.3301 12030.6035 17010.7422 26102.6797 43478.9531 | lr 2.5e-04 | norm 35241.0547 | dt 9.805 +type train | step 377 | loss 867.2521 1679.2969 2995.5278 4293.5195 5273.7598 6309.9233 7662.3271 9569.8770 12191.2051 17304.9219 26718.2637 45722.1836 | lr 2.5e-04 | norm 33525.4453 | dt 9.812 +type train | step 378 | loss 863.1098 1669.6184 2979.7756 4240.6450 5177.2524 6157.9775 7492.7866 9304.7725 11853.6992 16902.5430 26098.6660 43114.0664 | lr 2.5e-04 | norm 36169.1328 | dt 9.812 +type train | step 379 | loss 880.8303 1722.1530 3075.4431 4383.7559 5380.3032 6501.8022 7964.5693 10063.3740 12912.3369 18525.3906 28522.6270 48411.7930 | lr 2.5e-04 | norm 48827.1758 | dt 9.835 +type train | step 380 | loss 856.6975 1658.3622 2954.1089 4199.6201 5171.7734 6236.6611 7633.1807 9601.3916 12278.3398 17530.6992 26822.0859 44818.8633 | lr 2.5e-04 | norm 34153.8281 | dt 9.833 +type train | step 381 | loss 835.2623 1614.6237 2872.6147 4085.3188 4996.3638 5976.4497 7282.3286 9114.5508 11680.0439 16666.0488 25839.8301 42395.4297 | lr 2.5e-04 | norm 31650.5391 | dt 9.825 +type train | step 382 | loss 819.1320 1581.3817 2822.6826 4010.5889 4913.0674 5853.5312 7139.0674 8923.6045 11461.0684 16410.2988 25350.9902 41386.2148 | lr 2.5e-04 | norm 32515.5938 | dt 9.806 +type train | step 383 | loss 818.5679 1580.1729 2806.0198 3979.6238 4883.3330 5817.0664 7092.3184 8866.5537 11424.7373 16381.5791 25415.3906 41524.4414 | lr 2.6e-04 | norm 32430.3281 | dt 9.815 +type train | step 384 | loss 823.3600 1585.6234 2794.4109 3965.8428 4861.6396 5794.5244 7072.5542 8823.1943 11321.8799 16178.9707 25195.0859 41391.8750 | lr 2.6e-04 | norm 31202.1309 | dt 9.840 +type train | step 385 | loss 786.5049 1525.3208 2723.7727 3871.5237 4780.6655 5717.7461 6993.7559 8715.6660 11215.2607 16082.1416 25002.2578 41068.5469 | lr 2.6e-04 | norm 31414.1445 | dt 9.907 +type train | step 386 | loss 796.7159 1540.2062 2721.2334 3859.3931 4751.7852 5698.1353 6984.6733 8763.5537 11305.1426 16241.7969 25198.9102 41228.1992 | lr 2.6e-04 | norm 30636.7285 | dt 9.896 +type train | step 387 | loss 788.9802 1523.4795 2688.6116 3808.3582 4685.2134 5580.6128 6819.1016 8521.9697 10968.2959 15721.7461 24413.9062 39892.1641 | lr 2.6e-04 | norm 29863.5625 | dt 9.846 +type train | step 388 | loss 789.2552 1521.6798 2667.8550 3764.2952 4649.7891 5557.6025 6808.3823 8526.6396 10967.8555 15768.8867 24455.2949 40142.1172 | lr 2.6e-04 | norm 30122.7305 | dt 9.836 +type train | step 389 | loss 786.7187 1509.2217 2650.8545 3752.3367 4629.5342 5559.7388 6827.6870 8588.9580 11096.8887 15976.9619 24903.4062 41394.2930 | lr 2.6e-04 | norm 29110.7871 | dt 9.857 +type train | step 390 | loss 778.9668 1503.6643 2632.5444 3725.4290 4587.6685 5508.8628 6784.2856 8558.9258 11046.3262 15902.5625 24867.1797 41751.6016 | lr 2.6e-04 | norm 29241.8105 | dt 9.824 +type train | step 391 | loss 787.3346 1522.2559 2650.5049 3742.3877 4637.8535 5589.2305 6885.0098 8727.7549 11301.1182 16300.3428 25488.4238 42368.4883 | lr 2.6e-04 | norm 31835.6348 | dt 9.850 +type train | step 392 | loss 776.2679 1497.8418 2604.3281 3667.7622 4527.7300 5437.7578 6691.7114 8429.9639 10931.7734 15863.6699 24933.3047 41199.4609 | lr 2.6e-04 | norm 28931.6113 | dt 9.850 +type train | step 393 | loss 742.9926 1435.3696 2512.5742 3552.9998 4404.7866 5307.3872 6550.3804 8270.6348 10786.7637 15583.4053 24432.2402 40515.3320 | lr 2.6e-04 | norm 29471.4160 | dt 9.851 +type train | step 394 | loss 812.0922 1569.3696 2667.2578 3741.1230 4602.1587 5554.3276 6836.7021 8657.9707 11139.2363 15889.5645 24718.8867 41165.9102 | lr 2.6e-04 | norm 57844.1523 | dt 9.826 +type train | step 395 | loss 790.8582 1521.3453 2599.0803 3636.1206 4496.3086 5435.0015 6705.1387 8474.2500 10936.3018 15701.9980 24326.2637 41404.2422 | lr 2.6e-04 | norm 38789.7969 | dt 9.832 +type train | step 396 | loss 762.4769 1468.8479 2519.6504 3522.7395 4372.4712 5263.2505 6465.3750 8140.1816 10546.0293 15201.9629 23812.9863 39826.0742 | lr 2.6e-04 | norm 29509.2207 | dt 9.842 +type train | step 397 | loss 752.6666 1447.3772 2486.3538 3474.4094 4312.9619 5178.0264 6372.1392 8050.4741 10463.6143 15155.1514 23773.2246 39701.6836 | lr 2.6e-04 | norm 29772.3066 | dt 9.846 +type train | step 398 | loss 750.5697 1447.6743 2480.7705 3466.2368 4311.8159 5195.3623 6435.6592 8147.5635 10575.4072 15302.4492 23901.4395 40169.9609 | lr 2.7e-04 | norm 31727.9336 | dt 9.839 +type train | step 399 | loss 770.3212 1484.1948 2511.2832 3498.5522 4347.6709 5273.0654 6516.8354 8245.9365 10674.1406 15423.9648 24193.8340 41027.0391 | lr 2.7e-04 | norm 29021.1836 | dt 9.836 +type train | step 400 | loss 730.9641 1406.6750 2397.7681 3348.8508 4180.4585 5064.9756 6277.4268 7956.7671 10374.0830 15061.2676 23744.1230 39793.8047 | lr 2.7e-04 | norm 29163.4902 | dt 9.853 +type train | step 401 | loss 741.4269 1429.8556 2418.5203 3382.6787 4200.6406 5101.0615 6334.8076 8100.0566 10588.9326 15415.3145 24237.5020 40925.8203 | lr 2.7e-04 | norm 28671.6855 | dt 9.863 +type train | step 402 | loss 751.5198 1448.5797 2426.8179 3369.3899 4180.9258 5050.9658 6264.8872 7945.6499 10313.0127 15043.9658 23785.3008 40313.1523 | lr 2.7e-04 | norm 28235.4941 | dt 9.856 +type train | step 403 | loss 723.1539 1401.1910 2352.3750 3273.3459 4087.2488 4961.9077 6148.4077 7827.6553 10214.0898 14831.9395 23415.2129 39488.0273 | lr 2.7e-04 | norm 30310.4727 | dt 9.840 +type train | step 404 | loss 732.0934 1407.7109 2354.4197 3265.5930 4077.0146 4957.5825 6167.1733 7829.8872 10193.7051 14839.6787 23253.2070 39275.5859 | lr 2.7e-04 | norm 27303.8926 | dt 9.839 +type train | step 405 | loss 712.4612 1370.7134 2297.3413 3202.6382 4009.4031 4868.2515 6058.5493 7743.9658 10160.2666 14785.4766 23277.0312 39348.3242 | lr 2.7e-04 | norm 27129.4922 | dt 9.835 +type train | step 406 | loss 677.8785 1301.6774 2201.3335 3075.5020 3857.4934 4701.2886 5866.4956 7528.3472 9872.5312 14481.4092 23026.7070 39220.1289 | lr 2.7e-04 | norm 29076.0781 | dt 9.819 +type train | step 407 | loss 721.0940 1385.1237 2297.6372 3171.5659 3969.5120 4854.5737 6044.6724 7725.0269 10078.4482 14679.9180 22962.3008 39250.9609 | lr 2.7e-04 | norm 28244.0508 | dt 9.832 +type train | step 408 | loss 705.1107 1356.4214 2250.2917 3116.2444 3902.6741 4759.1377 5929.9717 7588.8604 9969.3262 14579.2910 23104.4688 39354.1875 | lr 2.7e-04 | norm 26908.5137 | dt 9.820 +type train | step 409 | loss 699.9760 1347.1819 2224.8213 3080.0010 3860.0969 4720.0913 5897.6592 7568.8589 9887.8691 14466.0088 22925.9043 39455.3359 | lr 2.7e-04 | norm 28462.9688 | dt 9.855 +type train | step 410 | loss 695.0104 1333.1519 2201.2656 3043.1089 3819.3530 4653.9829 5812.0459 7429.4785 9783.4561 14223.6582 22495.2324 37957.1641 | lr 2.7e-04 | norm 26007.9160 | dt 9.822 +type train | step 411 | loss 704.4468 1352.4480 2209.5054 3036.9980 3819.3950 4645.5112 5777.3076 7369.4648 9647.0840 14059.1660 22312.5508 38015.9414 | lr 2.7e-04 | norm 30244.6035 | dt 9.829 +type train | step 412 | loss 700.5698 1340.3822 2190.0806 3019.6260 3789.8855 4655.7007 5838.7773 7537.7119 9857.8496 14411.8496 22821.8203 38982.2031 | lr 2.7e-04 | norm 28155.9062 | dt 9.820 +type train | step 413 | loss 681.0617 1307.0183 2130.7542 2939.9099 3707.1340 4530.7749 5674.9644 7302.7603 9625.7812 14120.6162 22555.7988 38619.5469 | lr 2.8e-04 | norm 25272.4941 | dt 9.842 +type train | step 414 | loss 728.4499 1399.4601 2242.9407 3073.0796 3869.7361 4739.7412 5904.6064 7580.9697 9887.9004 14375.0635 22672.8008 39837.3906 | lr 2.8e-04 | norm 27490.4082 | dt 9.829 +type train | step 415 | loss 680.3179 1301.9888 2117.3137 2917.4480 3680.2039 4504.8164 5641.9053 7243.1519 9569.3818 14008.3008 22276.7617 37987.1523 | lr 2.8e-04 | norm 24607.8809 | dt 9.839 +type train | step 416 | loss 690.4197 1322.3673 2113.3767 2895.5034 3644.0200 4461.5005 5601.2725 7241.6680 9533.4141 13991.1250 22421.8945 38794.9219 | lr 2.8e-04 | norm 24760.4609 | dt 9.828 +type train | step 417 | loss 726.3036 1396.6940 2210.5063 3022.2979 3833.5508 4730.0107 5924.3828 7605.9370 9921.8213 14459.1094 22832.2539 39870.9023 | lr 2.8e-04 | norm 26964.4180 | dt 9.839 +type train | step 418 | loss 697.3807 1341.3685 2130.7324 2919.9871 3701.0349 4564.4326 5734.3564 7443.1519 9818.4609 14398.5215 22934.7324 39697.3516 | lr 2.8e-04 | norm 26289.6699 | dt 9.841 +type train | step 419 | loss 680.1213 1308.8778 2073.9272 2840.5955 3590.4099 4453.6699 5585.5078 7242.1055 9528.9102 13981.3047 22083.7324 38630.0508 | lr 2.8e-04 | norm 24434.6309 | dt 9.820 +type train | step 420 | loss 662.7059 1270.4171 2023.2521 2774.6790 3506.3062 4316.6621 5443.7002 7044.6562 9329.5879 13752.5996 22093.0547 38567.6094 | lr 2.8e-04 | norm 25099.4102 | dt 9.822 +type train | step 421 | loss 677.9163 1299.8562 2044.2212 2776.2205 3514.7495 4353.1250 5459.3760 7085.4390 9359.7500 13658.9180 21683.9219 37719.6289 | lr 2.8e-04 | norm 24156.3965 | dt 9.835 +type train | step 422 | loss 707.3037 1357.5708 2095.8220 2827.8926 3551.0762 4402.8374 5540.4790 7191.3447 9441.8398 13858.5566 22034.6543 38978.7188 | lr 2.8e-04 | norm 29637.7539 | dt 9.831 +type train | step 423 | loss 652.6030 1257.7461 1964.1461 2677.1792 3396.0859 4201.4595 5317.4551 6913.6631 9183.9482 13515.2119 21674.7910 37594.2109 | lr 2.8e-04 | norm 23986.1426 | dt 9.806 +type train | step 424 | loss 676.0773 1300.2375 2014.4991 2729.8167 3457.1321 4284.3218 5403.4570 7029.4692 9363.2637 13804.0732 22289.2148 38848.4102 | lr 2.8e-04 | norm 25822.1250 | dt 9.855 +type train | step 425 | loss 663.7884 1269.3926 1965.4929 2652.5073 3359.4009 4161.2798 5239.1401 6793.8018 9043.2646 13348.7949 21443.6895 37129.8672 | lr 2.8e-04 | norm 22954.5703 | dt 9.836 +type train | step 426 | loss 648.2769 1250.1549 1966.7593 2692.6882 3451.3926 4326.1587 5501.5312 7202.4292 9516.7148 13988.9629 22275.2168 38942.6758 | lr 2.8e-04 | norm 29843.4355 | dt 9.837 +type train | step 427 | loss 660.5159 1271.8438 1966.0844 2661.0122 3391.9263 4229.7495 5354.3677 6993.3940 9255.9561 13611.4307 21630.8359 37978.0938 | lr 2.8e-04 | norm 22708.6699 | dt 9.829 +type train | step 428 | loss 628.3566 1208.7769 1879.8918 2535.7568 3238.5674 4009.6917 5089.7510 6621.8481 8858.9277 13094.5166 20963.2676 36455.4570 | lr 2.9e-04 | norm 22224.4492 | dt 9.828 +type train | step 429 | loss 634.4161 1222.4310 1877.0458 2526.6426 3220.9668 4021.1226 5097.1060 6663.8813 8914.1562 13211.3037 21248.9434 37323.9062 | lr 2.9e-04 | norm 21727.8516 | dt 9.816 +type train | step 430 | loss 663.2331 1277.4884 1932.7125 2604.4702 3311.9307 4124.3198 5225.0039 6839.2495 9040.1494 13272.0732 21263.4844 37560.7188 | lr 2.9e-04 | norm 23847.6934 | dt 9.826 +type train | step 431 | loss 638.3351 1225.2310 1858.4615 2507.1082 3193.6548 3969.4968 5016.9712 6541.5728 8764.1514 12939.5283 20854.3340 36606.8594 | lr 2.9e-04 | norm 21228.4258 | dt 9.818 +type train | step 432 | loss 639.4071 1228.1572 1855.1348 2490.8477 3185.9033 3979.8672 5050.2959 6593.7393 8805.4854 13011.1855 20881.0391 36869.0625 | lr 2.9e-04 | norm 21262.5996 | dt 9.827 +type train | step 433 | loss 604.0366 1161.7794 1775.3821 2398.6167 3084.0598 3860.7271 4927.2505 6469.2158 8695.8730 12903.0352 20779.5410 36472.5195 | lr 2.9e-04 | norm 23230.5410 | dt 9.823 +type train | step 434 | loss 667.0782 1284.3013 1905.1340 2542.3091 3246.0344 4069.3701 5162.4321 6754.7197 8953.2178 13131.7715 20920.6387 36659.3125 | lr 2.9e-04 | norm 21593.3574 | dt 9.837 +type train | step 435 | loss 624.4064 1202.4418 1804.2164 2420.2039 3111.3967 3888.7629 4949.6934 6470.8242 8682.7471 12914.6582 20874.2285 36803.5938 | lr 2.9e-04 | norm 19478.8242 | dt 9.819 +type train | step 436 | loss 603.4269 1169.3854 1762.3700 2374.5112 3048.4529 3833.7791 4889.8652 6425.8242 8610.7207 12766.6768 20718.3555 36888.6484 | lr 2.9e-04 | norm 27738.0508 | dt 9.806 +type train | step 437 | loss 612.4574 1179.9298 1764.6302 2367.8406 3039.0796 3828.1660 4896.4331 6480.4028 8737.9902 13014.7656 21107.3594 37403.2227 | lr 2.9e-04 | norm 20441.0781 | dt 9.844 +type train | step 438 | loss 584.6595 1138.4719 1711.9265 2307.3416 2990.7319 3774.7815 4850.1729 6490.2476 8861.7588 13308.0869 22065.7773 39897.3594 | lr 2.9e-04 | norm 31730.9707 | dt 9.820 +type train | step 439 | loss 615.6710 1181.5784 1744.6254 2322.1946 2998.1895 3788.9998 4821.0415 6362.0791 8534.6113 12717.2432 20709.0605 37386.9297 | lr 2.9e-04 | norm 23442.8320 | dt 9.826 +type train | step 440 | loss 608.7630 1166.1770 1711.2375 2286.7505 2930.1008 3689.0520 4701.3853 6197.6738 8346.5957 12455.2314 20294.7285 36068.6094 | lr 2.9e-04 | norm 21891.5781 | dt 9.815 +type train | step 441 | loss 611.6796 1178.8403 1728.5537 2307.7908 2972.7383 3749.1804 4790.7593 6313.7969 8482.8086 12644.8750 20540.1172 36805.0664 | lr 2.9e-04 | norm 18971.0742 | dt 9.819 +type train | step 442 | loss 608.0899 1173.8641 1717.8882 2285.0095 2946.7175 3712.1255 4737.1372 6236.2788 8423.8711 12499.7295 20333.0898 36113.0703 | lr 2.9e-04 | norm 18781.8750 | dt 9.806 +type train | step 443 | loss 585.3846 1128.7954 1658.8202 2210.0371 2860.0183 3628.9160 4664.7080 6191.1733 8371.0615 12505.5498 20271.5293 36244.3828 | lr 3.0e-04 | norm 18841.6191 | dt 9.832 +type train | step 444 | loss 602.0470 1160.2649 1686.9469 2249.6990 2920.6194 3740.3774 4816.5332 6458.4561 8700.7764 12925.3232 20764.8027 36972.5273 | lr 3.0e-04 | norm 18290.7168 | dt 9.832 +type train | step 445 | loss 570.0376 1096.9329 1602.8633 2127.7212 2759.0945 3513.5103 4539.6592 6044.8809 8198.5176 12259.3848 19949.0840 35473.1836 | lr 3.0e-04 | norm 21682.6543 | dt 9.812 +type train | step 446 | loss 581.4177 1118.2202 1624.3762 2155.5693 2799.0474 3559.7285 4575.6914 6086.7461 8243.2578 12295.7334 19889.4141 35196.8164 | lr 3.0e-04 | norm 17401.4141 | dt 9.831 +type train | step 447 | loss 589.4793 1133.6531 1630.4620 2162.8762 2800.2036 3553.1841 4564.6890 6058.2148 8206.2920 12294.4834 20068.2695 35852.4336 | lr 3.0e-04 | norm 18871.1230 | dt 9.825 +type train | step 448 | loss 600.8271 1159.3055 1655.7408 2180.8489 2820.5537 3562.0659 4571.3486 6076.8574 8238.3945 12281.3857 19903.8086 35739.1133 | lr 3.0e-04 | norm 17779.7383 | dt 9.823 +type train | step 449 | loss 567.9058 1093.3138 1575.7889 2094.1191 2729.0293 3472.0256 4476.3789 5968.1494 8123.0957 12174.6602 19847.7109 35249.0781 | lr 3.0e-04 | norm 17036.4883 | dt 9.819 +type train | step 450 | loss 589.9988 1131.9564 1613.1477 2133.7366 2758.7524 3501.3745 4496.0186 5982.8369 8114.4590 12071.6621 19706.3867 35674.6016 | lr 3.0e-04 | norm 22016.4219 | dt 9.806 +type train | step 451 | loss 606.8292 1165.1997 1632.9161 2158.1499 2797.0583 3556.0598 4570.3955 6085.3125 8208.2363 12206.0684 19992.5645 36499.8594 | lr 3.0e-04 | norm 19372.4531 | dt 9.813 +type train | step 452 | loss 567.2114 1087.5730 1540.2206 2045.8204 2674.4126 3415.6509 4396.5674 5836.4126 7926.8589 11820.1445 19306.4395 34713.4102 | lr 3.0e-04 | norm 18202.3164 | dt 9.820 +type train | step 453 | loss 552.7731 1062.9474 1504.6531 1998.3857 2619.2686 3368.9958 4357.4561 5836.1040 7926.2783 11826.6895 19275.9023 34278.2266 | lr 3.0e-04 | norm 21131.8184 | dt 9.806 +type train | step 454 | loss 546.1105 1057.4642 1497.7899 1990.2903 2613.4382 3332.0886 4305.8091 5761.1919 7894.5571 11869.7080 19432.6191 34786.2422 | lr 3.0e-04 | norm 18808.6250 | dt 9.821 +type train | step 455 | loss 576.3270 1109.6633 1549.3967 2044.9967 2658.6406 3384.5754 4365.2837 5837.1650 7943.9990 11902.2588 19459.0391 34907.3750 | lr 3.0e-04 | norm 18266.2715 | dt 9.810 +type train | step 456 | loss 564.5654 1090.1782 1522.9719 2008.6093 2631.0916 3396.3311 4398.2446 5901.9180 8014.3633 12029.0801 19654.4141 35605.1602 | lr 3.0e-04 | norm 17058.1152 | dt 9.803 +type train | step 457 | loss 554.4741 1067.6672 1487.8629 1962.0229 2572.3513 3301.3643 4266.0039 5717.1787 7803.6274 11681.0977 19109.5742 34275.5078 | lr 3.0e-04 | norm 16076.2793 | dt 9.815 +type train | step 458 | loss 559.5302 1083.3579 1506.0145 1985.5149 2593.0276 3325.7720 4306.4922 5777.5190 7887.4385 11835.9238 19441.7344 34893.9336 | lr 3.1e-04 | norm 15179.6826 | dt 9.823 +type train | step 459 | loss 534.0577 1030.3427 1436.8502 1895.8688 2497.2390 3208.4678 4167.5308 5621.3877 7690.4219 11535.3359 18996.9570 34315.0352 | lr 3.1e-04 | norm 17014.9434 | dt 9.812 +type train | step 460 | loss 563.1372 1086.2747 1480.4412 1941.9277 2534.0625 3259.8999 4211.0386 5641.0537 7680.8516 11500.4062 18885.9980 34452.2305 | lr 3.1e-04 | norm 17463.3086 | dt 9.801 +type train | step 461 | loss 556.1309 1075.5675 1468.1343 1923.1232 2517.4470 3276.7507 4252.3613 5764.6338 7828.2261 11665.6494 18993.7246 34777.6250 | lr 3.1e-04 | norm 17210.7305 | dt 9.792 +type train | step 462 | loss 527.2477 1017.7214 1395.1213 1849.8303 2436.9673 3164.5933 4117.0811 5598.6313 7649.8237 11509.9229 19015.9844 34905.5312 | lr 3.1e-04 | norm 18290.6797 | dt 9.799 +type train | step 463 | loss 525.8926 1019.5366 1411.0776 1868.3105 2461.9834 3193.2017 4174.0879 5654.8960 7786.4517 11732.5605 19288.8145 34811.7969 | lr 3.1e-04 | norm 15765.7939 | dt 9.812 +type train | step 464 | loss 530.6445 1029.5507 1409.8314 1869.9949 2465.4082 3195.7297 4137.7949 5597.8311 7654.1602 11486.3662 19027.4629 34651.7031 | lr 3.1e-04 | norm 20127.0469 | dt 9.819 +type train | step 465 | loss 531.7518 1030.4963 1410.5836 1866.3850 2455.1033 3176.4971 4129.0122 5581.4175 7697.9717 11568.9053 19000.3867 34244.4648 | lr 3.1e-04 | norm 16012.9082 | dt 9.825 +type train | step 466 | loss 524.2151 1015.0563 1387.9387 1835.5580 2419.6934 3156.5029 4116.7803 5586.0483 7658.6631 11531.3291 19029.2148 35077.6836 | lr 3.1e-04 | norm 14938.2236 | dt 9.809 +type train | step 467 | loss 512.6706 988.5097 1354.9742 1805.5712 2390.1948 3121.2446 4066.3806 5500.2964 7575.6514 11321.5400 18596.6211 33717.4961 | lr 3.1e-04 | norm 15703.1641 | dt 9.814 +type train | step 468 | loss 516.6346 997.4273 1354.6964 1801.4574 2380.1118 3118.7542 4059.1292 5512.7441 7548.4893 11375.7480 18845.6914 34378.0703 | lr 3.1e-04 | norm 14073.6611 | dt 9.797 +type train | step 469 | loss 510.8907 1000.0903 1371.1061 1830.9526 2418.6519 3177.8867 4159.9395 5713.5723 7915.3037 12001.4092 19933.2266 36664.4609 | lr 3.1e-04 | norm 18904.7871 | dt 9.800 +type train | step 470 | loss 514.3059 994.5355 1348.0211 1789.9447 2366.1653 3094.9729 4034.7058 5480.5547 7561.5967 11399.9736 18776.3047 34221.5469 | lr 3.1e-04 | norm 12833.3623 | dt 9.802 +type train | step 471 | loss 515.8591 998.8851 1346.9342 1784.5361 2350.7261 3061.6882 3977.6392 5384.8794 7410.7764 11145.5889 18456.8262 33495.3477 | lr 3.1e-04 | norm 12679.7705 | dt 9.786 +type train | step 472 | loss 503.5048 971.4460 1311.5060 1749.3885 2313.8906 3032.8718 3955.1228 5374.5854 7395.1851 11095.8447 18265.8574 33049.5625 | lr 3.1e-04 | norm 14044.3379 | dt 9.800 +type train | step 473 | loss 526.7271 1020.5093 1361.6919 1803.0256 2373.7188 3116.5339 4053.8086 5580.4180 7643.5840 11452.8652 18705.3691 34225.4648 | lr 3.2e-04 | norm 14469.9365 | dt 9.797 +type train | step 474 | loss 511.6183 989.4985 1328.2449 1756.5392 2317.1653 3034.7087 3965.1465 5405.0820 7454.1401 11193.2451 18404.2266 33738.9141 | lr 3.2e-04 | norm 11967.0889 | dt 9.817 +type train | step 475 | loss 504.6570 973.4409 1308.2698 1736.8868 2296.9087 3001.2200 3915.5574 5328.8682 7329.7905 11027.3496 18144.1074 32871.4219 | lr 3.2e-04 | norm 11255.7012 | dt 9.803 +type train | step 476 | loss 492.0936 955.0850 1281.6847 1719.5964 2293.1987 3043.0376 3992.6719 5499.6562 7616.7031 11543.8672 19158.5234 35272.5781 | lr 3.2e-04 | norm 19309.3418 | dt 9.810 +type train | step 477 | loss 487.2065 942.4817 1261.5626 1682.6908 2235.1487 2928.4756 3831.5486 5230.0151 7240.8071 10935.8213 18166.8809 33189.7695 | lr 3.2e-04 | norm 12760.7402 | dt 9.792 +type train | step 478 | loss 459.7730 890.5406 1230.5361 1660.0999 2229.5347 2975.8477 3972.3193 5532.6538 7752.3711 11926.1172 20034.7891 36356.6211 | lr 3.2e-04 | norm 36040.7500 | dt 9.780 +type train | step 479 | loss 503.2612 975.2047 1319.1775 1764.1344 2329.7056 3083.7925 4029.3999 5542.8169 7604.5015 11463.4385 19011.7090 34841.8789 | lr 3.2e-04 | norm 21036.7637 | dt 9.779 +type train | step 480 | loss 493.9456 953.3799 1271.0782 1692.9264 2238.9509 2948.1052 3856.2239 5298.3354 7328.3491 11050.6729 18275.1504 33686.0156 | lr 3.2e-04 | norm 14475.9756 | dt 9.798 +type train | step 481 | loss 513.1932 995.9903 1338.3384 1793.2625 2372.8093 3151.1946 4115.9023 5650.0474 7747.6943 11563.7930 18936.8867 34992.4688 | lr 3.2e-04 | norm 16616.3887 | dt 9.791 +type train | step 482 | loss 468.4477 906.5158 1217.7882 1635.0485 2175.6040 2873.0542 3769.8508 5149.9326 7124.7021 10798.7871 17998.1211 32974.7461 | lr 3.2e-04 | norm 18256.8750 | dt 9.786 +type train | step 483 | loss 524.0073 1014.4254 1336.1337 1768.6488 2329.7471 3070.5356 3979.7024 5402.0522 7358.2627 10986.8838 18088.1641 33111.4609 | lr 3.2e-04 | norm 13470.7266 | dt 9.802 +type train | step 484 | loss 517.1330 1002.6399 1320.1252 1748.5017 2292.3215 3005.8799 3909.6501 5306.0181 7310.7935 11024.8271 18212.4434 33461.2617 | lr 3.2e-04 | norm 15253.0781 | dt 9.792 +type train | step 485 | loss 532.0242 1035.4178 1356.5049 1793.6633 2349.3843 3083.3547 3989.0959 5406.2349 7337.5620 10991.4814 18034.9297 33230.9219 | lr 3.2e-04 | norm 15902.0508 | dt 9.784 +type train | step 486 | loss 471.7535 914.8314 1223.6641 1652.5057 2204.0271 2934.3584 3842.1838 5255.0063 7236.9814 10927.8633 18260.2832 33567.6562 | lr 3.2e-04 | norm 14373.5840 | dt 9.797 +type train | step 487 | loss 487.0298 959.4604 1314.2252 1798.4254 2405.4502 3160.5596 4119.4941 5665.1309 7899.0737 12132.5664 20266.6504 37223.7305 | lr 3.2e-04 | norm 33865.9336 | dt 9.806 +type train | step 488 | loss 518.2552 1006.1432 1347.9938 1826.9299 2433.0286 3243.6016 4244.6636 5799.6626 7908.1187 11825.3936 19100.7559 35642.7305 | lr 3.3e-04 | norm 15840.0020 | dt 9.790 +type train | step 489 | loss 479.9221 933.0835 1248.5042 1683.9097 2237.6025 2975.5103 3888.4895 5325.6001 7325.2476 11022.3379 18250.5820 33178.4102 | lr 3.3e-04 | norm 14055.5410 | dt 9.807 +type train | step 490 | loss 493.2849 958.4548 1274.7651 1716.4460 2267.4651 3008.7815 3924.1870 5348.7607 7348.5337 11025.4795 18239.2324 33605.4219 | lr 3.3e-04 | norm 12683.4014 | dt 9.790 +type train | step 491 | loss 470.5002 912.7628 1209.3773 1630.3024 2162.0710 2860.2656 3726.8291 5089.1240 7015.6235 10470.7812 17342.0254 31783.0957 | lr 3.3e-04 | norm 13418.2080 | dt 9.793 +type train | step 492 | loss 523.1284 1014.5074 1327.7629 1776.7639 2325.3445 3100.7722 4026.5269 5540.8096 7498.2363 11223.8936 18467.6094 34213.3711 | lr 3.3e-04 | norm 19254.9531 | dt 9.775 +type train | step 493 | loss 472.7661 918.5424 1224.0516 1653.6936 2187.4622 2907.5847 3792.9690 5177.4097 7133.9541 10711.9775 17729.6719 32791.6289 | lr 3.3e-04 | norm 13858.6729 | dt 9.785 +type train | step 494 | loss 462.3058 899.9199 1206.8059 1639.7660 2180.9766 2895.9058 3786.3484 5191.1299 7187.4653 10832.8389 17978.4395 32933.8047 | lr 3.3e-04 | norm 13262.8320 | dt 9.788 +type train | step 495 | loss 471.3795 914.8304 1218.4501 1649.7797 2187.4531 2895.5674 3776.1030 5150.8042 7102.8242 10678.8633 17661.2109 32385.6719 | lr 3.3e-04 | norm 11368.6475 | dt 9.802 +type train | step 496 | loss 469.8214 914.1641 1212.9221 1646.5914 2177.7507 2886.0413 3757.7542 5146.3164 7079.2310 10644.0029 17656.6523 32699.6250 | lr 3.3e-04 | norm 12398.6885 | dt 9.791 +type train | step 497 | loss 474.3539 921.8780 1223.0986 1646.3180 2173.9441 2876.9587 3729.2339 5081.3730 6997.2578 10524.5264 17466.0293 32204.3281 | lr 3.3e-04 | norm 11875.5566 | dt 9.830 +type train | step 498 | loss 450.5984 877.8490 1172.1932 1593.4634 2119.6130 2827.6135 3688.4512 5058.4536 6964.1304 10477.0615 17430.6953 32411.1992 | lr 3.3e-04 | norm 11485.8096 | dt 9.790 +type train | step 499 | loss 471.4516 911.1855 1208.3678 1635.5453 2159.6680 2864.4192 3730.0264 5095.5825 7045.5708 10603.6318 17701.7188 32745.3809 | lr 3.3e-04 | norm 12598.5996 | dt 10.372 +type train | step 500 | loss 449.5930 874.2294 1170.5164 1588.1704 2115.3643 2802.5608 3676.2769 5023.4316 6968.3574 10495.3574 17439.6094 31850.1621 | lr 3.3e-04 | norm 12126.2285 | dt 9.791 +type train | step 501 | loss 457.2695 889.6763 1189.5270 1615.9066 2147.8171 2862.8479 3752.2302 5132.7676 7122.9829 10735.7236 17851.7969 32953.6250 | lr 3.3e-04 | norm 12238.7979 | dt 9.784 +type train | step 502 | loss 435.1518 848.0026 1135.1697 1551.3467 2067.2827 2754.7805 3612.4553 4955.0044 6868.0317 10395.1758 17285.9453 31915.4785 | lr 3.3e-04 | norm 14370.9346 | dt 9.794 +type train | step 503 | loss 461.5314 896.1357 1193.5129 1618.8730 2136.1855 2836.4871 3707.0864 5065.8662 6983.6626 10517.4912 17452.6719 32042.1641 | lr 3.4e-04 | norm 12188.8652 | dt 9.798 +type train | step 504 | loss 456.8396 888.9116 1185.7917 1607.0913 2136.0522 2830.7827 3713.1365 5095.7676 7044.8008 10646.6230 17628.5430 32260.5488 | lr 3.4e-04 | norm 12214.6172 | dt 9.808 +type train | step 505 | loss 473.5017 925.1757 1226.3689 1655.2826 2175.4927 2884.0002 3744.7402 5128.4409 7031.8618 10605.3457 17833.2754 33544.4219 | lr 3.4e-04 | norm 28993.4629 | dt 9.766 +type train | step 506 | loss 476.5643 926.4608 1222.3016 1657.0710 2188.5317 2907.5171 3777.4392 5139.3442 7017.6172 10498.6270 17415.3105 32315.8125 | lr 3.4e-04 | norm 13452.2598 | dt 9.783 +type train | step 507 | loss 433.7707 846.0240 1139.1315 1562.7843 2092.6187 2824.6018 3704.8479 5104.5376 7020.6748 10616.2988 17504.3027 32433.3750 | lr 3.4e-04 | norm 13673.5225 | dt 9.804 +type train | step 508 | loss 426.6683 829.7224 1114.8395 1525.6442 2038.4592 2713.8396 3566.6213 4900.4277 6827.2852 10290.8271 17094.1426 31728.5820 | lr 3.4e-04 | norm 14027.8662 | dt 9.778 +type train | step 509 | loss 422.7184 824.2852 1110.2899 1520.4019 2032.6084 2698.1863 3540.7368 4850.8926 6735.3618 10169.5283 16905.9766 31011.9727 | lr 3.4e-04 | norm 15820.0322 | dt 9.776 +type train | step 510 | loss 428.8918 839.8214 1128.9606 1545.5461 2061.8330 2733.6841 3592.0291 4913.6753 6838.8174 10367.1348 17264.4199 31554.6484 | lr 3.4e-04 | norm 13839.2061 | dt 9.794 +type train | step 511 | loss 434.6961 848.1714 1137.6215 1556.7601 2072.0574 2755.0740 3607.2637 4943.7188 6833.3447 10297.7529 17125.5703 31724.2148 | lr 3.4e-04 | norm 12316.5449 | dt 9.776 +type train | step 512 | loss 438.3427 852.7327 1145.3557 1566.3452 2088.1306 2777.0576 3635.5671 4996.5049 6928.5532 10432.7246 17342.1641 31807.9141 | lr 3.4e-04 | norm 11454.4990 | dt 9.782 +type train | step 513 | loss 435.9837 850.6353 1130.4613 1549.9906 2064.6196 2759.5632 3626.8748 4991.1323 6894.2837 10383.8262 17149.5156 31244.3789 | lr 3.4e-04 | norm 13245.0078 | dt 9.791 +type train | step 514 | loss 416.6556 811.3838 1094.3303 1502.8153 2011.2826 2679.1655 3519.4712 4827.1206 6716.5713 10154.3379 16923.0137 30949.6914 | lr 3.4e-04 | norm 10452.4814 | dt 9.777 +type train | step 515 | loss 411.5793 808.6389 1093.5427 1509.6931 2032.3501 2737.4670 3606.0613 4978.7671 6914.3154 10489.1396 17437.8789 31938.3711 | lr 3.4e-04 | norm 13809.4941 | dt 9.780 +type train | step 516 | loss 409.7178 801.0086 1077.0868 1477.1498 1982.0168 2648.1487 3479.7429 4785.8960 6657.3315 10045.3555 16713.4102 30695.6777 | lr 3.4e-04 | norm 9962.2178 | dt 9.784 +type train | step 517 | loss 514.9826 1029.2581 1362.5303 1855.8376 2406.8040 3191.5032 4124.9585 5566.3262 7508.9673 11042.1289 17768.1426 32098.4492 | lr 3.4e-04 | norm 15593.4492 | dt 9.780 +type train | step 518 | loss 494.0692 979.3760 1298.6586 1760.7178 2302.9468 3066.4480 3975.3293 5447.9805 7393.7354 11005.9805 18003.8438 33067.4375 | lr 3.5e-04 | norm 23201.7207 | dt 9.766 +type train | step 519 | loss 436.7550 855.0786 1143.2368 1563.8115 2084.0581 2766.5933 3610.9529 4939.7617 6846.7144 10348.1514 17162.3164 31492.8594 | lr 3.5e-04 | norm 12426.9443 | dt 9.796 +type train | step 520 | loss 392.2444 776.0107 1061.1995 1476.7661 1991.2991 2668.7590 3515.5522 4837.8999 6764.3955 10246.8877 17096.2305 31220.1875 | lr 3.5e-04 | norm 12522.5635 | dt 9.792 +type train | step 521 | loss 412.2909 807.1442 1086.4568 1499.5702 2001.1062 2680.7190 3533.9810 4877.9717 6779.5830 10222.9492 16971.0527 31223.8457 | lr 3.5e-04 | norm 13543.2988 | dt 9.779 +type train | step 522 | loss 435.8502 851.1060 1138.9487 1562.3192 2074.4053 2775.9092 3631.2083 4982.8970 6873.1714 10334.7617 17094.6250 31399.9941 | lr 3.5e-04 | norm 12611.3857 | dt 9.777 +type train | step 523 | loss 441.4851 856.6675 1143.5267 1560.0107 2055.7971 2737.7358 3581.3584 4913.6973 6803.6533 10345.9209 17404.0879 32477.4551 | lr 3.5e-04 | norm 16112.4785 | dt 9.772 +type train | step 524 | loss 412.6647 807.1360 1085.7839 1494.1289 1996.1873 2648.0681 3466.3960 4734.1738 6571.2080 9966.5146 16646.2988 30339.8984 | lr 3.5e-04 | norm 12894.8721 | dt 9.782 +type train | step 525 | loss 396.2867 772.1863 1038.2089 1432.9363 1920.7017 2566.6206 3371.7910 4617.4707 6429.1660 9723.4834 16151.5977 29660.9414 | lr 3.5e-04 | norm 13785.1836 | dt 9.783 +type train | step 526 | loss 420.8058 825.7694 1101.5321 1516.2692 2010.8081 2703.1160 3537.9214 4864.0269 6750.7759 10195.9229 16955.0508 31099.7754 | lr 3.5e-04 | norm 15768.5908 | dt 9.777 +type train | step 527 | loss 418.5854 820.4924 1103.6875 1523.4738 2032.9103 2732.0171 3585.0605 4930.9541 6786.3955 10186.7939 16854.6367 30930.7754 | lr 3.5e-04 | norm 16609.3086 | dt 9.777 +type train | step 528 | loss 413.1366 814.3625 1099.9139 1517.4276 2030.9430 2714.8184 3574.4082 4912.8730 6810.7319 10368.4199 17234.6797 31475.8320 | lr 3.5e-04 | norm 18170.3867 | dt 9.793 +type train | step 529 | loss 408.1713 797.8636 1067.7402 1474.8469 1970.9487 2643.3645 3479.9626 4808.5723 6685.7446 10118.9141 16810.7891 30928.3711 | lr 3.5e-04 | norm 13987.7256 | dt 9.785 +type train | step 530 | loss 424.1430 835.6762 1123.1561 1544.7115 2050.4741 2724.1223 3564.3787 4868.3975 6701.7427 10089.8848 16706.0938 30951.1504 | lr 3.5e-04 | norm 15364.8428 | dt 9.777 +type train | step 531 | loss 420.2748 825.8793 1100.7623 1507.5948 2003.0796 2674.4651 3517.5193 4824.3071 6677.1079 10188.9736 16892.6758 30682.7988 | lr 3.5e-04 | norm 33767.9883 | dt 9.781 +type train | step 532 | loss 413.1167 807.5253 1082.9381 1489.8701 1986.2244 2658.6094 3493.4795 4799.6157 6638.8516 10112.2061 16873.4863 30542.8164 | lr 3.5e-04 | norm 22058.8809 | dt 9.785 +type train | step 533 | loss 402.6951 788.9288 1055.1182 1460.3591 1948.1245 2612.2280 3435.2354 4743.8325 6587.2407 10082.3135 16975.8145 31363.7852 | lr 3.6e-04 | norm 16584.1484 | dt 9.777 +type train | step 534 | loss 413.1117 807.8257 1082.0155 1490.7017 1986.9055 2671.9954 3511.5791 4837.7412 6642.6509 9968.2969 16507.9961 30274.9766 | lr 3.6e-04 | norm 14375.9141 | dt 9.782 +type train | step 535 | loss 408.1015 799.6016 1071.3240 1470.6844 1962.7772 2634.6816 3467.3110 4786.6377 6692.5488 10161.6895 16855.1797 30849.3086 | lr 3.6e-04 | norm 16300.9609 | dt 9.784 +type train | step 536 | loss 382.5889 757.6782 1035.4512 1440.8086 1936.2493 2601.0276 3431.8035 4738.5518 6655.3193 10064.2324 16699.8770 30471.1035 | lr 3.6e-04 | norm 16686.3945 | dt 9.776 +type train | step 537 | loss 375.4684 745.8779 1022.3035 1428.6738 1913.9559 2573.2437 3399.1460 4718.4409 6631.3281 10080.5791 16842.7246 30909.7812 | lr 3.6e-04 | norm 15731.3506 | dt 9.785 +type train | step 538 | loss 412.4269 813.6844 1095.5164 1517.1577 2020.0757 2707.3579 3544.0527 4895.1777 6710.3535 10261.2549 17385.5371 32555.5703 | lr 3.6e-04 | norm 32545.6602 | dt 9.775 +type train | step 539 | loss 415.4244 814.5117 1098.6865 1532.5171 2047.9678 2757.8833 3610.3142 4932.0752 6782.5322 10189.6611 16788.1738 30955.1719 | lr 3.6e-04 | norm 15448.0049 | dt 9.780 +type train | step 540 | loss 394.8670 775.5660 1044.7109 1442.7426 1927.0977 2570.5044 3383.2148 4660.3340 6457.0356 9837.3066 16380.9531 29978.9102 | lr 3.6e-04 | norm 14374.1641 | dt 9.780 +type train | step 541 | loss 371.6929 726.3088 986.8947 1378.7959 1864.6616 2511.6389 3322.0320 4598.8252 6425.7808 9740.6611 16199.5840 29512.7363 | lr 3.6e-04 | norm 13140.5371 | dt 9.778 +type train | step 542 | loss 397.8028 779.8168 1047.3977 1451.9924 1937.8237 2604.8821 3410.7073 4690.7085 6463.6631 9771.5889 16294.5664 30061.1797 | lr 3.6e-04 | norm 12647.0713 | dt 9.779 +type train | step 543 | loss 384.6700 759.7048 1036.8109 1447.7524 1941.4503 2605.5283 3423.8743 4714.8936 6586.5913 9978.0332 16646.2246 30215.7852 | lr 3.6e-04 | norm 12125.8984 | dt 9.798 +type train | step 544 | loss 380.4756 749.6172 1018.1782 1423.7705 1903.6775 2566.2483 3390.9878 4688.6455 6517.0884 9903.2480 16472.2109 30504.4668 | lr 3.6e-04 | norm 17791.1777 | dt 9.757 +type train | step 545 | loss 380.1353 757.5237 1013.7044 1406.7203 1876.3270 2577.2405 3415.6406 4754.2441 6558.7300 9907.2090 16549.5957 30966.8691 | lr 3.6e-04 | norm 24038.0410 | dt 9.766 +type train | step 546 | loss 376.4614 739.2842 1003.4711 1399.2290 1880.4019 2520.0505 3328.9048 4585.8286 6348.7622 9606.1787 15919.9453 29194.5215 | lr 3.6e-04 | norm 11408.3428 | dt 9.792 +type train | step 547 | loss 415.0405 813.7428 1086.0580 1495.3807 1984.2958 2666.3953 3502.1323 4821.4282 6596.0098 9983.0195 16574.3555 30933.9023 | lr 3.6e-04 | norm 20258.6035 | dt 9.776 +type train | step 548 | loss 370.4225 726.5811 989.3552 1382.5802 1853.6851 2487.1370 3280.1650 4527.3047 6316.5029 9586.5625 15920.5625 29121.0645 | lr 3.7e-04 | norm 11465.4912 | dt 9.775 +type train | step 549 | loss 375.3438 742.8928 1004.4296 1403.9697 1883.2834 2530.0259 3336.2988 4581.0254 6348.4380 9661.5078 16119.9375 29711.2578 | lr 3.7e-04 | norm 13084.2422 | dt 9.772 +type train | step 550 | loss 389.4836 768.5016 1033.6151 1428.8389 1907.9058 2547.4727 3340.8816 4598.9224 6386.0474 9680.6455 16200.5518 29647.0977 | lr 3.7e-04 | norm 11479.2783 | dt 9.788 +type train | step 551 | loss 351.2715 691.9924 945.5143 1329.2202 1796.1263 2422.8474 3211.3579 4421.9873 6198.0283 9400.6523 15710.4570 28627.9785 | lr 3.7e-04 | norm 11418.3291 | dt 9.793 +type train | step 552 | loss 361.4677 711.4637 968.3825 1353.1509 1820.6296 2447.2034 3232.4231 4444.5742 6209.4644 9470.8418 15824.2402 28836.4453 | lr 3.7e-04 | norm 11685.3457 | dt 9.789 +type train | step 553 | loss 369.3875 728.9524 990.4438 1385.8225 1863.3815 2497.0862 3285.5759 4516.8633 6299.7334 9556.3779 15918.6602 28910.0957 | lr 3.7e-04 | norm 10003.0674 | dt 9.785 +type train | step 554 | loss 354.5022 694.4075 943.8774 1320.6156 1782.5945 2421.8257 3221.7009 4499.3350 6317.3882 9635.2549 16042.3799 29232.5078 | lr 3.7e-04 | norm 11641.5518 | dt 9.780 +type train | step 555 | loss 372.9573 735.3847 1000.6419 1401.5957 1871.3292 2508.1897 3295.6833 4533.0073 6302.9995 9557.4766 16034.7217 29626.3516 | lr 3.7e-04 | norm 12200.1396 | dt 9.777 +type train | step 556 | loss 364.3391 736.1445 1005.9081 1405.6328 1880.8163 2519.5195 3318.5977 4601.5977 6482.1279 9958.1777 16944.8789 31502.8555 | lr 3.7e-04 | norm 19507.0586 | dt 9.771 +type train | step 557 | loss 354.1808 753.8763 1042.9825 1459.3695 1955.6941 2605.2720 3398.2046 4744.0811 6829.5020 10621.7695 18382.1641 34497.7305 | lr 3.7e-04 | norm 46779.5117 | dt 9.758 +type train | step 558 | loss 355.2534 704.7725 962.7671 1348.7472 1818.2834 2443.5278 3229.6394 4441.3535 6207.5210 9441.2217 15785.8906 28799.5195 | lr 3.7e-04 | norm 11590.7979 | dt 9.783 +type train | step 559 | loss 371.7561 734.4226 994.4417 1382.0321 1848.3623 2487.6365 3276.1353 4517.9307 6285.8823 9568.5859 16034.5293 29359.5469 | lr 3.7e-04 | norm 12418.3408 | dt 9.773 +type train | step 560 | loss 371.9304 736.6155 986.8329 1374.2500 1835.9786 2478.2693 3282.3977 4519.7183 6245.2061 9472.7559 15720.7227 29157.4414 | lr 3.7e-04 | norm 13684.4990 | dt 9.765 +type train | step 561 | loss 359.1214 705.9291 953.8986 1338.2583 1794.8977 2429.6941 3202.0193 4411.9072 6141.7617 9350.8857 15621.9033 28809.8145 | lr 3.7e-04 | norm 12951.8262 | dt 9.774 +type train | step 562 | loss 365.1434 721.2328 987.8478 1393.7798 1869.9237 2529.6401 3346.0059 4631.3848 6450.0273 9857.3252 16493.0410 30309.2637 | lr 3.7e-04 | norm 14051.5166 | dt 9.777 +type train | step 563 | loss 354.4601 702.3259 959.8154 1347.9507 1817.5729 2442.5762 3235.9045 4476.2686 6261.0918 9533.3223 15954.4531 29203.9629 | lr 3.8e-04 | norm 14091.7559 | dt 9.788 +type train | step 564 | loss 334.8400 662.3313 911.9446 1288.3562 1747.1951 2360.1125 3136.1631 4330.1772 6089.2349 9256.8389 15458.4736 28168.5527 | lr 3.8e-04 | norm 11592.6689 | dt 9.795 +type train | step 565 | loss 352.6827 693.8746 944.6425 1328.6384 1794.1814 2415.8870 3195.6357 4411.7666 6136.7764 9326.7021 15608.2070 28668.5605 | lr 3.8e-04 | norm 11018.7686 | dt 9.787 +type train | step 566 | loss 357.5484 701.4119 947.6560 1327.0356 1777.3348 2401.0508 3169.1809 4380.7979 6094.3975 9290.2168 15478.6445 28447.1797 | lr 3.8e-04 | norm 12062.2012 | dt 9.767 +type train | step 567 | loss 347.7376 688.6335 937.7632 1314.5717 1767.0149 2370.5466 3133.3972 4326.6958 6077.4258 9221.9688 15327.4922 27828.0039 | lr 3.8e-04 | norm 11646.1201 | dt 9.789 +type train | step 568 | loss 340.7408 669.2550 912.6606 1286.5189 1731.8336 2341.3887 3094.1851 4283.9111 5988.9766 9152.3623 15493.6201 28744.9492 | lr 3.8e-04 | norm 11774.2744 | dt 9.763 +type train | step 569 | loss 362.0885 715.9032 969.8020 1358.2151 1817.8098 2440.5549 3207.7522 4416.1025 6115.9854 9282.1172 15590.4150 28827.5430 | lr 3.8e-04 | norm 12784.7588 | dt 9.776 +type train | step 570 | loss 352.3991 698.4088 944.8428 1323.6582 1777.9954 2407.4668 3186.6079 4406.0386 6093.8804 9292.2559 15484.7197 28851.2910 | lr 3.8e-04 | norm 16036.6084 | dt 9.769 +type train | step 571 | loss 363.1461 714.5640 961.5858 1337.1411 1786.1082 2408.6394 3174.0527 4370.3955 6055.0762 9223.3086 15349.0898 28295.2578 | lr 3.8e-04 | norm 11331.2012 | dt 9.769 +type train | step 572 | loss 345.9446 684.4611 932.8605 1308.6049 1755.2760 2365.3608 3120.8037 4317.0381 5985.4897 9103.2402 15258.2422 28086.7090 | lr 3.8e-04 | norm 11118.4092 | dt 9.779 +type train | step 573 | loss 348.2399 688.3804 933.5907 1317.3518 1776.7935 2400.7061 3160.9531 4340.7803 6036.4653 9176.5312 15385.9336 28380.4922 | lr 3.8e-04 | norm 12363.0234 | dt 9.779 +type train | step 574 | loss 341.8577 676.5841 926.0228 1298.4622 1753.2510 2368.8354 3145.1028 4349.0952 6095.2725 9337.8369 15541.3516 28352.7031 | lr 3.8e-04 | norm 13031.3740 | dt 9.781 +type train | step 575 | loss 339.4485 673.1496 919.4579 1296.2523 1752.9644 2367.6758 3126.3755 4304.7393 5968.0347 9071.7549 15138.8662 28146.1621 | lr 3.8e-04 | norm 11203.1406 | dt 9.785 +type train | step 576 | loss 358.4220 710.4844 963.9992 1343.6755 1794.3527 2418.7837 3185.9507 4396.9839 6101.4619 9332.5117 15664.5947 29004.7129 | lr 3.8e-04 | norm 14306.1191 | dt 9.791 +type train | step 577 | loss 332.0639 658.3323 897.6583 1264.7509 1712.1011 2309.7959 3067.1021 4246.0562 5913.0303 9017.2363 14989.8428 27299.9727 | lr 3.8e-04 | norm 13023.2744 | dt 9.781 +type train | step 578 | loss 348.5215 686.6907 933.7092 1310.1652 1756.4656 2357.0122 3100.9612 4265.0615 5930.7534 8999.2510 15028.7607 27489.7617 | lr 3.9e-04 | norm 11595.9453 | dt 9.771 +type train | step 579 | loss 333.5597 656.7624 899.9010 1271.7802 1722.1837 2337.0649 3112.8159 4331.6323 6053.6377 9219.5547 15352.0996 27755.4570 | lr 3.9e-04 | norm 11723.7314 | dt 9.774 +type train | step 580 | loss 359.6613 713.5676 966.7240 1346.9028 1801.2202 2416.2932 3181.7090 4369.1309 6086.7964 9225.7188 15324.9365 28063.6797 | lr 3.9e-04 | norm 17059.7578 | dt 9.784 +type train | step 581 | loss 347.2759 691.9755 945.9808 1329.2546 1783.7340 2408.8660 3177.1501 4384.9565 6077.0259 9227.3252 15378.9795 28350.5918 | lr 3.9e-04 | norm 12592.9316 | dt 9.788 +type train | step 582 | loss 338.8500 674.9096 917.4938 1288.4420 1727.3854 2354.3726 3119.4119 4334.9326 5990.0781 9129.4805 15300.4512 28238.6348 | lr 3.9e-04 | norm 11002.8369 | dt 9.776 +type train | step 583 | loss 349.3107 695.2200 942.9028 1319.8684 1769.5874 2394.7490 3163.3635 4366.9731 6050.2446 9177.5244 15234.2256 27862.3828 | lr 3.9e-04 | norm 9997.6953 | dt 9.785 +type train | step 584 | loss 335.7657 670.1129 921.5785 1299.9707 1757.3057 2404.6858 3206.4458 4469.1313 6201.8794 9490.3135 15802.2930 28937.6328 | lr 3.9e-04 | norm 11214.1621 | dt 9.789 +type train | step 585 | loss 374.2191 745.0934 1012.9741 1415.0715 1891.8976 2551.6506 3352.5659 4614.2021 6312.5864 9612.1504 15877.6572 29335.6191 | lr 3.9e-04 | norm 16265.2578 | dt 9.767 +type train | step 586 | loss 345.1758 685.2583 936.3815 1315.6896 1769.5035 2394.3538 3179.6367 4415.6680 6130.9893 9371.2812 15581.3301 28586.9414 | lr 3.9e-04 | norm 15489.9053 | dt 9.766 +type train | step 587 | loss 336.1685 669.3885 912.4224 1285.4221 1728.2456 2349.3799 3115.3904 4327.1470 6041.0283 9228.5508 15432.1260 28319.0586 | lr 3.9e-04 | norm 11713.0996 | dt 9.775 +type train | step 588 | loss 339.0379 678.6686 923.5248 1295.3049 1740.5176 2375.3049 3155.9148 4420.6763 6111.6851 9337.8955 15606.6367 28761.0117 | lr 3.9e-04 | norm 12572.7383 | dt 9.786 +type train | step 589 | loss 329.5785 654.4937 892.8372 1257.7209 1704.2540 2309.3413 3069.9771 4263.8550 5933.8018 9049.6289 15084.6367 27461.2344 | lr 3.9e-04 | norm 13290.0293 | dt 9.777 +type train | step 590 | loss 330.4297 654.3741 895.1691 1266.3201 1716.6356 2340.1895 3111.7444 4336.7290 6054.5986 9277.6807 15592.3115 28925.4492 | lr 3.9e-04 | norm 14949.5430 | dt 9.764 +type train | step 591 | loss 326.5122 649.1791 886.9855 1259.6019 1698.9331 2311.6157 3063.3813 4236.6914 5828.3940 8852.1025 14600.1719 26992.1211 | lr 3.9e-04 | norm 14458.4688 | dt 9.781 +type train | step 592 | loss 319.8119 639.1370 879.5273 1241.1720 1671.6460 2277.0415 3026.9773 4223.6074 5902.1997 9023.4961 15103.6992 27850.5664 | lr 3.9e-04 | norm 12107.5742 | dt 9.777 +type train | step 593 | loss 327.2247 648.2684 894.4164 1265.0265 1709.2324 2328.9373 3099.4194 4308.9365 5989.5830 9141.4844 15105.6289 27645.8477 | lr 4.0e-04 | norm 11837.4609 | dt 9.784 +type train | step 594 | loss 320.2612 640.8896 883.2583 1248.9071 1686.3265 2295.1902 3053.2659 4246.5381 5933.2520 9096.8867 15257.4688 28108.6445 | lr 4.0e-04 | norm 12173.6992 | dt 9.790 +type train | step 595 | loss 328.3389 655.9906 887.7338 1243.9019 1678.4808 2261.8450 2989.7026 4130.7778 5753.4092 8804.5537 14709.6270 26959.2891 | lr 4.0e-04 | norm 11797.5811 | dt 9.790 +type train | step 596 | loss 320.8624 639.9079 879.4866 1244.5380 1680.4761 2285.3118 3034.7942 4212.8838 5850.6133 8990.0430 15092.2969 27730.5840 | lr 4.0e-04 | norm 10842.3076 | dt 9.781 +type train | step 597 | loss 321.4964 635.9716 867.1489 1219.3741 1650.8694 2260.0068 3013.3455 4200.7778 5864.1064 9010.5996 15053.2422 27688.3340 | lr 4.0e-04 | norm 10535.0127 | dt 9.793 +type train | step 598 | loss 316.3688 625.9948 850.4066 1200.6509 1616.6968 2187.9604 2890.9116 3985.7930 5577.7993 8563.8535 14490.1758 26757.4785 | lr 4.0e-04 | norm 10757.6094 | dt 9.773 +type train | step 599 | loss 300.9215 592.8718 816.7250 1158.1843 1582.7056 2151.3005 2872.6360 4012.0205 5631.1558 8579.4180 14176.9844 25849.5723 | lr 4.0e-04 | norm 16868.0156 | dt 9.770 +type train | step 600 | loss 307.7319 614.2001 846.7397 1201.0039 1633.8827 2241.2368 3005.0286 4205.8052 5904.3257 9025.7051 15043.8105 27553.8633 | lr 4.0e-04 | norm 11547.9541 | dt 9.784 +type train | step 601 | loss 350.8146 701.9014 953.3291 1335.0232 1784.2542 2446.4709 3240.2107 4512.9829 6170.4292 9311.1123 15360.1055 28427.6270 | lr 4.0e-04 | norm 14999.5547 | dt 9.780 +type train | step 602 | loss 321.1172 646.5797 892.0261 1266.3352 1714.9225 2353.0693 3126.8210 4378.5479 6105.7480 9319.1719 15567.9551 29116.6914 | lr 4.0e-04 | norm 14929.4336 | dt 9.772 +type train | step 603 | loss 328.3246 654.3033 891.0909 1257.8813 1699.0850 2321.8286 3091.2896 4307.2480 5970.2485 9089.4678 15101.2812 27736.0645 | lr 4.0e-04 | norm 12042.0645 | dt 9.788 +type train | step 604 | loss 333.6810 665.0886 902.8473 1275.0399 1711.9182 2327.6733 3073.2249 4254.3081 5904.8726 9035.6045 15149.7637 27997.0957 | lr 4.0e-04 | norm 14761.8936 | dt 9.766 +type train | step 605 | loss 296.9297 587.7576 809.2891 1147.8331 1561.3600 2131.0784 2846.6414 3964.8267 5582.3706 8566.7754 14371.4531 26357.8125 | lr 4.0e-04 | norm 10596.7607 | dt 9.774 +type train | step 606 | loss 297.0076 591.7953 823.3516 1168.4918 1589.1736 2158.4280 2880.9231 4020.5005 5649.3281 8658.8867 14464.1836 26375.0547 | lr 4.0e-04 | norm 10672.8447 | dt 9.774 +type train | step 607 | loss 315.1200 627.8524 855.5669 1210.4355 1627.7711 2225.8936 2950.8740 4106.0649 5727.0034 8748.2666 14644.4561 27344.5820 | lr 4.0e-04 | norm 9510.8389 | dt 9.772 +type train | step 608 | loss 318.7684 638.2560 878.8159 1246.6561 1685.1628 2300.2163 3059.2390 4275.8325 5952.6118 9105.0879 15190.4590 28021.9277 | lr 4.1e-04 | norm 11516.9365 | dt 9.772 +type train | step 609 | loss 288.7224 573.8263 792.8759 1131.4264 1551.5997 2151.4883 2884.0293 4044.0610 5680.0273 8751.9150 14595.6133 26867.0098 | lr 4.1e-04 | norm 13294.8232 | dt 9.764 +type train | step 610 | loss 265.9340 521.6602 731.8395 1060.3927 1479.6755 2084.1958 2798.8643 3977.3779 5554.9858 8521.3447 14061.8652 25777.3965 | lr 4.1e-04 | norm 22984.3457 | dt 9.752 +type train | step 611 | loss 284.6660 557.5601 772.2072 1100.9478 1517.0609 2097.6719 2803.6987 3919.4651 5483.4619 8460.1133 14061.5049 25938.5664 | lr 4.1e-04 | norm 23927.5000 | dt 9.771 +type train | step 612 | loss 310.3485 614.1923 843.0862 1194.0067 1626.9556 2252.6602 3006.2168 4202.2681 5842.4707 8891.8564 14715.8877 27163.2070 | lr 4.1e-04 | norm 14195.0342 | dt 9.775 +type train | step 613 | loss 303.4432 604.1008 826.6334 1169.1213 1578.7849 2146.7014 2853.2720 3968.8486 5546.2446 8497.5967 14269.1328 26696.6973 | lr 4.1e-04 | norm 16737.4844 | dt 9.779 +type train | step 614 | loss 298.4465 598.1721 819.8977 1159.0442 1569.5477 2132.8420 2838.5222 3942.6780 5522.9839 8491.9551 14297.4453 26476.3301 | lr 4.1e-04 | norm 15248.5156 | dt 9.787 +type train | step 615 | loss 317.8238 636.4172 870.9980 1236.5513 1667.9797 2308.2832 3083.2810 4357.7925 5992.8394 9057.5820 15229.5059 29137.0977 | lr 4.1e-04 | norm 20126.2988 | dt 9.764 +type train | step 616 | loss 298.9072 591.6180 818.7289 1165.7935 1581.6599 2151.2964 2857.4236 3960.3711 5552.2188 8477.5527 14266.3867 26260.0195 | lr 4.1e-04 | norm 15803.5635 | dt 9.785 +type train | step 617 | loss 294.4400 588.9027 813.4688 1154.9863 1573.4410 2164.9458 2900.9829 4051.5898 5681.6611 8730.2021 14527.9590 26705.5039 | lr 4.1e-04 | norm 14532.2129 | dt 9.780 +type train | step 618 | loss 309.0461 615.5223 841.1015 1193.9889 1611.3582 2202.8213 2937.7549 4085.2583 5668.2720 8703.8770 14548.9805 27032.3828 | lr 4.1e-04 | norm 15189.9922 | dt 9.772 +type train | step 619 | loss 280.0513 573.0500 807.6541 1159.8723 1584.2670 2174.1763 2923.5840 4087.3354 5794.0557 8975.7744 15129.2441 28125.3926 | lr 4.1e-04 | norm 17534.4980 | dt 9.781 +type train | step 620 | loss 328.7717 654.1219 883.1624 1242.5017 1667.8639 2263.9780 2993.6536 4160.3228 5739.6538 8801.1719 14742.7334 27504.0664 | lr 4.1e-04 | norm 12298.0703 | dt 9.799 +type train | step 621 | loss 317.2255 636.5140 870.0520 1226.8143 1645.9454 2235.2583 2963.0649 4100.3579 5674.8711 8667.5928 14534.9570 26946.9707 | lr 4.1e-04 | norm 13406.4619 | dt 9.794 +type train | step 622 | loss 315.5002 631.7157 865.5915 1215.5543 1637.2856 2224.7957 2954.0515 4093.0166 5682.5269 8706.8115 14498.7129 26677.9805 | lr 4.1e-04 | norm 14630.7441 | dt 9.796 +type train | step 623 | loss 328.1014 659.0095 899.0587 1271.8156 1716.2139 2322.2759 3074.4929 4244.1533 5836.6606 8847.0850 14746.7451 27362.7188 | lr 4.2e-04 | norm 15911.9072 | dt 9.781 +type train | step 624 | loss 308.4575 615.4890 843.4534 1192.4561 1613.8015 2190.6582 2917.6660 4079.6113 5669.0024 8653.0205 14357.8545 26581.9297 | lr 4.2e-04 | norm 13398.6025 | dt 9.777 +type train | step 625 | loss 278.1555 555.1183 775.6382 1117.1309 1547.3748 2113.2434 2838.1211 3982.6379 5637.2036 8708.6396 14704.9805 27464.1191 | lr 4.2e-04 | norm 18630.8594 | dt 9.784 +type train | step 626 | loss 305.4507 614.6494 852.0338 1206.0636 1633.1951 2207.9507 2920.1069 4039.1270 5605.2173 8591.9678 14362.5703 26490.6543 | lr 4.2e-04 | norm 13813.4141 | dt 9.778 +type train | step 627 | loss 314.1040 630.1259 862.0447 1210.0448 1642.1927 2198.1797 2912.8008 4021.1008 5613.2061 8628.7871 14434.8096 26513.5391 | lr 4.2e-04 | norm 13508.9082 | dt 9.787 +type train | step 628 | loss 300.7485 597.9044 822.2607 1170.5134 1595.4352 2176.4333 2899.8462 4038.8638 5634.1924 8576.8145 14282.2432 26091.1816 | lr 4.2e-04 | norm 12354.6191 | dt 9.780 +type train | step 629 | loss 289.2139 579.5500 804.0834 1148.9755 1580.0913 2145.4705 2883.7683 4039.6797 5635.8252 8662.5283 14484.8535 26728.2324 | lr 4.2e-04 | norm 11687.2871 | dt 9.786 +type train | step 630 | loss 318.3697 641.6807 880.6199 1244.3035 1708.5742 2298.9675 3046.2654 4272.2944 5876.1118 8922.1738 14608.1309 27297.0059 | lr 4.2e-04 | norm 14419.5801 | dt 9.777 +type train | step 631 | loss 306.6877 612.5544 841.8976 1191.1180 1622.6720 2185.7026 2904.8782 4029.9241 5603.3896 8557.8184 14283.2949 26194.8984 | lr 4.2e-04 | norm 10027.6221 | dt 9.789 +type train | step 632 | loss 310.2861 618.8285 861.2435 1219.3988 1660.2985 2233.4485 2965.9512 4127.9834 5797.4365 8920.6396 15047.9736 27745.2871 | lr 4.2e-04 | norm 16019.2295 | dt 9.771 +type train | step 633 | loss 309.2953 619.9829 850.1409 1205.4061 1642.7368 2205.5566 2919.7922 4038.2051 5586.8296 8539.1562 14220.5879 26333.4688 | lr 4.2e-04 | norm 11402.4805 | dt 9.777 +type train | step 634 | loss 303.2503 608.0174 839.3498 1189.6772 1625.6943 2181.4536 2902.7400 4046.6987 5630.0596 8637.1758 14475.7090 26671.4414 | lr 4.2e-04 | norm 10564.6357 | dt 9.786 +type train | step 635 | loss 301.3912 607.8534 837.3341 1190.2052 1626.2665 2191.0173 2907.2332 4026.5574 5592.2661 8567.7012 14378.1260 26966.3340 | lr 4.2e-04 | norm 15340.5371 | dt 9.772 +type train | step 636 | loss 305.8720 607.7975 833.6973 1184.2166 1623.3212 2206.7864 2941.0596 4133.7939 5696.5615 8643.7832 14260.2764 26320.8555 | lr 4.2e-04 | norm 10807.1143 | dt 9.783 +type train | step 637 | loss 290.1564 582.4701 800.2013 1137.5354 1564.8794 2109.3535 2809.4299 3902.4399 5455.7671 8378.0078 14037.7002 26063.7012 | lr 4.2e-04 | norm 11279.6045 | dt 9.774 +type train | step 638 | loss 284.9128 571.9213 787.2089 1124.2463 1546.2294 2109.3765 2809.4983 3944.4543 5536.8857 8506.9756 14252.8428 26347.6875 | lr 4.3e-04 | norm 10722.7217 | dt 9.777 +type train | step 639 | loss 306.8765 615.6223 843.6017 1193.6075 1623.7893 2189.1558 2908.2400 4042.4519 5635.8071 8586.0879 14318.1436 26493.2773 | lr 4.3e-04 | norm 11512.5840 | dt 9.772 +type train | step 640 | loss 349.0634 696.7616 925.7635 1283.5577 1717.8850 2284.9438 2984.1685 4038.7041 5516.2256 8367.3008 13874.8262 25949.8340 | lr 4.3e-04 | norm 14477.1289 | dt 9.757 +type train | step 641 | loss 312.8685 628.4868 857.0804 1214.2042 1652.5931 2240.1243 2975.1660 4140.8599 5703.5864 8756.7812 14609.4277 26894.6504 | lr 4.3e-04 | norm 9734.3428 | dt 9.786 +type train | step 642 | loss 289.8488 579.8626 800.1317 1136.0292 1553.5548 2088.1143 2770.8430 3831.7217 5367.0298 8234.8008 13781.9346 25454.5273 | lr 4.3e-04 | norm 9779.4268 | dt 9.793 +type train | step 643 | loss 294.9722 591.4435 816.8251 1161.5104 1582.4915 2138.6050 2842.8848 3947.4446 5515.7480 8477.7607 14201.1494 26106.5137 | lr 4.3e-04 | norm 10080.4287 | dt 9.782 +type train | step 644 | loss 256.7179 510.7711 717.9376 1035.7700 1449.8568 1984.6418 2696.7241 3828.1902 5402.8359 8364.3057 13913.8945 25666.7168 | lr 4.3e-04 | norm 15330.9570 | dt 9.769 +type train | step 645 | loss 270.7041 539.5140 746.6383 1071.1110 1477.1548 2019.1788 2720.2849 3824.6367 5362.0332 8293.1416 13893.6826 25618.8906 | lr 4.3e-04 | norm 10509.9326 | dt 9.780 +type train | step 646 | loss 286.2034 576.5100 793.8358 1130.8594 1543.7134 2090.6084 2782.4614 3860.5725 5390.6421 8271.7314 13858.5605 25665.2207 | lr 4.3e-04 | norm 9326.3340 | dt 9.784 +type train | step 647 | loss 286.3062 576.3469 797.3268 1143.1504 1573.0844 2155.7234 2885.9414 4054.9873 5659.2061 8606.9521 14251.6914 26427.0781 | lr 4.3e-04 | norm 11187.0479 | dt 9.771 +type train | step 648 | loss 307.9262 620.7830 844.3780 1189.9417 1607.3470 2183.7275 2889.0281 4008.1536 5521.2139 8418.5312 14026.1465 26513.0918 | lr 4.3e-04 | norm 15101.3350 | dt 9.771 +type train | step 649 | loss 302.2459 606.2779 825.3885 1162.6637 1572.1272 2143.5635 2861.2104 4004.9043 5595.2842 8571.3457 14245.1963 26368.4023 | lr 4.3e-04 | norm 12555.2236 | dt 9.780 +type train | step 650 | loss 303.5333 607.1104 828.7795 1169.5535 1589.5344 2154.1582 2870.7017 3979.4241 5499.8579 8372.4551 14048.5869 26107.8555 | lr 4.3e-04 | norm 11591.1289 | dt 9.780 +type train | step 651 | loss 288.3168 576.0095 787.7579 1118.8944 1526.3977 2068.8726 2760.3596 3846.4497 5367.4839 8252.9316 13888.6426 25705.8438 | lr 4.3e-04 | norm 11937.4004 | dt 9.775 +type train | step 652 | loss 295.3608 588.3879 805.5623 1142.5719 1549.2490 2119.7971 2828.5352 3957.2466 5507.2217 8430.0986 14091.0996 26039.4707 | lr 4.3e-04 | norm 12097.4248 | dt 9.782 +type train | step 653 | loss 288.7986 571.7729 796.7092 1134.2471 1553.5059 2109.9241 2803.2795 3913.9092 5461.2944 8362.2939 13926.9238 25799.5156 | lr 4.4e-04 | norm 13932.1260 | dt 9.784 +type train | step 654 | loss 284.4231 570.3593 794.8811 1137.3439 1549.8394 2106.4612 2804.2756 3908.3523 5461.3169 8428.8652 14144.9502 26221.4043 | lr 4.4e-04 | norm 12518.8213 | dt 9.792 +type train | step 655 | loss 278.3307 554.7685 765.9702 1091.4520 1484.7207 2048.0669 2728.8176 3831.4690 5357.3374 8248.8926 13817.4814 25714.9238 | lr 4.4e-04 | norm 11222.7910 | dt 9.788 +type train | step 656 | loss 279.3769 558.3243 769.9982 1093.1494 1493.4703 2037.8866 2719.1758 3804.0940 5320.0059 8229.0879 13876.2412 25924.2051 | lr 4.4e-04 | norm 10269.9912 | dt 9.783 +type train | step 657 | loss 277.2820 551.9443 763.3575 1087.7894 1484.4766 2018.6555 2691.4436 3752.8472 5239.2959 8006.6753 13390.0146 24566.8672 | lr 4.4e-04 | norm 10210.5908 | dt 9.775 +type train | step 658 | loss 269.5129 537.7870 748.0508 1076.6646 1496.5925 2020.1606 2704.3682 3776.7095 5279.8979 8102.6558 13603.1074 25161.0742 | lr 4.4e-04 | norm 9678.3994 | dt 9.780 +type train | step 659 | loss 274.6729 551.1100 771.0805 1112.5999 1543.3959 2094.5959 2801.0078 3927.8801 5496.6304 8449.6602 14226.5234 26544.5312 | lr 4.4e-04 | norm 15272.2871 | dt 9.777 +type train | step 660 | loss 263.7790 529.7425 737.7999 1061.8005 1490.2108 2008.0555 2685.9207 3733.0972 5284.1650 8180.4214 13719.0908 25474.9180 | lr 4.4e-04 | norm 11117.7031 | dt 9.782 +type train | step 661 | loss 285.3334 572.5321 791.3207 1127.4685 1562.3768 2102.8218 2814.3013 3927.5972 5490.3345 8426.2617 14100.5938 26031.3301 | lr 4.4e-04 | norm 12038.9658 | dt 9.791 +type train | step 662 | loss 294.6623 588.9557 806.1650 1142.8335 1560.0806 2089.9810 2769.9551 3834.9436 5299.5605 8086.5269 13583.7715 25273.6602 | lr 4.4e-04 | norm 13081.4746 | dt 9.782 +type train | step 663 | loss 271.0911 539.3298 749.5189 1074.7684 1489.6067 2002.6320 2674.3843 3712.4170 5225.0532 8031.4536 13490.0703 24937.4766 | lr 4.4e-04 | norm 10317.1650 | dt 9.786 +type train | step 664 | loss 275.9138 550.0638 758.8618 1081.2748 1487.4712 2001.5452 2674.0742 3718.9226 5176.1743 7935.5459 13292.5889 24901.1621 | lr 4.4e-04 | norm 12252.0205 | dt 9.783 +type train | step 665 | loss 272.7431 547.5074 760.5906 1087.8564 1501.3247 2039.2024 2714.2212 3796.2021 5300.7827 8152.4727 13617.3145 25331.0918 | lr 4.4e-04 | norm 11185.4658 | dt 9.781 +type train | step 666 | loss 279.5688 562.5972 760.9341 1091.9581 1499.0466 2052.7114 2753.7693 3904.7739 5380.1479 8304.0625 14002.7334 27266.3848 | lr 4.4e-04 | norm 30875.9531 | dt 9.752 +type train | step 667 | loss 274.3135 551.6454 762.1656 1089.1803 1495.0679 2024.2975 2691.6147 3759.0234 5241.9282 8035.7183 13430.2031 25033.8164 | lr 4.4e-04 | norm 10646.4854 | dt 9.791 +type train | step 668 | loss 272.2419 546.8333 758.4465 1082.2346 1500.6067 2044.5132 2748.7114 3853.5615 5384.1743 8308.4395 13815.2266 25724.2617 | lr 4.5e-04 | norm 14726.9062 | dt 9.774 +type train | step 669 | loss 277.5215 556.6062 762.2194 1083.2222 1486.5948 2025.0396 2698.3550 3769.5312 5252.4912 8066.3213 13462.9668 25023.6445 | lr 4.5e-04 | norm 11536.4219 | dt 9.795 +type train | step 670 | loss 268.8320 537.5864 743.6116 1064.4496 1470.1448 1988.0682 2639.4272 3672.5930 5136.3857 7894.0776 13242.1289 24617.1562 | lr 4.5e-04 | norm 11304.1514 | dt 9.787 +type train | step 671 | loss 269.6255 558.2788 788.3037 1139.9695 1569.1755 2110.8567 2813.6848 3923.2793 5487.9961 8437.4219 14210.1865 27075.1797 | lr 4.5e-04 | norm 22532.2949 | dt 9.775 +type train | step 672 | loss 285.5142 582.4824 822.0110 1187.0450 1627.9557 2203.0818 2914.5515 4069.2722 5655.7915 8627.8682 14385.3564 27121.9082 | lr 4.5e-04 | norm 28738.6816 | dt 9.763 +type train | step 673 | loss 268.6535 538.9907 746.1078 1068.5548 1473.4175 1996.8698 2646.7874 3692.2893 5188.5137 7997.8472 13495.6543 25371.1367 | lr 4.5e-04 | norm 12096.4346 | dt 9.763 +type train | step 674 | loss 253.3959 505.0942 708.0530 1025.4611 1426.8638 1947.5251 2615.4839 3660.8596 5137.8862 7903.0991 13229.4600 24734.3379 | lr 4.5e-04 | norm 12472.2607 | dt 9.769 +type train | step 675 | loss 266.1600 534.3393 738.4427 1059.1976 1456.8564 1975.4099 2639.0000 3689.7126 5162.9146 7945.2847 13298.9238 24842.0938 | lr 4.5e-04 | norm 12974.2373 | dt 9.787 +type train | step 676 | loss 265.5353 531.0077 730.7255 1039.9319 1432.3359 1930.4666 2579.0471 3589.4419 5037.3423 7776.1909 13085.0352 24381.8203 | lr 4.5e-04 | norm 12779.5508 | dt 9.777 +type train | step 677 | loss 261.9519 524.3537 725.6760 1041.1094 1428.5337 1950.5254 2599.9517 3633.0408 5107.3486 7904.9258 13294.6250 24893.0801 | lr 4.5e-04 | norm 12044.1982 | dt 9.786 +type train | step 678 | loss 278.4207 557.9567 769.9657 1095.8345 1496.5416 2043.3031 2728.7080 3813.4746 5288.0532 8086.5430 13385.6133 24933.8750 | lr 4.5e-04 | norm 13099.5430 | dt 9.799 +type train | step 679 | loss 268.6030 541.3382 749.1475 1076.3430 1481.0111 2016.3896 2695.7700 3755.8647 5262.5112 8056.3057 13433.7910 24806.8535 | lr 4.5e-04 | norm 11048.6484 | dt 9.781 +type train | step 680 | loss 274.4252 554.2432 767.5661 1101.1780 1503.1021 2039.0078 2701.7766 3755.9297 5260.8130 8080.0029 13492.1270 25040.2793 | lr 4.5e-04 | norm 10804.5342 | dt 9.779 +type train | step 681 | loss 273.3124 546.3401 761.3273 1092.2568 1497.3127 2033.5386 2697.4194 3746.6689 5244.0610 8100.0151 13578.7129 25140.0371 | lr 4.5e-04 | norm 11171.5293 | dt 9.791 +type train | step 682 | loss 267.8973 532.1974 735.0219 1055.1271 1451.5355 1979.5608 2634.1458 3687.3027 5137.5176 7914.9131 13272.9023 24527.0234 | lr 4.5e-04 | norm 9622.3096 | dt 9.774 +type train | step 683 | loss 259.5973 520.9941 722.6185 1034.2797 1422.0461 1930.4861 2577.2363 3594.4646 5050.0801 7793.8203 13137.6445 24228.3965 | lr 4.6e-04 | norm 10520.4707 | dt 9.783 +type train | step 684 | loss 261.7742 525.1385 730.4445 1050.5302 1451.0598 1999.2838 2672.4851 3751.7712 5227.1074 8007.7456 13432.3945 25028.0039 | lr 4.6e-04 | norm 12006.3926 | dt 9.776 +type train | step 685 | loss 254.2379 510.5309 709.9918 1026.7612 1421.7219 1969.2251 2656.7820 3751.4060 5218.4673 8039.0479 13572.1348 25373.1133 | lr 4.6e-04 | norm 13235.1123 | dt 9.757 +type train | step 686 | loss 247.0048 497.2044 701.6068 1017.1072 1416.1920 1935.8312 2600.2771 3659.9312 5169.3071 7975.7671 13371.3672 24853.1758 | lr 4.6e-04 | norm 10305.3799 | dt 9.793 +type train | step 687 | loss 263.9820 528.6124 731.7798 1046.4747 1435.3289 1965.3589 2632.1375 3677.9766 5159.5068 7948.9561 13360.6797 24775.8086 | lr 4.6e-04 | norm 10440.1670 | dt 9.787 +type train | step 688 | loss 266.8318 529.4728 724.9819 1027.8315 1410.1846 1926.1674 2583.0591 3628.2891 5088.7227 7848.0898 13032.7109 23971.6348 | lr 4.6e-04 | norm 10102.3438 | dt 9.778 +type train | step 689 | loss 265.8502 530.2784 732.0089 1051.7795 1449.6415 1968.4330 2618.8350 3648.2527 5106.8828 7869.6587 13231.4307 24498.2734 | lr 4.6e-04 | norm 10177.2559 | dt 9.777 +type train | step 690 | loss 267.4825 550.8724 766.3617 1100.6226 1512.9536 2047.6090 2723.5464 3801.7166 5357.8555 8240.7031 13946.2500 26094.6055 | lr 4.6e-04 | norm 13508.0635 | dt 9.782 +type train | step 691 | loss 250.2090 505.0142 699.8370 1011.7961 1404.5754 1939.8118 2608.0522 3672.6677 5167.1943 7967.8110 13337.0576 24721.5137 | lr 4.6e-04 | norm 11002.1621 | dt 9.770 +type train | step 692 | loss 271.3289 543.1863 747.5898 1073.3872 1462.6216 2019.5287 2634.8369 3668.1106 5072.6753 7763.1611 13042.1719 24640.8574 | lr 4.6e-04 | norm 13089.6650 | dt 9.786 +type train | step 693 | loss 266.8875 533.7377 734.0509 1046.9871 1431.5747 1971.0874 2624.5173 3682.6990 5115.5967 7855.4536 13176.2207 24702.6543 | lr 4.6e-04 | norm 11800.6123 | dt 9.773 +type train | step 694 | loss 259.8097 519.8167 716.0936 1024.7258 1409.1575 1945.9125 2578.7617 3605.6404 5057.1772 7804.7339 13127.7871 24378.4199 | lr 4.6e-04 | norm 10478.3115 | dt 9.776 +type train | step 695 | loss 248.8719 493.9800 687.9774 988.1642 1365.3188 1882.2296 2484.1604 3473.4448 4896.0781 7537.6377 12681.2852 23632.1406 | lr 4.6e-04 | norm 10554.5469 | dt 9.777 +type train | step 696 | loss 255.9691 509.2494 706.7408 1014.1087 1394.6219 1907.5004 2524.5002 3518.0479 4946.2207 7645.6650 12916.9336 24021.0234 | lr 4.6e-04 | norm 10083.8496 | dt 9.782 +type train | step 697 | loss 258.4614 517.5339 716.2186 1031.7950 1416.1343 1945.1982 2574.4771 3600.0693 5037.4570 7808.6367 13138.6113 24460.8691 | lr 4.6e-04 | norm 10709.6709 | dt 9.779 +type train | step 698 | loss 270.0724 539.9553 745.1911 1069.1140 1465.0992 2021.5332 2685.0466 3771.8452 5269.4209 8158.5581 13775.5625 25809.9375 | lr 4.7e-04 | norm 10704.1855 | dt 9.790 +type train | step 699 | loss 263.2279 521.6479 722.6707 1040.4438 1434.4597 1959.1897 2597.3652 3622.7212 5084.8784 7826.5088 13070.4951 23990.2539 | lr 4.7e-04 | norm 11266.9268 | dt 9.798 +type train | step 700 | loss 298.5371 598.0982 814.6164 1163.5226 1557.1942 2130.3252 2790.0156 3853.9395 5285.9453 8027.6216 13481.6816 25488.0117 | lr 4.7e-04 | norm 13644.7998 | dt 9.763 +type train | step 701 | loss 257.8389 515.9069 720.5704 1041.1117 1434.7357 1987.2556 2604.9709 3660.7998 5111.2983 7843.5869 13172.2500 24787.8223 | lr 4.7e-04 | norm 13340.7656 | dt 9.774 +type train | step 702 | loss 250.2724 502.4230 747.4461 1194.2181 1678.6271 2400.8560 3221.6846 4707.6914 6406.3647 9528.8848 15369.2051 29969.1992 | lr 4.7e-04 | norm 27423.8652 | dt 9.743 +type train | step 703 | loss 266.3533 537.7590 772.6292 1176.4731 1642.0479 2325.8005 3101.7781 4439.8906 6084.6396 9215.5410 15094.5596 28831.3398 | lr 4.7e-04 | norm 20124.3945 | dt 9.752 +type train | step 704 | loss 266.3165 532.7197 728.6906 1038.6754 1417.1709 1969.7732 2584.8315 3615.8945 5059.0073 7799.2441 13219.9023 24900.6211 | lr 4.7e-04 | norm 12926.7773 | dt 9.775 +type train | step 705 | loss 255.8772 515.0701 711.5795 1020.1985 1403.0477 1932.0087 2537.8018 3531.3728 4957.0659 7640.4780 12868.9316 24154.5527 | lr 4.7e-04 | norm 11658.3447 | dt 9.782 +type train | step 706 | loss 234.8257 466.9978 652.7918 947.7440 1313.5948 1834.0446 2410.6206 3377.4053 4761.9941 7373.5669 12517.4365 23562.1406 | lr 4.7e-04 | norm 12631.3535 | dt 9.773 +type train | step 707 | loss 277.2814 560.2587 768.8245 1096.9490 1497.8992 2071.0854 2732.8257 3840.7886 5302.1636 8139.7188 13568.4229 25394.7988 | lr 4.7e-04 | norm 13181.0840 | dt 9.773 +type train | step 708 | loss 259.3722 519.7153 715.5355 1034.3359 1420.8684 1985.6217 2628.7068 3700.1790 5155.4429 7921.9058 13292.2686 24806.1172 | lr 4.7e-04 | norm 10189.3359 | dt 9.799 +type train | step 709 | loss 247.0317 491.5630 685.6026 998.1674 1380.3048 1932.7825 2571.3694 3627.7939 5088.4272 7875.6299 13237.0908 24727.2109 | lr 4.7e-04 | norm 12949.4141 | dt 9.772 +type train | step 710 | loss 258.2411 514.8120 710.9542 1029.2316 1413.6174 1962.1273 2591.4932 3644.4861 5089.5737 7811.8774 13068.9727 24375.5527 | lr 4.7e-04 | norm 11173.4346 | dt 9.769 +type train | step 711 | loss 265.2200 535.2632 744.3937 1071.8210 1471.3862 2029.8169 2675.3215 3742.0642 5174.5229 7930.4971 13156.7188 24381.5664 | lr 4.7e-04 | norm 15487.5352 | dt 9.788 +type train | step 712 | loss 243.2945 485.3632 682.9278 988.2284 1364.1748 1887.5145 2503.1292 3498.4666 4923.6929 7586.5542 12747.7412 23911.5078 | lr 4.7e-04 | norm 10962.8213 | dt 9.791 +type train | step 713 | loss 252.6967 507.2336 702.3885 1011.7641 1387.0107 1922.5868 2527.2219 3535.7700 4952.0454 7655.9067 12913.4941 24170.8945 | lr 4.8e-04 | norm 10274.3096 | dt 9.789 +type train | step 714 | loss 258.3856 519.0547 718.4956 1038.2058 1419.1018 1958.7064 2587.5701 3617.1707 5049.0913 7699.5186 12878.5674 24084.1641 | lr 4.8e-04 | norm 10790.3672 | dt 9.786 +type train | step 715 | loss 262.7112 523.4934 722.3926 1044.7373 1434.5835 2011.9264 2652.5923 3721.6628 5181.3013 7957.8828 13345.4688 25171.7363 | lr 4.8e-04 | norm 11506.1113 | dt 9.781 +type train | step 716 | loss 258.4469 517.5701 712.8647 1024.6575 1403.5375 1935.9620 2560.4600 3577.2561 4997.0444 7658.2905 12821.2539 23894.9336 | lr 4.8e-04 | norm 9065.5459 | dt 9.777 +type train | step 717 | loss 233.5958 468.8648 651.1603 947.1513 1310.7670 1828.5259 2451.3042 3445.6833 4841.3999 7488.4531 12539.8027 23295.5352 | lr 4.8e-04 | norm 12419.0254 | dt 9.777 +type train | step 718 | loss 238.1269 474.7037 661.4705 959.2399 1328.2495 1851.8530 2466.5898 3470.5457 4854.5513 7529.7661 12674.3164 23738.3750 | lr 4.8e-04 | norm 10086.7881 | dt 9.788 +type train | step 719 | loss 240.8206 480.9855 674.4878 982.2435 1356.1943 1883.8491 2496.8406 3494.4646 4912.4575 7617.1948 12778.4990 23938.2266 | lr 4.8e-04 | norm 10647.0107 | dt 9.792 +type train | step 720 | loss 239.4185 481.0641 677.7280 989.0304 1366.0773 1883.2255 2498.3716 3493.4365 4926.4922 7596.5903 12801.9902 23915.4512 | lr 4.8e-04 | norm 9731.7168 | dt 9.794 +type train | step 721 | loss 251.2313 502.3207 692.9702 997.8904 1370.3997 1887.8280 2509.5103 3486.1375 4862.0703 7446.6484 12412.9258 22955.3516 | lr 4.8e-04 | norm 10219.3652 | dt 9.788 +type train | step 722 | loss 251.4727 506.6350 703.6741 1020.1682 1399.2056 1949.1265 2592.8804 3641.6345 5041.3359 7714.7280 12856.1445 24365.0859 | lr 4.8e-04 | norm 11645.2520 | dt 9.779 +type train | step 723 | loss 255.8956 520.1780 725.5831 1044.5316 1432.1145 1980.0972 2639.8721 3741.2285 5180.4917 8125.0723 13620.6973 25560.0723 | lr 4.8e-04 | norm 16821.1191 | dt 9.781 +type train | step 724 | loss 247.2017 493.4312 689.4434 1001.6453 1384.3035 1902.0511 2530.2544 3553.0718 4964.4951 7659.5610 12807.3877 23771.6934 | lr 4.8e-04 | norm 9757.8584 | dt 9.790 +type train | step 725 | loss 241.1363 481.6775 673.9738 973.8755 1348.1469 1859.8468 2473.9951 3466.9346 4866.2886 7480.2480 12478.7979 23010.7812 | lr 4.8e-04 | norm 9205.4639 | dt 9.789 +type train | step 726 | loss 240.0911 479.5637 665.7298 966.1067 1334.5909 1845.9119 2457.0005 3429.2578 4822.0371 7474.3525 12646.1562 23622.7578 | lr 4.8e-04 | norm 11335.7979 | dt 9.768 +type train | step 727 | loss 278.4605 547.1072 733.0498 1059.1903 1450.0698 2041.1018 2733.6125 3932.9167 5436.2393 8391.8896 13957.8135 25681.3086 | lr 4.8e-04 | norm 13059.0000 | dt 9.771 +type train | step 728 | loss 233.4022 465.0892 647.9620 942.6501 1307.5925 1808.4143 2412.6895 3373.6509 4749.6997 7327.2920 12297.8398 22800.4570 | lr 4.9e-04 | norm 10144.5586 | dt 9.779 +type train | step 729 | loss 244.0124 487.8683 676.6164 978.2132 1351.1793 1864.9232 2465.7534 3448.9817 4807.7451 7406.8257 12405.7998 23386.7891 | lr 4.9e-04 | norm 11161.2139 | dt 9.776 +type train | step 730 | loss 247.5341 493.1534 682.7111 984.9296 1356.4010 1870.4573 2495.0615 3489.8691 4908.6196 7595.3135 12765.4248 23756.8516 | lr 4.9e-04 | norm 10024.3887 | dt 9.790 +type train | step 731 | loss 256.4083 508.8520 699.1345 1011.0281 1390.5602 1944.5619 2591.4055 3647.6731 5061.0742 7764.7173 12974.9746 24423.4883 | lr 4.9e-04 | norm 11010.2520 | dt 9.791 +type train | step 732 | loss 236.0922 472.0329 657.4690 950.4754 1314.0104 1818.0499 2423.8486 3384.8604 4767.4814 7350.0356 12402.2148 23270.7832 | lr 4.9e-04 | norm 9867.6162 | dt 9.771 +type train | step 733 | loss 242.3757 480.1707 657.4575 950.7498 1313.6158 1817.9493 2411.6499 3380.8489 4774.0303 7330.6475 12385.6973 23254.9258 | lr 4.9e-04 | norm 11025.5186 | dt 9.781 +type train | step 734 | loss 241.3614 481.8221 666.6731 961.2386 1329.1171 1834.7709 2452.7354 3433.7751 4855.9199 7498.2764 12544.5371 23352.8164 | lr 4.9e-04 | norm 9305.6982 | dt 9.794 +type train | step 735 | loss 260.8535 523.3453 722.9578 1039.6580 1422.5048 1953.7131 2591.6978 3643.5020 5062.6001 7778.7798 13037.0693 24503.2051 | lr 4.9e-04 | norm 11687.1279 | dt 9.776 +type train | step 736 | loss 231.6643 462.0371 650.9592 949.3329 1313.8817 1822.5568 2434.0496 3425.7046 4827.8706 7465.6982 12562.1035 23662.9297 | lr 4.9e-04 | norm 10795.2363 | dt 9.793 +type train | step 737 | loss 228.8701 457.9054 639.7307 935.8357 1300.6721 1806.5144 2412.4993 3381.4375 4766.8945 7355.6182 12344.1826 23049.0176 | lr 4.9e-04 | norm 8842.6631 | dt 9.770 +type train | step 738 | loss 243.1004 492.7356 693.5790 1014.6299 1406.7566 1940.0226 2579.8914 3616.9905 5091.8877 7902.4272 13247.8154 24868.8281 | lr 4.9e-04 | norm 11309.8330 | dt 9.783 +type train | step 739 | loss 221.4293 445.7092 629.3815 924.8890 1295.1182 1806.4587 2425.6646 3435.3176 4831.7456 7469.0273 12468.6680 23155.3223 | lr 4.9e-04 | norm 9020.7773 | dt 9.788 +type train | step 740 | loss 227.8205 455.0715 641.1498 941.4689 1316.1372 1805.3901 2420.6614 3420.3748 4877.9453 7553.7197 12801.3604 24240.4023 | lr 4.9e-04 | norm 12858.7500 | dt 9.776 +type train | step 741 | loss 227.5184 456.2822 636.3680 932.0865 1308.0854 1791.2732 2388.7388 3354.7263 4779.6597 7374.8779 12482.1367 23486.2812 | lr 4.9e-04 | norm 11378.2822 | dt 9.802 +type train | step 742 | loss 237.1120 471.7594 651.2879 946.4426 1324.9713 1835.3779 2447.1074 3452.5671 4851.0898 7400.7031 12337.1885 23148.0469 | lr 4.9e-04 | norm 9854.9277 | dt 9.805 +type train | step 743 | loss 224.2462 445.3369 623.4248 911.4752 1276.9551 1762.5852 2372.8301 3342.3406 4752.8369 7354.8306 12416.2900 23250.2969 | lr 5.0e-04 | norm 10500.4854 | dt 9.788 +type train | step 744 | loss 235.7686 468.9108 655.4746 955.4149 1329.9751 1829.1807 2440.0269 3426.4949 4829.3950 7455.1797 12497.2480 23210.5879 | lr 5.0e-04 | norm 10557.9453 | dt 9.792 +type train | step 745 | loss 241.7518 481.6609 668.3146 965.0455 1331.9736 1836.1458 2434.0957 3392.7385 4782.8750 7321.3296 12308.1973 22835.4766 | lr 5.0e-04 | norm 9430.1016 | dt 9.781 +type train | step 746 | loss 232.9078 466.5420 652.7521 951.2952 1321.3276 1817.3672 2423.2656 3402.9612 4800.0850 7407.4707 12519.2783 23374.3320 | lr 5.0e-04 | norm 10597.8184 | dt 9.796 +type train | step 747 | loss 263.6861 526.1696 721.8501 1039.5966 1417.2949 1949.0537 2570.6343 3578.0095 4963.6699 7547.2700 12527.0264 23566.2109 | lr 5.0e-04 | norm 11688.5088 | dt 9.793 +type train | step 748 | loss 257.6367 515.7778 706.6302 1021.3914 1397.0027 1935.8528 2575.4514 3612.9136 4996.6782 7546.2397 12337.8730 22958.6641 | lr 5.0e-04 | norm 8755.1416 | dt 9.786 +type train | step 749 | loss 243.5541 487.4059 684.2737 1001.5961 1395.4791 1911.8831 2549.0017 3582.0698 5032.8916 7685.1025 12823.1104 23831.2793 | lr 5.0e-04 | norm 10688.9961 | dt 9.790 +type train | step 750 | loss 242.9988 487.6526 681.5350 999.9848 1388.6719 1902.0706 2536.3750 3524.4810 4987.8667 7638.7275 12741.0293 24052.4824 | lr 5.0e-04 | norm 12792.8867 | dt 9.777 +type train | step 751 | loss 255.9489 513.5842 719.2222 1043.7488 1441.0930 1968.8364 2628.0339 3665.5337 5185.5908 7830.9067 13117.8174 24700.7461 | lr 5.0e-04 | norm 17961.4316 | dt 9.772 +type train | step 752 | loss 276.4968 555.2036 754.8520 1086.4973 1502.2654 2037.3221 2688.2637 3747.4006 5219.1235 7949.8887 13257.9346 24953.1699 | lr 5.0e-04 | norm 13419.2266 | dt 9.776 +type train | step 753 | loss 235.8728 477.7425 669.1974 973.7763 1356.1775 1858.3831 2481.6619 3474.6997 4934.4648 7568.3374 12727.9824 23849.0664 | lr 5.0e-04 | norm 11026.3496 | dt 9.791 +type train | step 754 | loss 237.4827 477.5493 668.2109 976.0657 1375.6461 1877.6530 2506.7319 3505.9194 4969.7979 7676.9937 12896.3516 24387.7383 | lr 5.0e-04 | norm 11484.2949 | dt 9.770 +type train | step 755 | loss 229.1644 458.2546 641.4576 943.2336 1333.4016 1808.0083 2420.5249 3393.4680 4831.1650 7452.1733 12552.7295 23621.5195 | lr 5.0e-04 | norm 10471.4287 | dt 9.785 +type train | step 756 | loss 238.4084 483.5242 682.7661 1006.4576 1423.1191 1923.4373 2559.1777 3587.8965 5086.1592 7795.7607 13064.8232 24539.6914 | lr 5.0e-04 | norm 12312.1357 | dt 9.785 +type train | step 757 | loss 237.5712 477.9444 669.7013 977.5562 1377.7616 1879.4745 2515.5117 3527.7495 4953.2944 7628.5859 12816.6523 24104.2773 | lr 5.0e-04 | norm 12505.3330 | dt 9.792 +type train | step 758 | loss 254.6398 508.6187 705.0024 1025.7041 1438.4886 1950.8760 2599.4331 3640.1121 5137.3237 7777.8770 13007.9863 24311.7715 | lr 5.0e-04 | norm 10439.9287 | dt 9.782 +type train | step 759 | loss 245.7818 497.2174 687.5063 997.4785 1418.9078 1896.0283 2513.7925 3498.6980 4930.6265 7604.0786 12783.6836 24279.7539 | lr 5.0e-04 | norm 11507.3945 | dt 9.781 +type train | step 760 | loss 242.8700 486.3788 678.5482 986.9230 1371.9985 1855.3950 2453.0510 3406.2361 4783.5381 7299.1289 12262.7959 22900.0645 | lr 5.0e-04 | norm 8629.5566 | dt 9.788 +type train | step 761 | loss 247.7578 499.7439 695.5770 1008.0851 1403.8990 1892.7137 2498.7153 3464.9619 4864.6274 7450.0996 12545.9629 23725.8984 | lr 5.0e-04 | norm 10213.7793 | dt 9.784 +type train | step 762 | loss 247.5206 493.3730 685.5222 988.8545 1385.5889 1850.5164 2445.2351 3387.3767 4765.6050 7367.8262 12554.5781 24346.7090 | lr 5.0e-04 | norm 23940.7656 | dt 9.774 +type train | step 763 | loss 232.1702 464.2046 649.2658 949.4799 1358.3918 1825.8895 2434.6147 3420.6333 4833.4111 7400.8975 12431.0078 23205.2676 | lr 5.0e-04 | norm 9915.8018 | dt 9.793 +type train | step 764 | loss 247.8789 499.2323 691.8995 1002.5196 1422.2091 1896.3809 2522.0647 3530.3650 4944.6074 7534.0439 12546.4375 23426.6992 | lr 5.0e-04 | norm 9711.3711 | dt 9.795 +type train | step 765 | loss 222.9160 446.2982 635.1819 933.7653 1347.4075 1831.4814 2464.2927 3483.1353 4916.3657 7466.4541 12250.0625 22749.3008 | lr 5.0e-04 | norm 14997.5410 | dt 9.771 +type train | step 766 | loss 245.1182 494.7595 687.8523 998.1328 1399.0182 1876.4407 2486.6614 3452.9326 4861.7549 7433.8174 12499.4307 23294.7227 | lr 5.0e-04 | norm 8693.2090 | dt 9.792 +type train | step 767 | loss 238.9624 477.1101 662.3220 970.4613 1368.8126 1850.8906 2479.3545 3455.6653 4876.0137 7502.2549 12696.1455 23896.3320 | lr 5.0e-04 | norm 9947.9932 | dt 9.795 +type train | step 768 | loss 231.2275 462.8018 649.3894 948.1061 1353.0105 1813.5564 2425.3494 3405.4167 4796.5430 7347.3555 12298.3984 22927.7832 | lr 5.0e-04 | norm 10194.8564 | dt 9.800 +type train | step 769 | loss 235.5417 465.6610 648.9053 950.4809 1346.2472 1824.2898 2440.0198 3425.5754 4853.8369 7387.5156 12364.9316 23118.7207 | lr 5.0e-04 | norm 8862.2510 | dt 9.797 +type train | step 770 | loss 245.7801 494.2903 687.3566 998.7831 1408.1063 1895.0070 2530.1602 3535.2202 4955.2788 7537.6714 12578.1982 23465.4961 | lr 5.0e-04 | norm 8727.7930 | dt 9.804 +type train | step 771 | loss 235.0401 479.3068 670.4651 982.5271 1402.6243 1883.4043 2495.3853 3483.8198 4891.5229 7476.5029 12480.4873 23530.5020 | lr 5.0e-04 | norm 15775.5566 | dt 9.784 +type train | step 772 | loss 241.3124 480.4532 674.5941 985.0995 1392.8093 1886.9885 2514.8582 3528.8640 4978.5171 7633.1533 12718.0430 23676.7812 | lr 5.0e-04 | norm 9628.5264 | dt 9.807 +type train | step 773 | loss 221.7487 444.2034 626.5848 922.3348 1328.5789 1794.3218 2394.9868 3375.0239 4777.7661 7374.8818 12371.2930 23257.0430 | lr 5.0e-04 | norm 9518.2607 | dt 9.785 +type train | step 774 | loss 240.9688 484.7021 667.7894 970.1155 1369.9366 1834.7802 2417.3557 3353.9150 4705.6934 7199.5962 12074.4834 22699.0078 | lr 5.0e-04 | norm 9944.3311 | dt 9.794 +type train | step 775 | loss 222.0938 461.8806 661.2152 987.4321 1425.8647 1906.7552 2568.8652 3607.9744 5171.9053 8094.0693 13927.3770 27318.0547 | lr 5.0e-04 | norm 22507.6582 | dt 9.784 +type train | step 776 | loss 229.6815 458.7408 641.9258 936.3839 1323.3813 1783.6031 2370.2412 3309.1025 4653.4492 7246.1304 12243.8760 22949.4258 | lr 5.0e-04 | norm 9925.0742 | dt 9.782 +type train | step 777 | loss 221.8560 443.9370 624.1618 913.1900 1306.1803 1754.1528 2329.1902 3250.5098 4607.4043 7085.0225 11928.0713 22334.2539 | lr 5.0e-04 | norm 11013.1650 | dt 9.788 +type train | step 778 | loss 251.8353 508.9770 713.8199 1045.1962 1476.0792 1965.9845 2586.6353 3635.4390 5066.3682 7807.8057 13197.1152 25184.4102 | lr 5.0e-04 | norm 17347.8945 | dt 9.775 +type train | step 779 | loss 255.6869 516.4431 715.6405 1036.6315 1451.5729 1918.3961 2534.1218 3553.0388 4926.4355 7532.3325 12685.3750 24001.7969 | lr 5.0e-04 | norm 15190.9375 | dt 9.775 +type train | step 780 | loss 229.7294 458.8828 645.8763 947.4606 1350.2896 1816.5576 2410.7690 3360.1450 4762.1182 7277.8081 12135.3447 22761.9609 | lr 5.0e-04 | norm 11668.2432 | dt 9.801 +type train | step 781 | loss 234.2856 468.8103 652.7028 953.0079 1345.4581 1807.8848 2408.6953 3354.6433 4715.2573 7254.7119 12223.2422 23159.7090 | lr 5.0e-04 | norm 11637.3105 | dt 9.793 +type train | step 782 | loss 231.9374 462.9711 659.5483 972.4149 1394.5215 1908.9160 2558.4028 3602.5059 5059.0547 7699.0503 12773.1182 24061.1113 | lr 5.0e-04 | norm 12984.9746 | dt 9.794 +type train | step 783 | loss 224.9613 452.5468 638.4056 936.5090 1328.6234 1791.3717 2386.9185 3333.8035 4706.1968 7200.4126 12152.2510 22997.4004 | lr 5.0e-04 | norm 10719.4648 | dt 9.793 +type train | step 784 | loss 252.0353 508.9302 694.9074 1005.8938 1413.5649 1914.0018 2542.6719 3571.2273 4956.2715 7516.5195 12471.2744 23196.2969 | lr 5.0e-04 | norm 11300.4746 | dt 9.776 +type train | step 785 | loss 236.5103 472.2329 660.9444 964.4755 1371.3102 1856.3447 2476.1191 3464.0981 4843.7837 7411.3555 12316.0596 23044.2832 | lr 5.0e-04 | norm 9965.3008 | dt 9.787 +type train | step 786 | loss 221.6264 451.7830 655.4307 986.9649 1422.6034 1929.3290 2582.6477 3646.9390 5164.7803 8052.6489 13741.5752 26399.0488 | lr 5.0e-04 | norm 23006.7793 | dt 9.777 +type train | step 787 | loss 212.2444 433.3300 614.1166 919.0986 1332.7925 1785.6180 2398.6611 3356.4009 4823.8994 7472.8755 12702.0137 24315.8477 | lr 5.0e-04 | norm 14324.3672 | dt 9.770 +type train | step 788 | loss 243.8523 487.1651 674.2042 974.3006 1375.0359 1844.1910 2431.4114 3377.5493 4709.1060 7173.1680 11952.9570 22571.8496 | lr 5.0e-04 | norm 10547.6211 | dt 9.802 +type train | step 789 | loss 236.1942 465.9283 644.2894 938.1164 1330.5227 1785.7826 2388.3999 3329.4731 4688.9395 7139.3027 11918.9854 22451.1367 | lr 5.0e-04 | norm 14429.4619 | dt 9.783 +type train | step 790 | loss 221.9656 450.4718 637.4090 936.9061 1326.5292 1798.9270 2409.7666 3372.3345 4788.6953 7312.7163 12235.9873 23009.9805 | lr 5.0e-04 | norm 12539.1953 | dt 9.786 +type train | step 791 | loss 221.1123 442.1646 618.2615 907.2472 1288.8438 1741.8914 2334.7930 3255.6143 4582.0371 7048.5957 11835.8213 22312.9258 | lr 5.0e-04 | norm 11184.3555 | dt 9.782 +type train | step 792 | loss 227.6743 455.1243 636.1222 930.3015 1331.4479 1779.6453 2370.4233 3315.5562 4687.6997 7150.6646 11983.1455 22423.5957 | lr 5.0e-04 | norm 11199.6084 | dt 9.786 +type train | step 793 | loss 228.7987 457.8407 637.6124 930.9797 1326.1794 1797.5582 2413.5854 3381.7598 4838.8828 7394.4409 12232.2461 23021.2793 | lr 5.0e-04 | norm 12131.2236 | dt 9.777 +type train | step 794 | loss 220.0295 441.4095 621.6675 918.3874 1311.6924 1787.3292 2382.3401 3370.2256 4749.1138 7300.0474 12290.0117 23414.6895 | lr 5.0e-04 | norm 11210.1855 | dt 9.789 +type train | step 795 | loss 222.3728 446.4792 623.4637 918.7493 1307.2692 1769.9326 2354.8247 3298.0095 4682.8115 7198.9126 12063.0635 22708.3340 | lr 5.0e-04 | norm 9526.8906 | dt 9.789 +type train | step 796 | loss 226.8873 460.7641 644.9778 947.4678 1342.7478 1808.8145 2403.8374 3362.0847 4778.4902 7333.8320 12412.3047 23534.0371 | lr 5.0e-04 | norm 10115.1426 | dt 9.781 +type train | step 797 | loss 217.7796 437.0104 618.8427 919.2878 1306.1171 1790.2749 2403.3838 3400.1318 4775.6406 7267.4688 12114.5947 22818.5762 | lr 5.0e-04 | norm 9302.2500 | dt 9.793 +type train | step 798 | loss 239.5570 479.2639 660.5560 962.9491 1349.2438 1856.7065 2470.5212 3487.6987 4855.4932 7420.6748 12433.2656 23610.2832 | lr 5.0e-04 | norm 11265.8359 | dt 9.783 +type train | step 799 | loss 217.3957 431.7208 597.4883 882.2672 1244.3984 1740.0160 2341.4517 3336.4521 4655.4170 7170.6733 12097.4395 23018.4727 | lr 5.0e-04 | norm 16491.1641 | dt 9.764 +type train | step 800 | loss 221.5512 444.5846 622.0772 911.3531 1294.8654 1752.4954 2350.4248 3284.7205 4660.2754 7154.0747 11958.4707 22321.8086 | lr 5.0e-04 | norm 10467.9932 | dt 9.786 +type train | step 801 | loss 226.1826 449.7870 632.7013 922.8827 1300.9535 1773.2440 2335.3738 3264.9521 4631.8433 7090.6035 11928.9658 22708.7422 | lr 5.0e-04 | norm 14469.5078 | dt 9.792 +type train | step 802 | loss 218.3020 434.3637 607.4926 891.9479 1275.2098 1740.1434 2323.2480 3269.9290 4636.5166 7144.8306 12026.6846 22683.0859 | lr 5.0e-04 | norm 10904.4121 | dt 9.795 +type train | step 803 | loss 222.1634 441.0049 619.8862 914.5554 1307.8096 1768.6176 2349.3652 3285.6299 4638.9531 7135.7104 11930.6631 22287.7734 | lr 5.0e-04 | norm 9683.3682 | dt 9.780 +type train | step 804 | loss 247.7982 504.0905 700.9657 1033.1876 1462.3704 2008.9327 2657.4036 3736.3472 5198.7100 7955.1636 13189.1895 24732.4688 | lr 5.0e-04 | norm 10695.4727 | dt 9.785 +type train | step 805 | loss 236.6743 470.4727 653.2998 959.8235 1363.4113 1866.8816 2477.3728 3487.5815 4860.1377 7364.7979 12312.7803 23199.3477 | lr 5.0e-04 | norm 9893.5645 | dt 9.771 +type train | step 806 | loss 216.9492 434.1473 610.5125 896.5240 1278.8362 1734.2290 2325.0535 3243.9341 4576.1611 7042.0991 11903.1045 22282.8125 | lr 5.0e-04 | norm 9369.5615 | dt 9.794 +type train | step 807 | loss 224.9785 452.0022 628.2202 917.3471 1300.6031 1801.1815 2377.5718 3342.1831 4683.1172 7126.9878 11837.1855 22232.1719 | lr 5.0e-04 | norm 10468.4736 | dt 9.776 +type train | step 808 | loss 225.9795 449.0508 629.4126 922.7651 1294.2164 1774.8885 2319.1399 3226.2417 4515.0762 6877.4058 11472.5498 21830.8320 | lr 5.0e-04 | norm 12553.1436 | dt 9.777 +type train | step 809 | loss 230.1705 456.1487 637.2975 933.5093 1323.1448 1807.7256 2388.5596 3326.8176 4673.5991 7057.0796 11711.2676 22046.7578 | lr 5.0e-04 | norm 10389.5791 | dt 9.780 +type train | step 810 | loss 235.4651 469.0379 642.0006 927.2004 1307.8030 1775.2189 2339.2307 3275.9968 4585.2642 7039.0103 11809.4746 22353.6016 | lr 5.0e-04 | norm 18173.2559 | dt 9.771 +type train | step 811 | loss 234.8647 467.7994 648.5398 946.5737 1338.1025 1807.2130 2401.1326 3333.8572 4687.2744 7192.3491 12000.0586 22219.0215 | lr 5.0e-04 | norm 12658.3691 | dt 9.795 +type train | step 812 | loss 233.8853 472.3193 646.7910 942.5109 1326.8950 1800.2040 2391.2673 3337.3906 4689.9912 7171.1567 12022.9893 22653.4375 | lr 5.0e-04 | norm 10231.6826 | dt 9.788 +type train | step 813 | loss 228.7046 455.2252 634.3587 930.6040 1324.6923 1808.5984 2387.7705 3334.5627 4718.9121 7159.8018 11899.2988 22172.7051 | lr 5.0e-04 | norm 9416.8398 | dt 9.795 +type train | step 814 | loss 226.3789 450.1695 622.7183 918.4200 1301.5938 1786.2064 2375.9365 3337.3784 4667.5703 7108.4341 11893.1611 22194.8477 | lr 5.0e-04 | norm 10353.2773 | dt 9.780 +type train | step 815 | loss 213.9247 425.7411 597.4836 877.3893 1253.5115 1720.0533 2276.2134 3192.0964 4548.3799 6861.0854 11347.0986 21085.4824 | lr 5.0e-04 | norm 9851.1680 | dt 9.787 +type train | step 816 | loss 226.7123 449.1071 624.4772 917.4194 1294.1968 1804.1705 2376.7749 3389.4426 4723.2593 7124.3135 11935.1367 22710.7852 | lr 5.0e-04 | norm 15738.0488 | dt 9.773 +type train | step 817 | loss 231.0251 460.2224 637.0966 931.5997 1317.4244 1825.3400 2378.7534 3362.8027 4724.0889 7123.5210 11787.6973 21849.8984 | lr 5.0e-04 | norm 8658.1729 | dt 9.782 +type train | step 818 | loss 221.7085 436.8236 603.5373 884.2866 1248.1746 1730.0419 2292.1650 3168.3718 4472.8071 6803.2939 11461.4277 21556.2012 | lr 5.0e-04 | norm 9829.1016 | dt 9.775 +type train | step 819 | loss 221.2719 442.8516 621.8531 915.7621 1295.5305 1786.7974 2353.1611 3315.3591 4685.3013 7090.3999 11908.5391 22690.7070 | lr 5.0e-04 | norm 10719.4697 | dt 9.793 +type train | step 820 | loss 217.9767 434.7347 611.7966 909.5505 1291.9728 1787.4120 2351.3159 3302.4971 4670.5903 7066.7861 11878.5625 22412.0762 | lr 5.0e-04 | norm 10803.1855 | dt 9.784 +type train | step 821 | loss 217.8355 432.8029 606.9778 899.6942 1271.8539 1762.1676 2320.5659 3257.5361 4612.6157 6993.5503 11710.8271 21850.9219 | lr 5.0e-04 | norm 9279.4180 | dt 9.789 +type train | step 822 | loss 233.2574 466.6114 650.5939 960.5302 1351.5610 1874.4965 2509.4282 3497.8589 4854.3726 7367.4663 12360.7061 23499.0352 | lr 5.0e-04 | norm 12114.6367 | dt 9.775 +type train | step 823 | loss 208.6059 421.6242 601.9371 900.4275 1284.7910 1774.7437 2358.0010 3304.6375 4670.8433 7123.0088 11963.4346 22783.3770 | lr 5.0e-04 | norm 10464.7031 | dt 9.796 +type train | step 824 | loss 218.6684 436.9514 613.3021 900.0600 1276.9299 1764.9342 2332.8723 3258.0388 4606.6055 7019.7441 11698.5840 21873.2070 | lr 5.0e-04 | norm 9937.1309 | dt 9.794 +type train | step 825 | loss 219.8442 440.1011 614.7866 908.9291 1284.7803 1769.9583 2333.9866 3262.2856 4573.7568 6957.7422 11637.0264 21900.5918 | lr 5.0e-04 | norm 9903.8623 | dt 9.796 +type train | step 826 | loss 229.6924 458.6930 636.4758 928.9030 1302.1907 1791.8925 2369.1360 3300.7556 4612.1113 7040.8916 11826.8037 22322.8652 | lr 5.0e-04 | norm 10070.4033 | dt 9.785 +type train | step 827 | loss 216.4757 429.0970 602.0475 891.1552 1258.5791 1739.7371 2303.7698 3212.3845 4520.0664 6911.5815 11542.9229 21601.5898 | lr 5.0e-04 | norm 9366.6494 | dt 9.790 +type train | step 828 | loss 223.3268 442.4680 615.1526 904.2430 1284.6301 1751.2274 2312.3374 3223.1377 4532.1812 6909.3110 11643.6064 21724.2539 | lr 5.0e-04 | norm 13019.9971 | dt 9.774 +type train | step 829 | loss 227.2158 452.0396 622.4149 907.5288 1272.1888 1751.0881 2300.5276 3198.8264 4493.0879 6772.9658 11335.2686 21239.7031 | lr 5.0e-04 | norm 9498.3311 | dt 9.793 +type train | step 830 | loss 202.2733 418.6630 595.6738 884.9742 1266.7389 1750.2074 2328.4890 3278.7458 4717.9331 7300.0513 12507.8809 24302.4160 | lr 5.0e-04 | norm 23441.6484 | dt 9.775 +type train | step 831 | loss 215.2366 431.2209 608.2926 909.9011 1296.7783 1800.7183 2367.9097 3312.6179 4691.6484 7189.1807 12069.2598 22949.9531 | lr 5.0e-04 | norm 11625.2988 | dt 9.781 +type train | step 832 | loss 203.0756 400.7527 564.4757 840.0953 1209.0603 1676.2181 2234.5161 3154.8896 4481.6099 6855.0713 11478.0566 21528.3887 | lr 5.0e-04 | norm 10201.7891 | dt 9.781 +type train | step 833 | loss 215.4185 428.8776 601.9686 890.2075 1265.5049 1761.7073 2336.4541 3277.8652 4626.9111 7018.3779 11738.6123 21956.3906 | lr 5.0e-04 | norm 9349.9688 | dt 9.788 +type train | step 834 | loss 227.5259 454.4324 624.0115 913.1360 1285.5946 1779.5472 2341.3938 3282.3455 4585.1323 6947.0059 11650.8652 21966.9023 | lr 5.0e-04 | norm 9582.4648 | dt 9.781 +type train | step 835 | loss 216.0291 428.0901 599.4032 884.8145 1258.5548 1737.1279 2281.9780 3187.3516 4487.6577 6818.4067 11481.1621 21654.3613 | lr 5.0e-04 | norm 8271.3203 | dt 9.783 +type train | step 836 | loss 217.2752 431.5995 601.3720 884.0049 1257.4769 1728.9749 2282.1560 3173.3037 4488.0322 6768.4424 11366.7422 21340.0215 | lr 5.0e-04 | norm 10249.6953 | dt 9.786 +type train | step 837 | loss 210.8703 421.2800 594.9780 884.8069 1255.5007 1738.4895 2294.5212 3213.8833 4554.4692 6937.1777 11648.2168 21729.3438 | lr 5.0e-04 | norm 7647.6284 | dt 9.794 +type train | step 838 | loss 228.4981 450.6124 616.4088 900.2849 1275.4135 1754.0225 2316.6152 3232.8938 4569.7305 6980.8706 11779.0000 22331.2520 | lr 5.0e-04 | norm 11630.9492 | dt 9.776 +type train | step 839 | loss 217.8685 436.2386 613.6060 909.3081 1290.6251 1802.3518 2375.5139 3335.7148 4724.6045 7115.4932 11795.9512 21981.6934 | lr 5.0e-04 | norm 9224.9512 | dt 9.782 +type train | step 840 | loss 226.7012 454.5149 635.9132 929.2515 1315.2523 1814.0997 2393.0647 3336.9609 4664.7441 7060.0537 11820.3145 22212.6094 | lr 5.0e-04 | norm 11164.3076 | dt 9.796 +type train | step 841 | loss 222.9747 446.7501 619.8494 909.9574 1284.8448 1783.9619 2341.6492 3279.6519 4606.9917 6935.1011 11541.3643 21563.3594 | lr 5.0e-04 | norm 9486.7490 | dt 9.782 +type train | step 842 | loss 207.8154 410.4366 579.1805 856.9669 1225.0707 1691.0919 2255.2253 3125.0327 4475.2871 6781.7471 11422.7715 21557.8672 | lr 5.0e-04 | norm 9251.1113 | dt 9.792 +type train | step 843 | loss 221.0231 434.1065 607.5483 894.3499 1270.9432 1771.5178 2344.4155 3284.4014 4646.9253 7071.0190 11937.5879 22660.8574 | lr 5.0e-04 | norm 10894.7412 | dt 9.798 +type train | step 844 | loss 221.9114 438.1707 617.2283 920.4290 1297.6514 1812.5933 2425.0403 3422.0757 4814.6587 7319.3760 12252.7979 23369.0859 | lr 5.0e-04 | norm 14645.7275 | dt 9.755 +type train | step 845 | loss 199.9424 399.2994 567.4112 847.3674 1216.1638 1675.9967 2226.5200 3120.9509 4478.6729 6831.4824 11575.1250 21814.0176 | lr 5.0e-04 | norm 10820.9355 | dt 9.787 +type train | step 846 | loss 224.2656 443.5293 617.6746 905.9401 1273.6024 1752.2134 2287.9702 3180.0752 4439.2222 6770.1387 11223.2861 21202.6113 | lr 5.0e-04 | norm 15044.2129 | dt 9.783 +type train | step 847 | loss 205.5074 405.9976 574.2120 852.7278 1221.7773 1704.9606 2259.7075 3175.3960 4500.8120 6841.2852 11382.7715 21213.5000 | lr 5.0e-04 | norm 8941.9658 | dt 9.784 +type train | step 848 | loss 210.9929 419.5494 590.6989 875.8083 1245.6158 1722.0895 2281.4121 3178.4456 4527.5122 6890.5127 11573.4746 21615.5469 | lr 5.0e-04 | norm 9017.1924 | dt 9.791 +type train | step 849 | loss 216.5266 429.2190 603.3196 892.6888 1261.1230 1737.0099 2298.0503 3197.9319 4525.3784 6897.4502 11541.7773 21724.3301 | lr 5.0e-04 | norm 8618.1914 | dt 9.792 +type train | step 850 | loss 224.0181 446.4865 616.6176 899.3779 1273.6772 1761.4293 2331.9622 3255.2529 4531.9814 6797.1260 11036.3125 20447.2812 | lr 5.0e-04 | norm 10629.8760 | dt 9.776 +type train | step 851 | loss 204.3502 402.9069 567.5548 842.6400 1210.2931 1670.9126 2227.5903 3122.5208 4449.2666 6799.7935 11266.9297 20953.9551 | lr 5.0e-04 | norm 9972.4326 | dt 9.814 +type train | step 852 | loss 223.4896 442.4184 615.3558 908.4423 1273.2329 1769.2692 2325.1338 3250.1792 4558.3320 6928.5024 11538.2666 21788.7188 | lr 5.0e-04 | norm 11141.1211 | dt 9.781 +type train | step 853 | loss 208.3673 409.8145 570.7650 846.7115 1200.7241 1679.7408 2229.4131 3108.8909 4403.7617 6676.4297 11192.9053 21125.4082 | lr 5.0e-04 | norm 10418.6260 | dt 9.785 +type train | step 854 | loss 202.1667 400.9506 563.3019 842.8453 1212.1436 1688.3947 2249.5591 3171.1204 4534.2988 6948.6934 11485.1240 21219.4160 | lr 5.0e-04 | norm 9982.4375 | dt 9.786 +type train | step 855 | loss 207.2179 411.1127 579.4969 858.6699 1224.8510 1689.2736 2238.0056 3115.1367 4443.9756 6825.4468 11321.5098 21214.6621 | lr 5.0e-04 | norm 9342.0898 | dt 9.789 +type train | step 856 | loss 217.8246 432.0851 602.4495 887.0428 1253.2927 1737.0507 2308.9805 3232.6895 4566.8613 6986.5293 11659.0146 21914.7441 | lr 5.0e-04 | norm 9411.2402 | dt 9.780 +type train | step 857 | loss 201.4504 400.4024 565.6837 843.9905 1207.4714 1682.8171 2238.6792 3146.1987 4477.1045 6827.1406 11412.2441 21305.2148 | lr 5.0e-04 | norm 9607.0537 | dt 9.784 +type train | step 858 | loss 219.2876 436.4592 609.9521 906.4296 1277.9199 1779.3206 2354.7158 3307.5295 4623.3774 7026.7563 11692.8252 21999.4336 | lr 5.0e-04 | norm 9234.1631 | dt 9.785 +type train | step 859 | loss 208.7638 412.7661 576.0557 855.1904 1216.2749 1682.9008 2236.9285 3141.8540 4452.6680 6779.5908 11430.9531 21383.4121 | lr 5.0e-04 | norm 10076.1260 | dt 9.776 +type train | step 860 | loss 201.2202 398.7419 561.9734 831.0167 1185.9758 1640.5040 2180.8455 3064.0952 4380.1865 6682.5127 11229.3965 20956.3672 | lr 5.0e-04 | norm 9178.0654 | dt 9.781 +type train | step 861 | loss 213.0572 423.4493 590.6282 871.7135 1232.1873 1708.0562 2253.3015 3152.7214 4446.4932 6800.2358 11350.1484 21131.6191 | lr 5.0e-04 | norm 8601.8740 | dt 10.148 +type train | step 862 | loss 191.7460 378.8719 542.0286 811.2659 1166.4487 1637.2045 2183.3853 3085.0422 4416.7017 6770.8691 11421.6279 21310.8887 | lr 5.0e-04 | norm 11412.0967 | dt 9.781 +type train | step 863 | loss 201.2160 400.0115 564.5753 843.5894 1205.8749 1673.0510 2227.1326 3119.3286 4442.4824 6856.9717 11490.1855 21492.4629 | lr 5.0e-04 | norm 10658.5176 | dt 9.772 +type train | step 864 | loss 209.6440 413.7085 581.2470 857.9671 1215.4058 1689.8007 2235.5625 3129.2183 4424.3823 6737.9976 11273.0713 21082.5996 | lr 5.0e-04 | norm 8857.1211 | dt 9.781 +type train | step 865 | loss 187.9272 371.6962 529.5613 801.3013 1154.5453 1623.9763 2167.1926 3059.4565 4403.7075 6797.7700 11508.6436 21790.2695 | lr 5.0e-04 | norm 12057.2002 | dt 9.770 +type train | step 866 | loss 218.3894 436.3930 605.3832 890.2292 1255.1862 1729.5535 2271.3474 3172.4285 4415.7471 6674.4917 11055.1875 20556.3047 | lr 5.0e-04 | norm 10201.1709 | dt 9.776 +type train | step 867 | loss 188.3897 373.3273 535.6253 808.4847 1160.7058 1627.3612 2168.3872 3051.1348 4384.1543 6738.1216 11254.5205 20857.3086 | lr 5.0e-04 | norm 9519.8838 | dt 9.773 +type train | step 868 | loss 216.5464 431.4276 602.9431 900.9076 1266.5999 1743.3348 2311.3838 3240.9978 4533.3652 6907.5781 11489.2520 21448.1641 | lr 5.0e-04 | norm 8854.3857 | dt 9.790 +type train | step 869 | loss 188.3176 373.3665 535.7969 809.5224 1165.7227 1634.3743 2181.8323 3062.0024 4386.4468 6723.3628 11254.9531 20978.4414 | lr 5.0e-04 | norm 9322.9287 | dt 9.779 +type train | step 870 | loss 228.1688 451.5919 618.3461 903.9789 1263.1715 1768.0311 2335.4707 3256.5166 4547.2690 6860.0708 11381.6875 20919.7227 | lr 5.0e-04 | norm 9499.4512 | dt 9.775 +type train | step 871 | loss 213.3931 424.0367 594.6097 879.9070 1240.4196 1736.0901 2307.4631 3272.7273 4559.2417 6857.6489 11371.8184 20894.7305 | lr 5.0e-04 | norm 8457.8086 | dt 9.795 +type train | step 872 | loss 219.0102 436.6859 604.1274 887.1725 1244.6187 1714.6512 2266.8801 3142.7600 4437.8286 6726.5850 11244.2627 20881.2461 | lr 5.0e-04 | norm 8723.6914 | dt 9.789 +type train | step 873 | loss 194.8649 387.8045 551.6030 827.3329 1183.0886 1642.2290 2176.1877 3045.3606 4350.0518 6657.2764 11193.9795 20704.5469 | lr 5.0e-04 | norm 8448.2188 | dt 9.788 +type train | step 874 | loss 192.9044 379.7080 533.1152 802.3653 1154.3832 1614.2816 2150.9116 3024.4893 4324.7544 6610.6924 11085.8213 20701.0742 | lr 5.0e-04 | norm 11161.1904 | dt 9.771 +type train | step 875 | loss 241.2629 483.8637 653.5076 958.6711 1335.1870 1893.2745 2516.3618 3528.4543 4904.4893 7279.6504 11888.9482 21656.0078 | lr 5.0e-04 | norm 9739.1338 | dt 9.771 +type train | step 876 | loss 200.2899 395.5484 558.5468 833.1403 1192.3608 1657.6752 2198.6443 3101.1594 4366.2700 6628.2832 11116.1006 20684.4297 | lr 5.0e-04 | norm 10561.9844 | dt 9.774 +type train | step 877 | loss 238.6008 472.1720 654.6129 963.1543 1349.1062 1852.9780 2441.2341 3433.9766 4732.4155 7131.7070 11807.2471 21723.5391 | lr 5.0e-04 | norm 11597.9014 | dt 9.797 +type train | step 878 | loss 207.0184 407.5342 574.5167 860.7194 1215.8872 1699.6404 2258.9854 3195.8369 4507.8550 6889.0293 11676.3633 21776.7227 | lr 5.0e-04 | norm 9934.6680 | dt 9.787 +type train | step 879 | loss 212.0688 420.1724 584.8245 877.3846 1236.8405 1719.2126 2270.7727 3186.5095 4470.8511 6827.0737 11549.4814 21658.7109 | lr 5.0e-04 | norm 10073.7910 | dt 9.785 +type train | step 880 | loss 200.2563 396.0668 556.8812 827.2860 1171.4188 1623.8160 2160.1589 3036.7983 4306.0493 6596.8618 11033.8818 20443.1816 | lr 5.0e-04 | norm 9486.5850 | dt 9.797 +type train | step 881 | loss 207.2076 413.0568 581.2318 863.9446 1215.4673 1677.3727 2241.1240 3106.0869 4384.0688 6681.2061 11244.0693 20928.0879 | lr 5.0e-04 | norm 7866.3022 | dt 9.797 +type train | step 882 | loss 195.9283 385.3231 544.1931 820.3674 1174.1382 1651.4011 2213.4978 3137.5847 4456.1489 6849.7510 11493.5498 21477.1797 | lr 5.0e-04 | norm 10129.0811 | dt 9.781 +type train | step 883 | loss 201.6842 401.0722 565.3175 840.6639 1195.8396 1656.7313 2193.1997 3059.7466 4348.5483 6623.6025 11090.4639 20526.6562 | lr 5.0e-04 | norm 7863.0220 | dt 9.787 +type train | step 884 | loss 216.6320 430.3584 605.0908 905.3253 1278.9542 1786.6313 2357.2214 3305.0039 4631.8701 7078.1953 12028.6191 22866.7734 | lr 5.0e-04 | norm 15728.7461 | dt 9.758 +type train | step 885 | loss 195.1135 396.2286 560.0578 842.8097 1192.5319 1644.7161 2191.3354 3076.3628 4361.3345 6663.1367 11247.4932 21019.5859 | lr 5.0e-04 | norm 11150.1797 | dt 9.786 +type train | step 886 | loss 204.0842 416.5422 578.6453 855.8870 1221.6150 1673.7596 2223.8774 3130.0894 4368.0674 6644.6875 11148.8271 20747.5996 | lr 5.0e-04 | norm 16591.2207 | dt 9.774 +type train | step 887 | loss 240.5154 473.2708 663.1074 973.7523 1388.9072 1920.4373 2545.3430 3524.4758 4834.1992 7107.2188 11267.3965 20457.2715 | lr 5.0e-04 | norm 15772.6055 | dt 9.760 +type train | step 888 | loss 193.8175 382.1868 542.7636 814.6554 1162.8474 1623.0289 2179.6228 3075.0066 4391.6260 6730.2744 11293.6602 21001.8320 | lr 5.0e-04 | norm 11782.5801 | dt 9.776 +type train | step 889 | loss 202.1974 402.0706 562.4969 842.1187 1190.9348 1653.1575 2201.3386 3076.1875 4368.8589 6655.4917 11170.4502 20943.2031 | lr 5.0e-04 | norm 11409.3340 | dt 9.802 +type train | step 890 | loss 203.9454 404.1576 567.4671 846.7015 1197.9884 1664.6226 2215.3096 3098.9534 4375.0840 6692.8921 11169.3574 20699.1699 | lr 5.0e-04 | norm 10129.7949 | dt 9.800 +type train | step 891 | loss 206.2371 409.7236 576.0087 855.2108 1209.6976 1678.2653 2233.6985 3121.1917 4410.4009 6736.6904 11245.6377 20863.4355 | lr 5.0e-04 | norm 9589.2910 | dt 9.791 +type train | step 892 | loss 195.4858 387.1137 545.9683 817.8693 1168.5828 1617.8713 2162.9492 3028.4980 4300.9766 6586.5474 11063.2324 20454.2188 | lr 5.0e-04 | norm 9312.5615 | dt 9.793 +type train | step 893 | loss 192.7491 379.1874 534.8287 802.8072 1138.5718 1593.6560 2122.5232 2974.9719 4248.4946 6522.6318 11042.7197 20500.3281 | lr 5.0e-04 | norm 8839.2744 | dt 9.790 +type train | step 894 | loss 219.3464 436.8821 605.8586 885.7289 1238.5201 1699.7988 2250.0454 3116.4509 4350.8765 6590.7710 11075.0459 20678.4316 | lr 5.0e-04 | norm 9250.0176 | dt 9.783 +type train | step 895 | loss 203.6040 405.7370 573.4254 857.9827 1218.4288 1684.5316 2235.6675 3118.2178 4420.1689 6737.0684 11306.3340 20926.8145 | lr 5.0e-04 | norm 8541.0605 | dt 9.786 +type train | step 896 | loss 201.8512 400.6295 560.0895 836.3380 1171.9097 1628.8641 2162.7231 3006.6067 4238.7793 6394.6953 10653.9795 19672.0840 | lr 5.0e-04 | norm 8883.8330 | dt 9.795 +type train | step 897 | loss 180.9841 356.8868 512.7947 781.7610 1119.0753 1577.7875 2123.9031 3005.1284 4277.8506 6556.6104 10998.1533 20376.7129 | lr 5.0e-04 | norm 9790.0645 | dt 9.773 +type train | step 898 | loss 198.0849 393.6776 557.9372 837.0349 1184.6071 1629.4619 2172.3464 3026.6667 4305.4844 6583.5278 11041.8711 20258.5938 | lr 5.0e-04 | norm 9215.2256 | dt 9.804 +type train | step 899 | loss 207.3495 406.9728 562.8423 835.2848 1173.7660 1630.9447 2169.8608 3043.0842 4280.5156 6525.8823 11019.4863 20463.8301 | lr 5.0e-04 | norm 10693.4219 | dt 9.781 +type train | step 900 | loss 208.1306 417.1328 585.6263 882.6647 1249.3839 1744.9115 2326.8035 3275.8616 4602.5444 7043.3193 11735.1367 21903.3496 | lr 5.0e-04 | norm 9276.8330 | dt 9.781 +type train | step 901 | loss 210.6866 418.9047 584.5249 873.5587 1219.0332 1696.4139 2248.9868 3145.0513 4392.3789 6715.3184 11127.0176 20487.9297 | lr 5.0e-04 | norm 12685.3604 | dt 9.780 +type train | step 902 | loss 195.1985 381.8834 537.3508 815.1722 1159.6813 1613.9783 2162.8376 3048.6765 4326.8008 6667.1621 11162.3926 20834.3828 | lr 5.0e-04 | norm 11304.4863 | dt 9.787 +type train | step 903 | loss 203.8647 400.2756 564.3450 849.4851 1194.9912 1655.9889 2204.3083 3055.9241 4335.1626 6631.6001 11076.5264 20353.6562 | lr 5.0e-04 | norm 10026.5859 | dt 9.810 +type train | step 904 | loss 182.0511 359.0077 515.8981 795.4852 1126.2715 1585.1653 2135.4890 3009.3975 4263.5518 6560.2764 10957.8457 20442.4512 | lr 5.0e-04 | norm 11457.8018 | dt 9.771 +type train | step 905 | loss 209.5171 411.3413 571.4579 856.9315 1201.9426 1678.7494 2242.9265 3172.1353 4417.0771 6671.1890 11174.2188 20872.8242 | lr 5.0e-04 | norm 12414.4785 | dt 9.785 +type train | step 906 | loss 208.8105 414.9288 577.3301 868.2557 1216.3429 1696.9314 2261.4399 3169.7275 4455.4766 6756.9526 11163.3125 20537.8867 | lr 5.0e-04 | norm 11245.6514 | dt 9.783 +type train | step 907 | loss 197.3101 388.3115 543.3901 824.1638 1157.9252 1604.8776 2130.7537 2991.2937 4241.7744 6525.9556 10994.4170 20284.6074 | lr 5.0e-04 | norm 9715.5020 | dt 9.780 +type train | step 908 | loss 199.9166 395.2209 554.5486 841.5110 1174.7715 1628.0833 2162.4851 3023.8528 4284.0088 6564.2153 11010.9121 20140.0781 | lr 5.0e-04 | norm 8730.0117 | dt 9.778 +type train | step 909 | loss 201.4497 397.7828 558.6647 842.3995 1186.2197 1656.5771 2201.8442 3083.0229 4358.2915 6658.7002 11097.2881 20260.4551 | lr 5.0e-04 | norm 8154.0034 | dt 9.809 +type train | step 910 | loss 203.8465 405.0257 566.2535 848.4048 1188.6244 1641.3610 2187.2061 3073.1331 4325.6143 6603.9038 11128.4268 20579.6348 | lr 5.0e-04 | norm 10665.8516 | dt 9.785 +type train | step 911 | loss 195.8364 387.2808 547.0784 827.4271 1163.4534 1626.8541 2168.7078 3057.8604 4325.2007 6703.2412 11480.6016 21699.4980 | lr 5.0e-04 | norm 15855.0967 | dt 9.793 +type train | step 912 | loss 210.8144 417.0968 580.5391 861.7614 1205.7424 1658.0010 2192.6565 3080.6685 4317.6094 6589.7798 11052.5645 20286.9121 | lr 5.0e-04 | norm 8468.0059 | dt 9.784 +type train | step 913 | loss 194.6149 383.3234 541.2385 817.8527 1142.5850 1584.4194 2115.0293 2973.5281 4214.6968 6495.4146 10899.4375 20087.5195 | lr 5.0e-04 | norm 9026.3916 | dt 9.786 +type train | step 914 | loss 196.5412 388.1909 548.1737 825.0842 1163.5778 1627.8823 2167.6658 3052.0718 4319.8804 6617.4448 11065.8008 20241.3457 | lr 5.0e-04 | norm 8356.8486 | dt 9.799 +type train | step 915 | loss 204.1339 404.2781 565.0702 843.4528 1186.2043 1635.2836 2159.1140 3005.6606 4244.1074 6508.0166 10894.8145 20034.8340 | lr 5.0e-04 | norm 7922.1318 | dt 9.800 +type train | step 916 | loss 207.8233 409.5325 568.9091 862.6859 1189.9825 1644.6844 2184.3452 3047.5835 4280.0337 6503.3066 10905.4658 20158.5059 | lr 5.0e-04 | norm 9714.5820 | dt 9.793 +type train | step 917 | loss 203.3413 401.1373 562.9302 850.9163 1188.0251 1659.0669 2210.5000 3125.4729 4373.9434 6667.9932 11162.5752 20508.2227 | lr 5.0e-04 | norm 8147.3472 | dt 9.786 +type train | step 918 | loss 212.4488 417.1703 584.3637 889.7568 1236.3885 1730.3608 2316.5811 3265.8862 4571.6763 6976.3623 11633.1621 21438.0938 | lr 5.0e-04 | norm 10151.5391 | dt 9.778 +type train | step 919 | loss 193.1951 383.8246 541.4022 825.7169 1157.4629 1607.1810 2139.8562 3010.7944 4269.1533 6544.6895 11052.7676 20595.6719 | lr 5.0e-04 | norm 8617.1318 | dt 9.770 +type train | step 920 | loss 196.5917 386.8170 545.8997 830.2835 1166.6646 1615.6371 2148.8818 3055.8987 4273.0850 6555.0444 10974.4785 20097.4531 | lr 5.0e-04 | norm 8177.2720 | dt 9.797 +type train | step 921 | loss 205.0458 405.6050 565.4285 854.2969 1190.4916 1649.3076 2201.4302 3104.6858 4360.2134 6692.3008 11358.1670 20824.8594 | lr 5.0e-04 | norm 9714.2832 | dt 9.775 +type train | step 922 | loss 191.8354 379.9294 537.5471 817.3585 1159.8336 1629.9055 2178.4138 3087.5869 4337.7529 6642.9023 11129.4844 20611.8633 | lr 5.0e-04 | norm 8975.5693 | dt 9.789 +type train | step 923 | loss 208.4471 413.0394 575.4679 866.6564 1207.8810 1681.1586 2227.3745 3123.8735 4379.6348 6705.0312 11325.3701 20905.5605 | lr 5.0e-04 | norm 9397.1758 | dt 9.786 +type train | step 924 | loss 204.9095 406.2117 570.7446 857.1948 1198.6987 1671.2734 2210.9736 3107.7126 4346.0049 6635.7832 11103.1006 20401.1816 | lr 5.0e-04 | norm 7881.3877 | dt 9.781 +type train | step 925 | loss 196.4987 388.9769 549.1464 829.5488 1171.2347 1617.5061 2148.9116 3020.3425 4275.6333 6607.1748 11167.4844 20643.7734 | lr 5.0e-04 | norm 8646.1934 | dt 9.786 +type train | step 926 | loss 188.3596 370.3833 525.7535 802.2230 1126.7009 1577.9399 2115.6731 3008.5393 4226.4624 6542.1948 11044.0967 20422.9336 | lr 5.0e-04 | norm 8973.4414 | dt 9.789 +type train | step 927 | loss 199.3478 394.5069 550.6194 826.6165 1159.4211 1611.5739 2148.0361 3032.1035 4246.0767 6556.6572 11068.0029 20446.2461 | lr 5.0e-04 | norm 9205.7471 | dt 9.785 +type train | step 928 | loss 190.6097 377.7565 536.8379 817.2939 1151.7487 1608.4550 2158.0215 3064.3896 4319.5459 6666.2632 11188.0605 20597.9902 | lr 5.0e-04 | norm 8355.5527 | dt 9.794 +type train | step 929 | loss 206.1783 406.4636 562.7867 846.8298 1191.3794 1652.1421 2208.0869 3126.3005 4356.5269 6660.7588 11201.3418 20817.3086 | lr 5.0e-04 | norm 9742.5820 | dt 9.780 +type train | step 930 | loss 185.9992 369.3215 527.3013 805.5210 1141.3398 1594.6093 2133.9316 3027.6667 4298.3159 6622.3613 11184.1084 20683.6055 | lr 5.0e-04 | norm 9104.5498 | dt 9.781 +type train | step 931 | loss 184.7637 361.6177 512.5672 778.8937 1106.5270 1544.6973 2076.1089 2956.1460 4190.9033 6464.6592 10870.4463 20010.2148 | lr 5.0e-04 | norm 9362.0771 | dt 9.785 +type train | step 932 | loss 189.0172 374.7798 533.2390 812.8983 1147.7970 1583.3688 2118.1667 2973.2388 4197.1670 6488.7705 10932.3945 20123.8242 | lr 5.0e-04 | norm 8773.1758 | dt 9.802 +type train | step 933 | loss 192.5792 378.1653 534.1443 809.4220 1141.8287 1588.3862 2132.0767 3022.1721 4236.0762 6493.0444 10904.7979 20002.3223 | lr 5.0e-04 | norm 7728.1182 | dt 9.779 +type train | step 934 | loss 213.1229 424.1594 593.7256 886.4728 1232.8105 1696.4178 2242.1907 3162.4661 4366.7368 6676.4644 11269.6562 20784.2852 | lr 5.0e-04 | norm 10460.6426 | dt 9.784 +type train | step 935 | loss 192.2693 377.3488 534.9863 816.8120 1153.8094 1612.0355 2147.7849 3038.7065 4280.1816 6604.3462 11075.6602 20407.6387 | lr 5.0e-04 | norm 8330.9941 | dt 9.786 +type train | step 936 | loss 198.2377 391.5599 549.9199 825.9175 1169.7686 1637.5208 2177.6831 3104.3833 4312.2773 6620.5713 11131.3252 20485.7656 | lr 5.0e-04 | norm 8893.5195 | dt 9.784 +type train | step 937 | loss 169.9439 336.1728 486.4207 753.1142 1074.8606 1517.7708 2062.9304 2945.2966 4152.1743 6415.0459 10868.2939 20291.7441 | lr 5.0e-04 | norm 10669.2285 | dt 9.790 +type train | step 938 | loss 184.5341 364.7864 521.7961 795.0372 1120.8849 1555.2538 2082.7590 2938.2163 4127.7808 6321.7373 10561.3076 19352.5469 | lr 5.0e-04 | norm 9090.5674 | dt 9.791 +type train | step 939 | loss 184.0809 360.0945 509.6652 773.6522 1097.1466 1529.1331 2050.4119 2909.1582 4089.1094 6277.3115 10539.9658 19272.9727 | lr 5.0e-04 | norm 7799.5503 | dt 9.796 +type train | step 940 | loss 198.6530 393.5268 550.7766 820.0326 1152.3818 1600.8198 2159.5515 3043.1497 4267.1782 6551.4805 10903.9141 19976.5332 | lr 5.0e-04 | norm 9633.7959 | dt 9.793 +type train | step 941 | loss 192.1340 379.6824 537.4938 819.4331 1142.1008 1583.5835 2114.6213 2985.8315 4165.4897 6383.2627 10713.6348 19666.9805 | lr 5.0e-04 | norm 7976.2637 | dt 9.777 +type train | step 942 | loss 200.0501 392.0023 547.0518 825.2642 1151.4650 1591.4216 2119.2993 2985.3450 4137.1763 6300.6636 10487.1094 19181.1133 | lr 5.0e-04 | norm 9306.9355 | dt 9.776 +type train | step 943 | loss 191.9770 377.2017 535.2997 818.8972 1153.5200 1601.5963 2133.2520 3026.8523 4241.1968 6510.9023 11026.8252 20401.9980 | lr 5.0e-04 | norm 8556.8115 | dt 9.782 +type train | step 944 | loss 185.1498 357.6632 508.6747 780.6415 1103.7738 1527.4258 2036.6301 2872.3765 4026.4756 6215.4194 10556.8662 19573.7285 | lr 5.0e-04 | norm 13287.4590 | dt 9.776 +type train | step 945 | loss 178.3086 352.2156 505.4223 769.5361 1088.7676 1534.6384 2073.9673 2952.2351 4156.0156 6388.5083 10767.2637 20122.5332 | lr 5.0e-04 | norm 9328.8975 | dt 9.785 +type train | step 946 | loss 184.4802 365.0924 519.4678 788.6193 1116.0956 1564.2526 2099.9939 2978.8167 4164.4761 6354.3018 10655.0391 19661.0000 | lr 5.0e-04 | norm 8999.4512 | dt 9.785 +type train | step 947 | loss 193.8322 385.6292 543.3757 816.9931 1150.2383 1596.3044 2137.7749 3020.1367 4222.6841 6509.7358 10958.4854 20293.9414 | lr 5.0e-04 | norm 8890.5176 | dt 9.783 +type train | step 948 | loss 182.2621 362.3582 516.5081 789.8069 1127.2972 1576.9968 2135.0835 3025.6921 4256.9268 6567.0210 11028.1279 20395.9648 | lr 5.0e-04 | norm 9380.8760 | dt 9.824 +type train | step 949 | loss 183.2833 360.1339 511.4018 774.9028 1104.4138 1534.9685 2063.0325 2913.2998 4100.1074 6325.9731 10717.0273 19821.6328 | lr 5.0e-04 | norm 8672.1748 | dt 9.831 +type train | step 950 | loss 192.6519 379.5876 532.3206 802.0741 1127.8878 1587.2234 2149.0923 3064.6118 4280.0254 6548.7549 10969.6875 20087.2148 | lr 5.0e-04 | norm 7477.2231 | dt 9.815 +type train | step 951 | loss 202.8875 401.5245 558.0788 842.2432 1168.9677 1616.8135 2149.1213 3037.8340 4206.6274 6433.5464 10810.4482 19936.9727 | lr 5.0e-04 | norm 7931.2134 | dt 9.782 +type train | step 952 | loss 191.3234 375.1929 526.2801 793.5228 1119.7141 1577.1505 2124.5691 3023.8267 4199.0562 6457.0557 10813.1172 19952.0273 | lr 5.0e-04 | norm 8054.5977 | dt 9.789 +type train | step 953 | loss 181.5121 358.0336 508.2428 770.3079 1099.4950 1542.3826 2076.7324 2963.9482 4159.0444 6384.1484 10612.5205 19503.4004 | lr 5.0e-04 | norm 8794.2539 | dt 9.784 +type train | step 954 | loss 189.1303 371.0454 520.3209 789.1022 1117.9138 1573.9996 2119.1206 3005.1384 4193.4741 6439.4683 10872.2754 20099.5508 | lr 5.0e-04 | norm 8079.2046 | dt 9.783 +type train | step 955 | loss 189.6309 371.7338 522.7829 791.8844 1115.0884 1556.6626 2092.2954 2955.6536 4162.8413 6374.8179 10721.4092 19949.6211 | lr 5.0e-04 | norm 9521.2393 | dt 9.778 +type train | step 956 | loss 182.2185 356.2580 505.2928 768.7167 1091.2865 1533.0144 2083.2485 2925.3022 4093.1069 6285.1465 10598.3809 19542.4004 | lr 5.0e-04 | norm 8484.5859 | dt 9.788 +type train | step 957 | loss 183.4653 359.8004 509.1161 770.9678 1092.9105 1525.0677 2064.0415 2900.5327 4098.2178 6356.9507 10691.6738 19681.7812 | lr 5.0e-04 | norm 8150.8101 | dt 9.788 +type train | step 958 | loss 189.5338 375.6926 534.6343 814.8373 1156.5038 1618.2582 2197.1467 3121.7747 4366.4849 6693.5537 11018.6582 20225.4629 | lr 5.0e-04 | norm 8445.3555 | dt 9.794 +type train | step 959 | loss 184.0036 362.4565 513.8291 778.4940 1106.9478 1526.0537 2078.2153 2884.1826 4066.4124 6241.8901 10432.7275 19158.7910 | lr 5.0e-04 | norm 7559.8101 | dt 9.787 +type train | step 960 | loss 204.9101 404.8571 574.1971 861.9987 1210.5826 1677.7045 2243.6582 3107.9514 4352.2939 6652.5591 11040.4619 20341.5898 | lr 5.0e-04 | norm 9672.7920 | dt 9.767 +type train | step 961 | loss 187.9341 369.7936 521.1368 793.2116 1119.5481 1564.4639 2116.2756 2952.7314 4094.8843 6306.0322 10552.7861 19465.9238 | lr 5.0e-04 | norm 8728.9746 | dt 9.782 +type train | step 962 | loss 201.2547 392.1928 542.8975 820.6303 1146.7948 1616.9617 2207.5110 3101.7646 4245.6313 6487.2759 10842.7568 20297.8594 | lr 5.0e-04 | norm 12578.4629 | dt 9.764 +type train | step 963 | loss 209.8613 415.0168 573.6481 855.3514 1187.9183 1656.4711 2232.8367 3100.1436 4207.3232 6396.2500 10573.4922 19560.3359 | lr 5.0e-04 | norm 9382.0625 | dt 9.765 +type train | step 964 | loss 175.9891 346.3172 495.5347 754.7046 1077.8129 1507.1357 2056.5200 2883.4302 4048.8604 6257.1489 10501.5811 19560.6406 | lr 5.0e-04 | norm 9138.1367 | dt 9.790 +type train | step 965 | loss 188.1856 370.8896 523.3722 792.9662 1110.7842 1561.1656 2119.1663 2959.8079 4138.5386 6349.2031 10579.9258 19369.9727 | lr 5.0e-04 | norm 8294.1211 | dt 9.795 +type train | step 966 | loss 187.7614 375.7529 531.6370 810.1558 1155.5175 1607.0934 2192.5364 3058.6880 4273.7456 6583.4800 10929.6738 20303.5918 | lr 5.0e-04 | norm 9575.4873 | dt 9.776 +type train | step 967 | loss 201.2124 400.5401 564.3424 850.9565 1193.2570 1639.0447 2200.5935 3062.4883 4280.9727 6617.5996 11086.2705 20501.6113 | lr 5.0e-04 | norm 10536.1094 | dt 9.778 +type train | step 968 | loss 174.8442 343.9034 492.0652 752.8044 1075.7677 1512.5601 2059.1968 2904.5066 4097.1606 6294.1055 10479.8623 19304.0059 | lr 5.0e-04 | norm 8055.5596 | dt 9.795 +type train | step 969 | loss 187.2896 368.0898 525.9507 803.2540 1135.2612 1582.1353 2129.9363 2972.6948 4170.7778 6370.3916 10651.9932 19602.2793 | lr 5.0e-04 | norm 7988.7446 | dt 9.796 +type train | step 970 | loss 191.8763 381.5532 541.7385 819.6445 1153.4637 1610.5276 2198.8955 3058.0684 4230.8711 6441.3540 10577.6309 19481.6055 | lr 5.0e-04 | norm 9633.1416 | dt 9.785 +type train | step 971 | loss 207.9134 412.8103 578.3366 860.9852 1205.4185 1666.7760 2247.4304 3122.8567 4288.1509 6539.8354 10685.6836 19596.3633 | lr 5.0e-04 | norm 8174.0435 | dt 9.795 +type train | step 972 | loss 177.8798 350.3680 505.9807 770.8680 1107.4133 1537.3478 2095.6826 2940.4475 4158.2661 6419.9092 10741.7041 19847.7871 | lr 5.0e-04 | norm 7682.6089 | dt 9.787 +type train | step 973 | loss 186.2337 367.1576 515.0508 776.8251 1099.1919 1527.1982 2082.0020 2891.1841 4067.3779 6273.5322 10423.4678 19129.4102 | lr 5.0e-04 | norm 7473.8892 | dt 9.802 +type train | step 974 | loss 174.4518 345.5727 495.1348 753.7578 1071.9141 1494.9839 2020.5214 2823.5254 3977.4734 6127.8564 10296.7188 19060.5215 | lr 5.0e-04 | norm 7023.9507 | dt 9.780 +type train | step 975 | loss 170.3334 334.8669 475.6811 726.0062 1042.1749 1465.4692 2001.3684 2808.3152 3967.3223 6154.5645 10297.3164 19049.4824 | lr 5.0e-04 | norm 7541.9971 | dt 9.782 +type train | step 976 | loss 180.0169 355.2725 506.6060 767.2666 1097.6752 1540.3032 2097.4006 2942.4058 4146.7217 6397.0664 10651.1074 19614.7363 | lr 5.0e-04 | norm 7021.4170 | dt 9.806 +type train | step 977 | loss 182.1244 359.3443 510.2165 773.7657 1096.4714 1535.9705 2102.5654 2945.9380 4119.2773 6388.5942 10670.5332 19698.6523 | lr 5.0e-04 | norm 8388.3154 | dt 9.782 +type train | step 978 | loss 200.7115 392.3488 548.7476 826.2408 1152.5774 1586.9368 2147.2300 2960.6250 4113.4707 6271.2754 10331.5801 19082.4863 | lr 5.0e-04 | norm 8607.7520 | dt 9.767 +type train | step 979 | loss 199.4410 392.0879 548.1324 822.6581 1149.7681 1588.9557 2154.1914 2985.3279 4124.0508 6328.1265 10498.0137 19514.5488 | lr 5.0e-04 | norm 9060.7432 | dt 9.789 +type train | step 980 | loss 194.6532 382.8930 539.0455 813.0410 1141.0021 1583.7570 2143.4167 2978.6492 4141.3198 6377.4385 10556.6221 19575.9746 | lr 5.0e-04 | norm 8275.1113 | dt 9.787 +type train | step 981 | loss 225.2205 453.5687 615.9157 915.5465 1258.1643 1753.2970 2377.6758 3259.9692 4533.5342 6865.2109 11160.1221 20032.5254 | lr 5.0e-04 | norm 11148.5859 | dt 9.767 +type train | step 982 | loss 180.4540 354.1120 505.9673 769.0547 1089.4264 1515.6698 2063.4656 2861.0527 4046.2029 6241.3394 10411.6221 19167.4570 | lr 5.0e-04 | norm 8203.0439 | dt 9.787 +type train | step 983 | loss 153.5665 301.5355 437.4083 684.3972 995.9342 1405.9036 1943.9675 2745.8291 3949.6079 6174.5308 10366.4424 19343.0039 | lr 5.0e-04 | norm 10133.2256 | dt 9.775 +type train | step 984 | loss 172.4251 341.7670 488.7117 745.7099 1065.3369 1488.6527 2028.0936 2830.0186 4015.4043 6199.2388 10302.7109 18980.1328 | lr 5.0e-04 | norm 7932.4136 | dt 9.795 +type train | step 985 | loss 178.3018 347.3602 494.9810 754.9442 1065.7388 1492.5767 2015.2590 2827.2229 3985.6321 6139.9775 10217.6934 18802.0762 | lr 5.0e-04 | norm 7457.7681 | dt 9.798 +type train | step 986 | loss 184.7148 364.8221 516.7234 787.3028 1115.4917 1556.2960 2106.6975 2941.4990 4118.0405 6359.7690 10505.6836 19316.9062 | lr 5.0e-04 | norm 7106.4365 | dt 9.791 +type train | step 987 | loss 205.4166 409.0003 569.6470 875.0672 1229.3553 1731.9047 2350.0718 3292.6704 4512.4097 6907.6924 11459.2393 21571.7109 | lr 5.0e-04 | norm 12107.8926 | dt 9.776 +type train | step 988 | loss 211.0285 413.8936 571.3135 856.6755 1185.4839 1646.4235 2211.0122 3052.1555 4195.4707 6404.6338 10485.3945 19348.8828 | lr 5.0e-04 | norm 8815.2510 | dt 9.781 +type train | step 989 | loss 188.1049 371.0497 526.7004 795.6090 1119.7268 1565.1992 2119.8723 2932.5879 4098.5132 6316.4058 10461.1543 19334.2930 | lr 5.0e-04 | norm 7723.9971 | dt 9.783 +type train | step 990 | loss 194.7580 384.9485 537.4897 808.6104 1130.8552 1572.7091 2129.5244 2950.1143 4104.0249 6344.1143 10422.0986 19283.8691 | lr 5.0e-04 | norm 7959.3740 | dt 9.782 +type train | step 991 | loss 182.7367 358.6445 506.8842 766.7646 1086.4465 1511.2650 2068.0205 2874.2832 4016.8059 6189.8564 10223.6748 18993.2148 | lr 5.0e-04 | norm 8643.3457 | dt 9.794 +type train | step 992 | loss 181.4011 358.5331 505.0569 765.8334 1076.8213 1511.4524 2070.3684 2891.5315 4043.1338 6342.0610 10571.0381 19725.0020 | lr 5.0e-04 | norm 11320.0342 | dt 9.783 +type train | step 993 | loss 197.4067 386.3889 540.3556 812.5809 1138.7894 1578.0149 2126.5938 2928.9927 4027.2273 6213.0063 10149.1777 18808.1367 | lr 5.0e-04 | norm 8902.9131 | dt 9.775 +type train | step 994 | loss 176.5590 345.1789 489.2217 751.0012 1066.8536 1512.2031 2061.4170 2882.3977 4054.3477 6317.7617 10463.3594 19463.2480 | lr 5.0e-04 | norm 8833.6875 | dt 9.775 +type train | step 995 | loss 181.8847 357.6772 509.3907 775.2641 1098.5004 1522.2186 2073.4055 2885.1729 4068.1953 6342.9834 10467.4990 19383.6270 | lr 5.0e-04 | norm 8994.4912 | dt 9.774 +type train | step 996 | loss 179.4306 353.8904 500.7944 772.0955 1102.9613 1569.0897 2141.2915 3007.6829 4206.3481 6574.5605 10938.0293 20461.6660 | lr 5.0e-04 | norm 9198.8818 | dt 9.787 +type train | step 997 | loss 167.7187 329.6922 475.0948 727.4550 1038.9963 1461.1443 1996.4584 2799.6855 3979.0171 6239.9937 10310.3730 19327.6934 | lr 5.0e-04 | norm 10763.8223 | dt 9.828 +type train | step 998 | loss 178.4299 353.6202 509.2830 782.0186 1112.6995 1567.9131 2135.7710 2991.8733 4200.0981 6495.3701 10699.3340 19753.2266 | lr 5.0e-04 | norm 8222.5098 | dt 9.831 +type train | step 999 | loss 182.6629 360.8153 512.9340 784.1912 1108.1516 1557.7811 2121.6250 2977.1011 4161.5698 6468.5010 10666.4443 19671.2871 | lr 5.0e-04 | norm 7648.7534 | dt 9.824 +type train | step 1000 | loss 193.2841 383.4294 536.4089 804.6520 1134.5203 1573.5819 2123.4272 2958.9958 4117.3071 6354.7944 10438.1455 19266.3340 | lr 5.0e-04 | norm 8503.9678 | dt 9.827 +type train | step 1001 | loss 189.7208 372.4745 524.0937 797.6953 1121.0331 1572.2319 2129.7773 2984.9346 4153.0181 6406.8135 10528.1680 19307.5742 | lr 5.0e-04 | norm 7650.9644 | dt 9.793 +type train | step 1002 | loss 189.3557 370.7829 520.1307 782.8370 1098.7058 1548.7228 2100.0132 2914.7542 4042.0244 6293.0752 10333.4219 19073.8359 | lr 5.0e-04 | norm 7662.7368 | dt 9.783 +type train | step 1003 | loss 177.2981 349.4783 496.1641 755.8187 1066.6445 1501.0054 2041.9055 2847.2961 4011.7886 6234.8442 10336.6982 19103.6426 | lr 5.0e-04 | norm 7504.4849 | dt 9.776 +type train | step 1004 | loss 177.5562 351.1443 498.5442 761.6721 1077.9099 1498.9978 2033.3516 2826.2229 3970.8804 6198.5879 10245.9570 18912.1777 | lr 5.0e-04 | norm 7560.2129 | dt 9.799 +type train | step 1005 | loss 187.7843 368.2599 526.6685 809.1875 1127.1511 1568.8198 2131.7190 2952.4785 4158.8267 6483.8848 10689.4082 19731.3359 | lr 5.0e-04 | norm 8277.7354 | dt 9.793 +type train | step 1006 | loss 182.0272 359.4733 507.9872 772.2671 1090.6394 1507.6307 2045.3230 2860.1787 4013.8684 6250.0825 10349.9814 19035.9980 | lr 5.0e-04 | norm 6909.5186 | dt 9.786 +type train | step 1007 | loss 165.6464 324.4062 469.1717 732.8072 1043.4185 1469.2755 2016.2532 2849.0020 4050.4053 6311.9092 10509.2930 19544.7949 | lr 5.0e-04 | norm 11848.1299 | dt 9.778 +type train | step 1008 | loss 176.6729 348.1938 501.7456 782.5453 1092.6382 1519.3479 2084.0554 2897.7871 4102.8291 6404.0415 10592.4033 19568.1758 | lr 5.0e-04 | norm 9516.4033 | dt 9.803 +type train | step 1009 | loss 183.4609 359.3513 504.8626 781.9005 1092.4644 1535.0942 2084.0491 2922.1904 4066.5298 6285.2983 10301.4561 19217.4902 | lr 5.0e-04 | norm 8870.7715 | dt 9.776 +type train | step 1010 | loss 191.1882 374.1537 524.9570 797.2507 1108.5836 1552.3993 2105.1445 2935.0195 4085.9790 6324.2305 10371.2168 19140.1445 | lr 5.0e-04 | norm 7886.8931 | dt 9.777 +type train | step 1011 | loss 177.4080 349.8849 494.1328 756.2938 1062.3051 1480.1842 2024.9426 2827.4214 3966.6438 6206.6611 10353.0254 19277.0625 | lr 5.0e-04 | norm 9160.2695 | dt 9.780 +type train | step 1012 | loss 192.9790 378.9502 535.5753 817.6339 1144.9614 1589.6675 2140.0215 2976.2339 4145.0347 6392.5947 10458.7256 19319.8027 | lr 5.0e-04 | norm 9001.5615 | dt 9.797 +type train | step 1013 | loss 183.5592 366.9355 520.0829 799.5735 1123.6776 1576.5610 2152.4929 3016.8704 4218.1582 6552.3203 10894.2207 20270.5293 | lr 5.0e-04 | norm 9120.1855 | dt 9.796 +type train | step 1014 | loss 175.1849 343.8033 492.5276 758.9223 1072.9077 1490.9807 2027.6233 2832.1995 3998.9836 6204.5112 10293.8037 18960.2754 | lr 5.0e-04 | norm 7421.3257 | dt 9.785 +type train | step 1015 | loss 179.3481 353.2473 501.6246 762.7018 1080.7205 1498.5198 2029.2561 2821.3525 3954.0684 6088.4004 10006.9053 18342.4844 | lr 5.0e-04 | norm 7387.6172 | dt 9.777 +type train | step 1016 | loss 174.5544 341.9654 485.2414 757.9713 1055.2405 1483.8879 2021.9745 2844.4668 3973.1038 6165.4927 10200.9727 18855.7812 | lr 5.0e-04 | norm 7431.2197 | dt 9.783 +type train | step 1017 | loss 173.2595 340.4633 485.6413 751.6730 1057.2504 1479.2780 2015.9113 2821.5830 3981.5466 6142.6641 10154.1699 18804.5059 | lr 5.0e-04 | norm 7225.5342 | dt 9.800 +type train | step 1018 | loss 165.8504 323.7794 468.0653 731.0268 1033.1592 1439.6290 1966.5785 2762.3225 3909.9653 6081.2695 10068.7822 18541.1133 | lr 5.0e-04 | norm 7912.8047 | dt 9.797 +type train | step 1019 | loss 181.1183 354.9211 502.6626 773.7805 1074.3531 1497.0449 2032.0798 2831.9175 3981.9739 6141.6846 10147.5449 18699.8105 | lr 5.0e-04 | norm 7589.5054 | dt 9.785 +type train | step 1020 | loss 172.6099 339.0784 488.5277 759.1464 1067.5049 1499.5198 2051.1191 2883.5479 4079.0122 6320.3311 10479.9102 19351.5723 | lr 5.0e-04 | norm 7260.4653 | dt 9.785 +type train | step 1021 | loss 159.2195 313.7686 456.5004 715.7909 1013.5086 1421.5477 1956.6105 2757.5991 3941.8472 6162.3198 10288.4014 19157.4062 | lr 5.0e-04 | norm 8436.5566 | dt 9.782 +type train | step 1022 | loss 173.2484 340.3713 485.3357 768.8569 1062.6342 1489.7666 2024.1113 2832.3591 4014.5098 6255.0479 10377.6865 19142.4805 | lr 5.0e-04 | norm 7757.6919 | dt 9.790 +type train | step 1023 | loss 173.8545 340.6801 485.5395 752.8256 1050.5063 1467.1730 1985.6642 2771.1228 3902.3682 6008.2993 9913.9658 18267.5020 | lr 5.0e-04 | norm 7502.4546 | dt 9.782 +type train | step 1024 | loss 185.7152 362.7472 514.2358 799.5469 1110.2012 1534.7346 2079.0249 2879.3708 4031.5073 6182.9932 10237.8516 18838.0273 | lr 5.0e-04 | norm 11212.9531 | dt 9.779 +type train | step 1025 | loss 168.9414 332.2019 476.3014 762.1293 1061.5682 1516.6189 2109.0986 2999.9507 4232.8276 6570.3940 10825.5498 19952.1719 | lr 5.0e-04 | norm 8373.9746 | dt 9.788 +type train | step 1026 | loss 167.8446 329.7500 475.6404 756.7084 1039.0227 1443.5050 1973.5852 2772.9448 3923.9351 6112.7065 10193.6729 19039.7129 | lr 5.0e-04 | norm 9964.8154 | dt 9.798 +type train | step 1027 | loss 180.3037 352.3866 496.9577 773.3251 1066.4559 1489.7056 2027.6704 2834.0278 3961.1094 6113.6694 10099.9326 18673.2324 | lr 5.0e-04 | norm 8915.5400 | dt 9.784 +type train | step 1028 | loss 168.7290 331.3901 474.7377 745.2128 1035.7217 1448.8961 1975.3718 2775.8481 3920.2393 6108.7021 10121.0312 18762.7207 | lr 5.0e-04 | norm 8228.5977 | dt 9.790 +type train | step 1029 | loss 184.8065 365.0956 515.4512 809.0453 1098.1829 1527.3446 2069.1392 2868.5779 4031.5415 6226.6309 10316.5771 19074.7422 | lr 5.0e-04 | norm 7411.1465 | dt 9.792 +type train | step 1030 | loss 182.9831 360.8415 513.4968 806.9028 1101.4960 1529.0087 2063.6321 2866.9846 4001.1357 6171.9868 10189.3770 18955.7754 | lr 5.0e-04 | norm 7270.7969 | dt 9.785 +type train | step 1031 | loss 180.8974 350.3371 499.4918 780.7579 1067.8638 1500.7864 2040.0155 2845.2505 3967.0234 6063.0093 9985.5781 18550.5625 | lr 5.0e-04 | norm 7649.7393 | dt 9.780 +type train | step 1032 | loss 169.9606 333.8392 478.4430 763.2040 1053.3688 1482.5031 2029.5919 2840.3838 4006.1846 6191.0776 10209.6201 18718.5664 | lr 5.0e-04 | norm 7258.8711 | dt 9.789 +type train | step 1033 | loss 168.0101 331.2337 477.7796 760.2634 1044.9380 1466.6487 1997.7339 2814.0742 3971.6138 6175.1182 10210.1270 18885.3223 | lr 5.0e-04 | norm 7002.5396 | dt 9.788 +type train | step 1034 | loss 173.0526 342.4899 491.0989 774.1570 1065.5548 1487.3030 2026.9111 2842.2305 4021.1580 6236.9854 10242.0898 18818.8125 | lr 5.0e-04 | norm 7086.1333 | dt 9.792 +type train | step 1035 | loss 185.7883 365.5461 512.0149 799.9175 1097.9353 1536.4113 2086.0598 2885.9265 4024.8528 6170.5928 10138.1328 18662.7129 | lr 5.0e-04 | norm 7423.6953 | dt 9.775 +type train | step 1036 | loss 176.1941 345.1675 490.4135 772.8863 1060.9877 1476.1276 1998.5831 2777.9692 3904.1204 6021.8047 9942.0928 18291.6680 | lr 5.0e-04 | norm 7406.9458 | dt 9.784 +type train | step 1037 | loss 178.5213 349.0097 494.2036 775.7042 1067.6533 1488.3195 2025.9294 2828.2314 3961.0835 6136.3589 10197.2930 18909.7461 | lr 5.0e-04 | norm 7225.3237 | dt 9.779 +type train | step 1038 | loss 183.8574 365.8048 517.8834 812.2274 1109.3694 1550.3207 2100.1208 2926.4839 4072.0571 6264.9448 10291.2031 18989.6680 | lr 5.0e-04 | norm 6758.2236 | dt 9.789 +type train | step 1039 | loss 170.3949 337.4774 483.5074 768.6037 1064.9363 1499.1449 2050.7146 2888.1599 4061.9250 6314.5737 10606.5576 19868.1582 | lr 5.0e-04 | norm 10049.5947 | dt 9.789 +type train | step 1040 | loss 167.1928 327.9224 467.4639 746.3146 1025.3292 1436.1475 1965.6844 2742.3555 3892.5410 6068.4341 10105.2900 18689.8906 | lr 5.0e-04 | norm 7463.7544 | dt 9.791 +type train | step 1041 | loss 175.2789 345.7499 498.1110 779.3541 1085.6678 1519.0782 2083.9456 2933.0820 4130.6689 6373.1675 10434.5586 19140.2422 | lr 5.0e-04 | norm 7835.1025 | dt 9.787 +type train | step 1042 | loss 192.4667 383.7135 552.0608 867.8144 1181.8339 1664.3938 2244.2354 3124.6270 4303.0688 6569.0537 10695.0664 19913.5859 | lr 5.0e-04 | norm 10018.9482 | dt 9.771 +type train | step 1043 | loss 193.2325 381.2045 527.4554 818.9256 1110.2972 1545.0670 2072.1655 2882.3293 3987.2439 6078.8828 9913.7842 18199.3359 | lr 5.0e-04 | norm 8354.7812 | dt 9.773 +type train | step 1044 | loss 172.8625 338.7428 482.4253 762.6112 1052.2374 1480.7220 2023.0034 2840.7998 3996.8938 6173.5347 10208.2725 18890.3379 | lr 5.0e-04 | norm 7896.7080 | dt 9.777 +type train | step 1045 | loss 165.9965 326.0151 471.8621 761.9357 1040.9883 1454.4652 1975.3268 2764.4771 3889.0583 6025.4375 9999.6064 18684.4902 | lr 5.0e-04 | norm 8387.0430 | dt 9.778 +type train | step 1046 | loss 181.7124 355.3749 506.9434 790.2969 1090.0908 1516.5533 2043.8914 2851.2920 3984.6306 6123.9634 10127.0176 18821.2637 | lr 5.0e-04 | norm 8504.5859 | dt 9.777 +type train | step 1047 | loss 175.3261 343.4607 486.2175 757.8975 1047.4778 1450.2162 1971.2446 2754.9385 3895.4453 6002.0605 9906.3818 18219.7246 | lr 5.0e-04 | norm 7376.6387 | dt 9.805 +type train | step 1048 | loss 176.4944 347.0070 493.9452 782.4447 1070.3636 1485.0295 2022.9175 2826.4521 3988.7686 6197.0576 10209.8926 18788.1309 | lr 5.0e-04 | norm 7131.6929 | dt 9.789 +type train | step 1049 | loss 170.0632 335.0439 479.8436 761.4221 1053.6812 1459.9851 1988.9287 2759.6802 3914.2744 6019.9854 9883.6367 18307.6289 | lr 5.0e-04 | norm 10731.1123 | dt 9.788 +type train | step 1050 | loss 172.8107 338.2784 487.1185 776.9445 1071.0994 1490.7632 2041.9094 2865.3213 4089.2070 6297.4336 10378.0068 19107.2051 | lr 5.0e-04 | norm 9673.6543 | dt 9.786 +type train | step 1051 | loss 173.8744 340.5248 489.3853 770.9831 1059.8542 1478.4065 2019.0631 2830.2507 3991.0205 6147.9507 10165.1699 18805.0254 | lr 5.0e-04 | norm 7719.3955 | dt 9.796 +type train | step 1052 | loss 194.2335 383.5757 539.8011 827.3252 1147.6783 1597.1143 2152.3013 2984.7468 4192.2544 6482.6123 10801.0684 20264.4336 | lr 5.0e-04 | norm 11390.7627 | dt 9.793 +type train | step 1053 | loss 160.2383 317.5671 462.1509 737.7923 1029.8098 1453.4080 1991.2081 2812.1416 4010.9873 6210.3916 10236.9482 18874.8828 | lr 5.0e-04 | norm 11625.9697 | dt 9.816 +type train | step 1054 | loss 171.8200 343.1007 489.6511 769.4030 1073.6323 1505.7294 2057.2368 2887.1399 4093.9299 6393.1875 10646.4941 19666.4531 | lr 4.9e-04 | norm 14674.3721 | dt 9.796 +type train | step 1055 | loss 198.9762 391.6134 547.5815 835.9332 1147.8411 1599.0083 2144.5542 2956.8650 4129.4292 6254.3833 10158.2432 18733.1016 | lr 4.9e-04 | norm 10237.7822 | dt 9.802 +type train | step 1056 | loss 186.0564 368.1058 519.9366 801.0349 1115.6456 1555.7300 2115.8020 2953.4258 4161.9248 6366.4067 10449.3887 19260.7910 | lr 4.9e-04 | norm 9623.8887 | dt 9.804 +type train | step 1057 | loss 166.1506 325.2487 462.8293 730.2507 1014.5151 1431.3413 1959.3451 2755.8254 3887.6121 5997.0425 10012.0078 18515.4180 | lr 4.9e-04 | norm 10157.6514 | dt 9.796 +type train | step 1058 | loss 181.4447 357.5791 505.4095 793.6168 1093.0996 1536.8645 2085.6658 2934.0393 4123.9512 6242.1416 10230.9346 18949.4922 | lr 4.9e-04 | norm 10099.3486 | dt 9.806 +type train | step 1059 | loss 180.4921 354.2044 499.5497 775.4191 1077.4473 1507.3110 2035.1786 2864.8201 4047.1545 6215.9810 10300.3467 19260.7578 | lr 4.9e-04 | norm 9475.3975 | dt 9.789 +type train | step 1060 | loss 164.7751 322.0921 463.9540 732.9011 1019.6915 1422.5464 1934.5302 2714.2405 3891.6277 5996.3091 10011.1445 18547.4531 | lr 4.9e-04 | norm 7889.5205 | dt 9.786 +type train | step 1061 | loss 175.4821 347.7858 498.4323 780.8900 1082.1533 1516.5239 2054.5269 2869.1338 4060.0598 6243.3706 10295.0488 19265.4707 | lr 4.9e-04 | norm 8934.4922 | dt 9.781 +type train | step 1062 | loss 170.8577 338.9616 481.4166 765.2031 1053.9171 1490.2977 2029.5632 2842.7839 4036.1125 6181.6641 10200.3096 18809.2207 | lr 4.9e-04 | norm 7282.0557 | dt 9.793 +type train | step 1063 | loss 171.0636 337.9684 488.4254 777.0250 1081.1848 1512.8553 2063.9238 2891.3911 4117.2422 6334.8545 10506.3135 19448.1445 | lr 4.9e-04 | norm 9703.6875 | dt 9.770 +type train | step 1064 | loss 172.7402 337.9397 479.4221 748.2239 1036.1445 1454.8867 1969.3087 2742.6272 3907.3892 5999.7905 9963.6172 18371.4297 | lr 4.9e-04 | norm 9546.2842 | dt 9.784 +type train | step 1065 | loss 167.8993 329.6945 470.9891 742.0960 1031.2025 1448.8070 1967.9006 2760.8289 3928.6968 5980.7441 9857.3340 18252.8379 | lr 4.9e-04 | norm 7975.5161 | dt 9.796 +type train | step 1066 | loss 181.9428 357.2200 501.4373 777.7607 1070.2111 1492.0724 2010.5718 2805.6453 3914.1235 5980.1040 9855.1084 18203.8652 | lr 4.9e-04 | norm 8775.6562 | dt 9.781 +type train | step 1067 | loss 167.3509 330.7445 471.9897 742.6082 1028.8464 1449.8341 1968.8320 2752.5959 3895.1289 5966.6167 9841.8594 18215.8340 | lr 4.9e-04 | norm 7630.8232 | dt 9.798 +type train | step 1068 | loss 168.1950 330.3706 473.9687 750.2726 1038.4412 1451.3776 1981.4158 2767.5286 3933.4121 6090.8252 10010.8916 18474.8340 | lr 4.9e-04 | norm 8570.3574 | dt 9.796 +type train | step 1069 | loss 169.2189 333.1448 484.3176 767.5281 1062.2786 1488.6320 2018.9401 2825.3357 4034.4805 6222.8027 10374.3320 19334.3359 | lr 4.9e-04 | norm 8333.6504 | dt 9.778 +type train | step 1070 | loss 174.9769 351.4630 511.1178 813.9321 1134.6460 1584.7245 2159.9373 3028.3965 4283.6392 6590.3901 10921.4551 20312.7344 | lr 4.9e-04 | norm 9013.4561 | dt 9.789 +type train | step 1071 | loss 163.2209 322.6961 463.7929 740.4977 1025.9178 1457.3511 1994.2040 2824.1191 4007.5891 6211.3516 10338.4434 19580.5137 | lr 4.9e-04 | norm 9448.0049 | dt 9.784 +type train | step 1072 | loss 185.6441 363.6054 509.0704 790.4761 1081.5616 1503.2295 2029.0267 2822.4548 3952.0212 6039.6494 10047.8359 18809.9844 | lr 4.9e-04 | norm 8373.6006 | dt 9.781 +type train | step 1073 | loss 170.6413 336.7715 484.2057 764.0823 1066.1030 1488.0420 2031.2109 2837.7866 4040.2576 6196.9731 10279.5342 18913.3730 | lr 4.9e-04 | norm 8316.3945 | dt 9.794 +type train | step 1074 | loss 168.2226 330.3405 476.3298 759.5876 1066.7327 1501.8079 2049.9915 2877.5688 4085.7458 6272.7070 10471.7109 19293.4492 | lr 4.9e-04 | norm 11218.6650 | dt 9.777 +type train | step 1075 | loss 176.1518 349.1010 496.3996 775.6071 1074.7227 1500.8138 2034.9233 2857.4375 4020.8513 6106.3755 10049.7100 18535.2051 | lr 4.9e-04 | norm 8047.5781 | dt 9.781 +type train | step 1076 | loss 184.5089 363.4213 508.9142 784.1254 1077.0845 1525.1335 2060.7832 2884.1467 4055.6011 6144.8311 10024.9336 18265.5996 | lr 4.9e-04 | norm 8327.7178 | dt 9.775 +type train | step 1077 | loss 163.9717 323.6000 462.8473 726.5958 1014.3118 1426.1692 1943.2408 2725.1592 3878.1135 5964.1489 9917.4697 18415.1797 | lr 4.9e-04 | norm 8635.7539 | dt 9.787 +type train | step 1078 | loss 179.9184 354.5094 502.9543 787.0192 1092.8508 1537.7152 2091.6777 2950.7903 4139.7246 6343.6841 10455.1406 19458.1504 | lr 4.9e-04 | norm 7815.6250 | dt 9.780 +type train | step 1079 | loss 170.0483 335.7840 479.6610 753.4261 1044.3878 1465.7075 2008.8314 2821.1052 4011.4751 6180.6113 10194.6289 18861.5352 | lr 4.9e-04 | norm 7875.9409 | dt 9.779 +type train | step 1080 | loss 170.4585 335.4502 485.2480 773.6064 1063.6826 1482.2261 2027.0275 2831.0933 4037.0886 6226.4282 10353.0449 19691.4082 | lr 4.9e-04 | norm 10764.7529 | dt 9.777 +type train | step 1081 | loss 171.1111 331.3724 478.6885 746.4015 1042.6851 1456.6699 1995.8777 2804.3840 3978.7646 6166.3730 10323.3037 19735.6816 | lr 4.9e-04 | norm 17261.6035 | dt 9.770 +type train | step 1082 | loss 182.5393 361.7749 506.4285 782.2342 1082.1804 1510.5994 2049.9902 2851.2134 4012.8083 6133.5562 10060.7480 18798.5938 | lr 4.9e-04 | norm 9607.0049 | dt 9.779 +type train | step 1083 | loss 178.9412 353.6476 501.3378 776.1921 1071.3226 1487.6713 2017.3206 2820.4268 3972.5415 6047.9678 9937.3047 18415.4043 | lr 4.9e-04 | norm 8572.3750 | dt 9.786 +type train | step 1084 | loss 167.2421 327.9198 472.5725 741.5912 1027.7639 1440.8357 1956.4607 2743.7942 3905.5513 6029.0464 10032.8721 18678.4609 | lr 4.9e-04 | norm 8570.6885 | dt 9.781 +type train | step 1085 | loss 176.2853 350.1115 494.4500 774.4308 1080.3893 1529.2529 2090.9917 2957.1665 4158.9370 6363.2500 10571.1904 19783.3047 | lr 4.9e-04 | norm 10583.2461 | dt 9.798 +type train | step 1086 | loss 165.1905 328.3344 469.8773 733.0631 1028.3357 1439.0034 1968.2979 2767.4785 3941.1558 6042.2241 9886.6670 18242.4434 | lr 4.9e-04 | norm 9074.3955 | dt 9.782 +type train | step 1087 | loss 161.5795 318.2834 461.5009 731.2576 1024.5386 1450.6798 1981.7798 2780.7178 3959.2905 6117.2217 10087.7715 18822.0703 | lr 4.9e-04 | norm 8900.5811 | dt 9.794 +type train | step 1088 | loss 176.4424 346.2033 496.6000 774.5165 1072.5350 1507.6566 2060.2744 2864.0977 4048.2969 6176.8979 10193.6836 18856.4785 | lr 4.9e-04 | norm 7458.4243 | dt 9.772 +type train | step 1089 | loss 172.2200 337.5369 480.1989 747.0784 1037.8016 1451.9196 1965.4417 2742.1174 3892.7546 5955.3501 9825.4355 18171.7910 | lr 4.9e-04 | norm 6801.4409 | dt 9.787 +type train | step 1090 | loss 164.3873 327.9551 468.2032 735.5189 1024.9493 1447.9724 1973.3617 2762.3135 3927.1367 6016.0996 9947.7002 18524.4727 | lr 4.9e-04 | norm 7975.8389 | dt 9.775 +type train | step 1091 | loss 164.8363 323.5523 465.4976 730.6933 1015.3666 1420.0422 1938.3246 2710.6731 3878.5000 5949.5752 9771.4961 17996.6602 | lr 4.9e-04 | norm 6867.0210 | dt 9.794 +type train | step 1092 | loss 168.7428 333.4005 481.1144 752.4207 1055.5988 1491.4193 2035.0542 2855.5012 4056.0256 6226.4717 10282.9922 19102.5566 | lr 4.9e-04 | norm 7120.1353 | dt 9.792 +type train | step 1093 | loss 173.9939 343.7465 488.6513 767.8441 1066.0094 1532.9498 2102.9277 2996.2554 4194.7646 6394.4810 10514.9092 19557.0547 | lr 4.9e-04 | norm 8076.8232 | dt 9.793 +type train | step 1094 | loss 181.0340 359.8850 507.5999 782.8931 1081.9445 1524.2736 2060.0637 2872.0730 3999.8303 6054.3823 9892.7891 18264.7227 | lr 4.9e-04 | norm 7234.0044 | dt 9.795 +type train | step 1095 | loss 211.7185 425.1433 586.8292 879.8110 1194.0891 1672.7130 2249.5273 3102.0200 4266.7930 6361.7046 10299.6768 18792.9531 | lr 4.9e-04 | norm 11403.7139 | dt 9.780 +type train | step 1096 | loss 162.9883 326.9502 461.3579 724.7831 1021.8987 1455.1683 2007.0306 2845.5671 4018.3955 6234.1792 10332.2334 19210.9277 | lr 4.9e-04 | norm 12518.7549 | dt 9.776 +type train | step 1097 | loss 168.4039 330.6693 475.2954 744.9077 1034.9683 1453.6301 1977.7579 2776.1697 3957.3306 6067.5288 10019.5742 18717.8242 | lr 4.9e-04 | norm 8380.0352 | dt 9.782 +type train | step 1098 | loss 180.2501 354.5651 497.9988 774.5121 1070.3319 1494.0782 2006.9440 2791.0627 3947.1875 6008.6016 9949.0234 18648.0332 | lr 4.9e-04 | norm 8271.0000 | dt 9.788 +type train | step 1099 | loss 177.1165 344.9455 486.7328 755.6942 1051.4786 1486.2773 2019.7231 2827.2207 4008.1980 6151.3765 10168.0801 18988.3867 | lr 4.9e-04 | norm 8471.1406 | dt 9.782 +type train | step 1100 | loss 176.7456 347.7149 489.2789 762.9214 1054.6461 1491.1292 2018.1364 2830.8745 3979.4829 6122.0166 10244.3408 19290.9316 | lr 4.9e-04 | norm 8063.4756 | dt 9.787 +type train | step 1101 | loss 167.9249 328.5909 471.3308 731.6221 1021.3132 1428.5879 1942.5602 2721.9443 3865.0813 5925.1377 9763.9922 18102.5449 | lr 4.9e-04 | norm 7397.3438 | dt 9.790 +type train | step 1102 | loss 165.1241 324.7854 470.2808 740.3987 1034.8202 1457.4540 1988.7703 2804.4077 3974.1851 6110.5708 10129.8057 18863.2227 | lr 4.9e-04 | norm 7660.4795 | dt 9.776 +type train | step 1103 | loss 175.8316 347.4133 492.6728 768.8005 1063.7028 1490.2943 2027.6332 2841.4302 4005.7839 6175.4805 10232.1250 19015.0898 | lr 4.9e-04 | norm 6862.0195 | dt 9.791 +type train | step 1104 | loss 168.6295 332.5161 476.7487 747.6957 1037.8884 1453.1366 1974.3336 2767.6147 3932.1270 6044.0098 9935.2607 18485.7793 | lr 4.9e-04 | norm 7474.6040 | dt 9.783 +type train | step 1105 | loss 168.3205 330.1903 469.4255 730.0116 1019.6008 1430.7074 1954.9271 2746.8931 3902.8967 6003.3071 9924.8643 18505.5625 | lr 4.9e-04 | norm 8006.6938 | dt 9.778 +type train | step 1106 | loss 158.0251 311.6184 448.6450 706.8804 993.0763 1405.3721 1922.3899 2714.4402 3860.9248 6003.6973 9961.6377 18631.8789 | lr 4.9e-04 | norm 8190.1885 | dt 9.805 +type train | step 1107 | loss 183.9572 364.7070 516.2744 798.9544 1109.4943 1545.5527 2091.0979 2907.5261 4120.9487 6274.0859 10234.2812 18844.0059 | lr 4.9e-04 | norm 8157.5361 | dt 9.787 +type train | step 1108 | loss 169.3377 330.6460 471.0212 728.8206 1023.8281 1436.2124 1960.2491 2747.9929 3923.6887 6049.5024 10005.6738 18745.9863 | lr 4.9e-04 | norm 9176.6914 | dt 9.786 +type train | step 1109 | loss 169.3843 328.9377 469.2189 728.4528 1007.3717 1409.8091 1911.2438 2667.3694 3797.7144 5809.8604 9582.2949 17883.5332 | lr 4.9e-04 | norm 7741.6675 | dt 9.767 +type train | step 1110 | loss 160.6693 310.8578 450.9619 715.5497 1011.1840 1431.7289 1954.0231 2744.6572 3900.0234 5985.5298 9865.2432 18270.1113 | lr 4.9e-04 | norm 7460.8877 | dt 9.777 +type train | step 1111 | loss 142.2794 278.3632 409.7702 658.1162 936.3640 1333.6133 1854.6335 2628.4944 3811.4182 5859.4346 9649.2666 17817.1641 | lr 4.9e-04 | norm 8878.9600 | dt 9.778 +type train | step 1112 | loss 160.7691 315.5051 451.0706 704.9370 995.4769 1408.8419 1923.5237 2714.3740 3854.0234 5892.7852 9761.1162 18108.5215 | lr 4.9e-04 | norm 6987.2090 | dt 9.787 +type train | step 1113 | loss 175.4706 342.0343 487.0685 758.9569 1054.1641 1466.0355 1992.7319 2807.7793 3990.2446 6118.8315 10163.2725 19103.6914 | lr 4.9e-04 | norm 11328.2461 | dt 9.771 +type train | step 1114 | loss 170.8260 336.5293 481.9919 755.2694 1048.2061 1459.3915 1984.6874 2770.4600 3911.2268 5967.3208 9803.3008 18126.8691 | lr 4.9e-04 | norm 7140.2100 | dt 9.779 +type train | step 1115 | loss 158.1444 307.8847 449.6082 710.8942 995.4779 1395.9996 1915.8400 2683.5798 3844.4033 5905.6885 9765.2383 18376.8047 | lr 4.9e-04 | norm 9674.4629 | dt 9.768 +type train | step 1116 | loss 164.9427 322.3835 465.2761 729.4241 1023.6191 1457.0162 1985.9960 2788.4124 3940.8494 6073.0391 10146.8799 19242.0332 | lr 4.9e-04 | norm 10259.2207 | dt 9.767 +type train | step 1117 | loss 162.9138 318.6475 455.6269 715.6326 1006.7361 1417.3016 1936.2932 2712.4531 3849.7681 5907.8955 9771.5195 18161.1875 | lr 4.9e-04 | norm 7362.7026 | dt 9.789 +type train | step 1118 | loss 170.5643 333.5934 476.1074 742.3345 1032.4417 1445.2040 1965.4213 2746.3125 3874.6226 5933.9536 9741.3447 18062.3789 | lr 4.9e-04 | norm 8113.6919 | dt 9.780 +type train | step 1119 | loss 161.4420 313.3378 450.4170 713.3342 1001.9809 1403.5481 1903.9542 2668.0454 3793.9343 5813.1577 9593.8516 17767.6328 | lr 4.9e-04 | norm 7101.9946 | dt 9.776 +type train | step 1120 | loss 165.0576 324.9678 466.9253 733.9477 1019.1253 1434.0471 1956.1984 2736.8025 3877.7041 5965.9375 9788.3428 18183.9785 | lr 4.9e-04 | norm 10675.6396 | dt 9.769 +type train | step 1121 | loss 160.4923 313.4608 453.8815 716.9042 1009.5484 1418.2407 1935.9534 2720.0552 3860.6663 5983.5308 9966.1064 18602.7051 | lr 4.9e-04 | norm 7543.7568 | dt 9.769 +type train | step 1122 | loss 157.0893 320.2824 473.2384 756.2275 1059.9757 1484.9656 2022.2034 2867.0049 4106.8623 6353.5210 10425.8750 19551.4492 | lr 4.9e-04 | norm 12540.0322 | dt 9.784 +type train | step 1123 | loss 171.6197 340.6113 484.2058 751.6920 1054.6650 1469.3616 1991.0359 2774.4172 3893.9824 5938.7617 9790.4023 18127.0801 | lr 4.9e-04 | norm 8053.9546 | dt 9.785 +type train | step 1124 | loss 198.1271 390.2063 540.3303 823.9559 1129.6726 1578.8920 2107.0693 2904.7112 3959.9392 5980.5469 9640.5527 18029.6758 | lr 4.9e-04 | norm 9925.5205 | dt 9.764 +type train | step 1125 | loss 171.5643 338.5608 479.5154 736.5244 1028.1908 1435.4926 1947.9716 2714.1665 3809.7556 5834.2544 9601.4365 17932.3438 | lr 4.9e-04 | norm 9941.7979 | dt 9.794 +type train | step 1126 | loss 167.3609 331.4747 470.3607 725.7244 1017.8754 1424.0562 1929.7350 2693.6968 3794.6741 5818.5444 9673.2021 18080.4961 | lr 4.9e-04 | norm 8021.1802 | dt 9.792 +type train | step 1127 | loss 157.7844 311.3251 452.6994 709.1034 1001.4432 1401.4866 1910.9625 2669.0137 3793.4685 5836.3740 9677.3613 18126.5508 | lr 4.9e-04 | norm 8716.6055 | dt 9.779 +type train | step 1128 | loss 158.7928 313.5139 452.1129 709.6096 995.7175 1397.8726 1904.6003 2683.9207 3793.1167 5828.7354 9605.7266 17867.8906 | lr 4.9e-04 | norm 6867.7715 | dt 9.788 +type train | step 1129 | loss 156.8400 307.9918 442.9471 691.5748 974.7819 1363.3676 1874.3701 2630.8555 3740.5916 5747.6421 9497.8398 17733.5156 | lr 4.9e-04 | norm 7663.9883 | dt 9.786 +type train | step 1130 | loss 154.3513 300.4436 434.0947 680.8495 964.5724 1354.4451 1855.3156 2607.8828 3712.2085 5704.5029 9460.0879 17719.4785 | lr 4.9e-04 | norm 6284.2007 | dt 9.786 +type train | step 1131 | loss 158.7118 312.2518 446.3452 700.7921 988.5568 1381.1624 1886.4153 2651.0815 3769.0837 5818.5020 9594.3213 17779.9082 | lr 4.9e-04 | norm 6965.5029 | dt 9.795 +type train | step 1132 | loss 170.5452 331.3202 472.1427 733.8358 1024.8644 1443.3767 1962.9141 2768.3840 3914.6370 5998.2554 9889.2920 18288.2754 | lr 4.9e-04 | norm 6612.1211 | dt 9.789 +type train | step 1133 | loss 163.8017 318.0114 451.7177 708.8002 996.0518 1410.9678 1928.9680 2709.5317 3858.8918 5923.2310 9787.7773 18367.8555 | lr 4.9e-04 | norm 7442.2671 | dt 9.787 +type train | step 1134 | loss 155.0429 302.3077 438.4437 694.4363 981.9985 1384.7465 1892.6390 2666.4722 3796.2178 5825.8491 9672.4619 18046.5098 | lr 4.9e-04 | norm 7603.9341 | dt 9.792 +type train | step 1135 | loss 159.0074 310.8881 447.3801 699.4183 988.1810 1388.0571 1903.1427 2666.4802 3809.3889 5800.1895 9568.0625 17817.3887 | lr 4.9e-04 | norm 8021.2495 | dt 9.777 +type train | step 1136 | loss 148.0822 290.5814 421.9875 662.7935 940.7858 1331.1432 1831.1670 2576.4312 3696.0728 5679.1392 9407.5508 17501.0078 | lr 4.9e-04 | norm 7001.5889 | dt 9.778 +type train | step 1137 | loss 177.3353 350.0507 493.6110 761.0450 1060.4783 1507.3887 2051.0530 2882.0625 4025.3643 6031.5815 9841.4561 18323.6113 | lr 4.9e-04 | norm 8408.3779 | dt 9.778 +type train | step 1138 | loss 167.9116 330.9573 477.1037 740.1721 1032.7444 1435.9727 1949.1331 2709.6951 3849.8992 5894.3257 9742.4805 18136.1953 | lr 4.9e-04 | norm 6586.0103 | dt 9.795 +type train | step 1139 | loss 154.2804 304.2061 446.9232 715.3510 1018.9645 1462.8456 2005.0520 2853.0991 4092.4058 6318.5552 10400.9219 19495.4258 | lr 4.9e-04 | norm 9390.5225 | dt 9.784 +type train | step 1140 | loss 158.3870 308.7877 443.9191 693.5253 971.0278 1367.9216 1873.3475 2624.4749 3749.8511 5723.9673 9510.2656 17816.1465 | lr 4.9e-04 | norm 8249.0342 | dt 9.783 +type train | step 1141 | loss 147.1684 288.0450 418.5063 661.8348 934.8275 1325.0107 1815.1810 2566.7615 3685.7385 5678.5664 9389.0576 17417.8242 | lr 4.9e-04 | norm 7920.6309 | dt 9.777 +type train | step 1142 | loss 170.1568 335.3113 474.4099 732.1926 1017.1251 1441.0916 1976.8755 2767.2456 3924.4021 6037.1343 10037.2715 19115.0566 | lr 4.9e-04 | norm 14074.9688 | dt 9.781 +type train | step 1143 | loss 166.2212 324.8170 462.2714 719.6633 1000.2003 1405.1874 1915.7220 2680.0300 3793.9741 5785.4971 9543.5615 17786.2422 | lr 4.9e-04 | norm 7785.8076 | dt 9.781 +type train | step 1144 | loss 175.4996 347.4242 487.2714 744.4727 1039.9058 1457.7043 1981.5120 2770.8130 3885.9707 5932.2988 9658.7998 17930.2363 | lr 4.9e-04 | norm 9551.6670 | dt 9.792 +type train | step 1145 | loss 161.8896 320.7955 460.1920 716.7885 1007.2132 1416.8418 1930.5228 2703.5625 3832.8655 5901.8022 9730.1670 18231.2598 | lr 4.9e-04 | norm 7578.4814 | dt 9.791 +type train | step 1146 | loss 169.3207 333.9835 472.8717 730.9259 1021.0812 1426.6503 1936.9089 2687.4106 3779.0217 5751.3428 9365.0674 17361.7773 | lr 4.9e-04 | norm 8079.0449 | dt 9.796 +type train | step 1147 | loss 163.6868 321.5248 459.5690 720.1232 1011.6216 1444.2676 1980.0756 2793.4094 3948.7283 5970.7158 9807.0010 18219.2422 | lr 4.9e-04 | norm 7547.8311 | dt 9.784 +type train | step 1148 | loss 163.5261 318.0017 454.6338 708.5490 995.9724 1403.5665 1913.5520 2683.5530 3797.3254 5819.4097 9583.6895 17863.5117 | lr 4.9e-04 | norm 8536.0000 | dt 9.782 +type train | step 1149 | loss 165.1638 324.3093 460.5331 713.1217 1000.4348 1404.6388 1916.0552 2682.1790 3816.2231 5836.8638 9641.1914 17944.4512 | lr 4.9e-04 | norm 6941.8511 | dt 9.791 +type train | step 1150 | loss 163.1996 316.0819 453.0847 711.3565 996.7545 1407.0192 1920.6781 2705.3181 3833.6714 5833.9565 9667.6357 18131.3945 | lr 4.9e-04 | norm 7315.2432 | dt 9.780 +type train | step 1151 | loss 167.1048 327.9641 461.8580 717.6683 999.6011 1413.7764 1931.9890 2712.4956 3828.0232 5911.4287 9752.1592 18428.0996 | lr 4.9e-04 | norm 9238.4141 | dt 9.774 +type train | step 1152 | loss 168.8597 333.0280 473.3778 728.9018 1021.6951 1418.1874 1918.6259 2665.8845 3784.0034 5770.1909 9509.6543 17748.2383 | lr 4.9e-04 | norm 8234.6904 | dt 9.785 +type train | step 1153 | loss 160.4311 315.1975 455.7086 707.9879 991.5260 1381.0275 1870.3296 2607.3271 3711.8481 5643.8379 9298.8232 17225.6680 | lr 4.9e-04 | norm 6430.5225 | dt 9.799 +type train | step 1154 | loss 164.1287 324.2693 462.4465 725.5608 1014.3290 1437.3792 1955.9855 2741.3208 3871.9172 5926.1045 9802.4287 18322.9297 | lr 4.9e-04 | norm 7469.8486 | dt 9.774 +type train | step 1155 | loss 172.6560 340.7817 478.6145 740.4659 1036.8033 1458.6794 1972.8143 2738.1829 3831.9009 5804.5439 9422.4160 17584.2480 | lr 4.9e-04 | norm 7337.5454 | dt 9.778 +type train | step 1156 | loss 164.2962 322.6621 461.1929 721.6460 1009.2049 1418.5336 1925.2721 2710.7383 3846.0488 5877.9336 9726.6377 18197.1602 | lr 4.9e-04 | norm 7139.3276 | dt 9.786 +type train | step 1157 | loss 168.6850 332.2460 472.7184 733.8030 1017.0520 1422.1932 1929.6875 2689.0769 3811.4768 5826.8013 9598.4600 17963.8027 | lr 4.9e-04 | norm 6814.7837 | dt 9.782 +type train | step 1158 | loss 157.4093 310.2235 444.7660 697.1240 981.7944 1382.1486 1884.3074 2649.0623 3791.0640 5849.0952 9687.9941 18024.2441 | lr 4.9e-04 | norm 6921.9751 | dt 9.788 +type train | step 1159 | loss 170.4446 338.2870 486.9975 749.6562 1056.4149 1478.4272 1997.1104 2775.9355 3910.9578 5962.1802 9837.5605 18428.2344 | lr 4.9e-04 | norm 7594.2178 | dt 9.784 +type train | step 1160 | loss 150.7948 295.4855 426.9406 669.1499 954.6563 1354.3707 1856.8696 2609.1987 3744.6570 5690.0088 9408.9668 17598.3340 | lr 4.9e-04 | norm 7290.6221 | dt 9.777 +type train | step 1161 | loss 148.9081 290.8304 423.3136 669.1027 947.7545 1343.2939 1850.8341 2611.7449 3737.6663 5764.6865 9552.3545 17900.2832 | lr 4.9e-04 | norm 6938.4844 | dt 9.792 +type train | step 1162 | loss 163.5253 321.5699 458.8528 709.9188 991.8674 1404.6289 1912.8879 2689.6045 3794.3101 5772.6904 9668.8105 18545.7812 | lr 4.9e-04 | norm 11685.5449 | dt 9.772 +type train | step 1163 | loss 170.5885 339.4719 480.2656 739.5280 1026.0928 1434.5381 1939.9296 2710.6904 3848.1882 5810.6162 9566.1328 17921.6523 | lr 4.9e-04 | norm 7989.2388 | dt 9.783 +type train | step 1164 | loss 159.0473 312.6357 452.1755 706.2347 994.1130 1399.9487 1909.5009 2671.7598 3801.7236 5760.6318 9554.8203 17874.6699 | lr 4.9e-04 | norm 7494.9165 | dt 9.780 +type train | step 1165 | loss 157.6693 306.8601 438.9073 683.3330 967.4187 1358.1257 1850.7849 2586.2603 3702.2126 5629.2241 9292.0332 17291.3047 | lr 4.9e-04 | norm 7070.1406 | dt 9.788 +type train | step 1166 | loss 154.9671 302.9409 439.4854 689.2181 972.0954 1367.1083 1867.0876 2603.0076 3723.2432 5713.1523 9513.1816 17762.2891 | lr 4.9e-04 | norm 6480.2378 | dt 9.777 +type train | step 1167 | loss 151.5555 295.3759 433.4819 684.5748 966.2515 1350.9451 1856.4269 2605.6987 3723.1372 5683.1567 9418.0088 17755.9512 | lr 4.9e-04 | norm 9539.8564 | dt 9.779 +type train | step 1168 | loss 147.1915 286.7771 418.3468 664.6685 948.8342 1332.2356 1825.0063 2564.2617 3693.4583 5619.3262 9269.5029 17130.7461 | lr 4.9e-04 | norm 6785.2388 | dt 9.784 +type train | step 1169 | loss 157.5945 309.1152 442.6846 690.6812 974.7066 1375.7251 1879.3341 2632.6501 3764.3162 5710.5757 9446.4805 17740.2344 | lr 4.9e-04 | norm 6384.2041 | dt 9.786 +type train | step 1170 | loss 152.4067 296.3015 430.1788 677.7092 957.7463 1349.9250 1844.9510 2590.6494 3692.7288 5621.7812 9226.0576 17159.6191 | lr 4.9e-04 | norm 6803.2749 | dt 9.782 +type train | step 1171 | loss 155.1108 302.3643 439.6920 692.1949 981.6835 1386.6633 1891.7732 2645.3335 3797.6948 5813.2490 9648.3936 17960.4902 | lr 4.9e-04 | norm 7168.0400 | dt 9.787 +type train | step 1172 | loss 159.5969 314.6985 448.8179 697.6729 976.7656 1395.3069 1906.3062 2705.5391 3847.6213 5817.5488 9561.8623 17777.3164 | lr 4.9e-04 | norm 6846.8877 | dt 9.778 +type train | step 1173 | loss 172.5523 338.0943 474.9734 727.1458 1016.5242 1423.2644 1929.0393 2690.9949 3822.2173 5765.2002 9443.1494 17537.7812 | lr 4.9e-04 | norm 6825.9951 | dt 9.788 +type train | step 1174 | loss 164.6006 325.7970 465.1897 719.6734 1010.5332 1406.4640 1908.3479 2655.4287 3770.2034 5725.3267 9459.8125 17678.9805 | lr 4.9e-04 | norm 7412.0161 | dt 9.777 +type train | step 1175 | loss 152.9267 301.1751 439.9075 689.6384 977.8172 1386.9099 1898.7069 2681.6418 3847.5518 5879.7861 9744.6318 18104.2090 | lr 4.9e-04 | norm 7125.3745 | dt 9.804 +type train | step 1176 | loss 160.1991 315.2717 452.3120 703.3170 985.3918 1385.2241 1894.0488 2647.8594 3802.1814 5741.0239 9422.5518 17606.4551 | lr 4.9e-04 | norm 7664.9214 | dt 9.774 +type train | step 1177 | loss 159.6897 315.9524 452.6815 703.7963 996.5559 1401.4597 1912.7321 2668.7119 3790.6584 5789.9771 9513.5488 17645.7656 | lr 4.9e-04 | norm 9284.4043 | dt 9.782 +type train | step 1178 | loss 161.6628 318.8575 454.3623 700.9962 994.0255 1398.4271 1913.3842 2678.2307 3804.3611 5760.8643 9424.2080 17531.8398 | lr 4.9e-04 | norm 7308.6665 | dt 9.777 +type train | step 1179 | loss 159.1756 311.8388 444.3848 689.4331 971.7782 1370.3237 1867.1180 2603.0894 3732.0776 5704.6685 9441.4688 17669.0938 | lr 4.9e-04 | norm 7208.5840 | dt 9.796 +type train | step 1180 | loss 161.3434 317.1086 464.0034 731.0673 1028.9442 1450.7168 2001.5229 2810.3040 3988.7073 6118.0981 10192.1533 19492.8203 | lr 4.9e-04 | norm 11428.4805 | dt 9.765 +type train | step 1181 | loss 169.2652 333.2012 475.7751 724.8268 1020.9601 1422.9739 1926.3597 2656.8975 3769.4380 5717.1611 9388.6045 17497.4902 | lr 4.9e-04 | norm 7254.2119 | dt 9.801 +type train | step 1182 | loss 158.7129 312.9655 447.3822 704.6982 1001.4799 1415.4634 1929.8904 2731.8540 3925.2964 5963.9824 9873.3193 18522.5527 | lr 4.9e-04 | norm 12589.1055 | dt 9.781 +type train | step 1183 | loss 160.1762 316.1213 454.6487 706.1674 1002.0868 1400.2555 1918.3824 2693.0181 3854.9534 5880.9741 9663.2168 18016.9297 | lr 4.9e-04 | norm 9204.0029 | dt 9.770 +type train | step 1184 | loss 162.4686 318.5996 457.7594 708.7020 1000.4174 1385.2297 1888.1354 2628.3413 3730.8928 5749.5132 9536.8281 17846.0469 | lr 4.9e-04 | norm 7991.4312 | dt 9.792 +type train | step 1185 | loss 144.3639 284.6567 418.4594 653.5344 938.4733 1319.0815 1811.4862 2558.7893 3690.7793 5640.7686 9348.1797 17514.6113 | lr 4.9e-04 | norm 9018.2412 | dt 9.782 +type train | step 1186 | loss 159.1247 316.6014 453.3786 707.0897 1001.8879 1416.3008 1954.9232 2766.5593 3953.3494 5981.2988 9943.2520 18850.7246 | lr 4.9e-04 | norm 10248.5156 | dt 9.779 +type train | step 1187 | loss 149.5188 294.1291 427.4157 672.1548 955.1965 1345.2018 1838.8130 2578.3496 3697.5020 5651.2349 9346.0898 17392.4180 | lr 4.9e-04 | norm 7110.7700 | dt 9.810 +type train | step 1188 | loss 161.4520 318.7256 457.6417 714.4774 1013.7028 1442.6583 1972.2395 2794.3025 3956.7073 5993.3979 9779.7842 18221.8418 | lr 4.9e-04 | norm 7955.8062 | dt 9.792 +type train | step 1189 | loss 152.0454 295.9826 429.1540 670.2783 951.1280 1339.0219 1838.1508 2571.1345 3704.4915 5657.8828 9388.9238 17573.6523 | lr 4.9e-04 | norm 7349.2114 | dt 9.795 +type train | step 1190 | loss 156.8275 307.3598 439.5231 689.5557 975.1992 1378.3354 1892.3977 2662.7620 3791.4653 5768.2979 9511.6055 17851.9746 | lr 4.9e-04 | norm 7428.9375 | dt 9.780 +type train | step 1191 | loss 150.8327 296.6606 432.8252 684.8423 972.1677 1375.4154 1891.8395 2660.6736 3830.9998 5839.8770 9709.1699 18277.4219 | lr 4.9e-04 | norm 7537.2563 | dt 9.774 +type train | step 1192 | loss 144.3909 283.6410 416.2601 655.9354 938.0121 1334.9122 1833.3826 2594.8440 3741.7146 5713.5117 9435.8428 17570.9551 | lr 4.9e-04 | norm 6899.0293 | dt 9.781 +type train | step 1193 | loss 170.3543 336.5225 476.3391 737.2958 1031.6720 1446.6121 1963.8619 2742.2388 3859.1206 5791.4678 9518.6094 17855.8008 | lr 4.9e-04 | norm 7724.1562 | dt 9.774 +type train | step 1194 | loss 158.3670 310.6132 445.6971 689.9289 974.7629 1361.7332 1854.4991 2597.5742 3729.6047 5674.8306 9394.2109 17616.3984 | lr 4.9e-04 | norm 6911.8511 | dt 9.795 +type train | step 1195 | loss 149.9887 293.7566 423.9294 661.7578 945.2308 1323.9312 1812.7322 2554.4023 3658.3853 5593.5693 9261.5332 17345.5566 | lr 4.9e-04 | norm 7034.0356 | dt 9.787 +type train | step 1196 | loss 150.8224 293.8025 426.7366 670.4752 957.3989 1360.7854 1866.1747 2612.9082 3761.9075 5696.4551 9375.1748 17407.9199 | lr 4.9e-04 | norm 6954.3916 | dt 9.791 +type train | step 1197 | loss 146.9776 286.0650 419.0999 662.3212 945.2090 1337.0067 1836.8966 2589.9688 3752.3110 5688.1841 9400.2871 17461.4199 | lr 4.9e-04 | norm 6747.5903 | dt 9.784 +type train | step 1198 | loss 159.3292 316.0085 455.5846 708.4866 1003.2271 1407.1743 1917.5627 2678.1865 3842.7222 5845.7603 9647.7148 17933.2012 | lr 4.9e-04 | norm 7052.5859 | dt 9.786 +type train | step 1199 | loss 170.0805 332.8804 471.9587 721.0068 1009.3912 1415.5427 1915.4532 2652.7710 3756.5842 5621.7261 9185.5508 16993.9844 | lr 4.9e-04 | norm 6331.5015 | dt 9.781 +type train | step 1200 | loss 152.1960 300.2652 429.8586 669.9665 947.5961 1336.0488 1821.5312 2556.5417 3659.5540 5558.5664 9170.7715 17127.1035 | lr 4.9e-04 | norm 6905.2881 | dt 9.782 +type train | step 1201 | loss 149.3786 295.1666 424.6052 663.6905 949.0017 1353.1089 1863.9049 2626.0344 3780.0676 5783.4863 9545.6719 17779.0410 | lr 4.9e-04 | norm 10270.9512 | dt 9.777 +type train | step 1202 | loss 163.8028 318.3158 456.3693 713.7045 1006.5903 1425.8761 1952.3768 2731.6729 3870.1316 5796.8467 9327.2246 17161.3203 | lr 4.9e-04 | norm 7620.2036 | dt 9.774 +type train | step 1203 | loss 157.8278 310.5995 449.3848 698.2758 981.3420 1375.8425 1877.1437 2602.7520 3723.6323 5652.9497 9252.6396 17131.2480 | lr 4.9e-04 | norm 6616.6318 | dt 9.793 +type train | step 1204 | loss 158.8079 312.3280 445.4011 688.9905 972.9841 1376.4694 1875.9240 2631.2561 3738.0938 5662.3618 9341.2441 17315.1875 | lr 4.9e-04 | norm 6752.3394 | dt 9.787 +type train | step 1205 | loss 159.7340 315.8814 450.0112 699.1631 986.6352 1397.1461 1908.6824 2685.2095 3835.5642 5783.9512 9521.6729 17730.7383 | lr 4.9e-04 | norm 7246.4839 | dt 9.791 +type train | step 1206 | loss 175.7337 351.1809 495.4639 767.3435 1072.8749 1505.4800 2049.8477 2861.6147 4009.2844 6024.9189 9895.8799 18518.4043 | lr 4.9e-04 | norm 8585.2471 | dt 9.770 +type train | step 1207 | loss 164.5267 321.8196 461.8751 720.0040 1018.5088 1455.2869 1998.8142 2813.1060 3988.7568 6058.3979 10024.6152 18816.4863 | lr 4.9e-04 | norm 8476.8438 | dt 9.774 +type train | step 1208 | loss 169.1922 333.5856 475.8365 730.6891 1023.5955 1438.7684 1954.1487 2727.3408 3850.6824 5845.1118 9586.2217 18000.9355 | lr 4.9e-04 | norm 8556.7695 | dt 9.781 +type train | step 1209 | loss 160.0359 314.8922 444.8626 692.9700 973.4235 1370.8347 1873.4822 2623.0454 3735.7551 5683.5718 9383.1113 17767.6641 | lr 4.9e-04 | norm 9450.2939 | dt 9.776 +type train | step 1210 | loss 162.4315 319.6236 452.7724 704.3976 984.0713 1384.0038 1883.0541 2637.1064 3728.3374 5617.6597 9250.7744 17394.1172 | lr 4.9e-04 | norm 9424.4668 | dt 9.764 +type train | step 1211 | loss 149.3007 291.2910 422.4007 662.7631 936.1240 1317.8226 1799.6847 2519.9534 3628.6257 5488.7388 9053.2188 16912.4883 | lr 4.9e-04 | norm 6969.8955 | dt 9.786 +type train | step 1212 | loss 155.6131 302.6177 435.4720 680.2910 965.3094 1367.9053 1874.6633 2637.4683 3759.3789 5670.2070 9362.3262 17454.4863 | lr 4.9e-04 | norm 7959.1597 | dt 9.776 +type train | step 1213 | loss 154.1876 301.7177 434.1107 676.7569 954.9046 1348.9873 1840.8157 2602.4673 3730.6790 5658.5273 9349.5742 17429.0664 | lr 4.9e-04 | norm 6458.5537 | dt 9.783 +type train | step 1214 | loss 161.9308 317.9212 455.7408 715.5013 1013.2662 1436.1416 1965.6904 2763.5698 3919.5752 5913.3071 9693.1572 18057.0918 | lr 4.9e-04 | norm 7946.0640 | dt 9.771 +type train | step 1215 | loss 156.6592 307.4574 438.3368 679.4095 960.6025 1354.0353 1845.8181 2587.8306 3691.1179 5607.2876 9269.8223 17359.3770 | lr 4.9e-04 | norm 6371.3052 | dt 9.784 +type train | step 1216 | loss 150.2791 292.4735 426.0714 667.9661 952.4147 1342.5540 1838.3867 2585.6255 3718.8540 5678.0991 9429.6514 17639.8984 | lr 4.9e-04 | norm 7518.3638 | dt 9.772 +type train | step 1217 | loss 145.8612 284.2087 415.7980 658.3183 941.3340 1329.1587 1825.8638 2570.2979 3703.4399 5636.0811 9312.6846 17404.7539 | lr 4.9e-04 | norm 6855.9766 | dt 9.781 +type train | step 1218 | loss 155.9902 306.4217 438.2580 682.4698 967.1666 1358.2693 1852.6122 2600.5593 3718.7695 5642.6108 9314.8574 17240.0078 | lr 4.9e-04 | norm 6475.9844 | dt 10.127 +type train | step 1219 | loss 146.6599 285.6024 413.5592 647.3350 927.7824 1311.1456 1802.1591 2526.9275 3618.9890 5532.8247 9126.5947 16965.7246 | lr 4.9e-04 | norm 6202.6479 | dt 9.783 +type train | step 1220 | loss 159.8418 317.2995 452.8905 711.4530 1000.1455 1450.2120 1993.8447 2830.4805 3952.9287 5986.8267 9916.8350 18618.0957 | lr 4.9e-04 | norm 12344.3223 | dt 9.748 +type train | step 1221 | loss 155.9532 305.8676 440.4208 683.9199 972.9449 1370.6694 1878.4719 2631.8098 3751.3828 5675.4902 9350.1191 17405.4258 | lr 4.9e-04 | norm 7104.4058 | dt 9.799 +type train | step 1222 | loss 152.4285 299.5103 432.9407 671.7690 956.7614 1343.6176 1838.5477 2567.4626 3692.8970 5604.9541 9234.5381 17208.5469 | lr 4.9e-04 | norm 6904.4683 | dt 9.784 +type train | step 1223 | loss 143.1285 279.8752 405.7513 633.2326 907.4016 1289.0004 1772.3936 2492.2524 3588.7671 5495.3594 9101.2617 16992.1191 | lr 4.9e-04 | norm 6784.9189 | dt 9.783 +type train | step 1224 | loss 152.0108 298.4293 433.6073 678.8294 970.4131 1363.4507 1864.2881 2597.8596 3729.9143 5687.9131 9408.7832 17546.0723 | lr 4.9e-04 | norm 8499.1133 | dt 9.794 +type train | step 1225 | loss 149.2138 293.8029 429.0464 672.0309 958.6135 1360.3134 1868.3784 2627.0596 3762.7043 5710.0752 9457.5469 17665.4648 | lr 4.9e-04 | norm 6919.3623 | dt 9.793 +type train | step 1226 | loss 156.8552 305.5410 439.7224 686.9211 969.2457 1363.0201 1867.0336 2610.0339 3730.0156 5681.7847 9397.9170 17480.7930 | lr 4.9e-04 | norm 7199.8657 | dt 9.795 +type train | step 1227 | loss 155.5592 316.0944 455.4826 716.0936 1005.8235 1390.6240 1886.6561 2636.8789 3823.3284 5837.8237 9766.4404 18430.4102 | lr 4.9e-04 | norm 11884.8457 | dt 9.785 +type train | step 1228 | loss 147.9498 289.3892 421.0541 661.7874 938.1401 1327.7748 1823.2793 2563.4702 3689.0840 5634.3765 9366.3633 17690.7559 | lr 4.9e-04 | norm 7160.8892 | dt 9.786 +type train | step 1229 | loss 153.5019 301.2330 435.1439 679.5117 963.5988 1361.6244 1863.7106 2607.3081 3726.3582 5622.6797 9270.0947 17270.9082 | lr 4.9e-04 | norm 6937.4751 | dt 9.791 +type train | step 1230 | loss 151.7240 295.9267 427.2257 667.1718 946.8817 1335.8634 1826.4855 2556.2676 3676.9412 5569.1743 9133.8848 16858.2109 | lr 4.9e-04 | norm 6897.9512 | dt 9.794 +type train | step 1231 | loss 156.6633 309.6340 442.7519 687.0978 971.2632 1375.5408 1884.5234 2645.7463 3798.5420 5764.4775 9566.8828 17913.6172 | lr 4.9e-04 | norm 8759.7529 | dt 9.793 +type train | step 1232 | loss 190.3218 388.8209 529.1705 791.6486 1088.2446 1565.2711 2136.1780 2991.7407 4089.9204 6141.1987 10010.0059 18702.6328 | lr 4.9e-04 | norm 14774.7373 | dt 9.747 +type train | step 1233 | loss 153.6881 297.3062 428.1100 667.3539 944.7988 1331.6843 1815.2330 2533.7666 3645.8562 5506.3945 9121.6758 16997.9102 | lr 4.9e-04 | norm 7854.8521 | dt 9.781 +type train | step 1234 | loss 154.8630 299.4459 432.1968 673.6075 953.7555 1347.3081 1839.9786 2570.6179 3684.1880 5589.7959 9245.2930 17310.9375 | lr 4.9e-04 | norm 7372.8208 | dt 9.797 +type train | step 1235 | loss 150.1594 294.5647 424.4569 666.7370 942.6713 1350.6259 1860.9498 2629.9868 3758.8132 5710.3555 9483.4854 17790.2363 | lr 4.9e-04 | norm 8041.9536 | dt 9.788 +type train | step 1236 | loss 147.9822 289.9191 416.0807 651.8494 922.0349 1301.8496 1792.0736 2524.4126 3632.5059 5516.1030 9134.6240 17113.1328 | lr 4.9e-04 | norm 7510.8462 | dt 9.789 +type train | step 1237 | loss 150.6576 296.3003 427.3636 662.6144 941.7514 1321.8610 1801.8197 2507.7083 3595.4512 5432.3354 8965.2773 16699.2148 | lr 4.9e-04 | norm 6434.0801 | dt 9.794 +type train | step 1238 | loss 167.2551 336.5515 484.3625 748.5666 1052.2739 1485.8716 2023.4917 2837.9192 3981.6172 5996.7793 9797.2285 18238.7793 | lr 4.9e-04 | norm 8257.1455 | dt 9.780 +type train | step 1239 | loss 150.3997 294.4526 420.6780 655.2402 934.9688 1325.2173 1822.7285 2570.1758 3673.1943 5586.0669 9199.4834 17095.8242 | lr 4.9e-04 | norm 6337.7754 | dt 9.776 +type train | step 1240 | loss 148.4353 290.0824 423.5176 665.3585 948.7282 1342.8739 1843.4802 2591.7852 3723.7705 5638.7764 9278.6963 17232.0820 | lr 4.9e-04 | norm 6068.1045 | dt 9.787 +type train | step 1241 | loss 142.9741 278.7877 408.3388 639.9702 921.2026 1306.4420 1799.4028 2529.5691 3621.6470 5518.1582 9164.7334 17193.8496 | lr 4.9e-04 | norm 6750.2568 | dt 9.774 +type train | step 1242 | loss 147.8348 291.1851 420.8160 660.3942 934.7624 1321.9595 1808.9637 2540.9556 3625.9331 5504.6924 9090.4219 17059.8262 | lr 4.9e-04 | norm 7904.0869 | dt 9.785 +type train | step 1243 | loss 158.9142 315.6210 460.9460 726.1324 1026.3129 1463.6744 1997.6018 2822.6841 4006.0828 6118.7383 10063.2637 18918.1504 | lr 4.9e-04 | norm 8616.3887 | dt 9.779 +type train | step 1244 | loss 172.4062 344.6409 484.4237 745.0261 1034.3110 1450.4288 1952.7108 2707.4214 3787.3496 5720.3335 9390.3535 17757.1738 | lr 4.9e-04 | norm 9237.5254 | dt 9.750 +type train | step 1245 | loss 153.5609 300.5978 437.9552 683.7899 973.5614 1372.8630 1876.1469 2638.1433 3771.9500 5716.5562 9481.1113 17740.0586 | lr 4.9e-04 | norm 7162.5815 | dt 9.769 +type train | step 1246 | loss 163.8990 325.7236 467.6606 724.9697 1018.0225 1412.7527 1923.6366 2685.8906 3808.9236 5779.9580 9544.6807 17799.0586 | lr 4.9e-04 | norm 8485.1641 | dt 9.788 +type train | step 1247 | loss 153.8383 301.8912 436.5777 680.7091 971.8067 1369.3519 1864.5541 2619.8152 3749.3262 5693.7485 9329.4814 17234.7207 | lr 4.9e-04 | norm 7596.6880 | dt 9.793 +type train | step 1248 | loss 160.0050 312.8784 442.9821 685.1166 969.4213 1363.3484 1853.3795 2588.4363 3648.8408 5521.6572 8995.7852 16652.8867 | lr 4.9e-04 | norm 6773.8906 | dt 9.782 +type train | step 1249 | loss 156.9373 307.0947 443.6429 691.2534 978.7046 1381.1703 1877.9768 2620.1357 3744.1797 5675.1680 9369.1455 17374.1738 | lr 4.9e-04 | norm 6303.5186 | dt 9.789 +type train | step 1250 | loss 186.4306 370.9738 513.5905 777.5756 1076.1417 1500.9802 2016.7556 2781.5610 3840.2556 5735.7998 9242.9336 16959.9395 | lr 4.9e-04 | norm 6895.8486 | dt 9.771 +type train | step 1251 | loss 151.6974 298.2267 426.6102 660.5124 944.5966 1338.6595 1827.3689 2555.6792 3647.6333 5568.4854 9204.5889 17206.6289 | lr 4.9e-04 | norm 6360.9673 | dt 9.779 +type train | step 1252 | loss 165.9378 327.6669 464.2881 714.0131 999.4195 1405.8262 1902.5876 2661.7039 3745.2432 5676.5522 9320.8984 17428.9160 | lr 4.9e-04 | norm 7030.4238 | dt 9.778 +type train | step 1253 | loss 143.6079 281.2597 414.7572 658.8855 937.3912 1329.8550 1832.8973 2579.4626 3713.4319 5662.1489 9352.8496 17466.6367 | lr 4.9e-04 | norm 6954.4912 | dt 9.775 +type train | step 1254 | loss 149.2525 292.5632 428.6096 670.9122 956.5388 1342.6848 1835.6276 2565.9011 3680.0588 5622.8882 9318.9297 17443.0234 | lr 4.9e-04 | norm 8558.2236 | dt 9.782 +type train | step 1255 | loss 151.9147 300.0965 431.1514 670.9105 955.8765 1340.2588 1834.0376 2557.2310 3654.6904 5563.7715 9222.6250 17187.8262 | lr 4.9e-04 | norm 6380.6841 | dt 9.794 +type train | step 1256 | loss 144.7235 283.8073 410.4966 645.7908 922.7590 1308.1873 1791.8401 2520.0969 3634.6194 5514.0127 9107.6133 17043.3379 | lr 4.9e-04 | norm 7332.4307 | dt 9.784 +type train | step 1257 | loss 142.3680 275.8102 399.8882 627.6588 901.1779 1269.0322 1743.3748 2439.4663 3507.6523 5338.1177 8841.0264 16464.0449 | lr 4.9e-04 | norm 6385.8320 | dt 9.785 +type train | step 1258 | loss 146.4362 286.9883 420.4387 666.8646 957.6530 1358.7303 1862.6989 2618.5369 3754.5496 5712.7246 9479.1602 17719.9316 | lr 4.9e-04 | norm 6234.4355 | dt 9.781 +type train | step 1259 | loss 148.3829 290.4688 420.6682 654.1299 933.8535 1318.4275 1803.1444 2528.1865 3622.8218 5523.8652 9147.8105 16907.6348 | lr 4.9e-04 | norm 6052.9429 | dt 9.787 +type train | step 1260 | loss 155.6244 306.2200 441.8535 692.6233 971.2444 1363.9417 1847.1498 2562.9021 3639.0808 5459.5020 8954.5488 16621.9453 | lr 4.9e-04 | norm 7195.1768 | dt 9.780 +type train | step 1261 | loss 155.5634 303.1082 436.6031 681.4785 962.2168 1362.2526 1852.4814 2587.2363 3642.1511 5493.6240 9021.4883 16821.0820 | lr 4.9e-04 | norm 8019.5493 | dt 9.769 +type train | step 1262 | loss 149.3224 292.4473 420.8676 659.1484 935.5464 1318.9283 1808.0338 2531.7859 3634.6550 5547.1387 9179.8906 17179.0195 | lr 4.9e-04 | norm 7300.5259 | dt 9.772 +type train | step 1263 | loss 150.2489 294.2027 418.9950 652.0478 925.6471 1297.0302 1770.4188 2462.9507 3537.0815 5379.5000 8913.2705 16626.4238 | lr 4.9e-04 | norm 7507.9097 | dt 9.787 +type train | step 1264 | loss 155.8794 305.5484 438.2484 680.0504 961.5100 1362.6305 1858.8677 2615.1182 3716.8416 5608.4316 9216.0703 17069.8730 | lr 4.9e-04 | norm 6514.0376 | dt 9.788 +type train | step 1265 | loss 157.1713 306.5573 438.1194 677.8638 963.9208 1362.0128 1871.9822 2617.1606 3731.2798 5662.0498 9333.1582 17432.7090 | lr 4.9e-04 | norm 7489.1714 | dt 9.779 +type train | step 1266 | loss 158.4701 308.0208 442.8428 685.6340 971.3908 1379.4077 1874.2714 2632.3269 3720.2573 5627.7490 9301.7861 17279.6699 | lr 4.9e-04 | norm 7038.6099 | dt 9.781 +type train | step 1267 | loss 145.9396 285.8623 415.9572 656.8375 943.7540 1345.5752 1853.6820 2611.0200 3741.9478 5642.0122 9307.3203 17254.0918 | lr 4.9e-04 | norm 6463.9082 | dt 9.788 +type train | step 1268 | loss 149.6978 291.3944 423.8001 662.4582 942.3915 1334.4769 1828.8939 2561.5781 3651.1104 5559.5264 9220.1162 17199.2793 | lr 4.9e-04 | norm 6451.0425 | dt 9.794 +type train | step 1269 | loss 149.4391 296.1627 430.8291 676.0346 966.6256 1367.7772 1883.5601 2654.2019 3788.9658 5783.2236 9572.4541 17879.5469 | lr 4.9e-04 | norm 6864.9458 | dt 9.780 +type train | step 1270 | loss 157.2276 311.8487 450.3569 695.5302 991.0881 1393.2686 1905.9669 2721.3777 3788.3286 5738.0684 9409.4561 17493.1328 | lr 4.9e-04 | norm 6707.1006 | dt 9.795 +type train | step 1271 | loss 159.3410 311.1212 447.4235 695.5098 976.7464 1384.1342 1881.9541 2631.6814 3723.4021 5668.2744 9343.7539 17451.0527 | lr 4.9e-04 | norm 7888.3657 | dt 9.788 +type train | step 1272 | loss 154.6841 301.3688 432.3174 676.0457 957.4653 1352.2759 1848.1909 2605.3196 3699.2527 5638.1162 9295.7598 17150.6348 | lr 4.9e-04 | norm 7161.5723 | dt 9.799 +type train | step 1273 | loss 151.2036 296.2427 429.7579 670.8836 955.2339 1346.7460 1837.3544 2594.3896 3695.1072 5636.9639 9266.1436 17105.6934 | lr 4.9e-04 | norm 6555.9224 | dt 9.794 +type train | step 1274 | loss 145.9338 283.2251 414.9952 656.4220 934.1871 1329.6693 1822.1646 2599.3154 3685.8767 5613.2607 9284.0918 17195.8379 | lr 4.9e-04 | norm 6621.5059 | dt 9.784 +type train | step 1275 | loss 148.0513 292.4591 424.0015 664.5272 943.9310 1332.8064 1815.5382 2562.0356 3636.9756 5541.1924 9120.9453 16775.6387 | lr 4.9e-04 | norm 5833.6685 | dt 9.796 +type train | step 1276 | loss 144.8677 281.6248 409.4327 644.5946 916.4962 1299.3696 1782.0173 2555.4580 3583.9209 5472.3677 9069.7549 16924.3613 | lr 4.9e-04 | norm 6360.4648 | dt 9.780 +type train | step 1277 | loss 146.9384 286.6546 419.3140 652.9605 933.0975 1319.5247 1803.6871 2594.2507 3622.8918 5510.0928 9060.8018 16840.6719 | lr 4.9e-04 | norm 6519.0962 | dt 9.787 +type train | step 1278 | loss 142.2281 278.5961 409.5038 648.5855 929.0002 1314.1471 1804.2876 2614.7944 3690.2803 5643.4512 9291.1514 17358.5430 | lr 4.8e-04 | norm 9343.8711 | dt 9.772 +type train | step 1279 | loss 145.7286 285.2281 414.6957 654.2142 936.7966 1336.6248 1839.4689 2659.2830 3710.5640 5658.3633 9304.4424 17329.8047 | lr 4.8e-04 | norm 7319.6050 | dt 9.791 +type train | step 1280 | loss 141.2338 275.7659 401.6032 628.2018 901.7111 1280.4177 1761.6772 2561.0713 3581.1479 5461.8936 9040.2568 16750.4258 | lr 4.8e-04 | norm 7061.6636 | dt 9.800 +type train | step 1281 | loss 147.0503 288.7862 422.4166 661.4769 944.8619 1325.7400 1817.9252 2619.2212 3662.6323 5552.5791 9142.4248 16955.2852 | lr 4.8e-04 | norm 6777.7549 | dt 9.810 +type train | step 1282 | loss 156.6527 308.0450 460.6831 722.2883 1029.6437 1454.1848 1978.0717 2867.9829 3939.6182 6044.6929 10138.9014 19114.6719 | lr 4.8e-04 | norm 12068.2490 | dt 9.775 +type train | step 1283 | loss 145.2995 280.6400 407.2501 645.0453 912.1501 1281.5033 1753.9204 2522.6519 3524.6975 5332.6465 8749.2461 16178.3281 | lr 4.8e-04 | norm 6889.0947 | dt 9.792 +type train | step 1284 | loss 160.1003 317.4982 452.3850 699.6824 993.8884 1408.7515 1916.0579 2749.3215 3792.9250 5739.3916 9480.6094 17810.6211 | lr 4.8e-04 | norm 6842.4463 | dt 9.791 +type train | step 1285 | loss 151.9846 291.8736 420.9949 654.7245 936.0211 1323.4233 1818.4835 2603.6724 3647.5303 5517.4922 9033.9834 16734.2461 | lr 4.8e-04 | norm 7656.2236 | dt 9.778 +type train | step 1286 | loss 148.3935 291.9742 421.6436 659.1251 940.6465 1325.5786 1820.7086 2597.5190 3638.0642 5538.0732 9133.8291 16956.0938 | lr 4.8e-04 | norm 6310.8745 | dt 9.795 +type train | step 1287 | loss 157.2169 309.1970 439.7112 679.3515 963.3639 1355.5524 1858.6053 2671.6748 3687.3484 5649.9121 9322.6592 17334.9199 | lr 4.8e-04 | norm 8224.1357 | dt 9.797 +type train | step 1288 | loss 149.2661 292.8660 425.6692 665.6295 940.6160 1324.4083 1806.7394 2576.6382 3600.3550 5457.7324 9009.2568 16734.4141 | lr 4.8e-04 | norm 6304.9805 | dt 9.802 +type train | step 1289 | loss 151.6410 297.3277 426.6448 660.5557 943.9368 1330.4148 1818.2423 2565.1096 3595.4453 5434.4102 8970.0342 16604.5098 | lr 4.8e-04 | norm 7345.5708 | dt 9.796 +type train | step 1290 | loss 150.3984 295.1589 428.5164 672.0076 959.1361 1363.8494 1863.0847 2660.5034 3724.5791 5649.9507 9305.4922 17305.0020 | lr 4.8e-04 | norm 6195.0791 | dt 9.789 +type train | step 1291 | loss 142.4711 279.6511 408.2275 645.2612 920.1891 1304.7476 1788.4581 2573.6438 3611.3945 5475.8979 8987.2959 16625.2363 | lr 4.8e-04 | norm 6189.1855 | dt 9.784 +type train | step 1292 | loss 140.6472 276.0258 401.1728 631.4617 906.6691 1287.5480 1769.2157 2528.5535 3567.4365 5464.0645 9007.9209 16763.6797 | lr 4.8e-04 | norm 6151.8389 | dt 9.787 +type train | step 1293 | loss 147.7308 289.0675 418.9398 654.3731 933.9298 1324.1388 1809.6848 2575.6304 3616.9106 5489.6523 9066.7041 16838.3691 | lr 4.8e-04 | norm 5833.7202 | dt 9.790 +type train | step 1294 | loss 157.5846 312.0178 445.0712 688.8185 970.4974 1372.9614 1873.2412 2664.2874 3715.8081 5615.7617 9136.1348 16914.0137 | lr 4.8e-04 | norm 6112.8037 | dt 9.792 +type train | step 1295 | loss 146.4948 285.8702 417.7953 656.0649 932.3774 1320.8243 1808.8340 2587.6670 3658.9543 5575.5415 9281.6484 17316.6152 | lr 4.8e-04 | norm 6456.9038 | dt 9.777 +type train | step 1296 | loss 148.9070 291.7983 425.0719 669.4807 947.0039 1351.7510 1843.6155 2643.6831 3663.0645 5509.5127 9075.5273 16821.9668 | lr 4.8e-04 | norm 6489.2969 | dt 9.790 +type train | step 1297 | loss 159.4686 313.8221 451.5143 704.4933 989.6583 1422.1182 1933.9656 2769.0225 3856.4353 5826.2427 9583.2920 17913.8262 | lr 4.8e-04 | norm 7164.0308 | dt 9.781 +type train | step 1298 | loss 143.6168 281.1482 408.7931 657.6017 937.4630 1329.1772 1818.3544 2572.5212 3664.5603 5592.1978 9347.7441 17353.8379 | lr 4.8e-04 | norm 7673.1431 | dt 9.778 +type train | step 1299 | loss 148.8466 289.2483 417.6815 654.8831 928.5043 1318.1010 1804.1786 2560.9324 3622.9729 5503.1670 9068.5615 16671.5781 | lr 4.8e-04 | norm 6780.9961 | dt 9.782 +type train | step 1300 | loss 140.1208 273.4610 397.9336 624.5629 894.6520 1270.7568 1746.1693 2493.2854 3517.9451 5362.7041 8859.5215 16474.8359 | lr 4.8e-04 | norm 6738.1338 | dt 9.785 +type train | step 1301 | loss 149.8308 290.9913 424.4752 660.7267 937.3345 1340.9106 1833.5729 2653.2275 3648.4985 5505.5933 9047.5186 16841.1660 | lr 4.8e-04 | norm 6724.2192 | dt 9.774 +type train | step 1302 | loss 143.5630 281.3604 410.4522 642.6942 918.2143 1297.9502 1781.5630 2535.6213 3596.7686 5471.0713 9020.0684 16752.8672 | lr 4.8e-04 | norm 6268.3184 | dt 9.785 +type train | step 1303 | loss 157.8417 308.5226 439.0540 674.7381 956.9678 1358.9143 1857.5320 2639.4253 3669.7476 5556.6484 9081.3330 16964.8965 | lr 4.8e-04 | norm 7484.5635 | dt 9.775 +type train | step 1304 | loss 136.7209 266.7838 392.2992 617.9316 884.9841 1266.1996 1740.6726 2493.2554 3534.4734 5399.5356 8930.4639 16637.1152 | lr 4.8e-04 | norm 6787.8359 | dt 9.789 +type train | step 1305 | loss 149.3099 292.1148 419.5080 655.8957 939.1671 1331.1115 1840.2156 2649.2146 3719.4641 5665.2471 9330.8398 17276.0566 | lr 4.8e-04 | norm 7222.0957 | dt 9.781 +type train | step 1306 | loss 153.0496 301.6901 431.9292 672.6852 949.5723 1353.9906 1852.9856 2638.2415 3696.2783 5592.5684 9195.8965 17183.0820 | lr 4.8e-04 | norm 7936.9819 | dt 9.778 +type train | step 1307 | loss 158.4014 314.7135 445.4279 695.0814 982.3980 1405.7717 1914.2144 2743.4600 3784.7732 5709.7148 9347.8604 17414.5156 | lr 4.8e-04 | norm 7842.4507 | dt 9.765 +type train | step 1308 | loss 148.6459 290.9434 423.1357 663.5667 943.3442 1334.4778 1826.6013 2600.9111 3644.7588 5546.3438 9207.8154 17185.2891 | lr 4.8e-04 | norm 7901.5161 | dt 9.789 +type train | step 1309 | loss 152.4678 299.5638 428.6535 664.5678 936.8351 1330.2159 1815.9646 2572.7485 3605.2485 5480.5498 9046.7305 16896.8848 | lr 4.8e-04 | norm 7867.2344 | dt 9.790 +type train | step 1310 | loss 153.7772 302.0312 431.0858 662.0098 938.3903 1302.4780 1770.7709 2480.4500 3520.5869 5388.8608 8849.8096 16536.0000 | lr 4.8e-04 | norm 12143.7051 | dt 9.784 +type train | step 1311 | loss 161.1962 316.0899 451.3715 700.7537 987.1735 1399.1340 1900.8929 2695.1890 3753.0042 5645.5737 9218.3916 17137.9434 | lr 4.8e-04 | norm 6908.0293 | dt 9.786 +type train | step 1312 | loss 150.9609 295.4423 420.3541 649.2842 924.0126 1297.1436 1776.6791 2531.1843 3554.6064 5384.1963 8869.7373 16533.8887 | lr 4.8e-04 | norm 7548.2544 | dt 9.805 +type train | step 1313 | loss 158.0422 313.9022 451.9687 696.6773 992.6328 1412.2914 1927.4045 2750.8159 3854.0928 5849.7236 9653.5801 17924.8867 | lr 4.8e-04 | norm 7632.9604 | dt 9.779 +type train | step 1314 | loss 142.3912 281.6786 415.9546 659.4508 952.9336 1354.8877 1875.3959 2687.7417 3799.3198 5847.9961 9697.5205 17974.2129 | lr 4.8e-04 | norm 10127.2969 | dt 9.783 +type train | step 1315 | loss 141.5064 275.5560 404.2993 635.5399 911.9620 1296.7369 1791.6879 2555.9602 3596.2324 5430.7402 8841.3467 16177.7393 | lr 4.8e-04 | norm 9195.6855 | dt 9.790 +type train | step 1316 | loss 149.3697 292.8333 418.7138 644.6844 918.5809 1303.8245 1786.1523 2563.8042 3559.2668 5422.4746 8940.0537 16753.8633 | lr 4.8e-04 | norm 8369.4395 | dt 9.776 +type train | step 1317 | loss 143.0092 278.5529 408.5341 642.9303 915.6018 1303.2799 1786.9000 2548.0461 3594.5498 5474.8101 9051.4277 16843.4316 | lr 4.8e-04 | norm 7032.3594 | dt 9.782 +type train | step 1318 | loss 154.7828 305.3284 434.3511 669.5677 949.5291 1352.7684 1850.2460 2652.3628 3692.5083 5606.0205 9230.2119 17170.7285 | lr 4.8e-04 | norm 7637.8608 | dt 9.778 +type train | step 1319 | loss 157.2637 311.9820 444.9951 688.9257 975.1692 1382.5980 1880.7102 2670.3135 3717.8982 5645.7134 9222.3711 17272.3613 | lr 4.8e-04 | norm 7367.4302 | dt 9.769 +type train | step 1320 | loss 147.2309 288.5369 418.1248 650.8523 925.7230 1315.0631 1797.4552 2558.7891 3601.6013 5487.1685 9053.7285 16888.0918 | lr 4.8e-04 | norm 7007.3291 | dt 9.793 +type train | step 1321 | loss 156.4761 308.9134 440.1235 681.6329 960.5088 1353.1522 1853.4224 2672.4956 3670.3726 5552.9702 9025.0518 16701.6855 | lr 4.8e-04 | norm 7359.9653 | dt 9.788 +type train | step 1322 | loss 147.2821 288.2243 415.8570 646.3881 917.6190 1297.0583 1771.6771 2535.2473 3546.8562 5382.7944 8906.3652 16605.0664 | lr 4.8e-04 | norm 6489.6108 | dt 9.794 +type train | step 1323 | loss 142.8994 277.5128 405.2662 636.1787 911.6292 1304.6415 1793.8350 2587.4915 3631.0945 5518.6650 9081.3438 16913.0801 | lr 4.8e-04 | norm 6476.1050 | dt 9.788 +type train | step 1324 | loss 149.9198 294.4115 419.7023 643.9246 918.9740 1308.0968 1791.3167 2561.4636 3575.7515 5451.0376 9026.1064 16844.6094 | lr 4.8e-04 | norm 7281.4302 | dt 9.783 +type train | step 1325 | loss 136.2343 265.6748 392.1956 619.7509 890.9212 1272.0061 1752.5199 2525.6143 3564.2913 5407.5381 8891.8486 16590.8613 | lr 4.8e-04 | norm 7656.2041 | dt 9.765 +type train | step 1326 | loss 145.3882 282.6175 405.2738 637.5388 902.5236 1302.3767 1801.1345 2603.0156 3615.2188 5502.4731 9013.2852 17088.2969 | lr 4.8e-04 | norm 10004.8271 | dt 9.779 +type train | step 1327 | loss 146.4011 286.5772 418.0949 657.1992 935.6848 1327.7656 1832.0298 2663.3569 3736.2678 5705.2378 9330.3008 17204.0020 | lr 4.8e-04 | norm 8325.2705 | dt 9.781 +type train | step 1328 | loss 148.7077 294.1978 426.8479 671.3492 954.1118 1351.1794 1842.8644 2638.0332 3678.8667 5593.2466 9186.6064 17168.7676 | lr 4.8e-04 | norm 7657.5698 | dt 9.791 +type train | step 1329 | loss 141.3544 272.3576 399.0923 628.0660 896.2919 1273.4410 1742.6682 2508.0066 3514.1775 5388.7627 8979.0312 16801.9844 | lr 4.8e-04 | norm 7613.3091 | dt 9.793 +type train | step 1330 | loss 152.8033 301.7271 438.2372 683.3931 971.0041 1381.1646 1884.0560 2698.9607 3727.0322 5682.3638 9327.8213 17489.4648 | lr 4.8e-04 | norm 7746.8804 | dt 9.776 +type train | step 1331 | loss 150.4739 290.7644 415.2477 651.0050 922.8960 1313.4141 1793.6339 2591.4731 3575.3362 5371.1343 8763.2314 16292.8643 | lr 4.8e-04 | norm 7342.7700 | dt 9.786 +type train | step 1332 | loss 140.6216 272.7988 397.2578 626.2895 888.8307 1262.7565 1732.3616 2503.9360 3478.0903 5298.3438 8754.3096 16407.6309 | lr 4.8e-04 | norm 6580.0815 | dt 9.789 +type train | step 1333 | loss 147.6548 286.8359 413.4536 646.5091 925.2490 1318.4663 1811.5104 2606.7104 3618.4180 5477.9399 9014.2227 16723.3809 | lr 4.8e-04 | norm 6237.5654 | dt 9.802 +type train | step 1334 | loss 141.9040 277.5267 403.0571 628.5722 904.5459 1286.1210 1760.3478 2537.8323 3547.5881 5424.4531 8978.6152 16716.4062 | lr 4.8e-04 | norm 6304.2476 | dt 9.784 +type train | step 1335 | loss 149.8046 295.0316 426.8037 663.0048 942.6329 1323.2651 1808.3761 2591.9468 3609.2966 5507.1694 9072.5859 16914.0840 | lr 4.8e-04 | norm 6991.5889 | dt 9.789 +type train | step 1336 | loss 160.2292 312.9051 447.4525 693.8083 985.8779 1381.0623 1875.1907 2676.6194 3731.2620 5578.3481 9130.1445 17060.4102 | lr 4.8e-04 | norm 9757.7617 | dt 9.780 +type train | step 1337 | loss 143.3685 281.1117 405.8733 637.3170 903.6028 1285.1011 1766.7549 2556.1165 3561.9609 5442.5269 8956.4502 16755.7188 | lr 4.8e-04 | norm 7595.9395 | dt 9.795 +type train | step 1338 | loss 139.7774 273.1787 399.8839 624.6716 895.8163 1272.6843 1746.4690 2524.2048 3535.2832 5427.6733 9000.6484 16875.8926 | lr 4.8e-04 | norm 7498.2476 | dt 9.788 +type train | step 1339 | loss 150.7958 294.6632 421.4280 652.7615 924.8854 1307.3341 1781.6501 2564.7349 3553.2266 5366.5151 8704.3867 16205.0635 | lr 4.8e-04 | norm 6748.4854 | dt 9.782 +type train | step 1340 | loss 141.0484 273.1068 395.9897 624.4988 897.5245 1279.0844 1748.9943 2533.1797 3518.5332 5363.6973 8885.7197 16598.1211 | lr 4.8e-04 | norm 6910.3003 | dt 9.789 +type train | step 1341 | loss 142.8349 275.9215 398.0065 624.8327 895.7274 1279.1571 1771.6501 2566.1914 3589.4863 5459.6387 9007.1758 16766.7012 | lr 4.8e-04 | norm 6922.2861 | dt 9.783 +type train | step 1342 | loss 136.2320 265.9233 390.0363 615.0096 880.9070 1258.6670 1736.4852 2518.1089 3512.3442 5338.0361 8782.6719 16328.4814 | lr 4.8e-04 | norm 6526.5264 | dt 9.787 +type train | step 1343 | loss 156.7762 308.3755 443.8714 682.8623 964.8082 1350.2908 1837.0173 2628.9844 3659.3513 5539.2544 9106.0059 16885.9746 | lr 4.8e-04 | norm 7067.8413 | dt 9.788 +type train | step 1344 | loss 138.5814 271.9026 393.1665 614.9091 880.7834 1246.3253 1705.1123 2459.9585 3432.6484 5235.7686 8608.6992 15925.4521 | lr 4.8e-04 | norm 5819.8062 | dt 9.784 +type train | step 1345 | loss 150.1143 295.3033 426.2949 661.6212 944.3120 1336.9602 1832.1232 2640.9307 3677.3911 5590.4307 9122.6016 16959.8047 | lr 4.8e-04 | norm 7617.0884 | dt 9.794 +type train | step 1346 | loss 144.9155 281.0859 406.7307 633.7709 911.7107 1303.7490 1797.3224 2608.2588 3625.1775 5547.4414 9188.5225 17171.1113 | lr 4.8e-04 | norm 6642.2119 | dt 9.784 +type train | step 1347 | loss 138.4512 271.6737 394.0707 618.1430 886.0542 1258.2517 1730.2207 2487.7830 3520.8149 5393.6167 8902.2734 16532.8691 | lr 4.8e-04 | norm 7631.0464 | dt 9.778 +type train | step 1348 | loss 144.1031 285.4110 424.4242 668.6439 961.8008 1354.2501 1873.8765 2698.5933 3764.3601 5691.0645 9343.6377 17237.5762 | lr 4.8e-04 | norm 11510.9990 | dt 9.787 +type train | step 1349 | loss 138.9022 269.6161 396.3313 618.8667 887.4738 1272.7178 1748.8176 2515.7954 3540.5823 5387.0127 8889.4551 16691.9551 | lr 4.8e-04 | norm 7934.6973 | dt 9.784 +type train | step 1350 | loss 154.1878 300.1640 431.6368 669.9398 947.2087 1344.3484 1837.8602 2621.3521 3647.4541 5510.0576 9032.4619 16800.9004 | lr 4.8e-04 | norm 6916.3379 | dt 9.785 +type train | step 1351 | loss 149.0515 293.1021 424.0698 661.1277 941.1443 1336.8273 1834.9775 2637.5676 3666.3059 5583.1211 9258.4004 17295.7109 | lr 4.8e-04 | norm 7079.2622 | dt 9.785 +type train | step 1352 | loss 140.4328 278.3040 412.4410 655.0552 932.1091 1324.1868 1811.2230 2598.0371 3644.9102 5504.5688 9058.3213 16876.9004 | lr 4.8e-04 | norm 7771.2900 | dt 9.783 +type train | step 1353 | loss 135.4869 262.2857 382.2303 600.3690 870.1796 1238.9020 1711.4631 2476.1152 3478.3057 5320.2920 8756.7676 16380.3652 | lr 4.8e-04 | norm 6286.4146 | dt 9.785 +type train | step 1354 | loss 142.1085 276.6840 406.0750 634.5839 907.2318 1293.3361 1773.5956 2538.6887 3522.6890 5331.2363 8764.8115 16351.2148 | lr 4.8e-04 | norm 7034.1025 | dt 9.787 +type train | step 1355 | loss 142.6838 278.6645 409.1062 642.5035 917.7226 1315.2782 1798.3044 2584.0393 3596.7427 5445.5552 8998.4502 16616.9453 | lr 4.8e-04 | norm 6609.5171 | dt 9.794 +type train | step 1356 | loss 142.3895 275.7953 401.3423 624.7574 893.7109 1264.8081 1728.3883 2486.0747 3460.5859 5273.2461 8713.6797 16293.3662 | lr 4.8e-04 | norm 6509.7568 | dt 9.774 +type train | step 1357 | loss 151.9352 298.0320 432.9064 682.1657 969.6976 1389.7029 1901.4905 2733.0208 3801.3472 5784.7871 9535.1240 17924.8418 | lr 4.8e-04 | norm 7459.6348 | dt 9.767 +type train | step 1358 | loss 153.8252 303.1528 435.1484 677.8279 954.4033 1358.9047 1851.2954 2663.3640 3690.9451 5587.3159 9254.0713 17315.9355 | lr 4.8e-04 | norm 6667.7544 | dt 9.784 +type train | step 1359 | loss 144.7212 282.3138 407.0057 635.2850 905.4850 1286.0629 1759.6500 2533.1348 3547.8276 5414.9219 8934.6006 16734.7305 | lr 4.8e-04 | norm 7046.8853 | dt 9.789 +type train | step 1360 | loss 143.6158 278.2914 400.6942 626.5538 899.3058 1275.7716 1755.9905 2523.6375 3530.9963 5362.2500 8780.7754 16241.4111 | lr 4.8e-04 | norm 6590.3340 | dt 9.788 +type train | step 1361 | loss 142.1766 276.9727 404.7381 634.1437 905.8253 1286.6163 1765.8071 2541.9758 3543.7888 5384.0571 8850.3887 16488.3027 | lr 4.8e-04 | norm 5644.6221 | dt 9.797 +type train | step 1362 | loss 145.3947 283.2325 410.7693 640.7529 914.0028 1294.3500 1766.3888 2534.2686 3540.1536 5352.0151 8775.5156 16290.4941 | lr 4.8e-04 | norm 6109.3955 | dt 9.808 +type train | step 1363 | loss 137.5794 267.5896 389.6306 615.8345 887.8822 1278.2607 1764.5977 2549.3408 3564.4292 5453.0640 9015.3359 16846.4668 | lr 4.8e-04 | norm 6667.9658 | dt 9.781 +type train | step 1364 | loss 162.6143 317.3268 449.6874 689.2690 976.2222 1390.2395 1877.9537 2660.5505 3647.1055 5466.8306 8802.7930 16264.6855 | lr 4.8e-04 | norm 6664.6709 | dt 9.787 +type train | step 1365 | loss 132.2652 256.7695 379.3622 602.2132 869.5873 1248.8792 1730.4484 2515.6470 3536.7168 5389.1675 8900.0684 16567.0762 | lr 4.8e-04 | norm 6268.6934 | dt 9.784 +type train | step 1366 | loss 145.1888 284.1940 405.8506 637.1718 905.6436 1299.1267 1775.8754 2551.4312 3541.1914 5400.2417 8998.9453 16859.7832 | lr 4.8e-04 | norm 6570.1831 | dt 9.781 +type train | step 1367 | loss 149.3492 292.1791 421.3198 657.8513 933.2725 1329.1143 1811.8011 2592.7256 3596.4683 5449.7251 8972.5605 16811.3770 | lr 4.8e-04 | norm 7039.0293 | dt 9.776 +type train | step 1368 | loss 146.5501 286.7549 413.5525 648.9830 925.5302 1342.2245 1846.2798 2687.0684 3708.0952 5640.4756 9349.0264 17542.6934 | lr 4.8e-04 | norm 7266.9790 | dt 9.781 +type train | step 1369 | loss 138.9658 272.6414 395.4286 622.3599 891.8281 1275.3915 1748.2681 2523.3093 3532.9836 5389.6313 8894.2549 16462.2910 | lr 4.8e-04 | norm 5863.7964 | dt 9.779 +type train | step 1370 | loss 144.5754 285.1264 409.7586 642.7147 915.2006 1301.7626 1774.6951 2542.5513 3529.4041 5336.3716 8767.5059 16288.5000 | lr 4.8e-04 | norm 7089.1802 | dt 9.780 +type train | step 1371 | loss 135.8900 264.5346 385.6478 604.0707 870.5336 1236.5273 1696.0708 2433.2959 3431.8276 5228.8252 8703.9453 16340.6826 | lr 4.8e-04 | norm 6488.6396 | dt 9.774 +type train | step 1372 | loss 136.7054 265.5334 387.2737 607.7367 876.0565 1255.1052 1729.8105 2503.1143 3505.1592 5370.6426 8933.7061 16682.6445 | lr 4.8e-04 | norm 7222.4004 | dt 9.778 +type train | step 1373 | loss 138.8836 271.7495 400.7264 628.1601 903.0224 1291.6255 1774.4973 2550.7935 3595.9934 5466.8291 9051.5654 16934.9004 | lr 4.8e-04 | norm 6495.3730 | dt 9.777 +type train | step 1374 | loss 143.4325 279.1055 405.8482 636.7113 907.3588 1300.3850 1775.6392 2552.9343 3570.9841 5452.6553 9044.8457 16965.0020 | lr 4.8e-04 | norm 6527.4849 | dt 9.784 +type train | step 1375 | loss 146.5423 286.8514 416.5464 648.5972 921.2812 1319.9382 1809.5129 2595.5620 3600.8611 5459.6436 9009.3643 16866.9434 | lr 4.8e-04 | norm 7344.4453 | dt 9.791 +type train | step 1376 | loss 139.3210 270.0192 394.1125 617.1523 893.4130 1279.8341 1761.3834 2546.8213 3565.2590 5410.6836 8857.7188 16445.9902 | lr 4.8e-04 | norm 6415.4341 | dt 9.804 +type train | step 1377 | loss 144.2975 284.3754 413.5755 643.0763 916.1927 1290.9171 1767.8644 2510.0742 3515.4746 5355.0039 8810.7852 16251.1426 | lr 4.8e-04 | norm 6981.2329 | dt 9.786 +type train | step 1378 | loss 135.7973 263.6818 387.8285 609.7951 884.0403 1260.4094 1730.4912 2494.5044 3512.9009 5371.1689 8829.1104 16358.4697 | lr 4.8e-04 | norm 6374.8047 | dt 9.790 +type train | step 1379 | loss 143.2088 283.7147 410.3358 638.0534 910.7665 1287.2622 1765.4827 2527.2954 3536.6858 5390.7100 8883.5928 16472.4336 | lr 4.8e-04 | norm 6200.8301 | dt 9.781 +type train | step 1380 | loss 139.8049 268.5896 391.8806 619.7917 886.9194 1270.4014 1750.0840 2522.6428 3537.3223 5390.6611 8892.0957 16742.4922 | lr 4.8e-04 | norm 6481.3545 | dt 9.768 +type train | step 1381 | loss 143.3491 279.6702 404.9754 636.1737 909.7114 1299.6147 1778.4747 2551.1809 3545.0720 5382.1128 8901.8164 16579.8477 | lr 4.8e-04 | norm 6667.6895 | dt 9.781 +type train | step 1382 | loss 144.5530 283.8324 405.6583 630.0749 901.7173 1297.0657 1778.9747 2558.3940 3546.2837 5404.7598 8912.2236 16687.2324 | lr 4.8e-04 | norm 7102.6387 | dt 9.787 +type train | step 1383 | loss 139.8289 271.4257 391.2642 616.6472 880.0914 1261.6184 1725.9563 2467.1714 3457.0601 5241.5205 8655.7520 16086.5762 | lr 4.8e-04 | norm 5797.4062 | dt 9.785 +type train | step 1384 | loss 138.4610 271.3823 395.6374 613.6172 876.8558 1253.3724 1720.7448 2475.9702 3460.6038 5237.9077 8580.2510 15837.1221 | lr 4.8e-04 | norm 5962.9277 | dt 9.784 +type train | step 1385 | loss 147.3410 285.9344 418.2825 645.9208 923.2763 1300.6743 1789.8832 2564.5413 3620.9641 5509.4912 8986.1895 16670.2168 | lr 4.8e-04 | norm 7006.2271 | dt 9.775 +type train | step 1386 | loss 135.8780 266.0486 386.6026 607.8698 871.9999 1248.2784 1720.0668 2489.2258 3490.0918 5276.0391 8607.0156 15860.3057 | lr 4.8e-04 | norm 6441.2817 | dt 9.791 +type train | step 1387 | loss 144.6567 283.9283 409.4724 642.1703 915.7665 1302.4694 1778.8398 2547.3115 3526.6812 5330.4404 8743.0762 16351.3633 | lr 4.8e-04 | norm 6832.0215 | dt 9.796 +type train | step 1388 | loss 149.7485 292.2182 417.3914 646.6838 919.4759 1306.0569 1789.7234 2551.9238 3549.4810 5351.9175 8726.0000 16360.3652 | lr 4.8e-04 | norm 7113.9692 | dt 9.779 +type train | step 1389 | loss 132.2485 250.8894 376.7823 601.3913 870.8776 1256.5734 1736.0732 2521.5898 3559.3296 5445.1074 9112.4629 17208.1953 | lr 4.8e-04 | norm 8084.5137 | dt 9.770 +type train | step 1390 | loss 147.7353 290.8466 422.1546 660.5726 940.3246 1334.4216 1821.0427 2597.4031 3614.1323 5501.4971 9099.6963 16958.9590 | lr 4.8e-04 | norm 6668.6230 | dt 9.808 +type train | step 1391 | loss 152.4914 300.1361 429.0127 664.9156 942.1976 1337.7953 1825.8978 2592.1570 3590.8208 5423.1440 8871.7539 16569.3926 | lr 4.8e-04 | norm 6831.9766 | dt 9.775 +type train | step 1392 | loss 150.7649 294.5315 422.4568 657.8118 934.4194 1331.9135 1814.7358 2593.3704 3551.1018 5303.4526 8566.2246 15839.3086 | lr 4.8e-04 | norm 6663.7324 | dt 9.789 +type train | step 1393 | loss 138.5650 272.2155 396.8592 619.6781 888.6204 1260.1830 1733.7603 2489.8325 3483.7825 5323.5156 8730.6758 16271.1807 | lr 4.8e-04 | norm 7397.2505 | dt 9.793 +type train | step 1394 | loss 144.3718 282.6650 406.6697 631.9590 905.5323 1298.5264 1778.6478 2540.7678 3574.8953 5430.4990 8934.5430 16636.8730 | lr 4.8e-04 | norm 6280.5469 | dt 9.791 +type train | step 1395 | loss 145.6149 292.9294 429.4785 674.0649 960.1415 1365.7937 1865.6071 2668.1318 3741.5208 5653.8164 9242.9463 17262.3750 | lr 4.8e-04 | norm 11337.6309 | dt 9.790 +type train | step 1396 | loss 141.7975 281.1093 403.0123 629.5776 899.2773 1281.2198 1758.3036 2517.0735 3499.9895 5301.0815 8645.6162 16059.2891 | lr 4.8e-04 | norm 6802.3535 | dt 9.772 +type train | step 1397 | loss 146.2753 283.2225 410.4832 642.7313 916.1486 1310.9269 1796.5507 2580.8455 3599.2236 5465.4409 8973.3809 16727.9414 | lr 4.8e-04 | norm 6707.9248 | dt 9.780 +type train | step 1398 | loss 139.0124 271.1654 398.2014 625.5219 900.9363 1284.9152 1767.7205 2525.9771 3555.8604 5429.8096 8952.3838 16621.0000 | lr 4.8e-04 | norm 6926.5020 | dt 9.786 +type train | step 1399 | loss 141.5865 277.3144 402.3788 632.4049 906.9243 1284.3064 1760.3665 2515.0854 3542.9329 5353.5425 8760.5137 16391.7480 | lr 4.8e-04 | norm 7680.6685 | dt 9.788 +type train | step 1400 | loss 150.0845 293.5323 421.9790 652.4897 930.2566 1309.9504 1779.2257 2525.8862 3522.9727 5341.7432 8798.3838 16503.1953 | lr 4.8e-04 | norm 6710.3438 | dt 9.789 +type train | step 1401 | loss 151.8421 299.2023 425.3778 660.8374 935.9147 1338.5425 1826.3347 2619.4275 3624.0015 5513.6772 9132.8477 17300.7500 | lr 4.8e-04 | norm 7880.3521 | dt 9.774 +type train | step 1402 | loss 143.7652 281.7260 410.2917 642.7517 923.5112 1323.3484 1807.6427 2591.6250 3605.1221 5460.2241 8908.5762 16531.6582 | lr 4.8e-04 | norm 6424.1406 | dt 9.779 +type train | step 1403 | loss 144.6936 283.4596 411.4669 640.7725 916.1375 1307.0354 1784.6940 2552.6382 3559.1284 5384.9673 8857.5811 16642.3535 | lr 4.8e-04 | norm 6533.4614 | dt 9.796 +type train | step 1404 | loss 140.1086 270.6825 395.1354 620.4451 888.3436 1263.2069 1738.2759 2483.8628 3473.0823 5288.2871 8748.7617 16519.4922 | lr 4.8e-04 | norm 7436.1689 | dt 9.785 +type train | step 1405 | loss 145.7772 285.7713 415.6022 655.9724 937.7036 1334.8413 1825.1061 2611.9355 3627.7122 5494.4546 9045.7949 17144.6250 | lr 4.8e-04 | norm 6756.6553 | dt 9.781 +type train | step 1406 | loss 173.3751 348.0031 484.7385 735.4709 1031.2986 1450.6295 1969.1815 2784.1353 3766.5579 5564.8149 8941.4131 16650.1934 | lr 4.8e-04 | norm 8698.7305 | dt 9.777 +type train | step 1407 | loss 137.6380 268.2063 392.2407 613.9492 882.1944 1249.1505 1716.3663 2453.4641 3432.5698 5209.5830 8505.8291 15863.5713 | lr 4.8e-04 | norm 6987.0044 | dt 9.788 +type train | step 1408 | loss 130.3149 255.8548 379.0912 603.7280 867.8491 1256.0490 1733.2871 2520.0408 3568.3740 5475.6982 9111.1963 17182.5703 | lr 4.8e-04 | norm 9325.2129 | dt 9.787 +type train | step 1409 | loss 153.2551 297.6874 424.5598 659.0217 938.4346 1348.2059 1842.4401 2652.6157 3661.3879 5522.9663 9088.4082 16934.5527 | lr 4.8e-04 | norm 6890.6128 | dt 9.791 +type train | step 1410 | loss 137.5493 269.7904 392.0457 616.2985 880.1864 1262.4976 1723.6804 2484.7146 3481.5750 5294.8730 8785.6846 16523.0918 | lr 4.8e-04 | norm 7032.6670 | dt 9.773 +type train | step 1411 | loss 150.1691 292.4494 416.2538 643.9568 915.6539 1302.9241 1788.7626 2557.2466 3554.9546 5388.7188 8833.5889 16542.3398 | lr 4.8e-04 | norm 6789.8770 | dt 9.780 +type train | step 1412 | loss 154.4316 298.5812 430.4667 669.1190 942.3538 1346.1169 1833.6171 2628.2324 3619.7424 5504.4385 9104.2344 17279.6719 | lr 4.8e-04 | norm 9313.5547 | dt 9.761 +type train | step 1413 | loss 147.1708 292.4749 421.3235 661.1683 934.9078 1322.3246 1803.6479 2580.0493 3601.1902 5472.5625 8997.5381 16703.6953 | lr 4.8e-04 | norm 6826.6611 | dt 9.792 +type train | step 1414 | loss 150.0055 300.9707 440.7774 683.5888 978.6631 1371.4121 1860.8889 2639.1350 3672.1709 5580.2612 9244.3135 17518.5352 | lr 4.8e-04 | norm 9024.1494 | dt 9.783 +type train | step 1415 | loss 133.6376 262.8280 385.9497 612.8287 888.4135 1274.6141 1768.3645 2565.3345 3630.2000 5561.3965 9091.4902 16919.4453 | lr 4.8e-04 | norm 7395.2910 | dt 9.781 +type train | step 1416 | loss 150.0729 291.9698 421.3198 658.8058 938.9699 1345.5021 1850.4720 2654.9246 3736.3049 5670.7422 9299.8027 17419.0938 | lr 4.8e-04 | norm 7847.9180 | dt 9.778 +type train | step 1417 | loss 143.6327 282.0194 408.7702 631.0541 904.2513 1291.2278 1757.6541 2505.5439 3504.4155 5291.6875 8682.9014 16335.9785 | lr 4.8e-04 | norm 7567.6777 | dt 9.793 +type train | step 1418 | loss 140.0204 275.8204 396.3441 614.5735 882.9713 1262.3796 1725.1864 2466.2024 3475.0994 5266.2656 8651.2812 16020.9854 | lr 4.8e-04 | norm 6827.9683 | dt 9.782 +type train | step 1419 | loss 133.3206 259.9981 380.7230 607.6061 874.7561 1260.3147 1739.3168 2497.6353 3527.0603 5387.5312 8945.5918 16828.4980 | lr 4.8e-04 | norm 7275.5161 | dt 9.786 +type train | step 1420 | loss 143.0195 282.1729 417.1736 663.7009 946.8168 1341.3292 1829.9230 2616.0496 3679.4333 5640.2065 9353.2285 17690.7012 | lr 4.8e-04 | norm 10004.3818 | dt 9.777 +type train | step 1421 | loss 152.5784 306.4864 454.8753 714.2543 1024.6937 1461.5972 1991.7712 2838.7954 3922.1345 5887.1353 9555.7266 17715.3047 | lr 4.8e-04 | norm 7164.3726 | dt 9.778 +type train | step 1422 | loss 135.3832 263.8202 386.4696 605.4190 873.0569 1246.8094 1721.5251 2465.7451 3465.2461 5285.4253 8676.6611 16265.7412 | lr 4.8e-04 | norm 6460.6108 | dt 9.789 +type train | step 1423 | loss 137.7571 272.8595 402.9914 632.0505 911.0193 1293.4954 1771.1088 2532.1135 3548.9270 5421.7100 8955.3965 16666.0039 | lr 4.8e-04 | norm 6751.9097 | dt 9.789 +type train | step 1424 | loss 128.4947 249.1469 369.2312 589.8347 856.7086 1227.7135 1692.6967 2427.0564 3438.1221 5264.4966 8706.9043 16358.2285 | lr 4.8e-04 | norm 7140.6211 | dt 9.796 +type train | step 1425 | loss 154.7071 303.0260 438.8936 684.3299 963.5674 1370.9192 1854.4373 2619.5293 3616.7632 5418.1055 8770.8174 16379.3574 | lr 4.8e-04 | norm 7076.9980 | dt 9.788 +type train | step 1426 | loss 134.7055 263.0583 384.9617 605.5004 870.6470 1251.0637 1722.3441 2470.9041 3459.3413 5245.6240 8589.8984 15998.5859 | lr 4.8e-04 | norm 6034.3838 | dt 9.790 +type train | step 1427 | loss 150.0787 296.8167 429.7369 668.4545 951.2352 1349.8069 1839.9399 2608.7986 3628.1074 5465.8550 8920.1963 16516.4199 | lr 4.8e-04 | norm 7045.8228 | dt 9.793 +type train | step 1428 | loss 143.4523 283.0599 410.3792 637.0436 914.0963 1303.2428 1785.2590 2553.9915 3570.3289 5402.7319 8875.5674 16521.9141 | lr 4.8e-04 | norm 6411.0298 | dt 9.790 +type train | step 1429 | loss 130.9751 253.6621 373.2471 590.1783 859.6276 1236.0830 1712.7131 2457.2246 3478.5955 5324.9321 8769.3809 16362.7832 | lr 4.8e-04 | norm 7083.2002 | dt 9.781 +type train | step 1430 | loss 153.8115 302.3858 437.2046 676.4224 951.4634 1373.0175 1869.4491 2660.2134 3650.4856 5435.7949 8788.9961 16343.3379 | lr 4.8e-04 | norm 7140.1841 | dt 9.788 +type train | step 1431 | loss 153.1727 298.8983 428.9794 656.2445 937.5656 1321.1887 1796.6493 2548.1011 3529.6182 5310.6040 8656.4893 16199.5352 | lr 4.8e-04 | norm 8145.0762 | dt 9.790 +type train | step 1432 | loss 135.8068 262.5674 383.5196 603.1691 866.8715 1238.4178 1695.1554 2435.8938 3428.0581 5232.9038 8689.0137 16124.8213 | lr 4.8e-04 | norm 6663.3047 | dt 9.784 +type train | step 1433 | loss 130.9291 257.1476 380.4098 605.9496 874.7573 1249.1733 1718.4148 2463.6138 3463.9089 5308.7612 8842.4775 16478.2246 | lr 4.8e-04 | norm 7016.4712 | dt 9.790 +type train | step 1434 | loss 132.3031 259.3281 387.8615 621.5906 903.9484 1299.4994 1787.5725 2575.4900 3643.9722 5579.7808 9221.5352 17433.8359 | lr 4.7e-04 | norm 10491.5400 | dt 9.784 +type train | step 1435 | loss 162.3163 330.7362 474.4827 729.7839 1032.2877 1472.2957 2010.0801 2853.8486 3923.0088 5895.8813 9593.3711 17684.4570 | lr 4.7e-04 | norm 7554.4858 | dt 9.788 +type train | step 1436 | loss 140.3795 277.6751 402.8015 634.5109 904.9014 1292.4524 1777.8627 2538.7349 3537.0273 5355.5322 8781.8633 16407.5508 | lr 4.7e-04 | norm 6332.5093 | dt 9.799 +type train | step 1437 | loss 174.1549 355.3913 491.4580 764.9187 1089.9170 1625.2909 2186.1738 3141.7234 4142.4619 6071.7627 9764.8320 18192.6094 | lr 4.7e-04 | norm 15811.8330 | dt 9.762 +type train | step 1438 | loss 147.8131 286.6846 413.8899 651.1337 927.0998 1338.4392 1820.4747 2611.4343 3609.8799 5438.9595 8926.7119 16728.5508 | lr 4.7e-04 | norm 6957.9761 | dt 9.798 +type train | step 1439 | loss 138.8580 269.8757 393.8607 618.5700 886.6038 1271.4949 1740.3331 2497.0923 3501.2693 5329.1313 8800.7041 16438.6465 | lr 4.7e-04 | norm 6991.8936 | dt 9.786 +type train | step 1440 | loss 150.6632 295.3005 424.9747 658.3135 936.6081 1324.3502 1792.3184 2529.4814 3481.8225 5248.0059 8566.8252 16057.0859 | lr 4.7e-04 | norm 6773.0273 | dt 9.768 +type train | step 1441 | loss 143.5005 280.6267 406.5564 636.7017 909.3430 1295.8861 1771.4146 2528.4619 3534.6819 5415.6982 9058.7100 17082.3750 | lr 4.7e-04 | norm 6720.2529 | dt 9.785 +type train | step 1442 | loss 159.2845 311.5856 443.0752 679.3757 960.3074 1372.9722 1873.5474 2651.5664 3662.5684 5468.8965 8886.8037 16406.6699 | lr 4.7e-04 | norm 6633.7773 | dt 9.787 +type train | step 1443 | loss 139.9048 275.0787 398.3706 623.1574 890.6765 1278.0135 1750.0758 2508.6475 3505.3865 5329.8926 8737.0059 16285.9375 | lr 4.7e-04 | norm 6855.0205 | dt 9.780 +type train | step 1444 | loss 145.2920 286.7760 414.3997 652.3785 934.1809 1360.0222 1873.1587 2720.2446 3773.9199 5709.2222 9422.7715 17650.0684 | lr 4.7e-04 | norm 7857.2544 | dt 9.764 +type train | step 1445 | loss 138.5781 273.4099 397.8124 628.2589 900.7649 1305.6725 1802.5876 2582.8237 3590.7686 5465.2344 8983.1250 16781.8320 | lr 4.7e-04 | norm 7294.9766 | dt 9.778 +type train | step 1446 | loss 135.2412 265.8708 390.2412 611.0406 875.8145 1247.7748 1709.2577 2439.8208 3429.7856 5207.0020 8573.6094 15956.4102 | lr 4.7e-04 | norm 6121.3442 | dt 9.790 +type train | step 1447 | loss 156.9855 309.9833 443.1711 685.5227 975.0845 1390.6396 1892.3434 2696.3789 3704.2278 5550.1069 9019.8359 16873.9043 | lr 4.7e-04 | norm 7411.0332 | dt 9.775 +type train | step 1448 | loss 139.1815 269.5953 396.5536 628.4286 903.5187 1308.6241 1820.1550 2603.5603 3645.8882 5488.4136 8920.7998 16572.5449 | lr 4.7e-04 | norm 8405.2129 | dt 9.771 +type train | step 1449 | loss 127.7023 248.3491 367.0572 585.2806 850.6382 1230.1262 1696.1008 2448.8416 3435.3408 5293.3584 8847.8652 16723.8965 | lr 4.7e-04 | norm 9352.9971 | dt 9.778 +type train | step 1450 | loss 142.5801 278.3758 404.5441 636.2774 911.0197 1313.7307 1801.5149 2591.2546 3582.8018 5467.5664 9018.9258 16871.5371 | lr 4.7e-04 | norm 7020.8838 | dt 9.785 +type train | step 1451 | loss 136.8884 268.3688 392.7191 616.3560 887.8288 1265.6292 1746.4446 2493.1406 3507.9304 5347.0264 8798.2070 16464.6445 | lr 4.7e-04 | norm 6923.0874 | dt 9.790 +type train | step 1452 | loss 132.4174 257.3369 387.1220 625.4759 910.5525 1309.5917 1807.3164 2621.8042 3675.2092 5598.0625 9252.1152 17720.4727 | lr 4.7e-04 | norm 9202.8838 | dt 9.763 +type train | step 1453 | loss 140.0451 269.7104 392.1304 610.7317 879.3094 1244.3212 1702.8278 2435.3875 3417.9207 5180.9150 8516.9268 15815.5811 | lr 4.7e-04 | norm 6866.8555 | dt 9.800 +type train | step 1454 | loss 129.4559 255.6220 380.2154 605.0712 874.2679 1272.6371 1778.3121 2561.2686 3605.8687 5546.3359 9280.4316 17484.3418 | lr 4.7e-04 | norm 12731.2236 | dt 9.771 +type train | step 1455 | loss 154.4167 306.7821 437.5883 676.8586 961.6861 1360.8584 1852.7738 2623.4873 3624.1008 5472.5767 8915.9053 16549.2266 | lr 4.7e-04 | norm 8069.9482 | dt 9.798 +type train | step 1456 | loss 160.9005 318.8356 458.7249 710.8354 994.2109 1399.2810 1876.4498 2635.5803 3597.0857 5356.7866 8704.6553 16293.7158 | lr 4.7e-04 | norm 13012.1758 | dt 9.792 +type train | step 1457 | loss 138.0450 268.8825 396.0611 622.5320 892.0761 1276.7155 1751.8191 2511.3389 3546.8765 5361.8574 8847.2109 16545.3613 | lr 4.7e-04 | norm 7516.9365 | dt 9.774 +type train | step 1458 | loss 142.6835 283.2912 410.8480 637.6566 913.6221 1304.1360 1778.9862 2523.8870 3532.2393 5356.3159 8739.7363 16230.0898 | lr 4.7e-04 | norm 7006.4102 | dt 9.792 +type train | step 1459 | loss 137.0193 268.8017 392.6786 616.8007 886.9418 1264.8555 1736.4586 2471.3979 3479.4592 5267.4458 8646.1426 16134.2988 | lr 4.7e-04 | norm 6631.8921 | dt 9.790 +type train | step 1460 | loss 144.7553 278.2529 404.4270 628.4517 898.5122 1282.7089 1743.0696 2493.5474 3522.8042 5340.8110 8805.5449 16488.1914 | lr 4.7e-04 | norm 7295.0146 | dt 9.807 +type train | step 1461 | loss 146.7228 288.2926 414.7600 642.9044 923.4371 1319.2646 1813.9586 2605.5310 3621.3689 5523.2456 9095.1748 17127.8184 | lr 4.7e-04 | norm 7048.1265 | dt 9.819 +type train | step 1462 | loss 138.6354 272.3325 397.1216 614.3801 888.2006 1272.2129 1745.8378 2503.8877 3497.9622 5326.5703 8754.9502 16308.2480 | lr 4.7e-04 | norm 6466.7769 | dt 9.775 +type train | step 1463 | loss 136.7572 269.4689 391.0376 611.2098 878.0497 1253.0389 1718.8130 2468.3325 3445.7380 5199.9175 8517.6084 15865.7637 | lr 4.7e-04 | norm 6150.7563 | dt 9.776 +type train | step 1464 | loss 136.1906 266.4309 392.0923 616.2477 886.2817 1268.1346 1747.9709 2495.3320 3501.0930 5292.5938 8683.3887 16172.9209 | lr 4.7e-04 | norm 6982.1929 | dt 9.793 +type train | step 1465 | loss 142.3147 280.5996 404.2903 629.2593 898.5734 1284.1879 1750.8851 2501.0574 3480.3032 5278.5688 8699.8975 16231.1777 | lr 4.7e-04 | norm 6862.1738 | dt 9.784 +type train | step 1466 | loss 140.5909 273.2089 402.9390 635.6516 916.7120 1311.5936 1803.1808 2586.1655 3622.2163 5532.1733 9149.4141 17102.0176 | lr 4.7e-04 | norm 6567.7866 | dt 9.778 +type train | step 1467 | loss 141.7803 283.1705 415.6515 651.6122 929.7941 1314.0664 1801.8684 2556.1230 3576.3042 5375.5708 8830.1426 16473.7266 | lr 4.7e-04 | norm 8701.3770 | dt 9.790 +type train | step 1468 | loss 136.1434 266.0520 390.3450 612.4693 884.1044 1269.4326 1750.2457 2514.0010 3529.8057 5357.3311 8834.0225 16603.6582 | lr 4.7e-04 | norm 8525.7520 | dt 9.787 +type train | step 1469 | loss 138.5959 270.5424 395.2002 613.0606 882.9821 1265.8088 1745.0599 2491.7310 3494.8828 5345.9487 8799.3145 16600.9961 | lr 4.7e-04 | norm 6725.1890 | dt 9.782 +type train | step 1470 | loss 136.6534 267.5371 390.1210 614.0027 884.2161 1262.4984 1731.2197 2468.9827 3475.4824 5303.8008 8708.1016 16179.4141 | lr 4.7e-04 | norm 6785.9409 | dt 9.793 +type train | step 1471 | loss 132.2029 257.2083 375.1887 587.7570 849.3647 1207.0258 1659.9885 2368.9026 3337.4731 5076.0952 8331.5645 15590.2256 | lr 4.7e-04 | norm 6545.0981 | dt 9.775 +type train | step 1472 | loss 146.3837 289.4002 415.7906 639.6459 910.5135 1282.5474 1746.7040 2471.3694 3460.1653 5237.0659 8540.2061 15919.6797 | lr 4.7e-04 | norm 6366.8389 | dt 9.806 +type train | step 1473 | loss 139.0571 270.8126 398.1233 623.8688 896.5999 1278.5516 1755.1105 2507.7717 3508.2671 5313.6494 8764.8604 16502.6582 | lr 4.7e-04 | norm 6434.6060 | dt 9.793 +type train | step 1474 | loss 141.6626 276.4304 396.1296 611.9297 877.7530 1253.7668 1717.3451 2452.4104 3423.6294 5191.4922 8601.7109 16147.6191 | lr 4.7e-04 | norm 6360.0781 | dt 9.787 +type train | step 1475 | loss 143.9088 280.6306 407.1528 629.8088 900.8286 1281.9563 1755.4631 2493.0771 3473.6592 5227.5342 8534.8779 15996.8027 | lr 4.7e-04 | norm 6699.5474 | dt 9.790 +type train | step 1476 | loss 134.7836 263.0015 387.9977 612.1633 877.1672 1250.6317 1715.9335 2445.8765 3440.0911 5233.8779 8629.2920 16135.1504 | lr 4.7e-04 | norm 6080.2031 | dt 9.794 +type train | step 1477 | loss 138.0698 272.9878 395.3229 616.3357 882.6018 1268.5878 1738.5305 2485.3940 3483.6167 5285.7388 8690.6016 16144.9268 | lr 4.7e-04 | norm 5552.0171 | dt 9.785 +type train | step 1478 | loss 141.1625 277.0754 405.1664 635.7225 915.1945 1309.5811 1789.7078 2565.0896 3568.3052 5422.4180 8941.2676 16779.2422 | lr 4.7e-04 | norm 7273.3721 | dt 9.786 +type train | step 1479 | loss 141.9620 277.7217 405.4504 633.4356 903.9084 1286.3478 1761.8317 2509.8672 3504.2170 5311.0186 8692.0176 16202.5703 | lr 4.7e-04 | norm 6018.5171 | dt 9.793 +type train | step 1480 | loss 136.3735 267.2939 390.6665 614.5210 882.7285 1266.3110 1744.0609 2495.2256 3512.3611 5323.1177 8834.1855 16434.1797 | lr 4.7e-04 | norm 7353.0449 | dt 9.787 +type train | step 1481 | loss 140.6723 275.2876 400.5308 624.6093 901.6686 1296.3860 1784.8790 2567.4021 3584.1501 5422.9814 8869.3027 16566.5820 | lr 4.7e-04 | norm 6487.7710 | dt 9.790 +type train | step 1482 | loss 152.0451 303.0035 432.9375 663.4795 938.0504 1341.5145 1838.0865 2618.7441 3630.7998 5490.1567 9031.5967 16877.5703 | lr 4.7e-04 | norm 7115.1953 | dt 9.783 +type train | step 1483 | loss 140.2043 277.1472 404.9764 634.5524 914.4518 1290.6880 1770.9009 2501.9927 3519.8494 5340.2993 8762.1992 16377.4521 | lr 4.7e-04 | norm 6524.5835 | dt 9.800 +type train | step 1484 | loss 142.0150 287.9377 435.7182 684.6710 986.2061 1379.2849 1895.7468 2684.1477 3785.8247 5778.4668 9557.9600 17998.1523 | lr 4.7e-04 | norm 10060.4111 | dt 9.806 +type train | step 1485 | loss 146.1651 291.0707 420.1400 652.4828 935.2895 1323.4928 1798.9834 2537.4609 3538.4883 5316.2368 8683.3711 16212.8652 | lr 4.7e-04 | norm 6265.7266 | dt 9.809 +type train | step 1486 | loss 136.3621 274.5926 407.1525 644.6421 931.5812 1327.2145 1829.9904 2618.8984 3695.1604 5597.4316 9126.0410 16900.0430 | lr 4.7e-04 | norm 6696.7583 | dt 9.796 +type train | step 1487 | loss 139.8717 276.4438 409.1225 645.2556 925.6507 1315.9712 1806.3074 2573.1023 3610.9470 5502.2896 9005.3457 16872.6328 | lr 4.7e-04 | norm 6721.9600 | dt 9.788 +type train | step 1488 | loss 135.6708 269.3829 398.5167 630.1155 912.5126 1307.8370 1802.5757 2580.3865 3633.2231 5544.8071 9098.3223 16891.0547 | lr 4.7e-04 | norm 7371.1162 | dt 9.794 +type train | step 1489 | loss 136.2353 268.7501 400.3062 633.5229 914.0366 1305.5730 1796.7704 2564.7593 3631.1467 5527.5220 9161.1445 17095.5371 | lr 4.7e-04 | norm 6549.6265 | dt 9.780 +type train | step 1490 | loss 141.0758 279.8077 409.0896 638.0809 914.4573 1297.6168 1781.1090 2540.3477 3588.7136 5490.9404 9061.3154 17115.9570 | lr 4.7e-04 | norm 7535.3154 | dt 9.799 +type train | step 1491 | loss 145.6731 290.1287 420.9579 653.2532 931.5360 1316.7579 1796.9497 2543.2446 3566.1763 5397.9189 8892.8027 16524.7637 | lr 4.7e-04 | norm 6049.7295 | dt 9.788 +type train | step 1492 | loss 153.4117 307.5048 441.9270 679.6623 961.0695 1351.0995 1843.6459 2601.7827 3652.0618 5567.5303 9179.4922 17238.4902 | lr 4.7e-04 | norm 6832.1963 | dt 9.792 +type train | step 1493 | loss 142.7639 279.6290 403.0912 629.0128 897.8696 1303.8624 1792.3997 2564.6621 3584.4590 5451.7803 9079.0020 17308.9746 | lr 4.7e-04 | norm 10692.6436 | dt 9.783 +type train | step 1494 | loss 145.5489 281.8356 408.0551 640.8295 915.3602 1319.0931 1801.0723 2561.0352 3565.5952 5342.9365 8781.5293 16507.2930 | lr 4.7e-04 | norm 7246.0229 | dt 9.776 +type train | step 1495 | loss 140.1457 277.4601 405.9394 637.4160 907.8492 1289.5771 1753.1299 2486.5566 3510.0918 5303.1001 8676.3857 16058.7109 | lr 4.7e-04 | norm 6132.4160 | dt 9.795 +type train | step 1496 | loss 153.5711 302.9016 436.2424 679.0048 961.5937 1361.0367 1843.2980 2611.2444 3636.6587 5462.0151 8925.2393 16678.2754 | lr 4.7e-04 | norm 6789.0923 | dt 9.802 +type train | step 1497 | loss 151.3111 301.2611 438.5970 678.1129 964.7417 1355.2264 1835.5387 2579.4160 3599.5142 5462.1748 8987.8926 16886.2539 | lr 4.7e-04 | norm 7732.0347 | dt 9.796 +type train | step 1498 | loss 139.2154 275.8040 402.3352 631.7322 908.9282 1307.7428 1792.2335 2548.9702 3565.8247 5401.7471 8863.4199 16535.2988 | lr 4.7e-04 | norm 6116.4922 | dt 9.791 +type train | step 1499 | loss 146.6634 292.0000 428.6492 672.3072 963.5385 1360.5172 1856.2712 2634.2485 3690.9941 5651.9023 9335.3438 17523.3848 | lr 4.7e-04 | norm 8340.8633 | dt 9.799 +type train | step 1500 | loss 135.8819 266.0783 386.0979 610.7355 878.4928 1247.4318 1693.9423 2408.0029 3380.9382 5122.5615 8403.0947 15698.8828 | lr 4.7e-04 | norm 6652.3467 | dt 9.789 +type train | step 1501 | loss 152.4884 303.3342 437.9232 677.6137 967.4364 1386.7914 1884.2323 2670.6240 3686.4573 5505.7041 8915.6973 16397.8398 | lr 4.7e-04 | norm 5855.5601 | dt 9.803 +type train | step 1502 | loss 137.2936 268.6661 392.9642 616.0984 885.1704 1256.2397 1725.6249 2463.5605 3454.1748 5249.4600 8549.3447 16093.3066 | lr 4.7e-04 | norm 8477.3887 | dt 9.791 +type train | step 1503 | loss 145.3967 285.8427 418.8063 649.8381 934.5898 1328.8511 1824.1400 2594.4309 3660.0408 5557.6211 9110.3672 16968.4688 | lr 4.7e-04 | norm 7312.9360 | dt 9.787 +type train | step 1504 | loss 141.0649 278.9048 406.0371 635.4601 911.2896 1291.0044 1766.3651 2503.0981 3539.2742 5368.6587 8755.6641 16305.7168 | lr 4.7e-04 | norm 6773.2598 | dt 9.774 +type train | step 1505 | loss 142.1166 285.5371 413.9633 644.3823 926.6757 1341.4298 1830.6362 2639.1230 3692.6387 5537.8389 8981.0537 16624.6367 | lr 4.7e-04 | norm 7657.3086 | dt 9.771 +type train | step 1506 | loss 141.8536 282.0644 407.6675 638.1581 912.0060 1297.2632 1773.1975 2528.1902 3539.7451 5353.0029 8818.2236 16513.9727 | lr 4.7e-04 | norm 8045.2314 | dt 9.781 +type train | step 1507 | loss 145.2314 288.3857 413.6254 649.2433 930.5782 1312.2675 1782.7129 2518.5366 3517.2305 5288.6528 8663.1787 16412.2871 | lr 4.7e-04 | norm 7352.3208 | dt 9.772 +type train | step 1508 | loss 163.0826 332.2588 476.3695 735.3130 1039.9830 1451.3217 1949.3921 2714.3982 3758.9814 5605.7285 9164.6504 17156.0898 | lr 4.7e-04 | norm 12516.2686 | dt 9.796 +type train | step 1509 | loss 148.5884 295.3084 428.8923 672.3380 963.6781 1365.2640 1850.6282 2618.9910 3675.7395 5560.6411 9155.7266 17092.5176 | lr 4.7e-04 | norm 7178.9995 | dt 9.786 +type train | step 1510 | loss 134.9234 265.2685 390.2348 614.5031 891.9850 1279.2874 1756.2251 2510.5779 3538.9631 5374.9849 8836.5195 16733.0234 | lr 4.7e-04 | norm 7503.1821 | dt 9.787 +type train | step 1511 | loss 142.0530 281.1193 407.9329 639.6381 913.4941 1297.4169 1772.7247 2529.2454 3544.1685 5327.0542 8742.0859 16361.7637 | lr 4.7e-04 | norm 7512.1655 | dt 9.785 +type train | step 1512 | loss 144.0004 286.3549 422.3798 658.4742 941.7696 1337.4618 1827.0927 2585.9478 3639.8208 5482.9570 8962.0088 16724.5703 | lr 4.7e-04 | norm 6312.5908 | dt 9.807 +type train | step 1513 | loss 139.1073 275.1989 402.3239 626.5577 908.6746 1281.7883 1757.1294 2487.0154 3516.6050 5338.1357 8812.7051 16470.5059 | lr 4.7e-04 | norm 6836.8862 | dt 9.799 +type train | step 1514 | loss 146.1437 289.0767 421.5469 653.9711 941.1248 1343.4958 1833.2366 2603.2478 3639.5630 5478.0137 8945.0234 16559.2461 | lr 4.7e-04 | norm 5969.7949 | dt 9.788 +type train | step 1515 | loss 143.3859 286.6931 421.1881 660.2155 943.8917 1349.8931 1843.8411 2605.6389 3634.0068 5529.8188 9060.2637 17075.4980 | lr 4.7e-04 | norm 7672.6924 | dt 9.780 +type train | step 1516 | loss 132.5807 261.7838 384.4174 606.9124 876.8480 1256.9242 1732.7701 2475.1216 3488.9858 5300.4092 8720.2881 16191.9434 | lr 4.7e-04 | norm 6129.0552 | dt 9.797 +type train | step 1517 | loss 142.8563 284.7581 423.5804 662.4219 957.9609 1367.4355 1873.7175 2661.3738 3735.5679 5708.6738 9493.6514 17852.8574 | lr 4.7e-04 | norm 7311.4932 | dt 9.794 +type train | step 1518 | loss 138.5682 277.1975 406.1292 636.2964 915.1837 1298.8561 1778.4275 2526.8691 3557.4771 5411.5166 8922.8232 16874.8516 | lr 4.7e-04 | norm 7481.1958 | dt 9.791 +type train | step 1519 | loss 139.3369 275.4050 399.3964 625.9410 895.6422 1282.0032 1760.1965 2497.5239 3496.8057 5333.4468 8764.7119 16494.0957 | lr 4.7e-04 | norm 7602.8057 | dt 9.788 +type train | step 1520 | loss 164.9152 323.0085 460.0586 695.2922 974.0253 1386.4110 1864.5522 2609.1748 3570.0420 5336.3008 8704.3037 16255.2734 | lr 4.7e-04 | norm 10136.5547 | dt 9.773 +type train | step 1521 | loss 176.1223 344.2581 481.8119 723.9982 1000.8170 1411.0400 1879.4307 2600.0405 3464.5972 5091.8511 8161.8706 15082.3721 | lr 4.7e-04 | norm 9472.6768 | dt 9.770 +type train | step 1522 | loss 144.1697 284.2272 414.6727 646.5303 926.6423 1314.6177 1787.3469 2538.3701 3533.7646 5328.4829 8694.0547 16183.8662 | lr 4.7e-04 | norm 6557.7915 | dt 9.787 +type train | step 1523 | loss 132.4455 260.9594 386.2924 605.9680 877.6646 1254.3369 1723.7668 2451.6233 3472.0708 5272.7490 8658.1875 16198.8730 | lr 4.7e-04 | norm 7403.1450 | dt 9.801 +type train | step 1524 | loss 138.7945 271.7692 397.3120 620.5143 887.5809 1259.0653 1722.0432 2443.8560 3445.5964 5262.1689 8714.2998 16334.2451 | lr 4.7e-04 | norm 6691.6567 | dt 9.793 +type train | step 1525 | loss 138.3072 272.9430 399.2312 628.4122 903.8711 1300.3473 1786.9888 2565.1462 3606.0542 5472.0933 9000.9619 16861.1582 | lr 4.7e-04 | norm 7008.7188 | dt 9.788 +type train | step 1526 | loss 139.6389 275.5856 400.3588 623.4308 894.4050 1280.1730 1751.1952 2493.6130 3492.6118 5294.6514 8661.3857 16134.9004 | lr 4.7e-04 | norm 7099.2373 | dt 9.792 +type train | step 1527 | loss 144.5270 287.3545 415.5603 645.4521 920.9961 1308.3597 1775.8273 2511.6646 3509.7480 5322.4341 8729.2236 16209.6172 | lr 4.7e-04 | norm 6371.5625 | dt 9.800 +type train | step 1528 | loss 154.3397 301.9776 434.0885 669.7844 946.9750 1356.9989 1835.7095 2612.4822 3595.1299 5417.8984 8909.9805 16820.1445 | lr 4.7e-04 | norm 7156.1973 | dt 9.788 +type train | step 1529 | loss 145.6938 285.4713 416.0646 643.6245 919.1843 1318.4688 1802.2708 2584.4185 3599.2253 5466.2051 8898.5000 16656.9629 | lr 4.7e-04 | norm 7152.2510 | dt 9.789 +type train | step 1530 | loss 139.1681 272.9078 399.7674 628.7974 901.3807 1302.2526 1800.2844 2587.9932 3618.3115 5496.1406 9059.6055 16955.6250 | lr 4.7e-04 | norm 7352.6865 | dt 9.771 +type train | step 1531 | loss 148.1880 293.8107 421.0887 651.3351 932.3582 1320.4331 1797.5342 2527.0193 3532.9868 5294.9756 8606.6826 16005.0078 | lr 4.7e-04 | norm 8060.3481 | dt 9.798 +type train | step 1532 | loss 139.6425 277.5029 408.0630 634.7904 911.5399 1296.5605 1766.0626 2496.7307 3515.5947 5328.1294 8769.2373 16403.6836 | lr 4.7e-04 | norm 6614.9971 | dt 9.785 +type train | step 1533 | loss 143.0520 280.6107 408.6717 639.7297 928.2983 1328.2494 1825.6161 2583.6643 3614.6641 5471.9116 8969.7598 16872.0078 | lr 4.7e-04 | norm 7857.8062 | dt 9.777 +type train | step 1534 | loss 139.9233 278.1029 404.9106 632.9924 905.2355 1290.9999 1764.3419 2509.4431 3533.2256 5363.9307 8856.8477 16596.5508 | lr 4.7e-04 | norm 6154.0244 | dt 9.800 +type train | step 1535 | loss 136.7166 270.0883 397.0077 624.6573 903.3304 1297.7686 1787.2990 2547.8816 3592.6997 5439.4531 8872.5547 16455.7305 | lr 4.7e-04 | norm 6807.2280 | dt 9.790 +type train | step 1536 | loss 141.2136 280.2666 412.6508 651.1061 930.7192 1329.1116 1820.6000 2594.1033 3631.1934 5515.8755 9078.1572 16968.3398 | lr 4.7e-04 | norm 6425.7480 | dt 9.794 +type train | step 1537 | loss 150.3123 295.0619 425.3568 657.8489 940.4655 1343.9320 1817.3627 2568.0066 3566.8049 5313.2490 8554.3340 15811.3232 | lr 4.7e-04 | norm 6346.7827 | dt 9.783 +type train | step 1538 | loss 138.3958 268.2702 396.0984 621.2914 895.7418 1281.6766 1756.7456 2503.2622 3518.0195 5331.2100 8822.3115 16689.1309 | lr 4.7e-04 | norm 7763.4575 | dt 9.790 +type train | step 1539 | loss 141.7021 278.3427 405.1856 631.8887 907.4537 1298.6187 1770.2605 2516.3838 3509.8130 5289.4648 8694.5840 16243.3447 | lr 4.7e-04 | norm 6850.3657 | dt 9.808 +type train | step 1540 | loss 130.3380 265.3031 395.2850 623.6304 909.2678 1284.5634 1768.5398 2543.9360 3597.6423 5552.4751 9387.3115 17909.4395 | lr 4.7e-04 | norm 13274.5186 | dt 9.780 +type train | step 1541 | loss 133.9255 267.5409 392.6469 613.9263 884.7986 1257.3978 1721.1230 2447.0852 3433.6562 5213.7451 8564.6172 16112.0332 | lr 4.7e-04 | norm 7538.7788 | dt 9.783 +type train | step 1542 | loss 144.3892 286.4935 417.2136 650.4696 927.4265 1315.6621 1793.5989 2540.4851 3551.1604 5372.3921 8792.5088 16416.9297 | lr 4.7e-04 | norm 6421.9600 | dt 9.794 +type train | step 1543 | loss 137.9422 273.8167 401.1896 625.3011 898.0308 1281.3458 1752.0365 2488.1899 3495.6025 5315.3672 8748.8926 16485.5000 | lr 4.7e-04 | norm 6824.1787 | dt 9.789 +type train | step 1544 | loss 136.8297 271.2773 393.4792 612.5906 887.0631 1268.4418 1741.1592 2477.2932 3484.9470 5289.4209 8668.3320 16191.5635 | lr 4.7e-04 | norm 7698.8354 | dt 9.792 +type train | step 1545 | loss 140.9776 278.6439 403.0012 625.6644 895.8245 1275.5388 1747.1097 2472.5220 3465.3704 5191.3477 8473.3496 15824.3652 | lr 4.7e-04 | norm 6168.4561 | dt 9.784 +type train | step 1546 | loss 135.7141 268.8918 394.2627 616.9272 889.6026 1266.3077 1729.6536 2454.1968 3455.0542 5212.2744 8546.3271 15924.1025 | lr 4.7e-04 | norm 6153.7451 | dt 9.793 +type train | step 1547 | loss 155.0056 309.9229 446.4569 687.9028 980.2070 1396.5964 1897.1294 2700.3398 3729.2615 5626.1484 9248.4570 17330.5078 | lr 4.7e-04 | norm 7367.4541 | dt 9.797 +type train | step 1548 | loss 127.4712 247.3207 364.1379 586.7896 853.6696 1233.1096 1719.3011 2462.9004 3494.2969 5314.9380 8942.5342 17178.2500 | lr 4.7e-04 | norm 14658.1270 | dt 9.784 +type train | step 1549 | loss 136.5631 268.7310 399.1641 627.8464 906.1207 1297.5479 1778.6813 2548.3054 3576.8430 5447.2852 9051.4482 17139.6719 | lr 4.7e-04 | norm 7415.2158 | dt 9.788 +type train | step 1550 | loss 143.2568 282.7775 414.4256 648.5229 934.9020 1345.7468 1842.0959 2621.4692 3645.7004 5474.3032 8914.8906 16518.9863 | lr 4.7e-04 | norm 6616.6284 | dt 9.803 +type train | step 1551 | loss 129.2964 255.8995 387.3532 616.4625 899.5995 1279.3022 1767.8801 2535.4426 3605.6865 5554.8242 9311.0195 17751.6816 | lr 4.7e-04 | norm 8151.3677 | dt 9.797 +type train | step 1552 | loss 142.8864 278.5372 407.1849 632.6938 908.1187 1299.6975 1779.4585 2532.8030 3546.7300 5342.7021 8795.7275 16438.9844 | lr 4.7e-04 | norm 7733.9570 | dt 9.787 +type train | step 1553 | loss 130.1987 252.5134 373.9914 591.7612 858.4546 1227.9037 1688.1305 2392.7236 3384.0854 5106.1929 8358.2480 15548.1758 | lr 4.7e-04 | norm 7144.3975 | dt 9.799 +type train | step 1554 | loss 130.5484 258.6987 390.1800 616.9908 895.0059 1285.0134 1768.2567 2528.3833 3587.3862 5456.9502 8938.6533 16736.1172 | lr 4.7e-04 | norm 7304.8413 | dt 9.788 +type train | step 1555 | loss 131.5511 260.8159 384.2802 607.9902 883.2492 1266.9817 1753.5406 2507.4895 3535.3784 5371.5947 8808.5293 16387.1348 | lr 4.7e-04 | norm 6422.5356 | dt 9.803 +type train | step 1556 | loss 143.1566 282.5349 410.6569 633.3348 904.4329 1274.6597 1727.1869 2438.0908 3424.7893 5168.5518 8484.7881 15767.3916 | lr 4.7e-04 | norm 6119.7988 | dt 9.787 +type train | step 1557 | loss 141.9473 283.9813 412.8372 638.7691 913.9673 1289.1770 1764.4939 2492.9663 3505.3667 5301.0620 8694.5859 16156.9121 | lr 4.7e-04 | norm 6157.5649 | dt 9.792 +type train | step 1558 | loss 139.3447 271.0283 398.4915 624.8107 900.5793 1281.4707 1749.0974 2470.3647 3459.4814 5218.1704 8499.9365 15875.8291 | lr 4.7e-04 | norm 6830.0078 | dt 9.791 +type train | step 1559 | loss 139.8579 277.5305 404.5338 630.6432 906.1158 1291.5824 1762.7129 2505.0093 3513.4717 5294.3081 8647.5391 16097.8252 | lr 4.7e-04 | norm 5706.5522 | dt 9.800 +type train | step 1560 | loss 133.8243 263.3133 389.1807 610.6135 884.6454 1268.1281 1745.7065 2474.7205 3474.2236 5283.2520 8685.3076 16221.5078 | lr 4.7e-04 | norm 5946.9937 | dt 9.786 +type train | step 1561 | loss 137.3128 277.3939 407.9135 640.6644 924.1388 1317.5596 1800.4333 2554.5588 3604.4441 5453.0859 8902.7979 16571.9375 | lr 4.7e-04 | norm 5551.3960 | dt 9.781 +type train | step 1562 | loss 137.1757 273.3900 405.2480 634.9305 916.0644 1302.0264 1785.9037 2547.2285 3587.8755 5436.2866 8969.7754 16869.1250 | lr 4.7e-04 | norm 7125.0327 | dt 9.798 +type train | step 1563 | loss 141.5657 281.4100 411.8167 642.6768 915.8621 1301.6422 1767.2415 2499.9739 3469.0444 5235.4219 8534.0010 16002.3779 | lr 4.6e-04 | norm 6046.4590 | dt 9.799 +type train | step 1564 | loss 148.8856 295.4775 418.9578 645.6360 917.2802 1303.1624 1770.6547 2504.1245 3483.2622 5224.5898 8564.7607 16022.2656 | lr 4.6e-04 | norm 6441.1162 | dt 9.802 +type train | step 1565 | loss 138.0427 269.7369 394.2877 611.6163 886.9890 1271.0183 1739.1030 2452.5745 3441.4226 5227.2471 8510.6172 15883.9473 | lr 4.6e-04 | norm 7421.8438 | dt 9.790 +type train | step 1566 | loss 135.9887 266.1842 394.5123 616.2328 892.2245 1275.5688 1750.9316 2481.4900 3505.0806 5306.6279 8651.4102 16147.8584 | lr 4.6e-04 | norm 6986.8018 | dt 9.787 +type train | step 1567 | loss 137.6907 270.6869 399.5031 630.4102 904.9791 1281.9636 1748.3480 2469.0845 3482.2329 5286.7725 8708.4482 16382.4336 | lr 4.6e-04 | norm 6855.8198 | dt 9.792 +type train | step 1568 | loss 147.4184 293.6129 424.3585 661.6836 943.1028 1359.3936 1848.2505 2620.3306 3632.7024 5432.6948 8848.9365 16455.3047 | lr 4.6e-04 | norm 6770.3267 | dt 10.157 +type train | step 1569 | loss 149.3688 297.4066 428.7398 670.1132 953.2368 1360.4500 1849.0699 2616.4539 3591.0659 5383.2256 8834.2910 16609.0449 | lr 4.6e-04 | norm 7981.2949 | dt 9.778 +type train | step 1570 | loss 135.7828 262.3518 388.0992 624.6442 906.3661 1279.6213 1763.7898 2500.9915 3514.0173 5365.6484 9135.3857 18030.1445 | lr 4.6e-04 | norm 20577.2031 | dt 9.782 +type train | step 1571 | loss 144.7193 283.8755 420.1593 656.6496 949.3933 1349.9695 1846.5216 2634.4055 3675.5144 5569.7173 9177.3359 17331.2832 | lr 4.6e-04 | norm 8199.2188 | dt 9.782 +type train | step 1572 | loss 142.7374 282.1267 410.9897 640.3159 921.5341 1307.5603 1786.9606 2522.5366 3551.8313 5409.1089 8834.7129 16539.6016 | lr 4.6e-04 | norm 7294.4155 | dt 9.796 +type train | step 1573 | loss 152.3599 301.4769 432.7563 667.4787 958.7550 1391.7821 1918.9982 2758.3027 3780.9915 5717.7129 9323.8496 17454.4219 | lr 4.6e-04 | norm 11492.5430 | dt 9.777 +type train | step 1574 | loss 129.1852 256.0464 381.6289 602.7147 874.8516 1246.8435 1722.9098 2436.7090 3443.0867 5236.7222 8653.0449 16289.4482 | lr 4.6e-04 | norm 7611.5117 | dt 9.810 +type train | step 1575 | loss 131.5713 258.7077 385.8468 608.6746 876.5721 1252.4532 1712.2654 2437.4043 3430.0825 5202.7041 8540.1885 15885.2207 | lr 4.6e-04 | norm 7789.8320 | dt 9.798 +type train | step 1576 | loss 139.4697 273.9593 400.7473 626.2797 903.4128 1278.8497 1746.1782 2462.2839 3459.2615 5218.8384 8513.8506 15806.5020 | lr 4.6e-04 | norm 7479.2217 | dt 9.793 +type train | step 1577 | loss 138.3402 275.8630 403.4706 631.5482 907.2380 1291.8942 1769.3137 2500.1614 3489.8616 5280.3120 8634.1865 16101.8574 | lr 4.6e-04 | norm 5876.4194 | dt 9.801 +type train | step 1578 | loss 135.9836 269.8046 396.1091 619.3081 891.2928 1265.9816 1732.3815 2458.5161 3461.4673 5278.6948 8763.1191 16431.2422 | lr 4.6e-04 | norm 5853.6230 | dt 9.791 +type train | step 1579 | loss 144.9040 286.2598 418.2446 649.1078 929.8959 1328.8905 1812.0361 2570.6299 3598.4609 5436.8486 8893.1543 16576.0840 | lr 4.6e-04 | norm 5797.4131 | dt 9.781 +type train | step 1580 | loss 143.4629 279.3162 414.8821 657.1299 957.3617 1376.6852 1880.9252 2679.1770 3771.3350 5734.7515 9373.7334 17705.4043 | lr 4.6e-04 | norm 8385.3135 | dt 9.779 +type train | step 1581 | loss 140.5681 277.4779 408.6827 637.0141 911.7696 1296.3660 1768.6068 2492.4531 3511.6663 5308.1289 8694.5000 16199.3281 | lr 4.6e-04 | norm 6285.9604 | dt 9.802 +type train | step 1582 | loss 137.2579 269.5967 397.7763 625.2772 897.5142 1288.4573 1775.6729 2526.6541 3540.7649 5365.8184 8888.5186 16822.9043 | lr 4.6e-04 | norm 7111.1841 | dt 9.781 +type train | step 1583 | loss 152.7497 305.3189 437.3890 672.8965 953.5472 1352.4365 1833.6454 2577.6572 3542.9277 5274.4985 8547.2148 15992.2676 | lr 4.6e-04 | norm 6666.6196 | dt 9.787 +type train | step 1584 | loss 157.1374 314.4419 452.4086 692.5972 980.4316 1400.8516 1869.5312 2625.4761 3527.7524 5170.6270 8194.3691 15325.3418 | lr 4.6e-04 | norm 10782.0889 | dt 9.768 +type train | step 1585 | loss 131.0367 261.4281 381.9407 600.3015 864.6676 1262.6404 1741.7750 2539.3796 3553.4424 5456.2368 9182.9062 17375.6641 | lr 4.6e-04 | norm 12676.9121 | dt 9.760 +type train | step 1586 | loss 136.7466 274.1422 399.9285 625.9446 902.2679 1301.6010 1788.4880 2584.5688 3590.0325 5503.0220 9185.3760 17307.4336 | lr 4.6e-04 | norm 9742.8906 | dt 9.777 +type train | step 1587 | loss 134.2629 263.6014 389.4509 609.8358 879.2939 1246.9392 1709.8068 2415.5864 3415.7539 5183.6597 8535.1074 15985.0713 | lr 4.6e-04 | norm 6927.4126 | dt 9.798 +type train | step 1588 | loss 141.0043 279.7392 408.6008 639.0568 915.5844 1306.3408 1782.3102 2528.3652 3537.8862 5339.8872 8813.5439 16595.3691 | lr 4.6e-04 | norm 7578.5059 | dt 9.787 +type train | step 1589 | loss 141.0583 279.4252 410.4835 642.4291 921.8589 1307.0632 1785.8459 2522.5234 3535.6699 5316.3662 8700.4248 16287.8887 | lr 4.6e-04 | norm 7022.0000 | dt 9.801 +type train | step 1590 | loss 134.5867 266.4394 389.1268 606.8989 872.8559 1239.3423 1695.9735 2397.7874 3378.2297 5109.9697 8374.5195 15648.7656 | lr 4.6e-04 | norm 6588.7173 | dt 9.836 +type train | step 1591 | loss 131.5073 255.8751 382.3249 607.8747 878.1310 1282.8060 1778.1250 2554.6411 3573.4148 5406.4312 9015.6709 16979.3672 | lr 4.6e-04 | norm 9048.4873 | dt 9.810 +type train | step 1592 | loss 142.9055 277.7483 407.0604 641.1683 917.2681 1339.2241 1839.2748 2633.8125 3667.9924 5553.3687 9139.5518 17253.2168 | lr 4.6e-04 | norm 8699.1084 | dt 9.805 +type train | step 1593 | loss 131.6567 257.7213 376.7151 591.3441 856.3715 1242.1804 1705.1606 2437.1755 3444.2827 5205.7344 8606.5869 16232.0908 | lr 4.6e-04 | norm 9922.0361 | dt 9.796 +type train | step 1594 | loss 137.9645 273.7258 400.0194 626.1096 901.0927 1281.9922 1753.3453 2479.7217 3494.1272 5321.7451 8769.4053 16508.4141 | lr 4.6e-04 | norm 7892.4888 | dt 9.814 +type train | step 1595 | loss 144.0384 287.1894 414.8176 643.6187 916.0606 1304.6908 1778.9874 2499.1221 3489.6152 5285.1865 8696.4111 16295.2051 | lr 4.6e-04 | norm 7220.6260 | dt 9.791 +type train | step 1596 | loss 146.2335 292.5042 429.4625 663.6259 951.8683 1353.2195 1839.0835 2601.7368 3616.4316 5414.4634 8765.2930 16253.6523 | lr 4.6e-04 | norm 6569.5815 | dt 9.807 +type train | step 1597 | loss 139.1532 275.3436 402.4063 630.3199 901.9107 1300.0015 1772.1945 2524.5034 3507.6665 5307.5024 8750.6699 16467.3555 | lr 4.6e-04 | norm 7609.0562 | dt 9.796 +type train | step 1598 | loss 134.5947 265.3402 390.7144 613.1777 882.6424 1259.2416 1732.9441 2460.9961 3470.0571 5294.6719 8786.9209 16476.8184 | lr 4.6e-04 | norm 6650.2935 | dt 9.801 +type train | step 1599 | loss 127.8375 258.5314 389.9182 620.3871 897.4303 1281.6736 1768.4213 2528.8198 3566.7683 5481.1401 9191.5957 17508.8926 | lr 4.6e-04 | norm 9114.1455 | dt 9.803 +type train | step 1600 | loss 140.1332 278.1677 408.6947 644.0962 927.0430 1325.1936 1810.9124 2568.0266 3586.7297 5407.8208 8905.9277 16721.5312 | lr 4.6e-04 | norm 6376.7788 | dt 9.796 +type train | step 1601 | loss 136.8357 273.0417 410.1291 649.4557 932.6349 1365.2191 1866.6427 2699.3916 3756.7739 5799.3667 9685.7539 18866.6152 | lr 4.6e-04 | norm 15095.2197 | dt 9.770 +type train | step 1602 | loss 133.8409 263.9120 389.7172 610.6190 881.4698 1253.9856 1711.0709 2423.7947 3422.1416 5202.6719 8599.6045 16175.2119 | lr 4.6e-04 | norm 6317.3540 | dt 9.818 +type train | step 1603 | loss 136.5454 268.5791 397.4575 627.1514 898.9403 1295.7719 1782.6173 2533.9805 3525.6313 5272.3564 8623.6631 16068.8037 | lr 4.6e-04 | norm 8641.2383 | dt 9.805 +type train | step 1604 | loss 139.4678 276.0583 409.5468 644.7031 923.4697 1321.7855 1813.2683 2565.2271 3624.1641 5439.5322 8862.9980 16477.6445 | lr 4.6e-04 | norm 6865.8848 | dt 9.791 +type train | step 1605 | loss 149.6779 295.8765 433.6253 670.8813 957.8967 1341.1782 1817.7405 2543.3108 3565.7332 5398.6138 8883.3506 16638.3320 | lr 4.6e-04 | norm 7785.2920 | dt 9.795 +type train | step 1606 | loss 134.3977 262.8377 386.9957 607.4233 873.6227 1242.5048 1703.5295 2416.4695 3419.3411 5200.2427 8580.8770 16117.9590 | lr 4.6e-04 | norm 6609.2241 | dt 9.797 +type train | step 1607 | loss 134.1863 265.4113 389.6208 609.5641 878.4833 1259.0009 1722.1929 2438.0706 3435.7500 5205.9966 8554.0518 15968.3496 | lr 4.6e-04 | norm 5766.6064 | dt 9.806 +type train | step 1608 | loss 159.8288 316.7211 449.2855 689.5870 982.3508 1405.3549 1887.1320 2657.2014 3602.5781 5330.2485 8545.3447 15963.3691 | lr 4.6e-04 | norm 8484.3369 | dt 9.785 +type train | step 1609 | loss 145.7543 287.2240 420.6389 656.7409 942.3938 1340.0212 1817.4817 2547.3013 3556.0171 5340.8940 8679.6816 16099.4854 | lr 4.6e-04 | norm 6653.4404 | dt 9.813 +type train | step 1610 | loss 142.8634 283.1976 410.6162 632.5844 909.5074 1280.0250 1749.0918 2472.4944 3437.3870 5209.3550 8667.4531 16529.4531 | lr 4.6e-04 | norm 7864.4951 | dt 9.819 +type train | step 1611 | loss 132.7227 262.0054 382.9185 597.5134 863.6797 1234.1113 1685.1685 2386.8142 3363.4656 5083.6895 8316.5186 15552.8066 | lr 4.6e-04 | norm 6332.4023 | dt 9.846 +type train | step 1612 | loss 132.6460 258.7729 376.1420 590.4413 851.4681 1223.7236 1685.5515 2391.9102 3344.1084 5057.6279 8348.1230 15943.8379 | lr 4.6e-04 | norm 8869.3271 | dt 9.819 +type train | step 1613 | loss 137.4699 270.7066 400.1618 627.7042 912.9062 1315.6877 1809.0411 2582.0093 3607.6951 5443.3013 8821.8984 16323.6143 | lr 4.6e-04 | norm 6544.0479 | dt 9.813 +type train | step 1614 | loss 137.8562 273.1585 402.6450 631.1346 905.9185 1300.4717 1787.1565 2542.4211 3570.6782 5402.7695 8872.3965 16551.2285 | lr 4.6e-04 | norm 6184.4561 | dt 9.799 +type train | step 1615 | loss 148.8175 289.8043 423.1889 652.1195 931.0043 1333.6499 1825.1885 2579.5225 3590.1785 5392.2979 8847.7979 16668.8125 | lr 4.6e-04 | norm 6988.1382 | dt 9.804 +type train | step 1616 | loss 151.1527 302.0571 431.5522 659.4391 928.6378 1302.9724 1763.4264 2474.0808 3416.9346 5104.8525 8326.7080 15577.4980 | lr 4.6e-04 | norm 7172.8931 | dt 9.790 +type train | step 1617 | loss 135.7216 268.7694 393.9847 611.3008 885.3771 1249.7839 1708.5361 2412.4092 3402.1777 5146.1787 8402.1377 15577.4609 | lr 4.6e-04 | norm 6643.6753 | dt 9.805 +type train | step 1618 | loss 141.1341 282.0467 412.0382 645.6419 923.0743 1315.0673 1787.0127 2538.1667 3540.2256 5314.4160 8668.7793 16250.1143 | lr 4.6e-04 | norm 6420.4585 | dt 9.777 +type train | step 1619 | loss 137.5479 272.6732 396.1458 617.7266 886.0395 1265.5836 1737.2201 2463.1177 3461.9917 5221.5674 8543.7617 15929.2129 | lr 4.6e-04 | norm 5979.5078 | dt 9.808 +type train | step 1620 | loss 130.8339 255.3665 383.4329 608.4544 875.9623 1261.1635 1722.6294 2440.6570 3429.7058 5178.5229 8483.6465 15994.4160 | lr 4.6e-04 | norm 8059.2856 | dt 9.786 +type train | step 1621 | loss 135.6442 269.0258 395.8421 619.6249 889.2339 1261.5986 1711.7083 2416.1895 3378.6494 5115.6519 8379.2246 15727.0957 | lr 4.6e-04 | norm 6007.7021 | dt 9.794 +type train | step 1622 | loss 128.3265 254.2428 380.1158 601.1852 874.3301 1254.2572 1721.5236 2448.1064 3433.9458 5205.6089 8584.2168 16023.4443 | lr 4.6e-04 | norm 6204.4043 | dt 9.778 +type train | step 1623 | loss 132.7891 262.5415 386.7979 606.1883 878.4738 1245.5973 1708.3540 2421.8345 3416.1987 5194.3516 8505.6357 15787.4434 | lr 4.6e-04 | norm 6044.9746 | dt 9.806 +type train | step 1624 | loss 134.3808 267.6652 395.8662 625.2542 899.5120 1286.4059 1764.1421 2508.1931 3517.4905 5317.6230 8704.6807 16249.4766 | lr 4.6e-04 | norm 6595.6528 | dt 9.786 +type train | step 1625 | loss 141.2402 278.5353 408.1088 638.7800 913.8646 1300.4673 1771.8948 2502.6296 3508.0706 5273.3057 8648.5723 16216.9229 | lr 4.6e-04 | norm 5255.8066 | dt 9.837 +type train | step 1626 | loss 142.2752 281.0277 408.8622 633.7424 909.8349 1296.5255 1770.6775 2497.4272 3483.3584 5242.3320 8540.1641 15825.2285 | lr 4.6e-04 | norm 5252.4526 | dt 9.815 +type train | step 1627 | loss 126.1872 250.1607 377.4940 601.2958 875.7551 1276.1033 1787.2395 2567.7800 3618.4226 5470.1548 8946.6836 16706.0664 | lr 4.6e-04 | norm 7169.1802 | dt 9.805 +type train | step 1628 | loss 131.2073 258.9759 386.3026 606.2844 874.7135 1250.8694 1716.0406 2436.0837 3446.6462 5235.1758 8662.2002 16220.0859 | lr 4.6e-04 | norm 5984.4805 | dt 9.787 +type train | step 1629 | loss 136.3769 269.5159 395.9028 619.2910 892.7448 1292.7996 1778.6576 2550.3003 3569.4885 5393.8589 8863.4795 16544.3652 | lr 4.6e-04 | norm 6069.3247 | dt 9.798 +type train | step 1630 | loss 138.1100 271.0081 401.9820 629.4175 908.6998 1303.3434 1787.7294 2544.6587 3578.4026 5374.3428 8740.3164 16149.6152 | lr 4.6e-04 | norm 6047.6450 | dt 9.795 +type train | step 1631 | loss 136.4735 270.8641 399.5148 625.7245 901.7102 1281.9246 1747.1152 2464.9531 3439.5454 5225.6069 8593.3428 16010.9551 | lr 4.6e-04 | norm 6160.0859 | dt 9.792 +type train | step 1632 | loss 132.1393 260.8650 385.7727 604.2853 871.3165 1237.7981 1703.0806 2421.0771 3418.5708 5199.7026 8600.7900 16145.9570 | lr 4.6e-04 | norm 6248.9028 | dt 9.797 +type train | step 1633 | loss 141.7760 276.3179 402.9773 625.8769 897.9925 1284.7681 1748.4008 2473.5125 3453.3823 5196.3511 8470.9766 15831.6670 | lr 4.6e-04 | norm 5887.2046 | dt 9.790 +type train | step 1634 | loss 132.7185 263.1811 387.8218 606.1869 875.4753 1245.4269 1708.4185 2425.9380 3430.1133 5207.7637 8606.1387 16155.7549 | lr 4.6e-04 | norm 6489.8804 | dt 9.796 +type train | step 1635 | loss 144.3768 285.3990 412.6820 638.6962 909.0321 1297.6655 1764.6088 2503.0420 3495.4158 5237.6260 8622.6260 16161.3516 | lr 4.6e-04 | norm 8155.5317 | dt 9.784 +type train | step 1636 | loss 136.5282 270.4756 398.9273 622.7267 892.2762 1271.3790 1734.3442 2449.2549 3429.5654 5181.6514 8526.5830 15906.6504 | lr 4.6e-04 | norm 5709.9658 | dt 9.797 +type train | step 1637 | loss 122.0485 239.6286 361.8104 573.4633 839.9847 1201.8358 1657.2261 2359.8435 3373.3970 5119.5112 8384.9082 15592.6230 | lr 4.6e-04 | norm 5819.6211 | dt 9.801 +type train | step 1638 | loss 135.2574 269.0477 397.2479 619.3709 891.7920 1264.3530 1733.8511 2458.0662 3469.4065 5251.4521 8641.2197 16104.0938 | lr 4.6e-04 | norm 5724.2036 | dt 9.787 +type train | step 1639 | loss 132.7916 262.1255 388.3178 605.2556 872.7606 1239.7075 1695.9636 2393.5750 3380.2285 5147.8711 8476.7832 15830.9385 | lr 4.6e-04 | norm 6198.6709 | dt 9.809 +type train | step 1640 | loss 137.8536 269.6252 393.2243 610.3267 876.8973 1241.8490 1695.8856 2384.2041 3358.9299 5049.7056 8251.5508 15384.1367 | lr 4.6e-04 | norm 6088.9629 | dt 9.795 +type train | step 1641 | loss 133.7195 263.7400 390.6642 609.8319 882.7712 1269.5698 1743.5852 2487.0933 3506.6267 5297.6328 8672.3691 16111.4590 | lr 4.6e-04 | norm 5344.8516 | dt 9.783 +type train | step 1642 | loss 132.2688 262.3171 387.0562 604.3245 871.5844 1255.1533 1714.0642 2440.4944 3438.5288 5207.8921 8582.6201 16166.8096 | lr 4.6e-04 | norm 6539.5796 | dt 9.795 +type train | step 1643 | loss 133.3427 264.7302 394.0545 627.4030 905.6917 1298.9418 1785.6675 2553.7085 3587.3191 5432.4443 8977.1807 16855.0176 | lr 4.6e-04 | norm 6247.2715 | dt 9.783 +type train | step 1644 | loss 134.5903 267.4368 392.6868 616.2444 887.4130 1267.9896 1741.5632 2471.1648 3479.4136 5277.7686 8657.5117 16317.2734 | lr 4.6e-04 | norm 6474.3179 | dt 9.783 +type train | step 1645 | loss 135.4208 269.8367 400.8649 625.0389 900.0310 1274.2506 1741.6361 2455.8499 3446.9102 5217.5303 8561.6914 15843.1465 | lr 4.6e-04 | norm 6373.2056 | dt 9.803 +type train | step 1646 | loss 137.6562 269.8923 400.5591 627.4519 903.9592 1296.2258 1783.6737 2545.2456 3590.4675 5468.6680 8969.0742 16805.8066 | lr 4.6e-04 | norm 8948.8135 | dt 9.780 +type train | step 1647 | loss 132.8046 265.7130 394.5625 623.1007 902.4037 1295.5586 1781.2944 2537.7058 3583.0332 5402.0684 8877.0566 16656.3047 | lr 4.6e-04 | norm 8331.1670 | dt 9.788 +type train | step 1648 | loss 137.8727 273.1537 402.6872 630.2360 915.3751 1305.2991 1786.1125 2522.7244 3552.0720 5347.0957 8759.6396 16282.9883 | lr 4.6e-04 | norm 5666.3423 | dt 9.802 +type train | step 1649 | loss 135.9354 271.6087 402.8760 628.1403 909.3162 1295.9563 1783.5088 2526.9192 3551.4001 5406.6084 8851.0967 16543.4746 | lr 4.6e-04 | norm 7128.9521 | dt 9.792 +type train | step 1650 | loss 139.6440 275.2555 406.6638 632.4323 910.8320 1300.9210 1778.8585 2522.6714 3490.4060 5266.5947 8666.4365 16337.0000 | lr 4.6e-04 | norm 8880.9150 | dt 9.795 +type train | step 1651 | loss 132.6438 259.3691 380.9677 598.5661 865.2722 1242.8583 1708.6421 2441.0527 3420.7795 5172.9893 8445.7402 15832.2695 | lr 4.6e-04 | norm 6628.5781 | dt 9.790 +type train | step 1652 | loss 138.7728 277.0126 404.4824 632.8909 912.3878 1291.6346 1760.1926 2495.5449 3494.9314 5308.2490 8733.1699 16229.5664 | lr 4.6e-04 | norm 6889.8252 | dt 9.789 +type train | step 1653 | loss 116.6390 241.3322 370.3534 597.9599 890.5983 1289.5713 1810.2411 2612.8506 3749.2319 5762.4692 9385.1416 17536.2734 | lr 4.6e-04 | norm 14741.0195 | dt 9.771 +type train | step 1654 | loss 112.8679 237.4689 367.4730 600.4625 907.5292 1330.0615 1880.1934 2728.2922 3923.9033 6041.8589 9842.0488 18191.9062 | lr 4.6e-04 | norm 17717.8262 | dt 9.757 +type train | step 1655 | loss 133.2025 264.3719 391.4008 617.5795 886.3038 1271.9762 1754.0579 2502.1194 3519.1953 5310.4307 8688.2168 16202.0977 | lr 4.6e-04 | norm 6256.0225 | dt 9.791 +type train | step 1656 | loss 131.1739 264.5488 394.0211 620.1449 904.7844 1292.1461 1768.7090 2525.7412 3548.4951 5394.5747 8836.3818 16436.2344 | lr 4.6e-04 | norm 7767.2534 | dt 9.798 +type train | step 1657 | loss 135.1026 268.6451 397.7467 622.6594 895.9626 1282.1812 1756.6477 2488.4939 3491.7041 5292.8926 8732.5117 16472.6387 | lr 4.6e-04 | norm 7478.4888 | dt 9.798 +type train | step 1658 | loss 137.9632 278.5669 414.7263 643.5254 922.8250 1314.6304 1786.1766 2522.2256 3523.8826 5308.7983 8638.6436 16144.2383 | lr 4.6e-04 | norm 7517.0054 | dt 9.789 +type train | step 1659 | loss 127.9787 250.7195 379.6368 603.8392 873.7335 1247.8026 1720.9056 2456.0544 3474.2007 5298.1870 8733.3867 16336.8975 | lr 4.6e-04 | norm 7957.8496 | dt 9.772 +type train | step 1660 | loss 138.8389 277.0503 408.7061 637.2325 910.8502 1293.6846 1766.6835 2496.0801 3514.9448 5299.7715 8648.8613 16056.0625 | lr 4.6e-04 | norm 6474.8062 | dt 9.792 +type train | step 1661 | loss 131.9022 268.9662 412.0626 654.2677 954.3471 1369.6300 1877.0050 2686.7271 3799.0366 5843.2847 9612.1641 18121.1250 | lr 4.6e-04 | norm 7561.0815 | dt 9.785 +type train | step 1662 | loss 129.6224 259.4314 381.4279 595.8273 857.4768 1225.2198 1684.5259 2392.6660 3380.5645 5155.2275 8539.9727 16033.9688 | lr 4.6e-04 | norm 6886.4219 | dt 9.788 +type train | step 1663 | loss 129.3353 255.1628 378.6896 599.6024 867.6553 1244.4897 1710.6741 2416.6873 3401.4810 5144.3740 8442.9072 15888.9775 | lr 4.6e-04 | norm 6403.2095 | dt 9.784 +type train | step 1664 | loss 139.3460 281.1760 415.7762 653.5202 946.2567 1329.5164 1820.5953 2587.1860 3613.7651 5499.5376 9087.3564 17116.8301 | lr 4.6e-04 | norm 7733.4839 | dt 9.790 +type train | step 1665 | loss 137.4013 271.3500 397.8906 628.0767 907.4155 1285.3733 1761.8020 2492.2114 3503.5610 5298.1206 8685.7969 16305.4834 | lr 4.6e-04 | norm 9091.3789 | dt 9.781 +type train | step 1666 | loss 137.5299 274.3429 403.9483 627.3213 894.2009 1266.8236 1727.1798 2444.3875 3417.8191 5143.3135 8401.7236 15621.5508 | lr 4.6e-04 | norm 6388.0317 | dt 9.794 +type train | step 1667 | loss 139.6145 274.1907 402.8557 628.7025 904.3849 1292.8840 1767.1877 2526.8076 3522.6873 5293.4736 8702.6777 16257.0000 | lr 4.6e-04 | norm 7388.7637 | dt 9.796 +type train | step 1668 | loss 138.2611 276.5147 402.6645 622.0253 888.0555 1259.7144 1720.9346 2431.1409 3419.0142 5126.9873 8452.5479 15833.8203 | lr 4.6e-04 | norm 7090.4517 | dt 9.796 +type train | step 1669 | loss 133.9514 265.1960 392.4387 613.1786 884.0880 1264.9175 1734.8389 2454.2949 3447.6606 5215.2241 8503.7568 15857.3252 | lr 4.6e-04 | norm 6545.8916 | dt 9.783 +type train | step 1670 | loss 131.8376 261.1576 384.7522 604.1127 877.0674 1259.7731 1735.0569 2474.9167 3512.9661 5335.8403 8815.9521 16416.3359 | lr 4.6e-04 | norm 6447.2080 | dt 9.818 +type train | step 1671 | loss 129.2321 254.6898 378.1634 596.2746 862.7143 1232.1177 1691.8394 2401.3008 3405.1292 5148.8013 8450.2539 15683.7158 | lr 4.6e-04 | norm 6065.6128 | dt 9.793 +type train | step 1672 | loss 129.3313 257.2119 387.3601 619.9308 897.5233 1308.3046 1786.6453 2576.9343 3599.6465 5472.3271 9043.9023 17016.9805 | lr 4.6e-04 | norm 8688.1582 | dt 9.789 +type train | step 1673 | loss 131.1502 258.8274 382.8994 604.5099 868.3879 1250.5211 1717.6941 2431.5234 3414.9863 5164.2979 8487.4180 15829.9492 | lr 4.6e-04 | norm 5456.9980 | dt 9.794 +type train | step 1674 | loss 149.3984 294.7524 435.3922 679.3520 968.4087 1375.9469 1881.1403 2665.2048 3735.5383 5656.6802 9348.4688 17653.3574 | lr 4.6e-04 | norm 8829.7988 | dt 9.797 +type train | step 1675 | loss 132.6539 263.7908 390.0076 611.3879 884.9222 1264.5618 1735.1353 2472.4734 3492.9446 5284.3599 8643.8154 16076.5537 | lr 4.6e-04 | norm 5456.0854 | dt 9.805 +type train | step 1676 | loss 136.8671 268.4365 395.1562 619.4824 895.2155 1285.8481 1757.5261 2501.0415 3524.8613 5316.8696 8771.2520 16381.2031 | lr 4.5e-04 | norm 5773.6846 | dt 9.801 +type train | step 1677 | loss 130.2491 257.5253 376.8517 589.0800 851.0814 1218.1575 1678.5995 2376.4937 3348.7549 5053.2969 8287.2373 15470.6523 | lr 4.5e-04 | norm 5769.6655 | dt 9.790 +type train | step 1678 | loss 137.8614 271.1132 397.9791 626.5860 897.7939 1285.1283 1754.1887 2491.8328 3494.9016 5242.7119 8544.0439 15859.2598 | lr 4.5e-04 | norm 5196.5078 | dt 9.788 +type train | step 1679 | loss 127.1000 250.6459 371.4427 585.9361 855.7761 1227.1089 1693.4069 2403.3438 3396.9377 5136.9707 8415.9580 15710.4834 | lr 4.5e-04 | norm 5312.8989 | dt 9.797 +type train | step 1680 | loss 137.6223 273.0310 405.4575 631.4745 909.6881 1273.8848 1743.4208 2448.5593 3455.7158 5197.3159 8548.5322 15871.1191 | lr 4.5e-04 | norm 7720.6890 | dt 9.806 +type train | step 1681 | loss 126.1882 252.0792 375.5648 592.4741 859.9030 1234.5896 1701.7682 2433.9277 3453.5276 5240.7925 8550.2725 15845.7334 | lr 4.5e-04 | norm 6081.5435 | dt 9.793 +type train | step 1682 | loss 133.0062 265.9154 387.7619 606.3934 881.8348 1275.3896 1767.4294 2518.8662 3548.3140 5360.3198 8791.9668 16471.1387 | lr 4.5e-04 | norm 6307.0977 | dt 9.790 +type train | step 1683 | loss 134.6165 265.6718 390.7120 609.9211 880.0441 1261.1748 1740.7179 2487.3623 3507.4387 5340.2695 8771.5625 16304.1777 | lr 4.5e-04 | norm 5755.9683 | dt 9.784 +type train | step 1684 | loss 119.4393 234.6319 353.0119 563.3112 829.8846 1208.6929 1680.7384 2412.0298 3428.8752 5196.0474 8496.5684 15842.7705 | lr 4.5e-04 | norm 6161.4912 | dt 9.797 +type train | step 1685 | loss 138.1581 269.9813 390.3273 607.7197 871.8046 1238.7136 1688.1450 2395.6350 3369.0337 5062.2061 8273.2295 15506.3613 | lr 4.5e-04 | norm 9084.4014 | dt 9.802 +type train | step 1686 | loss 142.7274 283.7546 416.1312 651.1792 926.9784 1316.6877 1782.4333 2498.0857 3460.1455 5153.4839 8288.2979 15382.6133 | lr 4.5e-04 | norm 6209.1724 | dt 9.798 +type train | step 1687 | loss 149.1122 299.6654 430.2010 665.9987 943.8892 1341.9230 1816.9347 2552.3687 3523.2004 5312.0308 8654.4141 16117.4463 | lr 4.5e-04 | norm 6448.7725 | dt 9.797 +type train | step 1688 | loss 128.3538 250.1228 372.8434 588.8484 855.7854 1244.7802 1710.9031 2463.4500 3481.8472 5270.6543 8664.6641 16134.5576 | lr 4.5e-04 | norm 6395.0029 | dt 9.796 +type train | step 1689 | loss 151.3123 300.1224 433.5214 668.4924 949.7893 1354.6833 1854.4344 2610.3840 3617.2688 5435.1860 8882.8379 16447.8301 | lr 4.5e-04 | norm 5888.8584 | dt 9.797 +type train | step 1690 | loss 128.8670 254.6735 378.9160 597.0469 865.2613 1262.8784 1744.1259 2506.7319 3529.1682 5338.1113 8716.9736 16275.5088 | lr 4.5e-04 | norm 6786.7261 | dt 9.834 +type train | step 1691 | loss 135.1304 267.8442 394.8170 621.2506 894.0051 1284.7629 1755.5276 2512.3955 3551.1519 5373.2734 8807.6807 16526.1484 | lr 4.5e-04 | norm 6772.8291 | dt 9.816 +type train | step 1692 | loss 131.3116 258.6881 380.5546 598.2820 866.9910 1259.1050 1744.2615 2508.2085 3531.4553 5338.8286 8714.9443 16223.1748 | lr 4.5e-04 | norm 6739.7310 | dt 9.799 +type train | step 1693 | loss 179.3506 354.1198 491.6228 737.8454 1018.1716 1455.0966 1966.5963 2712.7917 3683.6213 5405.5659 8578.4307 15871.6523 | lr 4.5e-04 | norm 10992.9746 | dt 9.768 +type train | step 1694 | loss 128.5757 257.1138 382.2048 604.0422 870.0594 1248.5883 1717.4949 2443.3965 3469.9941 5260.1353 8714.3896 16388.0957 | lr 4.5e-04 | norm 6595.2642 | dt 9.803 +type train | step 1695 | loss 131.9998 261.1876 384.2648 598.0537 866.6490 1235.6508 1695.5459 2401.7534 3393.0911 5125.3164 8368.1660 15574.8535 | lr 4.5e-04 | norm 6414.2681 | dt 9.809 +type train | step 1696 | loss 129.2523 253.5481 376.7983 590.3354 852.2903 1214.5726 1660.9827 2356.0049 3339.4260 5061.3564 8308.4170 15462.4512 | lr 4.5e-04 | norm 5455.6660 | dt 9.793 +type train | step 1697 | loss 121.5321 239.0042 357.1636 565.1808 827.2603 1189.7970 1645.9784 2344.7954 3331.3577 5080.3081 8357.7441 15535.1465 | lr 4.5e-04 | norm 5585.9370 | dt 9.798 +type train | step 1698 | loss 132.7277 265.8752 392.5457 616.7972 892.0734 1271.4694 1728.6960 2471.0403 3519.1118 5361.1777 8828.7529 16502.0664 | lr 4.5e-04 | norm 6524.5010 | dt 9.793 +type train | step 1699 | loss 138.2406 274.5923 401.9764 622.6354 896.4940 1274.8866 1745.6188 2466.9348 3469.6416 5233.2495 8581.4658 16005.6816 | lr 4.5e-04 | norm 6426.2720 | dt 9.814 +type train | step 1700 | loss 138.3687 278.7084 411.0057 638.9065 912.0374 1293.3884 1753.0460 2461.6074 3420.7393 5150.5312 8395.3320 15748.9883 | lr 4.5e-04 | norm 5692.1733 | dt 9.837 +type train | step 1701 | loss 134.6015 268.9638 401.5155 630.5601 906.7783 1287.8761 1761.7107 2489.6846 3491.9915 5256.9922 8593.1514 16054.0146 | lr 4.5e-04 | norm 6728.5488 | dt 9.816 +type train | step 1702 | loss 146.2093 288.2827 424.4410 658.3976 938.5258 1333.6882 1816.1019 2558.7083 3556.4287 5301.2939 8728.0098 16360.4170 | lr 4.5e-04 | norm 7481.2559 | dt 9.786 +type train | step 1703 | loss 127.9903 251.1922 371.5448 587.0375 853.9757 1230.6057 1697.4272 2421.5872 3421.2764 5171.2461 8433.9492 15634.3926 | lr 4.5e-04 | norm 6015.3755 | dt 9.807 +type train | step 1704 | loss 144.1350 283.2889 413.8994 650.6442 926.1976 1322.2384 1798.3322 2530.9888 3504.2764 5243.5635 8590.8906 16119.3564 | lr 4.5e-04 | norm 6790.6523 | dt 9.787 +type train | step 1705 | loss 125.4120 248.1833 369.6534 578.8990 843.5820 1207.1807 1655.6613 2368.5586 3360.6499 5100.7266 8402.3896 15708.2725 | lr 4.5e-04 | norm 6509.8140 | dt 9.794 +type train | step 1706 | loss 143.8468 284.9578 414.4062 649.1369 917.6161 1315.7393 1776.1052 2494.8210 3460.7534 5173.4780 8428.0469 15765.1309 | lr 4.5e-04 | norm 6170.3823 | dt 9.787 +type train | step 1707 | loss 121.9920 243.3580 365.4429 582.8585 849.1479 1221.1393 1681.2856 2406.7058 3410.5176 5179.3936 8540.9355 15971.9062 | lr 4.5e-04 | norm 5849.9380 | dt 9.789 +type train | step 1708 | loss 130.5444 256.9797 382.1665 601.1558 868.4921 1238.7991 1693.6210 2401.7063 3391.9075 5133.2236 8415.7344 15699.7236 | lr 4.5e-04 | norm 5943.8027 | dt 9.796 +type train | step 1709 | loss 125.5168 249.6024 372.0725 591.5169 863.5869 1252.3042 1735.9087 2482.7417 3491.2312 5305.3179 8714.3223 16257.9844 | lr 4.5e-04 | norm 7836.1377 | dt 9.781 +type train | step 1710 | loss 140.1998 286.4211 412.5123 639.9424 928.4332 1324.4880 1821.7133 2597.9448 3648.1482 5585.8066 9180.8818 17178.7500 | lr 4.5e-04 | norm 9799.4092 | dt 9.768 +type train | step 1711 | loss 156.3257 315.4496 471.6496 724.4280 1028.1759 1430.3724 1939.5962 2731.3389 3824.6475 5796.0127 9572.8105 18054.5859 | lr 4.5e-04 | norm 11662.8994 | dt 9.782 +type train | step 1712 | loss 139.8989 278.6772 404.9384 623.4432 895.5386 1268.9285 1731.9595 2429.4043 3372.2673 5068.2817 8255.7383 15419.2568 | lr 4.5e-04 | norm 8996.0801 | dt 9.780 +type train | step 1713 | loss 127.6076 255.4086 380.3668 600.7340 873.5526 1242.3737 1716.5244 2441.8411 3487.1504 5284.4150 8652.6660 16077.8369 | lr 4.5e-04 | norm 7321.0859 | dt 9.786 +type train | step 1714 | loss 135.5374 270.7021 393.1161 609.6304 877.5325 1254.0615 1717.1879 2429.2412 3407.3789 5122.1733 8314.5254 15359.3398 | lr 4.5e-04 | norm 6634.3628 | dt 9.782 +type train | step 1715 | loss 126.4570 249.7231 375.4900 593.1277 860.8649 1245.1537 1720.1494 2470.3770 3460.3186 5237.8188 8596.4932 16067.7266 | lr 4.5e-04 | norm 7360.9712 | dt 9.787 +type train | step 1716 | loss 130.9915 259.0087 381.8991 599.5966 864.6566 1241.9508 1699.5681 2419.6526 3413.5732 5127.8418 8381.4238 15595.7891 | lr 4.5e-04 | norm 5908.6694 | dt 9.781 +type train | step 1717 | loss 127.3608 251.6166 379.6784 609.2167 877.0422 1279.5779 1762.2074 2526.5112 3593.2744 5491.6040 9074.8027 17036.0430 | lr 4.5e-04 | norm 6832.4214 | dt 9.787 +type train | step 1718 | loss 126.0293 249.6805 372.5855 587.8890 852.5738 1217.6829 1671.8043 2381.9104 3362.5337 5115.6113 8392.6465 15654.6768 | lr 4.5e-04 | norm 6011.8857 | dt 9.780 +type train | step 1719 | loss 138.3224 276.7617 405.7678 631.6957 903.5547 1293.1920 1758.4257 2487.4385 3454.0081 5209.7988 8511.9062 15860.6523 | lr 4.5e-04 | norm 6510.9775 | dt 9.784 +type train | step 1720 | loss 122.0682 242.1237 359.8446 569.0947 832.0720 1194.8691 1652.3622 2353.1272 3340.0981 5079.9805 8285.8418 15356.3086 | lr 4.5e-04 | norm 5793.6934 | dt 9.788 +type train | step 1721 | loss 124.3163 244.2092 365.0167 576.3027 836.4463 1208.6931 1672.2427 2385.5950 3393.5679 5139.2715 8399.2432 15608.0732 | lr 4.5e-04 | norm 7068.7451 | dt 9.787 +type train | step 1722 | loss 138.9467 275.1131 402.1232 625.8949 897.6000 1284.7314 1750.3414 2464.1851 3431.6179 5109.3423 8346.9854 15611.9414 | lr 4.5e-04 | norm 6765.7119 | dt 9.771 +type train | step 1723 | loss 134.2080 269.6755 393.7587 615.0459 886.8608 1267.1709 1738.1737 2461.1267 3470.1904 5224.6289 8516.9980 15829.7627 | lr 4.5e-04 | norm 5762.1992 | dt 9.788 +type train | step 1724 | loss 132.0613 260.9935 387.6205 604.3094 875.1979 1250.6594 1716.3169 2438.6562 3442.4414 5218.7012 8575.7354 15935.0898 | lr 4.5e-04 | norm 5319.8130 | dt 9.792 +type train | step 1725 | loss 134.3444 266.4494 391.1092 609.8011 882.1981 1262.2903 1736.5009 2461.5168 3452.3552 5208.5034 8494.0498 15831.3867 | lr 4.5e-04 | norm 6540.7876 | dt 9.793 +type train | step 1726 | loss 131.8160 260.1811 387.9284 609.8332 882.9597 1260.5490 1722.4977 2442.3696 3452.0054 5218.4824 8542.6895 15881.3477 | lr 4.5e-04 | norm 5698.6621 | dt 9.789 +type train | step 1727 | loss 127.1360 254.6633 374.3547 585.9171 854.2753 1236.9905 1703.9547 2441.3303 3438.7708 5165.5996 8428.3555 15663.3428 | lr 4.5e-04 | norm 6255.6040 | dt 9.769 +type train | step 1728 | loss 128.6653 256.3417 379.9393 597.1643 864.4141 1240.6367 1708.5376 2417.8345 3407.7014 5137.4678 8426.7734 15642.4570 | lr 4.5e-04 | norm 6317.0044 | dt 9.776 +type train | step 1729 | loss 124.5073 247.5717 370.6984 586.3105 859.5468 1242.9213 1722.4247 2456.3425 3467.3540 5224.0566 8475.7607 15746.8203 | lr 4.5e-04 | norm 5406.8872 | dt 9.787 +type train | step 1730 | loss 128.9035 258.1119 377.5185 590.3829 854.9460 1234.4916 1705.5887 2434.3723 3440.2742 5183.4814 8452.5908 15633.4170 | lr 4.5e-04 | norm 5028.6079 | dt 9.792 +type train | step 1731 | loss 133.9824 271.0971 397.9584 620.5178 899.8351 1280.9188 1757.8496 2484.2236 3493.4993 5282.5073 8637.2930 16060.6768 | lr 4.5e-04 | norm 6227.6426 | dt 9.800 +type train | step 1732 | loss 138.9442 275.9015 406.3457 633.8136 907.6440 1305.5345 1774.3816 2517.1001 3521.1672 5281.4604 8662.6914 16285.6973 | lr 4.5e-04 | norm 6327.9824 | dt 9.792 +type train | step 1733 | loss 130.0019 258.8102 385.4868 601.0486 871.7711 1248.4292 1714.7836 2425.1067 3431.8340 5159.3115 8442.9639 15656.9316 | lr 4.5e-04 | norm 5995.0132 | dt 9.794 +type train | step 1734 | loss 140.0592 276.0277 407.0934 639.4780 912.9814 1309.8945 1780.5111 2519.8962 3494.5015 5248.8755 8543.2646 16035.8691 | lr 4.5e-04 | norm 6281.4360 | dt 9.797 +type train | step 1735 | loss 137.7879 271.0242 403.0276 629.1601 901.0097 1287.5112 1750.9419 2481.0891 3442.6963 5196.3359 8541.8213 16146.4707 | lr 4.5e-04 | norm 6592.4331 | dt 9.794 +type train | step 1736 | loss 124.6254 247.1040 372.2250 584.0641 848.5610 1221.3459 1678.9592 2386.3474 3371.9729 5098.6846 8338.2764 15448.3154 | lr 4.5e-04 | norm 5444.9102 | dt 9.793 +type train | step 1737 | loss 132.2903 262.7964 386.9451 603.7419 869.0488 1242.3254 1702.4486 2408.9866 3397.1035 5107.5957 8390.2920 15645.4092 | lr 4.5e-04 | norm 5172.9082 | dt 9.798 +type train | step 1738 | loss 140.1265 276.5119 411.9687 640.3398 913.4413 1302.5442 1765.1580 2483.6895 3438.0532 5149.9380 8309.4365 15539.2949 | lr 4.5e-04 | norm 6096.8828 | dt 9.781 +type train | step 1739 | loss 136.5295 273.7905 405.1544 635.8270 910.4266 1305.0763 1775.4725 2503.5273 3484.2432 5246.8984 8622.3770 16135.6982 | lr 4.5e-04 | norm 5793.0249 | dt 9.785 +type train | step 1740 | loss 126.8285 250.3920 375.5386 590.9604 857.1978 1230.8812 1685.4941 2396.5720 3389.4043 5104.5205 8361.0293 15572.2578 | lr 4.5e-04 | norm 6499.0962 | dt 9.783 +type train | step 1741 | loss 131.5634 262.5843 388.5171 609.4243 876.2892 1261.0862 1720.9998 2462.8276 3436.6360 5155.5391 8388.3369 15520.0781 | lr 4.5e-04 | norm 5326.4023 | dt 9.788 +type train | step 1742 | loss 118.6442 232.4877 349.5961 553.9276 815.6729 1190.8413 1646.9623 2372.0190 3366.5945 5124.8047 8450.3467 15791.4902 | lr 4.5e-04 | norm 6542.5244 | dt 9.794 +type train | step 1743 | loss 129.7818 256.6801 373.7186 586.7668 852.2734 1234.4990 1700.4800 2426.4631 3418.7998 5140.1079 8360.6943 15397.1592 | lr 4.5e-04 | norm 5372.8442 | dt 9.791 +type train | step 1744 | loss 137.9816 275.8405 406.1665 634.6689 898.8954 1290.3187 1746.5259 2455.6785 3409.2065 5104.0591 8323.6748 15522.5625 | lr 4.5e-04 | norm 5465.9937 | dt 9.785 +type train | step 1745 | loss 139.6778 276.5702 405.0491 636.4941 908.4170 1324.7981 1803.3535 2570.8850 3543.6533 5350.9448 8777.2266 16697.1465 | lr 4.5e-04 | norm 8896.7275 | dt 9.769 +type train | step 1746 | loss 136.5579 271.6948 397.2350 614.5818 887.6325 1265.2679 1733.8544 2454.1995 3452.6487 5190.7334 8470.2627 15686.1123 | lr 4.5e-04 | norm 5699.4639 | dt 9.789 +type train | step 1747 | loss 134.7212 271.0094 404.0754 636.1438 917.3414 1317.2812 1806.4073 2563.2798 3591.1360 5375.6187 8788.3242 16307.4316 | lr 4.5e-04 | norm 6040.4536 | dt 9.784 +type train | step 1748 | loss 141.2747 284.4642 417.9575 651.2109 939.3090 1354.7902 1868.4036 2697.0103 3761.3101 5627.6147 9103.0928 16689.8555 | lr 4.5e-04 | norm 6774.4917 | dt 9.780 +type train | step 1749 | loss 132.9383 265.8748 388.9562 608.9069 876.2407 1249.8992 1712.1177 2416.8750 3393.8604 5100.2261 8305.9219 15387.8906 | lr 4.5e-04 | norm 5506.7085 | dt 9.781 +type train | step 1750 | loss 129.8432 258.6136 387.2399 613.1337 892.8000 1290.4722 1780.3540 2544.4849 3594.6453 5429.5967 8852.9072 16391.3105 | lr 4.5e-04 | norm 5807.4810 | dt 9.776 +type train | step 1751 | loss 142.8152 281.8852 409.5089 628.2699 903.0945 1296.5719 1774.7217 2505.5938 3506.3489 5223.5796 8479.8555 15532.0869 | lr 4.5e-04 | norm 5836.6104 | dt 9.773 +type train | step 1752 | loss 127.4505 248.6077 374.9633 595.0311 865.9203 1256.8003 1738.9260 2484.2207 3508.2556 5287.9380 8780.7373 16495.9609 | lr 4.5e-04 | norm 9160.7344 | dt 9.763 +type train | step 1753 | loss 166.7886 329.4621 477.6619 709.1866 983.4426 1385.7000 1831.8120 2525.5913 3352.7991 4826.6777 7519.6055 13833.2451 | lr 4.5e-04 | norm 9091.5664 | dt 9.739 +type train | step 1754 | loss 133.8827 265.3153 392.7548 616.9563 890.0152 1278.6130 1748.8022 2469.8860 3460.8989 5184.8896 8410.0273 15636.0566 | lr 4.5e-04 | norm 6818.2231 | dt 9.770 +type train | step 1755 | loss 123.4712 246.0274 368.9638 583.8055 846.1790 1201.7914 1652.9469 2341.6704 3337.8704 5078.3291 8400.4971 15644.4707 | lr 4.5e-04 | norm 6050.7515 | dt 9.780 +type train | step 1756 | loss 126.5865 250.2106 373.2901 591.0804 855.8036 1222.7092 1678.0044 2366.5264 3349.0593 5032.0425 8227.5762 15249.5723 | lr 4.5e-04 | norm 6040.7979 | dt 9.774 +type train | step 1757 | loss 135.0472 267.7096 395.5575 613.6370 888.3488 1260.7607 1728.7382 2443.4995 3445.8865 5206.2549 8562.3525 15923.9707 | lr 4.5e-04 | norm 6324.0571 | dt 9.779 +type train | step 1758 | loss 130.5858 260.2118 386.4537 612.5743 884.6810 1271.1454 1743.6459 2482.3831 3517.3660 5288.6729 8637.7676 16015.8193 | lr 4.5e-04 | norm 5953.8335 | dt 9.789 +type train | step 1759 | loss 117.8506 229.5307 344.7657 547.0123 800.0668 1158.7664 1603.1653 2294.4961 3269.8872 4964.0239 8174.7012 15212.4365 | lr 4.5e-04 | norm 5874.3774 | dt 9.769 +type train | step 1760 | loss 128.2191 255.2193 376.3609 585.6025 847.7243 1221.9819 1683.1970 2399.2056 3382.7883 5145.8369 8453.0215 15651.8789 | lr 4.5e-04 | norm 5306.3594 | dt 9.776 +type train | step 1761 | loss 121.6433 241.1337 361.1708 570.3141 834.2484 1199.0891 1655.3074 2359.9863 3356.4360 5083.1587 8352.2012 15500.5977 | lr 4.5e-04 | norm 5501.8535 | dt 9.792 +type train | step 1762 | loss 124.7003 244.7029 365.1142 581.0087 849.6213 1236.7946 1709.7255 2456.6753 3473.0239 5236.8247 8545.0693 15808.0674 | lr 4.5e-04 | norm 5268.5010 | dt 9.791 +type train | step 1763 | loss 125.2931 245.5033 367.9033 581.7964 851.7438 1224.1908 1687.5161 2412.9856 3423.2607 5216.3662 8646.3691 16216.5586 | lr 4.5e-04 | norm 7560.5811 | dt 9.770 +type train | step 1764 | loss 128.5738 257.1189 381.7451 608.4881 885.5668 1336.3445 1871.5222 2743.8831 3834.1975 5709.8281 9242.5693 17352.6562 | lr 4.5e-04 | norm 8712.9229 | dt 9.753 +type train | step 1765 | loss 133.8053 268.7764 395.8287 618.1765 888.1276 1259.7065 1728.5083 2450.2119 3465.1157 5218.6719 8470.8535 15665.3701 | lr 4.5e-04 | norm 5512.7095 | dt 9.782 +type train | step 1766 | loss 126.7258 254.1441 379.9179 603.0873 880.8187 1260.5627 1741.0530 2481.0339 3521.5083 5314.2466 8624.0566 15942.7783 | lr 4.5e-04 | norm 5345.7441 | dt 9.778 +type train | step 1767 | loss 126.7656 252.4124 375.4847 589.6793 856.2477 1222.4684 1685.8405 2399.2429 3394.3628 5140.5225 8403.1494 15541.5898 | lr 4.5e-04 | norm 5655.3550 | dt 9.791 +type train | step 1768 | loss 127.3664 254.4730 382.5945 611.8656 899.1489 1313.1636 1820.7007 2617.7153 3666.1150 5515.2695 9088.1855 17032.0098 | lr 4.5e-04 | norm 7268.6680 | dt 9.775 +type train | step 1769 | loss 130.6397 261.9838 386.3214 603.2123 872.8099 1245.9900 1712.4822 2426.6885 3418.8008 5153.5537 8411.8174 15628.2490 | lr 4.5e-04 | norm 5415.4180 | dt 9.781 +type train | step 1770 | loss 128.9228 256.2328 381.6961 604.8596 882.0639 1282.4353 1765.6277 2520.1062 3528.3862 5323.4263 8799.6152 16570.1250 | lr 4.5e-04 | norm 7752.8105 | dt 9.777 +type train | step 1771 | loss 125.9271 251.0315 376.7036 587.9639 854.6067 1222.7312 1683.0536 2380.3252 3377.4624 5097.9438 8310.5420 15330.8438 | lr 4.5e-04 | norm 5372.3003 | dt 9.787 +type train | step 1772 | loss 143.1066 283.5626 409.3636 633.8739 908.2380 1300.2664 1778.4410 2504.9929 3471.1560 5180.2422 8397.7207 15649.6016 | lr 4.5e-04 | norm 6728.0103 | dt 9.776 +type train | step 1773 | loss 150.2974 296.7398 432.6103 661.1344 935.4772 1339.0273 1816.9243 2546.8884 3501.4514 5168.8066 8256.3564 15354.4355 | lr 4.5e-04 | norm 7320.2100 | dt 9.763 +type train | step 1774 | loss 133.6245 266.2477 397.8817 615.3464 887.4210 1272.6339 1738.1290 2458.2976 3432.3674 5182.9404 8459.2510 15685.9844 | lr 4.5e-04 | norm 6541.4028 | dt 9.784 +type train | step 1775 | loss 129.3299 255.8976 380.7546 598.2122 863.9188 1248.3402 1717.0854 2453.8269 3448.9531 5202.8730 8524.5146 15820.6562 | lr 4.5e-04 | norm 5653.0938 | dt 9.792 +type train | step 1776 | loss 124.2379 246.4294 365.5208 572.4771 836.8007 1215.3291 1674.2799 2386.9219 3370.7190 5094.6763 8352.1055 15467.4990 | lr 4.5e-04 | norm 6453.8130 | dt 9.779 +type train | step 1777 | loss 126.2707 250.3069 376.0991 595.3386 862.7236 1252.9227 1722.8051 2471.1699 3493.3108 5268.7227 8605.2695 15880.4297 | lr 4.5e-04 | norm 6039.4385 | dt 9.764 +type train | step 1778 | loss 130.8836 255.5256 377.0766 591.2957 857.9712 1241.1765 1704.9962 2420.1660 3409.2156 5140.9307 8423.7051 15744.9551 | lr 4.4e-04 | norm 5915.0078 | dt 9.775 +type train | step 1779 | loss 137.4571 273.4573 405.7835 636.6212 904.3568 1302.6215 1776.5503 2508.8323 3505.5457 5269.7163 8610.3760 16113.8525 | lr 4.4e-04 | norm 6172.8350 | dt 9.772 +type train | step 1780 | loss 129.4872 257.2891 383.6942 605.5845 872.3700 1242.7134 1687.8837 2374.2827 3339.0349 4994.6318 8184.5347 15212.7744 | lr 4.4e-04 | norm 6507.4932 | dt 9.780 +type train | step 1781 | loss 123.8108 244.6169 368.5139 576.1703 836.8148 1198.1270 1648.7795 2353.1406 3320.7500 5026.2236 8179.5405 15144.4902 | lr 4.4e-04 | norm 8122.8877 | dt 9.772 +type train | step 1782 | loss 130.5342 258.5875 383.2920 599.9459 865.4021 1250.1793 1713.1238 2437.3452 3444.8591 5172.7163 8450.0088 15588.0127 | lr 4.4e-04 | norm 5649.4722 | dt 9.792 +type train | step 1783 | loss 125.0501 247.0171 368.5637 575.3706 837.2845 1199.4503 1654.4023 2355.5200 3335.3945 5063.3394 8337.8623 15655.7266 | lr 4.4e-04 | norm 6300.1895 | dt 9.790 +type train | step 1784 | loss 125.8668 251.5132 374.7328 587.4332 857.0384 1238.5183 1708.6538 2430.9812 3445.0740 5208.0640 8522.3486 15852.8506 | lr 4.4e-04 | norm 5604.1899 | dt 9.794 +type train | step 1785 | loss 130.6534 258.3328 385.9081 601.9084 870.9919 1245.2036 1701.3032 2408.8442 3394.0703 5100.2319 8334.8975 15362.6992 | lr 4.4e-04 | norm 5302.8335 | dt 9.812 +type train | step 1786 | loss 124.4450 245.6150 366.7239 576.9841 842.0903 1215.7400 1679.8948 2388.9485 3400.4692 5152.4238 8458.3223 15615.5459 | lr 4.4e-04 | norm 5588.1128 | dt 9.790 +type train | step 1787 | loss 154.3529 303.4354 436.0011 661.3525 926.4326 1306.6212 1752.1619 2443.6111 3374.0625 5047.6621 8262.4570 15492.1221 | lr 4.4e-04 | norm 12121.7754 | dt 9.758 +type train | step 1788 | loss 126.4741 251.8179 375.9851 585.8352 848.7115 1217.9357 1674.2803 2397.3171 3402.8066 5168.7856 8570.8301 15976.7568 | lr 4.4e-04 | norm 7599.0322 | dt 9.784 +type train | step 1789 | loss 129.8581 261.5854 383.7394 600.7341 862.5685 1243.0928 1705.6360 2421.9358 3401.2229 5109.0674 8365.4150 15464.4180 | lr 4.4e-04 | norm 6033.9902 | dt 9.778 +type train | step 1790 | loss 126.7303 248.6196 371.1338 583.0640 846.7061 1208.5266 1663.7559 2352.9053 3360.5801 5073.5879 8298.4502 15439.4580 | lr 4.4e-04 | norm 6880.1411 | dt 9.772 +type train | step 1791 | loss 134.8419 268.5906 394.2254 615.9409 888.9048 1272.2826 1739.7119 2460.4631 3456.2190 5195.0850 8498.8643 15692.0918 | lr 4.4e-04 | norm 6067.8237 | dt 9.790 +type train | step 1792 | loss 130.4510 260.4011 385.8171 600.3138 869.6570 1249.0908 1715.4862 2445.2588 3451.6194 5230.6489 8570.1523 15815.7783 | lr 4.4e-04 | norm 6497.3125 | dt 9.775 +type train | step 1793 | loss 125.9344 251.1893 374.3901 586.5148 849.7628 1216.6594 1675.6541 2373.1584 3358.0557 5088.5806 8379.3457 15559.4453 | lr 4.4e-04 | norm 5686.1904 | dt 9.780 +type train | step 1794 | loss 128.5576 254.7580 377.1544 591.0481 860.1626 1231.2001 1695.8783 2418.7441 3416.9094 5174.2417 8449.0283 15689.2656 | lr 4.4e-04 | norm 5249.4082 | dt 9.777 +type train | step 1795 | loss 142.8153 280.6781 407.1607 629.5739 893.8030 1280.7162 1730.8358 2430.0254 3390.6365 5054.4795 8177.7188 15113.5264 | lr 4.4e-04 | norm 5872.1997 | dt 9.784 +type train | step 1796 | loss 117.5080 233.3847 351.0754 559.7212 819.4077 1187.2955 1640.4656 2347.4285 3323.6638 5028.3647 8282.1211 15338.2949 | lr 4.4e-04 | norm 5470.4619 | dt 9.790 +type train | step 1797 | loss 124.0008 246.7927 367.9214 576.8911 837.5402 1210.8267 1672.8710 2403.4111 3402.4912 5144.8828 8462.6797 15745.8252 | lr 4.4e-04 | norm 6111.5649 | dt 9.787 +type train | step 1798 | loss 124.1736 244.8375 366.0191 577.9968 844.1739 1225.0049 1691.6423 2421.4524 3420.5610 5191.8154 8541.0508 15959.8994 | lr 4.4e-04 | norm 6031.8467 | dt 9.778 +type train | step 1799 | loss 124.9951 247.8365 370.2524 582.8098 847.8091 1230.4700 1696.7296 2429.9985 3417.7612 5144.3345 8456.6240 15777.8994 | lr 4.4e-04 | norm 6741.0786 | dt 9.782 +type train | step 1800 | loss 123.6268 247.8287 373.1503 589.3184 859.7385 1236.5634 1698.6976 2411.1091 3412.6685 5135.2261 8421.0342 15557.8984 | lr 4.4e-04 | norm 5967.4839 | dt 9.779 +type train | step 1801 | loss 134.0107 265.3547 388.8299 607.2656 875.2898 1251.8904 1713.8804 2416.2622 3412.7476 5116.8691 8302.3711 15335.8066 | lr 4.4e-04 | norm 5810.7007 | dt 9.786 +type train | step 1802 | loss 140.0792 280.1763 413.0193 646.5219 929.1303 1325.7426 1792.4750 2518.0903 3501.1270 5197.0894 8422.4258 15784.9463 | lr 4.4e-04 | norm 7026.1274 | dt 9.777 +type train | step 1803 | loss 121.9698 242.3298 364.4180 574.2769 833.9826 1196.9871 1648.5062 2342.6746 3341.2534 5059.4575 8338.6641 15499.0703 | lr 4.4e-04 | norm 5686.9951 | dt 9.776 +type train | step 1804 | loss 118.8934 236.0614 352.9714 555.3309 815.0780 1183.0687 1647.0211 2351.5396 3346.6064 5104.1772 8412.0176 15736.7793 | lr 4.4e-04 | norm 6722.0957 | dt 9.788 +type train | step 1805 | loss 133.1499 261.0756 385.2176 601.3385 870.1070 1248.5902 1712.3368 2420.2327 3403.9404 5101.8442 8333.7676 15386.0723 | lr 4.4e-04 | norm 7014.3564 | dt 9.779 +type train | step 1806 | loss 127.2014 254.0907 374.6985 585.1241 847.3229 1219.0760 1672.4419 2391.3647 3365.5042 5089.4775 8374.4492 15589.7148 | lr 4.4e-04 | norm 5653.4717 | dt 9.784 +type train | step 1807 | loss 125.6315 249.0895 368.2763 580.3349 843.1828 1214.8638 1669.0117 2372.6409 3352.1157 5067.1396 8308.2803 15356.4277 | lr 4.4e-04 | norm 5690.3286 | dt 9.797 +type train | step 1808 | loss 121.6424 239.6638 360.5532 571.1423 836.4796 1211.2458 1671.1688 2382.8740 3392.2546 5130.3320 8401.6055 15540.6504 | lr 4.4e-04 | norm 5819.1631 | dt 9.799 +type train | step 1809 | loss 128.4724 252.9238 374.2861 587.1382 846.3157 1210.1472 1665.0184 2362.7974 3333.1763 4976.9062 8119.3110 14960.5449 | lr 4.4e-04 | norm 5545.3540 | dt 9.776 +type train | step 1810 | loss 122.1295 242.4408 361.6105 571.6675 833.8948 1201.0452 1654.6045 2353.6084 3340.3647 5043.9370 8258.3408 15251.3154 | lr 4.4e-04 | norm 5144.7222 | dt 9.789 +type train | step 1811 | loss 135.9382 269.3930 397.4238 617.6688 881.2532 1261.1437 1708.9380 2399.8728 3324.0588 4997.5093 8148.2749 15128.3555 | lr 4.4e-04 | norm 5439.3594 | dt 9.803 +type train | step 1812 | loss 130.3880 260.0499 384.9674 599.2956 867.9421 1249.7689 1705.0986 2429.5098 3374.0461 5058.3159 8273.8154 15263.9873 | lr 4.4e-04 | norm 5669.7275 | dt 9.795 +type train | step 1813 | loss 125.5014 250.9052 375.1908 586.5169 848.3915 1212.3358 1659.4445 2358.6318 3326.9438 4982.4204 8084.7881 14732.7500 | lr 4.4e-04 | norm 5913.1152 | dt 9.795 +type train | step 1814 | loss 128.6957 254.2523 377.0131 591.8384 856.9171 1222.6199 1678.8114 2362.9197 3340.5796 5068.9048 8272.5234 15466.7705 | lr 4.4e-04 | norm 7173.3228 | dt 9.778 +type train | step 1815 | loss 123.1939 242.6884 362.3536 572.6368 834.3745 1199.2087 1651.5203 2358.4360 3339.0190 5047.7314 8269.7207 15254.9951 | lr 4.4e-04 | norm 8574.8525 | dt 9.780 +type train | step 1816 | loss 140.8277 276.9578 405.1600 624.0803 893.4130 1278.8683 1744.9631 2462.7686 3421.9417 5165.2158 8475.9688 15764.4746 | lr 4.4e-04 | norm 5908.2554 | dt 9.778 +type train | step 1817 | loss 126.0721 248.8241 368.9313 577.8171 839.9987 1204.3826 1653.6011 2339.8411 3308.8718 5008.4932 8196.0430 15136.5586 | lr 4.4e-04 | norm 5747.3882 | dt 9.794 +type train | step 1818 | loss 122.9079 242.7532 364.7231 582.2814 846.5717 1243.9498 1719.9283 2469.2764 3477.7837 5268.0205 8735.5176 16377.6270 | lr 4.4e-04 | norm 9871.7080 | dt 9.768 +type train | step 1819 | loss 134.5381 266.0816 395.6486 619.6525 897.1975 1305.0770 1789.8173 2558.2041 3574.6497 5389.8706 8816.6191 16361.2158 | lr 4.4e-04 | norm 7346.7241 | dt 9.773 +type train | step 1820 | loss 133.1807 265.2998 391.3058 606.6255 878.0052 1256.8523 1719.6824 2434.5212 3416.7090 5164.1455 8459.6934 15629.3164 | lr 4.4e-04 | norm 5473.5845 | dt 9.779 +type train | step 1821 | loss 119.5630 236.2957 355.7523 563.1782 824.6193 1190.0465 1644.9622 2341.3247 3326.9602 5053.7178 8326.4277 15507.6084 | lr 4.4e-04 | norm 5534.0425 | dt 9.781 +type train | step 1822 | loss 140.8240 276.9881 409.0094 639.0076 902.7263 1284.0046 1729.9241 2427.8889 3354.7476 4997.3657 8166.0122 15208.6416 | lr 4.4e-04 | norm 6332.1143 | dt 9.766 +type train | step 1823 | loss 132.0259 263.8495 391.8776 616.6659 889.9711 1274.4102 1737.5782 2458.7036 3418.3708 5155.8867 8417.7871 15785.2891 | lr 4.4e-04 | norm 7572.7915 | dt 9.771 +type train | step 1824 | loss 140.3850 278.7658 404.2391 629.7707 892.9877 1285.1233 1749.4265 2475.8145 3419.8145 5120.8853 8377.5117 15602.7500 | lr 4.4e-04 | norm 6022.5640 | dt 9.779 +type train | step 1825 | loss 134.5851 270.2936 397.5209 611.8804 876.0192 1242.1041 1693.0638 2388.5332 3366.0117 5042.7510 8224.8506 15276.8896 | lr 4.4e-04 | norm 5799.3315 | dt 9.784 +type train | step 1826 | loss 125.8957 252.1606 374.8046 586.0997 853.0128 1227.1559 1688.2648 2403.0884 3404.4241 5142.3008 8442.7207 15504.6025 | lr 4.4e-04 | norm 5617.7002 | dt 9.790 +type train | step 1827 | loss 126.3148 249.6603 372.9410 583.3137 845.8663 1219.8591 1679.8279 2381.3757 3367.7549 5077.3931 8291.4512 15298.1514 | lr 4.4e-04 | norm 5457.1895 | dt 9.793 +type train | step 1828 | loss 127.6132 252.7573 377.2380 590.8987 857.6365 1218.8895 1672.9663 2355.1641 3339.5581 5046.0078 8265.1680 15226.3203 | lr 4.4e-04 | norm 5171.7935 | dt 9.795 +type train | step 1829 | loss 127.0341 256.0831 377.2062 590.6899 852.3715 1216.0291 1674.2029 2372.4551 3351.0896 5041.1587 8228.3018 15204.9023 | lr 4.4e-04 | norm 7133.2305 | dt 9.786 +type train | step 1830 | loss 126.4077 247.4085 371.0917 580.5163 846.2795 1215.9437 1663.6715 2358.6133 3322.5166 5012.3525 8177.4136 15219.7051 | lr 4.4e-04 | norm 4876.4224 | dt 9.776 +type train | step 1831 | loss 127.7088 253.7758 375.0290 587.7946 850.1873 1227.1654 1679.7611 2392.9800 3363.2271 5091.6816 8380.6748 15619.0898 | lr 4.4e-04 | norm 6572.2007 | dt 9.776 +type train | step 1832 | loss 154.9180 309.9294 443.5615 675.8857 965.8113 1395.0681 1886.5588 2678.8862 3641.8203 5323.1064 8532.7725 15793.8037 | lr 4.4e-04 | norm 7793.7749 | dt 9.756 +type train | step 1833 | loss 159.8567 314.3152 445.8375 680.7462 976.6002 1425.3586 1921.7424 2763.3420 3756.0930 5394.0088 8535.1475 15535.4795 | lr 4.4e-04 | norm 9956.1094 | dt 9.746 +type train | step 1834 | loss 125.0230 249.5216 375.8125 588.9073 855.0613 1222.2944 1681.1647 2387.0066 3390.8215 5139.6216 8470.6748 15699.4043 | lr 4.4e-04 | norm 6117.9116 | dt 9.789 +type train | step 1835 | loss 129.1543 258.5609 386.6311 606.4310 874.6043 1258.0051 1722.7279 2441.0542 3464.8823 5215.5889 8552.1992 15806.6992 | lr 4.4e-04 | norm 6290.9590 | dt 9.787 +type train | step 1836 | loss 123.1559 244.9742 366.1848 577.3745 841.5638 1215.9799 1671.9403 2385.9236 3378.8330 5113.1792 8384.9639 15490.1182 | lr 4.4e-04 | norm 6183.9238 | dt 9.800 +type train | step 1837 | loss 129.9149 258.0676 385.0206 600.9437 869.2207 1246.8625 1705.7986 2416.5735 3404.0557 5133.9341 8365.5508 15504.8691 | lr 4.4e-04 | norm 5402.4043 | dt 9.783 +type train | step 1838 | loss 125.4790 248.0827 372.8929 588.2141 854.2094 1223.4541 1674.9094 2374.4775 3373.7983 5090.2183 8368.1094 15504.3184 | lr 4.4e-04 | norm 5508.1611 | dt 9.784 +type train | step 1839 | loss 132.2941 268.8307 390.5439 605.9555 878.9366 1269.6324 1752.1348 2505.5386 3521.6379 5303.5078 8651.4590 15919.0703 | lr 4.4e-04 | norm 7571.4639 | dt 9.768 +type train | step 1840 | loss 126.6466 250.8933 373.3795 588.6666 857.8705 1242.5862 1715.8584 2438.6904 3433.5813 5141.5576 8450.1562 15589.4053 | lr 4.4e-04 | norm 5582.2705 | dt 9.782 +type train | step 1841 | loss 130.9222 261.6297 385.3355 601.7070 868.5635 1247.3958 1710.9094 2421.7026 3424.2578 5155.6187 8475.1641 15606.0527 | lr 4.4e-04 | norm 5098.9927 | dt 9.786 +type train | step 1842 | loss 115.8807 240.2356 388.4781 636.6050 933.8295 1342.9225 1867.5186 2671.8650 3849.3604 5893.6904 9689.4883 18029.6660 | lr 4.4e-04 | norm 12501.8350 | dt 9.791 +type train | step 1843 | loss 147.9286 302.4521 442.2887 687.4067 979.5219 1383.0513 1877.6283 2607.0510 3616.2693 5313.6943 8541.1699 15501.6230 | lr 4.4e-04 | norm 8622.9434 | dt 9.781 +type train | step 1844 | loss 128.9343 257.1060 382.2950 593.1190 859.4527 1238.9464 1697.2749 2422.3418 3403.9399 5105.4365 8297.8711 15317.0010 | lr 4.4e-04 | norm 5549.5840 | dt 9.777 +type train | step 1845 | loss 136.4668 273.4239 401.8453 625.3029 895.8582 1274.5918 1725.8176 2423.7048 3375.0005 5047.8174 8185.2310 15116.6416 | lr 4.4e-04 | norm 5598.1973 | dt 9.794 +type train | step 1846 | loss 133.2594 268.1979 394.9645 616.1669 888.6515 1267.4713 1736.8256 2455.4336 3453.8701 5204.1011 8500.1172 15750.5625 | lr 4.4e-04 | norm 6154.2773 | dt 9.795 +type train | step 1847 | loss 123.2986 244.4475 364.5265 571.4775 830.0903 1193.7285 1639.2848 2322.4019 3300.8855 4959.6587 8128.1030 14992.7383 | lr 4.4e-04 | norm 5351.7842 | dt 9.777 +type train | step 1848 | loss 129.5919 259.6630 382.9059 598.2778 862.1069 1243.4050 1707.9158 2434.7070 3415.9578 5163.9331 8408.8408 15494.6201 | lr 4.4e-04 | norm 5461.1753 | dt 9.779 +type train | step 1849 | loss 122.1413 243.5940 361.6898 570.4688 829.7257 1194.1610 1638.7743 2324.1133 3304.9165 4979.4766 8173.8647 14998.6641 | lr 4.4e-04 | norm 4427.7495 | dt 9.791 +type train | step 1850 | loss 133.1495 268.3787 393.6820 616.7395 889.7595 1280.4604 1748.9707 2478.7144 3465.1301 5217.3770 8503.8779 15595.5889 | lr 4.4e-04 | norm 5892.4414 | dt 9.785 +type train | step 1851 | loss 126.4002 252.9212 377.8227 593.4892 860.0286 1229.2913 1693.0178 2401.8223 3414.3054 5151.1772 8430.1406 15533.0410 | lr 4.4e-04 | norm 5274.7959 | dt 9.790 +type train | step 1852 | loss 138.6648 274.3987 408.4381 634.0651 909.3290 1359.9465 1870.0214 2709.2490 3702.6797 5528.5757 9076.4424 17069.8652 | lr 4.4e-04 | norm 9859.4277 | dt 9.750 +type train | step 1853 | loss 135.8205 270.0563 398.7106 610.7594 873.2739 1278.7921 1743.6030 2482.1514 3428.1851 5134.6216 8461.2227 15937.7129 | lr 4.4e-04 | norm 8318.2070 | dt 9.759 +type train | step 1854 | loss 128.7359 254.1336 378.6164 592.0277 856.2620 1234.1285 1700.7676 2418.8159 3411.5769 5157.8501 8421.6475 15496.4531 | lr 4.4e-04 | norm 5526.1777 | dt 9.795 +type train | step 1855 | loss 125.9160 251.7139 372.6440 587.0928 850.7479 1232.8369 1694.4591 2413.0781 3401.5525 5107.8735 8344.1924 15429.5518 | lr 4.4e-04 | norm 6065.3564 | dt 9.793 +type train | step 1856 | loss 131.4882 262.9075 386.8360 603.8705 867.6421 1243.1808 1696.0225 2391.5950 3344.2356 5015.6934 8175.7842 15126.5117 | lr 4.4e-04 | norm 6229.9966 | dt 9.785 +type train | step 1857 | loss 130.1729 255.5421 380.2824 596.6555 861.7469 1228.8528 1688.4993 2393.5281 3403.1897 5139.0088 8365.6074 15503.7920 | lr 4.4e-04 | norm 6400.5298 | dt 9.790 +type train | step 1858 | loss 127.4269 254.4158 383.6771 611.4253 893.4898 1280.8855 1762.5544 2511.1316 3508.4758 5258.9429 8552.2129 15851.6562 | lr 4.4e-04 | norm 7396.4653 | dt 9.784 +type train | step 1859 | loss 125.6577 249.1166 372.6577 584.9519 851.4380 1218.7605 1674.6569 2373.3816 3354.4243 5059.3901 8219.3271 15078.4844 | lr 4.4e-04 | norm 5191.9956 | dt 9.780 +type train | step 1860 | loss 125.4349 247.1501 366.3183 575.1416 834.7482 1200.5867 1649.3468 2335.5486 3284.1558 4961.0308 8213.3359 15347.9834 | lr 4.4e-04 | norm 5558.2202 | dt 9.775 +type train | step 1861 | loss 122.7028 241.9289 365.4922 578.7873 845.0102 1210.2449 1662.9526 2400.8208 3415.4795 5181.2412 8500.6230 15764.8730 | lr 4.4e-04 | norm 6865.4375 | dt 9.795 +type train | step 1862 | loss 129.1065 257.3225 380.3647 598.9492 867.7072 1244.6447 1708.3801 2431.5120 3452.2891 5201.4570 8504.0928 15667.3057 | lr 4.4e-04 | norm 5485.3105 | dt 9.794 +type train | step 1863 | loss 119.1788 236.2246 354.4858 565.1390 824.5908 1189.2468 1653.4089 2366.4177 3368.6355 5104.5825 8373.6367 15412.6973 | lr 4.4e-04 | norm 5038.7651 | dt 9.789 +type train | step 1864 | loss 122.7700 242.5635 364.1623 576.3818 839.6879 1210.0247 1656.0206 2358.3042 3331.4958 5024.8203 8209.1982 15099.6621 | lr 4.4e-04 | norm 5481.8701 | dt 9.784 +type train | step 1865 | loss 120.2253 237.9256 355.8326 559.2942 819.8355 1178.7917 1630.5306 2314.3301 3295.2585 4956.8535 8122.9521 15002.1494 | lr 4.4e-04 | norm 5268.7461 | dt 9.790 +type train | step 1866 | loss 126.6905 253.5714 380.3047 597.6478 879.9131 1271.7158 1746.7325 2475.0320 3481.7981 5181.7949 8393.2148 15456.3203 | lr 4.4e-04 | norm 6492.8691 | dt 9.771 +type train | step 1867 | loss 138.9903 280.9065 427.3039 677.7200 995.2644 1415.4763 1938.4585 2722.6028 3857.2900 5755.7310 9335.1748 17012.3965 | lr 4.4e-04 | norm 8230.6562 | dt 9.767 +type train | step 1868 | loss 121.6127 238.6068 357.4407 567.5572 829.2103 1208.8335 1669.5052 2407.2141 3410.7856 5145.0127 8403.4697 15600.7969 | lr 4.4e-04 | norm 5609.3623 | dt 9.792 +type train | step 1869 | loss 123.5750 244.8046 366.1042 571.1514 827.8047 1193.0577 1643.2821 2340.8953 3312.3152 5003.1807 8212.2041 15309.6406 | lr 4.4e-04 | norm 6331.4419 | dt 9.784 +type train | step 1870 | loss 125.7721 251.2977 373.7910 579.7147 842.6620 1198.1208 1640.1940 2318.3784 3269.7573 4892.2944 7965.5498 14664.4434 | lr 4.4e-04 | norm 5767.5493 | dt 9.787 +type train | step 1871 | loss 121.3679 239.4286 357.2005 564.7195 826.0542 1185.7552 1633.9318 2321.4043 3304.4082 5002.9126 8193.4473 15130.8838 | lr 4.4e-04 | norm 5623.6689 | dt 9.797 +type train | step 1872 | loss 128.2342 255.9357 377.7041 591.3597 851.5292 1215.3003 1666.6364 2361.3032 3358.3579 5068.7095 8299.6973 15455.4414 | lr 4.4e-04 | norm 6078.9707 | dt 9.785 +type train | step 1873 | loss 128.9128 255.2457 376.6053 588.0331 854.8988 1230.2686 1693.8052 2417.8179 3399.7739 5154.3560 8481.7070 15720.2441 | lr 4.3e-04 | norm 6131.4629 | dt 9.783 +type train | step 1874 | loss 113.9219 227.2096 345.7004 548.2053 802.4286 1157.5437 1603.9612 2281.2571 3269.2849 4919.8066 8017.3252 14731.4648 | lr 4.3e-04 | norm 4832.5952 | dt 9.790 +type train | step 1875 | loss 120.7773 237.6450 356.7022 565.1665 827.6017 1195.1626 1649.5563 2361.6565 3355.1565 5044.1733 8265.3691 15183.7852 | lr 4.3e-04 | norm 5144.1069 | dt 9.807 +type train | step 1876 | loss 121.5117 254.1530 383.8466 600.1729 871.3048 1233.3984 1702.6865 2414.6650 3450.7378 5188.0005 8498.2461 15809.6943 | lr 4.3e-04 | norm 8514.0068 | dt 9.788 +type train | step 1877 | loss 124.5135 263.7362 398.5887 616.1785 890.5822 1245.7355 1711.4458 2432.9011 3477.1313 5208.9946 8527.4482 15713.0312 | lr 4.3e-04 | norm 9933.7002 | dt 9.799 +type train | step 1878 | loss 126.0644 247.6791 371.6216 585.9595 852.9891 1235.9508 1702.9146 2428.6907 3427.1951 5178.4155 8486.6953 15677.9307 | lr 4.3e-04 | norm 5378.4019 | dt 9.795 +type train | step 1879 | loss 121.3045 241.2955 359.1345 561.8010 820.0779 1181.7178 1632.9954 2323.3792 3281.7690 4944.8218 8124.6392 15140.5166 | lr 4.3e-04 | norm 6286.5391 | dt 9.784 +type train | step 1880 | loss 116.5119 228.7578 343.3612 545.2512 794.8940 1156.1512 1602.6752 2296.4290 3264.3491 4925.7812 8053.9033 14929.0557 | lr 4.3e-04 | norm 5730.5415 | dt 9.776 +type train | step 1881 | loss 128.7353 256.9992 383.8846 596.1890 864.2018 1238.1033 1704.2355 2419.3389 3418.5591 5134.8140 8418.9482 15593.1299 | lr 4.3e-04 | norm 5620.3232 | dt 9.788 +type train | step 1882 | loss 126.2942 250.5145 370.4609 580.3903 838.9119 1214.8085 1673.5984 2381.2717 3359.0977 5096.3574 8424.9199 15844.0400 | lr 4.3e-04 | norm 6677.1562 | dt 9.771 +type train | step 1883 | loss 127.9869 257.5818 383.2989 595.8369 865.2574 1229.1938 1677.0568 2381.6121 3367.7246 5100.4160 8370.8555 15479.2539 | lr 4.3e-04 | norm 5394.0762 | dt 9.780 +type train | step 1884 | loss 120.6094 238.3423 356.4364 558.8052 813.8838 1172.4392 1623.7297 2322.6614 3308.5662 4991.4282 8219.7910 15149.4600 | lr 4.3e-04 | norm 4642.4575 | dt 9.780 +type train | step 1885 | loss 132.9987 258.7321 386.5425 604.5403 876.2975 1253.6139 1716.6986 2450.3584 3475.7151 5288.8833 8874.5859 16939.7656 | lr 4.3e-04 | norm 9778.2510 | dt 9.760 +type train | step 1886 | loss 115.9050 232.3871 357.9167 568.8193 830.7336 1200.3279 1660.9948 2374.6370 3411.5610 5128.9390 8386.2480 15532.4199 | lr 4.3e-04 | norm 7601.3022 | dt 9.790 +type train | step 1887 | loss 118.3624 233.5963 347.4844 550.3280 805.0922 1165.9534 1611.9631 2307.5310 3265.4690 4903.7319 8040.5098 14763.9189 | lr 4.3e-04 | norm 5494.1519 | dt 9.795 +type train | step 1888 | loss 121.8712 239.9436 364.3030 580.7671 846.6771 1217.3356 1674.9999 2387.4021 3406.1565 5140.0117 8448.2002 15725.4688 | lr 4.3e-04 | norm 6220.5278 | dt 9.790 +type train | step 1889 | loss 124.0870 245.4966 364.7921 575.6561 837.0590 1207.8425 1668.1334 2383.0439 3357.5176 5061.6289 8352.3066 15570.5879 | lr 4.3e-04 | norm 5686.0806 | dt 9.774 +type train | step 1890 | loss 127.7664 253.1861 377.0791 596.2473 861.2109 1238.4351 1694.7954 2401.4141 3356.5522 5028.7104 8229.2363 15379.9121 | lr 4.3e-04 | norm 6854.3486 | dt 9.778 +type train | step 1891 | loss 122.8505 244.3719 363.0686 571.6365 833.8513 1199.1903 1649.6029 2357.1887 3321.8657 5023.7002 8291.6367 15383.3594 | lr 4.3e-04 | norm 5774.5044 | dt 9.788 +type train | step 1892 | loss 123.8227 245.2582 365.2530 570.7791 827.4560 1193.0780 1640.0034 2326.7458 3286.8223 4937.9814 8080.5664 14974.5186 | lr 4.3e-04 | norm 5495.6450 | dt 9.780 +type train | step 1893 | loss 124.0284 246.1197 363.5760 568.6779 821.5842 1175.9769 1617.4561 2294.3066 3251.8999 4924.8413 8100.0005 15018.2510 | lr 4.3e-04 | norm 5715.4385 | dt 9.782 +type train | step 1894 | loss 123.7897 247.0665 368.5822 578.1735 838.7217 1199.6462 1648.6801 2340.4829 3306.6167 4969.6851 8142.4058 15118.9541 | lr 4.3e-04 | norm 5914.4839 | dt 9.778 +type train | step 1895 | loss 122.2772 239.6882 360.2233 565.1840 827.8606 1193.7831 1647.6740 2346.5337 3343.1787 5046.1143 8289.9111 15358.3369 | lr 4.3e-04 | norm 5494.3188 | dt 9.783 +type train | step 1896 | loss 129.9088 260.9751 384.4819 602.9116 870.8009 1275.8221 1764.6786 2546.2773 3554.1226 5317.2842 8652.4326 15937.5938 | lr 4.3e-04 | norm 5752.5405 | dt 9.762 +type train | step 1897 | loss 131.0855 265.4490 397.9011 624.4278 897.3336 1281.7939 1753.0452 2468.5930 3452.7085 5193.0293 8482.4668 15664.2744 | lr 4.3e-04 | norm 7223.6538 | dt 9.784 +type train | step 1898 | loss 118.9187 235.8176 355.5291 560.1213 816.4020 1170.5876 1610.2814 2287.3557 3257.0022 4935.1128 8150.4429 15111.3984 | lr 4.3e-04 | norm 5541.9380 | dt 9.784 +type train | step 1899 | loss 118.4156 233.2974 349.0541 550.7258 804.2581 1166.6960 1609.3649 2300.3413 3263.1626 4939.1519 8125.5200 15133.9443 | lr 4.3e-04 | norm 5881.0234 | dt 9.784 +type train | step 1900 | loss 122.1831 242.1867 363.6994 573.7236 835.6837 1202.0458 1650.4304 2350.8250 3328.3164 5004.4082 8200.1699 15211.6357 | lr 4.3e-04 | norm 5362.9429 | dt 9.776 +type train | step 1901 | loss 118.4395 231.9472 349.9756 552.4040 806.8455 1162.7896 1607.0082 2288.9111 3267.7000 4934.9609 8117.1724 15086.8945 | lr 4.3e-04 | norm 5447.2612 | dt 9.774 +type train | step 1902 | loss 119.9489 236.8548 353.8029 554.4791 807.6615 1164.5449 1608.3118 2289.7686 3255.5986 4918.9399 8071.7402 14951.5244 | lr 4.3e-04 | norm 5101.1538 | dt 9.773 +type train | step 1903 | loss 126.2520 250.0721 370.7150 577.8242 836.1398 1204.3141 1657.4548 2350.3149 3319.9492 5029.3911 8237.4648 15251.2197 | lr 4.3e-04 | norm 5302.7852 | dt 9.779 +type train | step 1904 | loss 120.6720 239.9983 363.3740 574.1930 843.8648 1215.4670 1685.4087 2405.9729 3429.8621 5158.2207 8408.8682 15589.3389 | lr 4.3e-04 | norm 7120.1704 | dt 9.784 +type train | step 1905 | loss 120.9404 239.9318 360.3813 567.8533 835.2243 1206.1857 1673.5552 2394.3840 3407.7302 5167.6948 8441.8398 15628.1328 | lr 4.3e-04 | norm 7696.4932 | dt 9.801 +type train | step 1906 | loss 120.9697 238.1533 355.3056 556.7714 812.3445 1171.3235 1613.3502 2292.8054 3259.8926 4922.2319 8097.3936 14953.4414 | lr 4.3e-04 | norm 5381.7588 | dt 9.794 +type train | step 1907 | loss 127.4555 251.8569 377.2076 588.5174 852.2086 1220.6432 1677.7333 2385.4495 3373.8960 5091.4399 8322.7480 15357.5156 | lr 4.3e-04 | norm 5716.6738 | dt 9.785 +type train | step 1908 | loss 124.5223 245.9167 367.4464 577.1646 837.3013 1212.3621 1662.8444 2364.2720 3340.3870 5008.8066 8189.2847 15086.1670 | lr 4.3e-04 | norm 5295.5913 | dt 9.782 +type train | step 1909 | loss 118.6454 237.3274 356.2038 563.0209 821.8157 1190.7632 1642.2064 2361.2988 3344.3152 5075.5576 8299.4570 15353.0996 | lr 4.3e-04 | norm 5402.0928 | dt 9.783 +type train | step 1910 | loss 118.7492 238.0160 360.2306 571.6486 832.4877 1221.5006 1697.6201 2464.5210 3506.0261 5312.0601 8706.0693 16054.8721 | lr 4.3e-04 | norm 6351.5234 | dt 9.782 +type train | step 1911 | loss 128.6209 258.3985 379.6935 590.9303 855.0596 1226.7673 1686.6095 2389.9360 3354.1721 5075.4297 8336.4258 15471.4658 | lr 4.3e-04 | norm 7057.8867 | dt 9.783 +type train | step 1912 | loss 135.2390 272.2508 401.1819 623.5675 886.3979 1276.1930 1733.5852 2461.7937 3420.3357 5095.6992 8321.6230 15249.2539 | lr 4.3e-04 | norm 6589.1382 | dt 9.786 +type train | step 1913 | loss 122.4666 244.8488 363.2147 567.2211 822.4230 1187.6814 1638.3318 2328.3564 3291.4028 4960.3086 8154.2734 15093.0850 | lr 4.3e-04 | norm 5278.7886 | dt 9.781 +type train | step 1914 | loss 127.3649 255.2259 377.0528 589.6623 855.2471 1228.3633 1690.7820 2401.4517 3403.1960 5109.8477 8316.4170 15342.5703 | lr 4.3e-04 | norm 6020.6069 | dt 9.781 +type train | step 1915 | loss 131.6151 259.8217 385.8853 599.4081 865.5406 1240.7090 1694.3385 2394.9294 3340.9077 5000.9888 8126.3716 14975.2793 | lr 4.3e-04 | norm 5357.5024 | dt 9.776 +type train | step 1916 | loss 118.6484 232.8255 350.5778 557.5328 817.4721 1191.0750 1645.2476 2349.4910 3332.1460 4997.1270 8112.3169 14862.7002 | lr 4.3e-04 | norm 5088.1753 | dt 9.782 +type train | step 1917 | loss 118.1841 233.2278 350.2529 548.7805 801.0394 1146.2074 1576.0525 2236.4128 3180.2651 4795.5127 7879.4365 14616.0566 | lr 4.3e-04 | norm 4607.9336 | dt 9.799 +type train | step 1918 | loss 134.4277 267.0207 394.5170 616.7562 884.6055 1265.2511 1723.3761 2430.1157 3402.9387 5055.6973 8190.9014 15152.0381 | lr 4.3e-04 | norm 6039.3760 | dt 9.780 +type train | step 1919 | loss 141.1175 277.9727 409.4227 634.2037 903.4040 1283.1089 1739.5574 2447.9587 3433.9104 5094.8945 8263.8447 15065.6250 | lr 4.3e-04 | norm 8427.0029 | dt 9.792 +type train | step 1920 | loss 137.9470 271.1143 399.1550 620.7712 886.3251 1275.4253 1751.8831 2470.3865 3469.6829 5203.2656 8492.0342 15655.0801 | lr 4.3e-04 | norm 7052.6484 | dt 9.786 +type train | step 1921 | loss 119.9720 239.0684 358.5121 565.7126 822.3082 1188.0074 1638.5150 2341.2898 3333.6348 5021.0767 8253.4697 15294.7666 | lr 4.3e-04 | norm 5710.8003 | dt 9.798 +type train | step 1922 | loss 117.7255 233.9926 352.6894 561.4656 817.5257 1178.7889 1632.1814 2329.0171 3318.0762 5009.7549 8268.7812 15259.5811 | lr 4.3e-04 | norm 6055.2529 | dt 9.788 +type train | step 1923 | loss 122.8254 246.2038 367.7441 578.7246 837.6786 1206.6565 1659.6083 2363.0640 3365.3235 5061.0376 8352.4004 15491.0801 | lr 4.3e-04 | norm 5922.2700 | dt 9.786 +type train | step 1924 | loss 117.4967 233.7448 352.9435 559.2814 819.5563 1189.0297 1647.4441 2346.4087 3334.5205 5035.7349 8233.4727 15260.1250 | lr 4.3e-04 | norm 5839.4644 | dt 9.786 +type train | step 1925 | loss 128.8678 254.6913 388.4958 611.7931 900.9997 1298.3905 1786.7129 2571.2205 3647.4375 5592.7427 9287.3545 17344.6016 | lr 4.3e-04 | norm 8106.9277 | dt 9.769 +type train | step 1926 | loss 122.9071 242.2422 363.7580 571.9200 836.1045 1214.3652 1676.3497 2387.9224 3355.3865 5056.4995 8303.3975 15433.8389 | lr 4.3e-04 | norm 6667.2832 | dt 9.772 +type train | step 1927 | loss 125.0801 247.7363 367.8034 572.5665 829.9325 1193.8279 1631.1079 2316.8992 3274.2776 4916.7373 8035.9404 14868.8730 | lr 4.3e-04 | norm 5745.4341 | dt 10.221 +type train | step 1928 | loss 127.9341 252.3725 372.8779 585.8356 851.5978 1237.3419 1699.8105 2427.2742 3395.4565 5055.8682 8225.3018 15129.9775 | lr 4.3e-04 | norm 5616.2876 | dt 9.776 +type train | step 1929 | loss 124.8715 246.2217 365.3317 574.0980 834.5464 1195.2617 1648.5361 2339.5645 3316.4810 4974.8247 8110.1035 14975.2412 | lr 4.3e-04 | norm 5407.1929 | dt 9.781 +type train | step 1930 | loss 123.6578 243.7085 365.2296 572.6322 832.8076 1198.0350 1651.9987 2349.8376 3324.4021 5019.9634 8216.7754 15276.7305 | lr 4.3e-04 | norm 5843.3740 | dt 9.789 +type train | step 1931 | loss 120.7001 241.6580 361.5816 569.2516 829.7357 1194.4358 1645.9767 2344.1655 3338.5806 4994.1968 8138.4072 14887.8594 | lr 4.3e-04 | norm 4782.5361 | dt 9.779 +type train | step 1932 | loss 122.7275 242.5646 357.3280 558.1018 812.6328 1165.6462 1604.8553 2286.8882 3244.5005 4865.4180 7939.7632 14661.9551 | lr 4.3e-04 | norm 5336.1260 | dt 9.777 +type train | step 1933 | loss 121.3002 239.4763 353.4423 555.2549 813.4984 1181.9540 1628.2583 2332.6147 3303.2102 4990.5059 8202.6084 15263.6328 | lr 4.3e-04 | norm 6267.4883 | dt 9.785 +type train | step 1934 | loss 127.7178 254.9182 376.0844 579.6543 842.9363 1216.1300 1678.3378 2387.4724 3381.8987 5124.2349 8433.2236 15664.2178 | lr 4.3e-04 | norm 6592.9272 | dt 9.789 +type train | step 1935 | loss 122.7801 240.8283 359.8059 567.1152 828.8171 1189.4519 1638.6614 2330.5537 3321.4077 5030.6396 8252.7715 15342.7744 | lr 4.3e-04 | norm 6605.8218 | dt 9.777 +type train | step 1936 | loss 134.7120 271.0424 398.5449 617.0601 886.7097 1268.8696 1731.0762 2444.6072 3435.2222 5183.6650 8429.2393 15691.1387 | lr 4.3e-04 | norm 7655.4712 | dt 9.792 +type train | step 1937 | loss 121.7162 240.2903 357.6017 564.1897 822.4339 1186.4825 1634.8580 2327.1384 3304.2485 4964.8481 8138.7769 15151.4883 | lr 4.3e-04 | norm 6378.3335 | dt 9.769 +type train | step 1938 | loss 117.2300 231.0405 346.2997 547.9132 802.1634 1172.9260 1619.0852 2315.9192 3275.6318 4879.9556 7927.9727 14566.4873 | lr 4.3e-04 | norm 6433.7681 | dt 9.782 +type train | step 1939 | loss 117.2664 230.0354 340.8916 543.3559 800.3452 1188.7722 1657.1272 2394.9658 3352.6841 4980.1499 8157.8657 15109.5811 | lr 4.3e-04 | norm 11654.4902 | dt 9.745 +type train | step 1940 | loss 118.8558 235.9458 354.7026 559.1477 817.0921 1175.1682 1625.2253 2305.3015 3280.6079 4955.7495 8153.2593 15119.6025 | lr 4.3e-04 | norm 5489.6450 | dt 9.796 +type train | step 1941 | loss 122.2822 247.2814 363.9947 571.2911 826.7872 1192.9720 1646.1882 2352.5796 3332.7271 5052.8887 8314.0498 15401.4463 | lr 4.3e-04 | norm 5459.4980 | dt 9.776 +type train | step 1942 | loss 123.7574 247.6569 368.1379 582.1795 837.0719 1202.7061 1644.6072 2339.6958 3294.5361 4952.5161 8130.4473 15103.2188 | lr 4.3e-04 | norm 5661.8530 | dt 9.772 +type train | step 1943 | loss 112.3861 220.8603 337.2749 537.8633 787.5400 1133.5735 1562.9518 2223.4277 3185.0381 4786.4360 7814.1987 14386.0547 | lr 4.3e-04 | norm 5042.4224 | dt 9.775 +type train | step 1944 | loss 118.1957 233.7977 354.6255 560.2111 820.2790 1184.1184 1647.5643 2359.1882 3344.9841 5063.7769 8319.7568 15436.8232 | lr 4.3e-04 | norm 6193.0728 | dt 9.787 +type train | step 1945 | loss 124.3266 250.0226 375.3033 589.6812 856.5643 1216.3147 1668.3928 2360.2998 3341.0762 5032.9995 8239.6553 15203.4961 | lr 4.3e-04 | norm 5378.7754 | dt 9.783 +type train | step 1946 | loss 120.2949 239.3438 356.3472 558.9489 817.7438 1176.4801 1617.1023 2304.7417 3279.4934 4936.0430 8097.6357 14956.6953 | lr 4.3e-04 | norm 4924.1055 | dt 9.793 +type train | step 1947 | loss 128.2371 253.6618 374.7216 589.5680 849.5821 1217.3760 1666.3862 2366.0146 3318.0229 4968.0210 8197.0176 15161.8105 | lr 4.3e-04 | norm 6050.3125 | dt 9.774 +type train | step 1948 | loss 131.4952 265.2135 384.4698 594.8538 852.6133 1214.2472 1658.7471 2340.0786 3268.3608 4868.8975 7943.3750 14684.3125 | lr 4.3e-04 | norm 6188.1060 | dt 9.766 +type train | step 1949 | loss 120.0998 239.4329 360.3909 570.2376 831.8151 1202.0552 1656.0078 2360.2480 3346.9604 5040.0273 8268.2422 15265.8887 | lr 4.3e-04 | norm 5076.4707 | dt 9.790 +type train | step 1950 | loss 137.0823 276.3030 410.0492 634.5695 897.7404 1272.8530 1702.6846 2373.0078 3265.7529 4847.7183 7782.9297 14479.2373 | lr 4.3e-04 | norm 6928.4092 | dt 9.762 +type train | step 1951 | loss 127.7023 255.0951 377.2299 589.3323 849.8831 1224.2699 1680.2130 2377.7959 3343.9951 5028.6973 8208.8135 15198.1162 | lr 4.3e-04 | norm 5565.7324 | dt 9.787 +type train | step 1952 | loss 121.8253 243.9523 366.9077 575.1589 837.0458 1196.2235 1648.1444 2338.1270 3328.0408 5008.5083 8156.7202 14977.6221 | lr 4.3e-04 | norm 5030.5630 | dt 9.790 +type train | step 1953 | loss 118.8377 231.0804 354.6867 561.2377 821.8867 1188.2660 1640.2534 2349.1523 3336.6216 5028.0854 8263.0859 15215.8037 | lr 4.3e-04 | norm 6548.7051 | dt 9.781 +type train | step 1954 | loss 113.6301 226.2315 340.3482 536.1155 789.3676 1142.4901 1588.7485 2274.9990 3244.9336 4937.7041 8115.8838 15037.8027 | lr 4.3e-04 | norm 6516.5723 | dt 9.796 +type train | step 1955 | loss 128.2654 256.1941 380.3016 596.3420 863.2640 1240.7397 1710.0974 2432.8945 3427.5083 5123.2495 8350.1084 15377.2783 | lr 4.3e-04 | norm 5480.6445 | dt 9.780 +type train | step 1956 | loss 116.8897 231.2364 346.4191 549.5645 801.9824 1196.8036 1668.3583 2428.6433 3421.9753 5160.1582 8481.6279 15674.9756 | lr 4.3e-04 | norm 8154.6313 | dt 9.757 +type train | step 1957 | loss 118.7359 234.4421 352.6732 554.3119 810.8812 1175.2620 1623.2445 2323.0159 3317.8086 4989.6812 8205.5801 15162.8262 | lr 4.3e-04 | norm 5225.6514 | dt 9.792 +type train | step 1958 | loss 117.7169 233.7608 349.1635 549.9636 804.2474 1155.2924 1597.0748 2270.4595 3247.7739 4911.7812 8010.3838 14801.6699 | lr 4.3e-04 | norm 5498.6411 | dt 9.781 +type train | step 1959 | loss 143.2225 291.4709 422.5414 648.2354 924.0125 1312.4004 1786.9788 2514.2842 3507.6252 5181.3311 8387.7959 15312.8818 | lr 4.3e-04 | norm 6144.2563 | dt 9.782 +type train | step 1960 | loss 122.5914 244.4159 366.1072 580.7031 842.7441 1229.4211 1704.7587 2466.0999 3476.5332 5254.6167 8655.6660 16176.3174 | lr 4.3e-04 | norm 6750.8135 | dt 9.786 +type train | step 1961 | loss 129.8488 262.5855 394.0254 616.9634 889.1858 1289.7223 1775.9834 2518.1965 3518.2441 5267.6353 8625.0977 16102.8604 | lr 4.3e-04 | norm 7171.0713 | dt 9.777 +type train | step 1962 | loss 124.4436 253.2350 378.9668 589.5493 860.6061 1230.3947 1694.3207 2397.6155 3385.1099 5122.0269 8371.0264 15523.1826 | lr 4.2e-04 | norm 7430.3423 | dt 9.779 +type train | step 1963 | loss 114.5947 227.7985 347.6755 556.1521 819.3871 1186.1373 1646.5640 2358.1699 3371.9441 5071.3076 8296.3193 15296.3965 | lr 4.2e-04 | norm 5805.8394 | dt 9.780 +type train | step 1964 | loss 127.1567 253.4675 379.0259 594.9283 866.2573 1251.6365 1717.5951 2446.9436 3475.1284 5227.9409 8593.4092 15990.9170 | lr 4.2e-04 | norm 6469.1831 | dt 9.786 +type train | step 1965 | loss 141.6982 279.5988 407.6204 625.6887 895.9852 1284.0394 1752.9403 2478.5623 3476.6799 5216.6748 8610.7529 16105.8770 | lr 4.2e-04 | norm 7751.2153 | dt 9.770 +type train | step 1966 | loss 126.6040 251.2905 373.3486 583.8477 842.2823 1215.2334 1664.9961 2359.4248 3313.9385 4966.8452 8115.3125 15227.0918 | lr 4.2e-04 | norm 6081.3257 | dt 9.778 +type train | step 1967 | loss 120.6868 242.2276 366.0399 575.8683 844.2575 1225.4075 1690.8096 2437.7095 3450.3921 5192.8896 8575.6748 15966.8721 | lr 4.2e-04 | norm 8200.9492 | dt 9.779 +type train | step 1968 | loss 125.9353 251.3430 373.5743 578.8350 844.3176 1210.1409 1664.9486 2363.7310 3332.2244 5008.4536 8155.9668 15013.6113 | lr 4.2e-04 | norm 5620.0298 | dt 9.798 +type train | step 1969 | loss 146.1369 279.9164 398.2395 618.3296 888.0673 1289.3373 1787.2581 2604.5217 3606.8589 5430.5000 8843.8945 16362.2822 | lr 4.2e-04 | norm 7773.2085 | dt 9.752 +type train | step 1970 | loss 118.7473 237.8588 355.5770 555.4376 814.2160 1174.8193 1621.0388 2306.8757 3281.4880 4934.4468 8092.3105 14982.9365 | lr 4.2e-04 | norm 5706.8267 | dt 9.791 +type train | step 1971 | loss 124.8197 250.0484 369.3396 575.6207 834.0137 1193.5867 1644.2323 2338.1160 3316.6829 4998.4390 8245.3447 15371.4092 | lr 4.2e-04 | norm 6587.0576 | dt 9.777 +type train | step 1972 | loss 132.3591 261.7452 395.7237 621.4791 908.0366 1326.8059 1842.6035 2654.6631 3772.0938 5735.6089 9510.4863 17991.5684 | lr 4.2e-04 | norm 15303.1514 | dt 9.749 +type train | step 1973 | loss 122.1978 241.0797 367.2091 572.4866 834.7846 1200.7422 1648.6829 2330.6096 3318.9524 4981.4023 8164.0894 15089.5527 | lr 4.2e-04 | norm 6249.8506 | dt 9.780 +type train | step 1974 | loss 127.6305 254.4429 381.5783 591.0807 853.8127 1226.1045 1686.2391 2391.4529 3390.9519 5107.0410 8387.1650 15557.4160 | lr 4.2e-04 | norm 5380.7495 | dt 9.788 +type train | step 1975 | loss 121.8706 244.0165 362.0880 567.2127 823.8978 1181.2208 1625.5264 2313.9253 3286.0994 4934.7441 8070.5479 14922.7461 | lr 4.2e-04 | norm 5617.4570 | dt 9.790 +type train | step 1976 | loss 123.8786 248.3853 364.5995 566.8297 823.5098 1176.0603 1612.9557 2289.8945 3235.7085 4850.1162 7912.4409 14621.4180 | lr 4.2e-04 | norm 5495.0674 | dt 9.792 +type train | step 1977 | loss 120.1482 239.9856 356.2815 558.0382 811.8999 1170.1921 1613.8221 2291.3694 3261.0498 4931.7842 8147.0137 15203.9131 | lr 4.2e-04 | norm 5417.0830 | dt 9.784 +type train | step 1978 | loss 123.8903 244.9503 363.6386 571.8856 831.7518 1205.1021 1661.2715 2368.5930 3371.4248 5071.8169 8268.7832 15137.5332 | lr 4.2e-04 | norm 5256.6206 | dt 9.781 +type train | step 1979 | loss 116.0075 229.3219 344.6500 545.3456 805.5971 1166.4628 1608.9753 2292.3655 3266.2261 4927.8496 8129.8779 15029.3262 | lr 4.2e-04 | norm 5638.4009 | dt 9.787 +type train | step 1980 | loss 137.3979 278.2426 406.8626 633.8906 911.4574 1289.6311 1775.7952 2530.5874 3555.4297 5405.5459 9062.2500 17118.7715 | lr 4.2e-04 | norm 10305.1865 | dt 9.777 +type train | step 1981 | loss 120.4598 242.8432 363.4668 572.3663 834.9433 1207.7889 1663.6089 2381.2683 3386.8572 5116.9375 8442.2090 15722.2725 | lr 4.2e-04 | norm 5630.6577 | dt 9.776 +type train | step 1982 | loss 117.1747 233.7796 349.2516 549.4371 806.5970 1160.4255 1605.3278 2283.8494 3243.8577 4884.9751 7988.7803 14757.0693 | lr 4.2e-04 | norm 5323.1968 | dt 9.779 +type train | step 1983 | loss 118.9716 236.0339 350.6877 548.9812 803.9526 1160.9999 1601.4939 2280.1670 3239.9417 4855.5093 7908.5342 14592.5000 | lr 4.2e-04 | norm 5479.4697 | dt 9.784 +type train | step 1984 | loss 113.3059 222.9572 336.5385 537.4651 793.7521 1162.4348 1619.7502 2332.8130 3317.3989 5010.9087 8212.0000 15128.7129 | lr 4.2e-04 | norm 6086.4648 | dt 9.780 +type train | step 1985 | loss 124.4975 246.3839 362.2802 563.4941 818.4397 1173.4209 1614.8706 2286.8872 3233.4138 4852.6187 7883.1387 14588.8457 | lr 4.2e-04 | norm 5717.7402 | dt 9.783 +type train | step 1986 | loss 123.8349 247.9746 365.2159 570.2092 823.2156 1183.7677 1617.6512 2300.8828 3243.1499 4836.3105 7946.8687 14786.2012 | lr 4.2e-04 | norm 6319.3135 | dt 9.769 +type train | step 1987 | loss 117.1289 234.4172 349.5798 546.5057 799.1440 1148.8928 1593.1188 2270.8679 3255.4292 4908.0366 8007.8750 14824.5723 | lr 4.2e-04 | norm 5159.1147 | dt 9.789 +type train | step 1988 | loss 127.8487 256.3979 375.4141 577.7156 833.0333 1191.1797 1628.4100 2293.8418 3239.2241 4820.8452 7893.2109 14643.8232 | lr 4.2e-04 | norm 5267.7256 | dt 9.779 +type train | step 1989 | loss 118.5892 235.4063 350.7607 552.3355 805.4982 1158.9091 1599.3428 2264.2332 3215.6958 4833.9688 7913.0566 14565.4668 | lr 4.2e-04 | norm 4956.4741 | dt 9.787 +type train | step 1990 | loss 117.2118 233.8441 351.4617 549.4588 806.9305 1158.6522 1604.7013 2284.2888 3270.8606 4929.3608 8062.0903 14813.5752 | lr 4.2e-04 | norm 5413.6118 | dt 9.801 +type train | step 1991 | loss 114.1764 230.7143 348.7393 550.6686 808.7698 1170.9291 1630.3917 2336.8311 3356.6030 5041.5078 8231.9238 15272.0615 | lr 4.2e-04 | norm 8697.0840 | dt 9.792 +type train | step 1992 | loss 119.7817 237.0114 354.5637 555.2809 811.3284 1168.8713 1611.3732 2302.1099 3277.9109 4956.9819 8132.2446 15059.5693 | lr 4.2e-04 | norm 4949.5864 | dt 9.787 +type train | step 1993 | loss 114.7628 227.8463 343.4374 547.4215 807.2936 1191.9535 1665.6768 2417.5852 3429.8828 5214.4346 8577.4707 15995.1787 | lr 4.2e-04 | norm 6385.1104 | dt 9.782 +type train | step 1994 | loss 124.6924 253.5486 378.0517 600.4579 876.4935 1276.6165 1754.4561 2527.1777 3560.7488 5330.7876 8650.2402 15978.0576 | lr 4.2e-04 | norm 7205.3018 | dt 9.782 +type train | step 1995 | loss 129.6964 258.3231 383.3220 593.8732 857.2659 1237.6104 1687.5460 2384.3257 3344.3469 5015.0771 8247.7568 15356.2754 | lr 4.2e-04 | norm 5990.4707 | dt 9.796 +type train | step 1996 | loss 141.9841 279.5721 412.3477 644.5230 922.3943 1349.5494 1847.4003 2631.6108 3658.0786 5489.9399 8998.3096 16859.1504 | lr 4.2e-04 | norm 7778.3779 | dt 9.795 +type train | step 1997 | loss 132.6047 265.6793 388.4864 603.7454 870.6937 1257.4917 1712.6556 2435.7876 3399.5310 5059.2319 8124.2363 15010.9629 | lr 4.2e-04 | norm 5839.6792 | dt 9.779 +type train | step 1998 | loss 120.8778 240.5072 360.0681 564.8535 822.6555 1189.3558 1642.0569 2350.8813 3344.1868 5064.0278 8361.1934 15567.4512 | lr 4.2e-04 | norm 5753.5474 | dt 9.773 +type train | step 1999 | loss 125.6734 250.0721 368.3730 579.9561 843.2244 1223.8240 1682.0388 2399.9722 3388.6741 5085.7402 8351.5176 15535.8428 | lr 4.2e-04 | norm 5636.2915 | dt 9.779 +type train | step 2000 | loss 129.9569 256.8399 371.9464 576.4457 842.1368 1233.2383 1709.1521 2457.1130 3442.7319 5147.9751 8461.3623 15713.6729 | lr 4.2e-04 | norm 5780.5874 | dt 9.770 +type train | step 2001 | loss 121.9351 242.4680 359.3414 566.5547 824.9233 1194.9332 1646.5496 2336.9028 3303.1885 4948.8271 8116.4365 14981.5312 | lr 4.2e-04 | norm 4770.5542 | dt 9.781 +type train | step 2002 | loss 120.9619 238.8835 360.5509 568.4093 829.6024 1195.6300 1641.4934 2330.8010 3317.1021 4983.2109 8134.1460 15129.6318 | lr 4.2e-04 | norm 5719.0654 | dt 9.771 +type train | step 2003 | loss 118.1032 236.4738 358.4092 567.1323 830.2203 1193.7891 1648.2543 2343.6736 3367.1528 5063.7988 8277.0742 15266.8115 | lr 4.2e-04 | norm 5820.1748 | dt 9.782 +type train | step 2004 | loss 127.2159 259.1260 390.7516 617.7729 901.5090 1291.4922 1767.4832 2492.9460 3501.3486 5219.3364 8466.4238 15682.9580 | lr 4.2e-04 | norm 6017.0229 | dt 9.765 +type train | step 2005 | loss 115.5706 231.4790 346.4379 543.7948 796.2960 1153.3763 1599.8989 2279.1606 3241.8579 4885.3970 8016.4639 14860.7842 | lr 4.2e-04 | norm 5517.6230 | dt 9.785 +type train | step 2006 | loss 127.4338 258.2940 380.8254 594.9158 863.9692 1241.2932 1706.2388 2419.2959 3391.4390 5058.4824 8236.1152 15172.2461 | lr 4.2e-04 | norm 5363.8589 | dt 9.789 +type train | step 2007 | loss 117.7415 233.3098 352.8065 557.2172 817.9360 1192.9912 1659.7072 2375.8545 3372.7688 5073.7471 8373.4209 15642.7949 | lr 4.2e-04 | norm 6276.2593 | dt 9.775 +type train | step 2008 | loss 120.2803 240.5243 361.3916 558.7890 814.5994 1168.9266 1609.6123 2273.1035 3217.1865 4829.6543 7904.0776 14737.9297 | lr 4.2e-04 | norm 5511.6621 | dt 9.782 +type train | step 2009 | loss 125.8105 252.1824 373.9869 580.1752 834.1063 1191.4172 1631.8016 2298.9380 3244.4138 4838.2373 7920.0059 14652.4326 | lr 4.2e-04 | norm 5819.9624 | dt 9.783 +type train | step 2010 | loss 136.6927 275.4602 403.5757 621.0684 892.3712 1271.0714 1720.2040 2429.0330 3388.7546 5052.4385 8242.4805 15251.8848 | lr 4.2e-04 | norm 5886.4834 | dt 9.763 +type train | step 2011 | loss 121.1711 242.1177 362.7169 567.6361 821.5707 1176.9939 1611.6477 2280.5938 3237.8142 4878.5127 7991.3037 14812.5820 | lr 4.2e-04 | norm 5071.5186 | dt 9.781 +type train | step 2012 | loss 117.4418 233.9379 351.2528 551.4494 804.0079 1152.6140 1586.8582 2253.5625 3203.9329 4818.5415 7905.4937 14526.2559 | lr 4.2e-04 | norm 5099.6533 | dt 9.796 +type train | step 2013 | loss 131.0002 268.2322 399.8236 623.1136 894.0387 1286.7781 1749.7151 2485.1699 3454.9172 5167.1934 8436.5557 15572.9375 | lr 4.2e-04 | norm 6387.4707 | dt 9.782 +type train | step 2014 | loss 124.6287 252.0124 371.5972 581.0767 842.4470 1209.1360 1661.5737 2353.2876 3334.0630 4968.2554 8072.0371 14840.2227 | lr 4.2e-04 | norm 7308.0601 | dt 9.781 +type train | step 2015 | loss 126.0448 252.2551 375.8329 588.6202 853.4275 1242.5071 1711.4658 2433.9126 3401.4836 5097.7500 8366.2666 15419.6797 | lr 4.2e-04 | norm 6915.9233 | dt 9.770 +type train | step 2016 | loss 119.0738 237.4154 362.8119 563.2888 827.4295 1199.5374 1655.3098 2374.8015 3378.5134 5084.1089 8317.9766 15254.7480 | lr 4.2e-04 | norm 5736.7593 | dt 9.783 +type train | step 2017 | loss 125.1863 245.4057 366.5963 574.8398 833.2817 1215.2777 1670.0378 2386.5337 3343.1904 5004.9526 8216.4072 15371.1309 | lr 4.2e-04 | norm 7232.7881 | dt 9.764 +type train | step 2018 | loss 116.8195 234.2343 351.1975 551.8574 808.1080 1167.5862 1614.0386 2298.2490 3286.1406 4971.6318 8181.7607 15216.0850 | lr 4.2e-04 | norm 5753.9614 | dt 9.795 +type train | step 2019 | loss 146.6007 293.8442 426.1482 641.5022 907.6647 1285.9681 1737.9424 2417.5649 3362.9629 4988.0605 8177.5088 15244.4355 | lr 4.2e-04 | norm 7945.9985 | dt 9.761 +type train | step 2020 | loss 114.5608 227.0361 345.9378 545.6143 801.7719 1170.5305 1621.6167 2320.0854 3307.9734 4987.1387 8182.4126 15040.8750 | lr 4.2e-04 | norm 5089.2393 | dt 9.775 +type train | step 2021 | loss 118.9829 241.0756 359.5630 564.6207 825.4366 1202.9255 1661.8369 2368.6836 3347.8330 4975.5820 8066.1992 14840.8213 | lr 4.2e-04 | norm 5310.9858 | dt 9.779 +type train | step 2022 | loss 127.2496 254.4727 375.6966 583.3456 842.1890 1205.1157 1635.8984 2306.4233 3230.9216 4800.5078 7753.6104 14222.1738 | lr 4.2e-04 | norm 4963.4619 | dt 9.779 +type train | step 2023 | loss 118.7940 235.8072 360.4071 553.7122 812.7872 1168.2858 1617.1572 2309.9177 3294.1509 4953.1582 8135.2275 15091.7354 | lr 4.2e-04 | norm 5643.8892 | dt 9.782 +type train | step 2024 | loss 115.6827 241.0836 369.9746 582.3187 854.9773 1229.0526 1699.9456 2458.4907 3471.7871 5270.1997 8713.0781 16240.0977 | lr 4.2e-04 | norm 7326.3955 | dt 9.795 +type train | step 2025 | loss 124.1601 246.5041 367.0667 577.1875 833.9760 1207.6018 1656.4786 2346.6128 3305.5225 4923.5415 8086.5977 15031.5674 | lr 4.2e-04 | norm 5959.8545 | dt 9.788 +type train | step 2026 | loss 116.8144 231.9030 347.9090 549.3624 802.9142 1164.1918 1612.1289 2302.1113 3289.2495 4922.1055 8074.1211 14935.4160 | lr 4.2e-04 | norm 5260.6084 | dt 9.783 +type train | step 2027 | loss 118.5998 236.1434 353.5048 557.0938 815.3560 1182.5042 1637.1462 2329.4924 3314.1958 4953.2246 8106.5562 14860.5811 | lr 4.2e-04 | norm 5331.3882 | dt 9.794 +type train | step 2028 | loss 121.4563 241.2334 361.5177 563.4210 821.7088 1182.3392 1636.1113 2333.3242 3316.5745 4986.1880 8156.4756 15125.7158 | lr 4.2e-04 | norm 5799.6245 | dt 9.786 +type train | step 2029 | loss 119.9908 237.2279 356.3700 561.7867 814.0292 1174.1603 1612.2871 2299.5059 3262.4998 4913.6719 8064.3301 15035.6758 | lr 4.2e-04 | norm 7017.2563 | dt 9.782 +type train | step 2030 | loss 143.3258 287.8023 416.8410 633.6177 900.2714 1291.0630 1760.8469 2507.7734 3455.2837 5077.7031 8170.4873 15097.3818 | lr 4.2e-04 | norm 6428.2349 | dt 9.752 +type train | step 2031 | loss 115.3610 230.9094 350.7304 557.6628 814.7871 1176.5238 1628.8784 2328.0137 3330.1162 5034.6660 8313.0264 15516.9980 | lr 4.2e-04 | norm 6845.6143 | dt 9.772 +type train | step 2032 | loss 113.2933 223.8763 341.6834 542.0404 799.9808 1162.1823 1613.2306 2305.4768 3297.4382 4948.7363 8051.1230 14780.3691 | lr 4.2e-04 | norm 4849.6777 | dt 9.794 +type train | step 2033 | loss 118.9703 235.5561 358.7801 563.7159 834.4952 1226.8793 1727.8768 2467.8057 3467.1641 5175.9546 8393.6973 15546.6377 | lr 4.2e-04 | norm 6721.1836 | dt 9.761 +type train | step 2034 | loss 118.6053 238.0105 354.9699 556.3389 814.4308 1175.4011 1625.9142 2324.6331 3281.5981 4911.1812 8055.7744 14844.4531 | lr 4.2e-04 | norm 5671.1279 | dt 9.774 +type train | step 2035 | loss 117.1855 231.8677 350.0231 552.9938 812.9154 1175.4358 1621.1241 2305.2976 3261.5078 4912.6592 8081.2393 15057.2988 | lr 4.2e-04 | norm 6229.7520 | dt 9.773 +type train | step 2036 | loss 118.7396 235.7834 352.9425 557.8698 816.5966 1180.5990 1624.1288 2325.4495 3312.1941 4976.0869 8117.7109 15041.6777 | lr 4.2e-04 | norm 5015.2100 | dt 9.784 +type train | step 2037 | loss 123.0177 247.0624 369.3855 582.1909 844.8848 1219.2247 1670.0916 2374.0405 3330.7085 4959.6309 8095.1509 14992.5879 | lr 4.2e-04 | norm 5864.7212 | dt 9.782 +type train | step 2038 | loss 131.3729 267.2473 393.1845 604.4507 873.3987 1241.5593 1697.3619 2395.5881 3394.8538 5069.7236 8258.2656 15231.9971 | lr 4.2e-04 | norm 5417.9468 | dt 9.778 +type train | step 2039 | loss 119.8116 238.0187 356.9531 559.5472 815.8819 1181.9036 1640.1172 2337.9006 3325.5417 4999.0898 8203.6660 15265.5273 | lr 4.2e-04 | norm 5026.3052 | dt 9.795 +type train | step 2040 | loss 112.0894 223.1261 338.1100 536.8868 789.9872 1154.9003 1605.8401 2304.9758 3299.0767 4988.0796 8235.2773 15289.9775 | lr 4.2e-04 | norm 4951.6729 | dt 9.787 +type train | step 2041 | loss 118.0536 236.5381 354.7922 550.0146 803.5470 1164.0934 1612.1808 2312.8171 3299.6685 4982.5444 8170.4580 15065.7822 | lr 4.2e-04 | norm 4986.7095 | dt 9.779 +type train | step 2042 | loss 119.9172 241.4207 360.3851 565.6031 828.8499 1193.8073 1647.7913 2355.4258 3354.7300 5022.2700 8183.7056 15055.8340 | lr 4.2e-04 | norm 5276.8999 | dt 9.798 +type train | step 2043 | loss 118.9962 239.8060 357.5006 560.4571 819.1823 1176.4900 1617.6757 2303.4976 3269.3491 4916.9497 8094.0479 14912.3750 | lr 4.2e-04 | norm 4966.7300 | dt 9.798 +type train | step 2044 | loss 122.8944 245.1055 373.0836 581.1208 846.9209 1214.1094 1667.7958 2358.6694 3346.5020 5013.5195 8156.9478 15052.3184 | lr 4.2e-04 | norm 5652.6445 | dt 9.794 +type train | step 2045 | loss 112.9455 223.1986 339.1526 539.3633 789.3464 1142.9006 1588.5598 2277.6411 3274.3438 4959.9761 8160.4429 15198.3105 | lr 4.2e-04 | norm 6187.9634 | dt 9.775 +type train | step 2046 | loss 119.6645 238.4825 360.9061 562.6574 815.7320 1177.0238 1617.1616 2306.3108 3256.4631 4929.9185 8173.5303 15351.5469 | lr 4.2e-04 | norm 5379.3701 | dt 9.790 +type train | step 2047 | loss 145.1465 295.1021 438.3163 655.3317 938.3898 1356.0228 1848.8058 2614.7212 3666.9519 5425.3477 8756.8975 16010.4512 | lr 4.1e-04 | norm 6522.4941 | dt 9.772 +type train | step 2048 | loss 118.7835 238.7586 434.9481 576.1521 840.9290 1202.5977 1660.2383 2358.7390 3373.5662 5107.5430 8457.9482 15737.3535 | lr 4.1e-04 | norm 5911.0308 | dt 9.815 +type train | step 2049 | loss 127.5782 256.7402 425.1493 592.9047 859.0773 1230.8015 1684.2324 2382.5002 3338.0144 4965.7856 8079.3096 14888.2695 | lr 4.1e-04 | norm 5892.5708 | dt 9.794 +type train | step 2050 | loss 115.9503 232.4271 386.6062 554.1179 815.5380 1177.5320 1627.6901 2309.1301 3291.4062 4930.0005 8021.1855 14679.0586 | lr 4.1e-04 | norm 4990.3940 | dt 9.803 +type train | step 2051 | loss 117.6154 233.8381 392.3459 553.1329 807.2159 1165.3142 1606.5648 2286.1760 3242.1658 4846.9795 7929.1035 14689.0859 | lr 4.1e-04 | norm 5211.7153 | dt 9.801 +type train | step 2052 | loss 121.1156 240.6290 395.4824 560.5629 813.6469 1177.8324 1619.0813 2304.2288 3276.1704 4913.4404 8040.0151 14870.6240 | lr 4.1e-04 | norm 5078.4595 | dt 9.802 +type train | step 2053 | loss 125.3861 249.8769 402.8709 577.2354 835.7296 1191.9219 1627.4203 2299.0891 3256.5195 4864.7178 7934.4390 14545.6768 | lr 4.1e-04 | norm 4427.1577 | dt 9.781 +type train | step 2054 | loss 117.9704 238.7228 392.1808 561.3804 814.9644 1179.6222 1626.6857 2318.9004 3289.5642 4954.6816 8119.9521 15031.7822 | lr 4.1e-04 | norm 5221.8325 | dt 9.773 +type train | step 2055 | loss 118.9677 239.4042 389.1277 562.7257 823.4857 1192.4370 1652.2148 2358.9438 3347.3706 4985.2524 8158.1069 15172.5723 | lr 4.1e-04 | norm 5812.6528 | dt 9.781 +type train | step 2056 | loss 116.6064 233.8205 382.9533 557.6311 812.3637 1179.2828 1628.8237 2339.3979 3325.1257 4961.3447 8155.4990 15198.4551 | lr 4.1e-04 | norm 7191.9912 | dt 9.798 +type train | step 2057 | loss 118.8682 236.6422 381.8597 551.4213 807.1541 1153.1877 1589.3116 2259.4622 3232.3877 4836.1655 7865.0381 14495.9189 | lr 4.1e-04 | norm 5569.4326 | dt 9.792 +type train | step 2058 | loss 119.2664 236.3942 387.5226 556.5544 815.4879 1188.7625 1641.6219 2353.5186 3318.8135 4951.3159 8043.3071 14753.5137 | lr 4.1e-04 | norm 5913.1846 | dt 9.788 +type train | step 2059 | loss 124.8529 246.5887 394.2020 570.7292 827.5464 1180.6016 1623.5372 2293.7026 3254.8569 4848.8945 7863.2661 14489.0176 | lr 4.1e-04 | norm 5920.7427 | dt 9.772 +type train | step 2060 | loss 116.9667 234.8934 387.7784 552.8335 809.0589 1160.8826 1604.0485 2285.7959 3261.7766 4940.6221 8122.7446 15038.1055 | lr 4.1e-04 | norm 6022.1821 | dt 9.790 +type train | step 2061 | loss 114.8292 235.6719 393.9415 582.2493 847.6525 1222.7052 1679.7686 2387.6431 3356.4683 4992.9399 8080.7729 14851.0264 | lr 4.1e-04 | norm 7846.1191 | dt 9.779 +type train | step 2062 | loss 113.3615 223.9679 373.9256 533.2850 786.8805 1141.0898 1578.1011 2256.5911 3240.4805 4908.5498 8103.6338 15084.8428 | lr 4.1e-04 | norm 6361.7661 | dt 9.778 +type train | step 2063 | loss 123.2573 248.0173 397.2485 573.6642 830.6203 1206.3585 1652.5894 2356.0312 3320.4905 4955.3853 8062.9653 14854.3281 | lr 4.1e-04 | norm 5189.6289 | dt 9.767 +type train | step 2064 | loss 115.8634 229.4009 370.1032 537.6205 787.2121 1146.3517 1588.5482 2279.2822 3259.2822 4905.3276 8048.2930 14900.2695 | lr 4.1e-04 | norm 5200.8174 | dt 9.781 +type train | step 2065 | loss 124.0112 246.3205 406.4586 574.3464 835.4691 1199.4232 1647.8306 2336.5815 3313.0225 4938.8257 8051.8418 14795.4814 | lr 4.1e-04 | norm 5190.4185 | dt 9.789 +type train | step 2066 | loss 123.5207 245.0419 395.5573 571.1893 829.2529 1200.0688 1650.5795 2346.6941 3328.4688 4990.4194 8136.2061 15069.5654 | lr 4.1e-04 | norm 5305.5405 | dt 9.784 +type train | step 2067 | loss 96.3903 188.7864 325.0317 484.2738 736.6403 1094.5886 1552.4401 2260.6116 3300.2534 4941.7158 7980.5420 14555.5635 | lr 4.1e-04 | norm 8748.0537 | dt 9.790 +type train | step 2068 | loss 120.1676 233.8020 379.0624 551.9529 804.4962 1169.6434 1608.6082 2293.7632 3256.2908 4836.1377 7881.2803 14537.2646 | lr 4.1e-04 | norm 4966.5752 | dt 9.762 +type train | step 2069 | loss 122.8298 243.4308 398.6634 573.4763 834.7818 1201.0399 1646.7207 2346.3945 3339.9197 5018.1274 8239.5830 15257.4277 | lr 4.1e-04 | norm 5303.8345 | dt 9.773 +type train | step 2070 | loss 111.2141 221.8902 415.7062 538.0617 792.4742 1159.6420 1607.8308 2311.2788 3298.2642 4947.8911 8137.0381 15053.0488 | lr 4.1e-04 | norm 5404.0879 | dt 9.784 +type train | step 2071 | loss 112.2530 221.0633 379.5338 531.6532 781.2267 1129.2811 1564.3164 2239.4971 3220.0161 4869.3457 8003.7725 14803.8643 | lr 4.1e-04 | norm 5166.4468 | dt 9.781 +type train | step 2072 | loss 113.8363 227.0351 390.1143 534.5759 782.3864 1135.6284 1572.1202 2260.2844 3216.8293 4853.7275 7977.6895 14771.4902 | lr 4.1e-04 | norm 6112.5078 | dt 9.768 +type train | step 2073 | loss 120.5956 238.6669 400.6388 556.5562 818.2443 1184.0977 1626.8911 2327.0618 3297.0181 4951.5732 8098.6763 14976.8672 | lr 4.1e-04 | norm 5097.9150 | dt 9.812 +type train | step 2074 | loss 120.9609 238.7518 399.6894 563.8364 828.5494 1188.0935 1633.8762 2300.3982 3263.9399 4891.2231 7985.2671 14731.8125 | lr 4.1e-04 | norm 4904.8413 | dt 9.809 +type train | step 2075 | loss 136.2262 273.6251 443.2125 633.1081 915.7423 1307.7861 1784.1475 2533.4595 3556.3057 5346.2085 8765.3008 16423.6719 | lr 4.1e-04 | norm 7487.6152 | dt 9.784 +type train | step 2076 | loss 119.8975 233.9778 387.6567 543.3924 795.3544 1160.4619 1603.1653 2294.7241 3260.2891 4950.7754 8186.1221 15305.0508 | lr 4.1e-04 | norm 5581.4629 | dt 9.785 +type train | step 2077 | loss 112.4323 224.2265 397.9420 542.3298 794.7827 1154.9512 1595.2003 2285.2100 3265.5535 4886.5391 7984.0015 14717.9014 | lr 4.1e-04 | norm 5062.5649 | dt 9.787 +type train | step 2078 | loss 114.8690 228.1871 386.4799 538.1005 792.0745 1151.1010 1597.7239 2289.1929 3254.0283 4879.2783 8019.2070 14775.1084 | lr 4.1e-04 | norm 5216.8735 | dt 9.771 +type train | step 2079 | loss 116.2910 232.2093 391.5266 546.8948 801.5806 1164.9106 1611.9211 2306.5723 3280.9470 4922.2280 8046.2021 14850.8838 | lr 4.1e-04 | norm 5031.7485 | dt 9.795 +type train | step 2080 | loss 129.4776 258.2475 427.1667 613.8856 900.1566 1308.1619 1799.4133 2593.1064 3646.6726 5447.4824 8958.8926 16563.5430 | lr 4.1e-04 | norm 7544.3848 | dt 9.770 +type train | step 2081 | loss 122.2239 242.4646 404.2131 561.4984 819.3280 1194.8464 1645.4666 2357.6775 3322.0957 4997.2852 8165.3560 15144.3047 | lr 4.1e-04 | norm 5722.5327 | dt 9.771 +type train | step 2082 | loss 116.8557 233.6796 392.5348 544.4039 797.9677 1158.4922 1602.3555 2287.3472 3258.6941 4847.5117 7907.6816 14564.1777 | lr 4.1e-04 | norm 5853.6460 | dt 9.780 +type train | step 2083 | loss 119.5846 240.1086 406.3183 565.0109 824.7864 1192.8439 1638.8564 2332.9856 3299.6833 4956.5562 8073.2197 14830.6699 | lr 4.1e-04 | norm 5450.0088 | dt 9.784 +type train | step 2084 | loss 125.7271 251.9765 410.2385 569.7231 823.0733 1197.2863 1638.3757 2323.7349 3265.5071 4874.9253 7936.7480 14604.9023 | lr 4.1e-04 | norm 5270.1489 | dt 9.775 +type train | step 2085 | loss 137.4466 280.8815 450.5956 634.6092 907.9538 1316.5344 1798.1837 2544.7778 3548.0437 5304.6885 8553.2646 15628.0967 | lr 4.1e-04 | norm 6708.7549 | dt 9.756 +type train | step 2086 | loss 118.1247 237.6458 393.9118 559.7411 818.8999 1182.3228 1624.1921 2309.7097 3303.4241 4931.9092 8045.1836 14836.1992 | lr 4.1e-04 | norm 5102.5366 | dt 9.777 +type train | step 2087 | loss 120.8765 241.0044 395.1515 560.8760 823.3886 1187.2405 1638.4517 2334.6226 3315.1760 4993.1260 8146.3906 15061.0664 | lr 4.1e-04 | norm 6048.7544 | dt 9.790 +type train | step 2088 | loss 126.8365 255.6849 404.8116 579.7986 839.1010 1192.6187 1637.4900 2322.7458 3295.5295 4948.1543 8075.9653 14870.1494 | lr 4.1e-04 | norm 7131.8989 | dt 9.783 +type train | step 2089 | loss 115.7393 233.8085 403.4784 560.8003 822.7278 1182.0562 1636.1442 2330.6279 3320.2393 4972.9072 8112.5415 14922.6836 | lr 4.1e-04 | norm 5146.4243 | dt 9.798 +type train | step 2090 | loss 119.8450 238.7423 394.8230 553.4907 808.8454 1178.3832 1628.5679 2331.5405 3310.8289 4992.6284 8200.6973 15233.6318 | lr 4.1e-04 | norm 5419.6440 | dt 9.782 +type train | step 2091 | loss 112.7088 223.6164 380.7175 529.7510 780.2588 1126.9434 1558.2638 2225.6155 3197.5356 4820.0396 7885.1470 14537.4180 | lr 4.1e-04 | norm 5366.4946 | dt 9.785 +type train | step 2092 | loss 119.3544 238.8607 398.6599 554.2192 812.3895 1169.9899 1616.4479 2300.6526 3254.2478 4850.6465 7908.1514 14653.7100 | lr 4.1e-04 | norm 6102.5854 | dt 9.770 +type train | step 2093 | loss 116.2451 230.4012 385.5913 543.6102 796.3656 1148.8279 1589.3422 2267.9055 3247.4893 4870.2236 7980.5771 14761.9072 | lr 4.1e-04 | norm 4834.1343 | dt 9.780 +type train | step 2094 | loss 118.9428 236.9444 391.4740 553.9764 806.6197 1162.6155 1606.4822 2292.9185 3257.2727 4888.7119 8030.2192 14905.2676 | lr 4.1e-04 | norm 5341.4780 | dt 9.782 +type train | step 2095 | loss 122.4912 243.3153 400.4174 568.4347 826.9343 1193.6390 1636.7517 2314.4995 3280.5442 4913.8984 8058.6704 14940.9688 | lr 4.1e-04 | norm 5455.0562 | dt 9.775 +type train | step 2096 | loss 125.3913 247.8937 403.4976 567.1247 823.9431 1182.9994 1608.7543 2269.0205 3180.8435 4714.7695 7634.9692 14080.5820 | lr 4.1e-04 | norm 5884.8726 | dt 9.771 +type train | step 2097 | loss 117.9664 233.2338 389.9197 548.6761 810.7852 1184.5403 1642.2269 2373.4663 3371.4229 5069.2749 8291.4102 15208.6680 | lr 4.1e-04 | norm 5042.5054 | dt 9.770 +type train | step 2098 | loss 110.7544 217.8201 368.9674 529.3195 779.5905 1135.5925 1580.6321 2262.2063 3233.5164 4832.0903 7917.9800 14543.5850 | lr 4.1e-04 | norm 4806.5576 | dt 9.771 +type train | step 2099 | loss 123.5182 247.1429 406.3687 573.1537 834.6403 1216.8577 1674.7986 2412.0112 3386.8345 5064.2480 8270.1826 15303.6123 | lr 4.1e-04 | norm 5780.6206 | dt 9.772 +type train | step 2100 | loss 118.9479 237.6572 386.2906 559.4650 815.5355 1185.2458 1643.4397 2352.4836 3332.9529 4984.4160 8183.3608 15257.1729 | lr 4.1e-04 | norm 5285.9038 | dt 9.781 +type train | step 2101 | loss 119.2918 236.4769 391.1519 572.3423 834.8018 1217.0284 1668.4053 2379.0225 3337.4448 4997.5273 8207.3379 15361.0264 | lr 4.1e-04 | norm 6456.8682 | dt 9.776 +type train | step 2102 | loss 126.3209 255.6325 410.0061 583.3684 850.2656 1224.6052 1674.8157 2368.0212 3362.4321 5007.8662 8191.5381 15158.4912 | lr 4.1e-04 | norm 6521.7202 | dt 9.783 +type train | step 2103 | loss 125.6389 252.1692 404.4611 570.2700 827.0016 1186.7278 1635.8419 2355.4167 3340.6643 5037.4512 8344.5742 15571.4814 | lr 4.1e-04 | norm 6197.9673 | dt 9.762 +type train | step 2104 | loss 107.0967 211.5598 360.2240 517.0118 763.8394 1114.8810 1549.0533 2222.2705 3207.7893 4842.8716 7961.3281 14786.5996 | lr 4.1e-04 | norm 5198.1958 | dt 9.777 +type train | step 2105 | loss 128.8282 261.2950 425.2650 614.3301 895.7831 1301.7032 1786.8536 2564.4814 3620.3047 5443.2017 8948.7451 16797.2305 | lr 4.1e-04 | norm 9880.2803 | dt 9.763 +type train | step 2106 | loss 120.2489 236.0140 390.1126 567.9036 826.4489 1219.3860 1682.0469 2426.3718 3411.5410 5139.2051 8427.5820 15559.6416 | lr 4.1e-04 | norm 6348.5723 | dt 9.775 +type train | step 2107 | loss 120.1968 241.1774 389.7449 559.6761 820.7962 1190.8667 1641.1830 2353.2212 3318.5972 4996.1851 8164.0391 15083.6924 | lr 4.1e-04 | norm 5518.1606 | dt 9.790 +type train | step 2108 | loss 113.7156 227.7748 374.2845 541.5387 797.5308 1157.4542 1616.3853 2324.9175 3309.6562 5015.4888 8204.5078 15252.1826 | lr 4.1e-04 | norm 6333.2095 | dt 9.779 +type train | step 2109 | loss 119.6544 243.9884 397.4848 567.6176 830.2196 1205.6019 1663.8142 2384.6577 3381.6011 5089.6724 8366.6143 15518.9092 | lr 4.1e-04 | norm 5497.1484 | dt 9.779 +type train | step 2110 | loss 117.7065 230.5157 377.1924 546.2764 800.0687 1167.4479 1617.0250 2330.8584 3307.4497 4965.0117 8125.7212 15064.7979 | lr 4.1e-04 | norm 5698.3545 | dt 9.771 +type train | step 2111 | loss 124.4311 252.2946 416.6708 612.6411 888.7045 1285.2848 1755.2257 2504.2163 3523.6079 5279.7056 8637.5469 15934.7617 | lr 4.1e-04 | norm 7114.9521 | dt 9.770 +type train | step 2112 | loss 115.5433 228.6574 375.1788 538.3107 790.8853 1150.7742 1589.6388 2264.9441 3205.7905 4797.3105 7856.6758 14630.1807 | lr 4.1e-04 | norm 5477.2349 | dt 9.778 +type train | step 2113 | loss 116.8129 232.2831 371.4399 543.6697 796.9481 1174.5331 1638.5876 2352.1160 3313.8037 4996.9209 8205.3340 15264.8447 | lr 4.1e-04 | norm 5626.5513 | dt 9.775 +type train | step 2114 | loss 121.1272 239.8152 386.8938 569.1116 826.9139 1200.3739 1644.1040 2336.7908 3283.7952 4920.3774 7984.9810 14810.2412 | lr 4.1e-04 | norm 6664.0088 | dt 9.780 +type train | step 2115 | loss 109.3392 216.3237 354.4354 520.7343 772.2797 1116.8707 1549.1439 2211.9470 3180.6260 4793.4775 7880.4790 14524.0625 | lr 4.1e-04 | norm 5381.8276 | dt 9.790 +type train | step 2116 | loss 119.8620 239.8933 383.2260 552.5940 803.9746 1154.8502 1584.9187 2245.3442 3197.6357 4771.3525 7832.8213 14471.3936 | lr 4.1e-04 | norm 4748.4307 | dt 9.807 +type train | step 2117 | loss 119.6339 239.5795 382.9456 557.8733 817.1227 1171.8324 1616.9740 2306.9480 3277.5461 4936.6484 8042.8091 14816.3145 | lr 4.1e-04 | norm 4647.1733 | dt 9.802 +type train | step 2118 | loss 114.6163 224.9772 369.2613 540.7296 788.5762 1142.3582 1583.6823 2252.4675 3197.0376 4822.7729 7973.7500 14896.7070 | lr 4.1e-04 | norm 6329.4614 | dt 9.796 +type train | step 2119 | loss 114.5587 230.2921 376.3008 552.9508 808.2737 1161.3247 1609.7709 2286.5640 3277.1006 4929.8677 8129.5981 15042.5176 | lr 4.1e-04 | norm 5842.2798 | dt 9.792 +type train | step 2120 | loss 110.9572 221.7001 367.0423 540.8073 798.6332 1161.7922 1616.2357 2308.9026 3304.8359 4995.2529 8229.8652 15258.7637 | lr 4.1e-04 | norm 5579.5942 | dt 9.791 +type train | step 2121 | loss 128.6786 258.9402 407.2507 587.7289 850.7216 1219.8226 1672.9536 2364.9048 3343.5256 5011.5928 8222.7275 15262.8652 | lr 4.1e-04 | norm 5496.3335 | dt 9.794 +type train | step 2122 | loss 115.4709 229.3356 371.5056 546.5742 800.7318 1166.7164 1614.2604 2305.5505 3278.0645 4915.5913 8070.2080 14926.6914 | lr 4.1e-04 | norm 5334.6191 | dt 9.788 +type train | step 2123 | loss 122.8059 243.4915 389.2990 566.4028 826.2548 1199.0992 1650.8865 2369.7388 3327.2742 4992.2700 8142.1436 15123.6602 | lr 4.1e-04 | norm 6069.1099 | dt 9.775 +type train | step 2124 | loss 119.1925 236.5885 379.0200 551.3197 808.4551 1166.6938 1614.4612 2306.5095 3294.5864 4978.0000 8171.5586 15151.6670 | lr 4.1e-04 | norm 5271.2275 | dt 9.794 +type train | step 2125 | loss 118.6656 236.7309 379.8662 555.0792 815.8628 1179.3463 1631.1873 2324.3982 3316.2102 4976.8340 8109.8481 14865.6055 | lr 4.1e-04 | norm 5109.3774 | dt 9.792 +type train | step 2126 | loss 130.5953 268.6259 428.4302 622.1233 917.2266 1307.7744 1820.3896 2586.7896 3674.7756 5434.5908 8626.6895 15502.7822 | lr 4.1e-04 | norm 9714.1533 | dt 9.789 +type train | step 2127 | loss 133.0019 270.2892 422.8472 621.9337 899.9246 1278.8351 1742.2736 2461.1370 3432.3447 5105.4355 8336.4551 15399.0869 | lr 4.1e-04 | norm 9924.3115 | dt 9.775 +type train | step 2128 | loss 121.0928 243.2318 390.4530 570.5915 836.5616 1199.4816 1648.2466 2332.9619 3285.4224 4923.2100 8031.5825 14887.2197 | lr 4.0e-04 | norm 5541.4780 | dt 9.772 +type train | step 2129 | loss 109.6323 216.8755 364.4334 539.8461 796.7356 1170.3185 1632.0948 2359.5471 3387.2783 5102.2378 8387.7021 15526.2715 | lr 4.0e-04 | norm 7494.5947 | dt 9.778 +type train | step 2130 | loss 110.9664 222.4687 361.6451 529.5347 781.0363 1131.2213 1572.1583 2256.4482 3242.8728 4915.0596 8118.7070 15129.7539 | lr 4.0e-04 | norm 6326.7358 | dt 9.778 +type train | step 2131 | loss 121.2239 231.3831 365.1844 527.9088 784.8154 1140.3091 1579.4493 2283.3054 3228.6577 4800.3276 7781.6597 14302.3711 | lr 4.0e-04 | norm 11673.5215 | dt 9.774 +type train | step 2132 | loss 126.1060 253.9283 400.5008 588.1688 850.3671 1218.8080 1661.0619 2350.6077 3308.4446 5001.8770 8188.2969 15217.5215 | lr 4.0e-04 | norm 6375.4414 | dt 9.768 +type train | step 2133 | loss 116.9843 233.2712 372.1725 549.6808 801.8737 1158.4188 1599.8745 2290.4248 3248.9934 4908.7275 8126.9688 15178.8672 | lr 4.0e-04 | norm 5996.6821 | dt 9.775 +type train | step 2134 | loss 117.6543 237.3395 377.9859 564.4302 830.4560 1205.2655 1670.0077 2379.6968 3373.0837 5048.8984 8242.5439 15161.8467 | lr 4.0e-04 | norm 5261.6772 | dt 9.793 +type train | step 2135 | loss 116.4159 233.2476 371.8715 561.8369 821.8390 1207.8079 1670.4009 2411.9502 3431.3445 5154.5034 8513.2988 15864.0264 | lr 4.0e-04 | norm 6437.2612 | dt 9.777 +type train | step 2136 | loss 114.6578 228.3932 364.7000 541.8102 792.6100 1148.3688 1586.9398 2262.2178 3230.5967 4831.8027 7918.1284 14614.5420 | lr 4.0e-04 | norm 5045.6021 | dt 9.781 +type train | step 2137 | loss 109.7920 219.2899 356.1453 528.5558 778.2291 1146.8435 1593.0909 2299.7009 3288.4834 4949.7793 8117.7495 15004.9336 | lr 4.0e-04 | norm 5234.7563 | dt 9.786 +type train | step 2138 | loss 110.4628 222.1510 359.9261 537.9253 795.8101 1149.0862 1602.1431 2287.9683 3281.8953 4921.6138 7988.1484 14678.8945 | lr 4.0e-04 | norm 5522.9185 | dt 9.781 +type train | step 2139 | loss 122.4183 246.1879 390.0025 574.4218 842.4252 1223.1726 1693.2863 2425.2632 3453.1553 5181.6929 8422.3789 15442.0635 | lr 4.0e-04 | norm 5194.3853 | dt 9.773 +type train | step 2140 | loss 109.1750 217.8036 352.6310 525.6475 779.7421 1132.3186 1575.3867 2256.1089 3249.0054 4912.7139 8044.5508 14813.3086 | lr 4.0e-04 | norm 4919.1270 | dt 9.791 +type train | step 2141 | loss 110.4268 220.0777 355.6274 527.1914 773.1585 1126.2328 1567.5270 2252.9070 3220.1465 4839.5952 7903.6094 14544.8506 | lr 4.0e-04 | norm 4548.9102 | dt 9.773 +type train | step 2142 | loss 139.3939 281.4840 426.7069 620.8047 888.9960 1251.9158 1698.1379 2395.9065 3389.9807 5065.8018 8206.4170 14964.3408 | lr 4.0e-04 | norm 13171.4043 | dt 9.770 +type train | step 2143 | loss 131.4699 267.4068 415.9863 607.2552 875.4320 1235.5684 1684.9521 2375.5828 3373.6938 5020.2964 8157.8389 14958.9893 | lr 4.0e-04 | norm 10109.1650 | dt 9.786 +type train | step 2144 | loss 114.1406 229.2833 368.5489 545.1085 804.0053 1157.5349 1595.3083 2274.1243 3246.1157 4874.6782 8016.4907 14909.9561 | lr 4.0e-04 | norm 5665.1187 | dt 9.798 +type train | step 2145 | loss 118.3525 235.1861 374.9774 549.5254 805.9977 1171.9253 1619.0554 2322.8755 3292.9751 4938.4004 8075.7397 14928.6289 | lr 4.0e-04 | norm 5805.5435 | dt 9.772 +type train | step 2146 | loss 116.9299 233.1075 371.0025 548.1724 799.8549 1160.7209 1601.7308 2286.8247 3259.5703 4859.0103 7926.2681 14671.2109 | lr 4.0e-04 | norm 5575.9546 | dt 9.783 +type train | step 2147 | loss 116.4694 232.2606 374.0347 551.5178 803.9943 1156.3074 1588.4293 2254.7903 3208.5471 4814.0557 7883.6885 14509.5127 | lr 4.0e-04 | norm 5336.4487 | dt 9.779 +type train | step 2148 | loss 111.2653 221.7723 356.7906 533.1740 784.6496 1137.2643 1574.9160 2245.7971 3231.9553 4853.9854 7938.8320 14679.3320 | lr 4.0e-04 | norm 5177.4590 | dt 9.799 +type train | step 2149 | loss 106.6107 213.5038 344.0268 519.4161 768.9913 1144.5933 1603.3770 2343.4468 3344.4487 5031.2339 8334.4512 15596.4893 | lr 4.0e-04 | norm 5683.7773 | dt 9.768 +type train | step 2150 | loss 110.9474 218.7025 353.9434 525.0885 770.2561 1110.7040 1539.0480 2191.7207 3138.8687 4709.7451 7759.6167 14343.8662 | lr 4.0e-04 | norm 4729.6733 | dt 9.791 +type train | step 2151 | loss 122.6568 246.3094 381.5126 566.4187 828.9508 1207.6571 1677.7775 2423.6594 3401.3079 5168.3164 8416.2822 15497.1533 | lr 4.0e-04 | norm 6492.7051 | dt 9.765 +type train | step 2152 | loss 125.7736 251.7861 391.4263 572.7108 831.9327 1188.3768 1635.8458 2318.6614 3296.1396 4947.8799 8131.2349 15070.6787 | lr 4.0e-04 | norm 5606.6836 | dt 9.789 +type train | step 2153 | loss 114.1102 228.8955 361.9889 538.4675 787.4703 1132.4673 1569.3998 2242.9546 3213.3281 4824.5918 7929.8096 14737.6797 | lr 4.0e-04 | norm 5020.9604 | dt 9.783 +type train | step 2154 | loss 102.8320 219.0372 380.1659 576.2129 849.9308 1212.6753 1697.4624 2424.9570 3532.7590 5340.6108 8743.5137 16232.6348 | lr 4.0e-04 | norm 10314.7275 | dt 9.789 +type train | step 2155 | loss 107.0471 231.9975 394.2692 602.4872 887.6722 1248.9823 1739.4392 2468.4651 3610.0425 5429.3916 8928.8652 16452.4414 | lr 4.0e-04 | norm 11063.7080 | dt 9.798 +type train | step 2156 | loss 112.5039 222.9736 363.2136 545.8789 803.8123 1179.3289 1630.9855 2364.1304 3320.3362 5000.1982 8256.6934 15289.6670 | lr 4.0e-04 | norm 7618.0493 | dt 9.778 +type train | step 2157 | loss 117.6158 236.7047 374.6740 554.2969 812.8336 1195.0282 1669.8524 2418.9678 3417.2222 5125.3853 8406.4395 15685.4727 | lr 4.0e-04 | norm 8021.8735 | dt 9.780 +type train | step 2158 | loss 118.2688 237.9950 376.4066 558.4362 812.7495 1166.8962 1610.1643 2281.2900 3241.4407 4856.3760 7940.2002 14691.7236 | lr 4.0e-04 | norm 6177.6455 | dt 9.787 +type train | step 2159 | loss 110.7994 221.4990 353.7669 527.6272 778.3553 1127.3806 1571.0221 2248.1968 3229.9790 4850.6631 7920.4697 14639.0127 | lr 4.0e-04 | norm 5881.8403 | dt 9.798 +type train | step 2160 | loss 128.9190 260.0716 400.1080 594.2551 863.7921 1237.5833 1685.5103 2364.9661 3301.9067 4892.6396 7907.4688 14607.8301 | lr 4.0e-04 | norm 6958.4844 | dt 9.766 +type train | step 2161 | loss 113.3082 227.7083 361.6179 540.4532 794.2176 1147.2383 1589.5929 2263.5889 3228.8970 4848.1421 7925.2085 14544.5332 | lr 4.0e-04 | norm 5228.0503 | dt 9.781 +type train | step 2162 | loss 112.9442 223.3730 355.2605 533.7205 788.4021 1149.3760 1598.4180 2295.3345 3301.7566 4999.0103 8220.3877 15238.6133 | lr 4.0e-04 | norm 5901.9253 | dt 9.791 +type train | step 2163 | loss 125.3553 251.4877 385.7175 574.0910 829.4561 1195.0403 1641.3405 2338.6824 3313.4583 4981.2427 8171.6582 15253.7510 | lr 4.0e-04 | norm 5563.0503 | dt 9.791 +type train | step 2164 | loss 131.3717 263.5486 405.7352 600.8025 866.9019 1247.2019 1705.4503 2418.6450 3394.1406 5061.3408 8236.6016 15067.0283 | lr 4.0e-04 | norm 5269.4019 | dt 9.774 +type train | step 2165 | loss 116.1469 232.9901 374.5508 559.8448 820.9383 1175.7559 1621.5643 2304.8638 3305.7515 4978.9492 8183.0483 15196.8613 | lr 4.0e-04 | norm 6584.1904 | dt 9.805 +type train | step 2166 | loss 105.3221 208.3286 340.5450 516.2534 769.9868 1123.9955 1572.2250 2260.8564 3259.6836 4938.1489 8169.2808 15201.9512 | lr 4.0e-04 | norm 6419.7354 | dt 9.781 +type train | step 2167 | loss 113.6001 225.2443 356.1761 533.0338 782.5171 1138.0503 1578.5023 2258.0288 3225.2705 4881.3071 8022.7437 14892.6689 | lr 4.0e-04 | norm 5915.7119 | dt 9.778 +type train | step 2168 | loss 119.0540 239.5808 377.5792 561.6586 820.8887 1189.3611 1637.2112 2347.0945 3316.8787 4983.2041 8211.4014 15380.3486 | lr 4.0e-04 | norm 6654.0464 | dt 9.786 +type train | step 2169 | loss 124.1879 251.8979 388.3583 584.7181 845.8054 1235.7566 1688.6143 2406.7695 3367.0876 5075.5361 8322.0439 15712.6807 | lr 4.0e-04 | norm 7493.7944 | dt 9.771 +type train | step 2170 | loss 128.6249 258.1522 387.1936 572.6134 837.8184 1226.2501 1696.9237 2414.1775 3418.5596 5104.1431 8242.5215 14994.7197 | lr 4.0e-04 | norm 5926.7329 | dt 9.779 +type train | step 2171 | loss 122.6810 246.0650 384.8500 573.8083 835.7719 1203.8782 1655.7249 2358.8711 3330.1226 4950.3779 8075.1997 14802.1816 | lr 4.0e-04 | norm 5465.4458 | dt 9.797 +type train | step 2172 | loss 107.3246 213.2293 342.5975 515.7697 763.1827 1102.3513 1535.6233 2194.6714 3149.4634 4728.6167 7720.6880 14271.0166 | lr 4.0e-04 | norm 4836.6729 | dt 9.793 +type train | step 2173 | loss 118.1226 236.2949 365.3239 544.7973 801.4736 1168.0217 1620.4563 2317.4014 3296.0017 4913.6377 7983.6885 14609.1406 | lr 4.0e-04 | norm 4666.3872 | dt 9.777 +type train | step 2174 | loss 127.6335 254.2267 393.6297 581.6430 854.8647 1267.1305 1763.2367 2507.7305 3486.7151 5134.7065 8331.0801 15333.7803 | lr 4.0e-04 | norm 6244.6025 | dt 9.771 +type train | step 2175 | loss 120.8126 242.4891 385.5098 582.6836 849.3597 1214.1746 1669.5803 2368.0356 3339.9382 5008.5005 8202.1602 15284.5820 | lr 4.0e-04 | norm 5737.4800 | dt 9.807 +type train | step 2176 | loss 121.3413 240.6648 378.4397 562.1654 821.4683 1174.3319 1614.5887 2279.3215 3232.9143 4828.0449 7856.1914 14383.8086 | lr 4.0e-04 | norm 6346.7939 | dt 9.806 +type train | step 2177 | loss 112.6725 224.9563 355.1013 533.5045 786.9434 1135.8826 1568.8008 2241.1389 3192.2085 4778.9458 7796.0171 14336.2744 | lr 4.0e-04 | norm 5378.8267 | dt 9.790 +type train | step 2178 | loss 121.0412 242.2722 371.0090 556.0906 808.4894 1178.1150 1636.9863 2374.7019 3363.9631 5038.6699 8304.4072 15381.1562 | lr 4.0e-04 | norm 5823.6782 | dt 9.765 +type train | step 2179 | loss 119.1682 242.9458 379.7960 564.9910 822.9883 1191.0580 1643.9038 2349.7900 3337.8169 4971.2031 8080.6011 14894.7402 | lr 4.0e-04 | norm 5282.7109 | dt 9.795 +type train | step 2180 | loss 114.1758 229.3046 361.8283 541.6905 795.6166 1153.1316 1597.1675 2282.9109 3255.5413 4891.5078 8020.3354 14914.4766 | lr 4.0e-04 | norm 5595.0151 | dt 9.790 +type train | step 2181 | loss 115.8685 232.0314 370.0786 553.0672 815.2267 1167.3473 1610.3098 2289.1499 3286.5254 4936.0767 8111.7651 14975.4014 | lr 4.0e-04 | norm 4995.1265 | dt 9.789 +type train | step 2182 | loss 114.5368 231.6686 367.5924 548.1395 805.1282 1165.8899 1609.2024 2292.2393 3261.4863 4859.8135 7959.2446 14614.8223 | lr 4.0e-04 | norm 4750.0176 | dt 9.780 +type train | step 2183 | loss 118.6360 237.1765 374.9585 552.7939 812.8217 1181.9480 1633.3453 2341.4070 3306.9951 4963.5703 8169.6348 15265.0254 | lr 4.0e-04 | norm 5515.6035 | dt 9.772 +type train | step 2184 | loss 122.1336 248.3361 387.4485 573.1168 826.2006 1188.4579 1632.8923 2316.7478 3258.1362 4870.4819 8026.1299 14947.4629 | lr 4.0e-04 | norm 6177.9087 | dt 9.791 +type train | step 2185 | loss 116.6389 235.5338 368.8326 552.1079 809.9362 1171.5421 1619.3020 2310.8188 3299.0759 4954.9570 8099.1562 14934.2754 | lr 4.0e-04 | norm 4799.7217 | dt 9.780 +type train | step 2186 | loss 115.2722 230.8683 360.8190 536.8076 789.3453 1152.8492 1599.0000 2295.3667 3279.0139 4917.4004 8017.4336 14811.8174 | lr 4.0e-04 | norm 5312.2622 | dt 9.780 +type train | step 2187 | loss 104.4660 205.1817 333.3131 505.1360 748.9579 1082.5956 1507.0986 2153.4578 3100.9006 4643.9634 7608.4272 14041.2881 | lr 4.0e-04 | norm 5215.4707 | dt 9.777 +type train | step 2188 | loss 121.1288 242.9362 370.2954 560.9473 826.2010 1202.9677 1661.4971 2363.9973 3351.4006 4996.5674 8146.7432 15090.9629 | lr 4.0e-04 | norm 5072.3633 | dt 9.781 +type train | step 2189 | loss 127.6600 261.0203 412.9662 640.6569 914.8681 1354.3632 1852.4232 2635.2949 3619.8433 5346.5859 8621.6270 16100.8154 | lr 4.0e-04 | norm 8646.7930 | dt 9.767 +type train | step 2190 | loss 116.4349 236.2086 369.6954 559.6219 822.9786 1189.4229 1636.7571 2339.0171 3335.3577 5016.9512 8233.2646 15214.0420 | lr 4.0e-04 | norm 5306.0142 | dt 9.783 +type train | step 2191 | loss 116.1134 231.1266 363.0023 547.0298 796.6639 1158.0348 1606.0338 2300.1807 3254.2878 4851.9302 7977.5293 14749.9580 | lr 4.0e-04 | norm 5997.8701 | dt 9.791 +type train | step 2192 | loss 119.4493 242.4536 375.9707 565.4785 820.8931 1183.9060 1631.4011 2324.6836 3285.4043 4924.4131 8073.3110 14976.6543 | lr 4.0e-04 | norm 5377.5903 | dt 9.774 +type train | step 2193 | loss 126.3035 249.7686 387.8118 581.4978 842.0888 1227.8748 1703.1707 2459.0850 3445.9204 5178.0088 8547.4668 15975.1592 | lr 4.0e-04 | norm 6594.9043 | dt 9.765 +type train | step 2194 | loss 116.2325 232.4640 361.7715 542.2360 790.3509 1130.7955 1553.4637 2196.4148 3132.2678 4652.7700 7572.8794 13951.7891 | lr 4.0e-04 | norm 4628.1846 | dt 9.787 +type train | step 2195 | loss 123.9415 251.7001 383.5154 568.3626 819.4760 1184.8483 1627.0543 2325.0510 3272.4788 4871.5190 7963.4307 14647.3779 | lr 4.0e-04 | norm 4852.7500 | dt 9.782 +type train | step 2196 | loss 124.3984 249.2066 384.6124 580.6601 832.5234 1187.8838 1605.6566 2250.9182 3144.8145 4662.8169 7612.3213 14099.1777 | lr 4.0e-04 | norm 5878.7930 | dt 9.770 +type train | step 2197 | loss 114.7124 231.1958 362.2896 540.8557 791.3635 1139.6799 1570.8250 2244.3223 3186.6936 4779.6611 7810.9795 14396.3320 | lr 4.0e-04 | norm 4713.8193 | dt 9.778 +type train | step 2198 | loss 113.1305 225.6986 354.2941 534.1865 785.4338 1135.8765 1583.4943 2281.6560 3287.6650 4916.0371 8001.7505 14719.8789 | lr 4.0e-04 | norm 5523.1562 | dt 9.801 +type train | step 2199 | loss 116.4762 231.8632 368.4504 558.1973 821.3632 1179.0928 1628.6057 2321.0139 3296.4504 4919.5684 8026.9307 14803.3965 | lr 4.0e-04 | norm 5756.0625 | dt 9.788 +type train | step 2200 | loss 134.8773 269.9120 408.2151 601.7913 867.3291 1266.4596 1713.2878 2441.4409 3365.4282 4966.4463 8020.5332 14778.8516 | lr 4.0e-04 | norm 5787.7622 | dt 9.761 +type train | step 2201 | loss 119.5677 237.0465 373.7435 563.9373 827.2944 1190.1760 1642.2134 2329.3013 3316.0854 4993.4463 8159.4331 15149.6406 | lr 4.0e-04 | norm 5218.8560 | dt 9.795 +type train | step 2202 | loss 114.1055 227.6105 356.9542 537.2347 790.6531 1148.8229 1590.4832 2278.1560 3248.9304 4885.7549 8051.2192 14858.8408 | lr 4.0e-04 | norm 4727.7783 | dt 9.784 +type train | step 2203 | loss 111.6524 233.4179 359.4171 550.7315 820.0068 1178.9114 1639.1926 2353.0762 3382.3320 5158.9683 8483.6963 15516.2012 | lr 4.0e-04 | norm 10277.9668 | dt 9.777 +type train | step 2204 | loss 128.0804 258.0551 392.4211 585.3883 848.9965 1230.4143 1686.9202 2391.4861 3358.5381 4965.1304 8012.2427 14710.7471 | lr 4.0e-04 | norm 5181.9399 | dt 9.786 +type train | step 2205 | loss 115.4915 236.9305 374.3226 569.0955 832.8222 1206.2828 1662.9539 2367.7241 3360.8999 5044.6958 8323.8223 15580.4766 | lr 4.0e-04 | norm 7056.8574 | dt 9.791 +type train | step 2206 | loss 114.8714 233.3110 366.9670 552.2087 812.5746 1172.5889 1627.0315 2322.1494 3309.0208 4975.9336 8198.4609 15274.4609 | lr 3.9e-04 | norm 5797.2637 | dt 9.785 +type train | step 2207 | loss 123.6834 249.1647 382.9668 562.7354 825.0742 1183.0806 1631.7341 2320.6179 3283.9189 4882.6313 7914.3604 14544.1133 | lr 3.9e-04 | norm 6304.4258 | dt 9.779 +type train | step 2208 | loss 111.9466 224.2192 354.4263 541.6657 800.0489 1160.5610 1614.7659 2325.9316 3312.3843 5019.8530 8383.4570 15580.7080 | lr 3.9e-04 | norm 6865.6777 | dt 9.784 +type train | step 2209 | loss 106.4264 210.9676 341.2975 521.3240 772.8993 1124.6984 1600.0164 2265.5620 3239.3066 4890.5776 8032.2617 14877.6826 | lr 3.9e-04 | norm 5016.3335 | dt 9.786 +type train | step 2210 | loss 108.4409 218.2451 345.9125 525.3604 778.3443 1125.7397 1564.0590 2230.3420 3198.8801 4812.1274 7892.8135 14528.9463 | lr 3.9e-04 | norm 5037.7632 | dt 9.784 +type train | step 2211 | loss 108.0625 216.0676 340.8687 519.6198 771.7061 1121.8527 1565.1555 2241.5413 3224.8662 4826.3110 7925.8999 14695.1064 | lr 3.9e-04 | norm 6083.6646 | dt 9.788 +type train | step 2212 | loss 118.7332 238.7977 375.6280 564.1891 825.8412 1188.9242 1645.7743 2341.6221 3327.8350 4986.9976 8157.7856 14980.2041 | lr 3.9e-04 | norm 4628.0376 | dt 9.785 +type train | step 2213 | loss 113.3397 226.0712 354.7516 542.0121 797.7096 1159.2561 1630.4740 2324.3491 3315.7197 4993.2139 8189.0981 15158.4248 | lr 3.9e-04 | norm 5648.9741 | dt 9.784 +type train | step 2214 | loss 114.0776 227.3876 353.9738 531.4402 781.8998 1143.8787 1589.6426 2284.9585 3250.5352 4860.0796 7971.5723 14757.7920 | lr 3.9e-04 | norm 5230.2637 | dt 9.770 +type train | step 2215 | loss 114.0712 228.3410 365.2366 551.3832 814.6746 1184.0107 1746.2263 2359.3901 3360.1099 5054.8745 8284.9326 15367.4053 | lr 3.9e-04 | norm 6565.5474 | dt 9.789 +type train | step 2216 | loss 119.2683 240.7586 376.5544 564.2028 823.4371 1184.5312 1731.5187 2299.3093 3237.2407 4838.0078 7911.6909 14699.8633 | lr 3.9e-04 | norm 7120.0508 | dt 9.781 +type train | step 2217 | loss 123.4365 246.0006 381.3683 572.6089 827.8914 1194.0746 1640.9855 2308.9116 3261.1152 4837.1084 7861.9131 14487.3174 | lr 3.9e-04 | norm 5297.0649 | dt 9.773 +type train | step 2218 | loss 115.1540 227.1237 357.6687 538.6606 793.7186 1146.1996 1619.0449 2270.9158 3253.1223 4890.0303 8031.5469 14848.5195 | lr 3.9e-04 | norm 5806.9521 | dt 9.775 +type train | step 2219 | loss 120.0668 235.0337 369.6455 545.6523 792.2639 1150.7899 1580.9093 2250.4092 3144.0066 4747.1758 7814.1416 14626.0459 | lr 3.9e-04 | norm 6477.6875 | dt 9.761 +type train | step 2220 | loss 105.8018 209.1452 337.8473 514.9592 768.9609 1121.2263 1655.0067 2247.0215 3218.9846 4817.4678 7909.2725 14528.0771 | lr 3.9e-04 | norm 5231.8638 | dt 9.787 +type train | step 2221 | loss 108.9572 216.9827 346.3320 524.5010 773.2361 1123.7163 1607.6265 2242.8811 3202.3059 4802.1338 7903.6001 14646.7285 | lr 3.9e-04 | norm 5072.8184 | dt 9.784 +type train | step 2222 | loss 111.1630 221.3275 353.7299 534.1365 788.4189 1128.5679 1732.7968 2228.9187 3194.8374 4800.9639 7882.6108 14653.3086 | lr 3.9e-04 | norm 6017.7690 | dt 9.796 +type train | step 2223 | loss 119.5912 239.6079 371.9127 556.8044 818.1326 1181.4543 1691.0483 2320.4504 3278.0032 4884.4355 8018.7681 14872.7305 | lr 3.9e-04 | norm 5119.6138 | dt 9.781 +type train | step 2224 | loss 110.8572 226.8099 363.5948 558.4705 826.5992 1195.8691 1752.2676 2366.2012 3395.4170 5094.3140 8349.5645 15451.4316 | lr 3.9e-04 | norm 7041.0864 | dt 9.785 +type train | step 2225 | loss 113.9519 224.1578 355.5151 544.8128 804.0742 1179.2664 1767.6484 2375.7488 3386.2656 5103.3794 8379.7998 15475.3047 | lr 3.9e-04 | norm 6577.8716 | dt 9.769 +type train | step 2226 | loss 106.0656 210.9243 333.9584 509.4934 756.4476 1098.2699 1604.0658 2185.4448 3137.9409 4721.1958 7766.0044 14354.1152 | lr 3.9e-04 | norm 5032.3994 | dt 9.776 +type train | step 2227 | loss 114.1148 227.2049 358.4787 540.9082 795.0468 1151.7205 1702.3811 2289.2986 3260.1978 4872.3384 7953.8970 14661.0820 | lr 3.9e-04 | norm 5389.6548 | dt 9.792 +type train | step 2228 | loss 121.4364 245.9227 378.7149 567.6885 822.2881 1183.4033 1722.6105 2316.2578 3282.9614 4964.0581 8108.1250 14980.4590 | lr 3.9e-04 | norm 5310.9824 | dt 9.779 +type train | step 2229 | loss 111.9412 222.8589 346.7445 530.1998 782.1064 1137.7167 1673.8524 2271.4233 3252.6179 4904.4082 8048.2627 14851.0156 | lr 3.9e-04 | norm 5188.1733 | dt 9.786 +type train | step 2230 | loss 114.9562 232.2496 359.2289 547.6271 804.5822 1152.6019 1675.6036 2256.2637 3214.5300 4823.7783 7856.5488 14484.6152 | lr 3.9e-04 | norm 4711.8960 | dt 9.786 +type train | step 2231 | loss 106.3476 210.1476 334.5969 513.2220 761.9600 1109.4086 1637.3512 2223.3599 3204.1418 4809.5498 7882.5405 14633.5400 | lr 3.9e-04 | norm 5324.2954 | dt 9.785 +type train | step 2232 | loss 120.2273 244.3312 378.0261 576.9061 842.0604 1204.8123 1740.5121 2346.7104 3325.0029 4963.0957 8126.8970 15024.4014 | lr 3.9e-04 | norm 5912.7026 | dt 9.797 +type train | step 2233 | loss 116.3328 234.4816 365.4166 556.2421 813.3162 1169.7080 1695.4937 2290.0801 3255.9236 4846.6440 7955.4453 14741.3242 | lr 3.9e-04 | norm 4915.9395 | dt 9.776 +type train | step 2234 | loss 117.1808 235.3909 368.3777 556.1318 816.5201 1176.4438 1695.3026 2311.6213 3275.5962 4948.1250 8163.2847 15291.2676 | lr 3.9e-04 | norm 5448.3857 | dt 9.780 +type train | step 2235 | loss 120.1873 243.2803 378.5959 576.0852 838.3337 1213.4158 1745.7758 2370.7168 3357.3320 5017.7178 8240.2168 15303.5352 | lr 3.9e-04 | norm 5248.4546 | dt 9.784 +type train | step 2236 | loss 125.1391 257.4081 395.2343 594.8000 859.3546 1235.8844 1766.3066 2402.9600 3377.9304 5003.3975 8096.4116 15044.9102 | lr 3.9e-04 | norm 6575.8379 | dt 9.786 +type train | step 2237 | loss 117.8471 242.2798 378.9407 574.9803 843.4268 1199.1343 1728.2556 2350.5828 3369.7080 5087.5044 8417.6660 15637.3682 | lr 3.9e-04 | norm 5333.2036 | dt 9.783 +type train | step 2238 | loss 136.4656 275.8648 418.0141 621.2133 899.7310 1313.9901 1887.1377 2594.2000 3599.1143 5369.5088 8835.7939 16429.3066 | lr 3.9e-04 | norm 8524.6016 | dt 9.755 +type train | step 2239 | loss 139.3326 290.0368 434.0623 641.1390 934.5917 1378.7314 1980.6624 2734.5366 3713.9448 5488.9009 8995.1621 16649.7539 | lr 3.9e-04 | norm 12198.9199 | dt 9.744 +type train | step 2240 | loss 113.3963 228.6232 360.6024 552.9049 815.6497 1171.6866 1684.2111 2300.3645 3292.3186 4942.2012 8124.3447 15049.1602 | lr 3.9e-04 | norm 5263.2822 | dt 9.784 +type train | step 2241 | loss 121.2635 245.3708 380.5001 574.0903 838.5779 1202.3069 1715.0001 2327.1636 3301.6086 4924.1641 8045.9736 14871.3633 | lr 3.9e-04 | norm 5607.1587 | dt 9.806 +type train | step 2242 | loss 121.9377 245.8677 379.9041 566.0181 832.4799 1194.3724 1713.3097 2357.2471 3362.0469 5043.2451 8341.0459 15704.3340 | lr 3.9e-04 | norm 6960.9927 | dt 9.782 +type train | step 2243 | loss 121.5858 247.8626 376.8576 576.0945 842.7095 1208.4648 1725.8856 2351.3306 3309.3267 4961.2759 8096.3271 15086.6406 | lr 3.9e-04 | norm 5682.8828 | dt 9.775 +type train | step 2244 | loss 120.0179 241.5913 376.9432 569.7488 831.8911 1190.4196 1702.6926 2307.4429 3264.8508 4879.3501 7981.6821 14728.5342 | lr 3.9e-04 | norm 4861.7544 | dt 9.800 +type train | step 2245 | loss 129.7032 261.5947 396.5084 592.4264 863.7090 1241.6587 1767.2972 2424.4712 3383.8228 5075.7227 8315.2930 15403.5762 | lr 3.9e-04 | norm 6465.9175 | dt 9.773 +type train | step 2246 | loss 122.6552 249.2260 382.8325 578.0929 838.5724 1195.9805 1703.8378 2315.1636 3281.7004 4887.3604 7999.2847 14869.4854 | lr 3.9e-04 | norm 4969.8091 | dt 9.793 +type train | step 2247 | loss 134.5662 272.6080 409.8445 613.7957 886.8829 1309.6183 1862.1755 2586.3306 3541.7922 5231.9463 8582.1426 16140.3984 | lr 3.9e-04 | norm 9424.3018 | dt 9.773 +type train | step 2248 | loss 125.2107 252.1709 382.9462 580.7502 846.4911 1243.0070 1772.0869 2455.7341 3456.6653 5161.8843 8432.6973 15654.9033 | lr 3.9e-04 | norm 5969.2939 | dt 9.775 +type train | step 2249 | loss 117.3094 235.4702 368.8318 558.5713 820.8928 1188.9449 1699.2173 2337.7969 3332.4434 4975.7715 8156.5825 15153.0586 | lr 3.9e-04 | norm 5635.5752 | dt 9.785 +type train | step 2250 | loss 119.4690 245.9706 378.5186 587.9583 857.3589 1240.4819 1767.4202 2424.0793 3414.3533 5107.6484 8359.3486 15520.4492 | lr 3.9e-04 | norm 6351.0034 | dt 9.775 +type train | step 2251 | loss 118.2399 238.0939 368.4753 558.5649 817.1876 1172.9193 1673.2510 2302.9978 3265.0413 4898.7310 8036.5674 14912.3418 | lr 3.9e-04 | norm 5325.5474 | dt 9.776 +type train | step 2252 | loss 122.1722 248.3771 384.5604 573.1173 840.6970 1209.2838 1742.8030 2371.6797 3372.4404 5040.2881 8231.0820 15188.2871 | lr 3.9e-04 | norm 5722.8032 | dt 9.783 +type train | step 2253 | loss 118.2644 244.5018 379.5141 582.4358 858.0276 1240.9026 1767.6060 2452.6277 3487.1558 5323.4238 8869.7471 16712.3477 | lr 3.9e-04 | norm 11144.9170 | dt 9.780 +type train | step 2254 | loss 120.3725 246.4809 380.7524 578.8314 854.6306 1239.8350 1767.6194 2428.6812 3420.9392 5078.3833 8187.5229 15018.7676 | lr 3.9e-04 | norm 6750.4126 | dt 9.772 +type train | step 2255 | loss 119.6931 244.0041 381.4602 573.9142 838.3736 1198.4519 1703.5930 2328.3232 3322.9631 4936.7671 7988.7100 14574.4512 | lr 3.9e-04 | norm 4444.2554 | dt 9.798 +type train | step 2256 | loss 124.5028 255.7013 397.3825 602.6172 880.1826 1254.2666 1772.9866 2437.0410 3431.7483 5126.8965 8401.2861 15609.9082 | lr 3.9e-04 | norm 6140.8564 | dt 9.786 +type train | step 2257 | loss 120.6792 244.3300 378.9445 575.9379 840.4998 1205.3970 1698.2991 2328.6494 3298.9570 4921.2642 8022.0557 14715.3584 | lr 3.9e-04 | norm 4640.6069 | dt 9.790 +type train | step 2258 | loss 115.2821 231.3540 364.3291 556.1465 818.8438 1180.9312 1700.8174 2343.2026 3335.5879 5005.6006 8093.2344 14859.1309 | lr 3.9e-04 | norm 5597.9253 | dt 9.796 +type train | step 2259 | loss 120.9823 246.8398 385.4768 587.8882 857.7389 1228.8546 1743.4758 2393.0542 3410.6694 5067.3877 8206.7471 15068.0771 | lr 3.9e-04 | norm 4501.7344 | dt 9.779 +type train | step 2260 | loss 116.5391 241.2308 379.0956 582.6923 858.0127 1214.2817 1731.9966 2382.0364 3392.2192 5107.2607 8442.2461 15675.1670 | lr 3.9e-04 | norm 6434.7139 | dt 9.773 +type train | step 2261 | loss 124.3790 250.8167 389.2505 592.2511 860.1353 1224.6459 1720.4543 2357.3374 3328.2788 4957.8140 8157.5176 15150.6875 | lr 3.9e-04 | norm 6589.4639 | dt 9.780 +type train | step 2262 | loss 123.1303 252.9400 392.8136 597.7206 868.5615 1228.0271 1721.5907 2360.3787 3369.6926 5046.9976 8276.8193 15290.6514 | lr 3.9e-04 | norm 6024.6372 | dt 9.792 +type train | step 2263 | loss 116.3524 250.1226 407.9251 634.7864 937.9878 1318.2572 1880.9264 2614.6794 3761.0237 5728.3452 9412.3633 17419.6602 | lr 3.9e-04 | norm 16455.4902 | dt 9.805 +type train | step 2264 | loss 108.3367 225.2250 361.4573 559.3413 830.2881 1200.8496 1710.7892 2426.4185 3497.5376 5330.3672 8765.7754 16236.7959 | lr 3.9e-04 | norm 9057.8428 | dt 9.784 +type train | step 2265 | loss 119.5622 242.4126 375.7681 570.0706 833.5627 1194.3901 1692.0721 2316.8438 3279.4526 4886.3652 7957.3970 14692.8027 | lr 3.9e-04 | norm 5930.8833 | dt 9.781 +type train | step 2266 | loss 121.0837 247.5227 379.6801 567.3776 828.1246 1179.9603 1666.0928 2301.9373 3265.9453 4891.4927 7978.6025 14749.7178 | lr 3.9e-04 | norm 6214.8042 | dt 9.788 +type train | step 2267 | loss 116.0805 237.8040 371.3469 566.2932 834.5070 1214.4406 1724.3119 2413.2007 3434.6260 5125.6162 8386.0420 15617.6924 | lr 3.9e-04 | norm 6570.4307 | dt 9.778 +type train | step 2268 | loss 122.2767 248.5316 388.0393 587.6799 857.6667 1244.8572 1774.4261 2464.4331 3462.1404 5192.4238 8436.3066 15586.0518 | lr 3.9e-04 | norm 8825.4199 | dt 9.780 +type train | step 2269 | loss 122.1534 247.2559 385.4664 583.2446 849.5079 1214.4459 1708.0867 2362.7671 3340.8694 5005.3481 8214.0918 15300.9170 | lr 3.9e-04 | norm 6536.1021 | dt 9.787 +type train | step 2270 | loss 118.3651 239.6158 371.5311 561.9562 818.4414 1172.4149 1674.7809 2293.7207 3270.1909 4884.8003 7971.2891 14723.1914 | lr 3.9e-04 | norm 5542.6001 | dt 9.797 +type train | step 2271 | loss 120.5874 246.9203 379.9477 575.7496 839.7378 1193.7328 1674.9775 2318.3721 3286.0759 4918.1597 8011.1328 14845.9990 | lr 3.9e-04 | norm 5654.9873 | dt 9.797 +type train | step 2272 | loss 120.6200 244.0778 375.0234 568.4819 831.7444 1195.6561 1712.0330 2344.8230 3306.3091 4947.0786 8100.4966 15021.1035 | lr 3.9e-04 | norm 5405.1216 | dt 9.793 +type train | step 2273 | loss 127.3995 262.0987 399.6443 609.9673 880.6794 1262.0165 1767.6279 2449.5359 3420.5393 5110.7485 8389.5986 15569.0488 | lr 3.9e-04 | norm 5314.2651 | dt 9.783 +type train | step 2274 | loss 134.8742 277.2240 418.1322 626.4984 899.1447 1291.1169 1817.6545 2516.0466 3505.1809 5161.5483 8325.8506 15251.4004 | lr 3.9e-04 | norm 6935.5854 | dt 9.782 +type train | step 2275 | loss 124.0609 250.3253 393.4797 594.5494 869.0526 1248.0941 1750.6157 2432.6670 3448.5178 5165.2900 8502.5801 15848.2012 | lr 3.9e-04 | norm 6047.7080 | dt 9.787 +type train | step 2276 | loss 113.2466 228.5078 361.4517 557.3501 820.2698 1205.2870 1720.2114 2419.7925 3436.2617 5190.2417 8485.4375 15725.4014 | lr 3.9e-04 | norm 6192.2842 | dt 9.776 +type train | step 2277 | loss 116.5187 237.5986 367.0468 564.4836 827.3617 1189.3429 1674.8782 2333.6897 3326.5874 4929.0962 7995.9287 14741.7109 | lr 3.9e-04 | norm 6075.4922 | dt 9.789 +type train | step 2278 | loss 117.3453 238.7531 370.0465 561.9088 821.1180 1183.0765 1669.4767 2319.9788 3286.2058 4905.1641 8046.6338 14986.2861 | lr 3.9e-04 | norm 5296.7974 | dt 9.781 +type train | step 2279 | loss 124.4713 255.8280 392.4533 592.2928 856.3804 1227.0094 1732.0195 2372.9956 3344.3867 4981.0840 8158.5381 15148.7217 | lr 3.9e-04 | norm 6144.7256 | dt 10.157 +type train | step 2280 | loss 119.3135 242.1859 373.0964 564.1051 822.5814 1184.0612 1651.4004 2303.8064 3250.3337 4852.7993 7976.7168 14829.7119 | lr 3.9e-04 | norm 4997.3398 | dt 9.786 +type train | step 2281 | loss 114.1279 233.5350 363.6485 552.8489 811.8142 1163.3623 1665.7479 2301.1589 3284.3386 4904.2822 8004.1606 14800.0986 | lr 3.9e-04 | norm 5265.8018 | dt 9.794 +type train | step 2282 | loss 112.8372 228.9710 359.8931 552.2332 818.6976 1185.3973 1688.1228 2319.5640 3300.9805 4944.5840 8048.0996 14901.3271 | lr 3.8e-04 | norm 4620.8525 | dt 9.783 +type train | step 2283 | loss 122.7968 249.1005 387.0193 596.9309 869.7090 1253.6138 1784.7633 2457.9712 3456.2087 5191.9526 8522.6621 15838.6924 | lr 3.8e-04 | norm 5571.5269 | dt 9.781 +type train | step 2284 | loss 134.0777 269.0151 403.8438 607.8499 878.3541 1253.2731 1771.9055 2417.5569 3354.1189 4984.8652 8133.6777 15351.3203 | lr 3.8e-04 | norm 6883.2349 | dt 9.772 +type train | step 2285 | loss 120.1389 241.6536 371.8816 562.5111 822.1016 1182.8766 1675.3601 2312.3933 3270.3013 4876.0640 7963.7422 14721.3115 | lr 3.8e-04 | norm 5149.1460 | dt 9.789 +type train | step 2286 | loss 118.1944 242.8454 372.6435 560.8608 821.0870 1173.2335 1662.7842 2295.9556 3280.5303 4906.8877 8062.1089 14911.5625 | lr 3.8e-04 | norm 5602.9673 | dt 9.778 +type train | step 2287 | loss 122.2040 246.2182 382.5912 586.9865 856.2775 1231.6331 1772.8086 2408.3313 3382.8274 5098.6558 8417.0566 15548.0752 | lr 3.8e-04 | norm 6378.1460 | dt 9.784 +type train | step 2288 | loss 112.1925 226.1223 352.0373 542.9005 804.0486 1178.6644 1688.7749 2379.7512 3370.9253 5018.5791 8152.7231 14968.0029 | lr 3.8e-04 | norm 5950.2119 | dt 9.772 +type train | step 2289 | loss 119.7652 241.0848 370.7046 563.5288 818.8459 1175.8879 1693.8750 2323.2617 3302.8679 4926.4966 8019.9448 14793.0059 | lr 3.8e-04 | norm 5386.7197 | dt 9.792 +type train | step 2290 | loss 124.0294 251.9852 383.8695 581.4315 841.2007 1202.7637 1705.0128 2343.6445 3324.3555 4960.9946 8041.0747 14764.6748 | lr 3.8e-04 | norm 5999.2295 | dt 9.779 +type train | step 2291 | loss 111.6204 223.1307 351.8545 541.1832 798.3990 1154.7334 1658.4131 2294.1421 3288.5098 4936.1494 8074.1362 14888.8408 | lr 3.8e-04 | norm 5635.2119 | dt 9.782 +type train | step 2292 | loss 119.1746 238.3038 363.9799 552.8463 808.1754 1179.3401 1659.0892 2318.3540 3269.7102 4855.7500 7923.9150 14754.6719 | lr 3.8e-04 | norm 5599.4429 | dt 9.774 +type train | step 2293 | loss 117.0919 237.3620 368.7767 561.3742 822.8498 1172.6025 1656.5876 2291.5801 3273.9941 4889.7866 7995.2246 14767.9697 | lr 3.8e-04 | norm 4672.9150 | dt 9.788 +type train | step 2294 | loss 107.7820 220.2176 349.3035 537.4701 801.9459 1158.0237 1709.1593 2329.1560 3368.6792 5033.9668 8139.2974 14782.5264 | lr 3.8e-04 | norm 6735.2720 | dt 9.793 +type train | step 2295 | loss 127.3961 256.2844 387.1663 592.0531 856.3096 1248.7402 1759.2766 2449.0752 3410.2356 5073.5918 8263.1182 15318.9453 | lr 3.8e-04 | norm 6314.2036 | dt 9.773 +type train | step 2296 | loss 118.8594 240.3112 371.9292 569.9948 836.6461 1194.7441 1693.8867 2335.5569 3293.8086 4874.4604 7937.5029 14727.9648 | lr 3.8e-04 | norm 5395.9683 | dt 9.792 +type train | step 2297 | loss 120.2957 243.1631 374.3522 572.6983 836.6508 1205.4166 1681.9562 2354.9741 3346.6846 5003.7139 8224.1777 15147.7871 | lr 3.8e-04 | norm 5091.8286 | dt 9.795 +type train | step 2298 | loss 123.3145 256.7609 401.1426 632.7621 915.4222 1353.7184 1911.8787 2693.7112 3710.5801 5509.7441 8989.6035 16852.8613 | lr 3.8e-04 | norm 9589.4512 | dt 9.763 +type train | step 2299 | loss 109.1759 220.6116 347.8120 542.2465 802.0063 1157.7231 1636.3549 2275.9951 3246.2852 4873.6807 8015.8589 14788.7520 | lr 3.8e-04 | norm 5028.4463 | dt 9.801 +type train | step 2300 | loss 117.4179 236.4999 363.1595 550.4115 812.3603 1176.3613 1686.2458 2315.6550 3300.3643 4949.2246 8145.8613 15239.1719 | lr 3.8e-04 | norm 6016.0078 | dt 9.780 +type train | step 2301 | loss 112.4680 230.8261 362.8409 561.4929 827.0134 1180.6230 1682.9545 2325.8445 3311.8113 4963.8701 8139.5967 15039.7285 | lr 3.8e-04 | norm 5924.8779 | dt 9.796 +type train | step 2302 | loss 116.4473 236.4471 359.0638 557.2231 807.6244 1168.3214 1681.6948 2303.5596 3271.5105 4916.2051 8054.3853 14892.9482 | lr 3.8e-04 | norm 5647.4893 | dt 9.775 +type train | step 2303 | loss 126.8144 261.5476 394.1262 602.0065 876.0346 1248.3579 1755.4902 2396.7239 3360.6230 4990.8623 8072.1631 14990.9512 | lr 3.8e-04 | norm 7234.9878 | dt 9.774 +type train | step 2304 | loss 115.8765 237.1928 367.1171 564.2874 830.9728 1179.5040 1694.4194 2316.9580 3309.1580 4943.3447 8062.7388 14928.2363 | lr 3.8e-04 | norm 5574.9302 | dt 9.785 +type train | step 2305 | loss 117.4108 237.4575 368.0268 565.2168 826.2581 1183.7539 1680.9124 2302.1851 3283.8579 4890.1104 7981.1670 14806.3164 | lr 3.8e-04 | norm 5675.0034 | dt 9.788 +type train | step 2306 | loss 113.9897 227.0517 356.8028 552.1827 815.1329 1177.7037 1684.9194 2321.0964 3304.1392 4919.5034 8040.2715 14905.7627 | lr 3.8e-04 | norm 5259.9351 | dt 9.779 +type train | step 2307 | loss 106.3355 217.3344 350.1620 548.4401 819.7351 1180.0042 1710.3821 2368.4480 3433.9758 5185.5850 8525.5723 15843.8633 | lr 3.8e-04 | norm 7600.4150 | dt 9.790 +type train | step 2308 | loss 119.3057 239.3291 365.5464 562.1075 820.9161 1174.6731 1678.7761 2296.6653 3270.1042 4889.4497 8045.0977 14977.6699 | lr 3.8e-04 | norm 7037.8535 | dt 9.772 +type train | step 2309 | loss 128.1758 261.4652 401.4013 613.4588 884.3898 1263.9946 1797.4962 2445.3420 3448.1187 5129.8975 8442.4619 15787.5205 | lr 3.8e-04 | norm 6526.0591 | dt 9.780 +type train | step 2310 | loss 120.5986 247.1232 382.2979 577.2349 842.2678 1193.6211 1683.6575 2305.7183 3287.7341 4907.8091 8042.9033 14904.5469 | lr 3.8e-04 | norm 5143.6089 | dt 9.795 +type train | step 2311 | loss 119.8767 244.2440 372.4367 564.6776 827.6039 1189.9940 1685.7181 2293.1755 3231.9446 4815.7236 7834.7881 14477.5391 | lr 3.8e-04 | norm 5374.8477 | dt 9.779 +type train | step 2312 | loss 120.6805 239.3799 371.0625 575.3662 839.5438 1214.3167 1722.0012 2375.5283 3377.8911 5079.2656 8329.4922 15544.1748 | lr 3.8e-04 | norm 5768.1323 | dt 9.785 +type train | step 2313 | loss 116.2467 235.9751 365.6779 561.3069 823.3600 1176.8663 1678.0830 2290.7019 3270.1187 4910.1196 8039.8076 15012.3008 | lr 3.8e-04 | norm 6131.0474 | dt 9.793 +type train | step 2314 | loss 115.1560 233.0147 363.6765 560.4967 830.0964 1185.7006 1696.2893 2343.6172 3370.3301 5060.9272 8266.5068 15216.7031 | lr 3.8e-04 | norm 5348.2412 | dt 9.786 +type train | step 2315 | loss 118.9891 246.6657 378.8820 585.8542 855.3348 1224.7485 1734.3011 2390.1543 3387.3081 5049.1484 8220.4580 15122.0957 | lr 3.8e-04 | norm 5569.3301 | dt 9.800 +type train | step 2316 | loss 115.5538 234.5276 366.2259 559.4131 822.1494 1183.7920 1684.1344 2322.5093 3291.6699 4914.0894 8045.9751 14868.4629 | lr 3.8e-04 | norm 4998.9888 | dt 9.786 +type train | step 2317 | loss 115.8764 236.0019 371.0832 569.8294 832.8577 1208.9628 1728.2955 2393.7473 3371.4243 5080.0684 8390.8965 15760.3574 | lr 3.8e-04 | norm 5683.9482 | dt 9.787 +type train | step 2318 | loss 126.5000 256.3209 388.7427 588.9389 857.2910 1241.5181 1762.8052 2419.5784 3385.4065 5001.0752 8117.1499 15001.2949 | lr 3.8e-04 | norm 4642.6587 | dt 9.779 +type train | step 2319 | loss 112.0273 231.0023 358.3808 547.0916 806.6577 1165.4832 1668.1469 2304.5908 3299.8306 4948.1724 8121.9902 14979.6865 | lr 3.8e-04 | norm 5774.5547 | dt 9.783 +type train | step 2320 | loss 117.8334 237.1090 365.5410 557.1136 811.4875 1167.4950 1668.1326 2286.3591 3269.9692 4879.7808 7978.3325 14813.2959 | lr 3.8e-04 | norm 4942.0322 | dt 9.797 +type train | step 2321 | loss 122.3117 245.4876 376.8260 578.3254 847.6699 1222.6062 1742.6981 2415.6182 3437.6101 5119.2700 8369.1807 15407.7881 | lr 3.8e-04 | norm 5145.4116 | dt 9.772 +type train | step 2322 | loss 123.3896 247.3345 376.6412 569.6949 828.4785 1188.3201 1687.4963 2324.4609 3306.0818 4933.9180 8053.1260 14884.7627 | lr 3.8e-04 | norm 5367.2246 | dt 9.796 +type train | step 2323 | loss 118.1008 239.3550 369.0878 564.4301 822.3485 1183.8092 1687.8202 2307.6475 3282.8667 4902.1245 8035.8564 14856.4287 | lr 3.8e-04 | norm 4865.7339 | dt 9.780 +type train | step 2324 | loss 119.2407 240.4537 375.9316 576.6323 840.8775 1229.7490 1747.0480 2423.1848 3401.4390 5019.9648 8154.8721 15126.4336 | lr 3.8e-04 | norm 6236.5254 | dt 9.770 +type train | step 2325 | loss 112.3127 225.5646 349.5038 539.4462 797.1062 1156.8691 1658.7463 2302.7588 3269.4800 4872.7471 7991.0615 14985.0303 | lr 3.8e-04 | norm 8136.9971 | dt 9.783 +type train | step 2326 | loss 113.6621 235.0953 367.4315 563.5529 832.0522 1197.3685 1709.1943 2348.9683 3350.8440 5019.4990 8200.7705 15224.8096 | lr 3.8e-04 | norm 6019.9385 | dt 9.783 +type train | step 2327 | loss 124.3946 253.1524 388.5940 589.7401 862.6372 1242.6141 1769.5090 2447.5217 3446.2898 5133.8525 8359.0488 15394.6230 | lr 3.8e-04 | norm 5253.5508 | dt 9.789 +type train | step 2328 | loss 116.6316 237.5301 365.9416 564.0765 829.3522 1188.1619 1694.9536 2347.8337 3345.9158 4998.7559 8114.6870 14945.9834 | lr 3.8e-04 | norm 5121.0420 | dt 9.787 +type train | step 2329 | loss 122.7402 248.3312 378.7437 583.2716 845.9359 1196.9128 1704.4995 2319.9565 3270.0962 4860.4302 7964.3418 14757.4121 | lr 3.8e-04 | norm 6148.0571 | dt 9.778 +type train | step 2330 | loss 112.5062 227.0794 352.5410 541.2041 797.9045 1148.3059 1649.7388 2265.2346 3238.7070 4818.0386 7825.6914 14476.1504 | lr 3.8e-04 | norm 5537.2529 | dt 9.785 +type train | step 2331 | loss 114.8300 230.6576 358.4250 553.4202 809.1263 1177.9351 1673.9860 2340.7119 3326.1543 4946.6885 8028.5264 14772.3711 | lr 3.8e-04 | norm 5628.2695 | dt 9.770 +type train | step 2332 | loss 123.7077 248.3374 379.3709 576.7695 840.9323 1214.3842 1724.0150 2379.0942 3369.5271 5009.8994 8169.5137 15145.2119 | lr 3.8e-04 | norm 5410.7988 | dt 9.790 +type train | step 2333 | loss 108.0401 217.4922 343.8833 542.0226 803.0308 1173.9316 1706.3521 2388.4375 3382.3240 5137.5215 8553.3379 16182.8789 | lr 3.8e-04 | norm 7459.4434 | dt 9.770 +type train | step 2334 | loss 114.9599 231.6891 359.7364 552.0453 807.7469 1159.0226 1652.0239 2262.0566 3230.4155 4837.0708 7885.1504 14562.8389 | lr 3.8e-04 | norm 4733.5195 | dt 9.785 +type train | step 2335 | loss 119.4712 242.5964 372.6978 573.3463 838.4606 1219.5013 1739.1926 2401.5083 3401.1194 5064.3491 8233.4473 15169.8086 | lr 3.8e-04 | norm 5254.6113 | dt 9.770 +type train | step 2336 | loss 119.5547 240.8972 368.5619 566.9338 827.9540 1194.4318 1692.3739 2318.9341 3265.2178 4850.0146 7890.8438 14567.0352 | lr 3.8e-04 | norm 5130.4180 | dt 9.785 +type train | step 2337 | loss 118.1413 241.4847 370.1088 562.8111 824.1371 1183.1500 1681.0497 2310.3562 3284.7249 4881.1323 7965.2754 14691.1953 | lr 3.8e-04 | norm 4790.5962 | dt 9.782 +type train | step 2338 | loss 122.3219 251.8006 387.7088 597.3536 876.5129 1266.0740 1793.7091 2477.2578 3469.2778 5156.3379 8436.3604 15640.4180 | lr 3.8e-04 | norm 5574.4106 | dt 9.788 +type train | step 2339 | loss 120.1883 243.9961 379.7441 585.8766 857.0295 1247.7847 1777.0524 2459.4197 3477.9758 5216.6382 8549.7295 15792.6846 | lr 3.8e-04 | norm 5890.8711 | dt 9.778 +type train | step 2340 | loss 115.2529 232.2546 360.5047 555.2321 813.8860 1171.1593 1659.8265 2310.4778 3298.6873 4957.5366 8096.2920 14938.4688 | lr 3.8e-04 | norm 4788.8149 | dt 9.781 +type train | step 2341 | loss 115.9768 236.0518 365.5456 560.3797 819.7611 1182.4673 1675.1718 2322.2222 3307.1416 4918.6016 8029.9556 14805.3926 | lr 3.8e-04 | norm 4795.2002 | dt 9.790 +type train | step 2342 | loss 118.1555 238.2897 368.8233 564.9832 824.2237 1177.0491 1660.8446 2278.2000 3220.7102 4787.4219 7780.0107 14338.1416 | lr 3.8e-04 | norm 4689.6943 | dt 9.791 +type train | step 2343 | loss 114.4114 230.1138 358.0296 548.8247 809.8798 1175.0334 1680.6750 2332.0325 3327.5007 4970.0449 8109.4653 15051.5791 | lr 3.8e-04 | norm 4957.4346 | dt 9.775 +type train | step 2344 | loss 106.3900 214.2920 338.2520 524.6022 782.7336 1130.9185 1626.0341 2256.6204 3255.8691 4893.8057 7945.7207 14622.2598 | lr 3.8e-04 | norm 5495.7505 | dt 9.803 +type train | step 2345 | loss 113.2465 227.5721 354.8611 548.0771 808.3865 1163.2556 1663.0608 2314.3867 3312.7156 4979.5039 8187.1104 15260.8262 | lr 3.8e-04 | norm 5269.9614 | dt 9.782 +type train | step 2346 | loss 121.1322 244.4871 376.1336 573.8773 839.2806 1212.5394 1711.4167 2377.8208 3356.9504 5011.3687 8159.7563 15089.5771 | lr 3.8e-04 | norm 4300.2041 | dt 9.793 +type train | step 2347 | loss 116.7255 239.3870 367.8267 563.6723 824.8864 1184.1479 1667.8713 2306.1130 3272.5854 4900.6714 8055.9917 14972.4922 | lr 3.8e-04 | norm 4831.1602 | dt 9.798 +type train | step 2348 | loss 122.8717 247.8918 376.5708 573.7890 835.1278 1200.2639 1693.9158 2342.1958 3305.4116 4924.1055 8059.0913 14917.1992 | lr 3.8e-04 | norm 5994.0835 | dt 9.782 +type train | step 2349 | loss 113.3693 231.6940 359.7514 555.9846 821.0866 1175.4200 1669.8158 2317.3879 3323.3208 4989.9541 8166.0952 15089.9922 | lr 3.8e-04 | norm 5357.2324 | dt 9.785 +type train | step 2350 | loss 110.7713 223.9560 349.7326 543.5032 811.2827 1170.4878 1670.5214 2343.6711 3377.6824 5073.0195 8325.7324 15379.5654 | lr 3.8e-04 | norm 5838.3179 | dt 9.785 +type train | step 2351 | loss 124.2902 251.2701 384.1838 583.3862 848.0171 1202.6222 1684.1238 2317.3728 3274.4033 4881.1753 8002.7998 14779.6074 | lr 3.8e-04 | norm 4614.8081 | dt 9.796 +type train | step 2352 | loss 114.6217 234.8209 363.6034 552.8195 811.5984 1164.5074 1651.5410 2276.3689 3248.0735 4840.6650 7893.1504 14598.4932 | lr 3.8e-04 | norm 4677.4683 | dt 9.800 +type train | step 2353 | loss 113.4338 230.9659 358.4712 547.0841 807.1844 1155.5186 1639.8646 2267.8875 3239.5381 4847.7544 7926.0874 14622.8770 | lr 3.8e-04 | norm 5066.4097 | dt 9.802 +type train | step 2354 | loss 122.5115 247.4556 376.9398 570.0034 827.5155 1187.4556 1676.3558 2321.8853 3271.7092 4866.8184 7916.8145 14637.8760 | lr 3.8e-04 | norm 4778.3857 | dt 9.789 +type train | step 2355 | loss 115.4935 234.5059 363.4624 560.6039 824.0184 1186.8455 1680.2053 2336.1899 3307.0771 4939.5859 8026.8965 14791.6387 | lr 3.7e-04 | norm 4444.7808 | dt 9.784 +type train | step 2356 | loss 114.9362 237.4855 369.9723 572.2403 842.9476 1209.4569 1719.3010 2377.1531 3383.4954 5024.8735 8182.6289 15097.9805 | lr 3.7e-04 | norm 5038.1704 | dt 9.799 +type train | step 2357 | loss 112.4870 227.1974 352.9741 546.7178 805.0650 1158.4645 1648.1530 2282.6643 3266.4905 4869.7690 7971.0991 14720.0811 | lr 3.7e-04 | norm 5028.5728 | dt 9.787 +type train | step 2358 | loss 124.5484 253.7645 385.4008 589.2869 851.0633 1222.6492 1707.9761 2345.8574 3280.0071 4843.1138 7849.9912 14482.4365 | lr 3.7e-04 | norm 5024.2041 | dt 9.793 +type train | step 2359 | loss 115.1130 237.9785 373.8235 579.5297 852.0421 1213.6770 1717.4962 2372.0615 3370.6870 5024.5156 8185.8643 15076.6934 | lr 3.7e-04 | norm 4879.3091 | dt 9.797 +type train | step 2360 | loss 115.6457 231.9293 361.7705 559.4302 819.4103 1181.8239 1675.4299 2322.5811 3292.0483 4903.9033 8040.7021 15064.4551 | lr 3.7e-04 | norm 5575.6865 | dt 9.792 +type train | step 2361 | loss 116.8998 235.7517 361.7004 556.9439 811.7100 1166.2662 1653.7429 2280.0247 3260.0559 4878.1406 7973.7856 14816.8477 | lr 3.7e-04 | norm 4937.5225 | dt 9.791 +type train | step 2362 | loss 104.6271 207.9001 328.4891 513.3309 770.0334 1121.9373 1615.5840 2257.6797 3254.8940 4841.5273 7856.3569 14467.6074 | lr 3.7e-04 | norm 7656.3418 | dt 9.783 +type train | step 2363 | loss 121.4157 245.1143 379.0803 583.8389 854.5775 1227.5277 1737.3745 2412.3379 3407.8828 5110.4155 8386.8477 15545.1152 | lr 3.7e-04 | norm 4765.4429 | dt 9.812 +type train | step 2364 | loss 118.9910 241.7198 372.7547 576.6995 839.5113 1215.3151 1727.2766 2406.4248 3433.3538 5145.0654 8413.7705 15522.4453 | lr 3.7e-04 | norm 5165.0938 | dt 9.797 +type train | step 2365 | loss 108.8875 219.3312 343.4196 535.1302 794.1707 1144.6813 1624.7145 2266.8503 3260.8540 4887.5908 7969.0640 14689.9492 | lr 3.7e-04 | norm 4529.3745 | dt 9.790 +type train | step 2366 | loss 113.3017 226.7402 351.6127 541.5696 797.7982 1143.2072 1625.9655 2269.4536 3249.1721 4900.0483 8037.5786 14907.7334 | lr 3.7e-04 | norm 5945.8535 | dt 9.783 +type train | step 2367 | loss 119.3228 242.2857 373.7460 573.6976 837.0859 1195.3870 1684.5901 2336.7932 3317.9221 4932.4932 8005.0034 14730.5625 | lr 3.7e-04 | norm 4217.7793 | dt 9.790 +type train | step 2368 | loss 119.3845 240.4733 371.0383 567.4078 829.0062 1180.5295 1660.4017 2292.8176 3279.1411 4894.5898 7959.5571 14695.2461 | lr 3.7e-04 | norm 4637.5620 | dt 9.792 +type train | step 2369 | loss 116.6319 244.3385 382.7296 593.8691 869.4511 1246.1202 1754.4719 2436.7383 3438.1038 5097.5718 8282.9844 15304.2461 | lr 3.7e-04 | norm 5830.2036 | dt 9.798 +type train | step 2370 | loss 114.3474 235.4321 365.7519 565.9474 832.8151 1194.0311 1688.4124 2351.2500 3364.1584 5037.7910 8239.7178 15240.2061 | lr 3.7e-04 | norm 5510.1636 | dt 9.832 +type train | step 2371 | loss 115.6901 238.6983 363.5024 562.6901 820.6239 1184.8413 1670.9194 2321.8940 3300.4045 4929.1318 8041.2734 14763.7510 | lr 3.7e-04 | norm 4816.5957 | dt 9.792 +type train | step 2372 | loss 116.1692 234.2771 360.1342 553.9788 813.5516 1172.9722 1663.1777 2314.0454 3291.8926 4934.6226 8055.6523 14950.8730 | lr 3.7e-04 | norm 6119.3608 | dt 9.794 +type train | step 2373 | loss 123.2938 249.8399 378.6449 578.0897 840.6257 1205.2758 1690.5325 2338.3496 3296.6831 4939.1758 8122.6089 15121.1719 | lr 3.7e-04 | norm 6200.5625 | dt 9.783 +type train | step 2374 | loss 112.6661 231.3695 361.0785 561.3470 830.9076 1199.8160 1706.4889 2383.8425 3411.2559 5161.5962 8545.3574 16029.7422 | lr 3.7e-04 | norm 7476.2295 | dt 9.769 +type train | step 2375 | loss 114.4362 231.8528 357.7743 547.1668 806.6490 1166.1919 1657.2142 2306.2031 3291.1038 4914.4160 8001.1606 14687.2549 | lr 3.7e-04 | norm 4745.7119 | dt 9.797 +type train | step 2376 | loss 114.0233 230.3626 354.6804 549.0709 809.6477 1164.7411 1643.1796 2289.4849 3258.4683 4870.0625 7973.9487 14744.9414 | lr 3.7e-04 | norm 5223.4302 | dt 9.790 +type train | step 2377 | loss 129.8640 262.9117 395.1176 605.4235 878.4877 1229.4036 1725.5063 2366.8784 3358.2878 4977.0068 8110.4434 14967.0830 | lr 3.7e-04 | norm 7600.3257 | dt 9.810 +type train | step 2378 | loss 129.2924 264.3491 398.9530 603.7089 877.0609 1235.9054 1732.2102 2381.9246 3366.0952 4976.5054 8063.0522 14822.4150 | lr 3.7e-04 | norm 5641.1367 | dt 9.790 +type train | step 2379 | loss 115.9970 232.2265 359.5112 550.2318 808.4274 1156.4189 1637.1654 2289.2517 3303.5754 4979.0879 8189.0156 15338.2939 | lr 3.7e-04 | norm 9654.1367 | dt 9.796 +type train | step 2380 | loss 118.4725 242.0497 371.0732 563.3782 821.3465 1177.3024 1654.9183 2293.3308 3273.1978 4870.8047 7945.4805 14695.0938 | lr 3.7e-04 | norm 4793.7896 | dt 9.788 +type train | step 2381 | loss 113.7432 230.9557 356.1740 552.7404 812.9938 1167.3419 1659.3063 2307.2866 3292.4370 4914.0645 8017.6680 14763.9629 | lr 3.7e-04 | norm 4929.3384 | dt 9.794 +type train | step 2382 | loss 109.6674 221.6885 347.7216 543.2159 805.6533 1167.2612 1661.6432 2327.8921 3344.0544 5013.3564 8198.3916 15123.5127 | lr 3.7e-04 | norm 4954.4844 | dt 9.792 +type train | step 2383 | loss 120.8074 245.9533 371.5424 569.7938 829.3328 1200.7214 1689.3676 2356.8350 3320.6018 4962.8071 8126.7437 15146.4521 | lr 3.7e-04 | norm 5247.2500 | dt 9.785 +type train | step 2384 | loss 115.3502 234.9355 365.7296 565.9679 829.1342 1194.9260 1687.0962 2343.4292 3337.0466 4961.8984 8085.8472 14861.9922 | lr 3.7e-04 | norm 4749.6353 | dt 9.793 +type train | step 2385 | loss 116.0383 231.7621 355.5616 553.5944 818.8560 1189.5626 1690.3801 2368.9106 3407.7209 5080.2129 8300.3564 15479.1260 | lr 3.7e-04 | norm 7263.6240 | dt 9.768 +type train | step 2386 | loss 120.3691 244.5354 371.6589 569.2142 839.4857 1210.1110 1706.7902 2373.2192 3358.9575 4982.5562 8065.5498 14774.2500 | lr 3.7e-04 | norm 5184.8906 | dt 9.784 +type train | step 2387 | loss 112.0969 227.6088 351.9225 547.8857 806.4760 1156.8062 1642.6125 2282.2266 3267.6809 4901.8574 8054.0889 14905.4014 | lr 3.7e-04 | norm 5387.2886 | dt 9.806 +type train | step 2388 | loss 111.6071 228.5545 355.3026 551.5730 817.0182 1174.0725 1664.1042 2314.5608 3304.0020 4935.6860 8023.5405 14723.0645 | lr 3.7e-04 | norm 4912.8608 | dt 9.800 +type train | step 2389 | loss 117.9282 247.0502 383.5487 590.1741 867.9179 1238.2134 1748.4733 2433.7607 3477.1577 5257.3145 8669.2197 16100.1494 | lr 3.7e-04 | norm 7156.0371 | dt 9.777 +type train | step 2390 | loss 115.1081 236.5872 368.0335 565.1238 829.5659 1185.1094 1673.2134 2320.3784 3306.7664 4971.8564 8122.9116 14988.2764 | lr 3.7e-04 | norm 5169.5771 | dt 9.807 +type train | step 2391 | loss 111.1269 225.3108 349.5409 542.1431 796.1575 1144.6992 1624.7863 2272.9614 3269.0298 4887.5376 7966.5874 14640.8877 | lr 3.7e-04 | norm 5010.9531 | dt 9.792 +type train | step 2392 | loss 118.2160 244.5270 378.4011 584.2760 854.7743 1218.8833 1713.5376 2384.0142 3383.0376 5057.0527 8325.3574 15426.9199 | lr 3.7e-04 | norm 7056.9150 | dt 9.793 +type train | step 2393 | loss 117.1709 238.3145 365.6431 566.0832 829.2070 1180.5874 1652.6858 2302.3950 3246.1230 4832.8438 7868.3096 14608.3105 | lr 3.7e-04 | norm 5596.1235 | dt 9.790 +type train | step 2394 | loss 121.8062 247.6525 377.5956 577.2887 837.3660 1194.4724 1667.9231 2308.7207 3243.7839 4813.6460 7907.8350 14774.6680 | lr 3.7e-04 | norm 5178.6489 | dt 9.781 +type train | step 2395 | loss 128.5048 260.4750 391.6329 595.1645 864.7926 1237.8732 1724.3110 2396.1611 3332.1560 4922.7100 7988.4746 14768.3418 | lr 3.7e-04 | norm 5966.8398 | dt 9.777 +type train | step 2396 | loss 112.4959 228.8281 354.3383 552.2220 811.0270 1168.7854 1662.0822 2311.3701 3312.0630 4898.3516 7941.4058 14484.9150 | lr 3.7e-04 | norm 7394.0405 | dt 9.780 +type train | step 2397 | loss 118.7306 239.1366 363.7076 554.0283 813.3573 1168.7665 1652.4983 2302.9836 3252.0098 4851.7749 7933.2622 14721.4385 | lr 3.7e-04 | norm 5984.2368 | dt 9.782 +type train | step 2398 | loss 136.0276 272.0455 405.0297 619.2324 891.4035 1286.9320 1793.8247 2503.9221 3440.7412 5107.5537 8304.2148 15439.3721 | lr 3.7e-04 | norm 7611.1543 | dt 9.773 +type train | step 2399 | loss 121.9417 250.7178 383.5986 583.8696 843.5374 1221.4264 1713.5341 2406.8477 3389.9219 5073.5430 8179.0444 15040.5605 | lr 3.7e-04 | norm 6715.8281 | dt 9.793 +type train | step 2400 | loss 118.5580 241.3507 366.9370 560.5428 816.2363 1165.3947 1631.7087 2256.7332 3204.6541 4779.6582 7795.9810 14463.6348 | lr 3.7e-04 | norm 5153.6123 | dt 9.789 +type train | step 2401 | loss 119.2352 242.0683 369.4058 571.7495 838.8341 1199.1749 1688.8955 2341.0718 3333.8372 4956.0415 8040.6074 14802.7441 | lr 3.7e-04 | norm 5537.8330 | dt 9.796 +type train | step 2402 | loss 112.2095 231.4762 358.1553 559.4167 824.4915 1185.6881 1673.0698 2334.6267 3320.5562 4949.0127 8074.6421 14986.3799 | lr 3.7e-04 | norm 6341.9897 | dt 9.772 +type train | step 2403 | loss 116.2015 237.4883 364.1945 560.5012 822.4932 1172.6949 1640.4659 2272.0007 3231.5708 4816.9253 7854.7910 14419.3516 | lr 3.7e-04 | norm 4504.4365 | dt 9.823 +type train | step 2404 | loss 113.3784 235.4270 361.1562 562.5874 826.8306 1188.2284 1667.3359 2328.1697 3288.7124 4886.3320 7984.9785 14757.5342 | lr 3.7e-04 | norm 5143.1562 | dt 9.786 +type train | step 2405 | loss 119.6562 246.9946 376.7972 580.6622 846.6339 1229.1993 1733.0837 2436.4226 3439.0596 5115.4780 8313.5000 15353.0400 | lr 3.7e-04 | norm 5037.0913 | dt 9.785 +type train | step 2406 | loss 116.2573 239.3284 367.1375 568.6223 830.1707 1201.2736 1690.3402 2375.2910 3352.5520 4974.7666 8099.1147 14832.4014 | lr 3.7e-04 | norm 4512.7344 | dt 9.785 +type train | step 2407 | loss 119.4529 244.0092 369.9118 565.7029 823.9365 1185.8467 1655.6832 2298.3091 3227.2078 4778.1855 7721.7422 14196.2920 | lr 3.7e-04 | norm 4826.7188 | dt 9.774 +type train | step 2408 | loss 122.3549 246.3970 373.8441 572.1647 834.3351 1192.8604 1674.4727 2318.6218 3242.2769 4792.4155 7776.6475 14368.8984 | lr 3.7e-04 | norm 8242.8389 | dt 9.796 +type train | step 2409 | loss 127.4986 263.9147 397.3596 602.6735 873.6204 1252.0125 1751.4426 2451.3965 3450.2175 5116.9092 8307.3789 15243.4229 | lr 3.7e-04 | norm 5943.7202 | dt 9.785 +type train | step 2410 | loss 118.6309 241.4431 370.4661 564.3419 824.7327 1175.2606 1663.1183 2313.6367 3313.6843 4957.4966 8083.8701 14952.0264 | lr 3.7e-04 | norm 4944.1069 | dt 9.803 +type train | step 2411 | loss 113.9367 230.4240 354.1581 543.7993 802.2647 1148.3708 1619.7451 2247.1731 3200.2483 4758.0337 7774.3540 14403.8096 | lr 3.7e-04 | norm 5113.3945 | dt 9.780 +type train | step 2412 | loss 111.9805 228.0332 352.8093 546.9844 808.3099 1159.3575 1634.2419 2273.8630 3237.2715 4837.2539 7810.2617 14388.4404 | lr 3.7e-04 | norm 4721.5879 | dt 9.798 +type train | step 2413 | loss 120.5283 244.1328 373.2852 575.3443 833.2813 1185.9227 1662.6967 2298.5562 3240.3503 4819.0820 7829.9473 14417.1865 | lr 3.7e-04 | norm 5257.7993 | dt 9.784 +type train | step 2414 | loss 110.5493 225.1683 347.5965 538.3495 796.8148 1154.3510 1634.5135 2300.4553 3271.2417 4903.2607 8002.0918 14724.3574 | lr 3.7e-04 | norm 4602.0830 | dt 9.789 +type train | step 2415 | loss 112.4743 228.7854 357.7786 557.6659 821.2603 1193.6362 1691.7322 2386.3242 3397.3608 5131.9150 8430.5635 15779.6484 | lr 3.7e-04 | norm 5796.0132 | dt 9.798 +type train | step 2416 | loss 119.9968 249.1182 381.5107 580.7683 850.7175 1229.8796 1710.4836 2391.1538 3365.5615 5036.2520 8229.9258 15306.3135 | lr 3.7e-04 | norm 6143.5952 | dt 9.771 +type train | step 2417 | loss 110.6240 225.5402 348.7634 538.7540 794.8291 1138.5430 1606.3188 2231.5691 3195.7671 4767.4834 7794.9141 14345.2773 | lr 3.7e-04 | norm 4274.6294 | dt 9.796 +type train | step 2418 | loss 106.6366 215.7296 334.7631 525.3536 784.9537 1137.1473 1623.1986 2278.3589 3284.5667 4933.7764 8037.9536 14806.2207 | lr 3.7e-04 | norm 5288.1465 | dt 9.790 +type train | step 2419 | loss 110.1256 219.8119 344.0185 536.7424 792.4415 1140.7178 1613.7744 2261.1438 3231.3845 4812.6021 7872.8081 14449.2549 | lr 3.7e-04 | norm 4603.2788 | dt 9.777 +type train | step 2420 | loss 110.4010 224.0726 346.8704 536.7022 791.3495 1140.8838 1612.6642 2247.0242 3210.6543 4779.3452 7812.7339 14325.4004 | lr 3.7e-04 | norm 4698.9443 | dt 9.786 +type train | step 2421 | loss 109.0188 223.0739 345.4221 539.2705 797.6904 1156.9810 1633.3672 2298.0103 3284.0454 4907.1426 8001.9902 14757.8506 | lr 3.7e-04 | norm 4995.0952 | dt 9.788 +type train | step 2422 | loss 114.0317 230.2359 354.3095 545.5991 799.4322 1143.1694 1597.2671 2211.8179 3143.2139 4589.6904 7331.4814 13227.4932 | lr 3.7e-04 | norm 5021.4771 | dt 9.776 +type train | step 2423 | loss 124.6417 253.7003 391.4411 606.5919 890.0947 1309.1105 1855.6710 2671.7351 3733.2078 5505.1099 8711.9453 15713.0664 | lr 3.7e-04 | norm 5367.9331 | dt 9.768 +type train | step 2424 | loss 111.1983 224.6780 345.2139 532.1118 790.1827 1143.9314 1626.4282 2269.7363 3242.5122 4832.7334 7841.7222 14358.6973 | lr 3.7e-04 | norm 5350.9087 | dt 9.805 +type train | step 2425 | loss 122.1629 253.6179 384.4659 583.7997 853.5610 1215.1555 1701.3535 2350.7947 3310.6118 4939.1274 7949.9087 14509.6299 | lr 3.7e-04 | norm 6058.1743 | dt 9.795 +type train | step 2426 | loss 115.5015 233.6319 360.2955 556.2118 818.7369 1186.8976 1672.2413 2342.6814 3326.7212 4951.5562 8086.2471 14981.2656 | lr 3.7e-04 | norm 5386.5991 | dt 9.787 +type train | step 2427 | loss 110.0373 221.0527 342.5919 530.6464 785.2100 1141.6603 1612.3157 2278.9771 3257.5923 4864.1006 7924.1211 14496.7939 | lr 3.7e-04 | norm 4969.7471 | dt 9.796 +type train | step 2428 | loss 114.2158 234.3234 357.9075 557.1570 819.8606 1189.2146 1675.8843 2358.2886 3319.9097 4957.2842 8127.3921 15094.2988 | lr 3.6e-04 | norm 5331.1270 | dt 9.796 +type train | step 2429 | loss 114.0355 233.5595 357.4225 551.7440 809.4335 1163.3890 1641.6729 2290.5630 3253.7207 4879.9658 7973.1279 14666.1670 | lr 3.6e-04 | norm 5024.2998 | dt 9.795 +type train | step 2430 | loss 118.4913 242.4492 370.3857 574.5849 841.5883 1213.9640 1701.9247 2371.4387 3357.3601 4982.3447 8083.7769 14888.0557 | lr 3.6e-04 | norm 4964.2354 | dt 9.791 +type train | step 2431 | loss 113.7443 230.9818 356.1404 555.8787 822.4894 1197.9111 1705.7198 2422.5659 3435.5020 5121.1948 8303.0068 15160.8291 | lr 3.6e-04 | norm 5356.2847 | dt 9.782 +type train | step 2432 | loss 110.6406 226.3283 350.5858 548.4312 814.0815 1185.3202 1673.7861 2354.3694 3348.0334 4972.3354 8008.9028 14601.1719 | lr 3.6e-04 | norm 4529.4673 | dt 9.793 +type train | step 2433 | loss 111.9434 230.3123 350.8961 546.2065 803.2976 1160.1047 1623.3955 2273.4946 3226.8489 4815.3770 7844.3247 14342.4512 | lr 3.6e-04 | norm 4071.3188 | dt 9.785 +type train | step 2434 | loss 112.0601 228.2173 347.7629 538.8871 797.6608 1155.5865 1643.6787 2313.3337 3297.1191 4938.7271 8039.7314 14740.0498 | lr 3.6e-04 | norm 4305.0122 | dt 9.785 +type train | step 2435 | loss 107.3919 219.0506 338.5613 528.5732 783.4009 1132.4574 1599.8837 2260.7837 3227.7400 4843.1270 7907.0957 14462.6592 | lr 3.6e-04 | norm 4147.1567 | dt 9.790 +type train | step 2436 | loss 108.2045 217.6060 340.2973 535.5190 796.1281 1162.0798 1662.5371 2348.9072 3343.2654 5033.0137 8293.9248 15461.2734 | lr 3.6e-04 | norm 5364.2285 | dt 9.784 +type train | step 2437 | loss 106.8883 216.3835 341.2675 533.5918 789.8985 1144.0298 1624.1008 2290.2930 3284.4714 4988.6025 8234.5771 15351.4199 | lr 3.6e-04 | norm 6299.3564 | dt 9.782 +type train | step 2438 | loss 118.3957 244.0894 373.2801 575.8331 844.4366 1220.5935 1711.6626 2398.9058 3397.7258 5024.8477 8149.5171 14935.2412 | lr 3.6e-04 | norm 4859.3037 | dt 9.795 +type train | step 2439 | loss 109.6208 223.4372 346.4978 539.5323 800.7531 1143.9552 1614.5244 2252.1047 3210.2783 4796.0747 7768.4893 14125.7803 | lr 3.6e-04 | norm 4777.2437 | dt 9.795 +type train | step 2440 | loss 112.2531 228.4285 350.9728 542.9963 802.0319 1151.8906 1618.7571 2261.7571 3241.0347 4818.6470 7816.9663 14408.7920 | lr 3.6e-04 | norm 4460.1777 | dt 9.796 +type train | step 2441 | loss 129.7290 264.4239 391.5566 602.1279 875.8510 1271.6244 1782.5632 2510.3047 3453.1191 5099.6030 8368.3877 15675.8008 | lr 3.6e-04 | norm 11605.9531 | dt 9.770 +type train | step 2442 | loss 115.7315 233.9508 359.4719 556.8008 817.2899 1177.1951 1659.8677 2329.1440 3303.9915 4925.7944 8016.3716 14690.0068 | lr 3.6e-04 | norm 4781.0879 | dt 9.793 +type train | step 2443 | loss 117.6902 239.2449 367.6808 569.0754 835.6125 1207.9119 1693.5385 2368.4226 3344.8357 4976.1475 8043.5874 14749.5801 | lr 3.6e-04 | norm 5080.4644 | dt 9.779 +type train | step 2444 | loss 112.7140 229.7983 357.6996 563.3191 832.0990 1212.8098 1711.0740 2420.3640 3423.1443 5085.7861 8267.6211 15215.5986 | lr 3.6e-04 | norm 5190.7061 | dt 9.791 +type train | step 2445 | loss 114.4526 228.5332 353.2409 548.8332 805.6885 1153.0608 1632.7504 2266.8271 3242.4792 4808.8408 7841.5649 14481.8672 | lr 3.6e-04 | norm 4783.9751 | dt 9.788 +type train | step 2446 | loss 114.3908 234.9057 356.9064 550.5985 809.2990 1172.0967 1650.4832 2319.5378 3295.6333 4938.3916 8075.7300 14796.9551 | lr 3.6e-04 | norm 5181.3198 | dt 9.783 +type train | step 2447 | loss 106.2621 213.6639 335.6564 526.0895 783.2240 1133.6558 1607.8611 2262.1697 3257.7593 4880.2739 7949.2451 14524.6855 | lr 3.6e-04 | norm 4711.2754 | dt 9.799 +type train | step 2448 | loss 125.4742 258.6479 386.9791 593.3626 863.5413 1235.3315 1728.7075 2412.3174 3387.6355 5018.9287 8105.5664 14888.6875 | lr 3.6e-04 | norm 5469.5469 | dt 9.777 +type train | step 2449 | loss 115.2403 233.3568 353.2774 540.0417 796.5872 1158.3325 1637.6991 2314.2349 3299.0896 4909.2983 7925.6943 14523.6025 | lr 3.6e-04 | norm 5865.8018 | dt 9.799 +type train | step 2450 | loss 113.8578 229.8798 354.9647 548.7841 807.1360 1164.3361 1640.3624 2305.9832 3276.4663 4856.5029 7906.7520 14504.9717 | lr 3.6e-04 | norm 4800.5923 | dt 9.791 +type train | step 2451 | loss 118.0144 239.5100 369.8546 567.5992 829.7805 1195.5740 1658.5601 2310.9805 3228.6492 4788.1655 7745.2480 14265.7988 | lr 3.6e-04 | norm 6199.5513 | dt 9.784 +type train | step 2452 | loss 124.5362 257.2805 387.7211 590.8062 853.7165 1214.3419 1687.8447 2341.6587 3307.3601 4940.3184 8044.3218 14850.7334 | lr 3.6e-04 | norm 5037.6245 | dt 9.796 +type train | step 2453 | loss 109.8542 218.7085 341.0557 534.4182 795.6732 1154.6311 1632.0565 2302.8435 3308.5962 4986.5703 8153.1436 14981.1328 | lr 3.6e-04 | norm 6869.8228 | dt 9.787 +type train | step 2454 | loss 115.5766 235.8910 359.0004 551.4071 812.9689 1178.8945 1658.6787 2340.5195 3319.3152 4952.7432 8038.2905 14607.9316 | lr 3.6e-04 | norm 4839.1494 | dt 9.797 +type train | step 2455 | loss 134.3840 273.7460 402.3047 610.2617 880.6479 1306.8054 1809.8854 2539.2810 3487.9138 5142.1968 8428.5635 15177.8369 | lr 3.6e-04 | norm 9113.5078 | dt 9.759 +type train | step 2456 | loss 122.2338 244.9465 377.6448 576.9114 840.1702 1212.5007 1704.3633 2377.4380 3377.5166 5010.1113 8173.2285 15128.9102 | lr 3.6e-04 | norm 7008.4116 | dt 9.794 +type train | step 2457 | loss 125.2787 258.5461 390.1351 594.0286 862.5227 1231.3572 1722.1179 2400.2798 3393.0635 5017.4409 8103.8691 14785.5078 | lr 3.6e-04 | norm 5990.7710 | dt 9.786 +type train | step 2458 | loss 116.8367 236.6866 363.1595 559.2203 817.0601 1169.9508 1646.7075 2304.7385 3263.3354 4852.3154 7889.2866 14493.4551 | lr 3.6e-04 | norm 5337.1304 | dt 9.791 +type train | step 2459 | loss 111.7784 227.4319 347.2105 535.1897 789.6695 1141.7527 1611.8909 2275.4641 3253.5405 4849.9238 7966.6626 14694.5244 | lr 3.6e-04 | norm 5049.8999 | dt 9.785 +type train | step 2460 | loss 117.9773 243.3236 370.3570 565.4816 826.4946 1198.4159 1675.4640 2352.1865 3333.3892 4926.7476 7992.5718 14583.7471 | lr 3.6e-04 | norm 4752.5718 | dt 9.781 +type train | step 2461 | loss 108.8459 222.2889 344.7836 534.9317 787.3936 1132.0800 1601.4398 2237.5457 3196.8162 4801.7905 7896.4082 14664.9727 | lr 3.6e-04 | norm 5079.5332 | dt 9.805 +type train | step 2462 | loss 118.4246 243.6936 370.7052 569.7963 830.9628 1195.5696 1681.6332 2363.3740 3353.4690 4985.0107 8134.0234 14963.5312 | lr 3.6e-04 | norm 4617.7339 | dt 9.786 +type train | step 2463 | loss 114.4975 232.1746 358.5536 557.4332 819.9229 1183.1173 1666.7512 2323.0325 3278.8960 4885.6396 7986.6558 14826.8652 | lr 3.6e-04 | norm 5301.3657 | dt 9.800 +type train | step 2464 | loss 116.9091 238.7103 364.4342 566.2731 834.9777 1209.7803 1700.1737 2398.8022 3393.2622 5059.3164 8206.9512 15064.7266 | lr 3.6e-04 | norm 4385.6387 | dt 9.782 +type train | step 2465 | loss 114.2149 233.8913 357.2051 557.6188 818.6207 1178.9109 1659.3663 2328.6848 3304.9832 4900.9619 7952.6680 14547.4697 | lr 3.6e-04 | norm 4643.2910 | dt 9.793 +type train | step 2466 | loss 113.0004 229.0299 355.8195 553.2742 821.4675 1189.4664 1670.6228 2353.6570 3349.9539 4993.9058 8090.7686 14759.4551 | lr 3.6e-04 | norm 4695.5581 | dt 9.789 +type train | step 2467 | loss 123.0961 249.5668 373.8991 570.9610 826.3029 1183.0181 1646.4834 2311.4658 3249.5500 4808.1792 7832.0225 14399.6904 | lr 3.6e-04 | norm 5807.0415 | dt 9.782 +type train | step 2468 | loss 116.4952 234.6078 359.5730 554.6591 814.0782 1170.8730 1644.2236 2313.3667 3256.4897 4808.1870 7777.4404 14189.1641 | lr 3.6e-04 | norm 4684.5020 | dt 9.778 +type train | step 2469 | loss 109.9187 222.8304 344.2297 533.0627 785.2099 1133.5964 1600.5985 2256.7637 3221.7358 4800.5864 7833.6660 14431.6201 | lr 3.6e-04 | norm 4328.5474 | dt 9.779 +type train | step 2470 | loss 109.4555 222.0623 341.2582 532.3635 782.4695 1132.0312 1594.2557 2233.2905 3186.5908 4766.4478 7774.8398 14308.3076 | lr 3.6e-04 | norm 5190.8442 | dt 9.778 +type train | step 2471 | loss 108.5300 222.3519 341.4153 534.4518 795.5052 1159.4058 1646.3506 2340.8652 3345.5818 5039.3584 8195.2383 14990.7666 | lr 3.6e-04 | norm 5875.8081 | dt 9.780 +type train | step 2472 | loss 108.5168 222.9248 347.8540 546.1340 812.2331 1168.2744 1657.8484 2341.8848 3352.0339 5016.4448 8142.9570 14908.6445 | lr 3.6e-04 | norm 4560.7520 | dt 9.787 +type train | step 2473 | loss 101.0875 210.3836 337.1501 538.9729 801.2866 1149.3010 1627.4032 2300.5813 3305.7771 4955.6362 8128.3774 15036.9990 | lr 3.6e-04 | norm 6487.8833 | dt 9.793 +type train | step 2474 | loss 117.8104 239.3399 364.9508 568.3104 824.0143 1181.5806 1646.7959 2287.1353 3201.8943 4759.7725 7736.1455 14310.5039 | lr 3.6e-04 | norm 5580.9517 | dt 9.804 +type train | step 2475 | loss 120.1688 242.3832 368.6124 570.1351 830.9894 1188.2686 1657.3944 2313.9111 3246.3245 4791.3486 7746.2212 14248.1328 | lr 3.6e-04 | norm 5183.1274 | dt 9.792 +type train | step 2476 | loss 115.9723 233.9903 360.1846 552.9718 812.0843 1156.8529 1625.8113 2274.2834 3258.1499 4855.3228 7947.5298 14618.6826 | lr 3.6e-04 | norm 5131.0913 | dt 9.784 +type train | step 2477 | loss 107.5440 217.5829 338.3775 532.9756 792.8723 1151.0765 1627.5566 2305.3027 3296.8101 4948.5752 8070.0781 14771.9346 | lr 3.6e-04 | norm 4671.9224 | dt 9.796 +type train | step 2478 | loss 116.0090 233.7583 356.3040 552.1835 808.0604 1173.9636 1642.0233 2321.4961 3215.5840 4734.4478 7629.8833 13923.9395 | lr 3.6e-04 | norm 5644.3359 | dt 9.771 +type train | step 2479 | loss 106.6508 217.9882 335.9682 522.5895 778.2585 1128.0184 1589.6241 2239.4412 3222.5154 4834.4077 7868.0454 14358.2432 | lr 3.6e-04 | norm 4368.2739 | dt 9.809 +type train | step 2480 | loss 120.2878 244.8966 373.3959 575.9645 838.4896 1201.8201 1666.6946 2326.8257 3280.2788 4840.1680 7841.8037 14400.0371 | lr 3.6e-04 | norm 4946.1274 | dt 9.814 +type train | step 2481 | loss 123.9401 252.5914 380.5654 588.2064 848.3197 1216.0779 1683.6741 2335.8767 3267.9873 4837.0596 7845.7939 14513.6475 | lr 3.6e-04 | norm 5281.5781 | dt 9.790 +type train | step 2482 | loss 109.2906 221.1266 338.1420 523.8662 776.7482 1119.4364 1581.7091 2214.7622 3173.5750 4751.2773 7730.1626 14264.1416 | lr 3.6e-04 | norm 5883.7910 | dt 9.812 +type train | step 2483 | loss 113.8407 232.1338 357.5455 554.6923 819.5923 1179.2250 1659.1337 2322.9414 3302.5796 4898.8516 7944.4634 14475.2051 | lr 3.6e-04 | norm 4410.6021 | dt 9.811 +type train | step 2484 | loss 108.9521 223.3863 345.6263 534.6957 794.9481 1146.5446 1624.9868 2293.7551 3283.6807 4880.2466 7839.4829 14161.0840 | lr 3.6e-04 | norm 5605.3711 | dt 9.802 +type train | step 2485 | loss 108.8883 230.7397 364.2738 573.7107 850.8660 1228.5232 1746.5243 2466.0774 3525.5654 5295.0303 8533.0625 15574.4189 | lr 3.6e-04 | norm 9270.1133 | dt 9.797 +type train | step 2486 | loss 109.2046 224.1624 351.0211 540.0662 794.5680 1136.2225 1604.2653 2253.1738 3229.2646 4860.0044 7931.7305 14519.9854 | lr 3.6e-04 | norm 4335.5527 | dt 9.806 +type train | step 2487 | loss 127.5137 262.7321 392.7867 601.1799 872.0668 1257.6427 1737.6470 2438.6382 3395.4146 5008.4595 8116.9604 14999.5117 | lr 3.6e-04 | norm 6785.9312 | dt 9.775 +type train | step 2488 | loss 116.1636 237.0482 360.4945 558.9434 820.1964 1184.1008 1665.3145 2346.6101 3317.0349 4947.5762 8029.5010 14703.0508 | lr 3.6e-04 | norm 4995.6812 | dt 9.794 +type train | step 2489 | loss 103.7624 210.3043 330.2644 516.6168 771.4468 1114.8335 1580.6726 2238.1411 3226.5889 4821.8286 7828.1172 14283.0996 | lr 3.6e-04 | norm 5005.5972 | dt 9.784 +type train | step 2490 | loss 108.2511 222.4689 344.6852 543.8291 806.5128 1183.5920 1676.2704 2373.1357 3404.5435 5096.5713 8329.6787 15275.3936 | lr 3.6e-04 | norm 5126.1396 | dt 9.784 +type train | step 2491 | loss 113.0672 229.7319 351.4336 545.9550 805.4223 1162.3545 1636.7821 2315.3530 3300.9697 4937.5732 8012.0825 14673.4102 | lr 3.6e-04 | norm 4318.9980 | dt 9.791 +type train | step 2492 | loss 113.7114 235.2619 358.6728 553.8101 812.2334 1149.5123 1608.8405 2238.9104 3199.5142 4794.4785 7857.8716 14542.6328 | lr 3.6e-04 | norm 5203.4062 | dt 9.793 +type train | step 2493 | loss 106.4140 215.9202 338.3173 535.1036 794.3867 1161.1486 1638.6565 2332.7720 3333.8982 5018.3335 8248.0918 15375.5518 | lr 3.6e-04 | norm 6999.0669 | dt 9.783 +type train | step 2494 | loss 120.3085 246.7376 375.7292 580.0703 841.1305 1219.9594 1694.1724 2376.0466 3305.6809 4872.2407 7870.8027 14489.2803 | lr 3.6e-04 | norm 5167.6680 | dt 9.773 +type train | step 2495 | loss 107.1177 219.0090 341.8051 533.9554 795.0383 1154.3884 1632.2202 2311.5913 3296.1746 4974.2842 8134.8706 15000.7217 | lr 3.6e-04 | norm 5585.2739 | dt 9.784 +type train | step 2496 | loss 108.9228 221.7079 344.7803 539.6280 797.8469 1149.0668 1617.5305 2280.2490 3260.9958 4909.7656 8054.6646 14768.1777 | lr 3.6e-04 | norm 4910.1387 | dt 9.792 +type train | step 2497 | loss 124.7337 254.6307 382.9955 588.9624 855.9324 1226.4668 1708.8140 2374.1108 3298.8000 4872.1411 7839.8003 14326.9902 | lr 3.6e-04 | norm 5240.3950 | dt 9.795 +type train | step 2498 | loss 116.4188 237.8402 361.4167 560.4747 817.5167 1175.2955 1635.6361 2272.7200 3207.3855 4746.4653 7701.3257 14171.9580 | lr 3.6e-04 | norm 4881.1025 | dt 9.789 +type train | step 2499 | loss 109.6592 223.0383 346.1868 539.5226 793.6147 1151.7910 1633.6670 2304.6863 3290.8882 4902.1694 7960.1357 14510.7617 | lr 3.5e-04 | norm 4632.6753 | dt 9.796 +type train | step 2500 | loss 119.6277 243.5866 367.9583 566.0325 824.2596 1176.3845 1645.8694 2295.6045 3244.1804 4826.4023 7801.1865 14305.2627 | lr 3.5e-04 | norm 6754.7695 | dt 9.777 +type train | step 2501 | loss 116.8226 239.8191 365.3003 567.7854 831.5831 1208.4513 1692.2924 2374.6719 3331.9951 4969.3452 8144.6982 15098.1514 | lr 3.5e-04 | norm 5355.2007 | dt 9.792 +type train | step 2502 | loss 111.0391 226.8514 350.9563 545.7408 804.3539 1167.5463 1648.1161 2323.4011 3309.6658 4931.0757 8018.2471 14644.5391 | lr 3.5e-04 | norm 4431.3101 | dt 9.774 +type train | step 2503 | loss 125.1848 245.5026 370.5873 571.0396 841.5738 1231.5729 1752.3190 2475.0308 3462.3479 5175.9668 8344.4668 15361.6699 | lr 3.5e-04 | norm 6942.2173 | dt 9.748 +type train | step 2504 | loss 120.3276 243.8469 372.1122 572.0135 832.0481 1196.9601 1667.4818 2332.5337 3288.3687 4855.7500 7827.6982 14294.7529 | lr 3.5e-04 | norm 4888.9263 | dt 9.785 +type train | step 2505 | loss 114.4880 234.8219 356.5224 548.6366 803.6089 1142.6853 1603.5591 2240.4883 3194.1558 4752.7764 7711.9360 14125.5420 | lr 3.5e-04 | norm 4837.0859 | dt 9.788 +type train | step 2506 | loss 108.2244 221.7298 344.8644 540.5894 797.6706 1151.3428 1615.8589 2275.8257 3250.8887 4869.1011 7968.0674 14602.5371 | lr 3.5e-04 | norm 4808.8013 | dt 9.781 +type train | step 2507 | loss 115.8291 234.1055 357.8816 555.9630 810.1451 1171.0726 1638.7427 2305.2930 3275.4460 4904.3159 8005.6875 14655.0879 | lr 3.5e-04 | norm 4422.9507 | dt 9.790 +type train | step 2508 | loss 115.9849 238.5168 365.2863 563.2830 823.7021 1174.7717 1631.1301 2271.7515 3219.8755 4800.9351 7877.7798 14519.8867 | lr 3.5e-04 | norm 4831.8984 | dt 9.793 +type train | step 2509 | loss 128.4877 252.7672 362.7363 557.6099 826.4700 1247.2496 1753.5426 2518.5129 3544.2341 5330.0845 8504.9414 15416.5957 | lr 3.5e-04 | norm 7310.7964 | dt 9.759 +type train | step 2510 | loss 111.7062 228.4640 350.1849 543.8127 800.4259 1156.1548 1627.7885 2295.4729 3271.7007 4863.3145 7939.9683 14656.1592 | lr 3.5e-04 | norm 5009.6602 | dt 9.793 +type train | step 2511 | loss 120.0692 247.9416 374.0915 571.6241 839.7166 1201.1265 1679.1379 2380.3154 3384.5613 4988.8711 7984.1816 14433.1797 | lr 3.5e-04 | norm 4546.8281 | dt 9.784 +type train | step 2512 | loss 110.0201 225.7016 348.9857 542.1191 803.9306 1153.2634 1624.7218 2285.4402 3275.4883 4889.3379 7946.6333 14479.8496 | lr 3.5e-04 | norm 4555.0615 | dt 9.795 +type train | step 2513 | loss 114.4252 232.5502 358.0313 557.0444 823.6412 1181.7411 1657.5952 2321.8276 3314.9019 4986.8379 8116.6309 14905.1768 | lr 3.5e-04 | norm 6301.5635 | dt 9.789 +type train | step 2514 | loss 117.7888 247.4791 372.7005 583.9329 853.2730 1247.5264 1743.5583 2475.6553 3442.7542 5108.9023 8380.1924 15462.5273 | lr 3.5e-04 | norm 6668.7031 | dt 9.774 +type train | step 2515 | loss 113.3311 231.1054 355.6174 553.7764 818.1346 1178.1702 1650.8569 2309.7192 3278.8420 4900.8047 7969.1230 14592.7256 | lr 3.5e-04 | norm 4847.8906 | dt 9.780 +type train | step 2516 | loss 117.1583 238.3454 361.0988 558.4821 814.3915 1162.3997 1620.3992 2271.2258 3204.6707 4769.7256 7779.2959 14395.3232 | lr 3.5e-04 | norm 5332.4604 | dt 9.794 +type train | step 2517 | loss 110.2015 225.0095 345.2631 542.4894 805.0280 1172.9874 1661.5410 2353.7620 3309.9424 4935.7256 8104.8408 15169.4531 | lr 3.5e-04 | norm 7274.6289 | dt 9.777 +type train | step 2518 | loss 118.3199 242.1692 369.4011 571.0469 840.3871 1206.9484 1680.2527 2349.9963 3288.0249 4847.9150 7840.0532 14323.3525 | lr 3.5e-04 | norm 7734.8276 | dt 9.794 +type train | step 2519 | loss 109.2579 225.3459 347.2336 543.0318 804.8130 1161.5449 1633.0771 2299.4819 3265.4668 4901.0518 8024.7910 14781.6152 | lr 3.5e-04 | norm 4982.2905 | dt 9.800 +type train | step 2520 | loss 120.8049 247.0316 376.9966 583.6613 848.2573 1214.4513 1691.6582 2380.1323 3340.5115 4986.0698 8070.7969 14850.9805 | lr 3.5e-04 | norm 5322.5156 | dt 9.783 +type train | step 2521 | loss 152.7819 317.7234 468.7410 724.4026 1023.7524 1484.6434 2034.8622 2771.2646 3733.2883 5405.5317 8636.9092 15738.0742 | lr 3.5e-04 | norm 8338.0518 | dt 9.758 +type train | step 2522 | loss 112.9255 227.4682 348.7158 546.4615 808.4619 1173.2957 1649.9592 2327.8486 3292.8560 4911.9561 7995.1743 14737.6250 | lr 3.5e-04 | norm 5027.5020 | dt 9.787 +type train | step 2523 | loss 121.0870 245.6959 371.9648 580.0321 852.5511 1261.9153 1759.3883 2524.0693 3510.8906 5146.3062 8217.6260 14927.4590 | lr 3.5e-04 | norm 5951.2197 | dt 9.810 +type train | step 2524 | loss 113.3539 229.4951 351.8954 543.7189 799.6828 1152.3055 1617.7028 2266.8074 3207.5449 4809.3979 7929.4868 14707.5771 | lr 3.5e-04 | norm 6217.8223 | dt 9.800 +type train | step 2525 | loss 115.9589 238.1115 362.0790 561.7550 827.9975 1184.8840 1659.0361 2316.4131 3298.5422 4918.1328 7996.9531 14569.2031 | lr 3.5e-04 | norm 5020.7466 | dt 9.791 +type train | step 2526 | loss 111.7259 229.8610 349.9019 540.6320 802.0413 1152.4210 1621.4604 2292.6448 3274.2354 4919.0024 8092.9932 14883.3164 | lr 3.5e-04 | norm 4496.9541 | dt 9.796 +type train | step 2527 | loss 114.5767 233.4647 358.5912 567.4800 834.7937 1217.7034 1710.3992 2433.0044 3442.9902 5151.0547 8399.2861 15463.4600 | lr 3.5e-04 | norm 5334.4839 | dt 9.812 +type train | step 2528 | loss 122.6167 249.6223 377.5898 580.4268 841.1991 1206.1428 1675.3344 2326.2749 3230.7417 4770.0908 7722.1313 14166.3984 | lr 3.5e-04 | norm 4591.7217 | dt 9.812 +type train | step 2529 | loss 152.9058 320.0855 487.8850 738.1428 1060.2943 1477.0835 2040.2041 2820.4055 4102.5469 5966.3257 9799.3398 18052.1680 | lr 3.5e-04 | norm 13297.9756 | dt 9.775 +type train | step 2530 | loss 126.1666 260.9247 397.6554 612.8702 896.9505 1273.3674 1778.4937 2490.6453 3587.3950 5361.6074 8867.6797 16377.3418 | lr 3.5e-04 | norm 6499.4204 | dt 9.795 +type train | step 2531 | loss 111.2235 227.3001 344.9378 536.3746 792.7622 1154.4370 1623.0483 2285.1455 3226.2505 4873.0957 7955.1987 14722.2188 | lr 3.5e-04 | norm 8277.1387 | dt 9.776 +type train | step 2532 | loss 112.1065 228.1919 351.6720 548.0134 810.1711 1162.4080 1637.1030 2312.1611 3290.4609 4932.8569 8073.5830 14810.2803 | lr 3.5e-04 | norm 5051.1309 | dt 9.797 +type train | step 2533 | loss 119.8424 243.2845 367.0992 571.3431 827.0516 1192.2329 1650.4170 2317.6248 3263.4185 4854.3540 7910.6821 14504.5176 | lr 3.5e-04 | norm 5399.9067 | dt 9.798 +type train | step 2534 | loss 116.7176 240.5359 365.9002 565.7296 826.0283 1187.4103 1650.1736 2309.2334 3252.9717 4829.0229 7880.0449 14468.4053 | lr 3.5e-04 | norm 4880.5190 | dt 9.778 +type train | step 2535 | loss 125.1452 258.7736 391.8823 601.6096 868.4114 1238.5221 1710.6974 2400.2878 3363.2739 4996.0508 8130.2676 15075.4355 | lr 3.5e-04 | norm 5714.1963 | dt 9.782 +type train | step 2536 | loss 117.1490 237.0593 360.4240 552.9084 814.0599 1159.4971 1620.3237 2264.5632 3225.3943 4804.5859 7773.9717 14199.4375 | lr 3.5e-04 | norm 4503.2231 | dt 9.786 +type train | step 2537 | loss 110.3983 232.5590 359.3492 560.0565 829.2094 1206.3267 1693.8406 2412.1086 3408.7932 5123.7754 8394.6582 15528.7715 | lr 3.5e-04 | norm 5955.4487 | dt 9.783 +type train | step 2538 | loss 110.8848 226.3458 348.5385 544.2573 806.7091 1168.0601 1643.0271 2313.1045 3294.7087 4929.8789 8125.7651 14893.8418 | lr 3.5e-04 | norm 5893.2905 | dt 9.786 +type train | step 2539 | loss 110.0570 226.3692 345.8932 537.8882 795.8564 1152.1971 1623.3416 2285.8684 3254.4292 4854.9077 7924.6851 14505.9873 | lr 3.5e-04 | norm 4980.3335 | dt 9.782 +type train | step 2540 | loss 105.1394 215.0955 331.6569 524.2010 777.0643 1128.4871 1598.7008 2262.7690 3267.8528 4885.5303 7985.0684 14610.1270 | lr 3.5e-04 | norm 4838.3999 | dt 9.789 +type train | step 2541 | loss 115.7169 238.1646 361.9582 559.5168 820.4940 1170.8309 1637.8254 2297.9695 3265.5151 4897.6831 8022.8379 14786.8438 | lr 3.5e-04 | norm 5056.7925 | dt 9.795 +type train | step 2542 | loss 110.6452 225.2773 345.2594 539.0886 793.6302 1138.0613 1598.6163 2246.4612 3208.8062 4783.1934 7781.8794 14157.5498 | lr 3.5e-04 | norm 3840.3123 | dt 9.791 +type train | step 2543 | loss 116.7293 239.0267 365.9214 566.3190 831.4420 1196.8417 1675.2063 2340.9644 3321.4004 4949.4614 7983.0864 14490.1660 | lr 3.5e-04 | norm 4368.7671 | dt 9.803 +type train | step 2544 | loss 122.6031 248.5978 370.6700 564.4272 819.8389 1181.1588 1635.6847 2295.7544 3217.8198 4725.0659 7722.1167 14216.5410 | lr 3.5e-04 | norm 5868.8555 | dt 9.776 +type train | step 2545 | loss 126.2959 258.3120 386.1433 593.7675 859.7565 1229.9573 1714.6523 2393.9531 3344.7415 4984.5908 8139.3774 15136.2568 | lr 3.5e-04 | norm 6270.9688 | dt 9.794 +type train | step 2546 | loss 119.7052 244.6903 371.8491 578.3007 840.0397 1211.1222 1685.4039 2362.5149 3306.7881 4945.5654 8083.3066 14980.1445 | lr 3.5e-04 | norm 5527.2075 | dt 9.789 +type train | step 2547 | loss 119.3187 243.4715 368.7558 567.4808 834.4866 1193.5128 1659.7732 2339.0977 3320.6350 4943.8809 8053.5527 14750.2822 | lr 3.5e-04 | norm 5082.3525 | dt 9.785 +type train | step 2548 | loss 108.5915 220.6022 338.7079 530.8407 790.1297 1141.8278 1613.9113 2285.6558 3262.4358 4895.1323 8000.2847 14809.2607 | lr 3.5e-04 | norm 5378.4917 | dt 9.780 +type train | step 2549 | loss 108.7560 223.0720 342.7519 534.2836 789.4665 1133.0934 1594.8562 2252.5261 3223.5767 4819.7393 7885.1831 14414.9395 | lr 3.5e-04 | norm 5080.5454 | dt 9.794 +type train | step 2550 | loss 108.8761 220.5592 340.4052 530.9319 788.6125 1133.1495 1607.5763 2273.2151 3260.5393 4899.6875 7973.3198 14514.1855 | lr 3.5e-04 | norm 4557.9761 | dt 9.790 +type train | step 2551 | loss 109.8227 223.2252 342.8600 535.0289 790.4295 1145.9735 1619.4889 2294.6299 3265.0117 4876.2788 7955.8755 14651.2842 | lr 3.5e-04 | norm 4757.3730 | dt 9.787 +type train | step 2552 | loss 114.5978 232.3986 353.3542 546.0593 801.4025 1146.6901 1606.4839 2257.3152 3204.6646 4775.4824 7793.5078 14153.3574 | lr 3.5e-04 | norm 4385.3027 | dt 9.799 +type train | step 2553 | loss 109.0117 222.4529 345.1578 553.9615 801.9551 1154.8591 1631.2565 2303.0044 3298.7378 4942.9727 8004.7227 14508.7246 | lr 3.5e-04 | norm 5207.4478 | dt 9.792 +type train | step 2554 | loss 110.6919 226.9763 346.2635 537.6399 790.9390 1138.8287 1592.9408 2243.5417 3184.1875 4752.2227 7719.4463 14061.1025 | lr 3.5e-04 | norm 4279.3726 | dt 9.801 +type train | step 2555 | loss 108.7649 222.7447 341.9503 536.9784 796.1589 1156.0145 1634.3472 2313.0522 3282.6477 4915.2290 7987.5107 14581.4004 | lr 3.5e-04 | norm 4127.1260 | dt 9.792 +type train | step 2556 | loss 112.1102 230.1125 350.2068 546.6957 804.3762 1163.7393 1635.5095 2292.3818 3250.8372 4854.7993 7901.3184 14401.6240 | lr 3.5e-04 | norm 3973.3984 | dt 9.798 +type train | step 2557 | loss 132.2449 271.4919 398.8535 608.3118 877.5094 1263.1100 1752.3356 2455.8696 3408.9895 5033.7549 8077.3120 14680.6621 | lr 3.5e-04 | norm 4749.0132 | dt 9.785 +type train | step 2558 | loss 109.8328 225.3909 345.9950 545.1045 801.3805 1149.5670 1612.4685 2254.3330 3158.0037 4727.7173 7731.5347 14222.0762 | lr 3.5e-04 | norm 5760.8867 | dt 9.775 +type train | step 2559 | loss 119.4760 245.0688 368.1029 566.1661 824.3044 1182.2073 1648.9097 2307.7415 3259.9673 4861.5630 7891.1450 14439.9180 | lr 3.5e-04 | norm 4515.8462 | dt 9.790 +type train | step 2560 | loss 106.4247 214.9850 333.9467 521.5469 775.2937 1116.8027 1584.8304 2242.1282 3214.3452 4839.7437 7920.7627 14553.0840 | lr 3.5e-04 | norm 5131.7979 | dt 9.778 +type train | step 2561 | loss 114.3075 232.5970 353.6779 548.4266 807.4968 1168.5100 1633.5479 2304.6997 3275.2749 4864.5166 7906.3662 14391.9043 | lr 3.5e-04 | norm 4470.5405 | dt 9.786 +type train | step 2562 | loss 104.8425 214.2220 330.0267 520.2303 776.2626 1121.3320 1590.6849 2247.7935 3220.2905 4837.7627 7910.3984 14427.3936 | lr 3.5e-04 | norm 4830.5854 | dt 9.787 +type train | step 2563 | loss 109.3588 223.3096 343.6191 534.7460 788.1101 1142.4121 1607.5114 2271.6636 3238.9133 4842.1289 7893.2637 14465.5586 | lr 3.5e-04 | norm 4468.0088 | dt 9.785 +type train | step 2564 | loss 121.3820 247.5049 377.0840 584.1399 847.2355 1205.3948 1676.6434 2352.7231 3339.7656 5028.9658 8191.0449 14998.7783 | lr 3.5e-04 | norm 4503.7065 | dt 9.779 +type train | step 2565 | loss 117.5241 239.1941 363.8875 564.4728 831.9892 1198.0881 1679.4351 2369.2263 3350.3833 4976.8232 8057.4663 14841.7520 | lr 3.5e-04 | norm 5392.5654 | dt 9.774 +type train | step 2566 | loss 108.7980 223.2829 344.6731 538.9194 797.6029 1147.1106 1609.9114 2275.7830 3243.1343 4824.2334 7833.3599 14302.0791 | lr 3.5e-04 | norm 4351.3281 | dt 9.802 +type train | step 2567 | loss 127.9965 263.9811 394.7949 609.1103 873.5938 1279.8379 1764.4103 2490.5720 3373.9580 4934.4985 7832.4736 14234.1650 | lr 3.5e-04 | norm 5596.0762 | dt 9.748 +type train | step 2568 | loss 110.5438 225.4467 346.5847 544.5922 807.0986 1162.8986 1635.9598 2311.5188 3293.1924 4954.1685 8083.9990 14738.2266 | lr 3.4e-04 | norm 4611.1851 | dt 9.802 +type train | step 2569 | loss 107.8663 223.9749 344.7298 539.6328 798.4055 1155.3619 1626.1908 2305.6211 3289.3298 4910.6870 8021.6162 14742.3047 | lr 3.4e-04 | norm 5758.2905 | dt 9.785 +type train | step 2570 | loss 107.0737 218.1754 333.8214 522.0687 775.0378 1123.9382 1577.8589 2241.6191 3187.3076 4750.8433 7749.7295 14209.0000 | lr 3.4e-04 | norm 4628.5112 | dt 9.787 +type train | step 2571 | loss 104.8226 212.4260 328.8750 521.7803 776.0540 1120.9832 1572.0129 2229.1814 3179.9478 4733.8794 7701.8975 14118.1123 | lr 3.4e-04 | norm 5037.9800 | dt 9.787 +type train | step 2572 | loss 111.4420 225.3378 341.4750 531.2593 788.8032 1143.6062 1609.2227 2281.8638 3236.9734 4856.2500 7910.4722 14405.6982 | lr 3.4e-04 | norm 4567.0596 | dt 9.789 +type train | step 2573 | loss 108.2945 221.8927 340.0858 530.1331 785.7249 1124.0762 1582.9692 2232.4180 3192.5234 4763.9678 7752.8003 14099.4736 | lr 3.4e-04 | norm 4483.6914 | dt 9.798 +type train | step 2574 | loss 117.9835 246.0389 370.7108 568.9086 825.6240 1168.9381 1620.7334 2256.2290 3208.8835 4781.2256 7735.9536 14050.0889 | lr 3.4e-04 | norm 3976.7451 | dt 9.802 +type train | step 2575 | loss 108.8881 220.6185 344.0326 540.4082 806.9579 1152.4005 1617.0999 2274.9949 3278.1753 4889.7300 7901.5986 14335.8379 | lr 3.4e-04 | norm 4719.5562 | dt 9.786 +type train | step 2576 | loss 107.6122 220.4029 336.4496 524.5197 772.9263 1128.2389 1606.8582 2285.1055 3235.6514 4866.4287 8006.1426 14862.7617 | lr 3.4e-04 | norm 6899.1689 | dt 9.781 +type train | step 2577 | loss 122.8863 252.3222 379.1975 581.7852 840.3351 1203.5118 1675.7778 2345.0347 3281.1877 4894.6675 7971.1567 14510.2012 | lr 3.4e-04 | norm 4649.7583 | dt 9.784 +type train | step 2578 | loss 113.3940 229.3537 352.0305 547.9053 801.2236 1155.4902 1610.8918 2267.2661 3197.4434 4767.6069 7802.5078 14256.9111 | lr 3.4e-04 | norm 4735.9126 | dt 9.782 +type train | step 2579 | loss 126.3991 258.9344 388.2004 600.7195 878.3746 1260.5449 1757.8082 2477.4751 3421.2888 5069.4204 8335.6152 15327.3906 | lr 3.4e-04 | norm 9915.1748 | dt 9.789 +type train | step 2580 | loss 108.4352 219.3647 337.3092 529.0610 783.3707 1135.3119 1599.2937 2269.9910 3225.3660 4822.4917 7903.3428 14465.0293 | lr 3.4e-04 | norm 5340.2246 | dt 9.773 +type train | step 2581 | loss 108.1698 221.0258 335.2960 531.9038 789.1748 1154.7300 1634.0443 2320.9319 3260.2263 4900.0898 8025.1724 14880.4756 | lr 3.4e-04 | norm 8059.4429 | dt 9.775 +type train | step 2582 | loss 109.9517 225.9071 348.1244 539.6305 796.5911 1143.1656 1600.7385 2256.9993 3208.2595 4786.3740 7782.4131 14274.4971 | lr 3.4e-04 | norm 5234.7163 | dt 9.790 +type train | step 2583 | loss 114.5738 237.3604 363.9716 568.7556 839.6199 1198.8790 1666.8755 2331.3140 3310.4182 4904.4854 7956.7412 14572.9053 | lr 3.4e-04 | norm 4904.5913 | dt 9.785 +type train | step 2584 | loss 121.0441 246.4954 375.7791 584.7836 846.6420 1220.8600 1690.2753 2366.2974 3294.0200 4857.0122 7889.7505 14449.2314 | lr 3.4e-04 | norm 5310.0298 | dt 9.776 +type train | step 2585 | loss 118.1737 243.1213 368.9442 567.4886 836.4400 1191.5430 1651.2715 2298.4924 3247.9927 4816.1743 7787.8833 14126.4180 | lr 3.4e-04 | norm 7028.7422 | dt 9.773 +type train | step 2586 | loss 113.7167 231.3547 353.2647 554.0712 817.6338 1174.0891 1645.4454 2324.3171 3312.4846 4933.6401 7992.3296 14537.4053 | lr 3.4e-04 | norm 5393.2803 | dt 9.786 +type train | step 2587 | loss 105.1798 217.1515 337.3976 535.5443 799.2266 1150.5354 1617.4730 2300.2236 3306.0063 4976.6626 8083.2729 14670.4004 | lr 3.4e-04 | norm 4516.6050 | dt 9.803 +type train | step 2588 | loss 108.8704 220.2148 338.5420 526.8716 782.5134 1125.4910 1589.9369 2252.4753 3226.3005 4803.9399 7744.6182 14048.5996 | lr 3.4e-04 | norm 5576.5161 | dt 9.778 +type train | step 2589 | loss 108.0458 222.5613 340.4504 534.0905 795.8761 1156.6544 1645.1125 2338.2737 3333.9204 4981.9653 8091.2944 14767.1797 | lr 3.4e-04 | norm 5160.6724 | dt 9.795 +type train | step 2590 | loss 114.1165 234.3719 359.4528 557.2994 819.2578 1186.2914 1659.8185 2346.9912 3315.6824 4949.5913 8043.2607 14672.7363 | lr 3.4e-04 | norm 4064.5566 | dt 9.799 +type train | step 2591 | loss 116.3201 239.6221 365.6653 567.4323 825.1913 1187.8284 1651.3064 2331.1040 3274.8088 4881.7705 7996.3555 14779.2412 | lr 3.4e-04 | norm 5042.1514 | dt 9.785 +type train | step 2592 | loss 108.5116 223.9785 349.0820 551.5033 812.8558 1186.7527 1659.9440 2354.8613 3316.7498 4995.1494 8274.9863 15328.0469 | lr 3.4e-04 | norm 7663.0742 | dt 9.785 +type train | step 2593 | loss 104.7096 210.2298 325.6761 512.9753 763.7933 1103.1813 1557.2224 2209.8909 3166.2419 4742.6621 7692.7949 13948.3857 | lr 3.4e-04 | norm 4648.9751 | dt 9.792 +type train | step 2594 | loss 100.2649 218.3537 343.4789 546.5201 828.4465 1203.9451 1699.2429 2450.9563 3490.7910 5314.2949 8727.0283 16003.9297 | lr 3.4e-04 | norm 9129.4766 | dt 9.782 +type train | step 2595 | loss 116.1668 232.8552 358.5698 552.6091 813.4109 1162.5051 1627.4843 2303.9636 3276.7112 4925.9722 8162.0259 15268.9023 | lr 3.4e-04 | norm 7509.8838 | dt 9.786 +type train | step 2596 | loss 111.9677 227.1921 352.0625 552.4670 810.6049 1169.7542 1644.5227 2324.1826 3294.3784 4927.5054 8022.0166 14656.8096 | lr 3.4e-04 | norm 5208.9990 | dt 9.787 +type train | step 2597 | loss 115.9294 237.9817 363.5804 568.4104 835.2820 1203.5061 1679.3380 2374.1428 3369.1265 4981.2661 8042.7148 14705.5264 | lr 3.4e-04 | norm 4767.3887 | dt 9.794 +type train | step 2598 | loss 113.3262 233.4055 348.3407 544.5776 802.4929 1160.7948 1633.7395 2319.8574 3279.9192 4919.7349 8035.0146 14715.8916 | lr 3.4e-04 | norm 4519.6113 | dt 9.793 +type train | step 2599 | loss 112.5756 229.0067 349.4735 545.6408 803.7078 1140.7107 1598.8794 2246.3972 3183.7625 4752.9180 7728.0112 14079.5205 | lr 3.4e-04 | norm 5225.5757 | dt 9.789 +type train | step 2600 | loss 111.3880 227.3309 351.1726 550.5377 814.7946 1175.0948 1652.7981 2342.8857 3312.1934 4934.3848 7994.9185 14531.5537 | lr 3.4e-04 | norm 4482.0552 | dt 9.793 +type train | step 2601 | loss 107.0435 217.1017 331.4399 522.2964 775.6418 1121.8696 1589.9048 2250.1946 3227.3887 4805.0098 7837.8379 14263.5918 | lr 3.4e-04 | norm 4430.3589 | dt 9.782 +type train | step 2602 | loss 109.0656 220.9033 337.7728 526.9156 784.6426 1132.8623 1594.2545 2258.2346 3202.1855 4769.9033 7734.7886 14041.0391 | lr 3.4e-04 | norm 4331.5078 | dt 9.793 +type train | step 2603 | loss 108.2813 220.1165 341.1359 536.5803 790.1494 1141.4813 1594.2025 2257.8711 3195.3770 4765.1904 7764.2412 14180.1270 | lr 3.4e-04 | norm 5309.7593 | dt 9.779 +type train | step 2604 | loss 105.6694 216.3163 334.5230 530.4289 788.7769 1140.1558 1608.0844 2276.5215 3245.2493 4847.6270 7844.9121 14261.5801 | lr 3.4e-04 | norm 4533.2124 | dt 9.784 +type train | step 2605 | loss 111.4302 228.1559 350.2175 541.6717 801.6268 1137.2556 1589.1207 2232.6975 3175.0840 4760.0688 7701.7046 14009.8301 | lr 3.4e-04 | norm 4342.9209 | dt 9.794 +type train | step 2606 | loss 114.7127 234.2967 353.4774 554.0688 808.0608 1170.7875 1634.3942 2309.2849 3248.0845 4819.7158 7845.6128 14355.2061 | lr 3.4e-04 | norm 4386.8179 | dt 9.787 +type train | step 2607 | loss 112.7236 231.8124 348.6111 542.8840 798.9672 1153.9558 1616.2368 2289.2695 3243.6953 4881.6938 8024.2163 14702.3018 | lr 3.4e-04 | norm 4868.6646 | dt 9.782 +type train | step 2608 | loss 104.9873 208.3717 326.1425 529.7819 778.0957 1130.4397 1585.6428 2259.5486 3247.9731 4923.5078 8218.0518 15362.3203 | lr 3.4e-04 | norm 7889.5317 | dt 9.775 +type train | step 2609 | loss 102.2488 208.0957 322.0548 509.6853 759.8186 1107.7825 1575.0381 2241.8730 3204.0349 4791.3857 7791.8335 14141.7480 | lr 3.4e-04 | norm 5067.2817 | dt 9.774 +type train | step 2610 | loss 108.9728 227.9411 347.3304 550.2223 818.6451 1194.3158 1693.3212 2419.1760 3457.4426 5213.9336 8521.3340 15502.8916 | lr 3.4e-04 | norm 5848.9458 | dt 9.780 +type train | step 2611 | loss 103.1908 208.4238 323.9532 508.7036 757.1082 1096.6469 1550.0515 2217.7371 3165.4731 4776.0205 7821.4048 14231.8340 | lr 3.4e-04 | norm 4864.8105 | dt 9.783 +type train | step 2612 | loss 110.2889 226.3857 346.7444 544.0052 807.6339 1169.9805 1647.6202 2336.6025 3328.3506 4996.6533 8132.1104 14836.9678 | lr 3.4e-04 | norm 4782.1929 | dt 9.789 +type train | step 2613 | loss 111.5050 228.1468 344.9617 539.5770 798.6182 1148.6357 1619.0870 2293.7544 3264.4138 4892.8237 7941.1294 14514.2891 | lr 3.4e-04 | norm 5067.1880 | dt 9.789 +type train | step 2614 | loss 100.9611 201.4223 316.3300 498.2061 747.1907 1089.7852 1551.6077 2227.4392 3204.4121 4836.5938 7962.2944 14546.8076 | lr 3.4e-04 | norm 6157.0552 | dt 9.790 +type train | step 2615 | loss 106.7389 215.4963 331.1970 518.6619 769.2629 1111.5167 1562.7306 2214.0364 3156.9551 4717.9751 7684.4321 13924.2188 | lr 3.4e-04 | norm 4310.1494 | dt 9.794 +type train | step 2616 | loss 109.3704 223.6288 342.8922 537.6794 793.5177 1147.6100 1614.2780 2288.1248 3240.0828 4837.8462 7906.5215 14525.8193 | lr 3.4e-04 | norm 4987.2305 | dt 9.789 +type train | step 2617 | loss 112.5179 231.4375 352.0165 548.6571 806.8571 1166.9467 1638.7996 2318.9238 3288.6838 4891.0571 7891.6675 14318.9883 | lr 3.4e-04 | norm 4704.0000 | dt 9.781 +type train | step 2618 | loss 102.8562 211.5507 326.1740 513.0852 764.2064 1105.1904 1560.3408 2211.9519 3166.5713 4745.5386 7715.5044 14050.9053 | lr 3.4e-04 | norm 4803.4624 | dt 9.785 +type train | step 2619 | loss 110.4637 226.0747 342.9049 531.8351 783.2567 1126.4255 1582.1261 2243.8992 3189.3926 4760.6250 7715.0801 14019.6025 | lr 3.4e-04 | norm 4140.2046 | dt 9.798 +type train | step 2620 | loss 116.9930 241.7684 360.3719 553.9351 805.9490 1151.3634 1605.0404 2248.8425 3164.9561 4746.0347 7745.0742 14092.6211 | lr 3.4e-04 | norm 4560.5195 | dt 9.794 +type train | step 2621 | loss 101.7960 209.6917 327.0160 522.8734 785.0073 1142.8508 1620.8025 2314.2256 3320.4639 5023.9521 8192.9629 14993.4551 | lr 3.4e-04 | norm 5540.8911 | dt 9.791 +type train | step 2622 | loss 119.9085 247.3274 363.6317 558.3986 814.8580 1180.7703 1639.0804 2313.5000 3226.4624 4821.6074 7881.2744 14413.9541 | lr 3.4e-04 | norm 5462.7393 | dt 9.767 +type train | step 2623 | loss 113.6956 232.6299 353.3489 547.3865 806.1473 1156.3824 1623.8882 2307.8955 3277.0591 4934.5562 8052.2920 14710.0898 | lr 3.4e-04 | norm 6133.7305 | dt 9.786 +type train | step 2624 | loss 112.0346 227.3651 345.9189 543.0511 799.2988 1157.8557 1616.2487 2294.8582 3239.2678 4853.8584 7904.7588 14412.9541 | lr 3.4e-04 | norm 4184.7935 | dt 9.794 +type train | step 2625 | loss 107.3819 219.0626 335.3162 522.0461 772.8044 1118.9391 1566.2712 2220.5505 3139.5286 4704.6069 7662.8252 13987.3975 | lr 3.4e-04 | norm 4706.3618 | dt 9.788 +type train | step 2626 | loss 115.0266 235.5042 358.2271 559.4955 815.2169 1188.3777 1658.6926 2370.0151 3293.7219 4837.9238 7784.4312 13979.9561 | lr 3.4e-04 | norm 4366.5815 | dt 9.773 +type train | step 2627 | loss 102.7152 205.1728 316.7784 500.3333 748.7160 1080.8110 1520.1184 2161.0300 3099.0950 4650.0581 7627.6572 13876.6055 | lr 3.4e-04 | norm 4304.5938 | dt 9.776 +type train | step 2628 | loss 105.1569 214.6610 332.2578 521.2111 774.7833 1119.5127 1571.2125 2232.8347 3174.7139 4769.1157 7792.9536 14184.3359 | lr 3.4e-04 | norm 3781.6318 | dt 9.792 +type train | step 2629 | loss 115.6035 237.5507 354.7592 555.3773 809.8511 1164.4802 1618.2024 2274.4844 3193.8672 4761.3901 7758.3804 14179.0869 | lr 3.4e-04 | norm 5137.2456 | dt 9.776 +type train | step 2630 | loss 103.4615 207.9466 322.9395 508.2451 753.5691 1093.3682 1539.8323 2202.1858 3153.6467 4742.6797 7780.5718 14176.1855 | lr 3.4e-04 | norm 4931.7402 | dt 9.793 +type train | step 2631 | loss 112.6605 229.8072 352.1364 547.9937 803.3043 1150.4707 1607.1461 2269.6875 3219.8240 4832.8379 7857.5586 14265.6133 | lr 3.4e-04 | norm 4341.2090 | dt 9.790 +type train | step 2632 | loss 105.4734 211.4890 325.0927 511.4205 760.2523 1105.1753 1561.4736 2234.3992 3179.7219 4779.5010 7819.6572 14246.7012 | lr 3.4e-04 | norm 4613.8140 | dt 9.788 +type train | step 2633 | loss 109.9999 226.6336 348.5298 544.0518 804.9235 1154.5520 1620.7329 2291.7456 3272.2839 4906.0186 8013.9497 14572.4131 | lr 3.4e-04 | norm 4369.6665 | dt 9.795 +type train | step 2634 | loss 109.8228 225.5780 345.0639 534.5433 786.2859 1132.3026 1587.0007 2246.0173 3188.3062 4814.2466 7877.1113 14344.0518 | lr 3.4e-04 | norm 4195.7837 | dt 9.823 +type train | step 2635 | loss 120.1133 252.2800 373.3106 570.2848 830.7342 1201.1682 1662.6797 2353.6416 3261.1841 4859.4302 7966.2163 14625.1094 | lr 3.4e-04 | norm 6985.8911 | dt 9.772 +type train | step 2636 | loss 116.3005 239.4981 362.1606 569.5365 831.8074 1201.0771 1674.5881 2359.0498 3279.8848 4867.6284 7935.3555 14581.6504 | lr 3.4e-04 | norm 6062.3735 | dt 9.777 +type train | step 2637 | loss 111.0342 225.9468 345.6778 545.2999 808.1956 1157.0193 1627.6805 2299.0876 3281.1123 4890.0103 7940.8379 14452.4404 | lr 3.4e-04 | norm 4824.2964 | dt 9.776 +type train | step 2638 | loss 110.6272 224.3088 346.1071 539.7415 797.9651 1153.0741 1611.5913 2282.1650 3221.0217 4812.0171 7874.6509 14396.5469 | lr 3.3e-04 | norm 4743.6450 | dt 9.785 +type train | step 2639 | loss 111.8023 231.1646 353.2054 544.7628 800.6483 1148.1666 1613.2209 2287.6016 3230.1104 4799.3496 7811.0513 14166.2148 | lr 3.3e-04 | norm 4932.0449 | dt 9.785 +type train | step 2640 | loss 111.8994 226.8609 347.7426 540.9010 796.2631 1140.6777 1587.0763 2254.6221 3206.6516 4786.3906 7799.6323 14126.6006 | lr 3.3e-04 | norm 4291.9238 | dt 9.782 +type train | step 2641 | loss 115.2219 234.6682 353.6049 544.3000 799.6838 1156.2761 1622.1885 2294.0610 3253.6499 4865.6567 7901.1240 14213.0449 | lr 3.3e-04 | norm 4457.0132 | dt 9.787 +type train | step 2642 | loss 113.9914 231.8846 355.3180 566.0651 827.4161 1195.6858 1672.7538 2373.5645 3373.3477 5092.4849 8349.6201 15290.6445 | lr 3.3e-04 | norm 6246.2935 | dt 9.781 +type train | step 2643 | loss 116.3936 239.7114 356.9491 552.5369 811.6301 1164.4528 1628.5737 2291.8774 3209.3406 4777.2437 7701.5015 13988.3086 | lr 3.3e-04 | norm 4752.0283 | dt 9.778 +type train | step 2644 | loss 106.3789 216.0188 333.0773 528.1815 781.2125 1134.3004 1592.7500 2262.3440 3210.6943 4815.0063 7861.5059 14282.6660 | lr 3.3e-04 | norm 4141.4595 | dt 9.783 +type train | step 2645 | loss 118.6237 244.3751 364.6295 563.0068 823.4850 1188.5603 1651.2117 2329.7971 3281.8750 4881.3911 7924.6743 14488.7354 | lr 3.3e-04 | norm 4217.9302 | dt 10.100 +type train | step 2646 | loss 112.6640 230.5741 349.4077 539.2006 793.4463 1139.4484 1586.3401 2232.7715 3173.9731 4737.4810 7701.8262 13949.4600 | lr 3.3e-04 | norm 3813.0532 | dt 9.796 +type train | step 2647 | loss 99.4948 200.5759 312.1706 493.5343 739.5445 1069.6543 1515.9934 2161.4893 3105.5266 4678.4927 7634.3745 13856.6094 | lr 3.3e-04 | norm 4422.5317 | dt 9.776 +type train | step 2648 | loss 111.8816 227.0588 347.2741 543.9243 797.5645 1148.0911 1601.1044 2268.5161 3216.0378 4800.4463 7792.3062 14139.0625 | lr 3.3e-04 | norm 4658.0854 | dt 9.789 +type train | step 2649 | loss 112.6615 231.1432 349.5804 543.7039 799.7098 1154.3976 1615.5632 2299.3354 3258.3967 4887.3735 7981.9761 14551.8135 | lr 3.3e-04 | norm 4918.9668 | dt 9.796 +type train | step 2650 | loss 110.8029 228.4798 344.4929 534.6624 788.4591 1131.0010 1579.5911 2218.3508 3133.3525 4660.4199 7555.4375 13677.9629 | lr 3.3e-04 | norm 5366.4258 | dt 9.786 +type train | step 2651 | loss 115.7424 237.3649 354.6523 551.9582 811.3466 1189.2236 1674.8934 2375.8066 3334.1462 4967.6636 8113.5732 14945.5898 | lr 3.3e-04 | norm 5554.0430 | dt 9.780 +type train | step 2652 | loss 112.0071 229.0626 345.0163 537.0770 794.3258 1155.2561 1632.4365 2325.2078 3289.1538 4913.4126 7974.3906 14511.6494 | lr 3.3e-04 | norm 5054.0366 | dt 9.780 +type train | step 2653 | loss 112.8147 232.5799 355.8768 559.0196 818.8804 1185.3083 1665.7540 2350.1116 3298.0525 4944.8975 8024.8496 14620.1230 | lr 3.3e-04 | norm 5331.7676 | dt 9.786 +type train | step 2654 | loss 109.9105 223.8664 340.0851 530.5239 783.9946 1134.7195 1595.0679 2256.5635 3206.3193 4830.9253 7927.8066 14561.4033 | lr 3.3e-04 | norm 4265.6152 | dt 9.788 +type train | step 2655 | loss 119.8655 247.9085 370.7235 569.6296 825.5272 1203.5281 1681.5989 2375.6011 3327.0002 4933.1055 7979.8960 14574.2773 | lr 3.3e-04 | norm 6233.5972 | dt 9.771 +type train | step 2656 | loss 106.0525 218.2740 333.2049 524.1033 776.4087 1124.0377 1573.7576 2237.1484 3191.2922 4787.8813 7851.3560 14219.4805 | lr 3.3e-04 | norm 4172.7866 | dt 9.787 +type train | step 2657 | loss 106.5664 216.8055 332.2210 518.8559 771.9890 1113.5818 1562.2646 2216.0894 3171.7788 4766.9209 7762.5420 14099.3467 | lr 3.3e-04 | norm 4267.3242 | dt 9.795 +type train | step 2658 | loss 105.9033 212.5597 327.3852 516.2715 768.8620 1109.5236 1560.7334 2220.4956 3185.5767 4790.8184 7824.3242 14206.6855 | lr 3.3e-04 | norm 4099.7720 | dt 9.791 +type train | step 2659 | loss 104.6367 212.9116 326.2546 511.3687 763.4832 1101.4132 1542.8439 2191.4824 3130.3083 4678.9922 7659.2427 13901.9688 | lr 3.3e-04 | norm 4070.4546 | dt 9.786 +type train | step 2660 | loss 115.9161 239.3361 360.5461 557.6387 829.0255 1199.4531 1674.2379 2371.9285 3337.1853 4959.2568 8024.9331 14431.2559 | lr 3.3e-04 | norm 5329.1699 | dt 9.779 +type train | step 2661 | loss 103.8239 211.4867 328.4370 518.2819 770.0233 1112.1140 1556.9152 2206.0662 3154.7532 4734.4722 7705.3696 13936.3457 | lr 3.3e-04 | norm 4091.9817 | dt 9.799 +type train | step 2662 | loss 115.5486 234.3117 353.2358 548.9684 809.5480 1162.6163 1616.9828 2284.1035 3245.6047 4847.4541 7911.3716 14490.3418 | lr 3.3e-04 | norm 4564.9390 | dt 9.781 +type train | step 2663 | loss 114.2236 232.1928 349.3640 537.3176 793.1732 1133.3662 1578.0061 2222.2917 3139.8979 4722.0244 7825.2808 14362.1133 | lr 3.3e-04 | norm 5387.8950 | dt 9.782 +type train | step 2664 | loss 112.4726 230.0266 343.4070 526.9081 775.1308 1113.0658 1560.2938 2207.1221 3113.8938 4667.7905 7640.0498 13875.5283 | lr 3.3e-04 | norm 4699.0103 | dt 9.778 +type train | step 2665 | loss 114.1890 235.2837 354.9594 548.3175 805.4943 1169.4336 1637.5677 2329.6177 3279.8472 4905.2725 7960.6128 14472.3193 | lr 3.3e-04 | norm 5372.0347 | dt 9.774 +type train | step 2666 | loss 113.2434 231.1990 349.6316 537.8885 786.5165 1130.2794 1585.9224 2245.5779 3184.8496 4765.0806 7775.4038 14132.8359 | lr 3.3e-04 | norm 4964.4907 | dt 9.794 +type train | step 2667 | loss 104.9889 221.3169 344.9712 546.7286 815.8512 1172.9839 1656.2988 2371.4324 3395.9976 5177.0000 8399.0186 15348.8594 | lr 3.3e-04 | norm 9479.6973 | dt 9.776 +type train | step 2668 | loss 103.6178 223.7765 350.7352 558.2600 835.4464 1212.3806 1717.9026 2486.1526 3542.1067 5428.4346 8795.7529 15968.6689 | lr 3.3e-04 | norm 12508.8594 | dt 9.760 +type train | step 2669 | loss 100.0560 213.3545 335.2587 537.5301 813.0246 1189.6238 1700.9248 2459.0469 3489.2371 5364.7285 8726.9922 15902.3965 | lr 3.3e-04 | norm 11824.2617 | dt 9.760 +type train | step 2670 | loss 108.7779 226.3420 349.9922 547.7084 816.1275 1172.6139 1654.1041 2366.1270 3368.7891 5113.3369 8310.0918 14959.1826 | lr 3.3e-04 | norm 6770.8408 | dt 9.780 +type train | step 2671 | loss 113.1413 232.4863 353.4072 541.3929 794.4399 1146.5541 1607.1823 2282.4360 3222.6377 4782.8340 7770.0586 14089.4180 | lr 3.3e-04 | norm 5685.4922 | dt 9.794 +type train | step 2672 | loss 108.7817 223.4093 340.6908 532.6755 787.4000 1137.7332 1600.7791 2278.1382 3230.0137 4855.5488 7925.2251 14485.6025 | lr 3.3e-04 | norm 6137.0269 | dt 9.796 +type train | step 2673 | loss 105.2562 213.8306 332.5588 523.4455 782.3260 1130.6349 1594.8608 2265.7468 3240.8438 4863.3467 7954.9326 14556.8027 | lr 3.3e-04 | norm 6757.5708 | dt 9.791 +type train | step 2674 | loss 116.3447 236.6408 356.7029 556.2928 818.5529 1178.6477 1647.5278 2319.2207 3292.7124 4931.0312 8039.7646 14712.8115 | lr 3.3e-04 | norm 6641.5195 | dt 9.783 +type train | step 2675 | loss 111.2397 227.7601 346.6985 538.6702 789.2681 1127.0917 1577.2756 2221.1748 3147.5154 4708.0503 7633.3628 13891.5781 | lr 3.3e-04 | norm 5795.3779 | dt 9.797 +type train | step 2676 | loss 105.9699 218.4520 336.0914 527.6729 784.0489 1121.3363 1568.4095 2220.6221 3182.8796 4762.2148 7784.6411 14102.5244 | lr 3.3e-04 | norm 4925.9326 | dt 9.786 +type train | step 2677 | loss 106.0322 216.3667 331.6696 518.6590 767.4144 1108.4661 1562.3842 2223.7795 3175.1873 4786.9272 7819.9175 14146.9141 | lr 3.3e-04 | norm 5034.7930 | dt 9.785 +type train | step 2678 | loss 112.5866 232.9916 349.2462 547.3670 802.1040 1183.5216 1672.2877 2387.8987 3362.2058 4989.3032 8052.0967 14594.3682 | lr 3.3e-04 | norm 5061.0234 | dt 9.784 +type train | step 2679 | loss 105.5151 215.1158 329.6563 517.2461 765.9282 1112.6238 1569.6433 2236.7544 3173.6479 4758.7710 7788.9141 14239.6074 | lr 3.3e-04 | norm 4796.9702 | dt 9.791 +type train | step 2680 | loss 105.9553 215.4903 329.6423 521.2405 770.7145 1114.1559 1566.7557 2225.6934 3164.1016 4738.6865 7713.6460 14010.5479 | lr 3.3e-04 | norm 4361.4771 | dt 9.791 +type train | step 2681 | loss 110.1846 224.2773 342.6859 531.9705 785.6207 1129.8058 1576.6775 2229.1711 3161.3823 4726.7383 7663.8711 13919.8438 | lr 3.3e-04 | norm 4037.3213 | dt 9.782 +type train | step 2682 | loss 121.5667 246.3119 367.8546 563.8196 826.0998 1185.6526 1659.2710 2358.0525 3330.0012 5015.6221 8224.6152 15122.4932 | lr 3.3e-04 | norm 6074.0762 | dt 9.788 +type train | step 2683 | loss 108.2328 221.2005 340.2417 529.5559 784.8107 1137.5535 1589.3402 2258.0674 3192.3330 4781.6694 7800.5762 14188.4443 | lr 3.3e-04 | norm 4523.4561 | dt 9.783 +type train | step 2684 | loss 111.9228 227.4771 344.0931 532.5634 782.2928 1123.9623 1566.1404 2210.0474 3120.9673 4647.7778 7525.0200 13573.0410 | lr 3.3e-04 | norm 4498.6504 | dt 9.801 +type train | step 2685 | loss 105.7990 213.4777 327.0510 513.5146 758.6389 1100.7498 1550.5436 2205.9302 3137.9500 4693.4707 7639.0879 13802.4463 | lr 3.3e-04 | norm 4704.6040 | dt 9.776 +type train | step 2686 | loss 107.4705 221.4759 338.2371 533.1207 785.9370 1133.4624 1585.1764 2250.9612 3197.4243 4804.4409 7862.3203 14309.3301 | lr 3.3e-04 | norm 4442.1196 | dt 9.801 +type train | step 2687 | loss 104.9005 211.2475 326.1658 514.9146 769.7687 1115.8469 1577.4419 2253.2939 3220.2410 4857.5615 7998.5361 14584.3848 | lr 3.3e-04 | norm 4922.0161 | dt 9.794 +type train | step 2688 | loss 105.5715 217.3964 335.6729 530.5997 793.6737 1150.2511 1629.1824 2332.1636 3332.4346 5002.0977 8175.4351 14835.2881 | lr 3.3e-04 | norm 5574.7134 | dt 9.792 +type train | step 2689 | loss 108.1538 220.9765 336.9677 523.8763 773.2045 1110.2427 1555.0043 2192.0564 3098.3633 4637.0264 7552.3770 13693.8369 | lr 3.3e-04 | norm 4329.0151 | dt 9.783 +type train | step 2690 | loss 116.2847 236.3422 361.0022 561.1592 828.0355 1184.2986 1650.3274 2345.9846 3293.1831 4962.3091 8173.6333 14971.6123 | lr 3.3e-04 | norm 5824.3516 | dt 9.771 +type train | step 2691 | loss 104.0689 213.6562 328.4953 514.1099 769.4974 1108.1449 1566.2627 2237.5000 3199.7400 4836.7935 7943.7163 14455.2305 | lr 3.3e-04 | norm 4917.3311 | dt 9.773 +type train | step 2692 | loss 110.2331 227.7478 348.5600 542.0371 800.8256 1152.1375 1614.6809 2288.0327 3241.6755 4837.1133 7875.3774 14284.2148 | lr 3.3e-04 | norm 5506.7217 | dt 9.794 +type train | step 2693 | loss 108.6822 223.7862 339.5932 529.9681 785.1313 1133.2365 1589.0277 2255.1145 3206.0327 4804.2632 7805.3740 14121.7148 | lr 3.3e-04 | norm 4652.6606 | dt 9.791 +type train | step 2694 | loss 100.6505 204.6697 317.9247 506.9174 759.6047 1111.6519 1579.5520 2261.3179 3218.7146 4827.1880 7904.1035 14516.2949 | lr 3.3e-04 | norm 5923.2339 | dt 9.781 +type train | step 2695 | loss 108.9900 223.3646 340.6238 536.0238 796.0999 1158.5901 1628.2817 2325.8350 3275.5347 4909.8701 8059.5703 14798.1572 | lr 3.3e-04 | norm 7793.3032 | dt 9.777 +type train | step 2696 | loss 113.3260 230.8195 353.0993 549.2718 807.0863 1161.8466 1624.2013 2303.6760 3245.2815 4837.2725 7846.6104 14269.6084 | lr 3.3e-04 | norm 4666.7339 | dt 9.778 +type train | step 2697 | loss 107.8076 220.3752 337.3937 524.9536 776.7478 1115.3998 1571.6904 2229.5508 3173.0210 4762.6641 7728.5234 13968.3740 | lr 3.3e-04 | norm 4528.3149 | dt 9.778 +type train | step 2698 | loss 109.5281 226.1448 342.4418 531.9876 784.1819 1142.2457 1586.8198 2254.1387 3161.0176 4714.1831 7637.5054 13911.6055 | lr 3.3e-04 | norm 5043.6548 | dt 9.769 +type train | step 2699 | loss 109.4695 223.5875 340.3261 531.0754 787.8549 1132.1600 1586.8389 2238.6658 3192.0730 4796.0767 7807.1577 14134.7002 | lr 3.3e-04 | norm 4571.6924 | dt 9.780 +type train | step 2700 | loss 114.4021 235.8520 359.6698 559.8142 830.8049 1176.0376 1652.4391 2312.8779 3291.9648 4874.1250 7865.2891 14077.9844 | lr 3.3e-04 | norm 6382.0859 | dt 9.804 +type train | step 2701 | loss 104.4755 213.8709 324.9818 511.4583 760.1512 1106.1763 1558.4155 2232.1672 3170.6868 4786.6177 7799.8389 14131.9316 | lr 3.3e-04 | norm 4690.6699 | dt 9.793 +type train | step 2702 | loss 104.5805 212.3745 326.7215 516.7274 768.5042 1119.5972 1574.3730 2248.8892 3210.4863 4817.2783 7831.3677 14125.2373 | lr 3.3e-04 | norm 4353.3403 | dt 9.798 +type train | step 2703 | loss 97.1128 195.8436 303.9033 485.5701 730.1888 1055.4825 1492.3997 2133.4592 3071.3613 4610.5264 7503.4062 13580.4307 | lr 3.3e-04 | norm 4514.6182 | dt 9.786 +type train | step 2704 | loss 102.8504 209.4958 326.5176 524.4358 790.8467 1164.5846 1654.9458 2375.2214 3364.4187 5085.7021 8294.7725 15100.3389 | lr 3.3e-04 | norm 7694.3530 | dt 9.783 +type train | step 2705 | loss 114.2661 231.5780 351.9601 547.2239 801.9187 1156.3333 1608.1556 2271.2068 3198.3269 4744.8916 7707.9478 13958.1318 | lr 3.3e-04 | norm 4253.6826 | dt 9.784 +type train | step 2706 | loss 103.7365 209.8876 324.4106 514.6559 763.5528 1099.7467 1545.7970 2195.1738 3131.1189 4685.8154 7665.6372 13884.1709 | lr 3.2e-04 | norm 3904.6218 | dt 9.792 +type train | step 2707 | loss 107.5076 220.1845 338.1982 529.2277 786.4042 1132.2971 1589.4023 2252.9070 3207.5781 4799.0244 7827.3291 14081.8604 | lr 3.2e-04 | norm 4372.0327 | dt 9.787 +type train | step 2708 | loss 111.2751 227.5600 345.6533 541.6109 800.0208 1157.8589 1604.6174 2270.8767 3179.0552 4743.9067 7698.4434 13958.1699 | lr 3.2e-04 | norm 4330.6968 | dt 9.776 +type train | step 2709 | loss 131.3967 271.6927 404.0010 625.4266 895.8286 1250.9197 1690.4075 2309.6846 3147.0479 4599.8652 7277.7368 13277.3936 | lr 3.2e-04 | norm 6232.6328 | dt 9.747 +type train | step 2710 | loss 106.4922 218.1659 332.6542 519.2332 772.5070 1115.9233 1570.0913 2224.9705 3165.2051 4735.5332 7673.7051 13819.9570 | lr 3.2e-04 | norm 4381.8047 | dt 9.788 +type train | step 2711 | loss 110.7148 226.0066 342.0600 539.4964 785.6836 1134.5328 1594.1842 2278.6682 3226.2441 4835.4497 7882.4839 14365.6191 | lr 3.2e-04 | norm 4434.5762 | dt 9.795 +type train | step 2712 | loss 116.0502 240.2776 368.1559 574.0764 844.9727 1203.4973 1669.6572 2347.3130 3296.3213 4908.5664 7962.4932 14471.4727 | lr 3.2e-04 | norm 5016.8301 | dt 9.784 +type train | step 2713 | loss 101.1843 205.8236 321.9413 508.1974 759.9088 1106.9171 1561.8712 2229.0796 3182.0164 4769.0879 7754.9980 13991.4531 | lr 3.2e-04 | norm 4041.2549 | dt 9.773 +type train | step 2714 | loss 108.4964 222.4921 340.6689 532.6682 788.5165 1130.7527 1580.1708 2247.5012 3192.2573 4790.9990 7819.6445 14171.6855 | lr 3.2e-04 | norm 4042.5813 | dt 9.793 +type train | step 2715 | loss 103.0105 210.8171 325.4137 521.9153 775.7147 1123.3175 1581.4733 2255.4724 3218.0771 4808.1641 7831.9941 14126.3564 | lr 3.2e-04 | norm 4962.8633 | dt 9.790 +type train | step 2716 | loss 104.5711 214.7954 331.0717 521.1828 778.1047 1120.1642 1578.4281 2243.1860 3209.5103 4841.1650 7915.8779 14329.2295 | lr 3.2e-04 | norm 3672.2498 | dt 9.788 +type train | step 2717 | loss 104.9403 213.8768 329.6557 516.6597 768.6816 1118.0437 1573.1644 2244.0369 3173.9075 4746.4355 7712.9395 13916.2539 | lr 3.2e-04 | norm 3635.2788 | dt 9.787 +type train | step 2718 | loss 104.3489 211.1716 326.6948 513.4835 766.7873 1114.0916 1570.1256 2232.0115 3178.3901 4766.2622 7786.5664 14026.1699 | lr 3.2e-04 | norm 4043.4336 | dt 9.781 +type train | step 2719 | loss 102.2904 207.1274 319.1871 503.0751 756.1073 1098.5580 1546.8955 2207.5161 3147.2437 4710.9873 7642.2646 13801.3232 | lr 3.2e-04 | norm 4256.2891 | dt 9.771 +type train | step 2720 | loss 120.2575 243.9684 366.7412 565.8143 821.0603 1179.7285 1620.6267 2281.3267 3167.8022 4726.5518 7658.8071 13938.4736 | lr 3.2e-04 | norm 8745.5371 | dt 9.778 +type train | step 2721 | loss 113.5236 231.9986 352.3522 550.1567 805.1582 1159.9667 1613.2161 2274.6929 3196.0471 4744.3955 7708.6802 13990.8994 | lr 3.2e-04 | norm 4087.5730 | dt 9.780 +type train | step 2722 | loss 105.2138 215.9623 331.4689 520.4235 773.3878 1116.4462 1567.0190 2231.3535 3186.0591 4788.8813 7804.6001 14133.1758 | lr 3.2e-04 | norm 4042.7791 | dt 9.789 +type train | step 2723 | loss 104.6726 213.6723 328.0033 512.5848 759.5438 1098.0823 1544.1683 2203.5269 3151.8022 4743.2529 7735.6587 13981.1328 | lr 3.2e-04 | norm 4616.0449 | dt 9.778 +type train | step 2724 | loss 108.8111 220.0636 335.7588 528.9385 782.8105 1135.6338 1587.4537 2255.7314 3195.3032 4777.7881 7760.0742 13948.0186 | lr 3.2e-04 | norm 3836.2854 | dt 9.801 +type train | step 2725 | loss 110.3907 225.5267 343.9555 538.4227 794.2546 1138.3060 1588.1041 2252.9883 3193.6111 4778.4185 7771.9766 14066.9160 | lr 3.2e-04 | norm 4307.0400 | dt 9.787 +type train | step 2726 | loss 104.5749 213.1999 328.9153 516.6660 768.8748 1105.8546 1557.3223 2218.6089 3163.1982 4763.7959 7796.0825 14165.3613 | lr 3.2e-04 | norm 5059.9204 | dt 9.781 +type train | step 2727 | loss 106.5052 219.3799 337.5864 533.5809 789.6635 1148.9032 1611.9126 2296.6687 3250.2551 4862.5459 7903.5776 14305.0781 | lr 3.2e-04 | norm 4270.2119 | dt 9.819 +type train | step 2728 | loss 111.3151 228.8848 346.7816 545.3771 806.8336 1160.9951 1624.9116 2300.1221 3258.0776 4886.1777 7967.3125 14437.6387 | lr 3.2e-04 | norm 4207.8213 | dt 9.807 +type train | step 2729 | loss 118.4550 250.4973 374.3280 578.5022 850.7252 1208.9493 1684.7778 2384.8508 3331.3308 4981.2017 8136.8076 14946.7441 | lr 3.2e-04 | norm 6648.2065 | dt 9.775 +type train | step 2730 | loss 106.4374 218.1330 334.8100 527.3918 780.7327 1133.2185 1601.9692 2308.6392 3293.6838 4963.5278 8119.5967 14708.5879 | lr 3.2e-04 | norm 5193.0308 | dt 9.778 +type train | step 2731 | loss 115.1429 233.7789 356.4422 557.4888 819.6672 1191.3621 1659.2456 2371.8984 3333.4834 4993.5718 8091.1143 14699.8281 | lr 3.2e-04 | norm 5240.2954 | dt 9.779 +type train | step 2732 | loss 103.9134 212.3522 325.4041 512.3345 766.6595 1112.1329 1573.3406 2261.2773 3209.8643 4837.1279 7944.5137 14484.0117 | lr 3.2e-04 | norm 4714.9487 | dt 9.773 +type train | step 2733 | loss 104.0559 211.2484 321.5346 507.4151 755.6350 1101.2014 1545.2687 2202.1646 3123.5964 4700.7427 7658.0312 13973.7988 | lr 3.2e-04 | norm 4439.5840 | dt 9.778 +type train | step 2734 | loss 104.0220 213.5348 328.2073 519.6324 775.7917 1130.2263 1597.5377 2278.5623 3218.1235 4840.2217 7887.7393 14247.8916 | lr 3.2e-04 | norm 4490.5098 | dt 9.795 +type train | step 2735 | loss 109.0195 224.8581 339.9956 529.9619 779.2325 1127.6859 1581.1851 2239.2891 3180.6147 4785.2671 7818.0298 14150.5186 | lr 3.2e-04 | norm 4451.9399 | dt 9.798 +type train | step 2736 | loss 109.1815 218.9043 338.2493 528.0585 780.5179 1131.5160 1582.9180 2264.5522 3172.3240 4752.6821 7767.9072 14242.2461 | lr 3.2e-04 | norm 6222.7637 | dt 9.771 +type train | step 2737 | loss 109.0072 220.2721 337.3385 526.7813 773.8115 1113.5204 1551.5524 2186.8105 3081.1729 4611.1621 7507.1895 13582.9375 | lr 3.2e-04 | norm 3966.4690 | dt 9.785 +type train | step 2738 | loss 108.8106 222.0795 339.2424 532.2380 786.8835 1136.6216 1597.3773 2274.9443 3229.0193 4836.3989 7896.3618 14316.4805 | lr 3.2e-04 | norm 4492.6963 | dt 9.786 +type train | step 2739 | loss 108.7011 221.1111 332.9231 519.7267 767.9772 1114.0829 1562.6926 2223.8555 3145.4170 4704.7100 7624.3037 13760.7510 | lr 3.2e-04 | norm 4513.2539 | dt 9.782 +type train | step 2740 | loss 100.2048 202.8113 313.9255 502.2194 751.8827 1099.2745 1562.6003 2246.8826 3227.6067 4893.8730 8089.8340 14785.9678 | lr 3.2e-04 | norm 4989.5166 | dt 9.772 +type train | step 2741 | loss 109.5578 224.5514 343.1855 535.1688 792.9897 1140.6189 1594.5361 2264.4985 3199.6074 4839.9736 7914.1895 14399.5635 | lr 3.2e-04 | norm 4493.0439 | dt 9.782 +type train | step 2742 | loss 108.2927 222.0654 339.4245 529.7490 785.1428 1124.9406 1580.9305 2250.2563 3186.5039 4781.1929 7780.7393 14108.3076 | lr 3.2e-04 | norm 4566.5591 | dt 9.792 +type train | step 2743 | loss 105.0231 210.7708 322.5703 511.5666 759.5795 1105.8798 1552.5476 2228.4771 3159.5935 4747.0684 7765.9878 14102.7158 | lr 3.2e-04 | norm 4620.0884 | dt 9.769 +type train | step 2744 | loss 112.3270 232.5530 352.0797 548.6715 810.5831 1159.8322 1619.7412 2285.9629 3207.0867 4807.6748 7856.3442 14262.6621 | lr 3.2e-04 | norm 4647.3755 | dt 9.779 +type train | step 2745 | loss 114.0103 235.7900 356.0568 554.3312 817.2759 1178.4595 1631.2220 2291.5232 3210.7358 4781.4414 7781.1714 14131.3896 | lr 3.2e-04 | norm 4301.8594 | dt 9.774 +type train | step 2746 | loss 116.9809 241.6422 361.5950 557.3999 817.0542 1174.8134 1650.2427 2329.9006 3271.5461 4896.9482 7979.0889 14454.7607 | lr 3.2e-04 | norm 4189.6108 | dt 9.783 +type train | step 2747 | loss 104.5238 212.6162 326.9935 514.1621 764.3322 1101.2720 1545.9869 2195.8523 3127.1135 4695.9888 7625.8984 13776.2295 | lr 3.2e-04 | norm 3732.8418 | dt 9.786 +type train | step 2748 | loss 118.3957 244.4947 367.3016 564.2760 820.4985 1168.0173 1618.8599 2297.2620 3222.2969 4844.5552 7925.6743 14420.5850 | lr 3.2e-04 | norm 5714.1484 | dt 9.776 +type train | step 2749 | loss 101.6399 208.2821 320.3226 507.0245 758.1793 1100.4866 1557.5131 2218.5015 3180.8887 4796.3384 7802.5757 14047.3018 | lr 3.2e-04 | norm 4778.0693 | dt 9.792 +type train | step 2750 | loss 113.2385 230.7066 354.1048 550.9486 813.1653 1172.6323 1643.0057 2334.4297 3270.6829 4881.4932 7933.8452 14500.6045 | lr 3.2e-04 | norm 5496.0830 | dt 9.769 +type train | step 2751 | loss 110.1368 223.4854 336.8746 525.4778 778.0203 1117.9412 1569.7323 2226.3062 3144.2910 4710.7900 7670.3574 14005.0371 | lr 3.2e-04 | norm 4645.1279 | dt 9.776 +type train | step 2752 | loss 111.7497 227.6204 344.8378 535.0786 790.1121 1140.7119 1601.0840 2283.8652 3226.7212 4818.3799 7831.1558 14217.0439 | lr 3.2e-04 | norm 4648.0308 | dt 9.784 +type train | step 2753 | loss 103.9069 210.2408 322.4686 503.5467 747.2830 1071.9353 1495.2184 2116.5471 3029.6902 4527.1084 7390.7578 13349.8760 | lr 3.2e-04 | norm 3905.2493 | dt 9.793 +type train | step 2754 | loss 103.1452 211.1414 327.1979 514.0465 770.5403 1118.8689 1576.1158 2239.9783 3188.8494 4808.4165 7842.5732 14195.6230 | lr 3.2e-04 | norm 4248.7222 | dt 9.787 +type train | step 2755 | loss 116.3659 239.3656 354.7061 546.5854 799.4062 1150.4316 1600.0774 2261.0688 3164.8948 4711.9468 7722.5020 14107.0137 | lr 3.2e-04 | norm 5141.8008 | dt 9.764 +type train | step 2756 | loss 120.9776 245.0647 365.0015 557.1398 799.0827 1159.8149 1602.9211 2289.7922 3183.2957 4712.3838 7694.8911 13995.8682 | lr 3.2e-04 | norm 10096.2910 | dt 9.724 +type train | step 2757 | loss 114.5440 236.5786 356.7235 556.0932 815.0218 1184.1028 1648.2762 2365.0989 3295.9070 4903.0986 7975.5938 14402.9375 | lr 3.2e-04 | norm 4886.9048 | dt 9.779 +type train | step 2758 | loss 106.9115 216.3562 331.0020 520.7807 770.3163 1131.1091 1585.8112 2271.8635 3220.0242 4815.9531 7834.1079 14319.1084 | lr 3.2e-04 | norm 4965.6729 | dt 9.775 +type train | step 2759 | loss 112.4025 228.0428 345.9367 541.7242 794.9252 1150.6273 1598.7023 2248.2522 3166.8115 4752.2534 7734.6309 14176.1191 | lr 3.2e-04 | norm 4814.8540 | dt 9.796 +type train | step 2760 | loss 98.1114 198.6106 306.9177 488.4364 735.3015 1066.7917 1501.9302 2144.3857 3074.8074 4635.6172 7564.5859 13634.3965 | lr 3.2e-04 | norm 4451.3779 | dt 9.773 +type train | step 2761 | loss 108.0067 219.6801 333.9560 515.8464 764.4830 1099.9739 1545.5111 2197.5818 3122.7104 4673.0889 7596.4756 13715.4336 | lr 3.2e-04 | norm 4592.5684 | dt 9.782 +type train | step 2762 | loss 103.5500 210.2270 323.5054 510.8604 761.3117 1099.4033 1540.4764 2196.6726 3119.7334 4691.7783 7676.9463 13938.5742 | lr 3.2e-04 | norm 4437.8369 | dt 9.777 +type train | step 2763 | loss 108.7507 221.9631 337.1689 527.3808 776.9673 1117.8309 1562.4427 2210.4219 3114.0078 4651.8877 7551.8428 13665.5225 | lr 3.2e-04 | norm 4597.2793 | dt 9.776 +type train | step 2764 | loss 118.4466 242.5678 368.3080 575.4424 835.3744 1187.6122 1631.7965 2284.8208 3195.3384 4788.7197 7731.0405 14117.5176 | lr 3.2e-04 | norm 5928.2778 | dt 9.771 +type train | step 2765 | loss 114.7631 238.8481 359.0879 560.7756 820.3218 1164.5583 1615.7173 2269.6519 3184.5447 4754.5044 7685.6772 14057.2666 | lr 3.2e-04 | norm 4121.9868 | dt 9.775 +type train | step 2766 | loss 106.0979 216.0244 327.4158 511.0997 757.6044 1089.5312 1533.4005 2190.1780 3116.6785 4685.2964 7636.5576 13889.0234 | lr 3.2e-04 | norm 4842.1567 | dt 9.776 +type train | step 2767 | loss 115.6735 243.8978 368.9290 569.2404 839.0038 1186.8988 1661.0139 2353.6487 3326.0088 5071.8496 8329.9863 15324.5283 | lr 3.2e-04 | norm 7727.3145 | dt 9.786 +type train | step 2768 | loss 109.8063 226.1998 342.5078 534.6725 786.5201 1127.8429 1582.0814 2238.7786 3174.0796 4775.9707 7728.1694 13976.3086 | lr 3.2e-04 | norm 4628.6133 | dt 9.779 +type train | step 2769 | loss 105.7628 214.5690 334.5907 530.8830 789.5361 1140.9259 1613.9562 2302.3425 3280.8367 4908.1489 7971.0010 14436.4492 | lr 3.2e-04 | norm 4906.1943 | dt 9.787 +type train | step 2770 | loss 111.9951 228.4985 350.9221 549.7934 807.9375 1165.2338 1634.8831 2329.3896 3294.4385 4982.6992 8195.9209 14955.6377 | lr 3.2e-04 | norm 5871.0054 | dt 9.777 +type train | step 2771 | loss 97.8556 196.8463 306.0307 490.9883 735.0439 1074.7479 1524.4015 2187.3284 3132.3022 4731.4492 7766.8569 14144.0498 | lr 3.2e-04 | norm 4387.6904 | dt 9.782 +type train | step 2772 | loss 103.8534 212.5264 327.1010 513.4761 765.7723 1107.2274 1562.0977 2223.5898 3156.3394 4720.5352 7644.9209 13712.6846 | lr 3.2e-04 | norm 4082.4961 | dt 9.777 +type train | step 2773 | loss 107.9222 215.9186 334.0828 522.5134 777.5917 1129.3131 1586.6163 2268.7314 3225.9456 4860.3145 7861.5615 14170.3389 | lr 3.2e-04 | norm 5474.3818 | dt 9.776 +type train | step 2774 | loss 109.5405 225.5430 343.5829 532.9455 787.4001 1128.3966 1578.1311 2244.4937 3180.6492 4754.4575 7708.3076 13978.5459 | lr 3.1e-04 | norm 4112.6104 | dt 9.777 +type train | step 2775 | loss 107.3880 218.4914 337.6948 531.2217 783.4185 1126.1755 1583.8241 2252.1384 3217.4180 4828.8701 7827.7690 14086.4912 | lr 3.1e-04 | norm 4095.1936 | dt 9.786 +type train | step 2776 | loss 110.9499 225.4164 343.9585 534.2574 787.9742 1143.2397 1602.2760 2286.0337 3224.9971 4838.6836 7918.4209 14448.1631 | lr 3.1e-04 | norm 5207.3032 | dt 9.779 +type train | step 2777 | loss 107.6027 230.2481 356.4587 552.3057 812.0760 1149.4148 1599.6162 2280.8228 3201.6804 4788.4722 7850.3667 14228.7871 | lr 3.1e-04 | norm 7088.9980 | dt 9.784 +type train | step 2778 | loss 105.8809 215.5272 327.9268 524.3218 771.7815 1127.1080 1578.9381 2262.4001 3175.7192 4758.5493 7687.1543 13941.6006 | lr 3.1e-04 | norm 5003.7144 | dt 9.775 +type train | step 2779 | loss 99.1416 201.0999 311.5154 494.6120 741.0438 1075.2693 1524.9010 2180.9810 3119.5017 4693.6211 7644.8223 13880.0488 | lr 3.1e-04 | norm 4540.6733 | dt 9.774 +type train | step 2780 | loss 110.2338 226.9402 346.5125 538.4077 793.4695 1143.1609 1599.9891 2261.8767 3183.1267 4748.1226 7695.0947 13866.4023 | lr 3.1e-04 | norm 4307.4351 | dt 9.788 +type train | step 2781 | loss 109.1830 223.1855 337.9787 532.3965 785.9584 1142.5132 1592.3129 2278.9922 3194.0361 4785.9258 7787.9111 14154.8633 | lr 3.1e-04 | norm 4695.1685 | dt 9.777 +type train | step 2782 | loss 105.6946 215.6411 329.2694 518.1739 767.1867 1117.2996 1581.7505 2261.7925 3195.6978 4812.1270 7863.2305 14333.4141 | lr 3.1e-04 | norm 4873.4399 | dt 9.780 +type train | step 2783 | loss 114.2121 232.6649 351.9806 548.5103 816.7394 1193.7805 1680.4060 2415.4224 3392.2061 5073.7241 8170.3975 14689.0508 | lr 3.1e-04 | norm 5246.6621 | dt 9.764 +type train | step 2784 | loss 106.1831 215.4554 326.0367 509.3846 761.2880 1106.5198 1561.0255 2235.7395 3183.1763 4811.8628 7802.4448 14066.3926 | lr 3.1e-04 | norm 4748.0874 | dt 9.780 +type train | step 2785 | loss 103.9775 209.3172 323.1942 510.5468 758.9065 1108.2245 1554.4403 2218.4995 3156.5752 4762.7212 7765.1587 14049.0332 | lr 3.1e-04 | norm 4479.6426 | dt 9.765 +type train | step 2786 | loss 103.9393 213.7984 331.9071 526.5560 785.6735 1140.5052 1598.6046 2284.0574 3240.7412 4897.2988 8012.9746 14579.7832 | lr 3.1e-04 | norm 5318.6587 | dt 9.776 +type train | step 2787 | loss 104.6944 213.1938 325.0708 509.6602 754.2914 1084.9517 1519.8779 2163.8535 3070.0986 4617.6982 7533.3901 13629.5762 | lr 3.1e-04 | norm 3905.2871 | dt 9.773 +type train | step 2788 | loss 96.7776 193.6977 302.7950 484.1231 725.2588 1056.1906 1498.3384 2143.0620 3076.1533 4656.7959 7624.9287 13821.3584 | lr 3.1e-04 | norm 4377.0444 | dt 9.778 +type train | step 2789 | loss 104.5697 213.4474 327.5239 511.9131 761.5839 1097.8510 1541.8070 2193.0078 3130.8826 4680.9238 7555.7920 13540.3906 | lr 3.1e-04 | norm 5026.8105 | dt 9.776 +type train | step 2790 | loss 106.4077 216.5582 329.9671 517.4710 761.5493 1104.2151 1541.2159 2192.4888 3082.4185 4600.8428 7457.1685 13601.4072 | lr 3.1e-04 | norm 5399.5112 | dt 9.778 +type train | step 2791 | loss 117.7801 240.9531 359.8443 564.9164 826.0044 1191.3129 1652.8174 2356.1272 3313.3008 4965.3711 8031.4624 14618.8867 | lr 3.1e-04 | norm 5135.8613 | dt 9.766 +type train | step 2792 | loss 100.2943 203.9516 314.6213 498.9630 751.6757 1094.4114 1549.0803 2218.8745 3171.0947 4771.4502 7758.8604 14034.3926 | lr 3.1e-04 | norm 4443.5210 | dt 9.771 +type train | step 2793 | loss 104.3708 212.0941 323.7039 509.1397 758.8438 1099.3134 1545.3427 2197.4136 3106.9019 4676.2329 7590.3340 13669.0625 | lr 3.1e-04 | norm 4295.4087 | dt 9.780 +type train | step 2794 | loss 109.3072 224.7930 344.7108 539.7530 797.7139 1157.8728 1622.0593 2319.1270 3285.8157 4910.9409 8008.3027 14456.9541 | lr 3.1e-04 | norm 4707.7271 | dt 9.776 +type train | step 2795 | loss 111.3025 223.0871 339.3104 530.6838 789.0410 1134.5636 1591.6943 2263.9094 3222.6313 4838.5786 7834.4351 14203.0078 | lr 3.1e-04 | norm 4500.8008 | dt 9.776 +type train | step 2796 | loss 107.0621 218.0068 333.9026 522.3704 772.9715 1118.5499 1566.9031 2235.5400 3185.3984 4791.6860 7816.3979 14146.3027 | lr 3.1e-04 | norm 4056.2878 | dt 9.787 +type train | step 2797 | loss 110.8599 224.2946 340.7716 533.5554 785.9261 1145.4393 1614.5300 2284.5110 3217.4988 4794.8950 7731.4233 13876.5762 | lr 3.1e-04 | norm 4319.4155 | dt 9.781 +type train | step 2798 | loss 108.3947 218.3566 333.5618 531.9755 785.9406 1173.6190 1651.2413 2406.4761 3338.3875 4962.8247 8051.9253 14546.6104 | lr 3.1e-04 | norm 6307.0312 | dt 9.765 +type train | step 2799 | loss 115.1879 235.1329 356.9953 555.2390 813.6429 1179.9628 1663.0824 2367.4692 3286.3555 4889.0664 7896.9688 14364.6914 | lr 3.1e-04 | norm 4818.1748 | dt 9.771 +type train | step 2800 | loss 110.1664 227.3248 342.2422 531.7486 782.9305 1138.8320 1603.8441 2284.6714 3220.8313 4844.1416 7920.4873 14368.2363 | lr 3.1e-04 | norm 4971.0371 | dt 9.786 +type train | step 2801 | loss 99.4989 200.7337 308.7642 490.1505 734.7318 1070.5184 1516.0375 2178.9753 3120.8826 4710.3091 7722.2339 14115.3223 | lr 3.1e-04 | norm 4742.2563 | dt 9.790 +type train | step 2802 | loss 105.4151 214.9275 330.7381 520.6984 771.5957 1107.0164 1551.4204 2197.7146 3134.2041 4706.3301 7662.3545 13839.6182 | lr 3.1e-04 | norm 4532.7812 | dt 9.785 +type train | step 2803 | loss 111.4964 227.2768 345.2693 537.7195 788.9832 1140.2830 1589.1289 2256.3999 3174.2100 4731.4307 7723.4160 13973.2061 | lr 3.1e-04 | norm 4881.3828 | dt 9.773 +type train | step 2804 | loss 114.0979 231.7358 351.8943 547.0570 806.4463 1168.1521 1634.5125 2327.9414 3237.5945 4842.5283 7885.8467 14334.4561 | lr 3.1e-04 | norm 5188.6919 | dt 9.778 +type train | step 2805 | loss 107.6584 219.8008 337.9929 529.1008 783.2621 1137.8754 1597.3228 2275.8176 3218.0381 4814.2437 7821.5034 14219.5117 | lr 3.1e-04 | norm 4538.7051 | dt 9.789 +type train | step 2806 | loss 101.1874 205.2369 315.8386 501.8939 750.6686 1079.8750 1524.3480 2177.4604 3108.0859 4697.3081 7651.0137 13856.4922 | lr 3.1e-04 | norm 4973.6406 | dt 9.774 +type train | step 2807 | loss 151.5409 323.8060 453.6185 673.1643 969.9656 1424.1292 1972.1478 2743.7725 3751.0122 5394.0400 8356.1416 14820.8613 | lr 3.1e-04 | norm 5278.5815 | dt 9.770 +type train | step 2808 | loss 109.9843 225.0437 342.2184 531.1917 787.5927 1123.9020 1578.4205 2233.1311 3177.8408 4785.1929 7782.7969 14086.0430 | lr 3.1e-04 | norm 4518.9331 | dt 9.795 +type train | step 2809 | loss 108.1384 220.6567 336.7552 523.7492 775.3967 1119.3580 1570.1042 2233.1223 3165.5303 4762.2764 7751.9468 14070.8809 | lr 3.1e-04 | norm 4125.0791 | dt 9.806 +type train | step 2810 | loss 107.8921 215.3509 326.1173 510.2962 752.7904 1097.2631 1538.3708 2212.7461 3135.2324 4733.5693 7762.1904 14124.0420 | lr 3.1e-04 | norm 4367.8872 | dt 9.794 +type train | step 2811 | loss 125.6666 256.5417 386.2475 585.3869 840.4978 1205.3966 1644.1632 2300.0146 3154.2312 4725.1069 7603.0801 13908.9863 | lr 3.1e-04 | norm 6143.4731 | dt 9.774 +type train | step 2812 | loss 109.7597 223.0438 336.8946 532.0576 787.2847 1140.9120 1597.5186 2270.0210 3186.9597 4772.1104 7699.4927 13966.3477 | lr 3.1e-04 | norm 4363.4951 | dt 9.775 +type train | step 2813 | loss 109.8901 223.8320 339.5324 531.6387 782.2472 1135.4509 1590.1340 2270.9075 3199.4712 4781.5327 7767.6646 14077.1572 | lr 3.1e-04 | norm 4440.5542 | dt 9.786 +type train | step 2814 | loss 111.0423 227.8355 346.5905 546.8741 811.5527 1187.3767 1662.7671 2374.9438 3330.5615 4965.5908 8033.3931 14529.1699 | lr 3.1e-04 | norm 4867.2617 | dt 9.783 +type train | step 2815 | loss 104.6879 213.7231 327.5939 514.5333 763.0378 1104.1796 1553.5149 2222.6157 3161.6201 4778.9971 7788.8213 14119.1758 | lr 3.1e-04 | norm 4295.7236 | dt 9.789 +type train | step 2816 | loss 105.7364 214.2734 325.6346 508.8450 756.7777 1093.1639 1534.4084 2191.5813 3117.1323 4712.5576 7740.9785 14111.4502 | lr 3.1e-04 | norm 4861.8984 | dt 9.770 +type train | step 2817 | loss 111.4865 226.7739 346.2074 538.8149 797.0527 1160.5447 1624.9126 2325.2231 3272.0264 4901.4390 7956.2432 14483.5215 | lr 3.1e-04 | norm 4861.7407 | dt 9.777 +type train | step 2818 | loss 102.1058 206.5942 319.8640 506.7352 755.8045 1093.7601 1539.7017 2206.0757 3132.5176 4709.0938 7707.8481 13954.3740 | lr 3.1e-04 | norm 4049.5881 | dt 9.793 +type train | step 2819 | loss 102.2119 208.6205 317.0210 501.5623 745.6728 1079.5670 1514.7040 2165.8887 3076.7910 4622.0913 7521.0601 13588.8545 | lr 3.1e-04 | norm 3918.0452 | dt 9.779 +type train | step 2820 | loss 105.5937 211.4025 322.9110 512.0636 762.6304 1109.8682 1565.6418 2245.0530 3192.2720 4792.5537 7774.0918 13953.1738 | lr 3.1e-04 | norm 4128.5757 | dt 9.785 +type train | step 2821 | loss 102.3605 210.1278 321.1274 509.8525 761.9568 1107.1290 1569.4608 2244.7915 3203.7988 4819.3345 7790.9326 13977.3652 | lr 3.1e-04 | norm 4118.9199 | dt 9.792 +type train | step 2822 | loss 106.5110 218.9979 332.6446 521.7526 777.6488 1145.0956 1615.0250 2323.9768 3285.9775 4933.6870 8066.8828 14632.8096 | lr 3.1e-04 | norm 5173.8721 | dt 9.785 +type train | step 2823 | loss 111.5795 231.1852 347.3737 542.9834 800.3160 1147.0049 1596.1631 2256.0566 3171.4604 4750.2739 7779.8296 14156.6143 | lr 3.1e-04 | norm 4841.2910 | dt 9.779 +type train | step 2824 | loss 106.4199 217.2937 331.1378 526.0730 777.7701 1128.6599 1582.6571 2258.4705 3185.9578 4794.1851 7872.6016 14310.6719 | lr 3.1e-04 | norm 3861.4182 | dt 9.776 +type train | step 2825 | loss 116.8187 239.7698 360.8219 562.3609 826.6631 1202.2655 1671.4862 2376.6389 3294.3372 4839.3545 7706.3828 13833.4014 | lr 3.1e-04 | norm 4627.2358 | dt 9.778 +type train | step 2826 | loss 105.1004 215.2464 330.6855 522.1049 774.5538 1111.1403 1554.3435 2214.6025 3149.5703 4751.5371 7769.3682 14121.7070 | lr 3.1e-04 | norm 4283.5444 | dt 9.786 +type train | step 2827 | loss 107.9703 220.7567 341.4400 539.5151 798.0350 1153.9958 1619.9963 2309.0759 3234.2437 4886.2974 8040.0332 14909.6670 | lr 3.1e-04 | norm 5229.5923 | dt 9.785 +type train | step 2828 | loss 106.4644 218.8034 334.3372 525.0966 780.0779 1121.1794 1579.8167 2241.5845 3159.0444 4739.1445 7701.7402 13927.8945 | lr 3.1e-04 | norm 4172.7520 | dt 9.780 +type train | step 2829 | loss 106.0132 217.4110 329.0676 516.5809 767.3445 1104.6665 1543.9990 2195.4502 3108.8557 4689.3169 7650.6499 13925.8516 | lr 3.1e-04 | norm 4037.6626 | dt 9.780 +type train | step 2830 | loss 102.0087 207.0882 320.1417 505.8115 759.3047 1100.4491 1551.9127 2226.1052 3160.4553 4737.7949 7737.1523 13979.7227 | lr 3.1e-04 | norm 4593.5503 | dt 9.792 +type train | step 2831 | loss 110.9560 228.5733 347.4798 544.2418 803.5399 1155.2502 1606.5693 2278.9207 3200.6545 4772.8252 7742.6807 14092.5361 | lr 3.1e-04 | norm 5058.2656 | dt 9.769 +type train | step 2832 | loss 114.8943 235.5424 352.2599 546.4617 803.3217 1139.9318 1582.5911 2225.4663 3125.6152 4672.9395 7560.5493 13714.3320 | lr 3.1e-04 | norm 5084.9438 | dt 9.775 +type train | step 2833 | loss 113.8342 237.3271 356.4122 549.2993 809.7072 1169.7540 1634.6761 2325.0657 3273.9243 4883.2246 7831.6577 14077.4316 | lr 3.1e-04 | norm 4150.6729 | dt 9.800 +type train | step 2834 | loss 106.6623 220.3114 337.8223 528.3400 786.8660 1136.5890 1606.3846 2293.6108 3252.1948 4918.6733 8000.5889 14439.4775 | lr 3.1e-04 | norm 4765.1650 | dt 9.780 +type train | step 2835 | loss 104.1155 213.8550 328.0616 519.0707 770.3071 1121.9714 1577.5730 2249.5283 3193.8938 4773.8579 7749.5137 14041.4395 | lr 3.1e-04 | norm 4455.6802 | dt 9.781 +type train | step 2836 | loss 114.6208 236.4060 354.2252 550.7493 811.2728 1179.0411 1635.7471 2325.8550 3251.4736 4823.7744 7793.3154 14048.1299 | lr 3.1e-04 | norm 4130.5635 | dt 9.780 +type train | step 2837 | loss 102.1448 207.6425 316.7845 497.2074 743.5621 1074.0111 1506.7419 2152.0828 3061.5261 4594.1299 7492.7432 13537.0820 | lr 3.1e-04 | norm 3936.1538 | dt 9.792 +type train | step 2838 | loss 103.0749 211.1881 322.7111 504.0372 748.4656 1077.2163 1518.2991 2162.4424 3070.3198 4593.5190 7415.8774 13381.3320 | lr 3.1e-04 | norm 3950.2400 | dt 9.792 +type train | step 2839 | loss 112.8794 233.4047 353.5053 549.7415 811.2952 1171.6979 1634.7875 2349.9790 3302.5112 4949.6807 7960.6030 14256.0527 | lr 3.1e-04 | norm 4918.6411 | dt 9.792 +type train | step 2840 | loss 110.6890 227.0049 345.6469 539.2360 795.2178 1141.1501 1589.2706 2261.2876 3187.7991 4786.6436 7731.4502 13897.2217 | lr 3.1e-04 | norm 3885.0391 | dt 9.784 +type train | step 2841 | loss 110.7467 228.5250 349.1669 542.7834 804.0676 1161.8813 1635.1462 2330.8015 3280.1875 4927.8320 7959.4106 14297.0508 | lr 3.1e-04 | norm 4301.5068 | dt 9.797 +type train | step 2842 | loss 116.8320 242.5629 371.1671 582.1027 866.6096 1265.3293 1784.0758 2564.5801 3534.8616 5267.7617 8522.2188 15536.0186 | lr 3.0e-04 | norm 8386.6699 | dt 9.770 +type train | step 2843 | loss 110.8102 229.7475 348.5204 548.9506 807.8486 1159.9839 1622.3046 2313.8896 3272.7539 4922.7842 7968.1641 14403.7393 | lr 3.0e-04 | norm 5554.5474 | dt 9.781 +type train | step 2844 | loss 115.1957 241.3366 367.6227 574.9672 838.0899 1200.7545 1671.9346 2370.1382 3294.3184 4903.4019 7901.4927 14173.5469 | lr 3.0e-04 | norm 7530.3784 | dt 9.773 +type train | step 2845 | loss 111.3233 226.6859 341.9694 542.1309 793.3458 1164.5021 1637.0044 2351.6321 3296.4294 4920.4932 7966.0801 14353.5703 | lr 3.0e-04 | norm 4852.8677 | dt 9.771 +type train | step 2846 | loss 118.0983 245.7719 371.1707 574.8137 834.9138 1184.9065 1631.1162 2291.1274 3189.3660 4733.8296 7697.3936 14022.2412 | lr 3.0e-04 | norm 5387.0176 | dt 9.774 +type train | step 2847 | loss 96.2521 193.8589 301.8333 493.1776 747.0922 1094.2939 1564.6577 2265.5364 3248.8782 4888.7891 7933.1846 14318.1885 | lr 3.0e-04 | norm 7737.5527 | dt 9.764 +type train | step 2848 | loss 114.3521 235.0564 355.8954 550.2252 807.9721 1171.5936 1639.0146 2349.0391 3267.3818 4877.5586 7878.3203 14153.3887 | lr 3.0e-04 | norm 5440.6177 | dt 9.768 +type train | step 2849 | loss 105.8968 217.5552 329.8586 518.5417 772.6647 1120.4979 1573.6678 2257.0190 3196.0276 4808.6772 7766.2983 13944.8789 | lr 3.0e-04 | norm 4888.6323 | dt 9.782 +type train | step 2850 | loss 104.1714 214.6240 327.9634 515.1755 764.5167 1107.8119 1550.2339 2211.2502 3131.5469 4700.3887 7644.9507 13774.9932 | lr 3.0e-04 | norm 4455.2422 | dt 9.793 +type train | step 2851 | loss 106.3962 219.9211 334.7242 522.7344 773.3246 1125.2487 1579.4753 2253.5085 3180.5747 4766.2290 7772.1997 14102.9434 | lr 3.0e-04 | norm 4594.3330 | dt 9.780 +type train | step 2852 | loss 97.8637 200.2537 311.1816 501.1190 755.8143 1111.4302 1578.8376 2287.5696 3259.4529 4920.1777 8064.1860 14678.7451 | lr 3.0e-04 | norm 6242.9634 | dt 9.781 +type train | step 2853 | loss 118.5826 247.1005 366.8577 561.8139 818.5344 1182.4095 1644.2283 2322.5327 3231.6733 4834.4736 7820.7197 14191.2256 | lr 3.0e-04 | norm 4889.5591 | dt 9.778 +type train | step 2854 | loss 109.9301 222.8004 338.0693 535.0837 788.7057 1146.4113 1610.2008 2301.3596 3228.3315 4834.6416 7864.1294 14306.8418 | lr 3.0e-04 | norm 4545.9575 | dt 9.769 +type train | step 2855 | loss 102.4510 207.5621 317.8218 500.2834 746.7237 1077.9136 1518.5894 2164.4724 3087.1384 4649.5464 7586.9780 13734.2656 | lr 3.0e-04 | norm 4191.6328 | dt 9.789 +type train | step 2856 | loss 115.0055 238.6835 354.7833 550.6728 805.8195 1145.5503 1567.8518 2193.8440 3067.4412 4568.6982 7342.7480 13271.6426 | lr 3.0e-04 | norm 4701.8628 | dt 9.765 +type train | step 2857 | loss 99.6692 201.2716 311.8162 492.8474 740.4631 1086.2920 1538.7101 2219.1824 3149.1707 4771.8545 7757.1265 14019.1641 | lr 3.0e-04 | norm 4528.1025 | dt 9.780 +type train | step 2858 | loss 105.0042 220.3738 336.2280 524.9693 779.0789 1124.6844 1583.0269 2258.9541 3193.1523 4840.5640 7905.5190 14317.6250 | lr 3.0e-04 | norm 5372.4199 | dt 9.772 +type train | step 2859 | loss 95.8614 193.7317 303.2610 482.3830 729.0101 1058.3398 1506.5498 2164.1067 3105.7578 4712.0308 7666.3340 13914.1738 | lr 3.0e-04 | norm 4335.0542 | dt 9.787 +type train | step 2860 | loss 110.8893 222.8575 338.3463 524.8827 779.1158 1136.8311 1600.6294 2306.9683 3273.1582 4916.6221 7978.4058 14382.4541 | lr 3.0e-04 | norm 4485.8550 | dt 9.780 +type train | step 2861 | loss 105.9900 215.6589 329.0477 517.3121 771.0450 1116.5402 1566.9381 2236.8538 3166.5359 4775.5454 7788.6562 14178.6670 | lr 3.0e-04 | norm 4423.5938 | dt 9.798 +type train | step 2862 | loss 102.2274 207.9846 317.6402 503.6185 749.6841 1086.3125 1528.8896 2185.2485 3104.5435 4655.9854 7563.6787 13602.0850 | lr 3.0e-04 | norm 4122.6372 | dt 9.787 +type train | step 2863 | loss 103.6721 211.0148 320.2929 504.8977 759.1505 1109.2291 1563.6322 2250.7114 3184.5371 4779.7388 7753.4766 14039.3135 | lr 3.0e-04 | norm 4610.4580 | dt 9.768 +type train | step 2864 | loss 106.2513 213.2348 324.9597 512.3552 761.3329 1103.2972 1557.2974 2228.9558 3156.6184 4761.6841 7780.6133 14183.2061 | lr 3.0e-04 | norm 5060.0312 | dt 9.787 +type train | step 2865 | loss 103.7687 214.7195 329.5309 520.1861 770.7103 1116.0848 1560.5643 2222.2952 3148.9836 4747.9058 7712.9150 13913.9023 | lr 3.0e-04 | norm 3898.0520 | dt 9.785 +type train | step 2866 | loss 103.0722 211.9839 328.4966 522.6228 775.6736 1145.0946 1588.4656 2282.2957 3221.9556 4872.6787 7939.7432 14468.0781 | lr 3.0e-04 | norm 4407.8076 | dt 9.776 +type train | step 2867 | loss 107.2393 219.4250 331.9597 515.7534 766.0602 1106.1722 1549.0398 2208.6675 3125.7996 4667.1777 7549.9639 13616.0723 | lr 3.0e-04 | norm 4126.3926 | dt 9.795 +type train | step 2868 | loss 113.1611 239.6363 360.6526 562.8978 829.3524 1189.7198 1659.5056 2375.7847 3312.0894 5035.2515 8230.9199 14914.2871 | lr 3.0e-04 | norm 6129.8022 | dt 9.778 +type train | step 2869 | loss 93.4461 193.5591 306.7458 499.0626 754.4301 1114.3130 1585.9203 2297.5884 3272.3342 4949.7485 8110.4854 14575.9229 | lr 3.0e-04 | norm 6539.3521 | dt 9.773 +type train | step 2870 | loss 112.7364 234.8737 348.0370 535.9153 791.3451 1138.1925 1592.2058 2264.2744 3202.1199 4777.7202 7741.8311 13944.0957 | lr 3.0e-04 | norm 4569.6812 | dt 9.792 +type train | step 2871 | loss 103.1220 212.0703 326.2589 513.5004 763.1005 1099.9512 1544.8545 2200.7119 3118.2219 4700.0342 7676.7886 13955.9570 | lr 3.0e-04 | norm 3994.6338 | dt 9.788 +type train | step 2872 | loss 98.7579 201.2390 311.3551 496.9824 744.3215 1090.3556 1553.2096 2225.5723 3168.3442 4794.1768 7881.9565 14510.1973 | lr 3.0e-04 | norm 5679.1709 | dt 9.770 +type train | step 2873 | loss 101.8321 208.5951 319.0029 506.6113 756.0806 1105.6307 1560.2917 2235.9934 3168.6660 4749.9336 7781.9321 14054.0977 | lr 3.0e-04 | norm 5159.1323 | dt 9.790 +type train | step 2874 | loss 106.1323 214.3433 329.9915 516.1823 762.2469 1096.7417 1531.1028 2168.8281 3063.0825 4595.8887 7480.8999 13542.4014 | lr 3.0e-04 | norm 4053.6228 | dt 9.799 +type train | step 2875 | loss 105.8065 217.3297 329.0103 514.0068 766.2977 1117.3534 1571.5612 2246.7483 3169.3550 4762.4312 7751.1855 14050.1455 | lr 3.0e-04 | norm 5004.4634 | dt 9.777 +type train | step 2876 | loss 111.5407 228.6384 346.8793 540.8040 794.1243 1137.8208 1578.4374 2233.9080 3138.4771 4701.4233 7689.8462 13953.0576 | lr 3.0e-04 | norm 4867.2354 | dt 9.778 +type train | step 2877 | loss 104.3408 225.5145 359.5150 576.2467 872.7344 1272.5568 1766.9640 2563.6794 3636.0044 5515.4453 9135.7988 16941.1797 | lr 3.0e-04 | norm 7358.8911 | dt 9.766 +type train | step 2878 | loss 116.4042 239.1714 358.9775 559.7889 823.4077 1197.9938 1668.6082 2389.3853 3301.0405 4938.0039 7959.9736 14452.9521 | lr 3.0e-04 | norm 4569.1416 | dt 9.776 +type train | step 2879 | loss 104.5019 211.6267 324.4102 508.7404 754.4088 1090.3514 1531.8342 2187.5771 3119.1265 4661.3486 7593.5400 13717.4053 | lr 3.0e-04 | norm 4227.6279 | dt 9.783 +type train | step 2880 | loss 103.1576 210.1259 320.2002 504.4321 753.4221 1089.7578 1530.6609 2192.6221 3136.1211 4705.5464 7607.9072 13695.2305 | lr 3.0e-04 | norm 4068.4326 | dt 9.791 +type train | step 2881 | loss 106.0822 221.2198 337.5820 532.3907 790.2376 1143.1050 1597.3407 2275.5000 3226.4949 4852.5942 7863.0020 14133.3135 | lr 3.0e-04 | norm 3865.3145 | dt 9.787 +type train | step 2882 | loss 110.5641 229.3494 348.1035 545.9649 804.5334 1169.5470 1635.5905 2327.3921 3260.6436 4899.2588 7967.5703 14390.9043 | lr 3.0e-04 | norm 4534.3037 | dt 9.791 +type train | step 2883 | loss 105.6446 213.4254 323.7838 507.5573 751.5776 1086.6044 1529.9047 2180.8677 3095.3857 4664.4482 7603.4932 13670.0273 | lr 3.0e-04 | norm 4281.6426 | dt 9.788 +type train | step 2884 | loss 100.3510 204.0443 311.7080 491.3668 735.9560 1063.3561 1506.2927 2163.9768 3101.8108 4696.9531 7663.9390 13837.6807 | lr 3.0e-04 | norm 4221.7354 | dt 9.793 +type train | step 2885 | loss 104.1096 215.5198 333.7339 526.7701 783.7836 1135.5868 1589.5123 2273.3062 3218.8740 4881.3428 7996.0659 14469.3047 | lr 3.0e-04 | norm 5243.2500 | dt 9.784 +type train | step 2886 | loss 101.7530 201.8749 309.8598 495.7874 732.5038 1068.8113 1501.1101 2160.6931 3074.9094 4653.7012 7664.0317 13857.7773 | lr 3.0e-04 | norm 4813.2505 | dt 9.777 +type train | step 2887 | loss 98.6835 197.3754 304.9687 482.2034 722.8895 1056.6656 1494.5647 2132.8162 3036.5977 4571.1636 7470.2974 13510.6699 | lr 3.0e-04 | norm 4715.6782 | dt 9.773 +type train | step 2888 | loss 109.3185 223.0255 342.6478 538.6381 794.3995 1155.1498 1605.1818 2283.6311 3218.7722 4855.5449 7899.5562 14346.9023 | lr 3.0e-04 | norm 4297.3613 | dt 9.787 +type train | step 2889 | loss 111.3182 229.9036 349.7647 543.3146 802.7561 1150.1433 1607.1046 2280.9661 3206.7603 4810.0962 7808.8115 14110.2256 | lr 3.0e-04 | norm 3857.9248 | dt 9.802 +type train | step 2890 | loss 105.1930 213.4254 328.9564 516.6141 771.3781 1107.4702 1547.4097 2189.9678 3099.3569 4656.2056 7610.4551 13716.0684 | lr 3.0e-04 | norm 3805.5190 | dt 9.813 +type train | step 2891 | loss 103.9662 212.2223 322.9044 505.7164 747.8724 1084.9026 1523.2482 2176.8364 3067.5706 4621.7183 7570.4453 13782.8564 | lr 3.0e-04 | norm 4291.6631 | dt 9.801 +type train | step 2892 | loss 100.9747 205.0580 317.3258 502.4211 753.4469 1095.1890 1547.0770 2219.3682 3134.6968 4745.5830 7792.0127 14199.3965 | lr 3.0e-04 | norm 4596.5166 | dt 9.782 +type train | step 2893 | loss 104.0246 215.0554 330.2336 520.3357 774.3799 1126.4440 1583.1962 2265.8821 3197.3623 4800.4229 7845.4414 14338.2266 | lr 3.0e-04 | norm 4535.1899 | dt 9.787 +type train | step 2894 | loss 116.0791 248.4156 378.2477 601.0218 886.4899 1293.4786 1784.5447 2540.3330 3516.7625 5255.5747 8479.9902 15384.5488 | lr 3.0e-04 | norm 5273.4155 | dt 9.771 +type train | step 2895 | loss 107.0597 218.3107 338.7632 531.4303 789.6356 1134.3558 1591.0458 2266.6084 3201.1262 4811.0908 7798.4546 14026.1699 | lr 3.0e-04 | norm 4292.4185 | dt 9.802 +type train | step 2896 | loss 104.0323 213.5759 328.7298 523.5482 784.3027 1136.5031 1601.4730 2299.1089 3252.0554 4941.6646 8107.9258 14749.5684 | lr 3.0e-04 | norm 5324.4141 | dt 9.787 +type train | step 2897 | loss 107.2559 221.6656 338.0825 530.9856 789.4894 1143.6716 1606.1860 2290.5720 3230.0459 4853.0005 7937.9990 14316.5127 | lr 3.0e-04 | norm 4356.4692 | dt 9.782 +type train | step 2898 | loss 108.7760 224.1007 340.7944 532.1345 787.5389 1139.4968 1595.1558 2277.9988 3212.7236 4812.6250 7759.6499 13875.0625 | lr 3.0e-04 | norm 3932.6882 | dt 9.782 +type train | step 2899 | loss 105.0980 217.3753 331.0443 522.0414 778.7373 1134.3108 1583.9398 2268.5024 3194.1238 4824.6479 7855.1382 14290.5801 | lr 3.0e-04 | norm 4639.9814 | dt 9.776 +type train | step 2900 | loss 107.3535 223.2756 336.8776 523.8475 771.2670 1106.4037 1544.4397 2187.9397 3092.0708 4611.4634 7482.6772 13480.4980 | lr 3.0e-04 | norm 4468.4976 | dt 9.789 +type train | step 2901 | loss 105.3363 217.7141 328.5280 516.7313 764.2184 1117.9384 1562.6877 2239.9150 3158.7410 4754.7568 7733.3623 13952.2012 | lr 3.0e-04 | norm 4135.8525 | dt 9.804 +type train | step 2902 | loss 105.7731 218.3331 335.1806 528.5451 783.8418 1130.0317 1578.7609 2240.8538 3169.0310 4763.0713 7723.8926 13955.1387 | lr 3.0e-04 | norm 3975.3550 | dt 9.785 +type train | step 2903 | loss 104.0996 212.4223 329.1636 519.0848 780.6860 1119.9352 1583.7856 2268.5781 3224.9685 4839.0786 7841.2070 14143.9355 | lr 3.0e-04 | norm 4995.8838 | dt 9.776 +type train | step 2904 | loss 108.6409 222.4139 338.7108 528.1915 786.7957 1131.1714 1586.0815 2267.3267 3216.2520 4874.1064 7952.0742 14426.8867 | lr 3.0e-04 | norm 4487.2617 | dt 9.791 +type train | step 2905 | loss 109.9747 227.5337 342.5560 533.9303 791.4362 1135.2684 1590.6709 2260.5210 3189.2554 4815.1001 7801.2744 14082.9385 | lr 3.0e-04 | norm 4052.2192 | dt 9.784 +type train | step 2906 | loss 105.0756 215.8661 326.7963 512.3956 762.4081 1106.7595 1554.2894 2219.4761 3141.5674 4730.5898 7687.9277 13857.9873 | lr 3.0e-04 | norm 3829.3613 | dt 9.783 +type train | step 2907 | loss 113.7561 232.8235 350.9424 548.1393 804.8120 1175.2695 1638.8191 2329.7087 3216.7410 4810.2793 7847.6108 14378.1270 | lr 3.0e-04 | norm 5499.1123 | dt 9.767 +type train | step 2908 | loss 103.8222 215.5150 335.1649 531.9757 788.3131 1138.7902 1584.8323 2261.3772 3197.9949 4827.6323 7884.6538 14222.4492 | lr 3.0e-04 | norm 4500.9321 | dt 9.789 +type train | step 2909 | loss 107.4516 224.6678 343.0341 540.6107 793.8246 1137.6088 1578.4951 2224.2368 3123.1250 4680.9785 7579.5508 13826.3691 | lr 2.9e-04 | norm 4800.4468 | dt 9.763 +type train | step 2910 | loss 105.3902 218.5019 332.9855 516.9372 765.7322 1105.5687 1548.2673 2208.6233 3114.3623 4663.9556 7596.3945 13760.3457 | lr 2.9e-04 | norm 4190.4717 | dt 9.781 +type train | step 2911 | loss 107.1304 218.6833 332.8717 522.1373 776.1554 1109.1237 1551.6198 2193.3984 3122.0989 4673.6221 7522.2861 13456.9727 | lr 2.9e-04 | norm 3751.5544 | dt 9.780 +type train | step 2912 | loss 107.8794 220.9435 335.3052 528.9184 784.9417 1141.1976 1598.2516 2271.2454 3186.0552 4808.5708 7743.7637 13911.7080 | lr 2.9e-04 | norm 4135.9438 | dt 9.779 +type train | step 2913 | loss 115.0964 237.9103 356.2853 561.5406 821.1561 1193.4021 1657.4177 2363.1980 3283.8562 4893.0137 7947.0356 14423.3408 | lr 2.9e-04 | norm 4517.7520 | dt 9.777 +type train | step 2914 | loss 103.8610 211.5116 321.6891 503.9147 753.2820 1083.6592 1520.4045 2167.7883 3099.5540 4677.0488 7573.9038 13698.9014 | lr 2.9e-04 | norm 4078.7634 | dt 9.780 +type train | step 2915 | loss 102.0754 210.6044 316.7777 498.7808 747.5401 1089.4178 1548.0214 2228.5977 3165.0068 4769.7734 7769.1978 13952.5059 | lr 2.9e-04 | norm 4763.2891 | dt 9.787 +type train | step 2916 | loss 104.6311 211.7067 321.2294 504.8865 752.0495 1084.3381 1522.0455 2174.6484 3082.6104 4641.2847 7574.0596 13637.6016 | lr 2.9e-04 | norm 4962.2769 | dt 9.783 +type train | step 2917 | loss 103.7881 212.3475 324.1353 510.2488 754.2947 1112.9902 1562.9506 2255.3472 3156.0347 4731.9463 7649.9893 13823.0469 | lr 2.9e-04 | norm 4324.5342 | dt 9.773 +type train | step 2918 | loss 115.2211 240.1954 357.6424 557.5286 815.5793 1174.0275 1631.1993 2320.1299 3252.7649 4851.8965 7846.5566 14150.7764 | lr 2.9e-04 | norm 4626.9082 | dt 9.784 +type train | step 2919 | loss 101.5998 212.8907 326.4104 519.5392 778.7014 1134.6907 1603.3457 2298.7317 3251.1643 4953.4521 8137.9854 14849.9648 | lr 2.9e-04 | norm 6402.1836 | dt 9.783 +type train | step 2920 | loss 100.9958 207.7479 321.2731 516.1923 776.4290 1126.1222 1590.3541 2286.6257 3249.9524 4878.6221 7885.2490 14183.9199 | lr 2.9e-04 | norm 5955.6553 | dt 9.766 +type train | step 2921 | loss 102.5297 212.8051 326.6718 516.2750 769.7243 1121.2795 1582.0201 2275.8496 3223.0881 4884.0840 7992.3252 14482.1660 | lr 2.9e-04 | norm 5140.5967 | dt 9.780 +type train | step 2922 | loss 100.5241 205.3354 316.9636 503.8779 756.7908 1105.2692 1567.9609 2261.9724 3210.5520 4846.0806 7879.3960 14252.4980 | lr 2.9e-04 | norm 4668.2212 | dt 9.779 +type train | step 2923 | loss 110.1229 227.4169 342.8771 535.1582 787.6445 1125.5450 1568.6100 2230.0327 3131.8931 4666.1558 7523.8184 13536.7959 | lr 2.9e-04 | norm 4395.8716 | dt 9.780 +type train | step 2924 | loss 104.3603 213.6166 328.3902 519.3746 770.2468 1121.8147 1573.3315 2254.3699 3155.6704 4734.8281 7674.9688 13881.7080 | lr 2.9e-04 | norm 4565.6562 | dt 9.785 +type train | step 2925 | loss 103.9571 212.3937 322.0387 510.0325 756.4425 1094.5491 1540.0962 2200.7925 3110.7910 4699.3047 7668.0264 13948.1924 | lr 2.9e-04 | norm 4268.9702 | dt 9.788 +type train | step 2926 | loss 103.8159 208.6382 321.7700 506.1506 750.6024 1084.2954 1532.9125 2194.7141 3103.5088 4687.1235 7608.1416 13763.2227 | lr 2.9e-04 | norm 4317.7007 | dt 9.771 +type train | step 2927 | loss 112.1285 234.0317 353.3793 548.4274 810.3628 1167.5569 1635.1401 2322.9465 3254.5381 4866.6738 7800.6484 13988.1689 | lr 2.9e-04 | norm 4151.6855 | dt 9.785 +type train | step 2928 | loss 114.9825 238.4480 356.7420 566.1620 834.2252 1216.5964 1705.0083 2439.8464 3418.8350 5148.3091 8438.4834 15583.9424 | lr 2.9e-04 | norm 5213.7485 | dt 9.769 +type train | step 2929 | loss 109.6013 223.4892 344.4284 536.4812 788.6088 1143.0734 1588.8416 2268.1013 3181.2505 4798.1235 7777.6992 14034.0020 | lr 2.9e-04 | norm 4346.8921 | dt 9.786 +type train | step 2930 | loss 95.8466 196.1473 305.1261 485.7642 732.9910 1059.4709 1502.1140 2141.6631 3038.4841 4599.5737 7473.6079 13564.5879 | lr 2.9e-04 | norm 5143.5986 | dt 9.775 +type train | step 2931 | loss 100.1043 202.4118 311.6598 496.6001 746.0131 1086.8796 1537.1544 2222.5881 3157.3801 4780.3721 7838.7324 14306.3574 | lr 2.9e-04 | norm 4696.8428 | dt 9.779 +type train | step 2932 | loss 107.0282 220.1098 336.4868 528.1298 781.2538 1128.7791 1574.9954 2240.9355 3142.2458 4720.5181 7665.4585 13856.2012 | lr 2.9e-04 | norm 4430.4907 | dt 9.781 +type train | step 2933 | loss 129.4837 268.7441 398.2071 597.9380 855.1423 1208.3351 1650.2523 2315.5986 3167.4568 4693.2422 7512.3145 13622.5947 | lr 2.9e-04 | norm 5205.5728 | dt 9.782 +type train | step 2934 | loss 101.1542 207.3113 314.8731 495.4838 741.4740 1072.7894 1507.7910 2155.0259 3053.0833 4616.7476 7538.0874 13630.9199 | lr 2.9e-04 | norm 4113.6602 | dt 9.768 +type train | step 2935 | loss 99.5513 202.0667 310.8441 497.5494 747.7159 1093.9172 1554.8989 2241.5991 3197.4417 4840.7676 7853.3809 14173.8320 | lr 2.9e-04 | norm 4986.8848 | dt 9.785 +type train | step 2936 | loss 99.2191 203.2062 314.4895 501.3794 751.2407 1088.7686 1529.3884 2181.0615 3100.2539 4667.3350 7573.3350 13689.0322 | lr 2.9e-04 | norm 4274.1650 | dt 9.781 +type train | step 2937 | loss 102.6755 211.4569 323.2693 512.3973 762.0203 1101.4469 1540.8918 2195.9839 3105.4802 4700.9561 7689.3940 13844.8916 | lr 2.9e-04 | norm 3967.4592 | dt 9.788 +type train | step 2938 | loss 111.7195 232.0722 349.8313 545.1014 804.2453 1164.8649 1621.1270 2297.5781 3212.3928 4821.9351 7792.5615 13953.9844 | lr 2.9e-04 | norm 4278.6816 | dt 9.787 +type train | step 2939 | loss 106.2008 218.5005 332.3640 524.2100 776.0311 1128.7983 1588.5028 2272.0117 3211.4509 4828.5439 7814.2207 14098.4414 | lr 2.9e-04 | norm 3781.8357 | dt 9.790 +type train | step 2940 | loss 108.3439 223.7449 338.5859 529.6826 778.3286 1113.1198 1554.1729 2202.5352 3105.8762 4643.6909 7525.3677 13583.1748 | lr 2.9e-04 | norm 3877.4294 | dt 9.778 +type train | step 2941 | loss 98.5174 200.1027 312.0678 502.1453 753.9705 1104.3058 1565.2722 2258.8491 3201.2017 4886.5972 7962.4678 14527.0244 | lr 2.9e-04 | norm 5592.6050 | dt 9.774 +type train | step 2942 | loss 113.1397 233.3586 352.5487 557.2666 810.7476 1177.4722 1644.4746 2344.6216 3297.4204 4981.8164 8132.2363 14794.4893 | lr 2.9e-04 | norm 5056.0127 | dt 9.775 +type train | step 2943 | loss 108.1530 222.8310 335.1269 527.9355 779.8369 1125.7462 1574.3677 2238.4443 3153.6787 4751.8013 7701.2822 13942.5977 | lr 2.9e-04 | norm 3704.0310 | dt 9.785 +type train | step 2944 | loss 104.7333 215.1914 328.1014 518.0367 766.7257 1110.6509 1550.6328 2210.2686 3136.0950 4732.6587 7689.7227 13877.4707 | lr 2.9e-04 | norm 3918.6155 | dt 9.794 +type train | step 2945 | loss 111.2558 229.5458 357.1678 568.7275 854.4590 1244.7592 1769.1902 2534.4321 3586.0864 5337.7671 8477.7744 15317.4355 | lr 2.9e-04 | norm 5168.3701 | dt 9.780 +type train | step 2946 | loss 118.0748 247.4471 370.5255 584.5515 850.0529 1219.7213 1683.0859 2369.3875 3274.2949 4822.9648 7700.8428 13874.0859 | lr 2.9e-04 | norm 5468.9868 | dt 9.777 +type train | step 2947 | loss 103.7554 213.3678 326.3191 510.1091 759.0443 1098.8500 1541.8689 2201.5972 3121.0969 4701.8633 7646.8706 13854.3320 | lr 2.9e-04 | norm 4155.8931 | dt 9.792 +type train | step 2948 | loss 106.6761 218.7555 330.7134 516.5709 763.5034 1113.5066 1571.1521 2262.2229 3196.4360 4844.6875 7949.5327 14501.5303 | lr 2.9e-04 | norm 4461.0449 | dt 9.771 +type train | step 2949 | loss 106.7482 220.7205 333.8279 524.7179 774.8713 1117.6516 1561.7771 2231.1133 3144.1433 4732.6543 7708.0869 13957.4268 | lr 2.9e-04 | norm 4201.0327 | dt 9.772 +type train | step 2950 | loss 103.0020 212.3106 322.8021 515.6626 766.7588 1114.8936 1570.7029 2243.0256 3150.7720 4726.8203 7717.7417 14076.8652 | lr 2.9e-04 | norm 4860.2031 | dt 9.788 +type train | step 2951 | loss 100.8339 207.6593 320.0476 509.8811 759.9176 1109.7877 1566.6497 2254.4453 3160.4700 4791.8354 7799.9194 14164.9863 | lr 2.9e-04 | norm 5017.7646 | dt 9.776 +type train | step 2952 | loss 103.6502 213.1134 324.8126 516.1165 772.3008 1128.2079 1595.4993 2315.2996 3304.9475 4957.8096 7993.3975 14333.9570 | lr 2.9e-04 | norm 5055.3726 | dt 9.781 +type train | step 2953 | loss 106.7445 221.6962 331.7514 521.5113 774.9049 1118.1816 1572.0438 2250.5762 3200.3604 4784.0269 7739.3374 13834.7266 | lr 2.9e-04 | norm 4765.3789 | dt 9.784 +type train | step 2954 | loss 109.5178 227.3996 344.9092 540.9712 798.5515 1153.7374 1617.5431 2311.0181 3256.1106 4858.2524 7865.8071 14168.6650 | lr 2.9e-04 | norm 4273.0386 | dt 9.792 +type train | step 2955 | loss 106.1214 219.2580 332.4134 517.8675 770.0523 1107.9617 1550.7739 2214.8777 3139.0718 4734.2441 7751.9697 14060.7451 | lr 2.9e-04 | norm 4764.9556 | dt 9.790 +type train | step 2956 | loss 106.4461 221.5425 337.3449 531.6533 787.8218 1143.6782 1601.3514 2289.3840 3208.8386 4814.9331 7811.1250 14195.9473 | lr 2.9e-04 | norm 4708.7510 | dt 9.777 +type train | step 2957 | loss 104.8132 215.4138 328.3235 515.1810 770.4220 1115.4205 1564.9814 2239.5193 3173.7764 4820.8164 7882.2212 14330.7158 | lr 2.9e-04 | norm 4288.0376 | dt 9.771 +type train | step 2958 | loss 114.3007 234.5576 353.3363 555.7188 819.1745 1199.0835 1674.1620 2407.4080 3356.4211 5070.5107 8293.2666 15209.2998 | lr 2.9e-04 | norm 5702.2310 | dt 9.772 +type train | step 2959 | loss 106.5335 220.8003 335.1519 530.3546 787.6857 1138.0911 1593.7712 2270.7778 3187.0369 4766.3545 7724.9570 13967.8135 | lr 2.9e-04 | norm 4084.8020 | dt 9.786 +type train | step 2960 | loss 106.0821 219.0696 332.9981 524.1285 775.0818 1126.6329 1578.0568 2251.2837 3165.1558 4764.7334 7760.7139 14011.6133 | lr 2.9e-04 | norm 3900.1309 | dt 9.790 +type train | step 2961 | loss 101.2476 217.2686 338.6289 531.8728 795.3851 1156.0123 1616.4066 2325.9314 3299.1606 4986.6133 8217.1250 15001.5107 | lr 2.9e-04 | norm 7351.1685 | dt 9.775 +type train | step 2962 | loss 103.2499 217.4359 339.5485 540.6375 801.8591 1159.7689 1631.5605 2343.0122 3313.0005 5047.4395 8318.6455 15363.3779 | lr 2.9e-04 | norm 6553.7881 | dt 9.782 +type train | step 2963 | loss 107.6690 221.6862 336.9707 530.0055 783.9337 1124.2173 1562.1005 2215.8555 3101.1863 4624.2422 7407.6016 13446.5361 | lr 2.9e-04 | norm 4478.8550 | dt 9.782 +type train | step 2964 | loss 103.1515 211.9094 327.0639 515.0128 767.4581 1106.4832 1553.5948 2224.3403 3150.5784 4761.8511 7750.5303 13986.9590 | lr 2.9e-04 | norm 4493.0723 | dt 9.775 +type train | step 2965 | loss 104.8055 218.2964 331.4387 524.1978 781.5156 1130.5695 1577.3010 2253.4624 3189.8308 4764.4478 7698.8652 13811.1621 | lr 2.9e-04 | norm 4378.7251 | dt 9.789 +type train | step 2966 | loss 110.8710 231.7990 356.6074 560.5895 831.8798 1189.6770 1657.0116 2356.0889 3327.9771 5025.6699 8174.5757 14817.7070 | lr 2.9e-04 | norm 4526.7217 | dt 9.782 +type train | step 2967 | loss 105.6584 220.5681 338.6536 529.2770 784.1244 1128.9080 1583.4348 2246.5349 3185.1069 4815.3560 7790.5879 14007.2578 | lr 2.9e-04 | norm 4353.4917 | dt 9.779 +type train | step 2968 | loss 107.5258 221.8023 335.8095 525.4729 776.2334 1114.2227 1553.0875 2212.4939 3086.1621 4618.2085 7495.2300 13745.5293 | lr 2.9e-04 | norm 7836.9150 | dt 9.791 +type train | step 2969 | loss 115.4168 233.6995 357.6902 561.0164 824.8578 1188.2673 1652.9681 2347.2896 3293.3750 4924.9639 7972.7275 14578.3994 | lr 2.9e-04 | norm 5185.4761 | dt 9.795 +type train | step 2970 | loss 118.7115 251.3354 375.5332 581.0930 847.1131 1208.6056 1661.5024 2337.2375 3260.3359 4838.2451 7789.9399 13989.8730 | lr 2.9e-04 | norm 4389.5107 | dt 9.805 +type train | step 2971 | loss 102.6270 212.9108 331.6387 531.4528 797.9304 1149.9028 1614.5693 2310.6768 3278.9795 4940.9546 8074.4443 14632.1885 | lr 2.9e-04 | norm 4519.3945 | dt 9.792 +type train | step 2972 | loss 107.7300 222.4279 339.3339 537.5668 795.6320 1152.1409 1611.6650 2285.8555 3230.1206 4814.8926 7801.5586 14089.7500 | lr 2.9e-04 | norm 4528.9883 | dt 9.787 +type train | step 2973 | loss 114.2109 240.0162 360.2844 563.0101 827.6436 1192.1770 1661.0223 2344.9199 3276.6296 4921.2466 7983.9785 14582.8027 | lr 2.9e-04 | norm 5380.6562 | dt 9.782 +type train | step 2974 | loss 111.3836 237.1589 362.0601 570.6465 842.2219 1212.2716 1669.7101 2344.0823 3270.3057 4888.7783 7851.9888 14167.7686 | lr 2.9e-04 | norm 5154.1836 | dt 9.771 +type train | step 2975 | loss 107.3775 226.5422 347.1410 545.9272 805.3854 1164.0627 1626.0420 2328.3811 3254.6323 4927.4473 8090.8853 14741.2695 | lr 2.9e-04 | norm 5792.2769 | dt 9.773 +type train | step 2976 | loss 112.2640 234.7939 353.8727 555.7158 819.0513 1202.6050 1665.6880 2391.4561 3306.3228 4875.7822 7779.1230 13985.4043 | lr 2.9e-04 | norm 5165.5625 | dt 9.767 +type train | step 2977 | loss 109.8407 226.4218 344.1351 539.0873 798.7731 1156.4115 1605.2950 2277.9309 3219.5393 4833.1572 7794.3906 14021.6719 | lr 2.8e-04 | norm 4287.1865 | dt 9.800 +type train | step 2978 | loss 110.0795 226.9695 343.6160 536.9424 794.9651 1151.7808 1596.0967 2263.2844 3199.7222 4815.7920 7827.4209 14178.4004 | lr 2.8e-04 | norm 4246.3911 | dt 9.793 +type train | step 2979 | loss 110.6357 229.8078 353.2271 556.5638 817.2493 1171.8712 1621.9268 2292.0171 3202.3445 4814.7695 7891.8486 14419.1104 | lr 2.8e-04 | norm 5008.0566 | dt 9.776 +type train | step 2980 | loss 107.2044 223.7030 341.8166 536.5834 797.3236 1149.0912 1611.4293 2294.1428 3243.3147 4854.1626 7829.9155 14021.8916 | lr 2.8e-04 | norm 3643.4556 | dt 9.790 +type train | step 2981 | loss 105.2691 218.3910 334.2091 526.3195 780.8491 1133.3397 1586.4802 2272.6313 3212.7759 4841.6772 7878.1909 14234.8662 | lr 2.8e-04 | norm 4559.5234 | dt 9.780 +type train | step 2982 | loss 104.2182 218.1570 332.0292 520.3881 772.6108 1106.3275 1542.5085 2199.1580 3096.8708 4650.3730 7569.9849 13690.9023 | lr 2.8e-04 | norm 5017.0537 | dt 9.771 +type train | step 2983 | loss 115.8125 241.6574 365.0651 575.3477 841.5430 1201.1180 1652.0858 2340.4448 3290.6055 4922.3457 8028.0518 14597.4590 | lr 2.8e-04 | norm 5501.6367 | dt 9.770 +type train | step 2984 | loss 102.6880 214.0401 329.5182 526.5385 784.0849 1133.0287 1588.1007 2264.6931 3207.0049 4829.4976 7905.0332 14362.2744 | lr 2.8e-04 | norm 4310.0342 | dt 9.790 +type train | step 2985 | loss 113.5635 234.6067 359.3668 566.6118 834.2535 1209.1016 1668.6028 2384.5715 3333.7690 5014.9585 8194.3672 14888.0342 | lr 2.8e-04 | norm 4603.1094 | dt 9.783 +type train | step 2986 | loss 108.5545 226.7014 347.2866 544.9563 805.8287 1158.7241 1614.5352 2284.5361 3232.1665 4826.8638 7806.6187 14235.2871 | lr 2.8e-04 | norm 4836.3472 | dt 9.805 +type train | step 2987 | loss 111.2268 229.9828 351.4410 549.4592 812.1892 1158.5140 1609.6989 2280.3677 3194.8831 4775.7261 7718.9043 13877.8633 | lr 2.8e-04 | norm 4078.2471 | dt 9.783 +type train | step 2988 | loss 102.0999 210.4248 325.2428 514.1315 769.7910 1126.6583 1549.6694 2204.2593 3112.3884 4644.5547 7551.1060 13574.7832 | lr 2.8e-04 | norm 3883.7944 | dt 9.791 +type train | step 2989 | loss 107.9785 224.4933 345.9419 543.3186 804.2344 1163.4857 1615.4021 2293.9492 3216.5300 4859.5161 7947.7275 14511.7852 | lr 2.8e-04 | norm 4562.8965 | dt 9.784 +type train | step 2990 | loss 112.4032 241.5737 369.5154 572.0911 838.8859 1210.9615 1647.6360 2320.2520 3292.9636 4930.7183 7941.4087 14242.9082 | lr 2.8e-04 | norm 5997.6748 | dt 9.789 +type train | step 2991 | loss 102.8690 210.4521 326.1414 517.4348 776.5872 1130.5657 1577.2085 2251.8989 3191.8657 4809.9180 7788.9697 14143.3105 | lr 2.8e-04 | norm 4457.6978 | dt 9.780 +type train | step 2992 | loss 106.5304 218.2442 332.9182 522.9595 777.8324 1167.2402 1566.3026 2229.7327 3148.3206 4755.1982 7744.7324 13969.5576 | lr 2.8e-04 | norm 4078.5352 | dt 9.778 +type train | step 2993 | loss 105.2057 217.0584 334.1056 525.7144 783.6841 1138.2384 1568.9149 2222.8647 3158.4614 4753.8086 7724.0962 13938.0938 | lr 2.8e-04 | norm 3766.2966 | dt 9.791 +type train | step 2994 | loss 100.7240 206.3053 321.0511 511.2191 766.2977 1155.7946 1542.7915 2194.6958 3139.5056 4732.7559 7704.6689 13913.2832 | lr 2.8e-04 | norm 4007.2676 | dt 9.796 +type train | step 2995 | loss 108.8803 226.2855 342.5049 536.9264 796.1643 1161.9802 1602.3389 2269.1445 3188.3171 4805.5942 7819.5425 14140.5957 | lr 2.8e-04 | norm 3764.7800 | dt 9.782 +type train | step 2996 | loss 114.1810 236.4945 358.3755 561.8679 825.0025 1238.8605 1672.4043 2386.4990 3331.6201 5005.1157 8113.1470 14678.9375 | lr 2.8e-04 | norm 4920.3589 | dt 9.773 +type train | step 2997 | loss 123.0452 253.2068 380.8850 593.1880 852.6901 1260.2104 1711.8030 2414.8352 3294.3594 4902.0991 7919.5825 14308.3896 | lr 2.8e-04 | norm 6810.7769 | dt 9.760 +type train | step 2998 | loss 115.5365 239.4467 364.3572 569.6664 843.4076 1255.5135 1675.0603 2368.8098 3332.3462 4988.9814 8052.2354 14523.5039 | lr 2.8e-04 | norm 4645.7729 | dt 9.788 +type train | step 2999 | loss 110.5884 230.5341 347.3980 539.3388 793.9512 1174.3571 1593.3293 2255.5669 3170.0571 4726.7090 7676.0161 13940.9277 | lr 2.8e-04 | norm 4415.3613 | dt 9.786 +type train | step 3000 | loss 111.2444 232.5534 356.0255 560.0015 824.0375 1217.1929 1652.6946 2341.6362 3268.1328 4870.0610 7859.9438 14119.0010 | lr 2.8e-04 | norm 4376.0303 | dt 9.779 +type train | step 3001 | loss 115.5393 243.0752 369.8031 597.0818 873.3757 1312.6190 1751.1624 2501.7686 3493.4514 5279.2822 8728.8408 16121.0859 | lr 2.8e-04 | norm 8376.4971 | dt 9.765 +type train | step 3002 | loss 105.1656 220.5904 339.6781 539.9118 804.3214 1199.8743 1624.2103 2306.8911 3243.8613 4870.7593 7911.7871 14396.3105 | lr 2.8e-04 | norm 5328.1226 | dt 9.779 +type train | step 3003 | loss 106.4614 221.0887 335.8455 528.6144 787.9188 1183.8983 1583.4490 2260.3579 3194.8577 4799.2290 7789.1719 14050.8223 | lr 2.8e-04 | norm 4987.2412 | dt 9.778 +type train | step 3004 | loss 114.2612 235.9413 356.8369 555.9783 823.5843 1241.8773 1648.4656 2326.6038 3265.5337 4894.6641 7960.3438 14508.3906 | lr 2.8e-04 | norm 4795.2144 | dt 9.770 +type train | step 3005 | loss 110.5331 227.6941 346.1893 539.5306 801.1409 1234.2888 1612.2859 2291.4253 3226.9622 4821.2036 7775.2744 13944.8750 | lr 2.8e-04 | norm 4826.3145 | dt 9.786 +type train | step 3006 | loss 107.2328 220.6911 336.5253 536.4467 796.9530 1264.2528 1686.7928 2413.6729 3406.8386 5150.4624 8338.0010 14998.0361 | lr 2.8e-04 | norm 6581.6392 | dt 9.762 +type train | step 3007 | loss 106.6120 221.9767 340.8329 539.2175 802.9980 1246.0254 1624.0986 2313.4380 3267.2588 4900.5352 7905.0337 14222.3760 | lr 2.8e-04 | norm 4557.4038 | dt 9.784 +type train | step 3008 | loss 108.3746 230.0681 353.5042 557.9638 818.7314 1268.1224 1644.3622 2346.0090 3280.5078 4943.1035 8075.5981 14624.5205 | lr 2.8e-04 | norm 5599.5205 | dt 9.798 +type train | step 3009 | loss 103.3725 213.3440 327.6258 519.6946 772.1410 1209.7849 1556.8325 2217.8201 3141.2944 4691.9453 7586.1523 13679.5967 | lr 2.8e-04 | norm 5264.6826 | dt 9.779 +type train | step 3010 | loss 109.6928 229.9144 348.8076 551.5319 805.4136 1254.5872 1619.0409 2303.8105 3223.5205 4839.8633 7849.2329 14246.7734 | lr 2.8e-04 | norm 5003.3999 | dt 9.778 +type train | step 3011 | loss 110.5440 228.0962 347.3053 544.3986 810.7632 1252.5006 1622.9431 2301.8721 3243.7654 4905.7920 7950.1440 14353.0312 | lr 2.8e-04 | norm 4326.5005 | dt 9.794 +type train | step 3012 | loss 114.7717 239.6846 359.8159 564.0193 823.5428 1298.9509 1682.7488 2424.9160 3346.7939 4958.7007 7983.7261 14298.3379 | lr 2.8e-04 | norm 4655.4575 | dt 9.778 +type train | step 3013 | loss 111.1177 234.5190 359.6595 579.3950 831.2441 1270.2770 1653.5151 2339.2312 3280.7927 4890.6729 7915.8374 14197.7227 | lr 2.8e-04 | norm 4387.7515 | dt 9.799 +type train | step 3014 | loss 106.1881 219.4747 336.3706 531.6563 792.1613 1214.7231 1597.1189 2268.4331 3210.4705 4836.8311 7862.4033 14177.0342 | lr 2.8e-04 | norm 4551.0703 | dt 9.792 +type train | step 3015 | loss 106.0235 217.9656 334.0415 524.7656 775.3137 1170.7604 1550.5884 2198.5474 3107.9741 4671.2881 7620.0903 13717.6709 | lr 2.8e-04 | norm 4045.7258 | dt 9.788 +type train | step 3016 | loss 108.4710 223.3627 344.0375 545.3344 806.5793 1249.9501 1617.6577 2295.2742 3225.4814 4837.6719 7875.7505 14240.6650 | lr 2.8e-04 | norm 4492.0430 | dt 9.788 +type train | step 3017 | loss 110.3498 228.6417 345.6165 551.0267 795.3395 1254.9436 1591.9973 2261.7578 3172.3040 4748.8726 7690.5562 13867.0010 | lr 2.8e-04 | norm 4686.7251 | dt 9.774 +type train | step 3018 | loss 98.3065 203.0475 313.4995 501.6658 752.3987 1216.6573 1554.1039 2234.0217 3175.1548 4818.9883 7858.5068 14234.9639 | lr 2.8e-04 | norm 5278.1040 | dt 9.770 +type train | step 3019 | loss 107.7952 222.5621 341.2148 552.4030 804.4057 1275.5133 1639.1085 2353.5129 3292.2097 4951.7935 8043.9678 14701.6094 | lr 2.8e-04 | norm 5145.2510 | dt 9.773 +type train | step 3020 | loss 111.2819 226.3207 343.7053 550.0068 809.0121 1279.1005 1631.4951 2327.0532 3268.7834 4881.1924 7898.3086 14319.8604 | lr 2.8e-04 | norm 5031.9746 | dt 9.781 +type train | step 3021 | loss 110.3090 231.6358 354.1782 554.0970 820.2974 1259.8406 1650.5902 2351.2415 3317.0635 5019.2988 8193.8311 14884.3359 | lr 2.8e-04 | norm 4702.8477 | dt 9.789 +type train | step 3022 | loss 113.3903 236.7150 359.1752 571.9079 840.9999 1307.0483 1707.8292 2445.8225 3429.9636 5169.1724 8399.8984 15281.0254 | lr 2.8e-04 | norm 6557.6787 | dt 9.785 +type train | step 3023 | loss 113.3292 234.9820 357.1235 574.2524 829.7000 1278.0989 1660.5448 2358.7061 3325.2832 4974.0547 8014.1899 14476.8926 | lr 2.8e-04 | norm 4927.6533 | dt 9.795 +type train | step 3024 | loss 112.5511 236.3204 357.4180 600.5811 820.5391 1261.8765 1618.2496 2286.5068 3213.0298 4817.1475 7816.8330 14116.3174 | lr 2.8e-04 | norm 5038.3159 | dt 9.783 +type train | step 3025 | loss 107.8479 224.0341 341.1401 545.0290 799.0325 1232.4526 1606.0155 2286.5586 3219.9873 4851.3428 7925.7251 14344.2559 | lr 2.8e-04 | norm 4539.2544 | dt 9.796 +type train | step 3026 | loss 107.0242 223.5913 341.0141 562.1175 792.8658 1233.2784 1605.3391 2291.1602 3232.7700 4867.5747 7928.1260 14305.7305 | lr 2.8e-04 | norm 4810.0288 | dt 9.798 +type train | step 3027 | loss 106.8556 222.7712 340.2290 544.9495 792.9636 1230.0994 1599.2772 2270.8345 3186.5020 4775.6245 7715.8208 13849.7842 | lr 2.8e-04 | norm 4645.8447 | dt 9.784 +type train | step 3028 | loss 103.9944 214.9543 330.1286 546.1273 776.0440 1183.8826 1559.2120 2210.3271 3121.0925 4679.9683 7557.6587 13627.4795 | lr 2.8e-04 | norm 4040.3594 | dt 9.791 +type train | step 3029 | loss 107.3812 221.6518 338.1324 552.4922 794.6937 1231.7152 1631.4512 2325.2976 3253.2390 4889.1694 7917.4473 14391.1934 | lr 2.8e-04 | norm 4598.2695 | dt 9.786 +type train | step 3030 | loss 110.2138 229.9356 350.4444 606.0716 803.4290 1235.7019 1632.3260 2324.1953 3262.1873 4904.2183 7961.2573 14460.0771 | lr 2.8e-04 | norm 5309.0381 | dt 9.790 +type train | step 3031 | loss 106.6246 222.0874 341.6011 563.9680 797.6830 1233.4233 1614.5166 2297.6045 3228.2185 4847.1699 7857.5229 14159.8252 | lr 2.8e-04 | norm 4744.3374 | dt 9.785 +type train | step 3032 | loss 112.9033 235.0811 356.5994 606.1567 825.0256 1256.9153 1633.4137 2309.2651 3246.4041 4854.3682 7833.0273 14039.6816 | lr 2.8e-04 | norm 4633.3540 | dt 9.781 +type train | step 3033 | loss 115.2125 239.5441 359.5785 578.1801 821.7585 1241.2681 1652.4050 2363.3552 3308.2175 4964.3584 8002.8198 14360.2480 | lr 2.8e-04 | norm 4011.9009 | dt 9.800 +type train | step 3034 | loss 104.9601 219.5093 336.0407 552.4056 789.0900 1189.0643 1592.1011 2256.7209 3201.1343 4809.8267 7805.5186 14014.7510 | lr 2.8e-04 | norm 3900.0303 | dt 9.802 +type train | step 3035 | loss 100.4581 204.6473 315.5471 527.6871 762.8298 1171.2395 1575.8591 2267.5808 3247.6262 4847.7197 7736.3423 13876.9775 | lr 2.8e-04 | norm 5790.3496 | dt 9.786 +type train | step 3036 | loss 106.4215 224.9080 346.6484 581.7184 817.1992 1229.6293 1639.9563 2340.6179 3329.2583 5017.1621 8155.4570 14757.0068 | lr 2.8e-04 | norm 5471.0615 | dt 9.791 +type train | step 3037 | loss 109.7822 228.7655 346.6406 583.4191 800.3267 1226.7860 1628.6879 2327.9863 3270.4651 4896.6616 7958.9434 14385.4668 | lr 2.8e-04 | norm 4622.6270 | dt 9.798 +type train | step 3038 | loss 111.6709 231.8563 350.0488 577.9148 808.0999 1224.8075 1604.0895 2263.3955 3171.9155 4753.5713 7746.7822 13964.1299 | lr 2.8e-04 | norm 3941.2781 | dt 9.808 +type train | step 3039 | loss 108.5164 226.8416 348.9738 572.4038 823.5520 1240.4851 1655.0326 2360.5693 3320.9490 5020.1587 8124.2256 14647.1807 | lr 2.8e-04 | norm 5020.7065 | dt 9.787 +type train | step 3040 | loss 110.4667 232.8252 350.8295 566.7576 813.0458 1230.3531 1642.5387 2334.7622 3290.0247 4949.9067 8041.1436 14580.0635 | lr 2.8e-04 | norm 5518.6069 | dt 9.791 +type train | step 3041 | loss 104.1494 220.3069 336.6296 567.1645 791.4786 1206.9268 1611.8885 2310.8477 3258.8245 4940.9189 8113.4326 14839.1211 | lr 2.8e-04 | norm 4855.7178 | dt 9.798 +type train | step 3042 | loss 106.4142 223.3942 345.0365 636.7520 814.3191 1217.3595 1628.5280 2304.4822 3253.9395 4851.3311 7843.4634 14030.0811 | lr 2.8e-04 | norm 5040.3940 | dt 9.803 +type train | step 3043 | loss 121.9541 252.6502 373.9130 589.9043 832.7668 1255.1105 1640.4849 2327.4744 3241.2744 4833.9541 7893.1392 14300.8389 | lr 2.8e-04 | norm 6037.7891 | dt 9.778 +type train | step 3044 | loss 102.8715 217.2079 337.2549 658.6750 807.2656 1246.3763 1672.1261 2410.7778 3408.3840 5246.2710 8710.2891 16079.0078 | lr 2.8e-04 | norm 8490.9453 | dt 9.774 +type train | step 3045 | loss 112.1102 235.2962 362.7841 670.8558 858.1440 1290.2830 1724.7639 2450.8374 3448.2556 5221.3174 8439.8027 15300.2451 | lr 2.7e-04 | norm 6497.2334 | dt 9.799 +type train | step 3046 | loss 108.5218 231.2034 358.3847 631.5640 832.7571 1234.0939 1645.8214 2322.5061 3280.8821 4945.3960 8055.7500 14598.5879 | lr 2.7e-04 | norm 5566.8501 | dt 9.805 +type train | step 3047 | loss 113.4835 236.1207 359.2102 647.2244 823.3625 1246.2677 1639.5176 2333.1650 3272.1455 4872.4409 7881.5840 14190.0635 | lr 2.7e-04 | norm 5895.3398 | dt 9.788 +type train | step 3048 | loss 110.6843 229.8427 353.6049 594.4148 811.3942 1230.1741 1612.6750 2280.0913 3195.7107 4786.8589 7734.3857 13977.1719 | lr 2.7e-04 | norm 4430.0122 | dt 9.804 +type train | step 3049 | loss 119.4613 248.8524 377.7284 639.5535 856.5052 1278.8995 1685.1128 2378.4343 3316.6177 4963.5122 8045.4648 14537.1113 | lr 2.7e-04 | norm 5828.0571 | dt 9.778 +type train | step 3050 | loss 112.3958 233.0915 349.6954 605.1307 800.6973 1218.3230 1609.8862 2289.9072 3213.2422 4806.0298 7773.1265 13989.4814 | lr 2.7e-04 | norm 4595.5791 | dt 9.798 +type train | step 3051 | loss 103.5192 214.5225 330.3106 583.4056 781.6360 1170.9639 1565.6979 2228.9614 3175.5183 4782.6274 7756.5244 13966.9648 | lr 2.7e-04 | norm 4059.9893 | dt 9.797 +type train | step 3052 | loss 109.3200 229.3660 349.1008 605.9709 808.7594 1206.0817 1619.3052 2303.5625 3245.9902 4867.5483 7935.8936 14356.7705 | lr 2.7e-04 | norm 4184.3979 | dt 9.873 +type train | step 3053 | loss 115.4878 238.9863 361.3945 609.7083 816.6189 1214.9500 1613.2560 2278.6641 3200.0166 4790.0713 7806.5835 14199.4795 | lr 2.7e-04 | norm 4426.2002 | dt 9.790 +type train | step 3054 | loss 121.7843 257.8842 385.3966 651.8452 877.0530 1303.3074 1730.3346 2428.5105 3365.7622 4984.4170 8057.6016 14507.4961 | lr 2.7e-04 | norm 5731.6973 | dt 9.780 +type train | step 3055 | loss 104.5065 222.9340 346.4594 579.0312 825.1505 1231.7731 1662.2638 2372.5969 3356.5559 5058.2246 8229.1182 14867.7734 | lr 2.7e-04 | norm 5071.0317 | dt 9.783 +type train | step 3056 | loss 103.3779 216.4769 335.2156 581.7529 804.2796 1206.0585 1619.7660 2316.2637 3279.5461 4938.8252 7935.4487 14319.3242 | lr 2.7e-04 | norm 4711.8662 | dt 9.794 +type train | step 3057 | loss 115.9944 239.1862 358.1567 592.4849 828.9373 1254.7827 1664.0472 2367.5347 3246.9980 4833.0605 7757.7485 14010.4131 | lr 2.7e-04 | norm 5314.8022 | dt 9.753 +type train | step 3058 | loss 105.4944 219.4591 337.1984 569.5751 795.0023 1205.5621 1624.6593 2334.0640 3278.1021 4947.5005 8102.8604 14691.7256 | lr 2.7e-04 | norm 5419.8252 | dt 9.777 +type train | step 3059 | loss 107.9604 231.5335 352.5205 600.0463 818.1238 1217.6066 1619.8510 2293.2791 3220.2566 4845.4810 7913.1821 14318.9424 | lr 2.7e-04 | norm 5096.0513 | dt 9.791 +type train | step 3060 | loss 103.1426 214.2019 326.6281 559.4355 771.1535 1159.8229 1555.8118 2229.9297 3150.0457 4752.0254 7770.6748 14103.5811 | lr 2.7e-04 | norm 4450.7378 | dt 9.785 +type train | step 3061 | loss 104.7615 216.5023 330.9638 545.4791 771.7701 1167.5032 1563.0499 2225.5674 3143.3716 4729.0093 7700.6387 13962.6611 | lr 2.7e-04 | norm 4571.4780 | dt 9.789 +type train | step 3062 | loss 113.7807 242.6203 375.7609 619.7313 910.8812 1371.7244 1809.3613 2613.0112 3685.2539 5633.6836 9183.7100 16769.1367 | lr 2.7e-04 | norm 8573.7637 | dt 9.774 +type train | step 3063 | loss 112.6381 236.2893 362.2321 597.9861 853.3245 1285.1409 1713.7465 2456.0710 3448.5476 5206.4707 8484.3242 15396.5625 | lr 2.7e-04 | norm 4671.3291 | dt 9.785 +type train | step 3064 | loss 110.4374 228.0967 345.8836 572.7335 803.0896 1224.9666 1627.3978 2301.3904 3213.8652 4784.0322 7786.1040 14070.8496 | lr 2.7e-04 | norm 4629.1777 | dt 9.784 +type train | step 3065 | loss 102.4754 215.5120 328.4624 536.9885 785.0005 1187.3575 1609.3861 2307.7749 3272.6697 4977.4160 8097.7549 14646.1855 | lr 2.7e-04 | norm 5621.8218 | dt 9.785 +type train | step 3066 | loss 103.6559 213.7243 329.5462 556.6381 782.6407 1169.5969 1572.9493 2238.7283 3166.5315 4767.3994 7779.6802 14002.4980 | lr 2.7e-04 | norm 4388.3022 | dt 9.796 +type train | step 3067 | loss 109.8873 230.5370 348.2552 585.1967 807.0982 1205.7371 1622.5090 2297.8965 3247.4421 4854.8389 7829.2832 14101.4697 | lr 2.7e-04 | norm 4647.9590 | dt 9.786 +type train | step 3068 | loss 105.6049 219.6989 335.6168 567.8203 784.8713 1183.5332 1583.1610 2253.9814 3183.7561 4782.3428 7809.4829 14046.3252 | lr 2.7e-04 | norm 4558.0781 | dt 9.801 +type train | step 3069 | loss 104.4964 218.8781 336.8676 587.7702 786.8646 1172.6835 1579.3490 2250.8069 3195.3801 4823.4868 7860.1025 14313.0264 | lr 2.7e-04 | norm 5181.3433 | dt 9.803 +type train | step 3070 | loss 111.4827 234.5803 361.1097 635.2064 853.6862 1282.0027 1728.4402 2470.0134 3440.0530 5172.3403 8393.4316 15303.7510 | lr 2.7e-04 | norm 5296.7114 | dt 9.779 +type train | step 3071 | loss 107.0718 222.8938 343.3908 596.0221 806.0895 1214.2015 1630.6001 2323.9775 3277.8455 4926.2334 8008.8247 14472.7666 | lr 2.7e-04 | norm 4938.1045 | dt 9.786 +type train | step 3072 | loss 107.1031 224.0095 342.1668 602.4496 796.0781 1197.1299 1599.1765 2279.0903 3227.1848 4826.0088 7842.9053 14204.6494 | lr 2.7e-04 | norm 4610.0479 | dt 9.802 +type train | step 3073 | loss 109.6232 231.0007 353.7683 635.9318 821.6104 1232.3699 1648.4012 2339.5332 3277.9155 4910.9102 7934.2061 14415.8301 | lr 2.7e-04 | norm 4540.6099 | dt 9.807 +type train | step 3074 | loss 105.5263 225.8808 348.1884 614.1066 824.1343 1229.9044 1647.8209 2339.1804 3313.1511 5031.3960 8324.7568 15405.2441 | lr 2.7e-04 | norm 6986.4834 | dt 9.787 +type train | step 3075 | loss 111.7040 233.9341 349.6638 621.2971 811.4076 1216.9598 1627.2288 2309.9114 3237.8728 4860.6641 7879.3730 14395.6758 | lr 2.7e-04 | norm 4610.3618 | dt 9.779 +type train | step 3076 | loss 124.7416 259.2561 386.5980 672.0366 870.8145 1301.5398 1737.8845 2471.5146 3408.6470 5055.4170 8112.8379 14583.6523 | lr 2.7e-04 | norm 5116.1118 | dt 9.777 +type train | step 3077 | loss 102.7637 211.1111 324.5726 582.3343 775.5237 1162.0450 1581.1517 2268.1838 3213.2664 4845.6611 7871.3833 14209.5938 | lr 2.7e-04 | norm 5374.8823 | dt 9.797 +type train | step 3078 | loss 103.3145 212.7535 326.0831 568.0989 766.3053 1153.5592 1547.4965 2195.7134 3102.1270 4669.1338 7548.1680 13579.1250 | lr 2.7e-04 | norm 4049.2844 | dt 9.796 +type train | step 3079 | loss 104.5356 223.1909 343.3541 596.5326 802.8363 1195.9685 1614.3577 2286.9182 3236.7344 4821.5649 7844.0459 14087.0918 | lr 2.7e-04 | norm 6384.6733 | dt 9.790 +type train | step 3080 | loss 104.4282 217.7072 334.1230 580.1281 781.8460 1169.8389 1566.0092 2230.2456 3153.0476 4744.7695 7746.2188 14044.9766 | lr 2.7e-04 | norm 4263.1357 | dt 9.792 +type train | step 3081 | loss 104.7483 219.6721 337.4720 568.2326 787.0527 1175.6184 1585.6290 2261.1272 3174.2954 4764.7471 7728.1562 13903.8652 | lr 2.7e-04 | norm 4611.0786 | dt 9.788 +type train | step 3082 | loss 102.1395 212.8646 327.9113 557.5739 774.8809 1160.4221 1575.7494 2252.6533 3191.9294 4797.0249 7789.3604 13976.8027 | lr 2.7e-04 | norm 4187.4609 | dt 9.789 +type train | step 3083 | loss 107.7072 223.4328 337.4613 573.9226 787.1464 1166.4144 1583.1787 2252.0881 3166.2139 4762.9131 7719.2148 13890.2842 | lr 2.7e-04 | norm 4351.8643 | dt 9.791 +type train | step 3084 | loss 113.7368 238.3597 358.7715 605.5557 821.3098 1216.7626 1626.2987 2301.6602 3227.5132 4842.2007 7821.9565 14258.7744 | lr 2.7e-04 | norm 4529.3291 | dt 9.795 +type train | step 3085 | loss 108.5467 224.6326 345.0988 600.7223 801.4644 1188.1226 1599.9510 2266.6370 3195.1860 4804.6196 7845.1523 14243.9834 | lr 2.7e-04 | norm 4530.0991 | dt 9.802 +type train | step 3086 | loss 91.0189 189.7771 315.1465 568.0602 796.6874 1199.7865 1671.7606 2393.2346 3434.3040 5274.2051 8754.7207 16358.7207 | lr 2.7e-04 | norm 12617.6387 | dt 9.794 +type train | step 3087 | loss 114.5539 241.3808 364.7647 637.6884 829.5283 1227.1534 1641.5721 2324.5967 3259.8188 4864.2832 7849.1914 14174.9033 | lr 2.7e-04 | norm 4673.6572 | dt 9.788 +type train | step 3088 | loss 101.7272 212.5224 326.6593 578.3632 779.0447 1171.9410 1587.7924 2273.7854 3197.2205 4816.4399 7881.9189 14336.3936 | lr 2.7e-04 | norm 4605.3311 | dt 9.780 +type train | step 3089 | loss 103.3033 213.4161 329.4124 579.6685 783.4235 1167.9857 1583.9594 2256.3362 3197.4597 4812.2959 7831.5391 14268.0566 | lr 2.7e-04 | norm 4738.7178 | dt 9.781 +type train | step 3090 | loss 101.0859 209.8871 323.6521 569.7628 769.2449 1146.5679 1552.8463 2207.2876 3140.8616 4725.6880 7665.2578 13752.2373 | lr 2.7e-04 | norm 3849.6575 | dt 9.791 +type train | step 3091 | loss 113.1631 236.5229 365.6096 631.9322 848.2621 1283.7419 1734.8218 2476.4480 3474.4221 5192.9502 8389.9570 15131.7744 | lr 2.7e-04 | norm 6173.5498 | dt 9.793 +type train | step 3092 | loss 104.5176 218.9761 337.7049 578.9539 799.0123 1199.3350 1616.5697 2306.8518 3254.1665 4893.6777 7966.9141 14349.0840 | lr 2.7e-04 | norm 5347.5225 | dt 9.782 +type train | step 3093 | loss 105.6654 221.0107 334.8127 578.9924 781.3541 1161.1100 1564.1941 2220.0168 3137.5754 4698.9106 7629.1230 13784.1836 | lr 2.7e-04 | norm 4097.8242 | dt 9.803 +type train | step 3094 | loss 112.5178 234.3646 353.7435 601.5578 803.1658 1193.1340 1605.2946 2283.6941 3202.9587 4810.5352 7863.4473 14304.8984 | lr 2.7e-04 | norm 4833.0728 | dt 9.790 +type train | step 3095 | loss 116.9382 248.4774 371.9942 618.2139 835.7037 1225.1902 1628.0404 2286.0015 3158.1648 4710.7402 7594.0059 13680.6729 | lr 2.7e-04 | norm 5097.2573 | dt 9.774 +type train | step 3096 | loss 107.8961 222.3032 339.8080 583.5898 791.6322 1171.1367 1581.7833 2241.0608 3151.0205 4752.6528 7757.2075 14117.7422 | lr 2.7e-04 | norm 4117.4336 | dt 9.798 +type train | step 3097 | loss 110.3673 233.2119 349.8375 577.1585 789.5754 1148.6509 1523.3204 2096.2737 2879.2239 4252.6777 6736.0400 12293.6016 | lr 2.7e-04 | norm 5709.5576 | dt 9.749 +type train | step 3098 | loss 105.7393 223.0814 340.9016 588.7383 791.1437 1181.5995 1597.8120 2278.3665 3207.4998 4795.2271 7714.1597 13846.5576 | lr 2.7e-04 | norm 4727.4922 | dt 9.788 +type train | step 3099 | loss 108.5127 223.9695 344.8844 602.7021 820.1337 1233.2341 1669.7262 2382.5781 3346.7722 5004.2705 8112.9790 14614.8760 | lr 2.7e-04 | norm 5097.0498 | dt 9.802 +type train | step 3100 | loss 111.2251 230.4608 349.8808 612.1051 818.6002 1217.6084 1648.6274 2352.5454 3310.6602 5004.0171 8146.8545 14680.5371 | lr 2.7e-04 | norm 4964.6987 | dt 9.793 +type train | step 3101 | loss 106.8005 220.5229 336.4914 595.8469 797.4382 1210.7437 1645.2523 2358.9519 3292.4888 4917.3154 7956.5845 14341.7812 | lr 2.7e-04 | norm 5639.7075 | dt 9.789 +type train | step 3102 | loss 117.7485 245.1169 368.5094 623.6616 838.8676 1235.3679 1658.1777 2343.8552 3266.1387 4879.8486 7919.9922 14305.3438 | lr 2.7e-04 | norm 4159.9448 | dt 9.792 +type train | step 3103 | loss 111.5167 233.3795 353.5925 612.3674 814.5929 1203.5667 1616.6390 2294.3442 3218.1746 4837.1367 7876.9316 14259.9893 | lr 2.7e-04 | norm 4178.9609 | dt 9.790 +type train | step 3104 | loss 109.2910 227.3124 343.2838 589.3297 798.4991 1189.6415 1609.4507 2292.8533 3216.0950 4766.3975 7648.8105 13689.4385 | lr 2.7e-04 | norm 5243.0625 | dt 9.797 +type train | step 3105 | loss 107.1364 222.7743 336.7332 587.1672 783.4105 1167.7699 1582.3308 2238.7156 3128.0803 4694.8979 7613.6201 13709.6279 | lr 2.7e-04 | norm 4721.8887 | dt 9.803 +type train | step 3106 | loss 96.7609 204.1003 318.2711 570.4395 773.0696 1153.1365 1569.7682 2251.3679 3226.0356 4914.5063 7989.1465 14476.6504 | lr 2.7e-04 | norm 7248.4766 | dt 9.796 +type train | step 3107 | loss 105.6449 217.6919 329.2749 576.6994 765.5317 1145.0933 1557.5349 2224.3147 3141.5996 4754.3091 7759.3779 14135.9355 | lr 2.7e-04 | norm 5208.4565 | dt 9.774 +type train | step 3108 | loss 96.3712 199.6829 307.9247 541.9330 733.4716 1103.0183 1508.3726 2173.3704 3069.3240 4647.7090 7600.7207 13887.7021 | lr 2.7e-04 | norm 7862.1421 | dt 9.773 +type train | step 3109 | loss 102.5269 212.9335 331.0378 578.1672 778.1495 1157.4961 1571.6401 2241.5850 3181.4138 4818.6738 7868.0337 14296.7402 | lr 2.7e-04 | norm 4321.9971 | dt 9.801 +type train | step 3110 | loss 101.4252 211.1108 323.2070 569.8256 777.5947 1168.5558 1604.8593 2302.7864 3248.6094 4921.5161 8029.5386 14633.8516 | lr 2.7e-04 | norm 5981.5244 | dt 9.787 +type train | step 3111 | loss 108.2728 225.0715 338.0235 582.0423 785.4411 1159.8596 1579.3448 2249.8289 3158.7917 4720.9360 7635.6104 13736.0527 | lr 2.7e-04 | norm 4867.3130 | dt 9.784 +type train | step 3112 | loss 112.1781 234.3437 355.2379 592.7172 819.3771 1220.9484 1639.8734 2337.1335 3267.4888 4916.3882 7998.6035 14372.5371 | lr 2.7e-04 | norm 4519.2837 | dt 9.781 +type train | step 3113 | loss 104.1449 214.1868 328.2943 568.9720 777.9458 1166.9216 1583.1759 2251.5925 3166.7368 4725.7227 7579.7983 13585.4756 | lr 2.6e-04 | norm 5063.9844 | dt 9.782 +type train | step 3114 | loss 102.1940 213.3250 328.9803 555.5153 783.8226 1166.2031 1587.4849 2265.4646 3229.6472 4863.6270 7883.6299 14124.0811 | lr 2.6e-04 | norm 3905.2793 | dt 9.792 +type train | step 3115 | loss 100.0693 211.4674 328.5771 549.2932 782.2265 1191.4265 1624.7429 2354.7896 3324.7705 5009.5742 8169.9346 14743.6104 | lr 2.6e-04 | norm 5978.9287 | dt 9.781 +type train | step 3116 | loss 113.2469 237.8887 356.3920 582.9727 810.7518 1192.3665 1611.9468 2284.9829 3191.5242 4820.3472 7797.6421 14248.7842 | lr 2.6e-04 | norm 4498.6401 | dt 9.783 +type train | step 3117 | loss 102.8014 210.2606 321.2374 553.7483 768.9860 1148.4468 1567.9498 2255.1797 3179.7825 4800.6143 7769.4072 13910.9121 | lr 2.6e-04 | norm 6050.4097 | dt 9.793 +type train | step 3118 | loss 102.3163 211.1407 322.6958 562.8824 757.9578 1126.7887 1530.2507 2179.2024 3091.6934 4649.1875 7506.2524 13481.2246 | lr 2.6e-04 | norm 4010.3691 | dt 9.792 +type train | step 3119 | loss 104.0298 217.3416 334.0048 564.3762 781.6260 1159.9832 1583.4846 2261.0000 3186.5010 4807.2788 7810.7085 14113.1172 | lr 2.6e-04 | norm 4398.2515 | dt 9.787 +type train | step 3120 | loss 113.7189 237.1554 364.7882 619.5588 855.0065 1263.5452 1703.0172 2405.1709 3329.1943 4971.2861 8059.0439 14522.7764 | lr 2.6e-04 | norm 6254.7002 | dt 9.785 +type train | step 3121 | loss 90.6800 190.8759 300.9886 543.2368 749.4080 1129.2031 1564.6218 2264.8350 3222.4255 4946.9546 8323.2012 15546.8115 | lr 2.6e-04 | norm 8714.7119 | dt 9.788 +type train | step 3122 | loss 104.5225 216.1988 327.8640 569.5914 779.7184 1169.6885 1599.3749 2290.4204 3236.6577 4875.4609 7950.6777 14263.8838 | lr 2.6e-04 | norm 5405.7212 | dt 9.781 +type train | step 3123 | loss 108.1586 227.6337 347.7110 591.7745 796.4719 1176.9746 1594.7327 2270.2676 3200.9885 4869.0186 8050.7485 14673.5654 | lr 2.6e-04 | norm 5418.8643 | dt 9.807 +type train | step 3124 | loss 110.7968 232.4125 351.1163 595.1172 807.6530 1217.9094 1642.1222 2343.9360 3218.9587 4792.9907 7800.7920 14151.4990 | lr 2.6e-04 | norm 5196.6064 | dt 9.780 +type train | step 3125 | loss 106.9166 219.9596 336.8972 576.4854 786.7795 1166.5623 1589.6400 2249.9026 3174.8923 4763.2466 7741.9580 13998.5762 | lr 2.6e-04 | norm 4710.4028 | dt 9.789 +type train | step 3126 | loss 97.3469 202.7195 313.8583 545.7148 755.6750 1128.6128 1556.2095 2223.9028 3151.7734 4743.3135 7687.1880 13804.1787 | lr 2.6e-04 | norm 4172.2803 | dt 9.798 +type train | step 3127 | loss 103.6825 215.0095 328.7478 565.1014 776.5308 1158.7150 1592.4419 2284.3730 3234.3774 4902.0679 7997.3047 14582.9639 | lr 2.6e-04 | norm 4536.7471 | dt 9.778 +type train | step 3128 | loss 101.2956 211.9722 326.0989 557.0026 766.7253 1143.2358 1557.5153 2220.7815 3144.5549 4736.7588 7682.2217 13794.1855 | lr 2.6e-04 | norm 4038.4133 | dt 9.793 +type train | step 3129 | loss 99.3769 210.0978 329.2669 563.7688 784.0819 1159.0323 1574.1825 2252.8633 3205.5806 4870.2847 8012.4429 14556.1641 | lr 2.6e-04 | norm 6307.9199 | dt 9.790 +type train | step 3130 | loss 106.7800 222.4753 340.1146 587.8035 801.5961 1185.2994 1619.9993 2314.1599 3252.1379 4907.9141 7977.4316 14441.6699 | lr 2.6e-04 | norm 4838.3970 | dt 9.797 +type train | step 3131 | loss 112.8970 242.7583 368.8273 611.8781 853.4413 1235.9128 1669.6571 2351.8162 3295.0417 4964.5332 8071.4839 14632.6689 | lr 2.6e-04 | norm 6909.9766 | dt 9.802 +type train | step 3132 | loss 106.4512 220.5629 336.1779 576.2421 779.6864 1157.6848 1569.6011 2217.7656 3107.5955 4636.8853 7462.0015 13446.6914 | lr 2.6e-04 | norm 4345.4810 | dt 9.807 +type train | step 3133 | loss 109.2714 225.0186 344.2346 579.8939 802.0365 1189.7767 1624.8044 2313.8564 3262.4927 4897.1953 7897.9209 14161.7207 | lr 2.6e-04 | norm 5897.5283 | dt 9.775 +type train | step 3134 | loss 104.1118 216.1237 330.1159 566.0861 769.7983 1137.2639 1550.9930 2220.3940 3143.7102 4742.4287 7714.0723 13974.7227 | lr 2.6e-04 | norm 4330.2573 | dt 9.798 +type train | step 3135 | loss 105.7414 220.1120 333.4317 571.8237 800.1393 1203.2126 1646.4640 2378.5725 3338.0750 5038.4316 8229.6416 15004.3916 | lr 2.6e-04 | norm 5462.8057 | dt 9.773 +type train | step 3136 | loss 102.6003 214.8777 329.2253 565.5367 786.1093 1167.4568 1589.9093 2265.0916 3195.2371 4793.3174 7772.6060 13944.8682 | lr 2.6e-04 | norm 4331.4331 | dt 9.793 +type train | step 3137 | loss 106.0727 222.8738 336.5154 572.8943 789.4390 1178.6586 1606.0400 2285.9666 3182.5598 4760.5171 7810.7607 14265.5498 | lr 2.6e-04 | norm 6056.1914 | dt 9.773 +type train | step 3138 | loss 105.7877 219.9345 331.9341 560.5880 772.8249 1144.0353 1558.4530 2217.4116 3124.4299 4726.7178 7716.1006 13951.7080 | lr 2.6e-04 | norm 4282.2363 | dt 9.798 +type train | step 3139 | loss 104.0849 215.9372 331.2797 566.3120 776.8076 1149.2997 1567.7462 2227.8838 3147.1196 4746.7085 7761.2402 14075.2490 | lr 2.6e-04 | norm 4107.1489 | dt 9.797 +type train | step 3140 | loss 102.5966 214.0149 327.9597 548.7531 776.6781 1160.2574 1582.8325 2278.7988 3193.7659 4795.5620 7785.9395 14089.7334 | lr 2.6e-04 | norm 4404.9404 | dt 9.792 +type train | step 3141 | loss 102.8767 213.4447 327.8038 550.7323 772.1663 1142.1544 1561.2869 2230.9980 3180.5159 4773.4609 7757.7886 13878.6211 | lr 2.6e-04 | norm 3878.6296 | dt 9.795 +type train | step 3142 | loss 103.7397 212.1760 328.9138 562.7021 777.0316 1161.9874 1595.0020 2277.4961 3188.0381 4801.5713 7797.8833 14143.3574 | lr 2.6e-04 | norm 4233.4985 | dt 9.786 +type train | step 3143 | loss 106.3710 219.3336 331.3334 564.0938 771.7825 1140.5868 1555.9236 2217.6416 3118.2722 4673.8594 7535.4814 13504.3691 | lr 2.6e-04 | norm 4015.8140 | dt 9.783 +type train | step 3144 | loss 108.5738 226.7868 345.5969 573.7206 795.0233 1160.0875 1582.1449 2244.7053 3163.1221 4762.5830 7676.3340 13888.2588 | lr 2.6e-04 | norm 5443.1875 | dt 9.788 +type train | step 3145 | loss 105.0547 217.8900 331.5570 560.7524 778.7408 1166.1313 1595.1705 2285.8069 3224.3230 4852.7549 7810.2349 14002.3555 | lr 2.6e-04 | norm 4201.2793 | dt 9.795 +type train | step 3146 | loss 98.8292 203.6798 314.8841 537.9179 752.6656 1123.9379 1546.3285 2227.1704 3156.7231 4757.7861 7744.1875 13944.3584 | lr 2.6e-04 | norm 3813.4146 | dt 9.796 +type train | step 3147 | loss 108.8659 226.7911 342.4814 574.1456 791.2640 1173.7576 1595.3949 2271.6345 3180.3870 4756.3125 7700.8740 13836.2979 | lr 2.6e-04 | norm 3991.2842 | dt 9.790 +type train | step 3148 | loss 102.8606 214.8874 330.3862 555.0970 774.0565 1147.4282 1563.7660 2232.7896 3148.1892 4723.5972 7656.8994 13765.6445 | lr 2.6e-04 | norm 3803.8650 | dt 9.796 +type train | step 3149 | loss 104.5343 215.4212 329.1798 566.0327 774.4495 1151.0347 1575.9935 2261.4739 3197.6663 4826.4536 7837.0083 14108.8516 | lr 2.6e-04 | norm 4113.9316 | dt 9.781 +type train | step 3150 | loss 107.7090 223.2817 339.2725 570.0789 781.4427 1147.9303 1558.5759 2210.4202 3114.8630 4668.5586 7556.5571 13577.9131 | lr 2.6e-04 | norm 3849.6245 | dt 9.782 +type train | step 3151 | loss 100.8888 208.0267 315.6732 535.0389 745.1240 1108.9380 1522.2379 2188.0171 3108.7302 4697.1870 7642.7900 13873.7168 | lr 2.6e-04 | norm 4781.2642 | dt 9.787 +type train | step 3152 | loss 109.7073 226.5327 345.3459 580.6294 806.9012 1189.7903 1627.2900 2320.1602 3263.7764 4901.7559 7888.6646 14161.1582 | lr 2.6e-04 | norm 4260.2954 | dt 9.777 +type train | step 3153 | loss 103.3988 215.1782 333.7658 565.2322 792.4668 1168.9294 1592.7374 2271.4927 3217.1765 4830.8159 7829.3364 14005.5615 | lr 2.6e-04 | norm 4813.3447 | dt 9.778 +type train | step 3154 | loss 106.1712 223.8378 342.1089 578.1158 796.5198 1182.2173 1604.5525 2279.4692 3191.8472 4785.1904 7814.3838 14220.5938 | lr 2.6e-04 | norm 4451.2793 | dt 9.778 +type train | step 3155 | loss 106.2000 220.8968 337.9903 556.0553 783.9561 1164.4446 1585.4028 2255.2883 3177.2888 4791.7246 7786.3711 14019.7100 | lr 2.6e-04 | norm 4353.5566 | dt 9.799 +type train | step 3156 | loss 109.2295 225.3375 346.7578 583.0588 808.0927 1197.8604 1627.1465 2315.2434 3260.3755 4885.8735 7902.9546 14202.6553 | lr 2.6e-04 | norm 4569.8281 | dt 9.801 +type train | step 3157 | loss 105.3804 218.2810 337.2202 567.3317 793.9111 1176.2252 1610.4905 2300.7751 3241.6401 4900.4419 8000.9780 14395.3525 | lr 2.6e-04 | norm 4458.5791 | dt 9.782 +type train | step 3158 | loss 104.3396 216.3254 329.9635 555.8170 768.9093 1136.5023 1558.0000 2221.2290 3141.7642 4748.0420 7723.2749 13887.0801 | lr 2.6e-04 | norm 3629.3904 | dt 9.783 +type train | step 3159 | loss 101.9502 210.6534 323.2112 553.7833 765.3212 1129.4780 1540.8540 2193.0471 3127.5042 4715.8799 7673.5366 13738.6279 | lr 2.6e-04 | norm 3966.8521 | dt 9.789 +type train | step 3160 | loss 104.5512 215.4528 328.1633 561.1467 775.8448 1159.7671 1586.2408 2266.4438 3186.1296 4813.5205 7954.2710 14648.7129 | lr 2.6e-04 | norm 6891.9121 | dt 9.771 +type train | step 3161 | loss 97.2346 202.2501 313.3508 537.7231 747.7061 1115.1527 1530.6251 2192.5242 3093.0056 4657.7852 7607.0288 13757.1816 | lr 2.6e-04 | norm 4400.2563 | dt 9.777 +type train | step 3162 | loss 109.0179 226.1230 343.8090 586.7215 805.3417 1198.3064 1630.6050 2342.8574 3278.3813 4917.2324 7985.5059 14448.4512 | lr 2.6e-04 | norm 4328.9976 | dt 9.788 +type train | step 3163 | loss 102.9928 213.5701 325.5385 548.8864 766.7054 1129.9375 1546.4121 2212.9521 3128.8228 4714.6357 7693.3682 13913.0947 | lr 2.6e-04 | norm 4154.3687 | dt 9.794 +type train | step 3164 | loss 105.3106 216.1983 334.7566 559.8170 780.3545 1156.2233 1573.7697 2237.4521 3128.2803 4694.5190 7601.3550 13717.5586 | lr 2.6e-04 | norm 4755.3711 | dt 9.773 +type train | step 3165 | loss 111.2660 232.4810 356.1192 596.5642 828.4878 1212.7852 1655.5995 2354.3801 3304.1528 5006.8291 8148.0898 14773.0684 | lr 2.6e-04 | norm 4772.1870 | dt 9.787 +type train | step 3166 | loss 108.0725 224.8739 343.5547 583.1729 808.0814 1199.6555 1651.7720 2358.5901 3304.2046 4941.4141 7962.3604 14292.8477 | lr 2.6e-04 | norm 4325.9224 | dt 9.783 +type train | step 3167 | loss 116.9721 242.3178 361.9173 599.6284 823.7437 1214.6267 1655.3674 2362.5459 3276.6716 4891.4912 7902.9653 14272.1367 | lr 2.6e-04 | norm 6198.3779 | dt 9.783 +type train | step 3168 | loss 105.5997 219.3584 331.6533 555.7817 774.9218 1148.1698 1566.4406 2229.6970 3138.6794 4730.3101 7661.4502 13842.4863 | lr 2.6e-04 | norm 4628.7705 | dt 9.785 +type train | step 3169 | loss 106.0509 220.8882 335.3206 560.0988 785.1509 1156.0076 1583.2688 2255.6292 3170.1353 4785.1924 7786.9321 14097.9580 | lr 2.6e-04 | norm 4437.4648 | dt 9.785 +type train | step 3170 | loss 117.3356 243.2269 362.0427 595.7959 827.6140 1217.9596 1655.7371 2363.3640 3301.0759 4931.3882 8005.5771 14431.8789 | lr 2.6e-04 | norm 5314.0229 | dt 9.771 +type train | step 3171 | loss 110.2044 229.4051 345.7233 576.8552 796.3111 1168.0149 1581.4742 2230.1667 3102.0867 4642.0396 7529.5737 13596.2031 | lr 2.6e-04 | norm 4733.7466 | dt 9.786 +type train | step 3172 | loss 99.3197 205.8170 320.5391 548.1448 767.3102 1136.9722 1565.4623 2244.9526 3198.2542 4831.6113 7817.1724 14003.5342 | lr 2.6e-04 | norm 4862.8037 | dt 9.781 +type train | step 3173 | loss 107.1381 220.1783 338.2675 570.7572 791.6079 1164.4144 1587.7935 2257.1233 3163.4539 4754.6787 7708.7617 13879.3105 | lr 2.6e-04 | norm 4263.6548 | dt 9.786 +type train | step 3174 | loss 110.8459 231.3241 347.4276 578.1327 796.0661 1170.9006 1603.7983 2280.8911 3187.5479 4786.3789 7785.0850 14064.3496 | lr 2.6e-04 | norm 4140.3828 | dt 9.788 +type train | step 3175 | loss 107.9795 225.9016 342.8758 562.5141 790.4908 1157.5375 1579.9906 2245.8545 3169.5518 4739.5078 7630.9961 13682.4307 | lr 2.6e-04 | norm 3694.9646 | dt 9.791 +type train | step 3176 | loss 105.6871 218.5983 335.2969 558.7463 792.0475 1168.4395 1599.3228 2287.0801 3224.9607 4887.1953 7924.9473 14247.5264 | lr 2.6e-04 | norm 4370.5684 | dt 9.788 +type train | step 3177 | loss 114.5315 239.2844 356.7076 584.4531 807.3982 1178.6251 1599.0988 2266.1709 3148.0005 4719.9121 7646.1846 13966.7539 | lr 2.6e-04 | norm 5502.4829 | dt 9.770 +type train | step 3178 | loss 113.7765 239.2628 363.2865 594.6628 827.0367 1210.5532 1642.3374 2309.0515 3213.8672 4782.5112 7699.2119 13766.7656 | lr 2.6e-04 | norm 3955.7744 | dt 9.799 +type train | step 3179 | loss 103.9025 214.8477 329.4184 554.1957 771.7992 1139.5825 1559.8669 2222.4475 3118.0593 4687.9287 7587.5757 13644.5977 | lr 2.6e-04 | norm 3661.2017 | dt 9.820 +type train | step 3180 | loss 125.4639 267.1943 394.2604 636.3760 874.2303 1277.8314 1717.3961 2414.0842 3337.8259 4929.9453 7908.4399 14158.6426 | lr 2.6e-04 | norm 7032.5210 | dt 9.775 +type train | step 3181 | loss 108.2400 225.3087 343.3307 571.6177 796.5281 1177.8970 1596.4656 2271.1538 3176.0649 4777.4438 7751.3823 13972.5820 | lr 2.6e-04 | norm 3488.4102 | dt 9.800 +type train | step 3182 | loss 95.7833 200.3704 313.3264 530.2697 752.0884 1117.6211 1540.1982 2196.0654 3133.6680 4743.8979 7725.0576 13924.6982 | lr 2.6e-04 | norm 4566.6045 | dt 9.794 +type train | step 3183 | loss 101.8599 210.6075 324.7165 550.3022 774.3809 1174.4181 1610.5912 2322.0771 3270.7549 4937.3462 8021.5376 14412.3369 | lr 2.5e-04 | norm 4886.6479 | dt 9.795 +type train | step 3184 | loss 103.8388 216.3540 329.7715 559.1832 784.0928 1162.5647 1586.9878 2270.0220 3172.1477 4757.5137 7690.0449 13918.0488 | lr 2.5e-04 | norm 5467.3052 | dt 9.788 +type train | step 3185 | loss 100.0120 207.5132 319.1158 543.0584 758.7610 1133.2423 1556.9915 2228.4419 3126.7288 4707.2627 7599.8862 13679.1865 | lr 2.5e-04 | norm 4151.5674 | dt 9.780 +type train | step 3186 | loss 108.3247 227.7498 344.4468 582.7883 808.9863 1186.0385 1605.1722 2258.1868 3126.4792 4624.7554 7413.6333 13356.9648 | lr 2.5e-04 | norm 4681.5869 | dt 9.780 +type train | step 3187 | loss 102.2482 211.7345 326.1157 551.3746 767.1852 1128.7384 1536.3907 2190.7358 3093.5762 4628.0840 7492.1270 13439.8271 | lr 2.5e-04 | norm 3716.9614 | dt 9.795 +type train | step 3188 | loss 104.0694 217.0502 328.2744 545.0452 766.1505 1135.2030 1562.2676 2225.1562 3130.3491 4731.9639 7647.8550 13793.6338 | lr 2.5e-04 | norm 5182.5869 | dt 9.769 +type train | step 3189 | loss 98.0656 203.2361 312.8936 527.9679 747.5890 1111.8446 1533.5435 2198.8679 3113.3748 4693.2681 7607.7783 13656.5830 | lr 2.5e-04 | norm 4222.7529 | dt 9.794 +type train | step 3190 | loss 108.6985 227.9469 345.7737 570.3235 798.3915 1173.3018 1605.8353 2288.1416 3204.9712 4806.0356 7793.0664 14034.5332 | lr 2.5e-04 | norm 3880.2932 | dt 9.796 +type train | step 3191 | loss 114.6291 238.2344 356.6716 588.3082 816.0760 1184.2017 1608.8784 2272.4084 3183.8711 4738.1538 7619.8838 13668.6406 | lr 2.5e-04 | norm 5023.7192 | dt 9.786 +type train | step 3192 | loss 110.2241 233.7243 351.6884 576.3891 799.9758 1175.5443 1598.0649 2268.2642 3158.0515 4744.0400 7715.3477 13978.9941 | lr 2.5e-04 | norm 5349.7959 | dt 9.789 +type train | step 3193 | loss 103.1427 216.3199 334.2343 569.8148 805.0487 1210.7188 1657.6763 2396.8887 3368.4417 5068.8369 8216.2715 14959.3125 | lr 2.5e-04 | norm 5217.6577 | dt 9.768 +type train | step 3194 | loss 115.9367 240.8076 367.0307 601.6351 834.5690 1232.1464 1661.5212 2343.6860 3201.0593 4752.2383 7642.2666 13724.9570 | lr 2.5e-04 | norm 4802.5361 | dt 9.777 +type train | step 3195 | loss 102.8336 218.3370 332.3716 552.3625 775.3831 1144.1672 1576.6182 2255.8994 3158.2261 4753.7549 7651.7139 13749.6924 | lr 2.5e-04 | norm 5417.3291 | dt 9.794 +type train | step 3196 | loss 108.9288 222.7459 337.6721 559.5912 785.3257 1152.3927 1576.6398 2245.5413 3157.8357 4769.4473 7754.0088 14060.3438 | lr 2.5e-04 | norm 4081.4238 | dt 9.789 +type train | step 3197 | loss 107.3786 224.4425 340.4893 561.4971 784.9978 1154.2482 1575.2372 2241.1187 3143.5796 4745.5464 7757.1733 14208.3828 | lr 2.5e-04 | norm 5364.8169 | dt 9.804 +type train | step 3198 | loss 108.3536 230.6304 347.3873 578.4354 813.0577 1210.6627 1671.1274 2412.6392 3366.0049 5054.5078 8137.4575 14589.3877 | lr 2.5e-04 | norm 5262.6104 | dt 9.789 +type train | step 3199 | loss 105.4010 218.4917 331.2710 546.9244 768.0688 1119.4678 1525.3938 2168.5754 3059.1829 4585.1699 7401.6289 13272.8125 | lr 2.5e-04 | norm 3679.9917 | dt 9.785 +type train | step 3200 | loss 104.7982 216.0904 331.4907 551.8101 776.8573 1139.8104 1558.6904 2245.2256 3167.1541 4784.3032 7809.8594 14245.6299 | lr 2.5e-04 | norm 5607.6138 | dt 9.791 +type train | step 3201 | loss 98.2277 200.6111 314.2116 536.9379 758.7599 1134.1902 1560.7604 2245.5994 3193.8328 4816.1162 7871.8560 14309.1299 | lr 2.5e-04 | norm 4305.7866 | dt 9.783 +type train | step 3202 | loss 105.3045 220.1305 338.4765 558.8192 791.2525 1155.8525 1585.2173 2256.5029 3168.3469 4781.6216 7809.9956 14173.1152 | lr 2.5e-04 | norm 4449.5439 | dt 9.788 +type train | step 3203 | loss 105.2433 217.8628 330.5582 544.1761 770.8464 1134.4233 1544.9578 2197.2056 3092.4905 4656.0303 7581.1201 13683.3672 | lr 2.5e-04 | norm 4369.7280 | dt 9.796 +type train | step 3204 | loss 103.8327 214.8003 330.2991 554.3967 780.0120 1156.9430 1588.8363 2268.3315 3188.5315 4798.2490 7776.4575 14102.0312 | lr 2.5e-04 | norm 4612.2988 | dt 9.790 +type train | step 3205 | loss 99.7429 207.7901 319.6593 540.1395 768.2876 1151.3650 1592.0247 2301.1436 3250.1260 4881.8398 7869.4604 14046.2744 | lr 2.5e-04 | norm 4404.5347 | dt 9.783 +type train | step 3206 | loss 101.3651 211.2628 324.6760 545.4384 768.9642 1144.4128 1586.4609 2282.9177 3223.9014 4869.4912 7899.0361 14183.4443 | lr 2.5e-04 | norm 4083.6680 | dt 9.797 +type train | step 3207 | loss 110.7234 230.1420 350.4702 577.4761 810.6389 1185.5939 1612.3242 2281.0151 3196.2969 4758.5176 7707.8638 13847.3818 | lr 2.5e-04 | norm 4236.2568 | dt 9.779 +type train | step 3208 | loss 103.4560 214.6008 332.1971 552.3672 785.4180 1170.1881 1613.9622 2309.4155 3243.3206 4900.6768 7918.3496 14271.4316 | lr 2.5e-04 | norm 4935.8179 | dt 9.784 +type train | step 3209 | loss 112.9066 240.0455 359.2897 594.5959 827.6135 1212.6624 1650.2377 2327.1313 3203.3535 4780.6748 7750.7236 14044.6875 | lr 2.5e-04 | norm 4567.0557 | dt 9.786 +type train | step 3210 | loss 106.7765 220.4690 336.0670 556.7881 782.8876 1158.9391 1589.4991 2275.2827 3181.0254 4749.7354 7656.8179 13785.7842 | lr 2.5e-04 | norm 4712.1763 | dt 9.800 +type train | step 3211 | loss 102.3663 211.0996 324.2371 543.7846 758.5180 1120.2505 1533.8746 2184.7825 3090.2573 4665.8452 7561.3076 13510.0586 | lr 2.5e-04 | norm 3845.7566 | dt 9.789 +type train | step 3212 | loss 103.1570 214.0504 328.0498 551.8671 778.8238 1162.3043 1609.7708 2313.5962 3254.7559 4894.9614 8003.5234 14556.0908 | lr 2.5e-04 | norm 4560.2549 | dt 9.778 +type train | step 3213 | loss 107.5780 223.4125 342.2597 562.8646 802.0599 1176.5656 1616.5308 2311.8279 3232.1296 4868.0444 7924.1548 14272.3770 | lr 2.5e-04 | norm 5096.3594 | dt 9.778 +type train | step 3214 | loss 112.2977 234.2055 352.7777 576.6599 813.0728 1194.7634 1624.6018 2303.4155 3217.9653 4806.5757 7783.0352 14031.0703 | lr 2.5e-04 | norm 4135.8652 | dt 9.782 +type train | step 3215 | loss 105.1545 217.2205 332.3752 553.8279 783.4483 1152.3710 1587.1962 2257.5688 3187.9841 4787.2666 7745.7061 13858.0459 | lr 2.5e-04 | norm 3843.8174 | dt 9.790 +type train | step 3216 | loss 111.0636 235.6645 354.6186 576.3071 805.8760 1175.9688 1596.2131 2254.5803 3148.9937 4729.4751 7700.5791 14050.6768 | lr 2.5e-04 | norm 4512.5000 | dt 9.778 +type train | step 3217 | loss 103.7670 217.5670 331.9844 551.9153 779.8506 1145.9180 1574.0413 2249.0632 3172.2830 4796.4526 7834.1431 14162.1699 | lr 2.5e-04 | norm 4499.5947 | dt 9.800 +type train | step 3218 | loss 104.9278 219.1764 337.7418 559.2637 791.8049 1174.7368 1613.6456 2305.3645 3230.4490 4882.9600 8002.1436 14568.3203 | lr 2.5e-04 | norm 4095.7739 | dt 9.799 +type train | step 3219 | loss 98.9970 203.7721 318.1130 532.3264 764.9380 1139.1324 1579.5310 2265.0889 3211.5146 4841.2651 7927.2705 14322.9580 | lr 2.5e-04 | norm 4527.4395 | dt 9.784 +type train | step 3220 | loss 104.2296 218.5205 334.7322 550.9022 786.1604 1158.3129 1593.8850 2270.1665 3187.6877 4779.7798 7776.6929 14085.8730 | lr 2.5e-04 | norm 5694.4165 | dt 9.783 +type train | step 3221 | loss 104.0950 219.1245 333.1923 551.6371 777.0244 1134.7606 1555.1212 2211.2483 3138.2837 4715.9741 7650.7681 13755.2754 | lr 2.5e-04 | norm 3895.6836 | dt 9.811 +type train | step 3222 | loss 113.0113 234.0825 350.1768 573.4853 801.4855 1174.7760 1592.2233 2257.5164 3132.6780 4720.1592 7827.3286 14318.3740 | lr 2.5e-04 | norm 7161.2461 | dt 9.780 +type train | step 3223 | loss 110.8403 233.2065 347.9012 569.4850 795.2172 1158.1711 1586.4275 2248.2087 3178.7717 4779.7666 7722.2949 13812.8359 | lr 2.5e-04 | norm 4608.7681 | dt 9.791 +type train | step 3224 | loss 103.4953 215.9453 328.7370 539.3935 765.3347 1132.0322 1567.6257 2257.0947 3157.2852 4720.6328 7712.4946 14025.2803 | lr 2.5e-04 | norm 5768.2153 | dt 9.782 +type train | step 3225 | loss 106.6904 221.9228 342.8748 575.8467 818.5951 1204.8048 1650.5720 2354.1340 3329.5679 5042.4897 8198.5156 14930.5293 | lr 2.5e-04 | norm 4847.5239 | dt 9.786 +type train | step 3226 | loss 96.2704 200.8958 312.9433 531.6153 761.2513 1126.5366 1571.8755 2261.9482 3229.2341 4872.5225 7835.1748 14017.3740 | lr 2.5e-04 | norm 5135.0483 | dt 9.782 +type train | step 3227 | loss 106.5667 222.1020 338.9344 558.7210 779.7329 1133.3413 1565.1017 2227.3774 3166.5027 4795.5923 7718.8413 13876.2207 | lr 2.5e-04 | norm 8161.1929 | dt 9.781 +type train | step 3228 | loss 100.1235 207.6253 320.4431 547.0257 763.4286 1127.1240 1564.7867 2238.5747 3171.4058 4824.6514 7895.3008 14271.4814 | lr 2.5e-04 | norm 4678.2627 | dt 9.778 +type train | step 3229 | loss 100.7746 210.0255 324.9564 546.1833 767.4738 1128.6730 1554.6886 2219.2847 3146.7268 4754.2627 7731.8794 13855.2656 | lr 2.5e-04 | norm 3750.3186 | dt 9.804 +type train | step 3230 | loss 101.3764 209.2015 320.0504 539.2899 760.0913 1118.2073 1542.9060 2201.4441 3128.1157 4736.0312 7703.3457 13815.7119 | lr 2.5e-04 | norm 3948.2170 | dt 9.782 +type train | step 3231 | loss 108.6366 223.9621 342.3750 565.8355 797.2391 1163.8049 1588.4231 2250.5413 3143.2021 4725.4253 7698.4062 13936.6396 | lr 2.5e-04 | norm 4359.6089 | dt 9.777 +type train | step 3232 | loss 102.2876 208.6791 319.0981 532.4127 758.3089 1133.0605 1570.2881 2252.1519 3151.2529 4727.2476 7684.2764 13970.1035 | lr 2.5e-04 | norm 4653.5063 | dt 9.779 +type train | step 3233 | loss 104.3759 220.6217 335.7737 556.0798 787.7172 1158.1038 1583.9502 2247.1951 3173.0955 4763.7764 7713.4775 13871.8594 | lr 2.5e-04 | norm 6121.8623 | dt 9.771 +type train | step 3234 | loss 104.1740 215.8507 325.8262 544.0198 764.2220 1127.1853 1556.9427 2232.1670 3153.7874 4763.8457 7774.0132 14116.4580 | lr 2.5e-04 | norm 5076.4595 | dt 9.793 +type train | step 3235 | loss 104.6080 217.6533 334.2181 559.3197 791.8564 1160.8402 1585.7468 2256.1414 3164.0920 4765.9155 7732.8491 14099.3613 | lr 2.5e-04 | norm 4854.3306 | dt 9.775 +type train | step 3236 | loss 98.1356 208.5450 321.8590 542.9706 775.9000 1142.3770 1576.5312 2255.9094 3196.0693 4845.4751 7958.4751 14448.3379 | lr 2.5e-04 | norm 5215.6304 | dt 9.783 +type train | step 3237 | loss 102.0506 212.3544 325.7142 542.9870 766.0125 1123.2850 1548.2665 2212.2214 3123.4956 4709.3887 7684.9946 13826.2559 | lr 2.5e-04 | norm 4000.9883 | dt 9.794 +type train | step 3238 | loss 101.6006 208.5584 321.3109 540.6660 767.3362 1139.2938 1575.1038 2265.9355 3184.7732 4793.0928 7812.8730 14108.1094 | lr 2.5e-04 | norm 4460.7192 | dt 9.774 +type train | step 3239 | loss 112.2431 237.2167 357.3460 577.6033 813.3243 1178.1271 1614.1672 2280.3208 3208.2744 4837.4146 7854.4434 14144.2949 | lr 2.5e-04 | norm 4746.0488 | dt 9.805 +type train | step 3240 | loss 99.5205 208.8941 324.8333 543.8680 773.5677 1134.7382 1568.1986 2239.7939 3194.2646 4837.8022 7912.8521 14305.4844 | lr 2.5e-04 | norm 4367.2769 | dt 9.813 +type train | step 3241 | loss 113.6066 240.0254 357.7952 585.3865 819.4716 1194.1655 1637.1199 2321.4573 3243.6831 4852.3662 7829.3882 14069.5537 | lr 2.5e-04 | norm 4060.8491 | dt 9.798 +type train | step 3242 | loss 97.9860 203.1692 314.6843 528.2832 755.2623 1113.7451 1537.9192 2202.9058 3134.3464 4716.7617 7601.4136 13545.0625 | lr 2.5e-04 | norm 3539.6077 | dt 9.795 +type train | step 3243 | loss 109.2475 233.2893 352.0857 574.9755 812.2250 1187.2836 1631.8904 2310.9299 3244.2454 4879.1641 7923.0498 14332.3330 | lr 2.5e-04 | norm 3912.0295 | dt 9.802 +type train | step 3244 | loss 106.8544 225.3327 343.2372 565.2975 798.6661 1174.8647 1610.1390 2288.1890 3188.5972 4765.6504 7758.7026 13957.0801 | lr 2.5e-04 | norm 3978.7656 | dt 9.784 +type train | step 3245 | loss 109.6630 226.6597 347.4880 579.1367 808.2234 1182.9856 1612.1306 2272.3035 3153.5916 4693.5703 7580.9224 13684.9736 | lr 2.5e-04 | norm 4469.5864 | dt 9.790 +type train | step 3246 | loss 103.8053 216.3843 330.2397 545.1899 775.5527 1124.7811 1556.2489 2231.2756 3161.2583 4769.3452 7702.0459 13930.8037 | lr 2.5e-04 | norm 4964.9849 | dt 9.780 +type train | step 3247 | loss 105.8327 217.6701 331.6876 556.7340 772.4220 1143.0096 1571.5963 2258.0928 3156.0544 4749.2783 7767.9277 13990.8320 | lr 2.5e-04 | norm 5315.1689 | dt 9.787 +type train | step 3248 | loss 102.2577 213.3162 326.7885 542.4156 768.2870 1133.7048 1563.9994 2237.1287 3156.6372 4756.2158 7720.2935 13858.7744 | lr 2.5e-04 | norm 3709.1943 | dt 9.807 +type train | step 3249 | loss 99.8432 204.4313 311.2353 517.9172 739.0007 1088.3611 1508.5438 2159.2119 3059.9082 4625.2471 7511.0396 13491.7373 | lr 2.5e-04 | norm 4810.0239 | dt 9.789 +type train | step 3250 | loss 97.8592 204.4210 318.5204 531.4071 761.5424 1111.6213 1533.7787 2182.5769 3107.0461 4687.9004 7616.6123 13638.4629 | lr 2.5e-04 | norm 4130.5039 | dt 9.795 +type train | step 3251 | loss 94.2774 201.0963 327.7475 558.4204 808.3376 1179.4612 1655.3223 2379.1221 3383.6824 5194.2617 8573.2207 15544.8906 | lr 2.5e-04 | norm 8532.4150 | dt 9.797 +type train | step 3252 | loss 108.6832 229.0309 347.8984 573.0765 807.1967 1187.9343 1620.4958 2303.2278 3197.9788 4775.9561 7757.9404 14091.1240 | lr 2.4e-04 | norm 4173.0278 | dt 9.777 +type train | step 3253 | loss 120.3711 253.2258 371.2204 608.7511 838.6810 1261.3910 1734.5505 2443.4995 3348.4961 5029.0874 8212.9805 14863.0557 | lr 2.4e-04 | norm 7718.4092 | dt 9.774 +type train | step 3254 | loss 102.9331 215.4325 326.3130 538.4345 765.5916 1133.6272 1557.2990 2226.7319 3143.1357 4773.8652 7783.5029 14033.5508 | lr 2.4e-04 | norm 4236.8638 | dt 9.780 +type train | step 3255 | loss 102.8246 212.2220 324.6316 535.1743 763.7346 1130.5266 1549.9735 2207.4395 3104.0149 4659.1191 7571.2026 13667.5879 | lr 2.4e-04 | norm 4234.3110 | dt 9.786 +type train | step 3256 | loss 114.0556 239.5166 363.9020 593.3383 826.0487 1203.6874 1624.9617 2282.8989 3132.2278 4643.2915 7490.8154 13540.6982 | lr 2.4e-04 | norm 4699.1401 | dt 9.774 +type train | step 3257 | loss 104.8004 219.7329 335.3289 549.8612 779.0024 1151.0839 1571.9769 2248.3240 3143.1174 4744.5635 7751.5649 14080.3604 | lr 2.4e-04 | norm 4555.1411 | dt 9.780 +type train | step 3258 | loss 107.0944 222.3705 341.0847 564.3607 796.5288 1184.9596 1633.5325 2348.0168 3267.8611 4892.2622 7983.6465 14611.9307 | lr 2.4e-04 | norm 5132.0620 | dt 9.774 +type train | step 3259 | loss 114.8493 241.0528 368.7701 608.7684 853.3661 1256.1493 1713.2585 2455.1108 3416.4504 5123.5269 8202.5840 14692.3193 | lr 2.4e-04 | norm 4719.1738 | dt 9.788 +type train | step 3260 | loss 104.1019 217.0681 330.0909 543.7377 771.8562 1140.1488 1565.9352 2236.7998 3143.4958 4714.6074 7688.4072 13865.6553 | lr 2.4e-04 | norm 4241.2754 | dt 9.781 +type train | step 3261 | loss 105.1811 219.1342 332.3753 548.0444 777.0555 1142.0679 1555.9072 2204.2258 3086.8748 4654.7646 7592.3818 13725.0225 | lr 2.4e-04 | norm 3857.6963 | dt 9.767 +type train | step 3262 | loss 102.8988 216.1244 329.8979 543.9118 777.9609 1150.5386 1593.0298 2276.0828 3193.5483 4820.1162 7809.8105 14104.1699 | lr 2.4e-04 | norm 7398.8389 | dt 9.792 +type train | step 3263 | loss 102.7429 215.9532 328.2707 544.6779 776.7391 1173.7905 1637.4685 2374.7659 3321.2234 4994.8818 8156.4512 14737.3965 | lr 2.4e-04 | norm 5260.1196 | dt 9.776 +type train | step 3264 | loss 103.0928 214.5973 330.0628 541.7812 774.1451 1144.7444 1575.6289 2257.7603 3162.4102 4774.8306 7803.2559 14121.5889 | lr 2.4e-04 | norm 4449.2983 | dt 9.782 +type train | step 3265 | loss 103.9691 217.6913 336.8333 558.4309 794.4554 1180.1067 1632.1766 2332.5422 3286.1846 4947.9985 8019.4482 14459.4424 | lr 2.4e-04 | norm 6288.9102 | dt 9.758 +type train | step 3266 | loss 109.4700 227.4079 341.9344 554.0728 785.5503 1153.9127 1567.4392 2224.2153 3103.6514 4648.6978 7568.4741 13627.3193 | lr 2.4e-04 | norm 4093.1450 | dt 9.803 +type train | step 3267 | loss 111.2829 236.9949 360.6865 580.3262 822.3176 1210.4048 1665.8741 2378.9951 3319.7993 4998.5410 8068.2808 14467.6895 | lr 2.4e-04 | norm 4948.2515 | dt 9.781 +type train | step 3268 | loss 97.4514 203.5347 320.5088 539.5309 778.0436 1147.7068 1592.1219 2290.4421 3241.3921 4884.5142 7886.1714 14149.9727 | lr 2.4e-04 | norm 4077.7344 | dt 9.785 +type train | step 3269 | loss 105.3891 217.4713 331.0496 540.7828 769.9108 1118.4022 1543.9510 2182.0444 3046.8418 4623.6289 7592.6362 14074.0215 | lr 2.4e-04 | norm 8114.9463 | dt 9.779 +type train | step 3270 | loss 102.8311 212.1089 323.7774 537.9702 758.1357 1115.2594 1543.0962 2202.8447 3121.2405 4723.8535 7661.5786 13790.6240 | lr 2.4e-04 | norm 4526.2534 | dt 9.784 +type train | step 3271 | loss 99.4056 207.3901 320.3617 535.5923 757.2375 1117.3700 1546.8649 2211.2686 3116.0957 4692.8394 7616.6182 13665.0957 | lr 2.4e-04 | norm 3752.0500 | dt 9.782 +type train | step 3272 | loss 97.8178 203.2873 313.6688 527.3073 751.0662 1109.3053 1539.9595 2213.7039 3132.7458 4733.8906 7683.4004 13857.4189 | lr 2.4e-04 | norm 4697.8560 | dt 9.779 +type train | step 3273 | loss 102.0443 214.2682 330.1852 546.6381 778.3727 1149.6270 1591.6575 2284.5427 3210.4106 4852.5156 7919.5186 14427.9277 | lr 2.4e-04 | norm 5175.9937 | dt 9.793 +type train | step 3274 | loss 104.7705 218.9100 335.8620 548.9100 781.3387 1153.0481 1588.8352 2262.6704 3171.9595 4761.3501 7665.7930 13742.9785 | lr 2.4e-04 | norm 4184.6245 | dt 9.779 +type train | step 3275 | loss 97.4236 201.9475 310.9714 519.5359 743.2922 1090.9032 1512.8732 2165.5864 3062.3589 4632.7944 7506.1235 13458.0293 | lr 2.4e-04 | norm 3929.5835 | dt 9.787 +type train | step 3276 | loss 101.8624 214.0551 333.3813 555.7356 795.6497 1170.6110 1616.7595 2319.9861 3258.3081 4929.6309 8000.8804 14435.2197 | lr 2.4e-04 | norm 4372.1226 | dt 9.787 +type train | step 3277 | loss 111.0646 232.7883 351.6173 569.9495 804.4596 1177.6431 1621.8551 2305.8567 3187.0386 4765.7764 7688.4053 13835.6982 | lr 2.4e-04 | norm 6413.2534 | dt 9.796 +type train | step 3278 | loss 113.7110 236.6239 356.2010 575.2318 809.0248 1191.6689 1635.1177 2321.5940 3159.6997 4714.7002 7626.1362 13801.5117 | lr 2.4e-04 | norm 7769.8452 | dt 9.783 +type train | step 3279 | loss 97.0543 202.4658 310.8090 515.1371 740.0948 1088.6689 1507.7119 2161.3433 3096.0642 4677.1084 7589.5039 13690.0469 | lr 2.4e-04 | norm 5318.4204 | dt 9.789 +type train | step 3280 | loss 102.5292 214.5055 326.9265 546.9066 778.1578 1145.7814 1589.0505 2276.5891 3204.3191 4831.6001 7819.8477 14117.3242 | lr 2.4e-04 | norm 4634.6167 | dt 9.793 +type train | step 3281 | loss 105.8566 220.0065 335.1706 552.3564 777.6132 1136.7017 1565.8979 2230.0986 3137.5039 4715.6982 7611.1406 13671.4521 | lr 2.4e-04 | norm 4102.3911 | dt 9.797 +type train | step 3282 | loss 98.6585 206.1893 316.1098 528.4853 751.5044 1099.3961 1519.1498 2170.3545 3075.0974 4649.9941 7538.7598 13588.7598 | lr 2.4e-04 | norm 4225.8145 | dt 9.801 +type train | step 3283 | loss 111.3579 228.9676 350.0249 573.1693 811.1729 1185.8760 1621.0392 2293.5657 3192.4124 4736.3022 7668.8311 13847.1562 | lr 2.4e-04 | norm 5226.8853 | dt 9.782 +type train | step 3284 | loss 119.9993 249.7702 372.1758 608.0939 849.5273 1270.0786 1738.2830 2483.6089 3417.6389 5122.3164 8363.2305 15242.4609 | lr 2.4e-04 | norm 9041.7344 | dt 9.771 +type train | step 3285 | loss 128.4940 272.0150 400.4338 647.1020 902.0911 1391.5771 1951.0979 2912.6401 3986.1431 5970.0801 9385.0156 16128.1299 | lr 2.4e-04 | norm 5706.4463 | dt 9.760 +type train | step 3286 | loss 100.4064 209.1800 319.7477 522.8685 748.8690 1095.0288 1510.8005 2159.8083 3057.4187 4640.1567 7572.4170 13811.7393 | lr 2.4e-04 | norm 6058.8101 | dt 9.790 +type train | step 3287 | loss 100.1862 209.3968 321.4121 530.5657 764.4254 1121.5590 1556.9435 2230.8157 3171.2278 4799.2446 7792.1797 13915.8145 | lr 2.4e-04 | norm 4056.4592 | dt 9.781 +type train | step 3288 | loss 98.9734 203.7256 314.3858 522.3685 752.3502 1119.4211 1555.6853 2246.4121 3164.3154 4817.7681 7827.2939 14133.8545 | lr 2.4e-04 | norm 4827.5371 | dt 9.794 +type train | step 3289 | loss 98.9269 205.6553 315.7234 523.7997 749.6731 1100.3896 1524.0603 2176.8677 3085.8301 4656.5820 7573.8569 13649.7256 | lr 2.4e-04 | norm 3862.4626 | dt 9.818 +type train | step 3290 | loss 103.6837 217.0352 332.4866 543.3882 778.0092 1141.2747 1581.9391 2249.9377 3159.4766 4766.8452 7763.0366 14022.9209 | lr 2.4e-04 | norm 4192.5513 | dt 9.806 +type train | step 3291 | loss 171.8929 382.6176 528.9305 801.5386 1111.3669 1623.6509 2187.1321 3071.6050 4046.1355 5724.2754 8775.8838 15135.9443 | lr 2.4e-04 | norm 7618.9775 | dt 9.766 +type train | step 3292 | loss 103.0385 215.9699 325.8916 530.1131 760.4740 1112.9133 1547.2113 2212.1433 3127.2075 4710.1699 7657.3262 13788.2402 | lr 2.4e-04 | norm 5333.4785 | dt 9.790 +type train | step 3293 | loss 104.2052 213.8737 327.4065 537.6897 769.9993 1130.4364 1558.3134 2215.1194 3113.5083 4684.6318 7613.5771 13817.8477 | lr 2.4e-04 | norm 5827.8726 | dt 9.784 +type train | step 3294 | loss 101.9246 211.6429 327.5251 542.8864 781.2197 1152.1768 1589.1367 2266.9180 3201.0659 4849.9707 7877.6865 14260.5205 | lr 2.4e-04 | norm 4066.3103 | dt 9.792 +type train | step 3295 | loss 112.3982 234.6201 355.9771 576.1916 813.0698 1176.5443 1587.1516 2235.0784 3080.2461 4605.3032 7481.4092 13718.0762 | lr 2.4e-04 | norm 5912.4575 | dt 9.766 +type train | step 3296 | loss 96.0972 210.2050 328.0418 560.9466 806.5557 1176.2023 1618.2870 2298.4675 3226.7209 4891.6436 7945.2393 14462.8281 | lr 2.4e-04 | norm 9075.0967 | dt 9.778 +type train | step 3297 | loss 96.9767 205.1796 321.9841 541.9990 783.1019 1153.8148 1603.6211 2299.9536 3250.0454 4910.2197 7979.8535 14323.2256 | lr 2.4e-04 | norm 5082.5322 | dt 9.802 +type train | step 3298 | loss 113.4847 239.2165 359.8147 576.1993 817.4075 1190.4775 1633.6987 2318.7114 3238.2422 4871.4209 7948.1699 14372.0811 | lr 2.4e-04 | norm 4912.5552 | dt 9.789 +type train | step 3299 | loss 107.5132 222.0176 338.5737 556.8992 799.3038 1180.6038 1627.7697 2320.9194 3241.7910 4877.2935 7950.7871 14528.6836 | lr 2.4e-04 | norm 5475.3345 | dt 9.784 +type train | step 3300 | loss 143.0656 292.1185 414.4645 638.7457 908.3471 1361.3433 1858.1547 2564.3552 3524.5361 5115.8335 8026.7861 14361.0762 | lr 2.4e-04 | norm 6745.1216 | dt 9.762 +type train | step 3301 | loss 105.7545 222.0532 342.1256 563.5315 804.0533 1178.2249 1624.3939 2321.8711 3261.6477 4869.1455 7863.8276 14115.3906 | lr 2.4e-04 | norm 5328.9624 | dt 9.787 +type train | step 3302 | loss 101.8160 212.6101 326.6857 537.1203 764.9457 1113.5205 1540.7380 2193.1699 3099.1018 4681.1685 7626.6768 13828.7266 | lr 2.4e-04 | norm 3895.8679 | dt 9.808 +type train | step 3303 | loss 106.5965 222.1515 339.3459 557.8508 796.8142 1162.4738 1604.8192 2292.0576 3248.0193 4891.0742 7907.3970 14104.3066 | lr 2.4e-04 | norm 3970.8481 | dt 9.798 +type train | step 3304 | loss 110.7727 232.9437 350.9141 567.3232 804.7854 1180.8732 1616.2952 2302.5303 3223.0859 4828.9429 7808.7090 13931.0342 | lr 2.4e-04 | norm 3698.1074 | dt 9.797 +type train | step 3305 | loss 104.4698 218.7527 333.8232 544.6970 778.7483 1136.0908 1566.8975 2230.0337 3147.5454 4726.3770 7657.4141 13799.3682 | lr 2.4e-04 | norm 3612.4211 | dt 9.794 +type train | step 3306 | loss 102.6838 219.7097 337.8732 560.8894 804.4456 1184.5168 1633.6069 2339.5496 3279.8357 4921.1616 7988.4395 14393.1680 | lr 2.4e-04 | norm 5591.9946 | dt 9.793 +type train | step 3307 | loss 101.8960 212.7271 326.8369 533.2623 764.3574 1125.5006 1556.5709 2227.4556 3143.8044 4765.4907 7796.8477 14139.0615 | lr 2.4e-04 | norm 4039.1030 | dt 9.811 +type train | step 3308 | loss 98.8497 205.9146 317.5085 526.1094 757.4441 1119.4242 1563.3267 2253.0588 3195.8301 4811.6226 7766.8135 13900.8867 | lr 2.4e-04 | norm 3755.2883 | dt 9.803 +type train | step 3309 | loss 111.5969 231.1084 349.9816 572.0497 810.4034 1184.0576 1612.7056 2293.4380 3183.9675 4807.9341 7724.2520 13905.2314 | lr 2.4e-04 | norm 5193.5757 | dt 9.806 +type train | step 3310 | loss 101.7125 212.6812 323.8898 532.3627 759.5766 1112.2239 1539.9180 2193.0381 3088.6245 4639.1982 7604.0498 13793.5762 | lr 2.4e-04 | norm 5496.5435 | dt 9.799 +type train | step 3311 | loss 122.5103 254.3735 379.5155 610.9277 863.4655 1265.7168 1718.5778 2433.4761 3329.0530 4899.7998 7833.9033 13975.3184 | lr 2.4e-04 | norm 7739.2559 | dt 9.757 +type train | step 3312 | loss 104.4749 217.9082 331.6334 545.3286 779.0754 1169.0391 1613.4238 2343.1631 3264.4775 4873.6729 7849.9404 14050.9775 | lr 2.4e-04 | norm 4782.6958 | dt 9.782 +type train | step 3313 | loss 104.8738 222.2714 337.6808 547.5557 779.9550 1135.9081 1563.2290 2220.6721 3124.3254 4697.5869 7605.0537 13719.6211 | lr 2.4e-04 | norm 4197.4253 | dt 9.822 +type train | step 3314 | loss 104.1691 224.2905 344.4041 564.6517 817.1279 1203.1992 1667.3149 2388.0647 3351.2244 5036.7139 8196.3545 14912.2783 | lr 2.4e-04 | norm 6763.2363 | dt 9.780 +type train | step 3315 | loss 107.6819 223.1779 342.4676 560.0221 801.0558 1152.1553 1595.4061 2261.0046 3194.1985 4804.1934 7768.0405 13996.0156 | lr 2.4e-04 | norm 6868.4824 | dt 9.787 +type train | step 3316 | loss 103.0304 214.3139 327.9058 533.0648 766.3364 1115.0691 1544.8480 2198.7661 3094.7109 4659.0786 7631.7446 13807.6377 | lr 2.4e-04 | norm 4982.2354 | dt 9.794 +type train | step 3317 | loss 101.5534 209.2860 318.0256 523.8942 753.9747 1112.2546 1549.0626 2228.8472 3142.8208 4754.9438 7708.8945 13895.6152 | lr 2.4e-04 | norm 4225.0317 | dt 9.784 +type train | step 3318 | loss 102.5161 212.3160 325.9831 532.3586 765.5444 1120.5000 1549.3700 2212.5906 3113.8679 4705.7012 7641.2563 13760.7383 | lr 2.4e-04 | norm 4178.1890 | dt 9.788 +type train | step 3319 | loss 113.5217 237.4930 358.0759 577.4691 817.7115 1200.6074 1652.2905 2348.6855 3230.8193 4863.1333 7904.0303 14318.6631 | lr 2.4e-04 | norm 5539.5991 | dt 9.771 +type train | step 3320 | loss 108.8681 230.2016 348.3048 566.5468 803.1296 1165.5106 1597.5243 2257.0994 3167.7278 4724.2744 7639.3325 13705.1650 | lr 2.4e-04 | norm 4603.4185 | dt 9.795 +type train | step 3321 | loss 96.9968 203.5625 317.8878 529.2191 764.6281 1120.7471 1558.3823 2244.9741 3199.9924 4840.9399 7881.9736 14237.7158 | lr 2.4e-04 | norm 4726.1650 | dt 9.788 +type train | step 3322 | loss 103.6985 216.4346 332.5815 545.7832 787.6210 1164.6183 1614.0046 2319.4690 3274.3694 4921.0723 8020.0874 14530.8770 | lr 2.4e-04 | norm 4380.7695 | dt 9.789 +type train | step 3323 | loss 107.9710 224.1759 341.5283 551.4753 785.7402 1141.1332 1561.2134 2209.9607 3088.1887 4650.5991 7586.7485 13796.4854 | lr 2.3e-04 | norm 5335.0967 | dt 9.788 +type train | step 3324 | loss 108.4607 227.8340 347.1680 561.8924 789.5701 1149.8279 1577.5431 2233.4507 3100.6548 4626.6094 7459.6250 13468.8779 | lr 2.3e-04 | norm 4681.8765 | dt 9.797 +type train | step 3325 | loss 104.0878 216.2900 333.1241 545.7657 783.9848 1147.8281 1592.4133 2274.8413 3214.9089 4870.7324 7936.2134 14420.7822 | lr 2.3e-04 | norm 4648.6182 | dt 9.829 +type train | step 3326 | loss 108.4259 225.6530 345.9752 570.1165 805.0917 1182.8367 1620.9701 2289.8857 3160.9561 4730.0610 7645.5938 13815.3262 | lr 2.3e-04 | norm 4375.6304 | dt 9.807 +type train | step 3327 | loss 115.2994 243.3376 366.7747 591.1375 831.9887 1211.6157 1653.3948 2324.0312 3178.0461 4738.7061 7701.2920 13965.8945 | lr 2.3e-04 | norm 4686.1812 | dt 9.780 +type train | step 3328 | loss 99.4457 208.6420 321.9243 531.1585 769.1258 1139.5483 1576.8417 2258.1013 3182.0684 4812.8818 7793.9204 13991.1709 | lr 2.3e-04 | norm 4364.2251 | dt 9.796 +type train | step 3329 | loss 107.0643 223.8236 337.7662 551.8053 787.3674 1154.2189 1591.3281 2254.9561 3167.2112 4741.6855 7714.1567 13962.1982 | lr 2.3e-04 | norm 4330.1978 | dt 9.789 +type train | step 3330 | loss 109.9875 229.0960 348.2361 565.3299 800.4019 1170.5807 1602.6707 2279.5266 3173.4612 4726.7700 7668.3994 13850.5029 | lr 2.3e-04 | norm 4475.2373 | dt 9.788 +type train | step 3331 | loss 107.8480 228.7411 346.8019 565.9482 798.3834 1168.8254 1612.5201 2288.3372 3191.1697 4781.1504 7739.8784 13925.1035 | lr 2.3e-04 | norm 4266.9561 | dt 9.787 +type train | step 3332 | loss 102.5818 213.7192 326.9635 533.4028 761.6242 1114.3761 1545.7943 2209.8064 3111.4380 4656.8052 7560.4502 13531.8057 | lr 2.3e-04 | norm 4017.3215 | dt 9.785 +type train | step 3333 | loss 100.8927 209.3620 322.3973 533.0349 762.4417 1119.3752 1539.7660 2176.0867 3052.3655 4586.4775 7486.7212 13547.8799 | lr 2.3e-04 | norm 4039.9265 | dt 9.783 +type train | step 3334 | loss 99.4686 209.3436 320.9449 535.2172 766.4730 1142.3131 1588.9587 2292.9180 3228.7178 4840.7603 7877.6885 14307.7598 | lr 2.3e-04 | norm 5662.1514 | dt 9.788 +type train | step 3335 | loss 103.9124 216.4433 328.2314 537.7262 766.8951 1123.0834 1548.1595 2202.5398 3099.5254 4646.4209 7544.2637 13562.7754 | lr 2.3e-04 | norm 3525.3320 | dt 9.792 +type train | step 3336 | loss 102.7958 214.0514 326.0806 535.3757 764.6778 1131.2969 1567.9823 2241.8994 3130.6704 4693.4268 7590.0264 13646.0381 | lr 2.3e-04 | norm 4044.5000 | dt 9.784 +type train | step 3337 | loss 103.3858 219.3268 330.4339 547.0140 784.1314 1170.1392 1633.6638 2370.0317 3279.4124 4965.5220 8182.8267 15103.3281 | lr 2.3e-04 | norm 8340.1826 | dt 9.789 +type train | step 3338 | loss 106.4925 221.3221 335.9241 544.1500 776.3610 1129.5388 1554.0427 2209.3188 3096.7751 4646.9263 7591.9775 13765.6777 | lr 2.3e-04 | norm 3728.3794 | dt 9.790 +type train | step 3339 | loss 100.5231 209.5314 325.6730 536.4312 769.5414 1135.0835 1569.1235 2239.5930 3150.4006 4743.4795 7702.9307 13879.2051 | lr 2.3e-04 | norm 3820.2649 | dt 9.794 +type train | step 3340 | loss 105.0571 217.5602 333.8495 543.1326 777.1804 1135.5469 1570.7729 2229.7715 3142.0178 4684.5522 7532.4355 13496.7344 | lr 2.3e-04 | norm 4008.5854 | dt 9.792 +type train | step 3341 | loss 110.4224 231.8088 349.7112 564.0978 804.1918 1171.0652 1619.7710 2315.6592 3233.3044 4869.5962 7935.2744 14276.7939 | lr 2.3e-04 | norm 5240.9092 | dt 9.786 +type train | step 3342 | loss 96.6785 201.9422 313.4040 515.2303 751.2368 1101.7349 1531.8535 2202.2131 3122.0815 4709.7529 7670.3706 13762.3994 | lr 2.3e-04 | norm 3480.1748 | dt 9.797 +type train | step 3343 | loss 96.6599 197.6147 307.5269 508.1522 734.1249 1079.7612 1499.8267 2137.4536 3015.6421 4549.6382 7365.1963 13133.8955 | lr 2.3e-04 | norm 3610.0166 | dt 9.794 +type train | step 3344 | loss 99.6034 206.8848 319.7056 522.8458 757.0638 1107.8228 1540.5203 2211.7996 3129.9377 4704.9688 7634.4141 13686.3867 | lr 2.3e-04 | norm 3878.7917 | dt 9.800 +type train | step 3345 | loss 101.2853 210.0073 323.3284 527.7146 757.3679 1104.5217 1523.4832 2171.4722 3060.4268 4618.5605 7456.3945 13332.1924 | lr 2.3e-04 | norm 3669.3484 | dt 9.792 +type train | step 3346 | loss 99.0944 204.5390 315.5635 516.4200 746.6255 1090.8385 1509.6814 2158.6494 3045.7866 4598.2559 7482.7734 13434.3467 | lr 2.3e-04 | norm 3667.4390 | dt 9.803 +type train | step 3347 | loss 108.3142 227.9397 346.4055 564.8284 807.3059 1177.1053 1621.1753 2304.5889 3226.8459 4862.3535 7855.7559 14089.1680 | lr 2.3e-04 | norm 4018.2139 | dt 9.779 +type train | step 3348 | loss 96.4203 199.1600 310.2623 522.6534 756.6002 1128.7286 1581.2675 2288.1677 3222.3545 4891.9917 7983.1533 14462.7422 | lr 2.3e-04 | norm 4319.9224 | dt 9.774 +type train | step 3349 | loss 100.8493 208.3096 319.3989 517.1963 747.1456 1090.2540 1502.7249 2142.9226 3028.1677 4538.4355 7343.4541 13175.7559 | lr 2.3e-04 | norm 4050.6921 | dt 9.793 +type train | step 3350 | loss 101.9164 209.5803 318.9611 522.0569 748.4933 1104.5869 1532.6688 2187.5095 3059.8435 4587.1309 7439.9819 13350.9580 | lr 2.3e-04 | norm 4167.6421 | dt 9.789 +type train | step 3351 | loss 118.3089 247.6210 371.2743 589.7271 825.7891 1206.9246 1660.6647 2339.2559 3228.8740 4784.0405 7650.8540 13686.4043 | lr 2.3e-04 | norm 4774.1030 | dt 9.780 +type train | step 3352 | loss 100.8890 212.4724 324.1460 533.7968 766.7141 1124.0972 1553.3044 2222.6626 3116.9009 4713.6074 7703.5684 13889.9463 | lr 2.3e-04 | norm 4028.2383 | dt 9.781 +type train | step 3353 | loss 101.1656 210.3518 323.2928 531.2283 770.0742 1129.9139 1567.2776 2241.2886 3154.3525 4784.7183 7771.7808 13978.6055 | lr 2.3e-04 | norm 3790.6265 | dt 9.798 +type train | step 3354 | loss 99.5030 206.7062 317.4584 520.7253 749.6506 1093.2961 1518.0017 2164.9592 3055.7991 4620.9375 7512.5078 13527.7705 | lr 2.3e-04 | norm 3738.6467 | dt 9.780 +type train | step 3355 | loss 104.3770 218.4041 334.5712 543.5643 777.2133 1136.0452 1572.4454 2234.4639 3130.4678 4678.6636 7520.7637 13471.9385 | lr 2.3e-04 | norm 3632.6040 | dt 9.785 +type train | step 3356 | loss 99.0625 206.3067 313.8334 515.4740 741.9363 1088.0084 1520.1337 2170.2917 3063.4592 4615.1348 7517.7939 13605.7900 | lr 2.3e-04 | norm 4278.4082 | dt 9.800 +type train | step 3357 | loss 97.3535 201.4081 308.7808 513.3798 738.8997 1088.5742 1508.2047 2164.2896 3057.2598 4618.7012 7512.3145 13486.4346 | lr 2.3e-04 | norm 3530.2107 | dt 10.119 +type train | step 3358 | loss 94.5778 197.1837 305.3377 505.6620 741.0712 1098.0277 1539.2043 2215.8274 3161.3494 4839.0645 7893.2627 14245.7686 | lr 2.3e-04 | norm 8601.7549 | dt 9.785 +type train | step 3359 | loss 97.1239 202.1159 311.9635 511.4004 749.4163 1107.9902 1557.8999 2246.3787 3212.2832 4870.3027 7881.1797 14091.9932 | lr 2.3e-04 | norm 7527.2759 | dt 9.782 +type train | step 3360 | loss 107.4130 233.7216 355.3943 584.5642 840.1036 1218.9697 1692.3696 2423.8696 3381.8931 5155.0405 8426.6602 15310.2559 | lr 2.3e-04 | norm 8922.1924 | dt 9.779 +type train | step 3361 | loss 104.4043 219.9091 335.2088 545.5007 784.7620 1146.8300 1590.2731 2262.7048 3174.6880 4766.0327 7722.0454 13897.5488 | lr 2.3e-04 | norm 4509.1094 | dt 9.794 +type train | step 3362 | loss 99.6273 204.3159 318.1699 521.8959 749.7462 1096.2319 1523.0067 2182.9915 3088.4668 4666.2476 7575.2822 13656.0596 | lr 2.3e-04 | norm 5708.6982 | dt 9.789 +type train | step 3363 | loss 109.0495 230.0559 349.3322 561.6648 794.7372 1160.1831 1594.7692 2263.1038 3141.8630 4694.4951 7606.7329 13736.5225 | lr 2.3e-04 | norm 4864.8027 | dt 9.774 +type train | step 3364 | loss 101.4284 211.8633 320.8870 521.1719 754.1338 1112.5835 1546.7046 2220.4045 3133.9111 4714.8027 7603.1699 13607.9414 | lr 2.3e-04 | norm 4166.2300 | dt 9.792 +type train | step 3365 | loss 97.2745 200.7528 314.9058 518.5969 750.6282 1103.0225 1539.4474 2204.6462 3118.2017 4704.9082 7624.3691 13722.0342 | lr 2.3e-04 | norm 4760.4790 | dt 9.785 +type train | step 3366 | loss 95.6485 196.8315 306.2373 503.6638 732.8741 1073.1833 1508.7155 2163.5935 3076.4001 4671.8438 7574.0361 13547.5908 | lr 2.3e-04 | norm 4095.1704 | dt 9.798 +type train | step 3367 | loss 94.6505 199.1514 310.3495 512.7352 746.4108 1095.6783 1529.3267 2207.9109 3121.0676 4718.6514 7686.0049 13953.8145 | lr 2.3e-04 | norm 4280.5195 | dt 9.788 +type train | step 3368 | loss 97.8242 202.1575 313.9170 520.4276 749.6526 1104.9116 1539.5258 2200.2622 3114.6401 4715.9360 7650.6777 13791.2891 | lr 2.3e-04 | norm 3761.2576 | dt 9.800 +type train | step 3369 | loss 99.4901 205.3876 316.1455 521.4361 752.3640 1101.5901 1531.3361 2195.6646 3116.5232 4725.2998 7700.3770 13816.0273 | lr 2.3e-04 | norm 3769.8953 | dt 9.796 +type train | step 3370 | loss 101.0672 210.5850 321.6440 523.2813 750.3253 1099.1787 1526.1665 2181.8091 3084.7693 4630.0425 7541.9824 13564.7812 | lr 2.3e-04 | norm 4278.8569 | dt 9.798 +type train | step 3371 | loss 108.7617 220.6510 339.1680 551.5394 791.4703 1153.5857 1599.8248 2280.2434 3219.7168 4889.8501 7965.7534 14424.4746 | lr 2.3e-04 | norm 6390.4966 | dt 9.790 +type train | step 3372 | loss 104.2940 216.4090 330.2568 539.4901 774.6151 1128.1144 1558.7238 2213.3225 3106.7522 4656.2261 7543.3311 13543.2881 | lr 2.3e-04 | norm 3653.0630 | dt 9.801 +type train | step 3373 | loss 103.6661 217.1985 338.4752 553.1776 794.8463 1160.5457 1606.9968 2274.2908 3180.9795 4782.9790 7728.6860 13946.9502 | lr 2.3e-04 | norm 6737.9185 | dt 9.782 +type train | step 3374 | loss 106.1237 223.7218 347.1840 565.6949 818.3039 1188.1888 1638.8828 2319.1189 3234.7837 4837.4751 7746.4497 13807.9844 | lr 2.3e-04 | norm 3894.1182 | dt 9.787 +type train | step 3375 | loss 99.0502 205.9109 314.2573 518.5670 744.9592 1094.1997 1516.4814 2178.3057 3064.2522 4612.2007 7470.5503 13354.1650 | lr 2.3e-04 | norm 3939.5786 | dt 9.791 +type train | step 3376 | loss 119.6386 251.6837 381.7948 603.2385 849.7296 1220.7159 1673.0741 2353.7786 3286.6377 4952.4502 8008.1948 14487.4043 | lr 2.3e-04 | norm 6769.8257 | dt 9.784 +type train | step 3377 | loss 108.1068 226.0483 350.1224 576.2866 820.1914 1214.9368 1681.3246 2414.4114 3315.7075 4953.6479 8031.0737 14501.6406 | lr 2.3e-04 | norm 5124.9761 | dt 9.777 +type train | step 3378 | loss 99.4372 206.3851 318.8206 523.9344 760.2313 1129.0935 1577.3679 2263.8408 3172.3809 4779.8730 7799.1660 14056.8262 | lr 2.3e-04 | norm 4526.1255 | dt 9.777 +type train | step 3379 | loss 97.5644 202.3854 316.2531 522.3594 763.1359 1121.8767 1573.0913 2254.0776 3190.4326 4823.8359 7864.7417 14132.1758 | lr 2.3e-04 | norm 4806.2705 | dt 9.788 +type train | step 3380 | loss 105.0005 218.5064 333.1353 548.7337 780.9482 1143.4270 1588.8910 2270.9546 3199.8108 4822.4209 7810.8379 14007.6299 | lr 2.3e-04 | norm 3918.2219 | dt 9.794 +type train | step 3381 | loss 99.0866 207.2248 317.0988 525.7894 754.6333 1120.2064 1562.0002 2248.8860 3153.8684 4764.0347 7746.4189 14018.9385 | lr 2.3e-04 | norm 3872.9639 | dt 9.790 +type train | step 3382 | loss 95.8038 198.4265 306.5584 509.9423 735.5023 1093.3359 1530.5129 2222.9722 3148.3027 4773.1660 7797.2061 14107.7070 | lr 2.3e-04 | norm 4048.6809 | dt 9.785 +type train | step 3383 | loss 115.8655 245.1946 394.3459 652.6228 930.4395 1400.5916 1964.1611 2860.4651 3877.9312 5904.0044 9582.8877 17631.0859 | lr 2.3e-04 | norm 10727.0693 | dt 9.757 +type train | step 3384 | loss 101.2586 211.8057 328.0738 538.1584 772.3227 1115.1377 1543.1866 2186.6252 3078.1921 4633.5273 7498.2271 13600.9912 | lr 2.3e-04 | norm 4657.2627 | dt 9.791 +type train | step 3385 | loss 96.9436 202.3769 315.0831 521.9228 751.9183 1105.8350 1549.3162 2223.1326 3152.6208 4747.3555 7686.7339 13711.7305 | lr 2.3e-04 | norm 3697.1475 | dt 9.792 +type train | step 3386 | loss 103.7985 217.1680 331.1683 535.5720 768.6868 1123.6714 1557.6218 2235.7327 3138.5911 4751.8569 7707.5278 14015.0947 | lr 2.3e-04 | norm 4820.0176 | dt 9.781 +type train | step 3387 | loss 105.7564 218.8942 333.8640 547.1636 780.8430 1132.3000 1563.3300 2228.6870 3122.7095 4684.5010 7623.4199 13796.8486 | lr 2.3e-04 | norm 4387.8237 | dt 9.787 +type train | step 3388 | loss 101.3591 206.6121 315.4783 517.9280 746.8403 1100.2188 1533.8374 2200.5483 3109.6379 4680.0703 7603.3696 13665.7393 | lr 2.3e-04 | norm 4262.4189 | dt 9.784 +type train | step 3389 | loss 128.0907 266.3668 399.9974 628.6830 892.1201 1271.5952 1731.6061 2452.4824 3414.3572 5103.6816 8268.2852 15154.0039 | lr 2.3e-04 | norm 7503.1812 | dt 9.776 +type train | step 3390 | loss 103.1711 216.3076 328.2906 529.8871 759.5615 1107.2234 1540.8503 2199.4819 3099.4441 4678.3115 7616.9380 13719.7236 | lr 2.3e-04 | norm 4176.4424 | dt 9.793 +type train | step 3391 | loss 104.3677 220.3564 336.6060 538.9217 777.0090 1140.0110 1587.8829 2275.4109 3189.6831 4817.5752 7820.9746 14079.0527 | lr 2.3e-04 | norm 3957.9690 | dt 9.785 +type train | step 3392 | loss 103.6698 213.2473 321.9704 526.3188 754.0975 1112.4427 1549.1899 2227.3137 3119.9478 4704.0664 7650.6216 13758.8896 | lr 2.3e-04 | norm 4047.0637 | dt 9.777 +type train | step 3393 | loss 93.5312 193.8433 301.6817 493.9317 719.5223 1054.2688 1472.4943 2113.6287 3011.0674 4578.8496 7481.5400 13434.8652 | lr 2.3e-04 | norm 3595.0632 | dt 9.791 +type train | step 3394 | loss 102.5111 214.7029 327.4182 530.6003 766.4056 1117.6743 1552.2742 2206.3257 3092.2517 4619.2158 7453.4868 13279.1191 | lr 2.3e-04 | norm 3501.2014 | dt 9.808 +type train | step 3395 | loss 103.8435 213.9469 323.5655 534.7849 765.0052 1133.3827 1579.8671 2255.3489 3139.6782 4689.5361 7670.7998 14007.6914 | lr 2.3e-04 | norm 5628.1646 | dt 9.775 +type train | step 3396 | loss 119.5113 250.7640 372.7212 596.0729 842.4152 1228.2037 1680.6259 2370.9326 3267.5532 4842.1436 7754.0981 13847.5859 | lr 2.2e-04 | norm 3767.5659 | dt 9.772 +type train | step 3397 | loss 99.7933 204.8186 313.7491 516.5791 742.8322 1091.7430 1527.4746 2182.1865 3058.8618 4585.0791 7423.0459 13272.0879 | lr 2.2e-04 | norm 4237.6958 | dt 9.790 +type train | step 3398 | loss 108.0697 228.3409 344.8692 555.5638 799.6119 1173.0023 1614.0486 2310.8418 3243.1382 4839.3784 7808.0229 14014.7217 | lr 2.2e-04 | norm 3819.0867 | dt 9.781 +type train | step 3399 | loss 101.2271 213.6958 325.3769 529.9373 766.0910 1115.6726 1544.5730 2204.7410 3110.8911 4673.9746 7574.0537 13592.5020 | lr 2.2e-04 | norm 4308.6182 | dt 9.795 +type train | step 3400 | loss 98.9808 205.8289 312.3658 512.6624 741.3210 1085.4067 1513.3579 2166.5571 3077.4883 4615.0015 7485.5376 13379.0820 | lr 2.2e-04 | norm 6098.9912 | dt 9.789 +type train | step 3401 | loss 99.6750 205.6606 318.2240 525.1974 758.4241 1137.3306 1584.5562 2287.4634 3225.5544 4898.8799 8026.2295 14533.9102 | lr 2.2e-04 | norm 4587.0269 | dt 9.778 +type train | step 3402 | loss 106.8696 223.2145 339.3617 554.3083 794.2036 1172.1052 1612.6938 2281.3494 3172.5684 4766.7993 7751.7334 14075.3477 | lr 2.2e-04 | norm 4884.6030 | dt 9.781 +type train | step 3403 | loss 98.0303 203.3913 311.7040 513.3188 743.0039 1092.8896 1527.7405 2202.7852 3120.4077 4695.3076 7638.4087 13627.7607 | lr 2.2e-04 | norm 4130.6772 | dt 9.781 +type train | step 3404 | loss 100.4110 209.6139 321.4181 529.7028 767.3409 1118.7766 1551.6716 2211.2703 3130.9285 4714.0908 7663.6084 13752.5908 | lr 2.2e-04 | norm 4298.3311 | dt 9.788 +type train | step 3405 | loss 108.9958 226.6714 348.6293 565.7803 810.3513 1175.9501 1609.3258 2278.6179 3141.0007 4675.0332 7500.6880 13499.6787 | lr 2.2e-04 | norm 4753.9590 | dt 9.772 +type train | step 3406 | loss 105.2843 221.2141 338.4066 548.0831 787.1522 1148.8594 1584.6790 2258.7725 3153.4949 4735.0068 7691.8071 13818.1104 | lr 2.2e-04 | norm 3566.6060 | dt 9.789 +type train | step 3407 | loss 113.1852 238.8911 364.4414 592.2736 851.3093 1226.3004 1698.1017 2401.8572 3342.5840 5031.7705 8151.5249 14526.3604 | lr 2.2e-04 | norm 7993.8740 | dt 9.798 +type train | step 3408 | loss 115.4906 244.7819 380.1205 624.7209 904.7281 1299.0614 1801.0887 2555.4521 3520.7393 5297.9199 8632.2666 15305.9072 | lr 2.2e-04 | norm 11556.6406 | dt 9.787 +type train | step 3409 | loss 107.4153 228.9900 347.0261 560.6674 797.5270 1198.2203 1665.0701 2389.2698 3291.1897 4900.8975 7869.4756 14148.6816 | lr 2.2e-04 | norm 4584.7529 | dt 9.780 +type train | step 3410 | loss 105.3517 219.4167 333.2892 537.5467 775.0125 1136.6345 1576.3705 2251.8875 3155.7961 4755.9072 7649.9893 13692.5098 | lr 2.2e-04 | norm 4144.1538 | dt 9.792 +type train | step 3411 | loss 103.2142 215.5258 326.6677 531.8918 764.1872 1122.7889 1550.4752 2208.6184 3102.5557 4680.5845 7608.5859 13634.8672 | lr 2.2e-04 | norm 4598.9834 | dt 9.781 +type train | step 3412 | loss 113.2855 238.0452 354.3517 567.4190 813.1689 1195.5568 1655.5862 2352.4214 3254.6870 4844.6372 7822.9087 14061.8535 | lr 2.2e-04 | norm 4423.5884 | dt 9.792 +type train | step 3413 | loss 103.9619 217.5596 329.4645 531.1930 763.3206 1111.5356 1541.8163 2197.1113 3090.2854 4672.4990 7623.6387 13857.6406 | lr 2.2e-04 | norm 4219.9111 | dt 9.803 +type train | step 3414 | loss 100.5615 211.7220 325.3046 530.2004 766.8669 1122.7982 1566.5652 2234.7476 3162.9175 4775.2812 7796.8408 13967.6328 | lr 2.2e-04 | norm 4047.6936 | dt 9.794 +type train | step 3415 | loss 98.5684 206.7773 322.0099 532.9332 766.8763 1124.9178 1569.1873 2253.7915 3199.6489 4817.9790 7857.4897 14232.0264 | lr 2.2e-04 | norm 5169.8203 | dt 9.775 +type train | step 3416 | loss 106.1209 221.0818 334.6111 543.7491 780.2130 1136.8416 1577.2153 2261.1826 3163.3235 4783.5039 7748.5195 13973.7070 | lr 2.2e-04 | norm 4321.9194 | dt 9.792 +type train | step 3417 | loss 106.5331 221.6090 336.3691 545.6221 785.2968 1139.2047 1573.9014 2238.4702 3123.4893 4696.1768 7657.5054 13915.8584 | lr 2.2e-04 | norm 4518.9282 | dt 9.788 +type train | step 3418 | loss 99.4345 207.7476 318.3319 519.8748 751.7083 1095.8219 1524.2490 2172.7522 3068.2986 4637.3184 7537.9639 13546.1338 | lr 2.2e-04 | norm 3698.8208 | dt 9.775 +type train | step 3419 | loss 111.3453 234.6505 353.9329 569.5239 810.3448 1177.9119 1619.0806 2286.5476 3158.7502 4744.9907 7664.7676 13870.1475 | lr 2.2e-04 | norm 4561.9829 | dt 9.792 +type train | step 3420 | loss 105.3048 223.0943 340.6830 552.8043 792.5008 1161.7177 1601.3623 2275.8132 3159.6436 4717.3350 7630.7002 13659.0088 | lr 2.2e-04 | norm 4227.8789 | dt 9.795 +type train | step 3421 | loss 109.2218 230.4160 345.4885 554.1833 796.8844 1163.7117 1606.9459 2289.7217 3214.7854 4824.8530 7789.0068 13965.6592 | lr 2.2e-04 | norm 3625.4756 | dt 9.802 +type train | step 3422 | loss 104.3923 215.4359 330.9403 537.8433 770.0734 1121.3778 1546.0090 2190.9304 3064.5300 4592.9092 7403.6846 13254.4756 | lr 2.2e-04 | norm 4134.3105 | dt 9.796 +type train | step 3423 | loss 99.2214 206.6153 317.4392 520.3128 751.7043 1109.3525 1545.1593 2215.4092 3122.7463 4698.6318 7620.3232 13723.9922 | lr 2.2e-04 | norm 3972.7522 | dt 9.790 +type train | step 3424 | loss 117.6904 246.5716 374.5461 596.0631 848.6733 1218.3604 1670.3688 2357.4617 3292.4543 4959.0293 8024.9424 14472.2432 | lr 2.2e-04 | norm 6122.0347 | dt 9.792 +type train | step 3425 | loss 98.9948 203.5106 314.1668 515.4688 743.0638 1090.9701 1523.8201 2180.2627 3096.3389 4667.6851 7540.7529 13448.0117 | lr 2.2e-04 | norm 3547.9194 | dt 9.780 +type train | step 3426 | loss 102.5307 214.6561 331.3577 539.1455 781.9779 1151.3113 1609.2770 2321.4224 3258.7480 4903.9521 8000.0996 14451.1836 | lr 2.2e-04 | norm 5870.2197 | dt 9.786 +type train | step 3427 | loss 103.8057 212.8795 324.3689 524.8824 750.1520 1099.1646 1525.9535 2182.6074 3075.1323 4617.5381 7542.0942 13660.7588 | lr 2.2e-04 | norm 3929.6348 | dt 9.783 +type train | step 3428 | loss 110.0415 228.3729 345.0920 553.8915 792.0344 1157.2867 1606.3734 2269.5806 3186.2581 4747.8281 7646.5376 13722.9092 | lr 2.2e-04 | norm 4344.2329 | dt 9.795 +type train | step 3429 | loss 102.5875 213.3786 323.6667 527.9841 756.8824 1106.1260 1529.4199 2178.4604 3061.1274 4601.2529 7480.4453 13383.8223 | lr 2.2e-04 | norm 3511.0576 | dt 9.802 +type train | step 3430 | loss 97.6359 201.2003 309.2289 504.3473 731.9447 1070.4937 1493.2311 2137.0464 3031.7451 4595.4399 7519.4824 13460.2363 | lr 2.2e-04 | norm 3672.7319 | dt 9.791 +type train | step 3431 | loss 103.3913 216.6671 332.1316 542.5688 780.7408 1149.8438 1590.5193 2269.2144 3194.1921 4833.3740 7878.3062 14190.1396 | lr 2.2e-04 | norm 3946.0559 | dt 9.792 +type train | step 3432 | loss 109.8831 230.2847 350.2921 556.2766 793.6863 1151.7958 1574.6035 2216.3320 3040.6370 4557.4375 7388.7275 13372.1270 | lr 2.2e-04 | norm 5078.1885 | dt 9.761 +type train | step 3433 | loss 107.8524 225.9935 343.0959 552.2512 794.7271 1167.2010 1621.5299 2322.0886 3229.9065 4831.9507 7775.8779 13995.1299 | lr 2.2e-04 | norm 4571.1436 | dt 9.783 +type train | step 3434 | loss 103.9150 216.8721 331.7039 536.5080 771.8752 1118.0315 1547.0081 2192.7834 3066.9976 4612.0020 7515.2705 13553.1504 | lr 2.2e-04 | norm 3926.4028 | dt 9.781 +type train | step 3435 | loss 99.9470 209.6507 321.5206 526.2889 761.5826 1113.1842 1555.6097 2236.5627 3154.4175 4766.7153 7719.4087 13908.9141 | lr 2.2e-04 | norm 3713.8677 | dt 9.794 +type train | step 3436 | loss 113.8743 236.0163 359.9385 574.5856 816.3467 1180.5299 1625.6404 2288.4316 3195.4067 4811.1562 7836.2905 14190.7598 | lr 2.2e-04 | norm 5181.8296 | dt 9.782 +type train | step 3437 | loss 104.6576 215.7834 332.5956 539.3655 774.2993 1131.1000 1571.0153 2246.9060 3166.6228 4773.5176 7779.2173 13959.0791 | lr 2.2e-04 | norm 3656.9651 | dt 9.788 +type train | step 3438 | loss 101.4591 214.4190 330.6343 539.2869 772.2791 1134.9319 1575.0862 2251.6233 3147.7456 4731.2324 7661.1729 13785.6816 | lr 2.2e-04 | norm 4280.9580 | dt 9.787 +type train | step 3439 | loss 104.5297 218.1812 338.5394 556.9783 800.4128 1163.8389 1610.9238 2283.2461 3196.9910 4782.0850 7703.6758 13822.3242 | lr 2.2e-04 | norm 6340.8657 | dt 9.793 +type train | step 3440 | loss 98.8290 202.5412 311.9919 511.0853 741.4706 1105.0967 1550.7676 2247.0007 3171.3647 4830.2275 7925.5479 14313.8545 | lr 2.2e-04 | norm 4859.2314 | dt 9.776 +type train | step 3441 | loss 108.3289 227.1060 337.8403 541.1579 776.3503 1140.8151 1586.0159 2272.6340 3169.7324 4743.1758 7681.5747 13805.2812 | lr 2.2e-04 | norm 4733.6631 | dt 9.793 +type train | step 3442 | loss 103.9818 218.3743 332.1920 535.9588 775.6290 1135.5846 1576.6180 2246.0493 3132.4268 4700.1729 7646.4526 13749.1152 | lr 2.2e-04 | norm 4177.3623 | dt 9.800 +type train | step 3443 | loss 103.7341 214.4715 329.9520 535.8044 767.9376 1125.3164 1563.0156 2227.2339 3127.2026 4686.6851 7633.4585 13822.3018 | lr 2.2e-04 | norm 4230.9595 | dt 9.784 +type train | step 3444 | loss 106.2639 220.5329 334.5616 542.5579 777.0401 1159.9197 1620.7869 2326.2783 3230.3420 4860.8462 7895.3188 14199.5117 | lr 2.2e-04 | norm 4489.8960 | dt 9.785 +type train | step 3445 | loss 99.7038 205.1682 315.5659 515.0156 745.1578 1096.5269 1528.3147 2190.1934 3086.0344 4636.0596 7472.5708 13434.8369 | lr 2.2e-04 | norm 4516.0845 | dt 9.779 +type train | step 3446 | loss 109.9023 231.3166 348.5526 555.6119 793.8969 1153.3011 1597.7336 2259.7156 3151.8152 4698.5903 7580.2451 13660.6113 | lr 2.2e-04 | norm 4231.6265 | dt 9.781 +type train | step 3447 | loss 109.8042 228.4711 348.2523 555.9434 795.6276 1157.8309 1600.8682 2267.1299 3164.6904 4734.0659 7757.6309 14138.3809 | lr 2.2e-04 | norm 4649.7290 | dt 9.790 +type train | step 3448 | loss 95.8288 200.0890 310.8908 510.4726 744.5486 1094.5216 1534.7662 2203.0540 3134.2522 4744.1182 7696.4624 13797.0830 | lr 2.2e-04 | norm 3552.2734 | dt 9.807 +type train | step 3449 | loss 107.9367 227.2799 342.8505 550.5814 785.8162 1156.5706 1604.6715 2292.6846 3209.4888 4826.5493 7854.1299 14146.5195 | lr 2.2e-04 | norm 3698.7007 | dt 9.821 +type train | step 3450 | loss 119.0378 253.9283 379.0496 611.7842 869.6568 1280.6301 1746.4799 2465.3198 3394.8887 5026.8096 8119.3071 14639.5537 | lr 2.2e-04 | norm 5015.1289 | dt 9.806 +type train | step 3451 | loss 106.1534 220.0875 336.8538 549.4678 790.7083 1149.5444 1588.1904 2246.7524 3132.4978 4683.3662 7586.7651 13709.4746 | lr 2.2e-04 | norm 4021.5828 | dt 9.804 +type train | step 3452 | loss 103.1743 215.4755 330.0219 531.9644 764.2427 1113.3717 1542.3802 2208.4150 3099.4629 4685.6025 7587.9102 13653.7588 | lr 2.2e-04 | norm 4286.0356 | dt 9.795 +type train | step 3453 | loss 132.1431 282.7610 406.9102 629.0948 877.6935 1286.7739 1767.5820 2504.2544 3393.8977 5059.9507 8175.4668 14703.1172 | lr 2.2e-04 | norm 6206.0039 | dt 9.770 +type train | step 3454 | loss 97.3325 203.8413 314.3525 512.6184 748.9082 1094.5229 1521.1816 2161.4739 3066.8887 4593.5381 7444.3271 13360.8721 | lr 2.2e-04 | norm 3856.3140 | dt 9.790 +type train | step 3455 | loss 95.9970 196.4424 304.9236 499.7880 730.3035 1065.2983 1487.1263 2125.7249 3018.6580 4539.9556 7347.1865 13114.6719 | lr 2.2e-04 | norm 3402.2981 | dt 9.800 +type train | step 3456 | loss 100.8555 207.8232 319.1375 516.7555 746.9841 1091.7972 1520.2570 2168.1321 3053.7788 4587.8818 7452.1743 13323.5850 | lr 2.2e-04 | norm 3608.5210 | dt 9.790 +type train | step 3457 | loss 102.5733 211.9152 323.0257 528.2712 760.9321 1117.8772 1551.3585 2213.8079 3103.8640 4653.6797 7621.7612 13783.6299 | lr 2.2e-04 | norm 4018.2571 | dt 9.800 +type train | step 3458 | loss 100.3373 209.7329 323.8289 527.3125 767.3925 1123.3149 1573.2058 2249.3706 3188.9133 4802.4639 7808.3154 14081.3340 | lr 2.2e-04 | norm 4099.9321 | dt 9.778 +type train | step 3459 | loss 108.1839 227.6177 343.1614 549.7664 795.7904 1158.8657 1605.4353 2282.7930 3182.8706 4781.9019 7744.4995 13820.4141 | lr 2.2e-04 | norm 3477.8525 | dt 9.805 +type train | step 3460 | loss 106.2207 221.5401 335.9333 540.7316 778.7390 1121.9551 1544.1224 2189.7334 3047.1692 4550.9863 7335.4424 13150.1133 | lr 2.2e-04 | norm 4122.2305 | dt 9.788 +type train | step 3461 | loss 102.8637 215.1379 327.9413 533.8576 775.3687 1139.2511 1585.9666 2275.8521 3204.6167 4868.2651 7945.9839 14342.8477 | lr 2.2e-04 | norm 3940.0330 | dt 9.788 +type train | step 3462 | loss 103.9485 215.0051 329.4363 536.0638 771.9238 1131.8933 1580.9131 2262.8845 3183.3835 4786.9028 7763.7456 13965.4102 | lr 2.2e-04 | norm 3760.2087 | dt 9.796 +type train | step 3463 | loss 99.0258 204.1074 316.3047 517.5685 750.8376 1100.1877 1535.0889 2195.9121 3110.8857 4712.4395 7670.0464 13803.4443 | lr 2.2e-04 | norm 3713.6782 | dt 9.798 +type train | step 3464 | loss 101.0597 211.5237 325.6628 536.2916 776.6137 1134.9481 1576.3263 2246.0928 3171.5735 4770.2012 7703.6401 13741.2822 | lr 2.2e-04 | norm 3956.0166 | dt 9.787 +type train | step 3465 | loss 93.0041 189.6053 293.8621 488.7396 715.6362 1059.7361 1493.7736 2163.4509 3067.8296 4627.5688 7498.5474 13375.8623 | lr 2.2e-04 | norm 3930.4346 | dt 9.779 +type train | step 3466 | loss 100.2979 206.4720 319.7686 524.2017 761.5038 1107.4158 1551.7377 2218.1992 3144.4797 4786.1392 7849.4092 14275.9805 | lr 2.2e-04 | norm 6840.8018 | dt 9.800 +type train | step 3467 | loss 96.2198 199.6983 307.2591 505.9266 736.9498 1093.1836 1532.0878 2202.5503 3109.4592 4707.5303 7626.1460 13657.6201 | lr 2.2e-04 | norm 3978.7488 | dt 9.778 +type train | step 3468 | loss 106.8856 222.6400 331.4755 536.9027 775.3620 1134.4135 1578.0817 2244.9221 3171.6943 4765.0889 7774.7788 14079.7637 | lr 2.2e-04 | norm 5596.0918 | dt 9.798 +type train | step 3469 | loss 102.1099 212.6169 321.3187 522.0523 753.9399 1109.9094 1547.3297 2224.7871 3123.2263 4698.6807 7600.6670 13558.5566 | lr 2.1e-04 | norm 4200.9058 | dt 9.786 +type train | step 3470 | loss 107.2799 227.1725 346.4241 558.2572 803.4769 1156.7772 1600.6688 2260.2197 3156.1411 4732.0254 7660.3677 13817.4863 | lr 2.1e-04 | norm 5043.6426 | dt 9.778 +type train | step 3471 | loss 104.3753 216.3846 331.7396 535.1428 766.8552 1111.8478 1537.5283 2180.6704 3057.5435 4582.7896 7418.3237 13331.4580 | lr 2.1e-04 | norm 3743.5703 | dt 9.800 +type train | step 3472 | loss 105.9960 221.3093 334.7376 537.4471 771.3823 1122.6145 1562.1434 2237.1482 3126.9160 4684.4243 7570.3594 13620.1162 | lr 2.1e-04 | norm 4438.2007 | dt 9.794 +type train | step 3473 | loss 108.9045 229.7708 346.5744 556.5165 800.0150 1174.9194 1623.6798 2316.5154 3228.8276 4860.6890 7932.0918 14204.2451 | lr 2.1e-04 | norm 4215.3364 | dt 9.781 +type train | step 3474 | loss 98.2881 203.4976 313.3348 510.6086 749.6852 1096.9355 1542.0902 2203.5535 3108.6846 4671.0254 7614.4790 13695.2061 | lr 2.1e-04 | norm 5145.4922 | dt 9.786 +type train | step 3475 | loss 97.8900 202.9160 311.8453 511.1312 746.1909 1089.8555 1521.6904 2175.5381 3093.9502 4679.1133 7595.7954 13595.7666 | lr 2.1e-04 | norm 3575.0627 | dt 9.787 +type train | step 3476 | loss 97.0640 199.5700 305.3461 498.1124 729.9011 1068.9531 1496.1899 2140.3413 3040.6287 4595.8809 7503.4814 13496.9775 | lr 2.1e-04 | norm 3856.3506 | dt 9.797 +type train | step 3477 | loss 113.1995 240.1482 354.6310 560.7694 808.3900 1202.0422 1661.4211 2384.6953 3278.4878 4874.5693 7816.8281 14021.2666 | lr 2.1e-04 | norm 5797.1255 | dt 9.774 +type train | step 3478 | loss 97.5896 202.6318 312.3686 510.9159 740.9722 1085.2393 1518.3735 2171.8450 3075.6790 4646.1055 7598.1265 13619.1445 | lr 2.1e-04 | norm 3619.4028 | dt 9.787 +type train | step 3479 | loss 101.6726 209.5015 323.0096 521.9446 760.5175 1101.6410 1530.6848 2184.3896 3088.6250 4653.6777 7524.8252 13489.0020 | lr 2.1e-04 | norm 4073.5916 | dt 9.791 +type train | step 3480 | loss 97.9997 201.1430 311.5377 509.1377 740.2845 1085.8677 1522.1013 2170.5366 3064.8652 4614.9937 7491.3628 13470.2334 | lr 2.1e-04 | norm 3512.9070 | dt 9.795 +type train | step 3481 | loss 102.3469 215.6274 328.5195 529.8298 763.5580 1103.6964 1539.2012 2181.2646 3074.8259 4646.0679 7561.2954 13641.7568 | lr 2.1e-04 | norm 4026.2644 | dt 9.796 +type train | step 3482 | loss 98.1826 210.7578 329.5594 544.5854 794.2773 1171.8855 1633.3351 2361.1428 3355.5803 5118.8892 8363.2383 14976.7734 | lr 2.1e-04 | norm 6331.5420 | dt 9.789 +type train | step 3483 | loss 98.6911 208.7860 323.6965 529.0609 768.5979 1131.2234 1586.3838 2284.3005 3223.1738 4848.6108 7874.8608 14193.6787 | lr 2.1e-04 | norm 4726.1812 | dt 9.780 +type train | step 3484 | loss 106.1242 221.2269 336.7968 544.2813 786.4694 1141.6680 1581.5885 2251.1279 3169.2632 4777.3086 7769.7993 13925.1035 | lr 2.1e-04 | norm 4107.5103 | dt 9.803 +type train | step 3485 | loss 103.1138 217.6231 334.6472 544.7770 794.4730 1166.4731 1622.0320 2311.7646 3239.1165 4857.0605 7877.6577 14140.3457 | lr 2.1e-04 | norm 4007.2883 | dt 9.795 +type train | step 3486 | loss 111.4314 232.4404 351.2337 559.3666 799.8629 1174.3984 1628.1450 2312.1470 3207.1919 4810.6826 7772.7969 14070.7871 | lr 2.1e-04 | norm 4342.4116 | dt 9.779 +type train | step 3487 | loss 96.6617 201.9962 315.1020 516.4662 752.4728 1100.1543 1540.8307 2199.2710 3111.0198 4688.3535 7652.5127 13738.6816 | lr 2.1e-04 | norm 3901.3574 | dt 9.790 +type train | step 3488 | loss 99.9430 208.8728 323.3395 523.7279 760.8291 1102.1106 1532.2251 2180.5095 3085.4919 4644.3691 7531.0894 13479.0010 | lr 2.1e-04 | norm 3615.6663 | dt 9.808 +type train | step 3489 | loss 96.5765 203.5917 313.1511 505.0786 739.5216 1078.7703 1508.1450 2163.4817 3074.5923 4641.6753 7539.1157 13344.3584 | lr 2.1e-04 | norm 4823.6699 | dt 9.802 +type train | step 3490 | loss 102.8880 214.0147 324.0413 527.6318 766.3147 1123.5956 1565.1353 2229.6934 3140.2595 4709.8511 7600.3467 13611.6113 | lr 2.1e-04 | norm 4312.8281 | dt 9.787 +type train | step 3491 | loss 103.2267 212.6647 320.9050 514.5073 746.5477 1089.7863 1520.7213 2166.0547 3050.9558 4600.8857 7500.7520 13509.9219 | lr 2.1e-04 | norm 3987.6489 | dt 9.788 +type train | step 3492 | loss 106.8948 224.1889 341.3431 548.2629 789.9604 1157.3920 1607.6521 2288.3438 3204.6526 4829.2661 7805.9087 14033.5371 | lr 2.1e-04 | norm 3991.4980 | dt 9.786 +type train | step 3493 | loss 91.6047 188.8146 297.6867 494.5041 726.8212 1074.1128 1516.5710 2195.8840 3131.7080 4752.5508 7752.3350 13910.4961 | lr 2.1e-04 | norm 4845.7397 | dt 9.792 +type train | step 3494 | loss 108.8397 227.9833 344.6107 553.5886 797.3073 1159.8328 1606.6285 2290.2043 3211.8542 4773.7603 7709.6914 13863.9131 | lr 2.1e-04 | norm 4131.1860 | dt 9.785 +type train | step 3495 | loss 113.6740 240.3490 363.5304 574.8782 831.2988 1201.0930 1651.8750 2327.2676 3226.8713 4850.6060 7832.9512 13979.0498 | lr 2.1e-04 | norm 4564.7798 | dt 9.795 +type train | step 3496 | loss 114.3432 244.2059 361.0674 562.0140 808.1704 1147.3557 1568.7455 2208.3340 3110.5637 4644.0991 7464.9209 13351.1865 | lr 2.1e-04 | norm 7168.8926 | dt 9.794 +type train | step 3497 | loss 101.7577 211.3385 322.5475 519.0024 750.2964 1087.6892 1515.6842 2155.2815 3038.8335 4577.9824 7407.2412 13294.2441 | lr 2.1e-04 | norm 4273.4810 | dt 9.787 +type train | step 3498 | loss 97.6559 201.8385 312.5944 514.9130 745.4370 1086.8931 1515.4646 2165.3667 3067.0210 4634.5498 7584.3311 13809.8662 | lr 2.1e-04 | norm 4420.8745 | dt 9.780 +type train | step 3499 | loss 102.7268 215.7957 330.3761 531.1147 769.8895 1117.8572 1558.2017 2211.8733 3117.3867 4724.2896 7677.9453 13831.5615 | lr 2.1e-04 | norm 4980.0649 | dt 9.809 +type train | step 3500 | loss 100.8103 209.0418 318.3153 516.4630 747.9207 1098.9868 1528.2916 2174.6460 3054.1494 4591.2852 7528.8584 13719.7383 | lr 2.1e-04 | norm 4237.5889 | dt 9.784 +type train | step 3501 | loss 98.0240 204.8139 313.6372 507.6733 737.8952 1077.2253 1496.1576 2132.7720 3015.2573 4535.2808 7346.4932 13124.5879 | lr 2.1e-04 | norm 3677.1199 | dt 9.792 +type train | step 3502 | loss 112.0877 235.9312 347.1094 553.2365 790.1866 1153.7441 1590.5464 2268.0706 3151.5896 4734.5986 7712.6792 13953.4814 | lr 2.1e-04 | norm 4315.3765 | dt 9.777 +type train | step 3503 | loss 102.8204 218.6114 334.8656 536.6583 781.7874 1150.0974 1617.8325 2331.7751 3305.8406 4987.3574 8096.1719 14553.8486 | lr 2.1e-04 | norm 5747.2109 | dt 9.785 +type train | step 3504 | loss 99.8090 208.9797 318.7164 518.1404 758.1434 1105.6995 1549.4797 2220.6519 3147.9424 4761.4619 7704.7183 13857.9727 | lr 2.1e-04 | norm 4308.2944 | dt 9.804 +type train | step 3505 | loss 97.5797 202.9661 316.2413 513.0787 749.9540 1100.3466 1541.3234 2205.2090 3121.6589 4694.6626 7667.4028 13817.1924 | lr 2.1e-04 | norm 3932.6792 | dt 9.805 +type train | step 3506 | loss 106.3702 221.3043 336.2414 540.8253 774.0572 1125.8276 1563.8992 2217.3496 3121.6562 4712.2808 7659.9102 13748.2510 | lr 2.1e-04 | norm 4035.2820 | dt 9.804 +type train | step 3507 | loss 107.8547 227.1089 343.0209 544.8489 783.7515 1136.1991 1570.9131 2230.3208 3105.6079 4686.0010 7617.7437 13659.8926 | lr 2.1e-04 | norm 3947.8608 | dt 9.788 +type train | step 3508 | loss 99.0448 206.7661 320.6479 519.4427 757.7166 1107.5508 1547.8766 2203.4009 3115.5063 4721.7407 7683.9639 13855.2158 | lr 2.1e-04 | norm 4180.0806 | dt 9.797 +type train | step 3509 | loss 108.5540 231.3925 354.8924 568.5195 817.6218 1189.4401 1643.3589 2320.9756 3215.3643 4841.0913 7856.4292 14208.8965 | lr 2.1e-04 | norm 5171.2227 | dt 9.781 +type train | step 3510 | loss 99.1972 206.1329 315.8376 511.8889 744.7913 1086.4591 1511.7883 2161.3467 3060.1829 4622.6890 7483.1826 13348.6504 | lr 2.1e-04 | norm 4059.6663 | dt 9.799 +type train | step 3511 | loss 97.5832 202.4432 316.9577 516.8548 755.0885 1110.7886 1558.2528 2239.0342 3164.6963 4781.6675 7737.7500 13851.3066 | lr 2.1e-04 | norm 3952.5215 | dt 9.787 +type train | step 3512 | loss 110.6278 239.5826 362.7663 579.9323 834.2949 1224.0033 1691.1981 2406.3079 3374.2725 5063.2637 8121.9995 14516.7021 | lr 2.1e-04 | norm 7586.8154 | dt 9.786 +type train | step 3513 | loss 95.0329 195.5756 304.7049 506.3543 738.2896 1091.4075 1545.6670 2215.3804 3119.8291 4725.5083 7782.2661 14149.4893 | lr 2.1e-04 | norm 6170.1523 | dt 9.795 +type train | step 3514 | loss 100.3637 209.5493 321.6033 519.7003 758.2627 1107.3624 1543.2784 2195.4446 3096.4368 4672.9082 7619.0229 13668.1660 | lr 2.1e-04 | norm 3966.5647 | dt 9.799 +type train | step 3515 | loss 104.3411 219.9126 336.1144 542.3227 785.3911 1149.7201 1600.2209 2293.1865 3220.6968 4842.1968 7865.7500 14093.0293 | lr 2.1e-04 | norm 3678.0815 | dt 9.797 +type train | step 3516 | loss 101.2912 209.3377 320.6785 520.7507 758.4321 1113.3064 1565.2472 2237.1763 3141.7988 4768.9277 7781.4644 14148.5576 | lr 2.1e-04 | norm 4887.3052 | dt 9.791 +type train | step 3517 | loss 108.5770 228.3490 342.7887 549.8475 797.0599 1167.0027 1607.4270 2294.9641 3200.2129 4774.7666 7749.0547 13921.7510 | lr 2.1e-04 | norm 4495.8730 | dt 9.785 +type train | step 3518 | loss 91.5790 191.9085 301.7825 498.5854 737.4209 1085.0747 1533.0377 2208.1797 3163.0203 4792.2324 7710.4053 13758.5400 | lr 2.1e-04 | norm 4664.6055 | dt 9.787 +type train | step 3519 | loss 110.5112 232.5296 347.7719 554.8685 801.0745 1175.9838 1637.0962 2339.6631 3251.1050 4869.9014 7852.3447 14019.8389 | lr 2.1e-04 | norm 3929.1921 | dt 9.781 +type train | step 3520 | loss 95.0338 198.9402 311.4169 511.5010 751.9554 1107.4222 1560.9513 2243.9541 3176.4585 4801.2236 7748.4380 13879.0039 | lr 2.1e-04 | norm 4496.3896 | dt 9.771 +type train | step 3521 | loss 123.9758 262.4498 389.4446 612.7154 878.2186 1293.2336 1782.3442 2561.9812 3489.5813 5200.6064 8299.6006 14933.8545 | lr 2.1e-04 | norm 7423.7090 | dt 9.746 +type train | step 3522 | loss 99.0512 206.2124 319.5094 520.8895 757.0076 1101.4191 1533.0780 2185.1707 3076.3542 4637.9912 7553.0049 13541.3750 | lr 2.1e-04 | norm 3578.1401 | dt 9.789 +type train | step 3523 | loss 100.6423 212.1833 328.4699 535.1326 777.9988 1136.7372 1586.8644 2260.8325 3184.6636 4832.2871 7880.5479 14137.0674 | lr 2.1e-04 | norm 4058.5935 | dt 9.809 +type train | step 3524 | loss 99.3000 206.0161 315.2234 511.0998 740.3028 1090.0475 1525.0778 2185.7566 3097.0732 4661.3721 7611.3481 13728.4551 | lr 2.1e-04 | norm 3940.8145 | dt 9.791 +type train | step 3525 | loss 103.9276 219.3574 331.3398 534.0109 778.9897 1151.7789 1617.8007 2340.7312 3262.3499 4893.0776 7913.5146 14119.5127 | lr 2.1e-04 | norm 3870.5430 | dt 9.785 +type train | step 3526 | loss 101.9023 211.4985 322.7916 519.9347 754.5685 1095.1154 1522.8590 2160.4800 3027.8540 4573.0195 7478.2285 13531.7832 | lr 2.1e-04 | norm 4439.0708 | dt 9.789 +type train | step 3527 | loss 102.2947 213.2325 328.8002 528.1750 763.3202 1117.9099 1560.1692 2237.4299 3121.7280 4687.5332 7568.1128 13537.1748 | lr 2.1e-04 | norm 4540.2861 | dt 9.803 +type train | step 3528 | loss 97.2678 203.4679 310.4269 501.6495 730.8724 1074.9795 1498.5494 2142.7822 3008.3250 4562.9961 7408.2632 13307.1631 | lr 2.1e-04 | norm 3527.0520 | dt 9.795 +type train | step 3529 | loss 101.1173 210.1915 325.1335 528.7271 767.5234 1121.7355 1559.7113 2225.4321 3130.3911 4715.1387 7656.7690 13737.4375 | lr 2.1e-04 | norm 4274.0142 | dt 9.802 +type train | step 3530 | loss 95.4507 196.8080 305.2359 498.0677 726.3670 1062.5050 1489.5850 2127.2966 3012.2339 4564.4590 7421.8779 13272.5830 | lr 2.1e-04 | norm 3569.8235 | dt 9.780 +type train | step 3531 | loss 108.9057 226.6461 344.7242 553.5389 797.6337 1151.2568 1603.9071 2270.6353 3165.6069 4769.5923 7739.3467 13862.4326 | lr 2.1e-04 | norm 5724.7637 | dt 9.792 +type train | step 3532 | loss 98.4232 204.8313 312.7390 510.3347 739.4001 1088.6357 1525.1846 2193.8237 3082.1868 4668.9346 7571.3467 13651.2734 | lr 2.1e-04 | norm 3617.7129 | dt 9.795 +type train | step 3533 | loss 101.0427 214.1136 327.0648 531.4089 768.1573 1126.2142 1562.6545 2225.5759 3087.9187 4661.9443 7585.9512 13894.5488 | lr 2.1e-04 | norm 4937.2124 | dt 9.789 +type train | step 3534 | loss 96.2418 200.2101 307.5823 498.7217 728.7809 1063.0089 1487.3492 2130.1362 3020.2610 4557.7095 7389.2290 13194.0537 | lr 2.1e-04 | norm 4013.4224 | dt 9.806 +type train | step 3535 | loss 95.0278 197.6690 304.7379 497.5537 728.0231 1072.4297 1508.1971 2166.3389 3068.0947 4633.9922 7600.4575 13730.6475 | lr 2.1e-04 | norm 3662.4675 | dt 9.791 +type train | step 3536 | loss 98.8749 202.6956 313.8761 511.9962 745.9179 1098.3392 1537.4973 2199.7075 3092.8574 4670.5430 7609.2705 13672.7598 | lr 2.1e-04 | norm 3620.1157 | dt 9.799 +type train | step 3537 | loss 100.0847 210.0877 322.0547 521.7549 754.7377 1106.6707 1549.4739 2226.9834 3140.6309 4754.6895 7740.6372 13872.0947 | lr 2.1e-04 | norm 3583.2341 | dt 9.783 +type train | step 3538 | loss 101.1683 208.9420 320.3061 514.2578 749.2651 1097.8596 1533.6797 2181.0229 3069.0759 4636.5474 7559.3706 13554.0371 | lr 2.1e-04 | norm 3736.2065 | dt 9.794 +type train | step 3539 | loss 101.7021 214.7900 324.2597 520.9404 760.0931 1102.0660 1541.5020 2200.3728 3107.7771 4723.9150 7719.7959 13873.9521 | lr 2.1e-04 | norm 3862.9910 | dt 9.804 +type train | step 3540 | loss 97.1871 202.2833 311.5700 503.6383 740.0472 1088.9652 1529.1616 2189.3794 3104.6133 4721.4307 7712.0923 13850.0537 | lr 2.1e-04 | norm 3753.1853 | dt 9.796 +type train | step 3541 | loss 106.0412 223.4032 336.9615 540.6486 780.3884 1138.0405 1582.6156 2248.0237 3140.6143 4775.2119 7694.3979 13861.0654 | lr 2.1e-04 | norm 5374.3335 | dt 9.791 +type train | step 3542 | loss 98.9899 204.4767 317.9475 519.9267 750.6495 1105.8533 1544.4066 2197.3857 3078.4487 4640.6011 7555.4697 13607.6318 | lr 2.1e-04 | norm 3860.3538 | dt 9.789 +type train | step 3543 | loss 99.7608 209.6268 321.6056 527.7284 773.4893 1145.6632 1604.0129 2309.2239 3292.1479 4993.2305 8150.7188 14609.2969 | lr 2.1e-04 | norm 4503.6616 | dt 9.778 +type train | step 3544 | loss 95.5357 194.9629 300.9398 496.4274 724.1667 1078.0800 1520.3075 2189.8843 3097.0898 4700.7837 7672.5952 13812.1191 | lr 2.1e-04 | norm 3846.7385 | dt 9.786 +type train | step 3545 | loss 98.0494 206.2477 313.3064 510.8216 748.2839 1101.0743 1542.9534 2222.4771 3126.8164 4729.1104 7716.2803 13931.5371 | lr 2.0e-04 | norm 4477.5347 | dt 9.786 +type train | step 3546 | loss 99.9740 209.0213 319.8053 516.1199 749.7587 1092.4781 1528.3064 2173.7244 3056.6904 4595.0693 7436.9678 13394.2314 | lr 2.0e-04 | norm 3904.5339 | dt 9.800 +type train | step 3547 | loss 101.6299 209.3625 318.8012 517.9803 754.1667 1110.0520 1558.4219 2230.4568 3138.3298 4732.6172 7685.6938 13752.2100 | lr 2.0e-04 | norm 3891.2012 | dt 9.802 +type train | step 3548 | loss 108.8088 228.0717 347.7496 556.0996 806.1808 1166.5049 1613.6453 2289.6921 3169.0862 4744.6108 7685.1558 13813.2412 | lr 2.0e-04 | norm 6302.7974 | dt 9.793 +type train | step 3549 | loss 102.0325 213.1977 327.5739 528.1194 771.2661 1118.6456 1561.5033 2223.1616 3136.7087 4740.8838 7690.3867 13650.8984 | lr 2.0e-04 | norm 3955.4148 | dt 9.792 +type train | step 3550 | loss 101.5170 210.9353 323.8878 517.8237 747.5080 1104.4529 1539.8582 2202.3335 3076.3423 4639.3022 7603.4922 13674.7598 | lr 2.0e-04 | norm 4587.3120 | dt 9.795 +type train | step 3551 | loss 97.5560 205.3486 317.0145 513.5498 748.1589 1094.5702 1530.7797 2188.8018 3097.0334 4652.0532 7566.1079 13491.3711 | lr 2.0e-04 | norm 3714.5110 | dt 9.800 +type train | step 3552 | loss 97.5843 204.3676 312.7125 512.0281 748.2238 1099.3038 1552.6954 2219.7383 3133.5403 4741.2192 7755.4321 14073.5498 | lr 2.0e-04 | norm 5499.0708 | dt 9.793 +type train | step 3553 | loss 102.2870 213.4016 326.2759 524.8849 756.6199 1100.7712 1535.2178 2182.0303 3074.8274 4669.9443 7624.8789 13804.0488 | lr 2.0e-04 | norm 3767.8872 | dt 9.793 +type train | step 3554 | loss 98.1362 203.8456 313.2408 507.7017 740.9058 1079.6829 1512.9600 2159.8491 3047.8401 4624.8813 7548.6104 13467.9297 | lr 2.0e-04 | norm 3535.1433 | dt 9.797 +type train | step 3555 | loss 102.3816 212.2321 325.0757 527.8558 765.9032 1122.1632 1559.8235 2225.4453 3122.6274 4735.3052 7723.7695 14023.0957 | lr 2.0e-04 | norm 4501.8345 | dt 9.788 +type train | step 3556 | loss 102.2546 212.4769 322.7537 518.1586 751.8294 1090.0953 1516.2045 2159.7219 3040.4932 4602.8257 7460.4048 13407.8145 | lr 2.0e-04 | norm 3921.9927 | dt 9.804 +type train | step 3557 | loss 96.4704 196.9387 304.3069 495.3584 729.2810 1074.4244 1502.2150 2149.1404 3036.2668 4603.4297 7488.6353 13508.1738 | lr 2.0e-04 | norm 3989.3777 | dt 9.789 +type train | step 3558 | loss 98.3773 201.6105 311.2844 510.8465 749.3601 1126.0228 1583.0256 2284.5146 3215.3772 4842.9761 7884.0742 14218.4189 | lr 2.0e-04 | norm 4148.1406 | dt 9.789 +type train | step 3559 | loss 105.7986 221.0563 332.2393 528.9272 768.7690 1127.9592 1574.5331 2243.5718 3143.6382 4730.4556 7652.1279 13713.3008 | lr 2.0e-04 | norm 4021.2322 | dt 9.787 +type train | step 3560 | loss 109.6159 231.6416 351.4118 555.5203 799.1442 1151.8196 1596.6492 2264.3982 3173.0579 4865.7852 7900.3921 14380.6602 | lr 2.0e-04 | norm 7246.0249 | dt 9.796 +type train | step 3561 | loss 99.0797 206.0902 316.9310 509.9980 745.5107 1084.6742 1512.2500 2153.5645 3017.3909 4557.3159 7407.8320 13389.2070 | lr 2.0e-04 | norm 4291.0366 | dt 9.784 +type train | step 3562 | loss 106.3628 219.5480 336.6060 542.8299 786.6053 1138.3865 1582.2656 2229.2786 3117.2825 4675.5684 7624.0791 13733.0684 | lr 2.0e-04 | norm 4302.7261 | dt 9.807 +type train | step 3563 | loss 103.6713 216.0352 328.6706 531.2794 773.6995 1143.0996 1591.1328 2283.8374 3185.6174 4769.1392 7763.0063 14001.4443 | lr 2.0e-04 | norm 4216.7002 | dt 9.777 +type train | step 3564 | loss 109.0880 230.2209 347.8986 561.4078 814.9454 1196.8779 1659.4967 2373.0032 3271.9480 4893.0137 7849.8916 14082.3848 | lr 2.0e-04 | norm 5873.0620 | dt 9.772 +type train | step 3565 | loss 102.2317 212.2695 325.6774 526.3907 761.9158 1116.5428 1563.2582 2236.3757 3138.3345 4734.5181 7676.0127 13758.8408 | lr 2.0e-04 | norm 3666.2119 | dt 9.786 +type train | step 3566 | loss 101.9165 214.8130 326.4924 526.3193 766.9404 1127.6799 1579.7789 2262.1638 3173.0847 4830.6587 7942.0249 14457.4941 | lr 2.0e-04 | norm 4421.6890 | dt 9.794 +type train | step 3567 | loss 98.8932 204.0707 311.5623 502.1922 731.8195 1072.9271 1506.9031 2169.5884 3063.3413 4646.7812 7605.1274 13747.7471 | lr 2.0e-04 | norm 4131.1841 | dt 9.788 +type train | step 3568 | loss 105.6118 221.5655 339.8581 543.5607 778.0806 1125.9552 1548.1154 2172.0200 3010.9551 4528.5894 7332.4102 13317.6797 | lr 2.0e-04 | norm 5161.6445 | dt 9.791 +type train | step 3569 | loss 95.9402 197.2678 304.9528 497.2480 725.5920 1061.8890 1485.3986 2117.7583 2992.9670 4513.7363 7351.0127 13222.9072 | lr 2.0e-04 | norm 3820.1567 | dt 9.807 +type train | step 3570 | loss 99.5909 208.5057 320.0507 517.1539 756.8494 1110.8290 1548.0797 2209.5527 3095.4944 4642.1294 7495.8779 13449.0205 | lr 2.0e-04 | norm 4200.0459 | dt 9.792 +type train | step 3571 | loss 96.4969 202.6244 315.8568 512.1685 747.9825 1095.0631 1531.2195 2191.6782 3089.0835 4651.3442 7522.8047 13503.7754 | lr 2.0e-04 | norm 3658.6104 | dt 9.794 +type train | step 3572 | loss 99.1039 207.9835 317.6912 517.8387 755.0930 1111.4802 1566.5448 2247.6389 3181.3579 4832.7661 7876.3472 14221.1338 | lr 2.0e-04 | norm 4499.2441 | dt 9.805 +type train | step 3573 | loss 91.4587 190.2224 296.1728 482.5966 711.8301 1051.7925 1490.8738 2141.1130 3045.2134 4609.5049 7467.4761 13313.4648 | lr 2.0e-04 | norm 3529.4741 | dt 9.812 +type train | step 3574 | loss 103.4308 212.1201 323.5812 516.6183 752.0159 1098.5140 1537.7828 2196.1777 3093.0879 4628.5005 7505.0928 13511.2607 | lr 2.0e-04 | norm 4050.5234 | dt 9.783 +type train | step 3575 | loss 95.1168 200.7151 312.7616 510.4092 755.6987 1106.3724 1553.6187 2224.7002 3152.9114 4807.1240 7777.0454 13927.2285 | lr 2.0e-04 | norm 5771.7798 | dt 9.794 +type train | step 3576 | loss 95.6853 201.8452 312.3685 507.6385 747.8732 1107.2957 1566.6255 2253.8853 3162.6431 4801.4946 7784.2773 13908.3047 | lr 2.0e-04 | norm 6601.5166 | dt 9.788 +type train | step 3577 | loss 106.2355 221.7050 334.9747 535.1843 776.1216 1149.5205 1610.8450 2298.7004 3162.4849 4747.4414 7663.7979 13824.9668 | lr 2.0e-04 | norm 7041.3037 | dt 9.781 +type train | step 3578 | loss 96.1573 197.0130 305.3442 495.4351 728.6730 1070.5928 1510.1906 2170.0979 3080.8164 4651.6885 7503.0366 13281.7197 | lr 2.0e-04 | norm 4011.5176 | dt 9.806 +type train | step 3579 | loss 106.0942 220.1755 334.8201 541.1121 780.2544 1151.0986 1611.0184 2306.3057 3250.8203 4947.6895 8100.9487 14601.7734 | lr 2.0e-04 | norm 4110.4365 | dt 9.778 +type train | step 3580 | loss 102.2890 213.1271 322.6281 520.2026 759.6349 1117.2083 1554.1257 2231.4780 3118.6704 4669.0757 7505.6211 13452.1846 | lr 2.0e-04 | norm 4876.8545 | dt 9.776 +type train | step 3581 | loss 103.0483 216.6847 327.3019 522.5698 757.0039 1115.9053 1560.9597 2237.0027 3137.7397 4718.5430 7644.0059 13657.5381 | lr 2.0e-04 | norm 4052.0457 | dt 9.809 +type train | step 3582 | loss 104.4196 218.4631 332.3181 533.3068 771.2230 1131.8334 1579.9702 2242.6467 3122.3025 4632.3457 7465.2495 13420.1123 | lr 2.0e-04 | norm 4211.5044 | dt 9.815 +type train | step 3583 | loss 101.7189 210.6097 325.2523 525.7750 772.7411 1130.1895 1578.7723 2259.7913 3153.8801 4744.0659 7693.1646 13842.7236 | lr 2.0e-04 | norm 4090.1770 | dt 9.799 +type train | step 3584 | loss 103.7051 212.8774 325.6454 524.9550 763.3875 1131.7428 1577.8225 2266.3936 3150.8696 4712.6436 7635.1523 13563.8613 | lr 2.0e-04 | norm 4122.9082 | dt 9.786 +type train | step 3585 | loss 89.1199 182.8572 290.5894 486.1776 717.3855 1068.1394 1511.5585 2186.4197 3105.0029 4697.7051 7734.6074 14093.8418 | lr 2.0e-04 | norm 5286.5117 | dt 9.793 +type train | step 3586 | loss 96.9153 200.2815 308.9254 504.3969 744.1307 1102.4929 1550.5325 2232.4924 3149.7388 4787.5645 7763.7559 13933.3867 | lr 2.0e-04 | norm 3981.8171 | dt 9.784 +type train | step 3587 | loss 100.6632 210.8962 327.5987 529.1403 767.3589 1118.5416 1561.2087 2207.1689 3108.7268 4674.1904 7617.5176 13672.5820 | lr 2.0e-04 | norm 4111.4150 | dt 9.803 +type train | step 3588 | loss 97.6789 203.1767 309.5561 506.5594 740.9597 1095.2245 1540.6639 2213.8516 3109.7981 4703.0229 7636.6553 13728.5254 | lr 2.0e-04 | norm 4287.1626 | dt 9.794 +type train | step 3589 | loss 105.9632 221.2013 342.4637 551.5592 800.8431 1168.0836 1619.2095 2299.7861 3200.1450 4791.0503 7700.0938 13932.1826 | lr 2.0e-04 | norm 5561.6904 | dt 9.780 +type train | step 3590 | loss 93.7540 194.4111 301.7343 493.6418 734.7504 1090.5172 1547.0479 2250.6072 3192.5005 4862.9717 7927.7944 14164.9326 | lr 2.0e-04 | norm 5687.7041 | dt 9.791 +type train | step 3591 | loss 101.3964 207.8421 320.6367 518.5225 748.7599 1100.9500 1546.7477 2211.8164 3097.9058 4673.3711 7656.1479 13906.7197 | lr 2.0e-04 | norm 4673.1016 | dt 9.795 +type train | step 3592 | loss 96.7145 201.3123 309.6375 504.1115 737.8161 1093.5365 1539.0735 2229.5054 3146.1423 4757.9863 7770.2119 13881.6250 | lr 2.0e-04 | norm 4274.3208 | dt 9.783 +type train | step 3593 | loss 99.6446 211.1011 320.2730 520.0260 758.0126 1103.8804 1544.0548 2195.6660 3109.7930 4693.3091 7585.4653 13484.4160 | lr 2.0e-04 | norm 4344.8848 | dt 9.798 +type train | step 3594 | loss 95.3361 198.4969 307.1350 498.8436 732.0901 1071.2817 1507.1194 2166.8149 3063.0652 4635.5449 7502.6416 13419.0684 | lr 2.0e-04 | norm 3598.9009 | dt 9.804 +type train | step 3595 | loss 108.2250 226.2359 342.4636 540.0341 777.9478 1150.1254 1623.8151 2324.8394 3236.4089 4863.3140 7934.7427 14337.2744 | lr 2.0e-04 | norm 7682.3315 | dt 9.770 +type train | step 3596 | loss 110.2592 233.4516 353.2393 558.8632 807.5178 1176.1259 1636.9259 2310.2539 3220.7815 4831.5098 7784.2100 13965.4014 | lr 2.0e-04 | norm 5198.9404 | dt 9.794 +type train | step 3597 | loss 100.9500 208.6545 321.5941 519.4982 759.2023 1109.0947 1555.3135 2207.3274 3102.1826 4706.6670 7668.5884 13759.1768 | lr 2.0e-04 | norm 3853.8684 | dt 9.789 +type train | step 3598 | loss 106.4329 223.0945 337.1850 540.1274 781.0684 1142.2980 1583.5270 2252.4333 3151.2078 4750.1582 7757.8389 13996.1299 | lr 2.0e-04 | norm 3693.8989 | dt 9.792 +type train | step 3599 | loss 90.4535 189.6300 294.5184 490.2864 732.0601 1069.5745 1527.1647 2193.0117 3095.2556 4721.6455 7769.7290 14163.3154 | lr 2.0e-04 | norm 5956.7920 | dt 9.790 +type train | step 3600 | loss 104.0038 218.9752 334.9186 540.6276 780.0310 1136.3927 1583.2607 2253.6636 3159.7778 4778.9473 7747.8350 13916.0850 | lr 2.0e-04 | norm 4539.6123 | dt 9.780 +type train | step 3601 | loss 101.5276 212.0954 327.1473 535.4228 777.6782 1141.3914 1600.7461 2287.9180 3222.7961 4861.8745 7866.1499 14047.7812 | lr 2.0e-04 | norm 4537.1665 | dt 9.799 +type train | step 3602 | loss 117.0602 244.6855 363.7519 577.0476 825.4573 1195.2760 1654.6176 2345.0852 3287.4602 4982.8115 8150.2832 14747.1514 | lr 2.0e-04 | norm 6056.1909 | dt 9.778 +type train | step 3603 | loss 100.4133 212.0893 323.0228 524.9951 766.4628 1120.8263 1560.6611 2225.8416 3114.9155 4660.8037 7562.9224 13567.7686 | lr 2.0e-04 | norm 3848.7434 | dt 9.778 +type train | step 3604 | loss 97.2550 202.0514 312.3193 506.6237 740.0305 1097.7524 1545.6204 2224.7842 3115.9524 4714.0684 7668.0215 13781.8574 | lr 2.0e-04 | norm 4375.9463 | dt 9.798 +type train | step 3605 | loss 96.2115 206.2684 318.3412 519.4850 762.7824 1106.5863 1554.2726 2209.5886 3139.0999 4736.8042 7693.6235 13787.2490 | lr 2.0e-04 | norm 5953.2593 | dt 9.794 +type train | step 3606 | loss 97.1724 200.8158 313.6665 515.9229 756.6474 1111.4208 1559.1687 2235.7939 3154.8789 4780.2202 7798.1792 14038.8164 | lr 2.0e-04 | norm 4922.4224 | dt 9.803 +type train | step 3607 | loss 96.2898 200.4243 309.1203 500.2583 731.8260 1068.3124 1506.0712 2144.6470 3048.4172 4633.8403 7548.9033 13590.7246 | lr 2.0e-04 | norm 4370.9771 | dt 9.800 +type train | step 3608 | loss 102.1612 217.6681 330.2737 531.0882 771.6669 1132.5435 1571.3032 2244.0942 3138.3276 4747.0254 7798.6875 14154.4277 | lr 2.0e-04 | norm 7129.5684 | dt 9.770 +type train | step 3609 | loss 98.0361 203.9120 314.4077 505.3364 741.4380 1092.6260 1530.6715 2195.9961 3079.2773 4660.1958 7544.3867 13596.4492 | lr 2.0e-04 | norm 4115.7476 | dt 9.790 +type train | step 3610 | loss 97.2907 201.2360 308.2808 497.9662 730.6091 1076.1831 1508.9105 2163.2754 3065.1826 4659.5942 7620.1118 13732.0654 | lr 2.0e-04 | norm 4902.7485 | dt 9.774 +type train | step 3611 | loss 100.7389 215.6621 331.3291 531.7040 780.1666 1133.6720 1595.4521 2280.1047 3219.8899 4904.2241 8008.6855 14472.5625 | lr 2.0e-04 | norm 5368.2246 | dt 9.790 +type train | step 3612 | loss 100.2146 213.5040 324.5143 526.1424 769.0562 1114.7931 1563.4965 2231.6208 3154.2866 4768.5942 7724.5498 13955.8662 | lr 2.0e-04 | norm 4818.9609 | dt 9.785 +type train | step 3613 | loss 97.8280 204.9268 317.2192 514.3123 756.2604 1114.5161 1560.4098 2228.7969 3147.1650 4738.2334 7744.7939 13967.9902 | lr 2.0e-04 | norm 4541.8145 | dt 9.793 +type train | step 3614 | loss 101.6024 210.5195 323.4517 523.4123 757.7583 1104.2604 1550.1322 2207.4233 3114.3396 4693.3569 7592.9541 13586.3154 | lr 2.0e-04 | norm 4034.0579 | dt 9.789 +type train | step 3615 | loss 100.0700 208.3750 320.5496 514.2738 749.0534 1101.6718 1541.5964 2195.1021 3089.7166 4661.5952 7587.7573 13584.0762 | lr 2.0e-04 | norm 3665.3271 | dt 9.794 +type train | step 3616 | loss 98.0203 208.6425 320.3758 522.6634 764.6044 1117.9058 1569.4332 2247.1201 3172.3706 4808.0469 7801.8652 13883.8398 | lr 2.0e-04 | norm 3932.1895 | dt 9.782 +type train | step 3617 | loss 96.4086 197.9780 305.6896 498.3868 734.4724 1079.5192 1520.9185 2189.9861 3106.3362 4731.4185 7722.8721 13820.8662 | lr 2.0e-04 | norm 4052.0823 | dt 9.788 +type train | step 3618 | loss 115.1876 235.5060 350.7754 563.0789 806.8901 1180.1520 1656.6448 2338.7070 3236.3154 4836.7666 7800.1279 13957.1113 | lr 2.0e-04 | norm 3943.4094 | dt 9.792 +type train | step 3619 | loss 94.6404 197.9512 307.6889 499.0245 731.2526 1081.9152 1525.6611 2191.1462 3113.5049 4731.6367 7717.5620 13908.2529 | lr 2.0e-04 | norm 3716.3281 | dt 9.801 +type train | step 3620 | loss 92.8206 192.8402 301.4756 491.8595 732.0751 1069.8000 1519.2644 2178.3479 3086.2512 4671.5537 7595.0146 13593.3906 | lr 2.0e-04 | norm 5402.2959 | dt 9.786 +type train | step 3621 | loss 102.2392 216.5631 329.4667 531.5335 773.3054 1132.5352 1572.8270 2234.9165 3100.4207 4696.8955 7684.1426 13911.7041 | lr 2.0e-04 | norm 5119.0923 | dt 9.781 +type train | step 3622 | loss 98.4405 201.5137 310.9079 502.4124 733.9908 1073.0676 1505.0042 2147.7559 3018.4094 4546.1914 7360.7490 13204.8438 | lr 2.0e-04 | norm 3886.6760 | dt 9.796 +type train | step 3623 | loss 100.5199 209.7559 318.9076 511.0141 742.8888 1082.4132 1509.2904 2148.7515 3027.8530 4562.0244 7376.4961 13287.1699 | lr 1.9e-04 | norm 3747.5776 | dt 9.798 +type train | step 3624 | loss 109.3453 227.9563 347.7855 555.5892 799.0525 1153.7454 1593.7302 2244.7349 3105.8513 4670.9541 7587.7266 13840.9873 | lr 1.9e-04 | norm 5287.9829 | dt 9.783 +type train | step 3625 | loss 104.2834 217.7653 332.0278 532.5623 772.8222 1128.2173 1575.9636 2237.9551 3133.3494 4750.3237 7754.9043 14071.0635 | lr 1.9e-04 | norm 4031.0818 | dt 9.789 +type train | step 3626 | loss 93.8602 193.9680 302.1689 497.7602 730.7901 1082.0277 1525.2346 2200.7275 3114.3193 4694.1050 7615.8428 13620.1279 | lr 1.9e-04 | norm 4656.4302 | dt 9.810 +type train | step 3627 | loss 96.4466 199.9363 310.0380 500.9744 738.3467 1081.8563 1527.0199 2182.9077 3087.8276 4669.6250 7580.6558 13595.2178 | lr 1.9e-04 | norm 4134.3931 | dt 9.799 +type train | step 3628 | loss 98.3392 205.8050 324.1418 527.1907 773.3088 1125.3152 1567.4761 2223.1794 3138.8013 4722.3530 7701.2681 13812.7666 | lr 1.9e-04 | norm 4050.9568 | dt 9.792 +type train | step 3629 | loss 87.2359 177.2257 278.8485 459.9318 692.8029 1039.7533 1488.1173 2204.9558 3154.2534 4788.8604 7723.4053 13712.8096 | lr 1.9e-04 | norm 5154.8662 | dt 9.763 +type train | step 3630 | loss 94.7596 197.2671 301.9297 488.6523 722.7683 1059.2834 1496.7760 2155.2449 3048.6584 4643.6528 7616.4365 13683.0127 | lr 1.9e-04 | norm 5147.5840 | dt 9.793 +type train | step 3631 | loss 96.9076 203.1600 311.9601 502.2565 737.4833 1081.2325 1523.0771 2178.8110 3069.8213 4641.0596 7557.7881 13451.0176 | lr 1.9e-04 | norm 4428.4517 | dt 9.797 +type train | step 3632 | loss 102.0114 209.5986 320.2814 516.4087 745.9681 1095.6970 1526.3051 2183.4319 3069.8828 4627.9326 7479.0591 13377.5693 | lr 1.9e-04 | norm 3897.7292 | dt 9.791 +type train | step 3633 | loss 99.1681 203.6370 312.7518 506.5313 742.6375 1086.0264 1521.5618 2181.0044 3075.2588 4657.9473 7583.3271 13605.3242 | lr 1.9e-04 | norm 3818.8318 | dt 9.796 +type train | step 3634 | loss 98.0185 204.8781 317.7263 522.2869 758.1111 1118.2992 1565.5432 2245.8523 3164.6338 4774.6680 7784.2998 14155.7490 | lr 1.9e-04 | norm 5061.7114 | dt 9.783 +type train | step 3635 | loss 101.6867 213.0700 325.9417 527.0946 765.5923 1118.6996 1559.8196 2220.6387 3122.5173 4707.2910 7641.9580 13707.7959 | lr 1.9e-04 | norm 3632.2141 | dt 9.797 +type train | step 3636 | loss 98.0779 203.2217 312.8811 505.6483 740.6878 1081.6403 1513.6570 2163.7258 3065.2224 4634.0811 7553.3062 13607.8535 | lr 1.9e-04 | norm 3950.6833 | dt 9.793 +type train | step 3637 | loss 104.1248 214.8419 323.9267 517.7896 750.4517 1111.8313 1557.4240 2237.4075 3128.1758 4693.9233 7543.8384 13477.0703 | lr 1.9e-04 | norm 4340.9077 | dt 9.778 +type train | step 3638 | loss 113.8300 245.5110 369.1423 577.9258 822.8462 1209.1099 1676.6575 2377.4963 3223.6355 4821.4985 7807.3521 14159.2607 | lr 1.9e-04 | norm 11106.0381 | dt 9.796 +type train | step 3639 | loss 118.0262 254.2196 374.9900 583.1968 829.2948 1206.2401 1669.5155 2354.1479 3212.5405 4791.6353 7704.9604 13782.5000 | lr 1.9e-04 | norm 8292.1602 | dt 9.776 +type train | step 3640 | loss 100.5592 208.8527 323.7877 529.9791 767.9854 1134.0559 1585.3440 2269.3538 3178.9526 4782.1099 7777.4629 13966.3408 | lr 1.9e-04 | norm 4318.8364 | dt 9.790 +type train | step 3641 | loss 100.6100 211.2596 319.3159 514.0585 751.5355 1107.0261 1554.2102 2226.9717 3108.3406 4705.9707 7677.0479 13884.9717 | lr 1.9e-04 | norm 4530.5107 | dt 9.795 +type train | step 3642 | loss 97.1053 201.8148 311.7189 502.7054 735.8037 1081.2904 1519.8278 2170.7036 3064.0710 4625.9170 7510.1904 13489.8750 | lr 1.9e-04 | norm 3828.1042 | dt 9.793 +type train | step 3643 | loss 103.1722 217.0155 329.3749 525.8360 765.9606 1105.0479 1535.3906 2169.4304 3035.4248 4558.7959 7398.7642 13324.1895 | lr 1.9e-04 | norm 4072.7776 | dt 9.797 +type train | step 3644 | loss 97.5084 200.4411 311.8909 506.3778 743.5589 1087.7063 1529.9066 2188.7456 3098.9490 4714.2471 7706.2061 13886.9443 | lr 1.9e-04 | norm 3831.4214 | dt 9.802 +type train | step 3645 | loss 98.7280 203.6726 311.1881 505.8110 740.7504 1085.1776 1520.7842 2177.0991 3070.4214 4678.7173 7675.1313 13907.3203 | lr 1.9e-04 | norm 3833.1262 | dt 9.787 +type train | step 3646 | loss 101.7229 211.0381 324.2708 523.1133 761.2233 1116.2572 1559.6580 2219.6074 3118.2988 4655.6001 7529.1362 13365.2441 | lr 1.9e-04 | norm 3417.5168 | dt 9.804 +type train | step 3647 | loss 115.3385 243.5377 362.0054 588.3506 848.5038 1223.2429 1664.9337 2339.1345 3194.1096 4802.3916 7768.2534 14067.2354 | lr 1.9e-04 | norm 8902.3125 | dt 9.759 +type train | step 3648 | loss 100.7014 210.3413 324.3701 519.0468 761.7685 1106.0891 1546.4683 2201.7021 3104.5276 4682.4580 7618.2617 13681.2783 | lr 1.9e-04 | norm 3784.0920 | dt 9.793 +type train | step 3649 | loss 97.3883 200.8171 308.3921 499.2611 733.9891 1079.9192 1526.8394 2187.2046 3093.3494 4683.3076 7627.4648 13691.3203 | lr 1.9e-04 | norm 4448.1079 | dt 9.789 +type train | step 3650 | loss 97.5266 199.4597 311.2068 507.6328 743.3103 1105.3038 1557.8918 2243.1509 3148.5576 4765.5352 7753.7769 13898.1787 | lr 1.9e-04 | norm 4039.3357 | dt 9.794 +type train | step 3651 | loss 94.9763 197.5294 303.8662 494.5443 726.2657 1065.7585 1505.1604 2153.4543 3061.1917 4633.5698 7551.2344 13492.9277 | lr 1.9e-04 | norm 3586.1858 | dt 9.799 +type train | step 3652 | loss 121.3727 255.5186 388.2578 643.4034 933.8970 1404.3029 1959.8047 2878.2249 3921.9646 5798.0625 9186.4941 16338.3018 | lr 1.9e-04 | norm 10483.8027 | dt 9.765 +type train | step 3653 | loss 100.1926 208.3108 325.1595 527.8049 761.6949 1108.0315 1553.7664 2212.1350 3083.3328 4648.2456 7569.8247 13666.8418 | lr 1.9e-04 | norm 5516.1958 | dt 9.789 +type train | step 3654 | loss 99.9857 208.5606 316.3148 511.2939 745.0651 1116.5178 1582.7947 2288.1570 3204.1086 4841.8584 7908.6611 14220.7383 | lr 1.9e-04 | norm 5161.8618 | dt 9.787 +type train | step 3655 | loss 92.0089 191.1243 295.4848 481.8401 709.1230 1050.8788 1482.2434 2133.0962 3007.3262 4582.7715 7496.9092 13683.8809 | lr 1.9e-04 | norm 6273.3501 | dt 9.806 +type train | step 3656 | loss 104.7187 212.1411 316.8024 511.4187 738.7963 1101.8223 1534.8693 2187.0947 3029.7688 4524.1582 7224.3960 12971.9521 | lr 1.9e-04 | norm 5062.6392 | dt 9.763 +type train | step 3657 | loss 102.5127 214.0923 327.9163 532.0735 772.0046 1131.4250 1579.2612 2247.0332 3126.9609 4723.0029 7750.0293 14009.0703 | lr 1.9e-04 | norm 7057.7119 | dt 9.787 +type train | step 3658 | loss 103.0558 211.4314 326.0429 519.9022 762.1285 1108.6364 1553.5081 2211.1824 3109.1008 4692.4180 7648.7217 13655.2373 | lr 1.9e-04 | norm 4286.2954 | dt 9.792 +type train | step 3659 | loss 96.7697 200.9318 309.4969 502.3950 736.0961 1078.6550 1521.0237 2169.4695 3062.1345 4647.1846 7607.1631 13682.5146 | lr 1.9e-04 | norm 4144.4268 | dt 9.786 +type train | step 3660 | loss 103.8851 216.2627 327.4550 527.0096 766.9543 1119.5122 1557.7122 2214.0393 3095.0925 4684.1865 7648.6602 13794.1641 | lr 1.9e-04 | norm 3856.9250 | dt 9.792 +type train | step 3661 | loss 98.4100 200.7970 311.4724 512.0389 739.8820 1101.5037 1551.2068 2244.7278 3149.8699 4735.0303 7684.6177 13882.2363 | lr 1.9e-04 | norm 4777.9131 | dt 9.790 +type train | step 3662 | loss 105.9236 224.7760 342.8902 546.2258 797.2892 1146.3555 1590.9113 2235.6333 3127.5610 4652.2632 7494.7559 13398.0811 | lr 1.9e-04 | norm 5679.9868 | dt 9.791 +type train | step 3663 | loss 102.3140 212.6137 325.4298 524.4328 767.1165 1107.8879 1543.1439 2183.9922 3060.9448 4597.0176 7427.3867 13333.1953 | lr 1.9e-04 | norm 3729.1609 | dt 9.797 +type train | step 3664 | loss 93.3607 193.9986 298.7036 488.2589 719.5633 1064.5326 1508.1998 2168.8921 3085.3218 4688.2910 7674.6489 13866.0088 | lr 1.9e-04 | norm 4242.3320 | dt 9.786 +type train | step 3665 | loss 100.7636 207.9244 316.0422 511.2682 748.5494 1095.5542 1541.9374 2207.3633 3098.7935 4658.0864 7563.0078 13595.6934 | lr 1.9e-04 | norm 4192.4106 | dt 9.784 +type train | step 3666 | loss 93.8259 192.2480 299.1537 487.6607 715.8494 1057.5664 1488.4988 2134.7092 3023.1057 4596.6235 7516.2090 13561.8643 | lr 1.9e-04 | norm 3672.6553 | dt 9.780 +type train | step 3667 | loss 101.1701 211.4123 324.7052 521.0061 759.1072 1108.7205 1559.1263 2233.1707 3141.5505 4754.3999 7797.4600 14082.7471 | lr 1.9e-04 | norm 4115.5020 | dt 9.791 +type train | step 3668 | loss 96.8406 201.1778 307.5710 500.0888 729.7995 1065.0345 1505.1139 2153.1025 3048.0203 4603.3574 7486.9780 13414.9844 | lr 1.9e-04 | norm 4196.9512 | dt 9.790 +type train | step 3669 | loss 96.0852 198.5499 307.4491 500.8041 734.9216 1083.4404 1522.7531 2180.0303 3063.4807 4639.9473 7552.5298 13508.0840 | lr 1.9e-04 | norm 4334.1406 | dt 9.793 +type train | step 3670 | loss 99.4824 207.2578 317.6733 507.9502 749.3624 1086.7029 1520.2725 2161.6741 3045.2310 4581.5396 7396.7998 13124.8379 | lr 1.9e-04 | norm 3743.4373 | dt 9.803 +type train | step 3671 | loss 100.1656 210.7417 322.8987 517.6635 757.6848 1095.9731 1530.4886 2165.2253 3029.8782 4567.6123 7454.2886 13400.2324 | lr 1.9e-04 | norm 3889.6155 | dt 9.792 +type train | step 3672 | loss 98.3054 206.5368 315.7439 511.0977 748.8266 1095.0977 1538.0815 2194.9900 3095.6404 4677.8809 7589.0986 13569.5586 | lr 1.9e-04 | norm 3435.8428 | dt 9.826 +type train | step 3673 | loss 99.3518 206.7557 321.3916 520.9169 757.1617 1106.8724 1549.6821 2204.5430 3109.6265 4687.0107 7599.4448 13529.7881 | lr 1.9e-04 | norm 3981.0337 | dt 9.800 +type train | step 3674 | loss 104.4051 217.2073 331.2264 533.6880 772.8757 1130.6390 1570.5659 2227.9863 3085.7876 4590.8311 7463.4600 13453.5527 | lr 1.9e-04 | norm 4318.4351 | dt 9.795 +type train | step 3675 | loss 100.8046 205.4949 320.0619 516.8387 754.8595 1090.2197 1523.8301 2162.6943 3018.2883 4547.1890 7419.6270 13488.5312 | lr 1.9e-04 | norm 4469.3682 | dt 9.796 +type train | step 3676 | loss 100.3006 210.2150 321.6117 519.5532 751.9144 1096.7338 1540.3685 2191.5864 3069.5320 4641.9819 7586.2793 13605.2646 | lr 1.9e-04 | norm 3554.0403 | dt 9.789 +type train | step 3677 | loss 103.4758 214.5934 324.7709 521.4427 762.2913 1115.5626 1557.6700 2225.0171 3105.3293 4680.5034 7646.0000 13737.7422 | lr 1.9e-04 | norm 3601.8901 | dt 9.773 +type train | step 3678 | loss 100.5139 209.5057 320.9064 518.0212 750.1983 1095.7159 1526.3783 2180.9592 3060.5593 4629.7979 7575.4321 13646.6230 | lr 1.9e-04 | norm 4407.9985 | dt 9.781 +type train | step 3679 | loss 97.9834 204.0601 314.1284 507.3111 745.7405 1106.0168 1560.7863 2244.1848 3154.1685 4782.2466 7760.7393 14046.9805 | lr 1.9e-04 | norm 5294.2158 | dt 9.781 +type train | step 3680 | loss 99.9597 207.2922 319.5515 518.4861 757.4661 1111.6224 1552.6117 2217.5950 3119.9075 4723.9536 7682.5786 13805.5312 | lr 1.9e-04 | norm 3571.4067 | dt 9.797 +type train | step 3681 | loss 101.9453 213.0591 329.3744 526.6284 764.5261 1117.9172 1552.4587 2195.3894 3063.7839 4599.8867 7445.6270 13379.3330 | lr 1.9e-04 | norm 4881.1025 | dt 9.808 +type train | step 3682 | loss 100.4888 209.7931 324.1987 520.6793 764.4080 1109.4767 1553.1685 2202.2981 3097.8704 4655.9971 7541.1445 13488.5596 | lr 1.9e-04 | norm 3672.4915 | dt 9.804 +type train | step 3683 | loss 100.3093 207.5316 318.5820 512.6592 748.5347 1101.5859 1534.0364 2184.4546 3052.0505 4587.7383 7432.0078 13283.5137 | lr 1.9e-04 | norm 3819.5020 | dt 9.787 +type train | step 3684 | loss 96.2265 199.9988 309.9359 498.2032 733.5604 1069.1879 1500.7256 2137.4531 3027.0361 4551.0732 7392.9429 13207.0234 | lr 1.9e-04 | norm 3736.6006 | dt 9.807 +type train | step 3685 | loss 97.0810 203.2604 312.4370 502.2966 740.2847 1084.0192 1523.6956 2175.9626 3062.2402 4632.0464 7526.1133 13537.4600 | lr 1.9e-04 | norm 3598.8718 | dt 9.804 +type train | step 3686 | loss 95.8846 198.0148 303.6654 492.2840 718.9006 1061.7036 1492.9106 2142.9397 3022.2471 4592.6108 7489.7954 13456.1924 | lr 1.9e-04 | norm 3850.9543 | dt 9.782 +type train | step 3687 | loss 104.4006 215.6090 327.4507 520.4642 759.2554 1118.5963 1566.4138 2240.8196 3127.1633 4744.3481 7711.4023 13872.9932 | lr 1.9e-04 | norm 4405.9263 | dt 9.794 +type train | step 3688 | loss 97.8841 202.8569 312.2361 505.6093 738.6306 1081.8096 1518.3431 2157.5330 3026.4224 4551.2422 7400.1909 13234.5342 | lr 1.9e-04 | norm 3780.0137 | dt 9.793 +type train | step 3689 | loss 101.3995 214.2946 332.7598 536.0981 782.9505 1132.9888 1571.8984 2219.5483 3117.5659 4670.9980 7496.7075 13383.9268 | lr 1.9e-04 | norm 3666.2844 | dt 9.804 +type train | step 3690 | loss 108.2020 224.4593 341.0324 550.7721 792.9393 1160.6924 1609.0554 2281.2429 3144.6238 4708.9053 7646.2471 13891.7705 | lr 1.9e-04 | norm 4410.0103 | dt 9.785 +type train | step 3691 | loss 100.4234 206.0171 314.7379 510.5591 746.2821 1098.9478 1536.8239 2182.0073 3056.1130 4593.6694 7452.9478 13451.8750 | lr 1.9e-04 | norm 4122.0400 | dt 9.774 +type train | step 3692 | loss 95.9496 199.2991 310.8230 505.6198 738.1308 1084.7880 1523.0134 2185.7012 3078.8484 4644.8867 7561.3203 13566.4580 | lr 1.9e-04 | norm 3510.3782 | dt 9.805 +type train | step 3693 | loss 96.3471 200.9220 314.2607 513.0451 757.7463 1127.2620 1590.7295 2300.3296 3237.1423 4917.6738 7969.1309 14333.8555 | lr 1.9e-04 | norm 4217.3101 | dt 9.793 +type train | step 3694 | loss 95.3136 195.4286 302.2874 499.9972 733.4237 1085.9028 1537.0969 2196.8213 3094.9849 4692.6128 7668.0464 13780.8496 | lr 1.9e-04 | norm 4196.1802 | dt 9.778 +type train | step 3695 | loss 97.7955 203.8211 315.8628 513.2550 760.7589 1105.7139 1553.6781 2211.8098 3118.9001 4691.2378 7647.8765 13791.1211 | lr 1.9e-04 | norm 3729.0989 | dt 9.808 +type train | step 3696 | loss 101.5585 212.5014 325.5344 518.8333 754.7133 1097.4285 1532.2574 2171.2981 3042.3252 4550.9609 7358.3804 13118.0283 | lr 1.9e-04 | norm 3628.8137 | dt 9.792 +type train | step 3697 | loss 92.7991 191.8174 296.4146 484.6439 728.5092 1055.4734 1491.2108 2143.8921 3037.2295 4602.0542 7507.3877 13461.8701 | lr 1.9e-04 | norm 3845.7249 | dt 9.819 +type train | step 3698 | loss 95.0303 195.5989 303.9012 490.8154 723.2264 1059.6006 1489.3641 2129.9019 3014.1443 4582.5122 7441.7222 13335.3125 | lr 1.9e-04 | norm 3316.9023 | dt 9.802 +type train | step 3699 | loss 99.4119 207.2787 321.1125 520.7144 772.4869 1131.4052 1588.9807 2275.0872 3204.5239 4826.2656 7780.0479 13800.9082 | lr 1.9e-04 | norm 3416.3225 | dt 9.798 +type train | step 3700 | loss 99.3452 204.3652 315.1480 506.9235 743.6146 1087.1134 1520.5671 2157.8999 3031.1079 4580.4541 7561.7266 13721.9922 | lr 1.9e-04 | norm 4112.2080 | dt 9.796 +type train | step 3701 | loss 100.9257 210.8569 319.6259 514.4393 763.1213 1099.2050 1545.6813 2208.2646 3084.4736 4655.4629 7571.0137 13560.2471 | lr 1.9e-04 | norm 3735.9812 | dt 9.794 +type train | step 3702 | loss 103.8680 214.9166 331.5318 536.6017 788.4069 1148.0320 1608.5217 2292.0168 3227.9368 4888.8174 7950.6636 14211.2256 | lr 1.9e-04 | norm 3751.1414 | dt 9.793 +type train | step 3703 | loss 103.8815 219.2028 330.2030 525.3214 770.9608 1137.9491 1594.4258 2295.4797 3197.8201 4799.4785 7774.5981 13915.1475 | lr 1.9e-04 | norm 4145.9028 | dt 9.803 +type train | step 3704 | loss 97.4065 203.4831 312.6767 502.5734 737.3716 1086.4897 1521.5906 2176.3989 3069.5962 4650.8516 7593.7852 13650.3184 | lr 1.8e-04 | norm 3713.1611 | dt 9.805 +type train | step 3705 | loss 102.6774 213.4929 323.5292 515.4094 758.7908 1099.8400 1539.5594 2200.4939 3081.0972 4654.4922 7618.2246 13759.5342 | lr 1.8e-04 | norm 3606.5659 | dt 9.806 +type train | step 3706 | loss 96.4717 200.2676 308.2858 501.7192 737.2640 1076.2688 1519.6736 2182.5986 3082.8740 4675.7402 7569.7925 13449.6387 | lr 1.8e-04 | norm 3437.4202 | dt 9.799 +type train | step 3707 | loss 101.2222 210.5421 322.9684 521.3088 762.5519 1118.2095 1569.2893 2246.3926 3157.8264 4760.1670 7709.2036 13747.5977 | lr 1.8e-04 | norm 4306.7964 | dt 9.793 +type train | step 3708 | loss 98.8333 213.8958 335.0118 547.7509 808.3525 1156.7241 1598.0978 2250.1001 3143.9204 4709.9229 7675.6724 13757.3369 | lr 1.8e-04 | norm 6376.8115 | dt 9.806 +type train | step 3709 | loss 94.3273 196.6722 304.7234 495.3651 736.8124 1082.4341 1531.3105 2205.8047 3112.3855 4707.3862 7682.3130 13728.4355 | lr 1.8e-04 | norm 3736.4006 | dt 9.795 +type train | step 3710 | loss 105.5230 223.4064 339.4421 550.5090 801.4180 1170.9263 1651.8706 2347.7168 3279.2466 4898.6729 7847.3657 13842.2734 | lr 1.8e-04 | norm 6082.0952 | dt 9.781 +type train | step 3711 | loss 93.7281 199.1128 307.2856 501.0889 750.3942 1086.5842 1539.3422 2199.4871 3117.1084 4706.9121 7572.3188 13502.9385 | lr 1.8e-04 | norm 4889.0801 | dt 9.780 +type train | step 3712 | loss 102.9117 216.3376 334.1036 533.0621 790.3527 1123.5718 1575.3966 2232.8269 3139.9016 4733.3745 7679.7622 13692.4102 | lr 1.8e-04 | norm 4672.1338 | dt 9.787 +type train | step 3713 | loss 97.6194 205.0398 319.4955 516.7364 767.0574 1101.4711 1543.6836 2204.1609 3099.7302 4697.7202 7700.0430 13991.4414 | lr 1.8e-04 | norm 5176.4673 | dt 9.786 +type train | step 3714 | loss 105.2890 220.4636 336.4867 543.0943 820.2618 1148.1892 1603.7639 2282.8059 3220.8313 4900.9902 8023.6064 14397.1963 | lr 1.8e-04 | norm 4973.3892 | dt 9.797 +type train | step 3715 | loss 101.9378 213.9575 328.7328 527.0308 776.2800 1122.0803 1567.1638 2212.9473 3112.1616 4667.1553 7556.8706 13502.0498 | lr 1.8e-04 | norm 3720.5757 | dt 9.807 +type train | step 3716 | loss 104.6160 221.2049 338.5798 547.1206 827.4772 1160.5924 1619.3920 2300.1472 3233.4590 4851.5654 7864.1377 14028.3760 | lr 1.8e-04 | norm 4031.6848 | dt 9.788 +type train | step 3717 | loss 104.8141 222.5718 340.8857 550.2750 839.7797 1161.6450 1624.4713 2297.5076 3215.8960 4851.4209 7929.2583 14296.8281 | lr 1.8e-04 | norm 4786.2642 | dt 9.788 +type train | step 3718 | loss 116.7216 244.8476 371.1754 577.0998 872.6724 1214.5189 1701.3071 2389.3853 3322.4934 4953.3887 7892.6846 13912.5420 | lr 1.8e-04 | norm 4236.8926 | dt 9.783 +type train | step 3719 | loss 107.1260 227.8018 350.9728 565.5363 865.0624 1180.6125 1642.1964 2306.5076 3201.6543 4814.4019 7782.4634 14006.7637 | lr 1.8e-04 | norm 4289.1108 | dt 9.791 +type train | step 3720 | loss 103.8117 218.1583 332.0670 533.9387 821.5278 1134.9923 1588.2217 2250.1936 3158.8491 4766.9873 7747.7446 13905.9736 | lr 1.8e-04 | norm 3429.2551 | dt 9.797 +type train | step 3721 | loss 101.9279 220.7770 348.4382 564.5817 898.1667 1190.6807 1672.0568 2380.3892 3375.6357 5115.0596 8363.9512 15010.0322 | lr 1.8e-04 | norm 8190.7764 | dt 9.786 +type train | step 3722 | loss 105.6118 223.8630 345.8229 547.7908 850.0826 1141.6016 1580.1589 2224.0171 3124.6514 4690.5967 7564.3525 13502.7373 | lr 1.8e-04 | norm 4124.2803 | dt 9.805 +type train | step 3723 | loss 100.0518 209.5846 324.6690 520.1354 832.3608 1113.1393 1557.5449 2211.9038 3103.9851 4681.1611 7649.7944 13715.5996 | lr 1.8e-04 | norm 4395.3892 | dt 10.106 +type train | step 3724 | loss 104.9398 222.9182 355.5621 576.7635 883.6244 1209.3328 1687.2856 2383.7766 3321.6143 5006.1147 8157.4395 14741.8857 | lr 1.8e-04 | norm 5308.5942 | dt 9.787 +type train | step 3725 | loss 101.9442 214.5722 334.2925 541.2761 859.6080 1153.9792 1609.7568 2268.5010 3196.0042 4800.2095 7856.4712 14188.2002 | lr 1.8e-04 | norm 3942.7080 | dt 9.796 +type train | step 3726 | loss 102.4034 217.0048 334.9928 536.1434 858.2693 1139.2095 1605.1830 2277.4690 3200.2278 4842.1885 7938.1069 14340.6064 | lr 1.8e-04 | norm 5107.3525 | dt 9.786 +type train | step 3727 | loss 116.3352 241.9670 368.9576 573.1033 882.5142 1184.1790 1626.4789 2281.3262 3169.2224 4780.8281 7838.5117 14198.5547 | lr 1.8e-04 | norm 7401.4067 | dt 9.782 +type train | step 3728 | loss 110.1557 234.2862 355.4312 563.4103 870.4977 1164.7488 1597.1531 2238.6819 3084.7598 4613.2334 7446.5015 13450.2988 | lr 1.8e-04 | norm 4854.6328 | dt 9.800 +type train | step 3729 | loss 112.8959 237.3786 362.6393 579.5015 906.4192 1213.8008 1696.5015 2394.3386 3331.6055 4977.9517 8035.6357 14396.9707 | lr 1.8e-04 | norm 5536.0645 | dt 9.787 +type train | step 3730 | loss 107.0070 225.7199 342.9359 544.3392 847.5937 1141.2593 1580.3748 2219.3608 3092.2627 4608.3828 7453.5771 13368.9209 | lr 1.8e-04 | norm 3949.9055 | dt 9.790 +type train | step 3731 | loss 104.1113 218.4905 335.7326 537.5023 850.7784 1131.4514 1582.2212 2236.3792 3133.5667 4705.1982 7604.1177 13592.6533 | lr 1.8e-04 | norm 4566.7427 | dt 9.795 +type train | step 3732 | loss 99.8993 212.9569 331.6122 540.2808 857.9795 1162.3185 1627.3699 2305.9626 3234.5916 4856.6240 7879.3677 14125.4209 | lr 1.8e-04 | norm 5110.2671 | dt 9.781 +type train | step 3733 | loss 106.6431 227.3866 345.1273 552.1800 872.8543 1152.8333 1606.2288 2266.0959 3161.8477 4776.0791 7797.3623 14062.5137 | lr 1.8e-04 | norm 4570.4888 | dt 9.797 +type train | step 3734 | loss 102.7535 220.5338 337.5618 542.2621 868.4559 1155.2428 1611.7234 2300.3225 3241.1677 4866.0864 7892.5889 14084.0635 | lr 1.8e-04 | norm 3864.3545 | dt 9.800 +type train | step 3735 | loss 106.6905 228.7280 353.0591 566.4325 891.0411 1200.6667 1671.7108 2368.1685 3300.0229 4918.6694 7992.4600 14355.9297 | lr 1.8e-04 | norm 4817.8350 | dt 9.803 +type train | step 3736 | loss 106.2697 223.8368 341.4260 548.6794 864.6715 1169.3604 1639.1372 2348.5068 3271.3269 4945.0112 8060.6001 14573.0859 | lr 1.8e-04 | norm 4554.8369 | dt 9.795 +type train | step 3737 | loss 102.6660 216.0574 333.4373 534.0798 833.8907 1122.0093 1561.1171 2206.5032 3103.6255 4665.6636 7556.0938 13537.5195 | lr 1.8e-04 | norm 3696.8218 | dt 9.806 +type train | step 3738 | loss 101.8301 213.0602 326.7742 522.9236 842.5187 1111.5062 1555.4226 2210.0132 3099.7966 4675.6665 7598.8315 13680.9111 | lr 1.8e-04 | norm 4474.7544 | dt 9.794 +type train | step 3739 | loss 106.6301 226.0752 345.7233 550.4749 870.7024 1156.9688 1610.0654 2270.1189 3174.5073 4775.2007 7703.9722 13788.4121 | lr 1.8e-04 | norm 4207.8232 | dt 9.807 +type train | step 3740 | loss 105.5012 223.1506 337.2562 537.1187 847.6581 1130.7644 1578.1917 2241.8718 3139.0017 4722.0220 7668.5361 13837.4150 | lr 1.8e-04 | norm 4545.5288 | dt 9.790 +type train | step 3741 | loss 109.5078 232.2855 349.5411 557.5057 890.3970 1185.3030 1654.3453 2341.4150 3253.8018 4871.6118 7932.2095 14348.8574 | lr 1.8e-04 | norm 4111.3486 | dt 9.787 +type train | step 3742 | loss 96.8013 203.6862 314.9699 510.4502 829.4196 1085.8514 1522.6963 2169.3416 3068.9937 4614.8911 7500.2207 13406.0254 | lr 1.8e-04 | norm 4174.3799 | dt 9.810 +type train | step 3743 | loss 106.6440 225.8386 344.3884 548.3145 861.4529 1145.1006 1593.0878 2244.3872 3141.4358 4695.5771 7608.8691 13543.6494 | lr 1.8e-04 | norm 4169.6001 | dt 9.795 +type train | step 3744 | loss 109.2074 231.1212 350.4081 556.8818 863.0087 1153.0490 1589.9930 2236.3142 3113.8044 4694.9604 7603.9653 13637.3145 | lr 1.8e-04 | norm 3576.0933 | dt 9.797 +type train | step 3745 | loss 101.4396 216.5159 334.6101 539.6764 854.2517 1139.5027 1598.4297 2269.2488 3188.9067 4794.5962 7774.6689 13888.5908 | lr 1.8e-04 | norm 4069.1318 | dt 9.792 +type train | step 3746 | loss 109.5428 230.7659 349.9262 556.8474 868.1904 1155.3593 1604.8700 2258.3577 3140.9585 4718.8765 7621.4341 13626.6064 | lr 1.8e-04 | norm 4774.6226 | dt 9.788 +type train | step 3747 | loss 97.9404 206.4241 317.8779 517.7383 828.2668 1120.3033 1572.1376 2251.1499 3176.1289 4753.7632 7706.3096 13743.4951 | lr 1.8e-04 | norm 5498.0454 | dt 9.782 +type train | step 3748 | loss 113.9650 238.5416 362.8906 573.3491 885.1000 1183.9348 1630.6458 2282.5117 3149.2568 4686.1357 7545.8130 13476.0479 | lr 1.8e-04 | norm 4820.2222 | dt 9.789 +type train | step 3749 | loss 105.4377 225.2137 348.4590 558.5836 873.2115 1181.8416 1656.6425 2335.1038 3281.8772 4943.6582 8006.1235 14196.5039 | lr 1.8e-04 | norm 4511.1167 | dt 9.791 +type train | step 3750 | loss 107.9265 229.5223 347.5807 556.2766 876.3394 1166.2332 1620.6534 2291.6309 3198.5857 4827.4224 7865.0850 14230.9844 | lr 1.8e-04 | norm 4254.0293 | dt 9.792 +type train | step 3751 | loss 109.1756 231.2762 350.3483 556.5077 868.9310 1169.0610 1635.1790 2316.6980 3246.0737 4906.4595 8023.3047 14454.7412 | lr 1.8e-04 | norm 6080.6685 | dt 9.786 +type train | step 3752 | loss 100.8066 209.4018 321.8798 521.6277 822.0130 1115.8680 1562.4584 2235.7261 3124.0957 4709.4790 7705.5234 13905.2812 | lr 1.8e-04 | norm 4582.3696 | dt 9.795 +type train | step 3753 | loss 101.2439 213.2956 326.3720 526.0948 842.7940 1122.2106 1574.1454 2236.7454 3133.8218 4690.3857 7549.9663 13407.8252 | lr 1.8e-04 | norm 4036.1230 | dt 9.789 +type train | step 3754 | loss 105.6695 219.1653 339.9408 554.1292 872.9211 1169.9646 1637.5830 2320.6870 3281.4507 4952.5142 8128.6245 14689.5762 | lr 1.8e-04 | norm 5210.8779 | dt 9.787 +type train | step 3755 | loss 101.9388 216.5945 331.0875 529.0088 834.9465 1127.6243 1578.8644 2237.5259 3133.7332 4732.0000 7674.3472 13719.0918 | lr 1.8e-04 | norm 3633.4822 | dt 9.805 +type train | step 3756 | loss 102.1318 215.0791 333.9346 532.1411 838.9733 1125.8572 1572.9072 2225.3135 3109.8315 4696.2402 7650.2290 13746.7266 | lr 1.8e-04 | norm 4353.7144 | dt 9.811 +type train | step 3757 | loss 108.6301 229.5994 345.9041 550.3464 859.2343 1156.5251 1604.1722 2256.1833 3129.4788 4696.4326 7639.4922 13719.8389 | lr 1.8e-04 | norm 3964.1826 | dt 9.787 +type train | step 3758 | loss 104.5603 221.0681 344.7959 557.3154 876.9976 1189.0072 1664.9803 2362.3926 3324.9363 5019.7881 8204.5986 14868.0254 | lr 1.8e-04 | norm 4497.8618 | dt 9.804 +type train | step 3759 | loss 106.6277 227.5562 353.3144 566.8381 883.0178 1202.9271 1667.7501 2385.4578 3338.2920 5069.9033 8260.2402 14866.4033 | lr 1.8e-04 | norm 5458.9585 | dt 9.791 +type train | step 3760 | loss 104.7804 220.6631 338.5965 550.2766 844.0281 1174.2728 1639.0994 2343.4932 3280.4160 4958.1162 8076.2285 14505.6611 | lr 1.8e-04 | norm 4945.5981 | dt 9.782 +type train | step 3761 | loss 101.9812 215.1581 333.0524 539.0728 843.4249 1159.2733 1625.3683 2317.2803 3260.8423 4929.7139 8010.4180 14387.1973 | lr 1.8e-04 | norm 4441.1294 | dt 9.784 +type train | step 3762 | loss 105.9336 227.0923 349.2789 562.2161 871.0269 1193.1204 1667.2180 2368.6040 3296.6838 4973.7441 8124.4390 14638.4404 | lr 1.8e-04 | norm 3820.9846 | dt 9.792 +type train | step 3763 | loss 101.0755 212.7735 327.8647 525.1342 835.7757 1120.0898 1567.5917 2225.9077 3133.8088 4731.4243 7697.5190 13798.8213 | lr 1.8e-04 | norm 3749.2996 | dt 9.796 +type train | step 3764 | loss 113.6707 240.5482 358.7129 565.7975 875.7615 1164.1182 1615.9781 2271.6235 3169.0056 4776.6304 7788.6660 14010.3633 | lr 1.8e-04 | norm 5047.9678 | dt 9.783 +type train | step 3765 | loss 93.8348 197.9951 309.9905 507.1324 813.8351 1121.2262 1598.9585 2309.1060 3268.3013 4968.2534 8050.1348 14357.6455 | lr 1.8e-04 | norm 4767.1680 | dt 9.804 +type train | step 3766 | loss 119.5018 261.7156 391.9897 612.7608 937.8039 1261.1353 1733.9260 2450.4399 3386.2415 5111.5444 8338.3018 14916.8252 | lr 1.8e-04 | norm 7126.3843 | dt 9.787 +type train | step 3767 | loss 103.0815 216.0695 330.4509 528.6354 832.9847 1121.8597 1571.2656 2222.6650 3126.0652 4691.3525 7610.6494 13638.3125 | lr 1.8e-04 | norm 3550.8501 | dt 9.800 +type train | step 3768 | loss 102.4566 218.6005 335.4432 533.9636 834.4137 1126.4348 1575.8674 2223.7505 3125.0972 4697.7085 7635.7471 13693.4785 | lr 1.8e-04 | norm 4040.7131 | dt 9.806 +type train | step 3769 | loss 109.0181 232.2908 352.8809 552.2546 847.6008 1147.3463 1599.4604 2258.0425 3166.2612 4761.3052 7720.3677 13848.4297 | lr 1.8e-04 | norm 5098.2275 | dt 9.806 +type train | step 3770 | loss 104.3489 219.7993 336.0746 532.5143 843.9982 1130.2836 1591.0651 2237.7041 3143.5044 4747.6416 7685.9023 13835.2246 | lr 1.8e-04 | norm 5472.5376 | dt 9.790 +type train | step 3771 | loss 99.8544 214.9043 328.1123 518.5705 818.7249 1097.0829 1546.0895 2198.0022 3090.2937 4688.2246 7666.8726 13849.5645 | lr 1.8e-04 | norm 5636.8760 | dt 9.793 +type train | step 3772 | loss 100.7490 211.5665 329.2400 528.0031 846.6786 1134.4381 1592.6190 2268.8733 3193.3611 4807.9497 7821.4883 14030.9863 | lr 1.8e-04 | norm 4874.7192 | dt 9.806 +type train | step 3773 | loss 106.0953 224.9261 341.9624 542.0244 843.3790 1144.7108 1575.7604 2223.6836 3073.5928 4600.0151 7447.5757 13400.3672 | lr 1.8e-04 | norm 4532.8755 | dt 9.796 +type train | step 3774 | loss 100.5611 213.7803 330.1243 532.2159 831.9906 1124.3210 1569.1455 2216.8284 3124.5408 4699.4561 7625.0820 13627.4863 | lr 1.8e-04 | norm 3466.2573 | dt 9.807 +type train | step 3775 | loss 101.7212 211.3240 327.2191 524.1556 822.4395 1116.4786 1564.3346 2222.6438 3122.8467 4660.5801 7581.7681 13567.8760 | lr 1.8e-04 | norm 3534.8928 | dt 9.796 +type train | step 3776 | loss 102.6637 220.4977 338.3368 540.0481 842.8759 1144.8510 1590.1199 2247.8948 3155.1692 4740.9175 7675.1714 13700.4453 | lr 1.8e-04 | norm 3531.6582 | dt 9.803 +type train | step 3777 | loss 102.4765 215.2335 335.5351 542.4503 841.6807 1140.7493 1591.2344 2240.2795 3137.5972 4688.4214 7647.0718 13643.1660 | lr 1.8e-04 | norm 4160.5376 | dt 9.800 +type train | step 3778 | loss 102.4673 212.8382 326.8550 526.6769 826.0817 1114.1936 1567.2893 2220.0781 3107.7112 4703.2959 7701.2832 13985.2314 | lr 1.8e-04 | norm 4394.6460 | dt 9.788 +type train | step 3779 | loss 97.1168 205.7074 319.7909 519.9559 815.1049 1113.5222 1566.5524 2222.5381 3140.4539 4760.5723 7735.9648 13864.5713 | lr 1.8e-04 | norm 3744.8530 | dt 9.799 +type train | step 3780 | loss 108.2681 231.9090 348.1930 552.2559 855.4467 1160.1188 1616.3911 2276.5806 3177.5410 4751.9902 7662.7471 13654.6855 | lr 1.8e-04 | norm 4065.7571 | dt 9.800 +type train | step 3781 | loss 111.1351 237.7728 366.2087 593.8489 892.5353 1235.7375 1702.8191 2388.5085 3219.5862 4802.5732 7800.8916 14064.3984 | lr 1.8e-04 | norm 8054.1514 | dt 9.772 +type train | step 3782 | loss 102.3522 214.9689 332.9260 538.0282 846.3616 1138.4434 1589.8750 2247.4839 3161.9941 4760.8032 7754.3442 13882.3379 | lr 1.8e-04 | norm 3466.3650 | dt 9.811 +type train | step 3783 | loss 110.2132 231.3708 356.8468 556.5944 880.6833 1187.1288 1659.9777 2364.1414 3289.0876 4957.3994 8052.5635 14541.6436 | lr 1.8e-04 | norm 6152.8730 | dt 9.789 +type train | step 3784 | loss 116.2965 243.7731 363.4303 571.5197 865.4326 1210.7732 1678.1075 2364.9814 3236.8313 4810.2158 7750.6465 13901.8662 | lr 1.8e-04 | norm 5056.2534 | dt 9.789 +type train | step 3785 | loss 115.7115 244.9521 367.6565 575.5549 888.0721 1214.1005 1692.2594 2385.3401 3289.6042 4862.3076 7805.5737 13826.7402 | lr 1.8e-04 | norm 4539.8047 | dt 9.787 +type train | step 3786 | loss 104.8143 222.5314 339.9589 544.3922 839.0228 1143.5383 1592.3416 2245.1619 3125.5752 4655.7661 7530.7778 13483.8779 | lr 1.8e-04 | norm 4280.8916 | dt 9.800 +type train | step 3787 | loss 101.5268 213.5067 325.9160 520.0079 816.8773 1101.6421 1543.7007 2186.1318 3076.0024 4612.5210 7476.6909 13392.0498 | lr 1.8e-04 | norm 3859.1316 | dt 9.795 +type train | step 3788 | loss 100.5824 212.6583 326.2828 524.0383 812.6110 1129.4385 1587.9972 2267.0569 3208.4197 4828.4385 7805.5361 13929.7441 | lr 1.8e-04 | norm 4270.9185 | dt 9.803 +type train | step 3789 | loss 104.3588 219.8510 335.5783 537.2888 831.6400 1137.2758 1589.0844 2249.5129 3147.9548 4742.5215 7739.5327 13892.0557 | lr 1.7e-04 | norm 3642.3999 | dt 9.809 +type train | step 3790 | loss 106.3987 225.9918 342.4587 548.1256 837.0482 1160.1738 1598.7864 2252.9397 3114.4385 4683.1709 7576.0884 13553.5264 | lr 1.7e-04 | norm 5132.5605 | dt 9.788 +type train | step 3791 | loss 104.2803 219.6567 339.5903 550.6908 853.0211 1174.5581 1647.3713 2335.4429 3298.5459 4971.4141 8060.3750 14483.8760 | lr 1.7e-04 | norm 4108.8013 | dt 9.804 +type train | step 3792 | loss 103.9165 221.1454 340.8405 539.6164 831.1775 1124.8312 1568.6273 2195.2874 3058.1284 4563.1504 7419.1807 13347.6104 | lr 1.7e-04 | norm 7227.9165 | dt 9.789 +type train | step 3793 | loss 106.9180 228.0546 347.6292 555.9564 868.6492 1171.3755 1634.0160 2312.8616 3221.6958 4834.5312 7961.4326 14468.3838 | lr 1.7e-04 | norm 6855.1055 | dt 9.802 +type train | step 3794 | loss 95.7784 204.0898 318.3696 515.9697 805.4850 1101.7018 1543.4586 2182.4873 3075.2214 4645.5430 7543.9663 13452.0361 | lr 1.7e-04 | norm 4331.0718 | dt 9.805 +type train | step 3795 | loss 106.8569 226.4445 345.8366 547.6219 844.7631 1146.8237 1591.8179 2238.9443 3137.3799 4704.3579 7618.4707 13597.1475 | lr 1.7e-04 | norm 3638.8232 | dt 9.811 +type train | step 3796 | loss 107.2866 237.0196 370.9785 596.9855 907.1597 1244.5291 1727.1827 2441.1331 3338.8801 5009.1431 8222.1162 15041.7344 | lr 1.7e-04 | norm 9708.9746 | dt 9.774 +type train | step 3797 | loss 100.3965 207.6154 319.7982 514.6202 803.1929 1101.1344 1544.0642 2194.0022 3085.4629 4696.2676 7708.8232 13959.9219 | lr 1.7e-04 | norm 5085.4678 | dt 9.794 +type train | step 3798 | loss 106.2535 223.7363 341.9196 541.9355 844.6110 1143.0375 1599.8208 2265.3550 3180.7993 4757.7744 7677.5425 13700.3379 | lr 1.7e-04 | norm 4224.6626 | dt 9.796 +type train | step 3799 | loss 107.8996 229.8676 349.9785 564.8073 876.9208 1201.4244 1663.9283 2343.3855 3234.9297 4805.9595 7728.0615 13770.6875 | lr 1.7e-04 | norm 4619.5737 | dt 9.794 +type train | step 3800 | loss 106.2176 226.1626 343.9891 551.0021 851.7181 1168.2520 1629.5272 2302.7327 3200.4673 4787.8887 7815.9829 14218.3438 | lr 1.7e-04 | norm 5281.0713 | dt 9.796 +type train | step 3801 | loss 105.6005 224.9817 344.7463 549.1476 846.6979 1166.6108 1630.0082 2302.4387 3223.0149 4861.7485 7905.4980 14149.1318 | lr 1.7e-04 | norm 4220.1372 | dt 9.797 +type train | step 3802 | loss 105.5539 222.6246 339.7489 545.6638 842.8088 1156.1207 1610.2321 2272.9951 3188.9663 4781.4819 7765.7041 13968.0615 | lr 1.7e-04 | norm 3955.5139 | dt 9.782 +type train | step 3803 | loss 102.5328 219.3693 336.6800 539.0018 830.1354 1131.3427 1574.6539 2226.1929 3123.3269 4697.6484 7658.3877 13773.2627 | lr 1.7e-04 | norm 3937.5710 | dt 9.791 +type train | step 3804 | loss 101.5459 214.1394 330.5941 531.3112 815.5269 1130.4418 1577.8691 2243.2480 3150.7366 4760.9858 7786.6982 14008.6172 | lr 1.7e-04 | norm 4226.9375 | dt 9.805 +type train | step 3805 | loss 110.3404 236.3383 353.0717 551.9006 838.4196 1148.5046 1587.1854 2241.0447 3101.7510 4618.7256 7493.7158 13384.6973 | lr 1.7e-04 | norm 3919.6477 | dt 9.788 +type train | step 3806 | loss 108.5902 228.5754 349.3739 553.7520 847.3377 1162.8192 1617.6573 2283.5686 3197.4888 4811.6553 7836.6045 14065.3008 | lr 1.7e-04 | norm 3582.4858 | dt 9.799 +type train | step 3807 | loss 109.4464 233.6440 350.0801 549.4952 842.2253 1142.7262 1594.1343 2249.0476 3117.2327 4732.0586 7711.3892 13964.5771 | lr 1.7e-04 | norm 5334.0747 | dt 9.792 +type train | step 3808 | loss 107.5635 228.2541 347.5701 558.3406 863.1844 1194.7344 1661.4102 2359.2173 3264.6812 4879.0703 7997.4482 14414.6309 | lr 1.7e-04 | norm 4995.7607 | dt 9.780 +type train | step 3809 | loss 105.4784 224.1417 344.1216 546.9990 843.3270 1153.2189 1600.0400 2252.4558 3125.0747 4640.2227 7488.6978 13401.3291 | lr 1.7e-04 | norm 3670.4277 | dt 9.790 +type train | step 3810 | loss 106.8904 228.2820 347.7740 555.7853 850.4181 1162.8530 1620.7715 2281.9233 3173.7991 4752.0762 7686.3403 13714.7451 | lr 1.7e-04 | norm 4056.5486 | dt 9.793 +type train | step 3811 | loss 110.8758 234.8774 359.3560 573.7555 881.8843 1214.6486 1685.3198 2384.7419 3329.2124 4997.8013 8109.6372 14475.6191 | lr 1.7e-04 | norm 4179.2012 | dt 9.794 +type train | step 3812 | loss 103.9961 224.0922 345.3410 551.3251 848.1541 1157.1196 1618.1135 2296.0005 3233.2998 4903.9482 8032.8076 14362.2773 | lr 1.7e-04 | norm 4550.8589 | dt 9.796 +type train | step 3813 | loss 102.5979 220.1131 341.5290 552.2742 858.3462 1165.0447 1624.1124 2284.3101 3207.1245 4783.8755 7755.0166 13850.7871 | lr 1.7e-04 | norm 4583.0195 | dt 9.808 +type train | step 3814 | loss 103.3758 218.3501 336.0554 537.3612 831.0922 1132.9988 1582.3158 2231.3013 3116.1316 4695.9028 7650.6724 13756.8457 | lr 1.7e-04 | norm 3774.2908 | dt 9.811 +type train | step 3815 | loss 102.0193 217.3227 335.7877 536.1874 826.0471 1134.0178 1587.0116 2231.4036 3147.8425 4738.3848 7674.5430 13704.5029 | lr 1.7e-04 | norm 3901.7156 | dt 9.802 +type train | step 3816 | loss 105.0438 223.2188 342.5967 552.8804 854.3187 1179.5447 1645.5812 2331.2302 3249.1160 4877.0918 7978.1787 14371.6084 | lr 1.7e-04 | norm 5456.2402 | dt 9.781 +type train | step 3817 | loss 100.1255 208.3925 319.4295 514.8037 806.5654 1100.0934 1539.4272 2185.8059 3074.5229 4606.9287 7511.9351 13544.4697 | lr 1.7e-04 | norm 4404.0161 | dt 9.785 +type train | step 3818 | loss 98.2439 208.5566 322.8770 519.0048 807.0309 1104.1799 1547.7560 2190.7632 3099.3101 4698.9614 7676.0938 13861.1465 | lr 1.7e-04 | norm 5632.9448 | dt 9.788 +type train | step 3819 | loss 99.2777 210.1555 326.0883 522.4290 809.7532 1110.9082 1556.5342 2198.3452 3105.0999 4677.4819 7620.4360 13800.2051 | lr 1.7e-04 | norm 5023.2153 | dt 9.801 +type train | step 3820 | loss 102.0353 213.2203 329.2747 528.5944 820.4861 1125.6715 1577.2385 2229.3713 3114.9412 4695.7075 7643.6416 13803.5420 | lr 1.7e-04 | norm 3808.0940 | dt 9.804 +type train | step 3821 | loss 100.5033 213.3036 328.6707 534.9240 828.4162 1145.4774 1611.6528 2295.1260 3224.7415 4838.5884 7835.8867 14009.5186 | lr 1.7e-04 | norm 4697.3062 | dt 9.796 +type train | step 3822 | loss 106.3887 223.8787 343.6771 548.8419 835.3500 1153.2562 1604.9379 2271.9451 3160.0068 4733.5649 7707.2681 13797.1738 | lr 1.7e-04 | norm 4333.0874 | dt 9.795 +type train | step 3823 | loss 100.8842 212.7155 327.5829 530.3691 820.8536 1139.4287 1599.7618 2278.2490 3201.8870 4817.5161 7848.5547 14048.8721 | lr 1.7e-04 | norm 3983.8118 | dt 9.798 +type train | step 3824 | loss 99.1845 207.7906 322.0623 514.1495 798.5991 1097.3773 1538.9901 2183.5159 3046.6982 4558.2930 7406.0513 13427.1406 | lr 1.7e-04 | norm 5830.4722 | dt 9.787 +type train | step 3825 | loss 94.2145 199.6037 309.7288 501.6757 791.0972 1082.0859 1529.8882 2178.5940 3107.7439 4708.1221 7681.8003 13805.4473 | lr 1.7e-04 | norm 4093.1602 | dt 9.814 +type train | step 3826 | loss 98.3392 206.9611 317.7324 510.1065 792.1683 1092.2177 1530.5605 2172.7642 3069.0767 4610.6304 7508.6582 13422.4844 | lr 1.7e-04 | norm 3739.9729 | dt 9.801 +type train | step 3827 | loss 102.5558 214.9046 331.5965 532.8251 822.7610 1133.9573 1587.0046 2254.7637 3145.8945 4747.6909 7741.6187 13838.5820 | lr 1.7e-04 | norm 4549.5615 | dt 9.802 +type train | step 3828 | loss 106.6828 225.7943 345.0916 544.4988 834.2404 1135.1357 1580.8490 2228.1621 3132.6077 4696.9268 7651.3994 13869.4551 | lr 1.7e-04 | norm 7115.4595 | dt 9.832 +type train | step 3829 | loss 102.8292 216.4751 331.7061 532.9745 827.8409 1142.1157 1595.3615 2282.9426 3196.3616 4784.0312 7707.3208 13709.3125 | lr 1.7e-04 | norm 3430.7007 | dt 9.792 +type train | step 3830 | loss 109.9372 231.9299 350.2954 562.3743 854.1005 1172.3442 1636.9478 2308.4907 3198.1975 4797.6836 7811.4102 14225.5703 | lr 1.7e-04 | norm 4357.6357 | dt 9.792 +type train | step 3831 | loss 101.3274 217.5209 335.8441 542.1553 837.7389 1153.2184 1608.7817 2275.8892 3198.9062 4817.3633 7870.2788 14046.0635 | lr 1.7e-04 | norm 4211.8320 | dt 9.804 +type train | step 3832 | loss 99.1394 209.8813 324.3337 524.1908 809.8812 1123.8856 1582.7283 2247.4207 3181.9812 4777.1597 7704.6577 13689.4209 | lr 1.7e-04 | norm 3730.4214 | dt 9.798 +type train | step 3833 | loss 106.1850 225.6572 340.0569 541.2318 828.0148 1141.3735 1595.1921 2254.5977 3138.7964 4736.3315 7740.2051 14008.4023 | lr 1.7e-04 | norm 4030.6628 | dt 9.810 +type train | step 3834 | loss 109.1281 230.1212 351.8755 559.3452 854.3527 1179.1204 1636.2092 2302.4092 3217.9956 4839.1226 7878.7842 14193.1924 | lr 1.7e-04 | norm 5332.0283 | dt 9.774 +type train | step 3835 | loss 100.4104 212.7645 329.2673 535.3208 831.9390 1151.9166 1623.7279 2318.7065 3262.9106 4920.5088 7965.6611 14293.2354 | lr 1.7e-04 | norm 4488.1299 | dt 9.801 +type train | step 3836 | loss 101.6804 215.0181 329.7827 534.2534 825.2307 1139.9873 1591.2295 2249.1943 3153.3076 4728.0581 7668.4746 13625.6406 | lr 1.7e-04 | norm 3524.8279 | dt 9.810 +type train | step 3837 | loss 98.8716 210.6381 325.7318 522.8508 812.9579 1121.0054 1577.4661 2242.7288 3133.4546 4720.5371 7665.9619 13610.1387 | lr 1.7e-04 | norm 3747.0825 | dt 9.801 +type train | step 3838 | loss 100.5122 214.5024 329.6176 529.7943 820.2490 1129.1949 1584.0707 2238.2864 3133.9519 4686.9194 7571.7939 13506.7715 | lr 1.7e-04 | norm 3682.4871 | dt 9.784 +type train | step 3839 | loss 102.2323 215.4296 331.5769 529.4102 819.3329 1130.8722 1593.2325 2255.1216 3167.4260 4773.6592 7731.0908 13853.3750 | lr 1.7e-04 | norm 3880.2520 | dt 9.799 +type train | step 3840 | loss 103.7421 217.0644 334.3195 549.8809 836.1313 1172.9165 1640.8373 2351.1650 3285.6086 4911.9175 7988.5479 14294.4248 | lr 1.7e-04 | norm 4870.5234 | dt 9.788 +type train | step 3841 | loss 110.1799 234.4467 355.4646 568.0208 868.8424 1219.0454 1701.5891 2435.0991 3356.2573 5030.1377 8068.8257 14391.1035 | lr 1.7e-04 | norm 6718.2534 | dt 9.787 +type train | step 3842 | loss 104.8329 218.4828 334.7019 533.7200 822.8851 1133.8965 1587.7369 2252.1091 3150.4065 4705.8594 7619.9097 13567.0801 | lr 1.7e-04 | norm 3726.7395 | dt 9.804 +type train | step 3843 | loss 102.1215 214.6006 331.2112 534.0418 818.6926 1122.1425 1563.8806 2208.8130 3108.0425 4666.6445 7535.3979 13425.7607 | lr 1.7e-04 | norm 3712.8267 | dt 9.806 +type train | step 3844 | loss 104.1881 220.5717 341.6586 548.6571 842.6918 1158.8555 1631.9331 2313.4795 3268.7080 4882.5483 7851.4795 13925.9531 | lr 1.7e-04 | norm 5377.2969 | dt 9.803 +type train | step 3845 | loss 100.8104 213.6709 328.1710 527.0809 808.9897 1117.4647 1553.5878 2203.0239 3087.0586 4605.3813 7466.5503 13280.1045 | lr 1.7e-04 | norm 3409.0212 | dt 9.802 +type train | step 3846 | loss 103.8995 218.6015 334.9352 537.4811 827.3054 1146.4375 1605.9209 2269.2122 3167.7424 4746.6060 7714.5352 13802.4434 | lr 1.7e-04 | norm 3811.1831 | dt 9.821 +type train | step 3847 | loss 107.3752 227.7913 345.8019 549.2755 844.2098 1157.9247 1619.5720 2291.4558 3203.4429 4823.2656 7856.1553 14107.8447 | lr 1.7e-04 | norm 4241.2598 | dt 9.798 +type train | step 3848 | loss 98.8528 208.2384 318.2577 513.0908 796.3881 1101.8585 1549.8124 2204.0784 3096.7725 4647.7354 7503.4219 13309.5068 | lr 1.7e-04 | norm 3434.1348 | dt 9.802 +type train | step 3849 | loss 95.4296 200.4452 314.0308 510.3950 792.6647 1099.2041 1553.2485 2209.4521 3126.8311 4749.3184 7826.5898 14045.6729 | lr 1.7e-04 | norm 3908.7893 | dt 9.800 +type train | step 3850 | loss 96.9332 201.7574 312.7841 514.1732 805.5397 1124.5203 1589.2803 2263.9265 3200.3081 4855.3521 8119.2959 14830.2783 | lr 1.7e-04 | norm 9159.5566 | dt 9.790 +type train | step 3851 | loss 105.5842 222.3283 342.4157 543.2177 826.7892 1143.6605 1594.0704 2242.3733 3144.8647 4718.8833 7645.3682 13621.4824 | lr 1.7e-04 | norm 3295.8728 | dt 9.812 +type train | step 3852 | loss 107.3416 228.7081 348.1984 554.1112 849.7408 1166.0845 1624.6973 2281.8206 3170.8228 4744.3647 7675.0254 13810.7031 | lr 1.7e-04 | norm 5524.0518 | dt 9.791 +type train | step 3853 | loss 110.4732 241.6760 365.3416 578.9008 878.9373 1194.6521 1661.6290 2328.9785 3242.1897 4837.9653 7863.8022 13919.2910 | lr 1.7e-04 | norm 5986.2061 | dt 9.803 +type train | step 3854 | loss 102.1850 213.6271 330.1215 526.9738 806.7081 1119.0809 1556.8962 2196.5549 3073.9763 4595.8042 7424.3965 13172.5596 | lr 1.7e-04 | norm 3454.7910 | dt 9.809 +type train | step 3855 | loss 109.1628 230.1636 348.9966 552.8212 848.1454 1166.7644 1644.7571 2332.4597 3262.5779 4898.3975 7917.2559 14230.7012 | lr 1.7e-04 | norm 6552.0405 | dt 9.781 +type train | step 3856 | loss 106.6836 222.0311 337.2565 533.4672 819.2640 1143.9413 1602.1021 2273.7913 3159.6836 4755.5815 7718.2383 13987.1680 | lr 1.7e-04 | norm 4756.7148 | dt 9.793 +type train | step 3857 | loss 97.8921 207.3671 318.6329 515.5703 798.3088 1117.2983 1586.1958 2260.3318 3181.8855 4806.1831 7912.8911 14374.5566 | lr 1.7e-04 | norm 5305.9741 | dt 9.790 +type train | step 3858 | loss 103.1836 216.5635 334.9663 533.2004 821.6479 1128.9495 1578.9944 2231.3027 3132.4268 4734.3188 7717.5586 13940.2607 | lr 1.7e-04 | norm 4327.5317 | dt 9.800 +type train | step 3859 | loss 105.0418 222.4165 343.3954 552.8415 842.2911 1170.8840 1635.8690 2316.4087 3226.0417 4827.7783 7864.7529 14003.8652 | lr 1.7e-04 | norm 3723.0112 | dt 9.805 +type train | step 3860 | loss 110.1805 232.8719 354.9126 561.5735 855.0618 1173.5928 1624.5492 2278.9556 3177.7495 4766.8770 7742.7290 13847.2422 | lr 1.7e-04 | norm 4559.7378 | dt 9.805 +type train | step 3861 | loss 106.0309 225.1109 344.0948 544.4000 832.2022 1175.0439 1639.8962 2335.5320 3256.9600 4853.5171 7828.1680 13858.5547 | lr 1.7e-04 | norm 3955.6599 | dt 9.796 +type train | step 3862 | loss 98.6869 208.2379 321.0763 518.2985 804.2645 1125.4109 1592.2328 2264.1873 3192.9180 4837.3071 7912.4424 14171.5840 | lr 1.7e-04 | norm 4677.9531 | dt 9.789 +type train | step 3863 | loss 107.2467 229.2955 354.6002 566.0774 862.4567 1205.9399 1689.4114 2391.8281 3338.7434 5005.2124 8122.8560 14489.8809 | lr 1.7e-04 | norm 5018.5181 | dt 9.806 +type train | step 3864 | loss 102.2097 214.1437 329.1277 527.2139 812.4434 1117.9993 1573.4265 2213.1343 3107.8481 4648.9785 7574.7876 13598.4424 | lr 1.7e-04 | norm 4655.5664 | dt 9.801 +type train | step 3865 | loss 103.1475 219.3257 337.0448 536.5194 818.5844 1133.6151 1584.2046 2241.2661 3136.1333 4705.4258 7635.6948 13654.7158 | lr 1.7e-04 | norm 3508.4163 | dt 9.800 +type train | step 3866 | loss 97.7244 206.7274 320.4559 518.1147 808.6188 1112.2983 1555.3313 2205.2222 3110.7407 4682.8442 7588.3364 13480.1465 | lr 1.7e-04 | norm 4094.3630 | dt 9.799 +type train | step 3867 | loss 95.6654 198.7507 309.4470 507.8269 788.5178 1102.4419 1548.7412 2208.2354 3093.4778 4669.2993 7649.9233 13743.4082 | lr 1.7e-04 | norm 5032.6343 | dt 9.791 +type train | step 3868 | loss 104.7422 219.0912 334.9144 541.1572 818.5768 1135.8727 1580.6841 2230.6897 3091.2844 4644.5205 7503.3340 13412.3164 | lr 1.7e-04 | norm 6555.9321 | dt 9.790 +type train | step 3869 | loss 100.5978 211.2391 324.9706 522.4215 798.3922 1116.7667 1566.6871 2220.2158 3133.1797 4671.9927 7494.8311 13282.1973 | lr 1.7e-04 | norm 4882.0728 | dt 9.790 +type train | step 3870 | loss 105.0659 220.7367 332.6851 540.5396 821.5040 1158.1260 1618.4987 2312.4824 3226.1829 4837.4297 7902.6455 14183.4502 | lr 1.7e-04 | norm 5526.8467 | dt 9.780 +type train | step 3871 | loss 110.2637 228.9922 350.9827 561.6344 841.6018 1192.5192 1656.9929 2384.7107 3230.8218 4731.1279 7713.7085 13867.9766 | lr 1.7e-04 | norm 9123.9736 | dt 9.734 +type train | step 3872 | loss 116.9908 245.7883 371.7361 589.0172 887.7115 1250.4036 1732.5815 2469.6165 3346.7881 4914.7383 7940.2441 14234.9590 | lr 1.7e-04 | norm 6474.1567 | dt 9.751 +type train | step 3873 | loss 103.6216 217.5599 332.9487 533.8903 822.7688 1133.8685 1589.9453 2254.6011 3174.6155 4755.1987 7712.4365 13737.0088 | lr 1.7e-04 | norm 4427.5225 | dt 9.806 +type train | step 3874 | loss 105.7427 223.3577 339.7024 539.1268 826.0407 1152.7379 1608.7800 2280.0801 3168.9272 4745.1289 7706.1562 13912.1309 | lr 1.7e-04 | norm 5296.8442 | dt 9.800 +type train | step 3875 | loss 101.2759 216.8418 331.8398 530.9534 812.8461 1119.8358 1566.1587 2204.6333 3085.1738 4626.3066 7504.2861 13403.3467 | lr 1.7e-04 | norm 4047.3103 | dt 9.813 +type train | step 3876 | loss 102.5632 223.5525 349.0956 557.7515 855.3660 1161.0984 1628.3586 2294.1360 3274.4919 5002.0225 8241.8418 15002.9277 | lr 1.7e-04 | norm 8454.8887 | dt 9.805 +type train | step 3877 | loss 105.7821 231.7431 354.1863 561.5997 856.6560 1194.8658 1664.9146 2356.0610 3283.8491 4926.9487 8022.5312 14452.1426 | lr 1.7e-04 | norm 7392.8130 | dt 9.784 +type train | step 3878 | loss 105.9987 222.3138 347.3929 555.2507 846.2872 1173.5885 1651.5791 2348.1094 3292.5601 5004.7583 8111.8418 14581.0234 | lr 1.6e-04 | norm 5108.1387 | dt 9.785 +type train | step 3879 | loss 106.9310 227.0186 349.8557 557.6030 858.3821 1178.3730 1643.6210 2319.4297 3254.5435 4933.7383 8017.0107 14372.7305 | lr 1.6e-04 | norm 6084.3633 | dt 9.787 +type train | step 3880 | loss 102.0564 218.0545 338.9396 548.4983 830.6517 1161.3142 1626.7280 2305.6201 3238.9968 4886.3389 7938.1382 14132.4102 | lr 1.6e-04 | norm 5013.3901 | dt 9.792 +type train | step 3881 | loss 103.1286 217.3379 336.4338 536.6572 821.0168 1137.9988 1596.3289 2263.5049 3168.6875 4777.7964 7824.3428 14028.3301 | lr 1.6e-04 | norm 4397.2051 | dt 9.795 +type train | step 3882 | loss 104.3356 220.7100 337.6883 538.3453 819.8821 1143.5659 1595.3251 2248.3298 3145.1343 4701.5249 7642.0117 13646.1885 | lr 1.6e-04 | norm 3784.0854 | dt 9.814 +type train | step 3883 | loss 102.5796 218.2380 334.0157 532.8912 817.1287 1136.9214 1595.2089 2255.4385 3199.7075 4810.1182 7784.6763 13914.2148 | lr 1.6e-04 | norm 4693.4814 | dt 9.810 +type train | step 3884 | loss 97.0962 204.0271 318.4312 512.8977 792.8039 1097.7161 1543.1051 2181.0349 3080.9143 4640.2188 7565.0264 13513.6758 | lr 1.6e-04 | norm 3681.2046 | dt 9.804 +type train | step 3885 | loss 103.5306 227.6781 358.3153 579.0512 883.7792 1234.6512 1746.3530 2512.7505 3533.8870 5434.1455 8872.7910 15897.3291 | lr 1.6e-04 | norm 9816.0010 | dt 9.772 +type train | step 3886 | loss 106.8372 225.4471 345.5511 558.2065 847.7790 1186.3555 1658.7383 2372.1199 3300.2190 4998.4434 8115.1260 14541.0742 | lr 1.6e-04 | norm 6200.5503 | dt 9.778 +type train | step 3887 | loss 99.8242 210.5534 323.0124 516.3500 799.2150 1101.3035 1539.4507 2177.4839 3072.6721 4615.0415 7479.0791 13288.9922 | lr 1.6e-04 | norm 3538.7258 | dt 9.799 +type train | step 3888 | loss 102.4839 219.2360 335.0815 532.3253 812.3427 1116.1656 1557.3020 2190.7002 3077.1069 4625.3467 7546.9272 13578.1504 | lr 1.6e-04 | norm 3648.3940 | dt 9.805 +type train | step 3889 | loss 106.2606 224.6852 342.0587 541.8658 825.5167 1145.8176 1597.8772 2249.9922 3145.2942 4733.2852 7702.4585 13794.6377 | lr 1.6e-04 | norm 4329.7798 | dt 9.799 +type train | step 3890 | loss 101.7884 215.6959 330.5652 529.0853 820.3342 1132.4739 1592.0327 2247.8726 3195.9719 4799.8071 7724.3667 13613.6104 | lr 1.6e-04 | norm 4166.6768 | dt 9.819 +type train | step 3891 | loss 99.2224 215.2277 334.6171 543.3754 837.9695 1155.6696 1616.7867 2286.0583 3239.2393 4913.1147 8076.4365 14414.5928 | lr 1.6e-04 | norm 5159.4507 | dt 9.813 +type train | step 3892 | loss 107.6993 229.8799 355.3192 565.2100 851.0535 1202.8684 1670.8721 2351.6663 3210.2815 4748.6221 7664.5088 13731.4346 | lr 1.6e-04 | norm 7792.1768 | dt 9.787 +type train | step 3893 | loss 104.0944 220.0158 338.7920 544.2350 832.9183 1151.8669 1612.0559 2276.2107 3210.2549 4841.7583 7874.0024 14114.5762 | lr 1.6e-04 | norm 3853.5503 | dt 9.806 +type train | step 3894 | loss 101.8890 217.8213 338.0279 539.2786 821.2840 1137.7275 1600.8359 2258.5659 3188.5811 4787.4985 7733.7090 13769.4062 | lr 1.6e-04 | norm 3809.5879 | dt 9.801 +type train | step 3895 | loss 109.2883 239.4174 373.3855 585.5291 905.3212 1268.5365 1753.9534 2492.4773 3476.8025 5220.7515 8508.4893 15212.8936 | lr 1.6e-04 | norm 6882.7236 | dt 9.791 +type train | step 3896 | loss 99.9537 212.7520 328.9860 524.9642 803.6395 1113.0802 1562.0465 2208.6997 3111.8555 4684.1309 7619.4126 13603.3516 | lr 1.6e-04 | norm 3891.9863 | dt 9.819 +type train | step 3897 | loss 102.9874 219.8733 337.5100 537.5834 820.1387 1136.5325 1585.5963 2235.7896 3144.4500 4734.3325 7652.8120 13568.2002 | lr 1.6e-04 | norm 3382.8127 | dt 9.808 +type train | step 3898 | loss 94.1283 199.5630 311.0872 502.3230 777.1427 1089.3561 1539.7196 2191.3242 3105.8276 4667.0903 7539.3530 13404.7324 | lr 1.6e-04 | norm 3602.4299 | dt 9.815 +type train | step 3899 | loss 121.7093 255.7132 375.0356 587.3472 880.3944 1224.1843 1709.7761 2405.6528 3328.3401 4948.1851 7925.6401 13892.5596 | lr 1.6e-04 | norm 3833.8203 | dt 9.802 +type train | step 3900 | loss 110.0231 232.1313 354.3353 558.0911 840.5884 1163.1248 1620.1543 2288.1616 3211.7090 4793.5688 7698.7021 13648.4023 | lr 1.6e-04 | norm 5407.6455 | dt 9.798 +type train | step 3901 | loss 108.8152 231.5568 351.4314 553.7461 838.7113 1168.0200 1625.1418 2299.1738 3194.3132 4857.1538 7972.5762 14521.6445 | lr 1.6e-04 | norm 5923.9253 | dt 9.798 +type train | step 3902 | loss 97.1509 205.5502 317.7515 509.0948 780.7916 1086.9325 1527.1935 2173.2415 3070.1252 4628.5825 7539.8755 13360.9297 | lr 1.6e-04 | norm 3217.0974 | dt 9.814 +type train | step 3903 | loss 106.7313 224.8982 347.0236 555.7929 841.8201 1172.8833 1636.3759 2303.9907 3199.5630 4793.0742 7760.4512 13876.9727 | lr 1.6e-04 | norm 3933.3904 | dt 9.787 +type train | step 3904 | loss 101.3634 214.5355 329.3714 536.4780 822.9849 1160.8674 1633.2111 2327.0491 3293.7432 5020.5669 8204.4648 14983.4297 | lr 1.6e-04 | norm 8404.5293 | dt 9.795 +type train | step 3905 | loss 100.9304 214.6948 327.4375 521.3190 800.5594 1110.9523 1561.2494 2210.0410 3119.5845 4692.8350 7605.5566 13487.0332 | lr 1.6e-04 | norm 3790.2883 | dt 9.806 +type train | step 3906 | loss 107.0067 225.6879 340.9184 542.5369 819.8208 1147.3955 1602.7378 2271.9485 3172.8748 4783.0137 7814.4067 13928.6328 | lr 1.6e-04 | norm 4421.6455 | dt 9.781 +type train | step 3907 | loss 95.1486 203.1786 319.8769 518.2025 803.5375 1126.6951 1597.3281 2278.5503 3240.6394 4876.2021 7906.4868 14108.9580 | lr 1.6e-04 | norm 5401.7710 | dt 9.817 +type train | step 3908 | loss 105.3549 223.7855 339.1390 539.7792 819.1083 1150.3003 1606.6727 2278.1992 3176.5735 4767.6338 7672.7666 13695.5029 | lr 1.6e-04 | norm 3937.9280 | dt 9.797 +type train | step 3909 | loss 98.0074 209.4180 329.9550 534.5106 828.2966 1136.1877 1598.2260 2267.7778 3217.5696 4882.6953 8014.0327 14317.1445 | lr 1.6e-04 | norm 4585.8887 | dt 9.801 +type train | step 3910 | loss 99.4613 211.9315 327.3617 523.7916 803.9852 1131.8911 1591.7047 2270.6145 3184.8347 4783.1743 7732.9399 13784.0938 | lr 1.6e-04 | norm 3694.1016 | dt 9.799 +type train | step 3911 | loss 97.0665 202.0867 314.6030 506.7639 787.1641 1091.3278 1542.8409 2198.1255 3110.1174 4714.7495 7646.4844 13676.7158 | lr 1.6e-04 | norm 3874.2903 | dt 9.788 +type train | step 3912 | loss 110.2993 238.6028 358.1255 552.7580 836.2386 1147.0465 1597.3074 2242.7515 3113.2844 4618.1313 7421.6499 13082.0381 | lr 1.6e-04 | norm 4506.9312 | dt 9.797 +type train | step 3913 | loss 101.8314 216.4069 334.0961 533.6326 825.1147 1139.7291 1592.1666 2252.6001 3152.8804 4735.7632 7672.5156 13660.5273 | lr 1.6e-04 | norm 3695.3860 | dt 9.802 +type train | step 3914 | loss 101.1122 215.5758 334.4694 542.4816 844.7164 1180.3026 1660.3687 2362.8091 3318.4026 4989.1821 8098.5229 14515.9238 | lr 1.6e-04 | norm 4312.3716 | dt 9.805 +type train | step 3915 | loss 101.6495 213.8612 328.3538 523.9852 810.2301 1127.8948 1587.3204 2255.4197 3163.6763 4764.8101 7701.0322 13774.0000 | lr 1.6e-04 | norm 4047.5947 | dt 9.808 +type train | step 3916 | loss 101.5927 216.2888 332.3548 527.7834 806.4509 1118.2009 1569.0804 2219.9871 3129.9312 4707.5220 7624.5610 13552.4131 | lr 1.6e-04 | norm 3749.2642 | dt 9.794 +type train | step 3917 | loss 99.0880 207.6572 320.4122 513.2330 784.6898 1095.5819 1539.2936 2172.1462 3058.3853 4600.4346 7423.5674 13145.4648 | lr 1.6e-04 | norm 3228.6099 | dt 9.796 +type train | step 3918 | loss 102.4582 215.6479 329.4885 524.0184 801.2972 1119.5992 1564.0328 2206.2661 3084.4792 4614.2534 7536.5850 13517.2988 | lr 1.6e-04 | norm 3864.2510 | dt 9.802 +type train | step 3919 | loss 94.2004 198.6233 310.0350 507.8560 787.0078 1107.6869 1565.2477 2227.0659 3118.4089 4723.1445 7719.3911 13921.4072 | lr 1.6e-04 | norm 4869.2446 | dt 9.793 +type train | step 3920 | loss 99.6137 210.4023 320.4427 515.0527 795.3173 1111.6764 1559.5895 2225.2080 3139.8789 4704.5742 7650.0366 13615.9316 | lr 1.6e-04 | norm 3768.3621 | dt 9.816 +type train | step 3921 | loss 96.5717 201.9777 316.4481 512.4467 790.0042 1098.2166 1546.6971 2204.7891 3095.8101 4648.5732 7586.8701 13550.2480 | lr 1.6e-04 | norm 3785.8601 | dt 9.807 +type train | step 3922 | loss 93.9374 197.2455 307.1335 498.5881 775.7703 1085.6765 1537.4558 2199.0210 3130.7368 4755.6807 7783.0005 13993.5059 | lr 1.6e-04 | norm 4142.3389 | dt 9.803 +type train | step 3923 | loss 96.6721 204.2754 316.4651 520.1842 795.8616 1111.3601 1568.4524 2224.5984 3145.9319 4742.2935 7685.8569 13600.6494 | lr 1.6e-04 | norm 4204.5425 | dt 9.807 +type train | step 3924 | loss 96.2624 202.5128 311.6249 499.8220 766.3058 1071.9978 1511.4135 2143.4133 3027.3718 4564.3242 7434.4336 13295.1758 | lr 1.6e-04 | norm 3993.5244 | dt 9.796 +type train | step 3925 | loss 103.4152 219.5414 334.2612 531.7805 810.3994 1139.1497 1601.8386 2275.3250 3187.1926 4795.0186 7819.6265 13995.4707 | lr 1.6e-04 | norm 3916.8247 | dt 9.787 +type train | step 3926 | loss 115.3560 247.2346 369.4576 576.5227 865.3577 1234.0156 1720.3199 2463.5952 3363.3003 4963.2705 8011.6060 14301.4375 | lr 1.6e-04 | norm 5469.4380 | dt 9.775 +type train | step 3927 | loss 95.1613 198.1881 309.1365 504.6428 781.0839 1090.5620 1550.7183 2224.9619 3157.4019 4799.2266 7803.8760 13852.5039 | lr 1.6e-04 | norm 4374.1982 | dt 9.786 +type train | step 3928 | loss 83.6277 175.7106 280.5800 470.9796 758.6212 1081.9883 1565.9064 2275.6946 3259.1731 5037.4946 8125.4722 14518.1172 | lr 1.6e-04 | norm 7309.6543 | dt 9.767 +type train | step 3929 | loss 102.1222 213.6816 329.1139 525.3585 802.7662 1123.5460 1573.3912 2228.6851 3117.6250 4649.5029 7515.9116 13350.6133 | lr 1.6e-04 | norm 3562.7146 | dt 9.795 +type train | step 3930 | loss 95.6444 200.7049 312.8194 499.0468 770.7662 1075.0837 1516.7231 2160.4985 3048.7656 4578.1836 7413.8389 13165.8877 | lr 1.6e-04 | norm 3603.6248 | dt 9.791 +type train | step 3931 | loss 93.1222 195.5346 306.7786 499.0363 776.4442 1087.6775 1545.4244 2212.8970 3143.5020 4741.9961 7690.5664 13639.4443 | lr 1.6e-04 | norm 3529.6572 | dt 9.812 +type train | step 3932 | loss 105.2965 223.6837 340.7178 539.6606 819.3652 1143.0751 1595.0226 2252.5256 3148.1433 4716.2207 7635.2866 13557.6162 | lr 1.6e-04 | norm 3218.6550 | dt 9.794 +type train | step 3933 | loss 112.0035 238.3457 360.7615 572.4348 861.3651 1214.9707 1705.7769 2423.6450 3364.3333 4964.1416 7978.0737 14089.0527 | lr 1.6e-04 | norm 6161.7515 | dt 9.786 +type train | step 3934 | loss 107.8989 228.4864 348.7557 560.3904 852.1501 1195.4492 1662.5610 2341.8154 3299.2761 4912.6104 7850.9634 13874.3457 | lr 1.6e-04 | norm 6445.8286 | dt 9.786 +type train | step 3935 | loss 103.6843 221.7380 337.5633 535.2557 816.3427 1146.3081 1602.4292 2265.9358 3193.0371 4791.8066 7713.1836 13709.6934 | lr 1.6e-04 | norm 3805.7009 | dt 9.790 +type train | step 3936 | loss 99.8872 210.5317 325.8530 528.1292 807.8272 1155.4349 1633.2754 2330.8806 3240.7671 4878.2783 7918.2754 14148.5928 | lr 1.6e-04 | norm 5050.1182 | dt 9.770 +type train | step 3937 | loss 106.4780 224.1612 344.1348 546.1870 821.2635 1151.1549 1607.3368 2265.4548 3140.8718 4712.6392 7629.4746 13567.1709 | lr 1.6e-04 | norm 4319.3550 | dt 9.786 +type train | step 3938 | loss 101.7617 213.9805 328.3784 521.7463 794.4257 1114.0862 1561.0176 2205.6284 3087.9419 4628.3657 7517.0522 13361.2549 | lr 1.6e-04 | norm 3532.7197 | dt 9.795 +type train | step 3939 | loss 93.4235 197.9881 308.3710 495.9612 766.6138 1087.3772 1552.4082 2227.9541 3152.4204 4822.6064 7905.9409 14225.6318 | lr 1.6e-04 | norm 4721.1152 | dt 9.784 +type train | step 3940 | loss 98.7018 206.3033 320.5125 517.5416 795.7068 1123.2638 1589.8263 2268.5364 3196.1108 4832.5732 7852.0752 14035.7314 | lr 1.6e-04 | norm 4403.4683 | dt 9.800 +type train | step 3941 | loss 94.5531 202.0821 315.4219 516.6675 804.1077 1136.7878 1608.6018 2311.4341 3254.1252 4919.0615 7952.3931 14056.3916 | lr 1.6e-04 | norm 4490.8433 | dt 9.804 +type train | step 3942 | loss 109.4436 229.2366 350.8036 556.8580 847.6673 1177.8350 1642.2489 2337.2520 3218.3799 4828.0796 7863.8350 14166.2588 | lr 1.6e-04 | norm 5351.1191 | dt 9.789 +type train | step 3943 | loss 92.7285 200.3060 314.3650 511.0825 790.4088 1098.3040 1557.6072 2222.5237 3152.4314 4800.4961 7837.5977 14062.4932 | lr 1.6e-04 | norm 4589.1167 | dt 9.798 +type train | step 3944 | loss 103.2434 217.3119 332.8403 530.2399 804.7788 1139.5037 1600.1594 2269.5127 3162.4014 4733.4326 7643.1426 13563.4209 | lr 1.6e-04 | norm 3888.5764 | dt 9.795 +type train | step 3945 | loss 97.4462 205.2637 316.0356 506.6989 783.4949 1097.6686 1557.0796 2215.2700 3137.2068 4740.0488 7702.8887 13804.9961 | lr 1.6e-04 | norm 4985.3857 | dt 9.793 +type train | step 3946 | loss 103.0152 217.8723 335.2836 540.6264 820.2623 1149.0175 1604.6449 2269.8684 3154.1743 4744.4814 7738.7803 13822.8330 | lr 1.6e-04 | norm 3947.7031 | dt 9.802 +type train | step 3947 | loss 120.4631 263.6327 399.8406 633.1794 933.1369 1311.2517 1781.5334 2489.0688 3409.9517 5057.7236 8090.3521 14557.4678 | lr 1.6e-04 | norm 5242.7827 | dt 9.763 +type train | step 3948 | loss 101.3318 215.7056 334.6409 538.1289 818.9132 1149.8551 1615.1313 2288.9153 3211.3530 4828.3154 7840.0840 13987.4531 | lr 1.6e-04 | norm 4264.7891 | dt 9.804 +type train | step 3949 | loss 106.7276 222.5727 341.9379 540.5317 813.5157 1149.4352 1609.6831 2278.4270 3182.0254 4803.7617 7806.8101 13892.2314 | lr 1.6e-04 | norm 4849.7314 | dt 9.783 +type train | step 3950 | loss 97.5329 205.9026 317.6832 510.8456 782.1329 1089.4712 1532.1416 2163.8977 3049.3486 4569.5586 7386.4272 13117.4844 | lr 1.6e-04 | norm 4088.0854 | dt 9.815 +type train | step 3951 | loss 97.2894 203.0882 313.1147 500.5272 773.3610 1084.2126 1527.0673 2176.0383 3071.8005 4637.7368 7519.3696 13337.4463 | lr 1.6e-04 | norm 3388.5500 | dt 9.814 +type train | step 3952 | loss 103.2189 219.3196 335.5720 533.3223 806.8024 1131.3755 1586.5107 2247.0876 3138.9094 4708.2383 7643.9204 13609.8477 | lr 1.6e-04 | norm 3461.4351 | dt 9.799 +type train | step 3953 | loss 102.1268 218.3628 331.6288 526.5985 800.5604 1117.5814 1568.5743 2227.8105 3123.1460 4719.2129 7734.8208 13869.2578 | lr 1.6e-04 | norm 4102.9287 | dt 9.799 +type train | step 3954 | loss 105.9176 223.6943 341.0417 543.4802 823.5815 1159.3259 1625.8689 2295.4487 3220.6973 4795.1191 7720.6963 13656.2930 | lr 1.6e-04 | norm 4040.6147 | dt 9.800 +type train | step 3955 | loss 101.8581 219.2087 339.1815 544.6177 824.7122 1155.9232 1613.9912 2272.1621 3194.3557 4823.4795 7857.1089 14153.6641 | lr 1.6e-04 | norm 4404.1318 | dt 9.814 +type train | step 3956 | loss 102.6623 219.6353 339.2186 537.7476 820.4305 1139.1812 1597.4708 2253.4578 3152.4980 4743.1699 7776.6021 13900.8525 | lr 1.6e-04 | norm 3939.7322 | dt 9.793 +type train | step 3957 | loss 105.3798 226.5093 345.4791 547.0521 826.0764 1153.5322 1616.5707 2280.4077 3181.5774 4769.5181 7739.3975 13771.4883 | lr 1.6e-04 | norm 3452.1536 | dt 9.818 +type train | step 3958 | loss 110.6420 232.8505 353.6264 557.3373 835.5587 1159.7975 1613.7108 2261.7808 3118.4167 4650.8652 7547.2578 13362.8838 | lr 1.6e-04 | norm 3771.7954 | dt 9.795 +type train | step 3959 | loss 111.4539 236.1561 352.3287 562.9319 850.7062 1189.4374 1654.7485 2326.3989 3201.4194 4760.5796 7713.9780 13755.5547 | lr 1.6e-04 | norm 5104.9888 | dt 9.797 +type train | step 3960 | loss 101.4376 215.0120 329.6245 527.9251 801.5157 1121.9907 1570.2391 2227.0698 3141.5586 4741.0273 7719.1265 13687.8848 | lr 1.6e-04 | norm 3457.1292 | dt 9.797 +type train | step 3961 | loss 97.0195 202.4132 316.5699 519.6298 798.5056 1105.8367 1561.7058 2213.1982 3098.3835 4630.7017 7647.3447 13775.4590 | lr 1.6e-04 | norm 7576.7881 | dt 9.785 +type train | step 3962 | loss 104.0719 219.6949 338.6224 534.5802 810.4226 1125.7263 1571.9520 2209.6582 3097.0249 4659.8467 7559.2734 13415.2334 | lr 1.6e-04 | norm 3438.5522 | dt 9.800 +type train | step 3963 | loss 100.4156 211.0665 325.7523 518.2726 791.1592 1101.9895 1548.1190 2208.1770 3108.0422 4661.3467 7593.3857 13492.4141 | lr 1.6e-04 | norm 3922.7329 | dt 9.799 +type train | step 3964 | loss 101.0523 210.7946 329.6834 526.6487 806.4210 1130.6847 1593.8884 2263.2805 3178.9009 4821.1069 7863.5474 14018.6279 | lr 1.6e-04 | norm 5858.0972 | dt 9.823 +type train | step 3965 | loss 104.4601 220.5489 337.8948 534.8550 814.9157 1127.4579 1576.9249 2220.6328 3126.8323 4716.9204 7643.3633 13573.9062 | lr 1.6e-04 | norm 3666.7434 | dt 9.796 +type train | step 3966 | loss 97.2461 206.6644 318.1089 508.7052 778.7135 1090.2863 1541.3641 2185.8391 3077.1680 4635.9526 7480.3584 13283.0928 | lr 1.6e-04 | norm 3366.9651 | dt 9.818 +type train | step 3967 | loss 107.8185 225.0033 340.0005 532.8903 813.9827 1129.2429 1586.8503 2223.8074 3122.9714 4674.2588 7550.3125 13411.2510 | lr 1.6e-04 | norm 5311.2656 | dt 9.813 +type train | step 3968 | loss 102.4828 214.2457 328.7270 524.0579 794.7249 1111.2184 1559.9510 2201.3687 3061.4282 4587.2939 7458.8745 13321.3867 | lr 1.6e-04 | norm 3574.6711 | dt 9.822 +type train | step 3969 | loss 100.7874 213.9223 331.2198 525.2698 801.9969 1113.5046 1553.9707 2190.6716 3077.9868 4613.5361 7444.1650 13146.0293 | lr 1.6e-04 | norm 3087.1013 | dt 9.824 +type train | step 3970 | loss 103.4342 220.7644 336.9422 536.5620 819.8149 1138.6327 1605.0974 2284.7708 3219.9636 4871.3813 7962.6982 14386.1416 | lr 1.6e-04 | norm 4401.4487 | dt 9.797 +type train | step 3971 | loss 104.5611 219.5074 336.7503 537.1665 819.9243 1152.2485 1608.6915 2280.8684 3207.9917 4814.5869 7808.6313 13894.9424 | lr 1.6e-04 | norm 3898.5564 | dt 9.807 +type train | step 3972 | loss 105.6494 222.8263 338.4588 553.5790 826.8058 1164.2188 1628.9915 2295.1746 3156.9409 4674.3018 7513.9390 13407.2549 | lr 1.6e-04 | norm 5195.2109 | dt 9.777 +type train | step 3973 | loss 100.1485 211.5532 326.2810 526.3677 812.1276 1159.0479 1632.9315 2338.6648 3269.0996 4906.7520 7868.4067 13963.1309 | lr 1.5e-04 | norm 4715.3301 | dt 9.784 +type train | step 3974 | loss 103.7161 221.0125 335.0890 532.4264 802.7281 1124.3953 1570.8687 2208.7974 3060.8972 4568.6172 7406.3975 13140.7002 | lr 1.5e-04 | norm 3235.7539 | dt 9.798 +type train | step 3975 | loss 102.4724 219.0577 332.2689 526.0706 794.3643 1107.1396 1553.5389 2191.8516 3085.2437 4658.1719 7606.4971 13547.1836 | lr 1.5e-04 | norm 3178.2820 | dt 9.813 +type train | step 3976 | loss 100.5500 212.3584 326.9198 523.9875 797.1942 1111.3354 1557.1582 2206.1003 3100.8699 4667.4209 7593.9917 13424.8730 | lr 1.5e-04 | norm 3228.8513 | dt 9.796 +type train | step 3977 | loss 109.2223 231.3451 354.3576 561.4370 837.7773 1176.3467 1636.1958 2288.6270 3162.3176 4710.1377 7614.3130 13512.8242 | lr 1.5e-04 | norm 4184.6777 | dt 9.796 +type train | step 3978 | loss 101.2185 214.5122 324.4711 520.9398 789.6352 1119.3589 1579.3876 2254.6814 3143.8433 4682.8081 7501.7695 13271.4062 | lr 1.5e-04 | norm 3691.4797 | dt 9.793 +type train | step 3979 | loss 100.9012 214.8006 330.1802 525.7089 801.0892 1117.7314 1568.8440 2207.0261 3073.5532 4645.7427 7527.5439 13396.3701 | lr 1.5e-04 | norm 4256.7402 | dt 9.786 +type train | step 3980 | loss 108.7730 229.0850 348.0362 552.8834 831.9134 1161.7743 1619.0018 2289.4500 3181.5439 4788.0439 7791.5967 13928.7998 | lr 1.5e-04 | norm 4027.5879 | dt 9.793 +type train | step 3981 | loss 99.2889 209.0958 325.8411 527.2532 804.8015 1139.4181 1597.7871 2278.7625 3197.4844 4798.2310 7791.3037 13873.0469 | lr 1.5e-04 | norm 3888.7119 | dt 9.789 +type train | step 3982 | loss 105.4436 224.7188 340.4430 540.4465 810.2454 1141.9625 1602.4202 2261.0032 3133.1768 4697.2100 7598.8667 13507.1455 | lr 1.5e-04 | norm 3701.8665 | dt 9.788 +type train | step 3983 | loss 103.2442 216.9521 330.0409 535.6158 813.6791 1149.6677 1617.4308 2289.5740 3214.5640 4804.6157 7735.4497 13726.6377 | lr 1.5e-04 | norm 3713.0044 | dt 9.794 +type train | step 3984 | loss 95.9414 203.5117 317.2212 511.3511 781.9708 1103.9229 1566.0405 2235.3970 3161.1523 4776.3594 7761.9077 13822.5186 | lr 1.5e-04 | norm 3611.4138 | dt 9.790 +type train | step 3985 | loss 101.7029 214.0072 328.2658 525.1752 794.5206 1133.3770 1596.2867 2283.4355 3185.0669 4774.2241 7733.5845 13601.0186 | lr 1.5e-04 | norm 3573.6816 | dt 9.784 +type train | step 3986 | loss 108.5400 229.3467 345.2722 544.4734 818.2901 1149.1571 1603.7415 2261.6284 3134.4651 4707.7930 7644.0781 13677.7529 | lr 1.5e-04 | norm 3973.6465 | dt 9.784 +type train | step 3987 | loss 91.9286 183.9714 285.6475 457.9193 703.5927 1016.0648 1439.8424 2073.2622 2933.8152 4347.2021 6961.1572 12307.3721 | lr 1.5e-04 | norm 9668.1572 | dt 9.760 +type train | step 3988 | loss 97.3432 203.8357 316.4272 509.0894 782.1002 1110.1206 1565.2939 2220.8389 3125.3792 4672.2422 7592.5791 13415.2051 | lr 1.5e-04 | norm 3342.5515 | dt 9.789 +type train | step 3989 | loss 95.8481 204.9064 317.0796 515.1634 791.9786 1108.2241 1565.0701 2211.8167 3112.1096 4678.3105 7633.2329 13511.2363 | lr 1.5e-04 | norm 3402.4526 | dt 9.798 +type train | step 3990 | loss 99.5317 208.9969 324.7044 521.3063 794.3522 1135.2664 1603.2717 2294.6970 3225.9429 4850.2598 7877.9434 14009.1504 | lr 1.5e-04 | norm 4116.0405 | dt 9.789 +type train | step 3991 | loss 98.7252 210.0967 324.2446 521.7625 799.1639 1119.8757 1575.2533 2225.8132 3140.7051 4749.0205 7760.1299 13780.1963 | lr 1.5e-04 | norm 3381.1492 | dt 9.798 +type train | step 3992 | loss 99.2634 208.8601 321.2999 511.4760 785.1543 1090.1930 1535.6427 2174.2954 3070.6960 4632.0151 7552.2573 13544.1357 | lr 1.5e-04 | norm 3953.5071 | dt 9.814 +type train | step 3993 | loss 98.0123 208.7902 322.0534 515.3358 785.8850 1103.2092 1554.0067 2206.0552 3129.1448 4709.5376 7650.5396 13466.5361 | lr 1.5e-04 | norm 3369.8779 | dt 9.798 +type train | step 3994 | loss 104.1004 220.0978 336.2440 531.8740 806.8066 1137.6383 1600.4376 2269.5471 3156.4771 4758.1870 7756.3486 13857.1426 | lr 1.5e-04 | norm 4082.3992 | dt 9.798 +type train | step 3995 | loss 115.7379 246.4067 372.3510 587.6944 872.8091 1221.0433 1710.7808 2392.6060 3278.5002 4885.2002 7939.0615 14265.7500 | lr 1.5e-04 | norm 6605.1333 | dt 9.782 +type train | step 3996 | loss 106.0137 224.4055 340.4314 539.1533 815.2438 1140.5470 1596.8984 2247.3218 3141.0081 4703.3267 7622.1782 13520.3047 | lr 1.5e-04 | norm 3603.3792 | dt 9.782 +type train | step 3997 | loss 103.2960 215.6379 331.0779 529.7990 808.2974 1129.4882 1584.6510 2237.9536 3132.3779 4714.6431 7684.9761 13731.8145 | lr 1.5e-04 | norm 3999.2437 | dt 9.800 +type train | step 3998 | loss 97.4091 206.2427 322.4775 519.3431 789.5952 1108.6927 1563.0586 2224.3237 3135.8701 4745.4126 7733.5400 13724.7627 | lr 1.5e-04 | norm 3245.7922 | dt 9.799 +type train | step 3999 | loss 89.9803 189.2884 295.8261 486.1885 752.5883 1073.6135 1530.3126 2198.8896 3128.0352 4732.4536 7624.6152 13560.3535 | lr 1.5e-04 | norm 4337.7358 | dt 9.794 +type train | step 4000 | loss 100.3757 210.9351 325.6488 526.5268 801.2264 1123.1747 1569.1450 2219.8440 3120.0400 4685.5234 7615.1211 13526.4189 | lr 1.5e-04 | norm 3247.9189 | dt 9.794 +type train | step 4001 | loss 109.8615 227.3906 349.5038 558.6437 837.1852 1173.4988 1637.0566 2309.6699 3171.7349 4751.3623 7683.8496 13739.0771 | lr 1.5e-04 | norm 4452.0684 | dt 9.780 +type train | step 4002 | loss 106.1465 224.4214 337.5710 532.1510 799.8292 1124.1364 1574.0175 2230.9836 3110.0132 4647.5078 7505.0044 13236.7598 | lr 1.5e-04 | norm 3842.6316 | dt 9.788 +type train | step 4003 | loss 106.8204 228.8745 345.6881 544.0515 816.8764 1147.0458 1599.8312 2242.4399 3117.8828 4668.9346 7511.4521 13222.8262 | lr 1.5e-04 | norm 4275.9082 | dt 9.786 +type train | step 4004 | loss 106.8507 225.5415 342.9371 546.5623 823.0806 1160.7209 1621.2073 2283.1284 3163.8572 4727.2974 7702.7510 13651.5654 | lr 1.5e-04 | norm 3616.2129 | dt 9.785 +type train | step 4005 | loss 100.1228 211.9066 334.7555 535.3560 818.9572 1137.8519 1593.4651 2244.8020 3166.2788 4774.2334 7762.5933 13716.4414 | lr 1.5e-04 | norm 4458.2656 | dt 9.798 +type train | step 4006 | loss 98.6524 210.3367 330.0359 538.7220 821.6733 1167.7401 1645.8533 2340.8723 3275.1667 4924.6113 8012.5117 14315.5488 | lr 1.5e-04 | norm 4816.3667 | dt 9.795 +type train | step 4007 | loss 104.1897 220.1523 337.1833 536.7995 812.3532 1133.1389 1586.8668 2232.7632 3133.7073 4713.1455 7660.2793 13659.8926 | lr 1.5e-04 | norm 3452.9924 | dt 9.793 +type train | step 4008 | loss 105.9738 224.1809 341.8141 539.9219 811.6974 1136.7369 1587.7900 2237.7400 3110.1523 4668.6084 7560.1382 13440.0078 | lr 1.5e-04 | norm 3613.9810 | dt 9.796 +type train | step 4009 | loss 98.8075 209.0992 321.2146 513.6342 784.0819 1097.1184 1547.7909 2192.5874 3084.2893 4618.9307 7447.3467 13146.4893 | lr 1.5e-04 | norm 3180.6238 | dt 9.803 +type train | step 4010 | loss 103.2767 218.2753 329.7713 523.7274 789.1248 1112.2002 1559.5708 2208.6321 3093.5420 4661.7383 7613.7236 13642.4863 | lr 1.5e-04 | norm 4110.8281 | dt 9.787 +type train | step 4011 | loss 103.5284 223.1492 344.3179 548.6293 832.1961 1148.9240 1600.9485 2259.5105 3160.3604 4702.6816 7496.3237 13145.8037 | lr 1.5e-04 | norm 4535.4858 | dt 9.781 +type train | step 4012 | loss 89.0394 189.4470 301.9857 487.5642 768.8661 1071.6456 1557.3605 2249.1663 3241.8352 5001.2998 8090.9463 14464.3994 | lr 1.5e-04 | norm 9347.0488 | dt 9.788 +type train | step 4013 | loss 96.9878 202.7847 315.7767 508.8843 776.7750 1098.5381 1545.2114 2193.3989 3077.7554 4640.4395 7549.0571 13431.0244 | lr 1.5e-04 | norm 3533.8201 | dt 9.793 +type train | step 4014 | loss 104.0077 219.2065 337.1733 540.1627 818.7062 1151.3362 1615.6250 2293.3586 3213.2224 4823.2593 7839.5454 13907.0010 | lr 1.5e-04 | norm 3282.1238 | dt 9.807 +type train | step 4015 | loss 96.0536 202.6786 315.7961 512.1537 783.2934 1110.9719 1565.3611 2220.3979 3104.4636 4672.1836 7631.4912 13572.9863 | lr 1.5e-04 | norm 4319.0781 | dt 9.793 +type train | step 4016 | loss 111.2677 238.0263 359.9951 560.5775 834.9263 1172.6338 1633.6067 2293.0430 3167.9683 4764.7588 7769.0063 13882.4160 | lr 1.5e-04 | norm 4092.9204 | dt 9.792 +type train | step 4017 | loss 103.7522 220.0915 336.9384 531.8054 798.8037 1117.1981 1568.7921 2211.1306 3104.5068 4644.6641 7498.7695 13224.7354 | lr 1.5e-04 | norm 3352.8247 | dt 9.794 +type train | step 4018 | loss 91.5505 191.3363 298.1312 481.5342 743.3842 1049.3396 1487.7832 2116.3828 3005.7295 4537.4263 7386.7334 13143.4844 | lr 1.5e-04 | norm 4076.9172 | dt 9.791 +type train | step 4019 | loss 99.0072 209.9254 325.8920 520.6335 787.0375 1112.2134 1564.8470 2224.1130 3127.8784 4704.0371 7646.6440 13635.2412 | lr 1.5e-04 | norm 3393.4871 | dt 9.795 +type train | step 4020 | loss 95.7102 202.0841 313.2946 503.7306 776.2578 1091.9640 1544.1843 2190.4595 3102.4468 4665.8076 7551.3262 13435.2998 | lr 1.5e-04 | norm 3779.3208 | dt 9.792 +type train | step 4021 | loss 110.7522 239.1913 363.3576 570.5761 855.5052 1199.7766 1676.9366 2373.2344 3317.1248 4964.6187 7969.8672 14079.6875 | lr 1.5e-04 | norm 4787.8296 | dt 9.786 +type train | step 4022 | loss 100.9500 213.5775 331.6022 531.9120 807.7638 1127.1337 1590.8472 2264.5803 3199.9243 4822.2891 7742.2695 13554.0117 | lr 1.5e-04 | norm 3973.1995 | dt 9.795 +type train | step 4023 | loss 98.1057 213.0827 332.0039 544.2784 816.0969 1166.5696 1651.9823 2394.3137 3316.2712 5080.5977 8331.2998 14852.4629 | lr 1.5e-04 | norm 9205.8477 | dt 9.771 +type train | step 4024 | loss 104.7980 223.4381 339.0575 537.8508 811.9337 1133.4974 1589.3505 2233.8787 3128.5950 4704.8062 7679.2734 13819.9385 | lr 1.5e-04 | norm 4263.4648 | dt 9.809 +type train | step 4025 | loss 96.7264 205.7582 319.5585 513.5078 787.1644 1110.8057 1571.9528 2229.9104 3162.9675 4784.5791 7769.2280 13726.7070 | lr 1.5e-04 | norm 3738.0757 | dt 9.797 +type train | step 4026 | loss 105.3723 223.9648 337.6259 534.2012 808.1036 1127.6085 1588.5304 2252.6128 3154.9524 4813.4683 7864.1938 14050.4814 | lr 1.5e-04 | norm 5384.7300 | dt 9.787 +type train | step 4027 | loss 109.9702 235.5538 352.7957 548.7587 823.6205 1145.4099 1603.8928 2251.8765 3114.2837 4683.0400 7577.2529 13484.4854 | lr 1.5e-04 | norm 4353.7378 | dt 9.796 +type train | step 4028 | loss 103.9413 219.8284 337.1468 537.2275 812.4749 1149.3456 1614.0101 2291.2222 3194.0774 4768.8066 7749.2227 13819.6465 | lr 1.5e-04 | norm 3950.4915 | dt 9.795 +type train | step 4029 | loss 97.7686 205.4140 317.2209 513.4351 783.1254 1120.6250 1582.8080 2253.9971 3150.0076 4719.1729 7684.5249 13761.4189 | lr 1.5e-04 | norm 4284.8848 | dt 9.791 +type train | step 4030 | loss 92.8816 194.8422 304.7191 494.3167 760.3760 1079.8539 1529.0411 2186.0364 3095.5574 4669.5527 7579.5728 13434.2266 | lr 1.5e-04 | norm 3826.5435 | dt 9.803 +type train | step 4031 | loss 97.9150 207.5993 322.5031 516.8633 789.2374 1102.5989 1565.6823 2220.8486 3172.0317 4767.9307 7655.7246 13409.9746 | lr 1.5e-04 | norm 4400.2041 | dt 9.803 +type train | step 4032 | loss 101.0031 210.5385 328.2994 529.7496 806.3636 1149.0571 1614.7112 2298.8613 3211.9778 4821.5542 7813.3550 13916.2891 | lr 1.5e-04 | norm 4190.6172 | dt 9.782 +type train | step 4033 | loss 100.1352 214.9027 328.4930 526.8824 803.1492 1124.5854 1574.2812 2228.0205 3117.9666 4654.0942 7540.3242 13359.8965 | lr 1.5e-04 | norm 3811.7334 | dt 9.788 +type train | step 4034 | loss 102.6331 218.7070 332.9888 530.4884 806.5204 1129.0134 1583.4086 2231.0793 3141.8054 4751.0547 7714.0815 13716.0830 | lr 1.5e-04 | norm 3830.2197 | dt 9.801 +type train | step 4035 | loss 102.0266 216.8579 331.7878 523.8260 800.3715 1132.5453 1593.0024 2256.5552 3142.7751 4698.4727 7590.1865 13431.3086 | lr 1.5e-04 | norm 3902.7285 | dt 9.787 +type train | step 4036 | loss 103.7797 217.8444 336.1026 536.6875 814.7819 1144.1371 1605.4813 2259.0542 3174.7129 4746.2373 7646.5605 13477.7754 | lr 1.5e-04 | norm 3416.5586 | dt 9.803 +type train | step 4037 | loss 98.2002 204.9471 315.8106 506.1891 776.8340 1093.3253 1547.7366 2204.3254 3102.5908 4667.8506 7571.5566 13442.6602 | lr 1.5e-04 | norm 3576.9138 | dt 9.787 +type train | step 4038 | loss 98.6867 209.5626 320.4896 519.8351 797.6523 1118.4790 1578.4685 2248.9956 3147.4409 4747.0337 7727.7471 13788.9736 | lr 1.5e-04 | norm 4062.3567 | dt 9.792 +type train | step 4039 | loss 127.5021 282.1137 404.0450 628.1054 931.9486 1341.4264 1877.3380 2612.2998 3532.0957 5124.3013 8010.1172 14044.9443 | lr 1.5e-04 | norm 5715.8159 | dt 9.768 +type train | step 4040 | loss 121.4395 256.6346 383.4023 589.7273 871.8165 1200.5488 1661.7769 2295.6741 3154.2495 4703.1177 7529.9331 13386.0703 | lr 1.5e-04 | norm 5007.9751 | dt 9.774 +type train | step 4041 | loss 96.8876 204.3391 316.6842 509.0240 777.6806 1094.4969 1551.8022 2206.3054 3119.4001 4705.4580 7610.1924 13482.6934 | lr 1.5e-04 | norm 3679.3511 | dt 9.802 +type train | step 4042 | loss 107.8050 226.3419 344.0148 546.0920 819.6422 1156.2992 1622.4302 2306.4460 3210.3916 4802.5332 7763.0205 13785.8818 | lr 1.5e-04 | norm 4003.4355 | dt 9.787 +type train | step 4043 | loss 106.4460 226.4952 344.7653 547.2358 825.7932 1155.7753 1610.9659 2269.2405 3163.2607 4753.5781 7719.7505 13747.4023 | lr 1.5e-04 | norm 3863.7629 | dt 9.795 +type train | step 4044 | loss 106.0917 222.9731 343.8384 548.1418 825.4948 1169.4835 1633.0712 2316.2244 3191.1831 4797.8145 7792.0469 13927.2305 | lr 1.5e-04 | norm 4597.8804 | dt 9.780 +type train | step 4045 | loss 96.8799 204.3958 318.0511 512.4144 780.9957 1108.9312 1568.6921 2218.4961 3109.4473 4641.4634 7511.2280 13255.2910 | lr 1.5e-04 | norm 4056.7158 | dt 9.790 +type train | step 4046 | loss 94.7741 200.1976 313.7805 505.1009 772.7582 1082.9056 1535.0885 2174.9277 3061.2852 4637.3838 7542.7046 13354.5801 | lr 1.5e-04 | norm 3848.8433 | dt 9.782 +type train | step 4047 | loss 103.3687 217.1046 332.3506 531.4311 802.6143 1128.4681 1589.5886 2247.4658 3154.2439 4712.7593 7650.0146 13599.1318 | lr 1.5e-04 | norm 4278.5205 | dt 9.790 +type train | step 4048 | loss 100.9797 213.4310 329.2172 523.3936 793.3214 1118.8542 1572.8666 2233.8228 3128.6680 4701.2188 7624.8057 13539.5732 | lr 1.5e-04 | norm 3902.9998 | dt 9.783 +type train | step 4049 | loss 104.8265 222.3653 342.5595 551.8688 837.6557 1214.5753 1720.2693 2487.2563 3443.8928 5152.0449 8199.9209 14332.7979 | lr 1.5e-04 | norm 4578.7661 | dt 9.772 +type train | step 4050 | loss 107.9069 228.6841 348.0681 551.9093 822.1580 1150.5662 1604.1396 2245.1099 3105.9136 4648.7925 7562.8696 13483.4619 | lr 1.5e-04 | norm 4158.0322 | dt 9.799 +type train | step 4051 | loss 105.1545 224.1743 343.9865 544.0999 818.1133 1145.3311 1604.5183 2259.3142 3176.4387 4776.7090 7716.8154 13608.4922 | lr 1.5e-04 | norm 4062.0745 | dt 9.808 +type train | step 4052 | loss 99.1322 206.6965 320.0849 515.5856 783.6926 1120.9915 1579.0123 2276.5203 3161.4343 4777.1787 7771.4644 13847.8145 | lr 1.5e-04 | norm 4173.6670 | dt 9.780 +type train | step 4053 | loss 102.2960 215.8778 326.2051 522.6124 789.9534 1135.2408 1606.6295 2303.5869 3225.7085 4858.6592 7896.9717 14182.1211 | lr 1.5e-04 | norm 5434.8599 | dt 9.782 +type train | step 4054 | loss 98.4427 207.2322 320.9707 515.4139 782.8068 1106.1479 1559.1498 2212.8369 3097.7698 4662.3135 7557.2500 13378.6514 | lr 1.5e-04 | norm 3642.6946 | dt 9.806 +type train | step 4055 | loss 103.3220 221.5100 337.4198 535.1083 811.9377 1149.3765 1614.2247 2288.3621 3215.1218 4842.1924 7899.9160 14098.0127 | lr 1.5e-04 | norm 4234.3726 | dt 9.804 +type train | step 4056 | loss 97.9361 207.3515 322.8715 518.9944 792.4661 1122.0829 1586.0110 2259.5911 3176.9878 4746.5693 7676.2500 13491.3926 | lr 1.5e-04 | norm 3048.7290 | dt 9.800 +type train | step 4057 | loss 100.2817 212.8516 325.2251 517.7087 785.7750 1119.2793 1591.3602 2273.0933 3189.8792 4822.7764 7808.5527 13796.7773 | lr 1.5e-04 | norm 4699.6201 | dt 9.807 +type train | step 4058 | loss 99.8875 209.6367 325.5586 524.7701 792.5299 1125.4314 1590.2468 2258.2852 3156.3110 4714.4648 7655.1445 13594.0908 | lr 1.5e-04 | norm 3594.6226 | dt 9.797 +type train | step 4059 | loss 98.8073 211.1143 326.3563 522.6066 797.7896 1126.3699 1587.6222 2255.7285 3179.8977 4783.9771 7713.1426 13651.6582 | lr 1.5e-04 | norm 3443.5593 | dt 9.799 +type train | step 4060 | loss 92.6011 205.1645 315.9073 524.0551 822.6256 1181.9266 1675.8749 2420.3262 3419.2109 5271.5151 8610.5244 15306.7236 | lr 1.5e-04 | norm 8702.8848 | dt 9.783 +type train | step 4061 | loss 102.7299 220.0346 336.2720 534.4567 804.6962 1131.3975 1586.6702 2238.7183 3149.8713 4766.0151 7751.8647 13804.5371 | lr 1.5e-04 | norm 3492.9282 | dt 9.801 +type train | step 4062 | loss 101.7464 215.7184 329.7396 520.4272 789.5299 1112.4264 1573.6973 2225.9438 3139.9414 4758.3525 7775.7925 13907.0967 | lr 1.5e-04 | norm 4057.6619 | dt 9.794 +type train | step 4063 | loss 99.3275 211.0326 322.9490 521.3505 798.5175 1135.7870 1608.8291 2311.5000 3232.8765 4894.4810 8056.7505 14414.3594 | lr 1.5e-04 | norm 5571.2363 | dt 9.793 +type train | step 4064 | loss 107.2699 231.1195 346.8113 544.0936 814.7501 1164.4375 1637.4430 2303.3096 3210.1411 4812.9092 7773.0942 13656.9814 | lr 1.5e-04 | norm 4301.2920 | dt 9.792 +type train | step 4065 | loss 102.0191 218.5789 332.3963 529.2327 803.2109 1130.3550 1586.6238 2252.6072 3145.0952 4724.4082 7675.2539 13693.4697 | lr 1.5e-04 | norm 4104.0103 | dt 9.808 +type train | step 4066 | loss 101.0878 213.9325 329.4903 521.5577 791.3842 1108.8765 1556.0596 2207.1567 3111.2222 4715.3984 7707.6348 13702.4443 | lr 1.5e-04 | norm 5029.4482 | dt 9.794 +type train | step 4067 | loss 106.8185 226.8892 344.2652 549.2626 824.4352 1161.7863 1624.7450 2304.5042 3229.7654 4864.4272 7979.4819 14245.1553 | lr 1.5e-04 | norm 5778.5498 | dt 9.790 +type train | step 4068 | loss 101.9501 213.8126 333.2615 528.4977 802.8424 1128.4017 1594.4740 2273.4270 3217.8494 4881.2012 7936.6855 14130.9463 | lr 1.5e-04 | norm 4774.9683 | dt 9.798 +type train | step 4069 | loss 95.7993 204.4687 321.5252 520.2113 787.2621 1115.9081 1582.1152 2249.4761 3190.2847 4846.8604 7905.3105 14063.4668 | lr 1.5e-04 | norm 4482.8354 | dt 9.812 +type train | step 4070 | loss 95.1781 200.1908 314.3572 506.8996 774.0892 1085.9443 1533.7886 2168.2737 3069.4409 4628.4106 7531.9980 13331.5791 | lr 1.5e-04 | norm 3166.9648 | dt 9.804 +type train | step 4071 | loss 96.5148 203.1995 316.8936 510.1567 775.2203 1102.5045 1559.5551 2228.3489 3154.2747 4738.7368 7691.7383 13540.3916 | lr 1.5e-04 | norm 3317.6760 | dt 9.796 +type train | step 4072 | loss 101.1562 217.1442 332.5273 528.9027 803.1340 1134.8728 1593.4240 2255.4443 3157.3252 4731.7358 7648.5264 13614.7539 | lr 1.5e-04 | norm 3401.1045 | dt 9.798 +type train | step 4073 | loss 104.4179 220.9918 338.4957 535.8029 809.5673 1141.5651 1598.4304 2245.4473 3136.8340 4696.1978 7586.6367 13396.2812 | lr 1.5e-04 | norm 3685.1394 | dt 9.796 +type train | step 4074 | loss 106.5552 228.8842 348.0128 550.5773 821.2141 1153.5792 1614.2417 2264.4373 3164.0552 4756.6953 7749.2803 13836.9053 | lr 1.5e-04 | norm 4085.9197 | dt 9.792 +type train | step 4075 | loss 108.6847 238.2315 359.4202 562.4332 840.7896 1172.3640 1633.1927 2302.1809 3201.8276 4818.3672 7853.8936 13929.9395 | lr 1.4e-04 | norm 5228.3184 | dt 9.796 +type train | step 4076 | loss 101.8990 218.6126 335.6559 534.9102 806.0562 1127.5548 1571.6758 2208.4690 3094.3706 4650.4414 7586.4790 13446.3740 | lr 1.4e-04 | norm 3661.3223 | dt 9.791 +type train | step 4077 | loss 97.7436 207.5118 318.4323 506.2581 770.1540 1094.1166 1545.7358 2202.6399 3089.3726 4656.1885 7570.2593 13442.0039 | lr 1.4e-04 | norm 3830.4980 | dt 10.114 +type train | step 4078 | loss 99.5022 210.3799 324.4603 519.0687 788.6004 1108.5721 1556.9852 2211.7361 3102.5784 4654.1904 7585.2080 13474.1865 | lr 1.4e-04 | norm 4707.2539 | dt 9.789 +type train | step 4079 | loss 104.9978 225.0949 341.6849 541.0510 811.7579 1137.0605 1585.9741 2227.1277 3102.5703 4636.4419 7508.6016 13338.0762 | lr 1.4e-04 | norm 3698.5879 | dt 9.795 +type train | step 4080 | loss 109.4992 232.6862 352.6492 560.1119 833.2988 1181.3270 1647.5437 2322.4551 3220.2688 4827.4126 7890.5283 14171.0078 | lr 1.4e-04 | norm 4104.9668 | dt 9.778 +type train | step 4081 | loss 104.9396 218.1891 335.4895 543.2174 813.1680 1165.8326 1638.8615 2316.9839 3179.9822 4745.5830 7698.1968 13709.3896 | lr 1.4e-04 | norm 4871.7490 | dt 9.782 +type train | step 4082 | loss 93.6155 196.0799 305.2206 492.3596 754.9742 1067.0388 1513.3336 2150.2739 3033.6252 4586.9268 7479.2773 13291.7930 | lr 1.4e-04 | norm 3678.8618 | dt 9.795 +type train | step 4083 | loss 97.2819 205.1576 316.3218 506.9224 773.2456 1096.3801 1547.2526 2202.2402 3104.6560 4681.4131 7614.7842 13437.6592 | lr 1.4e-04 | norm 3457.6880 | dt 9.808 +type train | step 4084 | loss 103.1138 219.4368 337.7727 540.1093 816.5791 1142.7307 1605.8396 2252.1775 3170.0930 4750.9546 7668.5059 13476.4697 | lr 1.4e-04 | norm 3204.5947 | dt 9.798 +type train | step 4085 | loss 97.7995 205.6324 321.8702 518.4901 780.9329 1104.6595 1553.5316 2194.3887 3090.6362 4654.6411 7616.3086 13518.4619 | lr 1.4e-04 | norm 3560.9399 | dt 9.790 +type train | step 4086 | loss 94.8009 199.3981 308.7986 496.4059 755.4484 1073.4185 1527.2330 2177.8179 3066.8870 4635.9575 7500.7861 13246.3350 | lr 1.4e-04 | norm 3325.0100 | dt 9.787 +type train | step 4087 | loss 101.3907 213.4814 327.6745 520.8164 786.6294 1106.7234 1553.4858 2190.5222 3086.3811 4660.5190 7623.7881 13530.3291 | lr 1.4e-04 | norm 4240.7676 | dt 9.792 +type train | step 4088 | loss 112.6069 239.2656 359.3646 553.4872 820.6738 1160.7617 1609.3964 2249.8452 3059.9707 4576.1611 7453.0347 13418.0244 | lr 1.4e-04 | norm 6633.6001 | dt 9.777 +type train | step 4089 | loss 99.0442 206.7487 315.9471 504.8737 768.3114 1076.8729 1512.5082 2143.8816 3002.1018 4545.6060 7399.8428 13185.6680 | lr 1.4e-04 | norm 4196.1919 | dt 9.788 +type train | step 4090 | loss 103.5154 217.2940 334.4030 534.8730 800.9343 1122.2456 1577.0555 2230.0081 3130.6270 4728.7539 7682.9302 13671.4141 | lr 1.4e-04 | norm 3713.5693 | dt 9.792 +type train | step 4091 | loss 97.9203 205.5696 316.7186 504.2697 761.4271 1077.4991 1523.1772 2164.5786 3059.1121 4636.2900 7567.1851 13319.1377 | lr 1.4e-04 | norm 3281.3022 | dt 9.805 +type train | step 4092 | loss 93.1886 194.8696 306.0367 494.2918 755.1630 1063.4011 1507.9983 2134.4661 3030.6848 4565.9897 7399.3936 13064.8164 | lr 1.4e-04 | norm 3178.0640 | dt 9.806 +type train | step 4093 | loss 104.3605 216.1689 329.8484 524.0709 796.4912 1131.5027 1590.6731 2259.5632 3157.4414 4752.4092 7710.0835 13657.3711 | lr 1.4e-04 | norm 4047.3088 | dt 9.792 +type train | step 4094 | loss 92.0427 192.6508 307.0849 491.9896 756.5181 1081.9142 1536.2723 2200.7778 3107.0942 4727.9458 7728.8662 13740.6582 | lr 1.4e-04 | norm 4156.3911 | dt 9.799 +type train | step 4095 | loss 102.5289 217.8256 334.2376 535.1149 800.4349 1135.5745 1590.4005 2247.1030 3144.2749 4755.6772 7774.7871 13823.3584 | lr 1.4e-04 | norm 3708.6331 | dt 9.792 +type train | step 4096 | loss 99.6298 211.0833 325.0850 516.6406 781.9684 1101.9235 1545.9310 2185.7019 3073.1521 4624.9082 7541.1157 13343.5215 | lr 1.4e-04 | norm 3134.3853 | dt 9.797 +type train | step 4097 | loss 93.3505 195.9842 305.8259 493.4601 752.8923 1070.5516 1510.5610 2148.2852 3023.9629 4552.2666 7376.4429 13066.7129 | lr 1.4e-04 | norm 3301.9819 | dt 9.791 +type train | step 4098 | loss 98.2913 206.5596 318.5843 504.8453 767.1305 1089.9941 1546.1115 2198.4294 3089.3416 4684.3296 7655.8892 13669.4805 | lr 1.4e-04 | norm 3644.9644 | dt 9.795 +type train | step 4099 | loss 94.4327 199.6393 307.5686 493.1245 750.8565 1064.5144 1501.5044 2131.0879 3021.8767 4554.0459 7407.5195 13023.5254 | lr 1.4e-04 | norm 2971.2410 | dt 9.812 +type train | step 4100 | loss 98.2279 209.3222 321.5414 512.5966 777.2274 1103.8036 1558.3596 2201.5471 3096.4165 4670.4092 7601.2529 13479.0303 | lr 1.4e-04 | norm 3994.3184 | dt 9.794 +type train | step 4101 | loss 99.7168 210.5904 324.9641 521.9863 791.0930 1123.2649 1576.2255 2240.1140 3130.0479 4700.1372 7624.9307 13493.7637 | lr 1.4e-04 | norm 3238.2876 | dt 9.798 +type train | step 4102 | loss 89.6456 187.1676 293.9200 474.7132 733.0587 1036.1423 1474.5380 2102.4282 3006.6733 4582.4648 7517.3574 13373.8057 | lr 1.4e-04 | norm 3542.8066 | dt 9.798 +type train | step 4103 | loss 95.5751 197.0006 301.9134 484.9251 739.4381 1054.2714 1492.9072 2142.0305 3024.8259 4585.1265 7505.5562 13330.5732 | lr 1.4e-04 | norm 4168.1211 | dt 9.786 +type train | step 4104 | loss 111.0379 232.2460 347.1740 547.3497 814.7662 1140.2568 1591.7559 2236.0925 3134.9712 4712.4121 7695.3003 13631.7959 | lr 1.4e-04 | norm 6330.6152 | dt 9.790 +type train | step 4105 | loss 109.1209 229.7155 347.2597 548.4938 821.6322 1164.3325 1631.5812 2303.4998 3208.6438 4826.8901 7832.8745 13961.7988 | lr 1.4e-04 | norm 6393.9639 | dt 9.781 +type train | step 4106 | loss 103.9050 216.9395 333.2359 527.3097 790.5569 1128.7937 1573.1207 2238.6343 3098.0427 4624.0220 7432.6924 13032.8076 | lr 1.4e-04 | norm 3328.6621 | dt 9.787 +type train | step 4107 | loss 108.6459 230.6197 348.6071 560.9005 838.5882 1197.5718 1671.4728 2392.5881 3324.7715 5024.0967 8254.0732 14888.7988 | lr 1.4e-04 | norm 6078.8130 | dt 9.778 +type train | step 4108 | loss 110.9546 232.5376 348.6713 547.2748 812.9277 1145.4403 1602.1538 2260.3655 3157.4468 4738.7632 7697.9526 13646.2861 | lr 1.4e-04 | norm 4599.7749 | dt 9.785 +type train | step 4109 | loss 101.0602 213.7394 325.5972 515.2620 779.7113 1099.2876 1550.0315 2197.6208 3077.0310 4582.6992 7393.0552 12993.1436 | lr 1.4e-04 | norm 3904.0884 | dt 9.799 +type train | step 4110 | loss 126.1730 274.5762 393.6613 600.4077 875.0781 1222.0039 1679.3297 2349.3879 3186.0337 4786.7471 7893.8623 14210.0645 | lr 1.4e-04 | norm 9193.1084 | dt 9.767 +type train | step 4111 | loss 103.1438 216.4071 328.6909 522.4498 782.8566 1100.0682 1537.3821 2172.9558 3018.5149 4537.5337 7383.0864 13188.4512 | lr 1.4e-04 | norm 3926.3909 | dt 9.785 +type train | step 4112 | loss 97.7639 205.2852 313.2405 499.8923 759.6339 1074.6687 1524.8936 2167.7444 3051.3606 4609.5654 7480.0854 13231.7900 | lr 1.4e-04 | norm 4873.0596 | dt 9.804 +type train | step 4113 | loss 102.2558 214.6098 328.7116 522.2703 783.8629 1106.0476 1554.7603 2193.8142 3085.5835 4641.6035 7557.8965 13350.9775 | lr 1.4e-04 | norm 3377.0796 | dt 9.796 +type train | step 4114 | loss 100.3275 212.9592 328.3500 521.6238 785.8442 1110.5000 1566.3246 2220.4021 3115.5225 4707.4961 7658.0669 13566.1807 | lr 1.4e-04 | norm 3942.9309 | dt 9.785 +type train | step 4115 | loss 91.2433 194.9214 303.9049 490.9709 751.7629 1071.3323 1521.6340 2176.3081 3084.8018 4674.1250 7581.3193 13367.0879 | lr 1.4e-04 | norm 3748.0010 | dt 9.803 +type train | step 4116 | loss 101.8835 217.5695 331.7811 521.5782 791.9081 1098.7844 1540.9023 2169.7136 3052.2634 4601.0684 7418.1694 13093.8965 | lr 1.4e-04 | norm 3835.3650 | dt 9.799 +type train | step 4117 | loss 98.9909 210.5507 324.0224 517.6732 781.5110 1103.4696 1556.8282 2217.5728 3115.6794 4694.3960 7636.7988 13482.3379 | lr 1.4e-04 | norm 3696.3320 | dt 9.781 +type train | step 4118 | loss 97.4087 208.0072 321.8437 515.1201 783.5214 1112.1846 1570.4702 2238.9670 3150.7134 4767.4678 7729.8013 13730.8340 | lr 1.4e-04 | norm 3540.6030 | dt 9.791 +type train | step 4119 | loss 104.2266 223.2004 341.3951 536.7422 807.9141 1131.3555 1594.3373 2257.3909 3124.4683 4752.8501 7717.9727 13839.0635 | lr 1.4e-04 | norm 6695.3188 | dt 9.793 +type train | step 4120 | loss 96.1555 201.3048 310.6728 496.8455 764.4233 1082.2817 1539.8539 2192.0481 3084.7812 4648.2876 7545.9346 13415.1865 | lr 1.4e-04 | norm 5528.0322 | dt 9.785 +type train | step 4121 | loss 93.9609 199.4194 307.2023 493.2285 756.5862 1087.5608 1541.7294 2216.2708 3109.2322 4672.0029 7549.1797 13311.8516 | lr 1.4e-04 | norm 4236.8770 | dt 9.791 +type train | step 4122 | loss 107.4569 225.9285 343.8810 544.4957 823.2106 1161.0769 1624.6509 2290.7695 3188.5393 4739.9419 7560.0044 13232.3398 | lr 1.4e-04 | norm 3390.4680 | dt 9.795 +type train | step 4123 | loss 109.1091 231.2014 350.3447 549.1921 820.5639 1156.7021 1616.7086 2256.0051 3053.4641 4524.1807 7271.3027 12950.8662 | lr 1.4e-04 | norm 7293.8569 | dt 9.759 +type train | step 4124 | loss 102.0194 215.6732 331.0428 519.9828 783.4450 1108.9279 1564.4803 2209.0754 3080.3142 4639.7451 7534.9609 13382.8691 | lr 1.4e-04 | norm 4135.7915 | dt 9.800 +type train | step 4125 | loss 101.6303 214.7717 327.0060 522.6024 786.0369 1104.6569 1548.6792 2187.1946 3058.6426 4584.5269 7493.6030 13292.8398 | lr 1.4e-04 | norm 3604.6003 | dt 9.800 +type train | step 4126 | loss 99.1990 211.5328 325.6450 520.0096 788.6799 1110.7065 1556.0294 2206.8298 3097.8853 4669.6831 7586.9639 13424.9785 | lr 1.4e-04 | norm 3475.6321 | dt 9.808 +type train | step 4127 | loss 103.3211 221.2893 340.2721 541.1991 816.3094 1156.7297 1631.6782 2308.7678 3235.9304 4867.6724 7844.4717 13763.3623 | lr 1.4e-04 | norm 3860.1885 | dt 9.793 +type train | step 4128 | loss 106.8112 228.6182 349.4997 551.4266 820.6733 1150.4714 1598.9952 2231.2437 3102.5410 4625.8730 7438.2397 13193.0645 | lr 1.4e-04 | norm 3426.7493 | dt 9.777 +type train | step 4129 | loss 94.6291 198.5530 310.2986 501.2808 765.4460 1086.8657 1535.7175 2189.3538 3101.0496 4679.1968 7608.7812 13451.7627 | lr 1.4e-04 | norm 3393.8413 | dt 9.784 +type train | step 4130 | loss 94.2889 196.9637 305.9897 496.8054 754.3525 1074.7272 1523.9548 2170.0417 3071.3130 4628.8960 7485.5596 13150.0273 | lr 1.4e-04 | norm 3319.1091 | dt 9.792 +type train | step 4131 | loss 101.6594 216.2458 331.4525 525.4267 792.4422 1125.7336 1573.2007 2239.0764 3123.5469 4702.2402 7660.5020 13594.8037 | lr 1.4e-04 | norm 3601.2534 | dt 9.788 +type train | step 4132 | loss 104.1692 222.0863 340.2959 541.6982 816.6294 1147.5756 1608.2755 2289.1873 3202.9861 4845.0566 7921.5972 14131.6123 | lr 1.4e-04 | norm 5523.6323 | dt 9.781 +type train | step 4133 | loss 99.0373 208.0869 322.0593 516.6342 784.1710 1109.2386 1562.6429 2215.6204 3116.9949 4706.3828 7664.8955 13627.6582 | lr 1.4e-04 | norm 3725.1985 | dt 9.794 +type train | step 4134 | loss 98.3283 211.0734 331.6526 537.0134 817.3420 1174.4381 1659.4292 2389.7734 3329.7153 5099.5444 8264.2598 14682.1553 | lr 1.4e-04 | norm 6543.3462 | dt 9.785 +type train | step 4135 | loss 97.2367 203.8191 319.0826 513.8783 778.3806 1097.0618 1543.5189 2189.9353 3083.4763 4651.2461 7568.3799 13348.3730 | lr 1.4e-04 | norm 3384.6943 | dt 9.797 +type train | step 4136 | loss 96.7783 205.3269 319.0150 510.7376 773.8420 1102.0457 1554.4894 2211.6782 3121.4409 4672.2100 7536.9595 13214.9697 | lr 1.4e-04 | norm 3567.6401 | dt 9.790 +type train | step 4137 | loss 105.5512 222.3933 338.0469 533.6686 802.0925 1133.7695 1584.1793 2240.0098 3118.2368 4693.5454 7640.4375 13551.7676 | lr 1.4e-04 | norm 3592.8965 | dt 9.796 +type train | step 4138 | loss 93.5659 204.8300 328.0177 534.5911 821.0300 1163.7698 1644.5195 2339.6160 3307.7148 5026.0620 8204.1865 14577.1289 | lr 1.4e-04 | norm 6630.8687 | dt 9.788 +type train | step 4139 | loss 95.6676 207.1907 326.0115 522.4413 797.4019 1134.5559 1602.1461 2288.9121 3213.5098 4909.3247 8048.6353 14330.7871 | lr 1.4e-04 | norm 4990.6997 | dt 9.792 +type train | step 4140 | loss 106.2555 225.1501 344.8611 562.4691 838.1738 1190.4684 1665.9794 2357.1978 3246.6484 4868.5391 7952.8794 14272.3789 | lr 1.4e-04 | norm 6256.9341 | dt 9.777 +type train | step 4141 | loss 94.6854 200.2830 309.2855 496.6433 753.5354 1070.8411 1504.2301 2134.7615 3001.9570 4521.9824 7352.6328 13059.6162 | lr 1.4e-04 | norm 4076.6846 | dt 9.795 +type train | step 4142 | loss 98.6589 204.6326 318.3363 511.2906 776.3558 1100.3867 1548.5249 2203.3159 3086.8330 4685.5747 7651.2158 13616.6416 | lr 1.4e-04 | norm 3787.8594 | dt 9.789 +type train | step 4143 | loss 102.6791 217.2814 334.1154 534.0305 810.0422 1148.7992 1606.6279 2289.0894 3199.8455 4833.7637 7966.1758 14247.6357 | lr 1.4e-04 | norm 5165.2046 | dt 9.789 +type train | step 4144 | loss 98.4339 206.5963 318.1807 508.5548 767.4614 1085.6006 1534.2085 2171.7273 3048.6997 4590.1880 7481.8672 13278.4365 | lr 1.4e-04 | norm 3437.6011 | dt 9.805 +type train | step 4145 | loss 102.2771 217.1859 332.7687 530.4515 800.5695 1137.8555 1591.8081 2253.4473 3121.1201 4711.7173 7684.7021 13729.0029 | lr 1.4e-04 | norm 3901.7937 | dt 9.790 +type train | step 4146 | loss 99.5002 210.7603 321.7295 511.3607 772.9948 1091.3383 1540.6106 2187.9941 3074.9150 4635.1387 7551.8418 13399.9258 | lr 1.4e-04 | norm 3233.9250 | dt 9.798 +type train | step 4147 | loss 97.2825 203.7752 318.8833 513.1384 781.2752 1103.7069 1558.3068 2218.2803 3109.4402 4697.0757 7638.5894 13576.4160 | lr 1.4e-04 | norm 4317.3579 | dt 9.807 +type train | step 4148 | loss 108.2489 229.4318 347.6175 548.8035 816.0580 1139.5420 1578.1040 2211.7234 3053.0664 4542.0903 7372.2480 13117.5215 | lr 1.4e-04 | norm 4635.4731 | dt 9.772 +type train | step 4149 | loss 99.7840 209.1220 323.1091 515.9789 777.0078 1105.5687 1556.6886 2197.2974 3091.7207 4664.4648 7606.8457 13498.8994 | lr 1.4e-04 | norm 3591.3425 | dt 9.800 +type train | step 4150 | loss 104.3301 221.4298 341.0758 541.6000 811.5245 1137.0496 1599.7903 2261.0229 3164.5308 4760.3511 7773.6343 13759.5049 | lr 1.4e-04 | norm 5354.0596 | dt 9.779 +type train | step 4151 | loss 105.5340 220.4371 333.6058 530.8467 798.6676 1129.2446 1576.0645 2235.1484 3111.9355 4642.0312 7440.7974 13063.6680 | lr 1.4e-04 | norm 5408.5435 | dt 9.769 +type train | step 4152 | loss 93.7860 197.0182 303.4550 491.6379 747.5224 1053.2512 1489.4069 2120.6189 3002.4392 4544.4971 7401.2090 13132.7979 | lr 1.4e-04 | norm 5022.5254 | dt 9.784 +type train | step 4153 | loss 96.7276 204.7484 317.1863 507.4563 765.5989 1083.2954 1523.2675 2145.0488 3011.9624 4500.5049 7289.7129 12813.9473 | lr 1.4e-04 | norm 3565.5916 | dt 9.785 +type train | step 4154 | loss 98.2850 210.6521 322.1075 509.6978 778.1823 1096.5209 1550.8038 2195.5488 3066.6665 4604.6636 7483.2231 13206.0303 | lr 1.4e-04 | norm 4045.7671 | dt 9.791 +type train | step 4155 | loss 100.2150 208.5604 322.0988 510.8807 773.9677 1097.6011 1541.4922 2178.4167 3037.1750 4534.9673 7328.2729 12980.9111 | lr 1.4e-04 | norm 3709.8479 | dt 9.827 +type train | step 4156 | loss 97.3645 205.1841 317.6225 507.1089 770.2568 1090.6464 1546.0951 2179.9146 3088.1155 4631.5732 7496.5435 13186.4258 | lr 1.4e-04 | norm 4262.5142 | dt 9.785 +type train | step 4157 | loss 96.2200 202.5111 316.9273 513.4801 780.1951 1112.5889 1575.3687 2240.0154 3166.8853 4775.0254 7719.4697 13632.8320 | lr 1.4e-04 | norm 3699.1267 | dt 9.806 +type train | step 4158 | loss 100.1249 208.6292 322.1173 510.4539 770.5951 1095.0740 1542.7263 2186.8027 3069.4170 4625.4775 7555.1167 13405.8877 | lr 1.4e-04 | norm 3944.9617 | dt 9.791 +type train | step 4159 | loss 95.9054 204.8021 319.7213 516.9810 788.6028 1123.1512 1591.9587 2263.4265 3187.9678 4820.2471 7841.5044 13948.6230 | lr 1.4e-04 | norm 4372.9453 | dt 9.789 +type train | step 4160 | loss 100.2600 211.3688 324.7688 517.2325 784.0914 1105.5034 1553.8574 2202.2502 3086.9473 4682.6689 7628.4751 13596.6289 | lr 1.4e-04 | norm 3645.0723 | dt 9.800 +type train | step 4161 | loss 101.0928 216.4156 332.4405 528.9282 797.3718 1130.4445 1597.5144 2270.0146 3194.2263 4820.7622 7863.0669 13907.2529 | lr 1.4e-04 | norm 3314.9844 | dt 9.804 +type train | step 4162 | loss 89.9619 187.4229 294.3217 480.0899 742.5263 1050.6377 1496.9033 2135.4954 3032.0942 4555.0986 7441.3662 13161.8438 | lr 1.4e-04 | norm 4039.5251 | dt 9.801 +type train | step 4163 | loss 78.6146 163.1431 258.7336 424.0424 670.8161 971.9371 1415.2096 2067.0122 2973.0317 4631.1675 7671.6147 14100.4863 | lr 1.4e-04 | norm 11740.7480 | dt 9.784 +type train | step 4164 | loss 79.6216 165.1090 261.5660 431.0839 677.8979 980.2627 1425.7136 2072.9924 2982.0667 4635.3159 7658.8818 13957.6914 | lr 1.4e-04 | norm 10442.9443 | dt 9.785 +type train | step 4165 | loss 90.2413 189.5752 295.5128 483.9761 741.8107 1059.2607 1507.9963 2153.6814 3059.1479 4637.6338 7556.2354 13384.5039 | lr 1.4e-04 | norm 3521.9363 | dt 9.788 +type train | step 4166 | loss 94.0644 198.9906 309.5324 499.5797 760.0746 1079.1182 1535.9634 2190.4629 3087.6934 4669.5498 7623.7495 13582.7139 | lr 1.4e-04 | norm 5224.8091 | dt 9.793 +type train | step 4167 | loss 100.2617 213.1080 333.7419 543.4265 828.0342 1183.3206 1656.2111 2373.7605 3320.2229 4988.6538 8256.1953 15026.9199 | lr 1.4e-04 | norm 8758.1738 | dt 9.769 +type train | step 4168 | loss 107.3723 231.5596 346.2909 539.8553 809.0336 1131.3932 1580.6329 2219.5405 3114.8257 4679.6284 7575.3945 13425.6719 | lr 1.4e-04 | norm 4344.4722 | dt 9.793 +type train | step 4169 | loss 99.7103 210.1313 319.4504 508.7108 767.6017 1080.5956 1515.3036 2137.5298 2991.5327 4485.6533 7300.2715 12937.6875 | lr 1.4e-04 | norm 3918.9817 | dt 9.801 +type train | step 4170 | loss 98.6250 207.8369 321.3094 512.1656 769.1252 1087.7496 1536.4910 2180.7324 3068.6084 4631.2881 7583.8433 13509.7998 | lr 1.4e-04 | norm 3540.6895 | dt 9.803 +type train | step 4171 | loss 92.8974 195.7574 306.2834 497.7468 759.1329 1077.0363 1523.4486 2160.4656 3066.9233 4663.5342 7624.7026 13448.4834 | lr 1.4e-04 | norm 3976.2883 | dt 9.807 +type train | step 4172 | loss 93.4189 199.4618 310.8569 500.1021 759.4970 1078.7035 1513.4502 2147.3486 3012.0176 4541.7368 7409.1182 13104.2832 | lr 1.4e-04 | norm 3865.2937 | dt 9.799 +type train | step 4173 | loss 100.2577 212.0572 324.0869 511.6083 771.9096 1085.8523 1530.1238 2162.1582 3029.7004 4560.0967 7393.2817 13015.2637 | lr 1.4e-04 | norm 3259.2942 | dt 9.794 +type train | step 4174 | loss 103.4060 223.0804 338.8836 545.4273 820.5084 1164.4657 1627.6201 2299.4175 3206.7292 4809.2373 7823.2344 14072.4004 | lr 1.4e-04 | norm 5378.0327 | dt 9.784 +type train | step 4175 | loss 95.8874 201.0827 310.9834 506.7109 767.2711 1084.1993 1533.3351 2189.9072 3087.0498 4685.9497 7634.5303 13584.1279 | lr 1.4e-04 | norm 3993.8652 | dt 9.798 +type train | step 4176 | loss 100.2596 212.4781 325.4056 519.8469 788.7885 1121.6963 1570.4685 2220.0205 3099.8333 4662.0708 7559.4102 13342.9238 | lr 1.4e-04 | norm 4369.9839 | dt 9.804 +type train | step 4177 | loss 102.0055 214.8596 328.9815 524.2775 792.1083 1116.8959 1567.4191 2217.3755 3099.9031 4672.6812 7606.6626 13487.0000 | lr 1.4e-04 | norm 3724.8530 | dt 9.797 +type train | step 4178 | loss 102.4821 215.1032 328.4898 522.7902 786.5651 1117.3126 1566.8474 2233.2026 3106.4377 4642.3374 7541.3574 13334.5254 | lr 1.4e-04 | norm 3688.7026 | dt 9.795 +type train | step 4179 | loss 95.2182 193.2906 307.6898 493.7945 752.6651 1079.1263 1520.8562 2166.7236 3028.8433 4579.1846 7510.1650 13262.0986 | lr 1.4e-04 | norm 6347.0386 | dt 9.794 +type train | step 4180 | loss 105.2145 226.9707 347.3415 554.2391 835.8329 1179.2673 1645.8398 2312.4192 3270.2263 4879.3599 7705.0361 13432.1855 | lr 1.4e-04 | norm 4679.4556 | dt 9.787 +type train | step 4181 | loss 105.3482 222.0265 334.7354 525.8907 790.3399 1122.6562 1575.3958 2238.6482 3130.0935 4724.6836 7678.1318 13687.7559 | lr 1.4e-04 | norm 4327.1245 | dt 9.792 +type train | step 4182 | loss 102.7326 215.1173 327.6126 525.3416 791.3569 1135.8876 1595.3260 2270.1138 3162.9639 4748.8550 7754.2720 13735.2666 | lr 1.4e-04 | norm 3700.7136 | dt 9.795 +type train | step 4183 | loss 97.3067 206.3981 315.7271 506.1453 762.1937 1079.0137 1521.5629 2160.6167 3044.8867 4634.8081 7656.8813 13738.5195 | lr 1.4e-04 | norm 5358.6348 | dt 9.785 +type train | step 4184 | loss 103.1550 219.2895 336.8818 534.7502 802.1926 1129.5555 1589.2167 2246.8167 3140.4595 4756.1758 7787.3101 13879.0361 | lr 1.4e-04 | norm 5054.8262 | dt 9.803 +type train | step 4185 | loss 96.3576 202.7617 314.9543 503.7581 763.0739 1075.0076 1524.1881 2155.7905 3041.5923 4549.3252 7346.1587 12986.0996 | lr 1.4e-04 | norm 3580.4690 | dt 9.794 +type train | step 4186 | loss 100.1537 213.5229 326.6704 517.7485 782.8890 1104.8666 1553.0306 2196.8130 3073.0928 4627.7275 7558.8193 13398.9668 | lr 1.4e-04 | norm 4205.4023 | dt 9.792 +type train | step 4187 | loss 102.8563 219.6126 335.8177 533.7498 805.8383 1130.5090 1588.1450 2240.0337 3130.2959 4707.7192 7638.6406 13409.6631 | lr 1.4e-04 | norm 3491.9805 | dt 9.789 +type train | step 4188 | loss 94.6017 199.2733 309.5477 497.7155 764.3947 1088.2526 1542.6355 2193.0637 3095.2195 4651.0693 7572.0527 13453.7314 | lr 1.3e-04 | norm 4089.5591 | dt 9.807 +type train | step 4189 | loss 96.5800 203.4745 316.3094 511.3951 776.3790 1116.7095 1584.1107 2259.4807 3122.1726 4697.3740 7600.5610 13510.8418 | lr 1.3e-04 | norm 4566.9463 | dt 9.777 +type train | step 4190 | loss 99.7120 209.0623 323.9340 518.8261 784.9116 1110.9646 1563.0034 2210.9624 3114.4226 4669.4663 7577.5859 13356.9502 | lr 1.3e-04 | norm 3585.9475 | dt 9.787 +type train | step 4191 | loss 102.5044 213.0278 322.6193 521.1008 786.9314 1140.5819 1622.7162 2344.1284 3258.5984 4979.5093 8242.1426 14784.5049 | lr 1.3e-04 | norm 6623.7036 | dt 9.775 +type train | step 4192 | loss 97.2508 208.2725 322.9030 517.5025 785.1635 1119.1689 1582.8940 2246.2148 3170.4460 4802.1787 7762.5615 13724.2285 | lr 1.3e-04 | norm 3788.0662 | dt 9.785 +type train | step 4193 | loss 101.0938 220.8455 340.4047 541.7250 821.6256 1170.0801 1659.9727 2362.0212 3307.2148 5004.1221 8117.2007 14327.7451 | lr 1.3e-04 | norm 6862.9731 | dt 9.787 +type train | step 4194 | loss 98.0370 207.7235 321.5571 516.0969 789.7086 1131.3799 1594.7268 2274.3176 3163.1165 4753.8042 7680.1753 13588.7969 | lr 1.3e-04 | norm 3742.5583 | dt 9.802 +type train | step 4195 | loss 100.4888 208.5746 323.2196 518.4918 787.8494 1117.2683 1570.0022 2228.0889 3119.9993 4670.5166 7575.6641 13413.6367 | lr 1.3e-04 | norm 3841.9377 | dt 9.794 +type train | step 4196 | loss 97.4725 205.2653 315.8221 504.9185 766.8840 1084.3418 1535.0734 2175.8904 3060.1313 4599.5234 7424.0386 13135.8779 | lr 1.3e-04 | norm 4074.6240 | dt 9.784 +type train | step 4197 | loss 96.5183 201.9150 307.4706 492.8053 744.0662 1065.8545 1515.9458 2169.0840 3053.3367 4625.0586 7536.4873 13508.7168 | lr 1.3e-04 | norm 4123.8760 | dt 9.790 +type train | step 4198 | loss 101.5515 218.2048 333.2994 531.1882 791.7775 1121.1703 1564.7427 2193.9580 3045.1453 4581.6592 7442.4292 13207.2363 | lr 1.3e-04 | norm 4017.9944 | dt 9.790 +type train | step 4199 | loss 95.8694 200.9643 313.5067 497.9545 757.5829 1073.1182 1522.9370 2148.7866 3032.9070 4565.6484 7399.8149 12957.0410 | lr 1.3e-04 | norm 3470.4871 | dt 9.792 +type train | step 4200 | loss 94.3271 197.3120 306.3682 496.4799 760.8397 1088.3051 1551.3512 2212.5869 3121.3728 4712.7324 7663.0449 13556.6719 | lr 1.3e-04 | norm 3752.5020 | dt 9.771 +type train | step 4201 | loss 97.4044 203.5067 314.7359 504.4700 765.6677 1089.7870 1537.3787 2179.1218 3071.6301 4619.4658 7521.8223 13346.3027 | lr 1.3e-04 | norm 3484.3643 | dt 9.800 +type train | step 4202 | loss 96.9722 203.7927 312.1730 498.8682 752.5417 1074.4326 1522.7961 2178.4849 3054.8923 4637.0347 7636.4502 13586.5869 | lr 1.3e-04 | norm 4929.5059 | dt 9.796 +type train | step 4203 | loss 101.3312 217.9766 332.8818 526.9308 801.2834 1124.4817 1588.5438 2243.4333 3161.0303 4808.7559 7860.8110 13965.4443 | lr 1.3e-04 | norm 5242.3271 | dt 9.790 +type train | step 4204 | loss 95.1163 199.7716 311.8513 500.8502 761.0410 1079.3384 1523.7933 2166.2371 3054.1125 4620.2554 7516.9438 13267.9980 | lr 1.3e-04 | norm 3380.3914 | dt 9.803 +type train | step 4205 | loss 104.3548 221.4426 336.4383 532.3231 796.7682 1129.9990 1585.9404 2247.8176 3135.2100 4708.4365 7653.1411 13526.4258 | lr 1.3e-04 | norm 3592.8523 | dt 9.797 +type train | step 4206 | loss 96.1792 200.6384 310.0035 496.0626 754.1392 1064.4493 1499.8184 2122.6860 2992.1646 4501.2021 7331.1714 12980.9297 | lr 1.3e-04 | norm 3452.1721 | dt 9.804 +type train | step 4207 | loss 94.7807 202.3639 315.2370 509.0447 780.4819 1122.5215 1604.6091 2306.6846 3253.2256 4984.8975 8232.5166 14811.6855 | lr 1.3e-04 | norm 6775.6104 | dt 9.775 +type train | step 4208 | loss 94.4949 198.7893 304.9922 488.5592 741.8532 1057.9872 1498.4392 2131.8623 3004.8076 4558.4116 7399.8179 13040.8857 | lr 1.3e-04 | norm 3194.6609 | dt 9.800 +type train | step 4209 | loss 96.9195 209.0004 325.8940 523.6605 802.8277 1153.8497 1640.9069 2356.8193 3332.8228 5079.9160 8253.5107 14627.5176 | lr 1.3e-04 | norm 4636.3354 | dt 9.778 +type train | step 4210 | loss 93.0372 196.1446 306.1994 492.4588 748.9648 1061.4777 1509.4708 2147.6680 3041.4788 4617.3784 7561.6143 13425.6104 | lr 1.3e-04 | norm 3467.2964 | dt 9.802 +type train | step 4211 | loss 98.0151 205.6698 317.0436 506.8179 767.5588 1090.9146 1537.1110 2176.2021 3072.2957 4618.8105 7486.5264 13185.8740 | lr 1.3e-04 | norm 3890.8796 | dt 9.802 +type train | step 4212 | loss 96.4827 206.3430 316.9955 508.8212 774.1194 1109.0303 1579.7021 2259.2651 3178.2056 4802.6587 7781.4219 13772.9062 | lr 1.3e-04 | norm 4096.0132 | dt 9.782 +type train | step 4213 | loss 103.6983 216.3075 329.8099 525.2267 781.7250 1107.3142 1559.2964 2188.6621 3058.8652 4592.3477 7457.8369 13275.5713 | lr 1.3e-04 | norm 3834.8789 | dt 9.794 +type train | step 4214 | loss 91.1875 191.9274 299.9986 486.4934 747.0159 1068.5626 1518.8116 2178.0439 3083.5100 4690.3501 7658.1782 13523.0088 | lr 1.3e-04 | norm 3633.7981 | dt 9.791 +type train | step 4215 | loss 96.9597 206.0923 314.4682 503.8802 765.7719 1088.8048 1536.5366 2180.7959 3067.5720 4618.5493 7540.2495 13366.7793 | lr 1.3e-04 | norm 3650.1653 | dt 9.798 +type train | step 4216 | loss 98.1231 210.5380 319.4669 509.4614 768.4354 1085.9614 1532.0045 2162.4871 3032.0757 4554.3584 7410.6309 13120.5869 | lr 1.3e-04 | norm 3954.9202 | dt 9.783 +type train | step 4217 | loss 103.6469 221.8731 338.2624 531.2950 790.7314 1120.9840 1574.8424 2232.2964 3110.3274 4708.4819 7719.1934 13762.1162 | lr 1.3e-04 | norm 4378.6626 | dt 9.788 +type train | step 4218 | loss 97.5778 203.7836 316.2431 506.6295 769.5704 1111.5095 1576.7175 2258.1204 3181.4526 4788.0352 7776.4956 13691.2520 | lr 1.3e-04 | norm 4284.0781 | dt 9.780 +type train | step 4219 | loss 101.9552 217.4283 335.1661 531.7543 800.5004 1130.6721 1585.7810 2242.5173 3153.5476 4755.1294 7708.4014 13580.2666 | lr 1.3e-04 | norm 3338.9097 | dt 9.792 +type train | step 4220 | loss 96.1427 203.7068 312.3362 502.6404 761.2786 1078.9299 1519.6287 2156.2429 3025.4731 4538.3350 7367.1841 12972.3730 | lr 1.3e-04 | norm 3167.3042 | dt 9.804 +type train | step 4221 | loss 93.3411 195.8161 303.2867 486.1907 738.8456 1049.5452 1482.5704 2103.2053 2975.2432 4491.6123 7304.0112 12790.0664 | lr 1.3e-04 | norm 3458.0847 | dt 9.797 +type train | step 4222 | loss 99.5471 211.0344 323.7130 519.2799 780.8179 1121.0215 1590.2974 2271.2495 3161.6772 4773.2979 7780.3813 13759.2617 | lr 1.3e-04 | norm 3847.3586 | dt 9.798 +type train | step 4223 | loss 96.8079 203.6103 317.7293 512.9630 775.9427 1100.3502 1549.0592 2196.9551 3100.0630 4690.9609 7658.9375 13515.5645 | lr 1.3e-04 | norm 3758.6802 | dt 9.807 +type train | step 4224 | loss 100.4849 213.2249 321.2219 508.5292 765.1045 1079.6348 1526.3099 2166.9465 3027.8264 4604.5835 7543.0693 13355.2080 | lr 1.3e-04 | norm 3864.1809 | dt 9.797 +type train | step 4225 | loss 96.5544 203.5294 314.2654 510.8637 780.4766 1110.6396 1570.8054 2233.3015 3139.0178 4767.8535 7795.1572 13897.3125 | lr 1.3e-04 | norm 4309.5312 | dt 9.791 +type train | step 4226 | loss 101.6695 216.8992 330.9813 518.2723 780.2934 1097.0295 1538.3297 2168.4460 3046.1602 4591.5586 7475.9814 13290.2520 | lr 1.3e-04 | norm 5715.6362 | dt 9.792 +type train | step 4227 | loss 94.3548 196.9142 306.2766 492.9471 750.9380 1068.4524 1507.3341 2143.6785 3022.9517 4562.0410 7459.8872 13321.1553 | lr 1.3e-04 | norm 3638.4834 | dt 9.784 +type train | step 4228 | loss 96.4904 202.3450 317.1016 509.3088 769.8210 1093.9460 1534.7772 2173.8823 3072.7698 4628.3828 7568.6362 13431.4463 | lr 1.3e-04 | norm 3572.7073 | dt 9.783 +type train | step 4229 | loss 101.3032 211.0746 331.0663 528.8926 804.0627 1161.0913 1640.9331 2358.7410 3267.7766 4905.4663 7980.4487 14098.3721 | lr 1.3e-04 | norm 4737.6387 | dt 9.790 +type train | step 4230 | loss 102.1848 215.7366 332.8502 535.2809 806.3796 1152.8718 1620.9255 2298.6592 3190.4165 4782.7725 7768.7158 13708.8613 | lr 1.3e-04 | norm 5475.5107 | dt 9.800 +type train | step 4231 | loss 96.2950 203.3745 315.2682 507.8681 769.4551 1095.2311 1544.2633 2200.9319 3092.5664 4659.0015 7598.7744 13451.6934 | lr 1.3e-04 | norm 4499.0205 | dt 9.799 +type train | step 4232 | loss 96.4732 202.0229 312.5189 502.7086 765.5746 1088.6918 1539.7555 2200.4790 3109.4526 4706.5801 7608.2739 13375.0879 | lr 1.3e-04 | norm 3552.9282 | dt 9.789 +type train | step 4233 | loss 98.9774 207.0729 313.4272 504.1291 757.1913 1076.4938 1515.9788 2154.6392 3042.4441 4611.8750 7561.2744 13506.7295 | lr 1.3e-04 | norm 4911.6333 | dt 9.790 +type train | step 4234 | loss 102.4254 218.7670 334.3667 529.6731 792.7625 1123.1271 1576.9180 2227.4849 3119.3557 4679.2744 7603.6802 13444.8867 | lr 1.3e-04 | norm 4006.6213 | dt 9.799 +type train | step 4235 | loss 100.2723 210.5324 325.0054 525.5519 788.6889 1128.4500 1586.3904 2253.3179 3146.4780 4722.7407 7675.9160 13617.0596 | lr 1.3e-04 | norm 4006.4111 | dt 9.784 +type train | step 4236 | loss 94.4715 199.9901 313.6395 505.7080 770.5500 1095.6925 1548.6698 2197.9136 3118.1753 4706.2207 7632.3013 13523.2051 | lr 1.3e-04 | norm 3647.6064 | dt 9.797 +type train | step 4237 | loss 104.4152 223.2930 338.8220 528.8410 794.4178 1126.0642 1589.6364 2243.3940 3135.1626 4685.4424 7582.9756 13357.6973 | lr 1.3e-04 | norm 4514.9966 | dt 9.806 +type train | step 4238 | loss 98.1767 207.2560 319.9266 513.1139 789.0549 1139.4775 1629.6547 2347.6836 3298.9004 4992.8330 8081.6792 14315.9775 | lr 1.3e-04 | norm 5881.7759 | dt 9.783 +type train | step 4239 | loss 97.9506 204.8564 314.3804 502.9625 764.6129 1085.2021 1534.5133 2188.3850 3071.9949 4633.4316 7499.8540 13252.6836 | lr 1.3e-04 | norm 3745.8069 | dt 9.789 +type train | step 4240 | loss 98.9322 209.0897 321.8205 512.0388 776.5602 1098.4578 1549.3245 2197.3059 3100.5415 4664.0679 7589.2778 13368.6650 | lr 1.3e-04 | norm 3954.0508 | dt 9.792 +type train | step 4241 | loss 94.1187 203.0272 320.2952 518.0063 786.0113 1120.6240 1580.9720 2248.4297 3191.7585 4865.6060 7964.9736 14051.5664 | lr 1.3e-04 | norm 5175.3208 | dt 9.788 +type train | step 4242 | loss 103.7542 222.8706 338.0292 538.6779 811.3808 1146.1017 1601.5172 2253.0410 3141.8762 4708.5649 7657.9473 13495.5225 | lr 1.3e-04 | norm 4153.6650 | dt 9.799 +type train | step 4243 | loss 95.9466 203.7550 313.3990 507.5411 764.3026 1091.5470 1541.8394 2197.5916 3103.8223 4700.5767 7707.1494 13664.7334 | lr 1.3e-04 | norm 3921.8347 | dt 9.795 +type train | step 4244 | loss 100.3476 212.2457 323.1399 513.9807 772.3721 1095.6074 1548.7711 2196.4497 3091.1230 4657.1006 7584.3999 13402.6289 | lr 1.3e-04 | norm 3460.4685 | dt 9.815 +type train | step 4245 | loss 101.5201 215.9329 329.0069 522.9819 780.6721 1114.3164 1558.4779 2207.0078 3079.1394 4625.1499 7544.3193 13432.5527 | lr 1.3e-04 | norm 3963.8513 | dt 9.800 +type train | step 4246 | loss 103.9607 220.6510 343.2057 552.1765 832.1825 1192.2322 1668.3611 2371.4617 3302.3823 4967.1040 8126.0996 14425.4834 | lr 1.3e-04 | norm 4355.8750 | dt 9.789 +type train | step 4247 | loss 100.7675 210.5411 320.7845 510.8283 768.8019 1099.2888 1541.4055 2183.1995 3027.5298 4553.9121 7411.9946 13078.2959 | lr 1.3e-04 | norm 3903.9924 | dt 9.774 +type train | step 4248 | loss 94.4976 198.4568 309.7769 499.8371 761.3533 1076.3782 1523.1726 2177.4561 3067.3669 4633.2793 7552.1147 13316.9609 | lr 1.3e-04 | norm 3651.7209 | dt 9.799 +type train | step 4249 | loss 95.9461 201.8218 310.2137 499.4706 762.0582 1090.2043 1540.4852 2189.8164 3088.1384 4652.6421 7559.1011 13263.9082 | lr 1.3e-04 | norm 3492.4167 | dt 9.792 +type train | step 4250 | loss 100.2147 213.3472 328.7595 525.0319 784.2115 1108.5854 1552.3644 2189.5632 3070.9312 4637.3696 7550.6880 13409.1885 | lr 1.3e-04 | norm 4371.9131 | dt 9.796 +type train | step 4251 | loss 97.4433 206.2659 316.7567 507.2121 763.0487 1087.5217 1535.6212 2188.0674 3094.1204 4660.5781 7576.6763 13345.1611 | lr 1.3e-04 | norm 3382.3784 | dt 9.782 +type train | step 4252 | loss 99.6563 208.2797 318.0922 504.9533 763.0667 1081.8069 1533.9030 2174.0027 3057.4109 4609.6465 7501.2192 13325.4854 | lr 1.3e-04 | norm 3547.9275 | dt 9.778 +type train | step 4253 | loss 123.0767 262.5128 386.7386 597.3827 890.9241 1273.6111 1783.1415 2512.8042 3469.8740 5104.5967 8089.5449 13944.4951 | lr 1.3e-04 | norm 4551.9478 | dt 9.781 +type train | step 4254 | loss 101.2103 213.2567 326.5851 520.7025 783.7758 1116.1908 1571.8975 2224.9089 3103.8145 4681.7827 7638.9531 13582.7812 | lr 1.3e-04 | norm 3613.4048 | dt 9.791 +type train | step 4255 | loss 101.2426 217.0999 329.4666 523.9495 785.7463 1097.5459 1533.8654 2147.8770 2996.4858 4522.7192 7355.2554 13090.8994 | lr 1.3e-04 | norm 3957.9280 | dt 9.788 +type train | step 4256 | loss 93.0535 195.2948 303.4529 491.1061 747.7806 1073.7660 1525.4465 2177.3494 3075.4917 4638.5928 7532.2104 13256.3174 | lr 1.3e-04 | norm 4201.4204 | dt 9.801 +type train | step 4257 | loss 101.8104 215.3631 327.5847 526.1445 790.5463 1143.8982 1616.9061 2311.3108 3231.0361 4866.6914 7900.6221 13953.3281 | lr 1.3e-04 | norm 3716.8015 | dt 9.775 +type train | step 4258 | loss 97.2801 206.3367 319.8678 511.8981 770.5872 1095.4373 1542.9253 2185.8621 3069.9243 4599.1426 7520.2095 13251.4854 | lr 1.3e-04 | norm 3290.8503 | dt 9.804 +type train | step 4259 | loss 101.5567 217.1939 332.8242 527.7018 795.4381 1126.6240 1596.7383 2249.8975 3145.2844 4746.0972 7710.0244 13643.3965 | lr 1.3e-04 | norm 4322.9243 | dt 9.793 +type train | step 4260 | loss 98.8716 209.7603 324.8646 519.1978 788.7463 1118.8829 1577.8718 2249.7893 3138.4812 4735.2222 7693.3555 13525.7510 | lr 1.3e-04 | norm 4309.2905 | dt 9.785 +type train | step 4261 | loss 101.1670 217.6757 331.5703 529.7189 799.2881 1131.1031 1590.4370 2249.9404 3149.3999 4746.9688 7660.2695 13456.4648 | lr 1.3e-04 | norm 3647.5476 | dt 9.794 +type train | step 4262 | loss 96.8911 203.4283 310.6964 494.0619 747.0359 1057.9269 1490.3336 2111.5554 2960.7756 4460.8643 7247.1440 12830.2861 | lr 1.3e-04 | norm 3410.3743 | dt 9.794 +type train | step 4263 | loss 105.5209 224.1991 342.7828 542.5460 813.1373 1157.6941 1631.9232 2316.3877 3221.2935 4861.2891 7937.9214 14164.4697 | lr 1.3e-04 | norm 4974.1206 | dt 9.785 +type train | step 4264 | loss 93.6186 198.0686 308.6533 492.8452 750.2068 1068.0527 1516.9314 2147.7754 3044.9556 4547.6860 7259.9058 12638.4082 | lr 1.3e-04 | norm 5427.7417 | dt 9.805 +type train | step 4265 | loss 110.0518 235.7404 354.6597 553.9410 828.0525 1165.3833 1622.5050 2281.6992 3121.3015 4584.1289 7359.1318 12918.0078 | lr 1.3e-04 | norm 3927.7527 | dt 9.777 +type train | step 4266 | loss 98.3984 206.7201 319.6010 505.8915 763.9000 1091.0587 1536.4528 2185.8269 3080.6438 4638.2251 7508.8682 13250.2422 | lr 1.3e-04 | norm 3881.9197 | dt 9.796 +type train | step 4267 | loss 91.3267 191.4749 296.8928 478.7089 732.9175 1051.8202 1499.3031 2152.1765 3055.3198 4639.6250 7572.6099 13510.0771 | lr 1.3e-04 | norm 3825.1355 | dt 9.807 +type train | step 4268 | loss 109.6370 230.9205 349.5710 548.0173 817.1122 1171.8477 1650.7661 2346.2117 3259.0400 4894.7314 7964.5825 14090.8340 | lr 1.3e-04 | norm 4038.8311 | dt 9.783 +type train | step 4269 | loss 94.8460 200.5859 310.4240 495.0635 747.8628 1059.1564 1500.9181 2134.5117 3019.7021 4561.3311 7442.7075 13206.9580 | lr 1.3e-04 | norm 3573.5952 | dt 9.807 +type train | step 4270 | loss 92.9491 195.8988 305.7857 492.9175 751.2526 1068.4749 1511.4353 2145.3096 3019.7932 4554.1191 7378.1392 13010.1904 | lr 1.3e-04 | norm 3466.1011 | dt 9.789 +type train | step 4271 | loss 115.7081 251.9180 376.8830 589.4817 859.3703 1210.3436 1636.7080 2244.0593 3032.5701 4433.8574 7074.6421 12573.2051 | lr 1.3e-04 | norm 5096.3970 | dt 9.763 +type train | step 4272 | loss 100.4634 212.9210 324.8912 515.0245 778.6892 1115.5288 1572.8528 2236.8652 3125.4458 4695.4126 7645.9067 13518.6455 | lr 1.3e-04 | norm 3674.6104 | dt 9.792 +type train | step 4273 | loss 99.5837 208.8831 319.8607 511.0660 769.5031 1097.2754 1546.6615 2189.3867 3081.9705 4684.0469 7650.0562 13502.0449 | lr 1.3e-04 | norm 3601.5925 | dt 9.782 +type train | step 4274 | loss 116.2183 251.1916 376.0854 583.3894 858.0445 1215.5793 1690.8871 2366.4768 3254.0591 4900.5527 7993.4482 14162.9072 | lr 1.3e-04 | norm 6246.6318 | dt 9.774 +type train | step 4275 | loss 92.1139 193.3972 302.7246 493.1740 760.3934 1097.7212 1565.1792 2270.2717 3202.5168 4853.1377 7995.2642 14223.0137 | lr 1.3e-04 | norm 4449.1377 | dt 9.800 +type train | step 4276 | loss 92.3291 195.4941 304.9224 494.9707 752.8386 1078.6600 1529.7814 2195.7988 3110.6746 4715.8960 7659.6768 13531.3682 | lr 1.3e-04 | norm 3770.9788 | dt 9.810 +type train | step 4277 | loss 98.5578 205.0603 319.4396 509.3756 767.4722 1092.5754 1541.3351 2197.8506 3072.5193 4648.1362 7671.2959 13712.6689 | lr 1.3e-04 | norm 4816.7266 | dt 9.788 +type train | step 4278 | loss 95.2348 204.2095 313.0657 499.5888 760.7590 1092.1211 1559.1207 2238.2627 3161.6938 4769.6196 7692.7168 13502.6006 | lr 1.3e-04 | norm 4550.4136 | dt 9.788 +type train | step 4279 | loss 100.0004 211.1505 322.6785 511.3450 771.5108 1102.4607 1552.4534 2226.6648 3107.2773 4708.4805 7709.6216 13843.3262 | lr 1.3e-04 | norm 4700.3003 | dt 9.787 +type train | step 4280 | loss 95.9624 201.1555 308.3562 488.8848 746.5350 1061.2421 1499.1516 2141.9341 3012.0732 4549.0903 7441.2178 13108.2656 | lr 1.3e-04 | norm 3802.9241 | dt 9.788 +type train | step 4281 | loss 95.2195 201.4016 316.8915 508.3112 775.2131 1111.1073 1564.6713 2229.2742 3121.2021 4693.1387 7647.2188 13523.8652 | lr 1.3e-04 | norm 3879.9338 | dt 9.783 +type train | step 4282 | loss 94.7787 199.5992 314.5826 512.6111 786.0508 1126.5804 1602.2208 2294.7881 3221.6394 4805.5312 7728.5894 13518.0918 | lr 1.3e-04 | norm 3512.1301 | dt 9.780 +type train | step 4283 | loss 96.5352 201.8363 310.7784 497.9219 754.6009 1070.6338 1517.5403 2156.4436 3033.8379 4603.2480 7499.5527 13220.1797 | lr 1.3e-04 | norm 4539.8027 | dt 9.783 +type train | step 4284 | loss 102.7143 218.0328 331.1496 527.3882 791.3880 1134.3000 1596.7827 2265.9446 3128.2146 4694.7002 7633.1362 13458.1826 | lr 1.3e-04 | norm 4484.9468 | dt 9.777 +type train | step 4285 | loss 101.1649 215.9414 328.6254 523.7519 781.2920 1122.5897 1583.2053 2248.7742 3144.5725 4730.8999 7667.0386 13487.0234 | lr 1.3e-04 | norm 3898.1694 | dt 9.784 +type train | step 4286 | loss 97.0056 204.1249 313.4625 501.4221 755.5003 1088.1177 1537.5729 2191.3171 3078.4683 4638.7129 7512.9204 13197.4443 | lr 1.3e-04 | norm 4122.7153 | dt 9.784 +type train | step 4287 | loss 95.9432 201.9995 309.0418 493.9695 746.3291 1065.7885 1506.5145 2149.9265 3022.4861 4592.6152 7484.2173 13282.4629 | lr 1.3e-04 | norm 3653.2188 | dt 9.790 +type train | step 4288 | loss 92.4508 192.3606 301.1926 489.6360 746.8546 1059.0239 1510.2825 2156.3357 3052.3364 4639.8135 7621.5908 13553.9883 | lr 1.3e-04 | norm 4796.2627 | dt 9.789 +type train | step 4289 | loss 94.5221 200.2931 311.2835 499.4188 760.1216 1087.5150 1548.6687 2215.6372 3125.7144 4713.4844 7653.7598 13497.6963 | lr 1.3e-04 | norm 3516.8840 | dt 9.789 +type train | step 4290 | loss 108.8826 231.9559 354.1056 565.2485 831.3711 1180.0068 1640.0573 2316.8025 3183.2217 4792.7632 7789.7944 13895.6084 | lr 1.3e-04 | norm 5869.1763 | dt 9.775 +type train | step 4291 | loss 95.1542 200.0671 305.6478 495.2712 753.2208 1083.2897 1531.8792 2193.1753 3083.8508 4686.3784 7672.0859 13707.5273 | lr 1.3e-04 | norm 4140.7109 | dt 9.776 +type train | step 4292 | loss 105.5224 221.7915 331.8278 522.7753 780.1290 1106.7953 1560.3097 2222.2622 3121.2278 4741.1577 7704.2090 13631.6885 | lr 1.3e-04 | norm 4132.2817 | dt 9.779 +type train | step 4293 | loss 99.7440 211.5950 325.1820 517.1694 781.8427 1117.1246 1577.7488 2252.8237 3165.1133 4799.8506 7824.3545 13804.3457 | lr 1.3e-04 | norm 3840.0132 | dt 9.793 +type train | step 4294 | loss 98.5029 208.3799 319.5613 510.3159 770.1790 1098.6598 1548.6851 2199.1233 3086.5437 4678.9297 7603.7930 13356.5498 | lr 1.3e-04 | norm 3369.2927 | dt 9.792 +type train | step 4295 | loss 100.2012 211.2568 318.3886 507.9295 760.0162 1094.2817 1546.3728 2200.9077 3068.5923 4660.1509 7677.4111 13774.8916 | lr 1.3e-04 | norm 4263.2715 | dt 9.801 +type train | step 4296 | loss 95.2828 199.0548 306.9406 493.5581 749.8547 1079.1411 1531.6116 2192.3948 3101.1694 4732.8555 7733.8467 13668.3867 | lr 1.3e-04 | norm 3461.8586 | dt 9.788 +type train | step 4297 | loss 97.5440 205.0509 317.3384 508.0005 762.9682 1082.4783 1523.9366 2162.9468 3033.0400 4579.4785 7482.6797 13293.0410 | lr 1.3e-04 | norm 3599.6562 | dt 9.789 +type train | step 4298 | loss 95.5780 198.5140 304.6007 489.9503 741.5654 1073.5321 1525.6884 2187.1555 3061.1084 4651.2314 7638.8320 13516.3867 | lr 1.3e-04 | norm 3565.3025 | dt 9.797 +type train | step 4299 | loss 100.5897 211.2420 329.0742 531.7099 798.5730 1150.3005 1628.8595 2331.1714 3252.4194 4875.9741 7901.0449 13904.5127 | lr 1.3e-04 | norm 4062.0723 | dt 9.788 +type train | step 4300 | loss 97.3400 199.4049 311.7085 506.7609 769.1003 1117.8401 1590.8584 2290.7288 3196.6177 4809.9536 7795.8843 13782.2852 | lr 1.3e-04 | norm 6414.8296 | dt 9.786 +type train | step 4301 | loss 98.4828 208.0436 317.1471 505.2641 766.2443 1081.1715 1528.3326 2168.0154 3036.6865 4541.8726 7347.7690 12913.6992 | lr 1.3e-04 | norm 3908.0898 | dt 9.786 +type train | step 4302 | loss 99.1761 206.0294 318.4876 503.3257 757.2579 1078.8270 1517.7887 2159.8516 3021.6526 4563.7168 7459.7690 13150.4268 | lr 1.3e-04 | norm 4050.5181 | dt 9.781 +type train | step 4303 | loss 98.6759 207.2158 321.9256 514.5679 775.7731 1119.4276 1582.9984 2255.0684 3143.8538 4724.9243 7661.3101 13545.9326 | lr 1.3e-04 | norm 4540.0962 | dt 9.788 +type train | step 4304 | loss 97.9576 203.1652 319.2746 510.0016 763.7468 1090.4391 1546.0481 2200.4441 3092.9377 4668.5337 7595.2998 13409.5273 | lr 1.3e-04 | norm 3412.8540 | dt 9.787 +type train | step 4305 | loss 103.5230 216.6961 334.7107 529.9925 794.8148 1132.0238 1577.5804 2202.4644 3035.0029 4529.0908 7348.3584 12979.9922 | lr 1.3e-04 | norm 5197.2954 | dt 9.782 +type train | step 4306 | loss 95.5499 201.3352 309.9390 502.6011 763.8273 1094.3224 1549.2406 2211.0178 3118.8008 4715.2119 7679.2397 13610.8691 | lr 1.3e-04 | norm 3964.1213 | dt 9.803 +type train | step 4307 | loss 100.4440 213.2887 327.6310 519.0820 776.6727 1107.4178 1566.1625 2218.6057 3108.7812 4692.3984 7626.2603 13462.2168 | lr 1.3e-04 | norm 4223.5737 | dt 9.791 +type train | step 4308 | loss 100.9367 209.2934 318.9083 509.6375 763.2793 1092.2327 1537.2465 2181.7229 3059.8098 4614.6255 7544.7817 13441.0449 | lr 1.3e-04 | norm 3743.5029 | dt 9.796 +type train | step 4309 | loss 94.0793 197.5885 304.7946 491.1188 742.0527 1058.6477 1501.8132 2135.2080 3014.0291 4575.5659 7498.8315 13187.4990 | lr 1.3e-04 | norm 3676.5271 | dt 9.792 +type train | step 4310 | loss 97.2458 200.3373 307.7881 492.6627 747.7131 1066.0530 1501.8790 2137.3994 2995.6479 4550.7705 7474.0898 13156.7891 | lr 1.3e-04 | norm 3638.9429 | dt 9.791 +type train | step 4311 | loss 100.2000 209.2280 323.0281 528.3615 789.8364 1130.5422 1592.7655 2262.0383 3195.1270 4863.0005 7935.8125 14100.7891 | lr 1.3e-04 | norm 4863.5498 | dt 9.805 +type train | step 4312 | loss 95.3282 199.9116 305.0803 488.6501 736.2549 1052.1389 1484.5562 2109.8433 2967.6726 4475.9214 7293.8281 12813.6826 | lr 1.3e-04 | norm 3580.0549 | dt 9.782 +type train | step 4313 | loss 122.6310 251.5748 381.1168 601.3972 874.8210 1273.6421 1789.0580 2487.9885 3322.0562 4809.5425 7720.1025 14101.9219 | lr 1.3e-04 | norm 15160.3506 | dt 9.759 +type train | step 4314 | loss 130.0792 264.3118 400.8331 627.5385 905.6031 1313.0862 1835.0520 2533.4998 3389.4773 4888.3008 7839.7129 14216.3057 | lr 1.3e-04 | norm 14524.8828 | dt 9.749 +type train | step 4315 | loss 90.4411 188.0221 293.3320 476.2834 724.8141 1046.6006 1496.1265 2146.0596 3038.8110 4605.3774 7471.8301 13123.8994 | lr 1.3e-04 | norm 4189.1582 | dt 9.800 +type train | step 4316 | loss 95.5323 200.1707 309.6927 497.9423 750.6660 1064.3347 1499.4852 2131.1702 3006.3833 4547.9624 7385.2778 13036.6650 | lr 1.3e-04 | norm 3879.6526 | dt 9.804 +type train | step 4317 | loss 91.7208 192.6891 299.8373 487.4186 739.1469 1052.9652 1495.3625 2131.2307 3024.2046 4575.5254 7409.3467 13073.8779 | lr 1.2e-04 | norm 3379.1780 | dt 9.822 +type train | step 4318 | loss 99.6071 206.8252 317.2715 505.9132 767.0834 1100.0178 1561.7434 2230.3726 3117.1812 4701.2417 7663.4673 13577.9199 | lr 1.2e-04 | norm 3902.6384 | dt 9.783 +type train | step 4319 | loss 92.1210 191.9352 300.0621 481.5076 737.4410 1055.5114 1503.9528 2154.0449 3031.0950 4619.6987 7533.2524 13402.9854 | lr 1.2e-04 | norm 4048.3108 | dt 9.803 +type train | step 4320 | loss 102.5930 218.6548 332.2864 527.3343 786.7394 1112.1705 1551.0706 2180.2888 3013.6099 4498.9414 7249.7974 12754.0977 | lr 1.2e-04 | norm 4599.0542 | dt 9.801 +type train | step 4321 | loss 98.0561 207.1128 317.2184 504.8073 760.1221 1078.1887 1518.9829 2151.1487 3011.6931 4529.2515 7347.1675 12942.1377 | lr 1.2e-04 | norm 3622.7449 | dt 9.822 +type train | step 4322 | loss 101.4928 212.4088 326.6099 517.0738 776.7592 1113.4031 1571.1476 2233.0073 3130.1765 4737.1953 7707.0361 13555.8154 | lr 1.2e-04 | norm 3547.0144 | dt 9.817 +type train | step 4323 | loss 98.3615 207.8186 318.5688 508.6960 767.0974 1095.8079 1547.7849 2187.6580 3078.9656 4600.7178 7400.3892 12836.1768 | lr 1.2e-04 | norm 3586.9570 | dt 9.793 +type train | step 4324 | loss 99.2777 213.1556 333.2564 532.8402 810.5518 1154.6095 1629.5566 2315.6301 3254.8545 4906.9556 7975.0688 14186.5078 | lr 1.2e-04 | norm 4408.8008 | dt 9.793 +type train | step 4325 | loss 92.8104 195.0008 303.9775 487.9152 740.4744 1054.3628 1493.5103 2131.8757 3006.6943 4567.8306 7458.6421 13127.1094 | lr 1.2e-04 | norm 3318.2996 | dt 9.777 +type train | step 4326 | loss 116.2858 252.5886 379.0302 605.6438 879.8809 1244.0259 1717.9727 2399.5039 3273.8684 4851.6167 7867.3408 14024.3945 | lr 1.2e-04 | norm 6772.0884 | dt 9.776 +type train | step 4327 | loss 94.4144 198.9381 305.4680 488.8077 743.7292 1067.4988 1513.8092 2169.7344 3078.2437 4648.1455 7562.6221 13331.2080 | lr 1.2e-04 | norm 3910.0010 | dt 9.791 +type train | step 4328 | loss 91.7879 198.4261 309.0872 499.1567 767.4678 1104.4753 1578.9746 2260.8169 3218.8069 4919.8960 8139.0967 14692.5557 | lr 1.2e-04 | norm 6769.8994 | dt 9.796 +type train | step 4329 | loss 117.7477 250.5421 381.7608 595.9816 888.1879 1258.0548 1760.9712 2475.9915 3396.6255 5013.8164 8071.9170 14190.7129 | lr 1.2e-04 | norm 7170.6904 | dt 9.792 +type train | step 4330 | loss 117.3083 247.9670 373.3399 586.9351 875.3545 1222.8214 1705.3569 2386.8706 3278.5083 4897.5586 7881.4414 13840.2324 | lr 1.2e-04 | norm 7172.0737 | dt 9.785 +type train | step 4331 | loss 93.2243 195.2780 305.2162 490.0389 745.1099 1061.2981 1505.4220 2148.0227 3030.3040 4585.8267 7518.3970 13289.2607 | lr 1.2e-04 | norm 3356.8516 | dt 9.787 +type train | step 4332 | loss 95.9770 202.2932 310.2889 497.4114 752.8615 1089.4794 1550.0989 2227.3596 3140.2188 4768.3296 7724.1230 13561.0928 | lr 1.2e-04 | norm 3637.2629 | dt 9.787 +type train | step 4333 | loss 90.6513 189.6087 294.8512 474.4397 724.3759 1044.9867 1478.3020 2119.3069 2998.3701 4554.5581 7410.2388 12936.3975 | lr 1.2e-04 | norm 3531.2310 | dt 9.782 +type train | step 4334 | loss 100.3416 214.3513 323.9270 517.6188 783.0076 1124.9415 1592.4563 2272.1848 3182.2373 4771.9937 7734.3794 13696.0537 | lr 1.2e-04 | norm 4250.4111 | dt 9.793 +type train | step 4335 | loss 96.6451 204.2343 312.6193 497.4768 750.2327 1069.2096 1513.2029 2142.7744 3003.3306 4530.4683 7376.3994 13009.1992 | lr 1.2e-04 | norm 4143.7871 | dt 9.799 +type train | step 4336 | loss 102.7549 216.3437 333.4398 526.3632 785.2059 1112.4918 1559.9023 2206.0081 3106.0703 4677.9092 7596.8340 13394.0254 | lr 1.2e-04 | norm 3331.5754 | dt 9.805 +type train | step 4337 | loss 90.2863 188.3467 292.9714 475.5289 726.6781 1051.1340 1502.5056 2171.3472 3085.2522 4661.3838 7574.9604 13323.0049 | lr 1.2e-04 | norm 3794.2358 | dt 9.780 +type train | step 4338 | loss 97.1783 203.1768 311.0915 498.9020 750.7971 1070.6299 1520.9235 2154.2363 3030.2146 4578.9878 7442.1572 13222.9160 | lr 1.2e-04 | norm 4380.5693 | dt 9.773 +type train | step 4339 | loss 101.2999 214.9032 327.4362 520.2925 780.7372 1114.0033 1575.5781 2231.0684 3151.8708 4773.6279 7776.7637 13639.3555 | lr 1.2e-04 | norm 3574.2222 | dt 9.788 +type train | step 4340 | loss 98.1650 208.3968 320.5007 517.1205 776.6661 1117.6787 1572.5020 2237.2083 3102.9260 4656.4590 7539.6211 13308.6260 | lr 1.2e-04 | norm 4448.0889 | dt 9.791 +type train | step 4341 | loss 119.8749 258.7882 392.2928 630.1740 911.6573 1335.3770 1828.3513 2539.8955 3327.6919 4868.5342 7841.8672 14317.5273 | lr 1.2e-04 | norm 11382.0684 | dt 9.760 +type train | step 4342 | loss 108.3079 243.8745 369.3562 578.8441 850.9319 1200.8011 1625.6974 2208.2954 2974.9656 4330.2456 6839.8682 12103.8750 | lr 1.2e-04 | norm 5332.2622 | dt 9.753 +type train | step 4343 | loss 110.6689 234.1815 355.7823 556.3622 822.3325 1158.3573 1598.9813 2229.4326 3064.0151 4546.0894 7318.8691 12969.9531 | lr 1.2e-04 | norm 4378.4824 | dt 9.766 +type train | step 4344 | loss 99.8040 209.4597 323.3243 510.1579 765.7134 1097.8300 1539.7731 2183.3328 3038.6555 4590.4604 7482.5645 13220.2109 | lr 1.2e-04 | norm 3773.9688 | dt 9.782 +type train | step 4345 | loss 93.6824 198.1060 307.0126 489.6648 745.3110 1066.7502 1516.3275 2165.4646 3051.6836 4634.2603 7564.6211 13399.7656 | lr 1.2e-04 | norm 3700.8167 | dt 9.790 +type train | step 4346 | loss 97.3558 204.4673 315.6988 506.7086 767.9880 1105.9471 1560.5410 2223.4653 3132.5027 4748.0474 7719.9736 13747.5723 | lr 1.2e-04 | norm 4026.2507 | dt 9.788 +type train | step 4347 | loss 95.1467 198.5839 306.8205 491.7663 744.8547 1067.4189 1513.4885 2155.1948 3034.3325 4576.7759 7427.3672 13108.7197 | lr 1.2e-04 | norm 3698.7336 | dt 9.793 +type train | step 4348 | loss 99.6252 210.9104 323.3240 515.2832 768.9541 1097.8684 1548.7659 2199.5610 3060.9756 4606.3008 7474.3965 13209.2266 | lr 1.2e-04 | norm 4842.5771 | dt 9.781 +type train | step 4349 | loss 97.9136 206.5878 320.6632 518.2152 780.8322 1132.8094 1601.6794 2278.7378 3152.1414 4711.3477 7620.9585 13451.7949 | lr 1.2e-04 | norm 4065.6538 | dt 9.782 +type train | step 4350 | loss 94.8219 198.6618 309.3347 500.0415 759.6697 1093.1415 1552.2837 2215.9082 3127.2449 4730.4790 7710.8179 13734.3350 | lr 1.2e-04 | norm 4219.4727 | dt 9.786 +type train | step 4351 | loss 89.4886 187.7205 297.3028 483.8771 752.4408 1081.2799 1541.6724 2223.9929 3139.8740 4892.6914 8051.8613 14495.3623 | lr 1.2e-04 | norm 9472.3525 | dt 9.761 +type train | step 4352 | loss 100.0470 213.1076 327.2411 516.4418 775.9373 1108.9403 1557.5447 2206.4448 3058.9495 4580.3105 7416.3252 13164.5205 | lr 1.2e-04 | norm 3817.2590 | dt 9.786 +type train | step 4353 | loss 96.1888 201.1385 311.1842 500.7165 755.3074 1087.8889 1537.6050 2183.8291 3064.6289 4630.0576 7579.6812 13418.3799 | lr 1.2e-04 | norm 3766.1438 | dt 9.797 +type train | step 4354 | loss 102.3059 212.1453 325.1196 521.1761 781.7515 1118.9211 1580.2538 2247.0503 3124.0713 4701.4478 7624.5811 13437.7852 | lr 1.2e-04 | norm 3717.1660 | dt 9.796 +type train | step 4355 | loss 101.3208 214.4100 329.7574 524.4870 786.3665 1110.6846 1556.7008 2188.4944 3058.2854 4594.1387 7487.8906 13138.6152 | lr 1.2e-04 | norm 3380.8193 | dt 9.791 +type train | step 4356 | loss 96.0846 200.2163 310.6750 497.7012 757.0203 1091.5209 1547.5265 2212.4143 3117.8430 4689.8706 7607.9126 13359.3662 | lr 1.2e-04 | norm 3723.3101 | dt 9.784 +type train | step 4357 | loss 92.7119 192.7323 300.3694 484.2536 740.8974 1061.8785 1511.4741 2158.0051 3057.0581 4616.2285 7466.5933 13079.2998 | lr 1.2e-04 | norm 3295.0203 | dt 9.789 +type train | step 4358 | loss 97.0700 202.4697 312.5620 505.6067 760.6608 1092.4257 1532.9550 2178.3279 3029.1558 4534.2217 7371.8228 13044.7207 | lr 1.2e-04 | norm 3528.2690 | dt 9.780 +type train | step 4359 | loss 99.4896 208.3457 318.7061 516.2023 774.7886 1119.6710 1586.0404 2261.3276 3169.1421 4797.6040 7865.7002 14059.9199 | lr 1.2e-04 | norm 4479.0552 | dt 9.772 +type train | step 4360 | loss 97.7668 207.0462 322.2889 515.8079 779.5661 1112.9624 1560.0996 2223.3953 3097.7510 4658.2827 7549.6304 13306.9814 | lr 1.2e-04 | norm 3410.1418 | dt 9.799 +type train | step 4361 | loss 97.0560 204.0582 318.9072 511.2468 773.0308 1106.2177 1557.6143 2216.1589 3111.6018 4672.0952 7545.2773 13256.1953 | lr 1.2e-04 | norm 3015.8518 | dt 9.791 +type train | step 4362 | loss 96.7608 205.3221 316.3526 506.4233 766.1268 1092.3856 1539.1394 2188.6992 3055.5239 4613.4600 7521.5098 13387.1055 | lr 1.2e-04 | norm 4891.5210 | dt 9.791 +type train | step 4363 | loss 93.7195 194.0672 301.8151 488.7165 743.0410 1069.8992 1515.9709 2179.0530 3053.9221 4613.6875 7484.8848 13212.3486 | lr 1.2e-04 | norm 3726.9685 | dt 9.782 +type train | step 4364 | loss 93.7958 195.8469 299.4478 484.2632 734.0625 1055.6433 1503.7003 2152.1458 3032.8499 4599.1011 7543.5977 13312.4893 | lr 1.2e-04 | norm 3884.4932 | dt 9.791 +type train | step 4365 | loss 95.5761 199.7717 307.8846 493.8736 752.2903 1072.1353 1516.7607 2165.0366 3055.0508 4586.5806 7383.9004 13075.6699 | lr 1.2e-04 | norm 3522.3896 | dt 9.798 +type train | step 4366 | loss 108.0628 230.8611 350.3043 556.0793 828.8928 1169.7106 1637.2612 2313.9583 3217.6121 4816.5879 7816.4941 13789.4570 | lr 1.2e-04 | norm 5314.0928 | dt 9.788 +type train | step 4367 | loss 94.0147 199.3391 308.4231 500.1562 760.5493 1095.4858 1557.0957 2230.0400 3137.3347 4758.1401 7752.5308 13770.4883 | lr 1.2e-04 | norm 4551.4800 | dt 9.796 +type train | step 4368 | loss 89.0465 185.6420 289.5352 468.9306 714.7068 1014.2762 1441.8420 2052.2251 2922.5405 4433.9663 7259.0405 12832.5527 | lr 1.2e-04 | norm 3586.9419 | dt 9.797 +type train | step 4369 | loss 100.5858 212.8864 329.4597 524.1158 780.9171 1121.2083 1571.0239 2231.0039 3091.0269 4658.3687 7601.2139 13498.3721 | lr 1.2e-04 | norm 4678.5117 | dt 9.788 +type train | step 4370 | loss 99.5029 212.2910 324.1098 517.6130 775.3235 1110.4924 1568.3077 2232.7446 3118.8403 4687.9790 7618.4395 13327.7207 | lr 1.2e-04 | norm 3891.0002 | dt 9.789 +type train | step 4371 | loss 100.2566 209.6685 320.5709 509.4559 765.7754 1095.1262 1542.3171 2184.9443 3049.9326 4620.1606 7624.9170 13660.9863 | lr 1.2e-04 | norm 5555.9678 | dt 9.804 +type train | step 4372 | loss 109.0386 234.3761 354.2369 557.6414 831.8317 1198.8333 1665.0986 2327.7175 3141.4280 4640.2573 7466.7114 13222.8281 | lr 1.2e-04 | norm 5886.5859 | dt 9.792 +type train | step 4373 | loss 97.1821 208.4067 320.1771 515.9678 776.8931 1112.5199 1572.5167 2238.7249 3141.3384 4739.4561 7691.7246 13505.1016 | lr 1.2e-04 | norm 4339.4976 | dt 9.795 +type train | step 4374 | loss 94.1564 197.4001 305.8570 488.2218 738.4827 1061.0509 1505.8871 2145.4587 3020.8733 4576.8452 7470.9551 13257.5488 | lr 1.2e-04 | norm 4078.2336 | dt 9.793 +type train | step 4375 | loss 95.8463 199.2175 312.8999 503.7236 761.3590 1110.3685 1579.7062 2269.1946 3192.9551 4831.7295 7911.6396 14039.9893 | lr 1.2e-04 | norm 4569.3184 | dt 9.778 +type train | step 4376 | loss 93.6651 198.0529 309.3762 500.9945 762.1295 1093.8088 1552.1401 2221.1936 3151.4036 4754.1777 7689.0068 13401.0830 | lr 1.2e-04 | norm 3952.4976 | dt 9.788 +type train | step 4377 | loss 91.5000 192.5876 296.4488 477.8860 729.0568 1057.6804 1498.7178 2152.8474 3016.8262 4528.6709 7350.2056 12974.2021 | lr 1.2e-04 | norm 3589.4419 | dt 9.786 +type train | step 4378 | loss 99.9498 209.6386 321.3187 509.5500 764.0781 1087.8513 1528.2318 2161.8892 3031.0608 4561.0161 7423.4761 13075.4258 | lr 1.2e-04 | norm 4047.1643 | dt 9.796 +type train | step 4379 | loss 93.5316 197.9480 307.0082 495.8409 754.6149 1088.7263 1551.5358 2217.5078 3139.3516 4755.6387 7708.3994 13463.0078 | lr 1.2e-04 | norm 3373.8862 | dt 9.807 +type train | step 4380 | loss 98.7339 210.6942 320.3939 508.8745 768.6599 1090.3840 1523.9288 2150.7891 3010.3113 4510.7812 7303.1235 12899.6289 | lr 1.2e-04 | norm 4728.9272 | dt 9.788 +type train | step 4381 | loss 97.3265 204.3782 314.3407 503.8427 760.4578 1095.2252 1545.5518 2208.0745 3109.3240 4689.5366 7614.8354 13448.3730 | lr 1.2e-04 | norm 3689.7188 | dt 9.792 +type train | step 4382 | loss 97.5999 206.8034 319.9846 511.4334 772.6370 1100.1553 1548.2367 2191.2649 3072.3855 4640.4194 7538.0503 13258.5381 | lr 1.2e-04 | norm 3567.4062 | dt 9.796 +type train | step 4383 | loss 96.7788 202.2520 311.3521 499.8180 756.7138 1086.1173 1536.3278 2179.1785 3069.0554 4635.8682 7554.5850 13282.6689 | lr 1.2e-04 | norm 3788.7795 | dt 9.783 +type train | step 4384 | loss 85.7498 176.8935 277.5854 452.7289 696.8069 996.9054 1428.7056 2053.3916 2921.7629 4449.5181 7280.1543 12892.3066 | lr 1.2e-04 | norm 3960.9216 | dt 9.794 +type train | step 4385 | loss 95.4842 199.3123 307.0134 493.0910 746.7599 1075.5582 1520.6370 2177.8320 3062.5481 4642.1118 7570.7803 13309.1445 | lr 1.2e-04 | norm 3624.9790 | dt 9.786 +type train | step 4386 | loss 99.8780 210.1198 326.2594 522.9765 785.0161 1115.4283 1561.8927 2214.8438 3092.7808 4666.1904 7588.0430 13419.9434 | lr 1.2e-04 | norm 3381.1978 | dt 9.788 +type train | step 4387 | loss 94.8506 202.7636 312.0932 499.2906 752.4454 1066.7272 1511.2595 2146.8384 3035.2656 4589.9287 7463.7471 13178.3662 | lr 1.2e-04 | norm 3253.1855 | dt 9.788 +type train | step 4388 | loss 96.3223 202.5314 312.4818 503.1058 759.2881 1095.8030 1554.2657 2228.6467 3126.2666 4733.0117 7722.9912 13710.9316 | lr 1.2e-04 | norm 4362.8892 | dt 9.795 +type train | step 4389 | loss 103.5717 218.1276 328.8346 518.8817 772.9373 1104.1564 1540.2698 2162.6060 2994.5220 4455.9238 7146.4800 12574.5078 | lr 1.2e-04 | norm 3650.1799 | dt 9.762 +type train | step 4390 | loss 92.1627 194.0678 303.3813 487.1224 736.4672 1059.3989 1499.3989 2152.2202 3027.7051 4626.5835 7615.8970 13493.5449 | lr 1.2e-04 | norm 4064.9148 | dt 9.792 +type train | step 4391 | loss 99.4828 211.7668 326.1577 522.6191 785.4205 1125.6609 1589.1400 2258.1260 3148.0884 4713.0186 7646.5361 13526.1230 | lr 1.2e-04 | norm 4455.0356 | dt 9.797 +type train | step 4392 | loss 91.0507 194.2172 302.4590 487.7559 741.5342 1062.3142 1518.6725 2175.2485 3073.4214 4639.0532 7505.9146 13139.3730 | lr 1.2e-04 | norm 3566.2324 | dt 9.798 +type train | step 4393 | loss 90.2482 189.2648 293.4465 473.3507 728.7471 1036.7861 1486.2992 2121.7605 3009.1226 4568.6709 7465.7407 13064.3262 | lr 1.2e-04 | norm 3784.7788 | dt 9.785 +type train | step 4394 | loss 91.9911 194.9572 300.1256 478.8848 732.2328 1051.4120 1488.3799 2120.6726 2998.1045 4553.2734 7411.1113 13077.5312 | lr 1.2e-04 | norm 3639.1042 | dt 9.796 +type train | step 4395 | loss 99.5454 210.3204 324.2287 519.1619 779.2307 1119.7634 1573.5781 2235.6685 3117.3521 4730.2725 7707.5864 13735.4424 | lr 1.2e-04 | norm 4215.7949 | dt 9.792 +type train | step 4396 | loss 98.1544 205.2712 320.7872 512.5853 772.0690 1101.0236 1546.1696 2200.1558 3079.0327 4650.6846 7568.6680 13344.9863 | lr 1.2e-04 | norm 3486.0979 | dt 9.790 +type train | step 4397 | loss 95.4724 198.7364 307.7342 492.0517 743.1282 1063.5603 1503.5995 2133.8083 2996.4229 4503.9478 7320.8423 12846.4775 | lr 1.2e-04 | norm 3322.4912 | dt 9.794 +type train | step 4398 | loss 104.1814 217.3465 330.3683 526.7095 791.3395 1135.9609 1596.6742 2268.3979 3165.3618 4763.7026 7701.7969 13479.9395 | lr 1.2e-04 | norm 4116.0996 | dt 9.783 +type train | step 4399 | loss 97.7057 204.6977 316.9346 504.5422 760.3420 1086.2977 1530.2062 2172.2126 3041.7490 4581.8901 7441.4727 13134.2168 | lr 1.2e-04 | norm 3165.3752 | dt 9.799 +type train | step 4400 | loss 90.5724 188.9741 301.5196 493.4526 753.1093 1086.3013 1542.5814 2201.7849 3102.4966 4669.1201 7569.3589 13300.1602 | lr 1.2e-04 | norm 4341.9351 | dt 9.798 +type train | step 4401 | loss 97.6410 207.5677 317.3921 507.3117 766.8773 1103.0725 1565.2214 2235.9172 3133.8872 4741.2178 7724.7163 13598.5254 | lr 1.2e-04 | norm 3768.1873 | dt 9.786 +type train | step 4402 | loss 97.7178 208.3057 317.0747 509.5888 768.9517 1097.7751 1547.5466 2225.5168 3113.3638 4748.4038 7723.4570 13609.0986 | lr 1.2e-04 | norm 6183.3384 | dt 9.790 +type train | step 4403 | loss 95.1512 197.3599 304.5419 490.7081 745.3043 1065.4265 1503.9164 2141.7607 3016.1016 4554.0869 7391.8774 13006.9111 | lr 1.2e-04 | norm 3180.5164 | dt 9.786 +type train | step 4404 | loss 97.6270 204.7471 317.8112 505.7562 767.1686 1091.2112 1544.2444 2187.4490 3077.2180 4664.0215 7572.7646 13339.9053 | lr 1.2e-04 | norm 4034.4180 | dt 9.799 +type train | step 4405 | loss 108.7251 226.5155 341.4117 535.7156 803.8860 1171.8403 1654.1915 2373.1726 3259.4895 4858.6445 7822.7236 13807.1006 | lr 1.2e-04 | norm 7590.9751 | dt 9.765 +type train | step 4406 | loss 92.8570 195.1528 303.0618 488.2791 742.9631 1067.0452 1515.2185 2164.3662 3045.3071 4605.6943 7482.3149 13237.9961 | lr 1.2e-04 | norm 3889.3784 | dt 9.789 +type train | step 4407 | loss 99.6014 211.7683 328.3694 522.3182 781.5165 1099.8677 1544.8250 2173.3564 3056.5725 4595.8633 7454.2002 13137.8721 | lr 1.2e-04 | norm 4494.6890 | dt 9.803 +type train | step 4408 | loss 97.0072 206.6249 318.3258 511.7730 769.6450 1096.2737 1548.4589 2187.5964 3086.9810 4676.0894 7647.5576 13555.0137 | lr 1.2e-04 | norm 3734.4094 | dt 9.803 +type train | step 4409 | loss 97.8364 207.4203 320.8783 510.9876 769.4725 1096.3790 1550.6710 2208.8750 3103.8911 4689.6338 7649.7612 13577.6260 | lr 1.2e-04 | norm 3615.0728 | dt 9.794 +type train | step 4410 | loss 95.7062 202.0398 312.7111 498.8108 755.2739 1080.1147 1525.9406 2168.4990 3053.8445 4619.2876 7512.8057 13290.5801 | lr 1.2e-04 | norm 3483.7031 | dt 9.775 +type train | step 4411 | loss 97.6691 207.1028 317.6568 510.2936 769.0364 1107.9955 1558.7892 2215.8262 3087.2539 4645.7646 7581.6768 13458.7324 | lr 1.2e-04 | norm 3915.1328 | dt 9.786 +type train | step 4412 | loss 96.6150 205.4094 318.5936 509.3089 764.1555 1082.0337 1524.5033 2154.6577 3035.5300 4546.3979 7358.3760 12903.0557 | lr 1.2e-04 | norm 3356.9180 | dt 9.815 +type train | step 4413 | loss 95.6137 200.9616 307.4376 492.2250 742.9928 1068.0437 1507.2958 2156.1597 3035.8601 4572.9209 7438.9424 13021.5322 | lr 1.2e-04 | norm 3419.8281 | dt 9.788 +type train | step 4414 | loss 104.3993 222.1310 337.1150 532.4805 799.8224 1125.7395 1582.5912 2246.1270 3172.0383 4780.5503 7819.6284 13850.7148 | lr 1.2e-04 | norm 6393.8584 | dt 9.790 +type train | step 4415 | loss 105.9352 227.3548 340.9928 536.3710 805.1888 1153.9915 1617.1560 2307.6941 3218.7498 4850.7822 7921.6851 14045.9844 | lr 1.2e-04 | norm 4235.5640 | dt 9.787 +type train | step 4416 | loss 99.9320 211.4644 325.6930 518.9916 780.0067 1113.4709 1574.9890 2233.1433 3129.7134 4666.7637 7567.1680 13335.8389 | lr 1.2e-04 | norm 3435.0959 | dt 9.789 +type train | step 4417 | loss 96.3107 204.8430 315.9964 506.4899 766.9666 1109.2382 1578.0835 2260.0283 3176.0981 4799.0801 7801.9507 13801.8242 | lr 1.2e-04 | norm 3460.7090 | dt 9.785 +type train | step 4418 | loss 168.7645 352.1014 486.7566 740.0040 1046.7188 1545.7096 2118.6707 2959.1101 3845.1592 5602.8145 8772.5020 15425.2539 | lr 1.2e-04 | norm 10387.1162 | dt 9.739 +type train | step 4419 | loss 94.7343 199.7743 307.4986 496.9882 752.4503 1077.2369 1523.3190 2166.1982 3023.8445 4536.9844 7363.5635 12962.8818 | lr 1.2e-04 | norm 4121.5400 | dt 9.786 +type train | step 4420 | loss 94.9399 200.9169 308.7022 492.9332 748.0294 1073.2838 1517.2998 2163.1409 3043.3521 4611.3525 7571.7715 13322.0430 | lr 1.2e-04 | norm 3515.5007 | dt 9.795 +type train | step 4421 | loss 102.8790 219.3601 336.0424 530.0294 792.8912 1131.5251 1584.6317 2240.9180 3145.8083 4703.3701 7586.9268 13236.0029 | lr 1.2e-04 | norm 3895.8711 | dt 9.797 +type train | step 4422 | loss 101.6799 213.5613 321.7590 504.0663 759.0905 1078.9900 1512.1083 2136.1370 2977.8455 4480.3486 7272.7427 12726.1816 | lr 1.2e-04 | norm 3862.6641 | dt 9.786 +type train | step 4423 | loss 101.9086 217.8029 332.0341 522.1441 782.7329 1106.9338 1554.8807 2201.4934 3073.3713 4639.3296 7559.9727 13377.9912 | lr 1.2e-04 | norm 3979.1467 | dt 9.783 +type train | step 4424 | loss 98.6816 205.2226 317.3812 505.8008 763.5082 1102.0422 1548.7634 2216.2510 3129.7507 4718.4058 7615.0342 13384.5713 | lr 1.2e-04 | norm 3643.0127 | dt 9.791 +type train | step 4425 | loss 98.4618 208.8759 322.7148 514.4853 783.4495 1124.9093 1595.6289 2265.2556 3190.2708 4814.9438 7805.6431 13684.6240 | lr 1.2e-04 | norm 6361.2764 | dt 9.786 +type train | step 4426 | loss 96.5711 206.2248 320.0139 518.4477 778.4108 1112.0944 1568.5469 2228.0652 3123.4714 4744.0342 7771.4165 13708.2461 | lr 1.2e-04 | norm 5400.7368 | dt 9.801 +type train | step 4427 | loss 97.4936 204.9433 314.9109 500.2290 757.5391 1079.0537 1522.0295 2157.2529 3029.2349 4577.6738 7428.7598 13068.3037 | lr 1.2e-04 | norm 3765.9155 | dt 9.789 +type train | step 4428 | loss 92.4773 193.6827 299.3556 485.8600 741.0122 1082.9486 1549.1487 2228.8433 3130.9106 4760.1255 7742.7769 13627.8906 | lr 1.2e-04 | norm 4680.2646 | dt 9.796 +type train | step 4429 | loss 92.4094 193.6958 299.3187 482.8815 734.4720 1057.2390 1498.9653 2133.8589 2998.4888 4516.3936 7315.7104 12877.2334 | lr 1.2e-04 | norm 3915.0237 | dt 9.801 +type train | step 4430 | loss 111.7131 231.0601 361.3872 567.9550 840.9710 1208.8369 1679.4368 2417.1785 3356.7095 5078.5107 8200.3857 14248.2695 | lr 1.2e-04 | norm 6660.3364 | dt 9.772 +type train | step 4431 | loss 97.7221 206.1768 320.3864 510.7943 766.3329 1094.6729 1539.9114 2184.5237 3067.3088 4621.6333 7507.7017 13269.1416 | lr 1.2e-04 | norm 3980.5303 | dt 9.798 +type train | step 4432 | loss 118.4929 254.4153 384.6931 604.0374 884.7202 1253.4575 1721.2972 2372.7532 3179.6504 4703.7773 7464.3926 13171.6221 | lr 1.2e-04 | norm 5261.5576 | dt 9.762 +type train | step 4433 | loss 104.2247 224.0045 343.6505 548.4790 821.4197 1172.0892 1638.6055 2322.2361 3221.4580 4877.6348 7833.9990 13793.6465 | lr 1.2e-04 | norm 5020.4058 | dt 9.777 +type train | step 4434 | loss 94.5615 196.6700 305.9829 495.8077 752.5835 1084.2770 1532.2391 2179.4124 3090.1882 4681.7578 7619.0068 13432.9453 | lr 1.2e-04 | norm 3318.1711 | dt 9.794 +type train | step 4435 | loss 100.9370 214.9934 326.7360 516.7081 773.6288 1101.7129 1546.6224 2185.2229 3063.1497 4606.2764 7521.8579 13344.3975 | lr 1.2e-04 | norm 3957.3882 | dt 9.781 +type train | step 4436 | loss 93.1447 193.0789 299.4219 486.4893 739.9149 1056.3136 1494.5210 2127.9141 3001.0581 4535.1387 7402.3970 13053.2217 | lr 1.2e-04 | norm 3704.1580 | dt 9.791 +type train | step 4437 | loss 97.8971 206.9650 318.1612 506.3227 765.8928 1095.4197 1551.7324 2212.2959 3097.2913 4658.6504 7539.7852 13178.8779 | lr 1.2e-04 | norm 3548.1650 | dt 9.792 +type train | step 4438 | loss 101.8590 213.0458 328.5059 523.8259 784.4557 1123.9406 1581.7428 2237.8071 3134.9512 4744.5957 7755.9663 13695.0605 | lr 1.2e-04 | norm 3608.1169 | dt 9.786 +type train | step 4439 | loss 91.4225 189.0109 295.3420 475.5709 721.9212 1037.6018 1468.7211 2098.0344 2968.4082 4494.3564 7319.0806 12940.7285 | lr 1.2e-04 | norm 3406.8706 | dt 9.807 +type train | step 4440 | loss 97.5307 205.1266 315.9201 506.0258 762.6230 1098.6544 1554.5219 2214.2078 3110.0298 4702.1211 7677.3379 13651.5176 | lr 1.2e-04 | norm 3664.8367 | dt 9.801 +type train | step 4441 | loss 98.7136 207.0170 319.7029 510.2103 768.7646 1106.1841 1559.4822 2221.9243 3127.8452 4741.2109 7738.9897 13732.1953 | lr 1.2e-04 | norm 3977.4070 | dt 9.803 +type train | step 4442 | loss 94.4549 199.3100 306.2661 488.5030 741.1389 1064.0686 1502.1050 2130.7219 3009.0361 4563.1538 7483.9077 13262.6885 | lr 1.2e-04 | norm 3568.9485 | dt 9.804 +type train | step 4443 | loss 96.8824 204.3586 315.0348 503.5387 757.0078 1082.6592 1531.6451 2174.6641 3056.8635 4639.0591 7565.3438 13420.8574 | lr 1.2e-04 | norm 4157.5151 | dt 9.794 +type train | step 4444 | loss 97.2428 200.8170 307.8672 492.4929 743.8466 1075.0563 1515.6976 2152.8613 3011.9221 4534.5781 7387.2446 13051.4814 | lr 1.2e-04 | norm 4060.2456 | dt 10.127 +type train | step 4445 | loss 99.1505 208.4752 318.0122 504.1325 758.3134 1077.1575 1517.7985 2151.8718 3037.2371 4603.9644 7505.6885 13240.3926 | lr 1.2e-04 | norm 3652.7102 | dt 9.799 +type train | step 4446 | loss 105.2760 222.9944 335.2747 526.5709 784.0717 1128.8569 1584.0039 2248.0842 3121.6831 4712.3618 7700.5073 13715.4385 | lr 1.2e-04 | norm 4278.6914 | dt 9.793 +type train | step 4447 | loss 95.1194 201.0440 313.5392 502.1888 760.9388 1090.5696 1542.7314 2191.4661 3090.4316 4660.6255 7565.4668 13243.5537 | lr 1.2e-04 | norm 3383.1055 | dt 9.809 +type train | step 4448 | loss 91.6518 201.8191 316.9954 516.5464 778.9012 1118.8887 1588.9502 2254.0994 3148.1172 4792.4512 7911.7500 14143.2969 | lr 1.2e-04 | norm 8303.8047 | dt 9.782 +type train | step 4449 | loss 99.8746 206.7993 317.4686 506.5523 759.1807 1085.8884 1526.1000 2161.7112 3028.7180 4559.9233 7397.0723 12995.6689 | lr 1.2e-04 | norm 3334.3135 | dt 9.794 +type train | step 4450 | loss 108.0502 227.1434 348.6151 557.4468 831.5348 1220.6144 1708.9304 2448.7705 3390.7432 5088.5840 8199.5508 14458.8330 | lr 1.2e-04 | norm 5555.6802 | dt 9.790 +type train | step 4451 | loss 98.1704 209.9540 326.2956 522.5887 785.5140 1114.2261 1567.7106 2217.8306 3121.6011 4721.5850 7675.7471 13489.8291 | lr 1.2e-04 | norm 3552.5408 | dt 9.814 +type train | step 4452 | loss 96.8940 202.3657 311.8303 504.7066 771.1632 1115.0469 1577.8350 2241.7373 3131.9832 4687.6670 7664.9082 13605.7822 | lr 1.2e-04 | norm 5886.2466 | dt 9.788 +type train | step 4453 | loss 99.2628 212.2402 327.5755 520.0636 782.9430 1113.1270 1561.9270 2201.9688 3086.3481 4637.7178 7491.3887 13117.3457 | lr 1.2e-04 | norm 3527.1531 | dt 9.809 +type train | step 4454 | loss 97.2850 209.6239 332.2731 535.8221 810.3962 1148.3341 1617.3496 2288.8992 3214.5369 4850.9800 7923.3843 13933.2393 | lr 1.2e-04 | norm 4514.5640 | dt 9.815 +type train | step 4455 | loss 102.7309 216.9046 339.2265 546.9874 826.0989 1195.6875 1685.4617 2404.3608 3353.6282 5047.7476 8209.3652 14511.5352 | lr 1.2e-04 | norm 5052.3105 | dt 9.790 +type train | step 4456 | loss 104.1356 220.9470 337.8198 533.6628 797.5136 1136.1338 1590.0392 2248.3643 3153.7026 4750.2012 7709.6367 13557.2266 | lr 1.2e-04 | norm 3535.7407 | dt 9.813 +type train | step 4457 | loss 94.4272 199.2296 312.1017 503.6330 763.3869 1087.5942 1539.4628 2185.6284 3082.2734 4654.8608 7612.6099 13392.1152 | lr 1.2e-04 | norm 3553.1052 | dt 9.815 +type train | step 4458 | loss 105.1908 253.1489 410.7253 693.4411 1045.2762 1449.4346 2010.1715 2818.2832 3943.2180 5800.7271 9596.7646 17466.6543 | lr 1.2e-04 | norm 18899.7207 | dt 9.777 +type train | step 4459 | loss 100.3256 223.4930 352.0168 570.3408 858.4915 1209.1122 1695.7274 2392.1091 3368.0212 5036.7222 8206.2617 14643.4160 | lr 1.2e-04 | norm 6646.3057 | dt 9.798 +type train | step 4460 | loss 100.1573 211.6208 326.4298 519.4420 780.7372 1110.9801 1562.4280 2208.7751 3101.8037 4686.1411 7620.0762 13460.0479 | lr 1.2e-04 | norm 4333.1147 | dt 9.785 +type train | step 4461 | loss 97.7737 209.5919 320.3187 510.0597 772.1861 1104.4148 1563.8304 2226.5100 3105.4307 4682.8555 7648.6309 13596.2266 | lr 1.2e-04 | norm 4033.1038 | dt 9.791 +type train | step 4462 | loss 101.4167 213.5986 327.4219 523.3860 784.7554 1121.2537 1577.7784 2235.4197 3108.7371 4656.9009 7563.7012 13360.9072 | lr 1.2e-04 | norm 4863.2495 | dt 9.809 +type train | step 4463 | loss 107.0620 229.4595 350.6602 557.0402 822.1760 1164.3367 1631.8398 2301.9756 3200.0425 4805.2202 7813.7432 13824.9521 | lr 1.2e-04 | norm 4386.5361 | dt 9.793 +type train | step 4464 | loss 99.1270 214.2852 332.0261 531.7565 803.3037 1137.3086 1602.8450 2253.5164 3148.4014 4742.3311 7733.5527 13680.8945 | lr 1.2e-04 | norm 3536.4656 | dt 9.817 +type train | step 4465 | loss 99.4392 211.7391 327.3490 528.5382 800.0843 1143.1150 1621.9355 2302.2354 3215.1353 4857.1533 8046.2300 14386.0068 | lr 1.2e-04 | norm 5956.4663 | dt 9.797 +type train | step 4466 | loss 99.3890 213.4101 326.2480 517.4403 777.5757 1116.5177 1571.3304 2222.0366 3117.0420 4682.9351 7562.1875 13234.5332 | lr 1.2e-04 | norm 3380.9170 | dt 9.812 +type train | step 4467 | loss 94.7694 197.6877 307.1641 494.9789 752.4106 1076.7091 1531.1918 2177.2378 3097.7405 4682.9971 7615.4541 13370.7754 | lr 1.2e-04 | norm 3782.8071 | dt 9.794 +type train | step 4468 | loss 98.9630 207.3916 322.5182 523.7744 795.1051 1130.9514 1584.8473 2243.0076 3133.1006 4681.1885 7561.8086 13306.0732 | lr 1.2e-04 | norm 3664.6250 | dt 9.786 +type train | step 4469 | loss 101.2685 218.1423 333.9526 532.1753 800.1280 1134.2062 1591.5211 2250.9604 3164.0640 4746.4634 7718.3657 13515.3818 | lr 1.2e-04 | norm 3394.0425 | dt 9.814 +type train | step 4470 | loss 99.7080 213.4484 329.7455 529.3469 798.4890 1142.7151 1611.7384 2289.2581 3222.1021 4873.4902 7917.9097 14045.4082 | lr 1.2e-04 | norm 4095.0310 | dt 9.802 +type train | step 4471 | loss 98.4366 207.1588 317.7762 502.8090 762.4075 1081.2263 1519.0216 2152.4089 3040.0642 4575.5923 7503.1475 13262.6855 | lr 1.2e-04 | norm 4521.8159 | dt 9.782 +type train | step 4472 | loss 91.3898 194.7020 304.3963 497.2010 755.0832 1076.8900 1521.6934 2160.8455 3038.0703 4603.2388 7526.7485 13427.8516 | lr 1.2e-04 | norm 4451.9219 | dt 9.803 +type train | step 4473 | loss 101.8585 217.8203 333.6420 529.7578 790.6205 1119.2712 1570.7932 2220.9739 3123.6685 4698.9751 7699.4565 13675.4697 | lr 1.1e-04 | norm 4561.3545 | dt 9.793 +type train | step 4474 | loss 106.2194 231.1270 355.2251 564.6601 852.2254 1220.2480 1695.9347 2390.6431 3350.7351 5003.2666 8109.8359 14247.0391 | lr 1.1e-04 | norm 5101.5898 | dt 9.795 +type train | step 4475 | loss 97.7359 207.4384 320.2488 516.3233 777.2865 1113.6182 1568.6760 2220.6936 3111.8374 4673.6289 7601.5786 13409.5586 | lr 1.1e-04 | norm 3405.7251 | dt 9.807 +type train | step 4476 | loss 108.6013 231.8040 349.9394 553.8350 825.6724 1166.7860 1656.4089 2364.7163 3319.2034 5035.2764 8237.8408 14606.7051 | lr 1.1e-04 | norm 6804.5122 | dt 9.785 +type train | step 4477 | loss 101.3264 216.4563 334.0922 533.4876 798.2410 1130.5116 1592.1512 2250.2402 3163.6748 4780.6226 7820.3242 13944.2539 | lr 1.1e-04 | norm 4133.8589 | dt 9.796 +type train | step 4478 | loss 99.0112 213.1226 327.5150 519.2364 783.0709 1111.3773 1570.1420 2214.5933 3116.5349 4712.3726 7699.3604 13567.0576 | lr 1.1e-04 | norm 3243.6416 | dt 9.805 +type train | step 4479 | loss 98.0210 210.3746 327.4535 526.6555 796.7006 1126.1740 1587.7231 2244.8459 3168.3848 4794.4238 7783.6543 13630.4355 | lr 1.1e-04 | norm 3934.0608 | dt 9.804 +type train | step 4480 | loss 96.2447 204.7361 317.9437 517.7847 779.3303 1114.3457 1571.4030 2231.2646 3137.4578 4785.3906 7929.4844 14013.6514 | lr 1.1e-04 | norm 4543.1768 | dt 9.797 +type train | step 4481 | loss 104.5698 221.5867 337.1274 530.6840 790.8110 1120.2307 1559.3105 2186.1292 3042.4873 4519.3633 7349.6401 13018.1318 | lr 1.1e-04 | norm 3600.2783 | dt 9.801 +type train | step 4482 | loss 102.6265 216.4326 326.9954 516.5167 778.9068 1116.6931 1574.9464 2236.1025 3114.7466 4675.1787 7535.0562 13209.4814 | lr 1.1e-04 | norm 4899.5039 | dt 9.790 +type train | step 4483 | loss 102.7126 217.9297 332.3984 532.9415 795.4938 1132.3706 1588.7151 2229.3577 3127.3340 4722.8628 7704.7383 13651.5283 | lr 1.1e-04 | norm 4145.8682 | dt 9.800 +type train | step 4484 | loss 90.5465 192.3176 301.1718 490.5908 750.1783 1090.2112 1555.7899 2234.5693 3165.6909 4788.8174 7793.1260 13719.1328 | lr 1.1e-04 | norm 4165.9580 | dt 9.791 +type train | step 4485 | loss 101.1058 216.0552 331.9047 527.9133 798.9636 1145.5043 1614.0280 2281.2454 3201.5706 4841.3711 7908.0942 13934.7354 | lr 1.1e-04 | norm 3661.4580 | dt 9.804 +type train | step 4486 | loss 103.4315 223.5995 347.6606 558.1963 826.6462 1168.1062 1626.9474 2275.0471 3174.4329 4784.8486 7768.4336 13656.3076 | lr 1.1e-04 | norm 3482.6794 | dt 9.800 +type train | step 4487 | loss 105.5831 227.3680 344.9333 554.8971 828.9551 1186.5679 1657.2559 2335.3035 3260.1558 4894.4707 7949.8159 13930.2305 | lr 1.1e-04 | norm 4028.0959 | dt 9.798 +type train | step 4488 | loss 111.2606 242.0772 374.9647 598.8307 888.2943 1264.6898 1753.7435 2465.0972 3390.9070 5081.3833 8168.2524 14515.9775 | lr 1.1e-04 | norm 4867.0078 | dt 9.785 +type train | step 4489 | loss 94.9512 201.2930 313.6937 505.3612 773.7350 1118.2832 1588.3585 2272.1548 3222.2415 4843.2432 7794.6836 13611.8242 | lr 1.1e-04 | norm 4052.8469 | dt 9.809 +type train | step 4490 | loss 105.2277 229.5491 348.5783 551.0167 821.3922 1184.1078 1656.1708 2356.9734 3257.9658 4864.9326 7911.3916 13938.9980 | lr 1.1e-04 | norm 4395.5166 | dt 9.788 +type train | step 4491 | loss 97.7087 207.8662 320.4564 514.5094 776.9365 1102.3502 1548.0127 2194.0232 3081.3735 4634.0859 7554.4321 13294.2246 | lr 1.1e-04 | norm 3274.9951 | dt 9.814 +type train | step 4492 | loss 109.2419 229.7035 354.7976 561.6478 829.2184 1191.7163 1663.9163 2334.7913 3182.4919 4746.6387 7679.1890 13464.8213 | lr 1.1e-04 | norm 5019.8994 | dt 9.789 +type train | step 4493 | loss 93.7943 206.0814 326.2697 527.9118 802.2193 1129.4583 1596.7069 2253.6907 3208.0786 4877.4043 8043.3931 14297.6758 | lr 1.1e-04 | norm 7389.7075 | dt 9.812 +type train | step 4494 | loss 104.9896 225.8207 345.7902 540.9528 810.8343 1148.7828 1606.9980 2254.4119 3121.5225 4684.1274 7591.8667 13367.2139 | lr 1.1e-04 | norm 3398.5986 | dt 9.807 +type train | step 4495 | loss 102.8841 216.9084 325.4181 518.3895 778.9154 1115.6873 1575.0111 2246.1196 3146.2874 4741.7876 7713.9082 13888.2969 | lr 1.1e-04 | norm 7449.4399 | dt 9.781 +type train | step 4496 | loss 95.5923 201.6596 318.9750 517.5652 782.3405 1122.1364 1586.3835 2251.8066 3174.0681 4758.4863 7748.6997 13687.6270 | lr 1.1e-04 | norm 3624.6543 | dt 9.789 +type train | step 4497 | loss 99.8633 216.8916 339.6504 541.2245 810.2078 1149.9741 1605.6606 2264.9612 3179.2456 4818.4028 7950.1694 14194.1699 | lr 1.1e-04 | norm 5993.5420 | dt 9.817 +type train | step 4498 | loss 101.9952 216.3388 334.5825 534.6138 803.0223 1145.7209 1612.1084 2287.8286 3192.0908 4773.0591 7689.0596 13459.0996 | lr 1.1e-04 | norm 3539.0925 | dt 9.799 +type train | step 4499 | loss 96.1739 204.3332 316.5755 509.9254 770.8354 1093.4968 1538.3553 2177.6184 3058.0107 4604.2407 7534.3813 13285.9561 | lr 1.1e-04 | norm 3718.9739 | dt 9.793 +type train | step 4500 | loss 96.6581 206.8928 317.2312 511.8606 777.4357 1116.8096 1583.2991 2266.7405 3175.8682 4757.8682 7690.3384 13498.5352 | lr 1.1e-04 | norm 4798.7437 | dt 9.795 +type train | step 4501 | loss 106.6985 225.5162 344.8131 549.0146 821.9122 1178.2529 1654.2507 2346.0227 3274.1035 4863.4893 7820.2285 13687.6982 | lr 1.1e-04 | norm 5025.5332 | dt 9.779 +type train | step 4502 | loss 99.8411 211.5030 324.7394 521.9001 788.4969 1139.3059 1603.2452 2273.8503 3182.9246 4763.2031 7714.8740 13534.8154 | lr 1.1e-04 | norm 3570.2336 | dt 9.795 +type train | step 4503 | loss 101.6035 216.9476 334.5625 531.5068 800.8786 1140.7504 1599.7900 2258.6963 3151.7954 4734.2324 7670.9707 13536.8047 | lr 1.1e-04 | norm 3510.7671 | dt 9.815 +type train | step 4504 | loss 103.6153 224.9326 344.3208 547.9698 819.0355 1165.4321 1636.9373 2305.3579 3205.7910 4819.8472 7835.7661 13749.9707 | lr 1.1e-04 | norm 3583.1709 | dt 9.801 +type train | step 4505 | loss 99.2079 209.8193 320.8905 515.9291 784.7724 1129.7145 1598.5935 2254.8745 3158.8096 4774.9204 7911.1797 14226.6768 | lr 1.1e-04 | norm 4709.1289 | dt 9.809 +type train | step 4506 | loss 100.2927 212.9383 327.9410 523.0090 787.3688 1114.5597 1568.0992 2228.7007 3135.9236 4716.5122 7624.1030 13294.9609 | lr 1.1e-04 | norm 3288.4238 | dt 9.807 +type train | step 4507 | loss 97.7070 213.4478 331.0213 525.2466 788.8114 1127.7244 1592.6060 2243.3838 3146.5908 4720.4883 7681.5000 13594.8643 | lr 1.1e-04 | norm 5659.1465 | dt 9.797 +type train | step 4508 | loss 101.3411 215.0517 325.5167 516.3698 778.6418 1108.3607 1569.3574 2223.7090 3152.4358 4819.5190 7930.6216 14026.4668 | lr 1.1e-04 | norm 5755.8921 | dt 9.796 +type train | step 4509 | loss 101.3501 217.6681 339.6286 545.7509 825.5535 1184.7849 1674.7582 2379.8809 3365.7368 5088.5635 8312.2764 14685.8877 | lr 1.1e-04 | norm 6628.4111 | dt 9.784 +type train | step 4510 | loss 98.2729 211.9731 329.4788 526.1761 792.9983 1123.0242 1575.3364 2206.4653 3104.7905 4654.8564 7484.1240 13065.6279 | lr 1.1e-04 | norm 3521.3938 | dt 9.815 +type train | step 4511 | loss 104.3918 222.9687 341.7079 547.7133 814.1387 1162.9303 1635.0172 2309.5049 3210.3391 4820.9263 7891.4731 13989.8350 | lr 1.1e-04 | norm 4123.1680 | dt 9.788 +type train | step 4512 | loss 98.8365 215.1315 331.1155 534.7134 803.3024 1140.5055 1603.8075 2266.3870 3185.5850 4790.5493 7814.6855 13754.7568 | lr 1.1e-04 | norm 4674.9448 | dt 9.780 +type train | step 4513 | loss 110.6444 234.6791 355.7762 555.7600 824.5188 1185.0658 1664.1802 2350.3906 3201.6653 4728.1992 7630.9980 13429.4072 | lr 1.1e-04 | norm 5158.3105 | dt 9.789 +type train | step 4514 | loss 98.0590 209.3957 320.6497 515.0286 778.3261 1109.6608 1565.6211 2218.1653 3105.4634 4674.8721 7604.9551 13417.6309 | lr 1.1e-04 | norm 3659.9194 | dt 9.786 +type train | step 4515 | loss 98.1819 211.3817 325.9551 527.0214 791.0505 1125.2693 1590.1866 2241.0615 3134.7661 4685.5952 7656.3213 13598.7959 | lr 1.1e-04 | norm 4578.5034 | dt 9.799 +type train | step 4516 | loss 95.0705 202.8490 315.1433 508.3445 769.0807 1100.9209 1549.2778 2198.1624 3106.1279 4681.1963 7614.6841 13351.1055 | lr 1.1e-04 | norm 3441.5569 | dt 9.799 +type train | step 4517 | loss 99.3109 212.9590 327.9267 524.2141 793.2098 1133.0046 1596.3302 2254.1824 3161.5828 4763.8691 7736.5288 13635.6055 | lr 1.1e-04 | norm 3319.6953 | dt 9.790 +type train | step 4518 | loss 99.8093 212.9743 327.7563 522.6803 782.7148 1108.5806 1555.6329 2192.7253 3080.1689 4637.7344 7526.5215 13234.7852 | lr 1.1e-04 | norm 3304.1484 | dt 9.803 +type train | step 4519 | loss 107.3399 227.8843 346.8892 542.6499 807.5863 1160.1744 1628.9073 2303.8660 3189.3052 4735.4966 7632.6924 13489.9512 | lr 1.1e-04 | norm 4947.7808 | dt 9.793 +type train | step 4520 | loss 96.6251 206.7011 320.8235 510.8009 772.6912 1096.7018 1549.3755 2197.7708 3115.6475 4704.5229 7638.8066 13424.4414 | lr 1.1e-04 | norm 3450.4919 | dt 9.816 +type train | step 4521 | loss 101.1474 218.6540 339.8553 544.6423 818.9886 1170.9016 1643.0061 2328.8923 3247.4675 4889.9307 7962.1836 13992.9199 | lr 1.1e-04 | norm 4534.7344 | dt 9.796 +type train | step 4522 | loss 102.2446 219.1001 340.7626 550.4072 821.6578 1159.9758 1621.0194 2280.9302 3192.0547 4778.6772 7719.1846 13529.4111 | lr 1.1e-04 | norm 3649.7529 | dt 9.788 +type train | step 4523 | loss 97.3893 209.6160 326.8514 530.6949 796.9280 1145.4867 1615.7927 2296.2993 3228.9480 4866.0576 7940.5151 13991.2617 | lr 1.1e-04 | norm 4490.6128 | dt 9.795 +type train | step 4524 | loss 98.0447 208.9613 318.9767 511.4052 775.2628 1111.2688 1566.4792 2217.3562 3114.4832 4707.2017 7611.4961 13326.5107 | lr 1.1e-04 | norm 3703.0723 | dt 9.802 +type train | step 4525 | loss 99.5069 212.2207 325.1403 519.5451 785.7145 1111.3708 1563.1378 2207.1770 3100.4282 4678.7295 7652.8076 13503.2637 | lr 1.1e-04 | norm 3800.3049 | dt 9.796 +type train | step 4526 | loss 105.9189 227.2750 347.8641 552.7416 813.0953 1164.0458 1622.2490 2273.6460 3139.4648 4673.1377 7596.1060 13400.0508 | lr 1.1e-04 | norm 3510.4009 | dt 9.793 +type train | step 4527 | loss 98.0600 210.3821 322.6896 525.7703 797.1296 1153.8954 1634.3864 2319.2026 3238.9390 4872.2651 7900.3218 13964.4648 | lr 1.1e-04 | norm 4929.3901 | dt 9.785 +type train | step 4528 | loss 103.7070 222.5724 337.0542 538.3801 800.7943 1145.4075 1620.3860 2289.7041 3203.3413 4788.0020 7758.2529 13659.3213 | lr 1.1e-04 | norm 4144.3125 | dt 9.792 +type train | step 4529 | loss 100.1229 211.3175 326.9179 518.2495 778.3551 1110.5867 1564.2958 2213.3977 3101.6880 4657.1797 7584.3389 13378.4570 | lr 1.1e-04 | norm 3839.3577 | dt 9.816 +type train | step 4530 | loss 100.4781 215.5060 334.6207 531.6292 797.9517 1133.3748 1593.8116 2252.4412 3154.6519 4748.3350 7712.8989 13559.1055 | lr 1.1e-04 | norm 3562.6272 | dt 9.798 +type train | step 4531 | loss 99.2799 211.1571 324.4532 517.2057 773.9854 1097.1627 1531.2734 2162.1233 3026.3438 4555.6323 7434.4326 13033.0889 | lr 1.1e-04 | norm 3752.5872 | dt 9.794 +type train | step 4532 | loss 103.1965 218.5087 338.3535 538.8270 816.2086 1166.9934 1645.2043 2337.2688 3227.2751 4839.3252 7859.4448 13810.8408 | lr 1.1e-04 | norm 5436.5845 | dt 9.798 +type train | step 4533 | loss 103.9526 221.4869 341.8880 550.1902 822.2224 1182.9075 1664.0182 2355.0596 3280.2439 4909.4688 8002.3481 14169.2793 | lr 1.1e-04 | norm 3686.8960 | dt 9.806 +type train | step 4534 | loss 103.6617 219.6893 336.2774 533.4532 800.0295 1148.4758 1611.4707 2286.0645 3203.0986 4802.6216 7761.4771 13619.1426 | lr 1.1e-04 | norm 3407.2153 | dt 9.812 +type train | step 4535 | loss 109.5797 235.4494 358.0081 558.2596 831.7542 1171.6627 1633.8915 2295.9106 3180.2388 4748.5508 7646.7192 13300.5977 | lr 1.1e-04 | norm 3879.9907 | dt 9.803 +type train | step 4536 | loss 97.1669 204.3127 318.1650 513.8997 775.7689 1101.5851 1557.8508 2214.7671 3116.6650 4689.1465 7655.0020 13511.7148 | lr 1.1e-04 | norm 4542.8740 | dt 9.786 +type train | step 4537 | loss 98.8156 205.4320 318.5258 515.5839 778.4408 1137.0732 1614.0361 2302.3979 3209.0730 4804.1377 7804.8506 13910.8076 | lr 1.1e-04 | norm 4091.8672 | dt 9.787 +type train | step 4538 | loss 96.0428 203.5452 315.9807 506.7655 764.2982 1089.6436 1539.4242 2185.0938 3076.1021 4647.5913 7572.0532 13282.2109 | lr 1.1e-04 | norm 3360.3904 | dt 9.803 +type train | step 4539 | loss 95.6815 201.7681 313.7849 508.5119 769.7404 1108.1285 1565.3839 2238.9829 3152.4612 4768.5820 7721.1099 13542.1914 | lr 1.1e-04 | norm 3685.5054 | dt 9.796 +type train | step 4540 | loss 109.1175 237.3816 357.0844 557.8521 829.0199 1174.9376 1630.7567 2293.9927 3155.1941 4714.6401 7650.3545 13484.9326 | lr 1.1e-04 | norm 5065.3003 | dt 9.792 +type train | step 4541 | loss 95.1281 203.3076 314.9586 506.9470 771.1207 1095.6611 1549.7979 2191.6958 3105.2974 4686.0396 7609.2583 13360.8096 | lr 1.1e-04 | norm 3462.1538 | dt 9.808 +type train | step 4542 | loss 97.1787 209.6685 323.0076 517.7853 781.9343 1117.7196 1571.9268 2214.2495 3125.8438 4725.9014 7653.9678 13477.5996 | lr 1.1e-04 | norm 6381.0791 | dt 9.802 +type train | step 4543 | loss 100.4494 214.4088 330.5135 528.8645 791.0392 1127.7903 1590.2275 2253.8774 3163.9851 4748.6895 7748.5864 13737.3438 | lr 1.1e-04 | norm 4055.3579 | dt 9.793 +type train | step 4544 | loss 101.2704 219.1321 337.6177 535.7804 804.6277 1140.5103 1604.2406 2281.3677 3169.5027 4773.2627 7769.3364 13855.6816 | lr 1.1e-04 | norm 5352.4824 | dt 9.782 +type train | step 4545 | loss 98.5128 211.7296 324.2212 514.5248 772.7844 1104.1180 1551.9612 2203.9470 3084.9534 4646.0542 7546.6294 13271.2344 | lr 1.1e-04 | norm 3916.2371 | dt 9.792 +type train | step 4546 | loss 102.3812 217.3738 334.7497 533.6757 795.5880 1127.9386 1576.3771 2216.8589 3074.3381 4620.1602 7547.7290 13328.3330 | lr 1.1e-04 | norm 3803.3486 | dt 9.792 +type train | step 4547 | loss 101.0505 218.2165 333.0219 526.9583 792.5297 1127.1086 1586.4716 2241.6133 3140.5493 4756.2930 7769.7700 13772.6885 | lr 1.1e-04 | norm 4747.5615 | dt 9.791 +type train | step 4548 | loss 99.7398 209.5779 323.2478 516.2296 784.6882 1138.1573 1610.6827 2308.6838 3228.8052 4852.7446 7931.7798 14188.4717 | lr 1.1e-04 | norm 5562.8521 | dt 9.791 +type train | step 4549 | loss 109.5863 233.7995 359.1417 575.9761 850.5458 1205.4158 1675.1149 2362.1470 3279.5928 4911.9795 7999.8120 14143.9375 | lr 1.1e-04 | norm 3881.8430 | dt 9.794 +type train | step 4550 | loss 99.7361 211.2700 326.2460 517.8599 777.8992 1111.0253 1559.5793 2194.7754 3055.7881 4585.7593 7413.0352 12971.1748 | lr 1.1e-04 | norm 3741.3875 | dt 9.812 +type train | step 4551 | loss 93.9852 196.7505 313.9207 505.5467 769.4640 1103.1406 1562.7483 2207.8770 3115.4209 4671.5996 7555.2109 13178.1826 | lr 1.1e-04 | norm 6574.5210 | dt 9.816 +type train | step 4552 | loss 96.2320 202.6510 316.1543 506.9453 764.3862 1088.7891 1526.2708 2148.0557 3011.6921 4548.9297 7381.0034 12972.1797 | lr 1.1e-04 | norm 4332.5059 | dt 9.790 +type train | step 4553 | loss 116.6567 251.3438 375.0137 583.2842 850.5095 1181.4814 1648.9728 2297.6946 3223.6753 4884.8398 7850.0039 13792.3877 | lr 1.1e-04 | norm 6636.4902 | dt 9.798 +type train | step 4554 | loss 103.3027 219.6744 334.8338 534.0004 801.3391 1136.7864 1594.7888 2253.7429 3163.4731 4758.4648 7739.7520 13563.4951 | lr 1.1e-04 | norm 3583.2366 | dt 9.808 +type train | step 4555 | loss 105.7874 222.6387 337.6550 535.9574 796.2291 1136.8250 1596.2325 2255.9421 3152.6643 4737.1367 7695.3862 13602.2549 | lr 1.1e-04 | norm 4042.7449 | dt 9.779 +type train | step 4556 | loss 108.5319 231.6334 356.2787 567.0983 836.0836 1203.9016 1690.8801 2396.5198 3287.2715 4952.0854 8102.7080 14493.1064 | lr 1.1e-04 | norm 6777.7476 | dt 9.781 +type train | step 4557 | loss 99.9956 211.9107 324.9104 518.5742 778.0178 1111.0525 1564.9020 2216.2515 3100.0969 4647.1587 7536.5293 13222.7500 | lr 1.1e-04 | norm 3211.4785 | dt 9.803 +type train | step 4558 | loss 108.2012 236.4009 358.9457 561.6101 836.4808 1185.7665 1666.7124 2342.2256 3253.6714 4858.7095 7844.9272 13704.4277 | lr 1.1e-04 | norm 3652.0242 | dt 9.806 +type train | step 4559 | loss 102.0813 217.3291 335.9086 538.0404 808.6276 1165.1085 1633.1837 2294.8269 3159.3232 4706.0967 7620.1978 13449.6338 | lr 1.1e-04 | norm 4166.8979 | dt 9.800 +type train | step 4560 | loss 100.2599 212.8500 326.2070 518.5995 783.2925 1118.7053 1566.9963 2198.4773 3062.2212 4596.4033 7469.3442 13062.4531 | lr 1.1e-04 | norm 4280.3911 | dt 9.806 +type train | step 4561 | loss 103.0086 218.6438 336.6901 537.3069 804.8079 1148.8337 1605.3817 2271.1511 3180.5671 4797.3174 7844.1519 13899.3594 | lr 1.1e-04 | norm 3809.4983 | dt 9.791 +type train | step 4562 | loss 103.8233 222.0897 339.5172 535.0569 797.0251 1152.6476 1606.3418 2260.5496 3066.0757 4546.0171 7361.2563 13052.8389 | lr 1.1e-04 | norm 4740.4399 | dt 9.779 +type train | step 4563 | loss 104.7858 225.0966 340.0522 536.9224 796.6738 1142.2002 1602.0807 2275.7373 3157.4817 4738.9873 7705.4604 13634.2695 | lr 1.1e-04 | norm 4016.1326 | dt 9.785 +type train | step 4564 | loss 101.2958 216.4446 333.6837 530.8928 789.5748 1123.0188 1576.1056 2219.9768 3096.8887 4654.6045 7531.3276 13274.8936 | lr 1.1e-04 | norm 3745.4741 | dt 9.798 +type train | step 4565 | loss 102.5598 218.1952 337.1700 540.0670 807.4046 1170.9288 1646.9203 2353.8525 3275.2363 4914.0278 8019.5581 14245.7539 | lr 1.1e-04 | norm 4523.8735 | dt 9.782 +type train | step 4566 | loss 99.1478 209.2915 321.2260 517.9416 779.3492 1118.4285 1577.6877 2227.6101 3105.8621 4677.4692 7575.9551 13287.5459 | lr 1.1e-04 | norm 3476.9380 | dt 9.798 +type train | step 4567 | loss 95.4664 205.6751 316.2337 506.1395 762.9098 1086.8188 1533.8577 2173.6958 3068.9998 4641.9683 7551.3013 13253.1357 | lr 1.1e-04 | norm 2981.9192 | dt 9.817 +type train | step 4568 | loss 97.4508 207.1563 317.0751 506.9249 767.5062 1100.0978 1549.3728 2205.6001 3116.4717 4690.8599 7581.3403 13233.6582 | lr 1.1e-04 | norm 3367.2849 | dt 9.796 +type train | step 4569 | loss 95.5354 202.4280 313.1934 501.1880 760.2610 1086.3408 1545.2601 2198.4585 3115.1978 4763.4048 7855.0771 13992.0723 | lr 1.1e-04 | norm 6032.5674 | dt 9.800 +type train | step 4570 | loss 103.3358 218.0540 332.1873 528.8830 793.8925 1142.2081 1610.7753 2289.7146 3192.8887 4777.2700 7771.2583 13787.4961 | lr 1.1e-04 | norm 4132.3516 | dt 9.782 +type train | step 4571 | loss 97.6269 208.0398 325.1641 522.8278 782.8706 1129.9642 1592.8357 2272.1091 3178.9429 4806.1377 7839.4062 13790.8740 | lr 1.1e-04 | norm 3555.6853 | dt 9.795 +type train | step 4572 | loss 101.5180 218.3561 333.4975 534.6093 798.6035 1136.3708 1588.3658 2239.5718 3118.0139 4682.9927 7548.4883 13321.6035 | lr 1.1e-04 | norm 4011.4329 | dt 9.791 +type train | step 4573 | loss 99.0667 210.3042 326.2120 525.7254 804.6438 1149.4446 1630.4236 2327.0503 3282.5671 4947.8164 8047.6289 14131.2266 | lr 1.1e-04 | norm 5330.0986 | dt 9.796 +type train | step 4574 | loss 117.1632 254.2429 383.4063 599.0596 899.3279 1278.2798 1780.9711 2528.7505 3482.9287 5185.5708 8509.3242 15092.1436 | lr 1.1e-04 | norm 11212.5801 | dt 9.776 +type train | step 4575 | loss 116.5401 247.1714 374.9476 591.1656 890.3290 1291.2402 1799.6130 2576.8843 3529.1846 5236.8579 8503.6387 15024.8301 | lr 1.1e-04 | norm 11140.9912 | dt 9.764 +type train | step 4576 | loss 115.7458 249.5540 369.0507 578.0430 859.5629 1277.9489 1744.2749 2438.8665 3265.9822 4764.1162 7510.6826 12975.0518 | lr 1.1e-04 | norm 9359.8076 | dt 9.742 +type train | step 4577 | loss 98.5481 210.1938 325.4008 517.3504 782.5090 1122.1699 1584.0326 2246.3638 3145.3447 4738.3950 7678.5015 13565.1582 | lr 1.1e-04 | norm 3851.1960 | dt 9.811 +type train | step 4578 | loss 94.5496 199.6269 305.7868 489.6585 742.9771 1059.5017 1502.9442 2130.2549 3006.5081 4545.8750 7537.2710 13466.2246 | lr 1.1e-04 | norm 6751.2676 | dt 9.785 +type train | step 4579 | loss 101.8896 216.6251 333.8633 532.4920 803.2027 1142.0227 1600.3843 2272.9980 3193.9661 4842.3398 7906.0986 14118.5605 | lr 1.1e-04 | norm 5080.4517 | dt 9.802 +type train | step 4580 | loss 101.6906 217.4451 332.6659 529.2778 794.3732 1128.1791 1589.2333 2243.5386 3130.1680 4732.3247 7719.2617 13644.9512 | lr 1.1e-04 | norm 3943.0964 | dt 9.812 +type train | step 4581 | loss 115.1845 252.3685 378.3839 593.6071 866.4229 1232.3044 1692.4958 2337.3501 3192.0703 4657.3604 7454.0498 13154.3535 | lr 1.1e-04 | norm 5572.4902 | dt 9.786 +type train | step 4582 | loss 107.3639 226.6362 346.1495 548.5491 808.0103 1152.5464 1611.1978 2271.5000 3163.9578 4752.4512 7757.1382 13805.8145 | lr 1.1e-04 | norm 5329.9336 | dt 9.792 +type train | step 4583 | loss 97.3243 206.6373 319.9221 510.6139 774.3123 1111.3223 1572.8573 2240.7932 3165.2734 4796.4419 7854.4907 13976.1895 | lr 1.1e-04 | norm 4930.0718 | dt 9.793 +type train | step 4584 | loss 102.6190 220.5331 338.8933 539.3370 802.9942 1140.4580 1588.7594 2218.1716 3100.0857 4635.2905 7514.2832 13220.0371 | lr 1.1e-04 | norm 3619.4392 | dt 9.794 +type train | step 4585 | loss 114.6594 247.2493 365.5732 567.7141 838.7100 1199.7781 1667.6511 2361.9785 3236.7822 4808.0005 7719.9604 13401.5566 | lr 1.1e-04 | norm 3794.8384 | dt 9.790 +type train | step 4586 | loss 96.3748 204.1529 315.6545 503.5697 761.3585 1098.9880 1553.3766 2208.3999 3091.2639 4663.3286 7606.6309 13386.5293 | lr 1.1e-04 | norm 3989.9053 | dt 9.795 +type train | step 4587 | loss 105.9296 226.8383 345.9515 544.0551 809.2742 1158.7085 1622.6351 2287.4146 3164.6873 4721.5586 7612.7075 13288.9404 | lr 1.1e-04 | norm 3933.6150 | dt 9.792 +type train | step 4588 | loss 100.5211 215.2448 332.9302 530.3774 795.4786 1125.3273 1575.3660 2213.9927 3088.6440 4649.9458 7511.4995 13185.8945 | lr 1.1e-04 | norm 3077.8892 | dt 9.799 +type train | step 4589 | loss 96.7576 205.4422 317.7205 510.2789 765.3196 1097.2927 1544.7438 2183.8367 3040.5508 4578.7314 7408.1123 13149.8750 | lr 1.1e-04 | norm 4660.9976 | dt 9.793 +type train | step 4590 | loss 98.8219 210.0891 323.5309 514.1132 772.4408 1103.2310 1552.0374 2191.9075 3083.2280 4652.3511 7570.7188 13328.2021 | lr 1.1e-04 | norm 3481.6877 | dt 9.793 +type train | step 4591 | loss 102.8202 219.7938 336.6142 538.8257 800.4031 1147.3813 1598.8334 2261.4414 3136.6589 4698.3374 7586.0400 13352.4697 | lr 1.1e-04 | norm 4051.7371 | dt 9.791 +type train | step 4592 | loss 107.3856 234.2984 359.9553 578.7741 852.9650 1231.5698 1739.2240 2462.8301 3408.1755 5113.2339 8424.4375 15150.9141 | lr 1.1e-04 | norm 8953.3945 | dt 9.759 +type train | step 4593 | loss 100.4182 216.7881 337.2191 539.7188 809.9067 1151.4009 1617.2212 2275.4075 3179.5315 4763.5552 7723.6182 13553.0898 | lr 1.1e-04 | norm 4840.4688 | dt 9.785 +type train | step 4594 | loss 94.6213 198.5996 308.8570 497.3354 752.9527 1076.8770 1526.2395 2160.9590 3039.4004 4582.5215 7476.3726 13201.7910 | lr 1.1e-04 | norm 4557.7852 | dt 9.792 +type train | step 4595 | loss 101.6692 220.2560 335.2620 536.1434 795.7645 1138.9949 1594.6564 2249.9985 3146.6047 4710.1826 7667.3330 13455.9980 | lr 1.1e-04 | norm 3807.9902 | dt 9.796 +type train | step 4596 | loss 95.1314 202.3324 311.7289 500.0996 754.9265 1080.2502 1524.8435 2160.1248 3046.4766 4583.8721 7482.5454 13136.0791 | lr 1.1e-04 | norm 3436.8608 | dt 9.810 +type train | step 4597 | loss 99.7015 212.4606 330.1388 529.9392 805.3169 1152.2437 1633.4225 2314.9575 3287.3816 4946.8247 7998.5732 14114.9707 | lr 1.1e-04 | norm 3870.7046 | dt 9.783 +type train | step 4598 | loss 98.1555 211.2525 325.9870 517.7406 781.4713 1109.6957 1564.4407 2219.6562 3142.7932 4742.4941 7714.3013 13539.2354 | lr 1.1e-04 | norm 3755.5322 | dt 9.797 +type train | step 4599 | loss 94.0226 199.6794 311.8908 507.3943 765.2099 1098.6440 1563.1499 2223.9480 3144.6868 4755.8101 7708.3071 13491.3389 | lr 1.1e-04 | norm 4074.8342 | dt 9.785 +type train | step 4600 | loss 106.8379 225.4808 350.0650 555.7753 828.0401 1173.4265 1635.6921 2301.4990 3209.7966 4848.4844 7934.7095 14084.1152 | lr 1.1e-04 | norm 5093.0161 | dt 9.782 +type train | step 4601 | loss 94.2032 200.0701 314.5115 504.9339 765.0917 1095.2167 1552.5521 2207.5366 3121.2673 4714.1738 7661.2544 13483.1816 | lr 1.1e-04 | norm 3766.1621 | dt 9.791 +type train | step 4602 | loss 97.9493 208.3943 321.8818 514.8679 775.8627 1108.1047 1551.0205 2191.2607 3080.8457 4616.6235 7473.2549 13077.2295 | lr 1.1e-04 | norm 3253.5200 | dt 9.794 +type train | step 4603 | loss 98.9934 213.0353 327.7101 525.0568 787.8374 1122.2859 1588.0890 2238.1733 3142.8086 4742.1641 7683.7485 13523.6084 | lr 1.1e-04 | norm 4834.0151 | dt 9.790 +type train | step 4604 | loss 106.1688 226.1264 344.7627 544.5502 805.7912 1158.6614 1618.0260 2282.3083 3119.6355 4631.9834 7483.7339 13171.0410 | lr 1.1e-04 | norm 5023.4341 | dt 9.798 +type train | step 4605 | loss 100.1336 212.7092 324.7494 516.5546 775.3589 1109.4368 1549.5183 2189.0352 3049.0212 4571.3276 7432.9844 13034.1172 | lr 1.1e-04 | norm 3375.3857 | dt 9.783 +type train | step 4606 | loss 98.6309 210.6499 326.3966 524.0645 788.7637 1126.8573 1578.1145 2231.9385 3135.0879 4733.5439 7712.1094 13508.0488 | lr 1.1e-04 | norm 3284.9695 | dt 9.804 +type train | step 4607 | loss 105.2186 220.7966 342.7676 556.5593 834.0262 1224.6923 1733.1927 2499.6057 3435.6677 5225.0483 8577.1592 15382.6514 | lr 1.1e-04 | norm 7830.1240 | dt 9.781 +type train | step 4608 | loss 106.2150 225.1001 348.9487 554.5399 832.8788 1197.3704 1680.3778 2393.2537 3312.4822 5008.9082 8120.5024 14369.3975 | lr 1.1e-04 | norm 5007.0874 | dt 9.783 +type train | step 4609 | loss 100.5917 218.7641 339.0297 542.0215 810.1526 1148.5312 1607.6211 2270.5469 3182.9126 4798.2002 7758.5068 13618.5508 | lr 1.1e-04 | norm 3757.6460 | dt 9.794 +type train | step 4610 | loss 98.9476 209.1300 321.3593 514.0021 770.0036 1096.9375 1549.0934 2194.3474 3091.3833 4667.7158 7570.1973 13286.0645 | lr 1.1e-04 | norm 3827.4839 | dt 9.798 +type train | step 4611 | loss 102.9303 219.4701 336.7866 535.7088 799.4703 1143.0283 1607.0277 2271.4697 3146.0349 4703.6553 7637.5322 13435.2998 | lr 1.1e-04 | norm 3946.2314 | dt 9.803 +type train | step 4612 | loss 105.5897 226.6109 343.7764 549.7571 818.2145 1183.9271 1656.7887 2358.6426 3258.2156 4931.8149 8044.8364 14381.7900 | lr 1.1e-04 | norm 6176.3140 | dt 9.779 +type train | step 4613 | loss 101.8007 211.1423 327.0364 527.3596 789.0251 1139.8372 1605.4343 2294.3052 3181.2708 4696.6489 7539.3315 13092.7344 | lr 1.1e-04 | norm 4467.2920 | dt 9.793 +type train | step 4614 | loss 100.6562 215.9774 327.6944 521.1677 784.8415 1128.4875 1587.7684 2256.0955 3148.0181 4747.8872 7745.1318 13666.3018 | lr 1.1e-04 | norm 4043.3530 | dt 9.799 +type train | step 4615 | loss 103.9452 218.8321 332.4260 537.0929 801.9967 1147.0360 1613.6929 2297.9465 3246.8892 4873.1284 7935.1240 14061.8730 | lr 1.1e-04 | norm 4884.3931 | dt 9.789 +type train | step 4616 | loss 103.5162 219.7589 335.7703 533.0590 795.2981 1129.4919 1588.2386 2247.4160 3143.5742 4724.8330 7722.5869 13641.3955 | lr 1.1e-04 | norm 3255.5903 | dt 9.799 +type train | step 4617 | loss 98.7469 212.6857 327.5529 525.3093 794.2854 1114.7272 1572.1715 2212.4912 3094.5652 4674.7026 7609.5674 13490.8877 | lr 1.1e-04 | norm 4979.6270 | dt 9.802 +type train | step 4618 | loss 96.1916 203.4733 316.9836 507.3353 762.7938 1102.6499 1554.6414 2205.1697 3086.9971 4617.0137 7485.5347 13160.3027 | lr 1.1e-04 | norm 4064.9751 | dt 9.811 +type train | step 4619 | loss 95.0550 210.0750 335.6462 539.7275 819.0140 1172.7346 1655.4169 2409.8545 3315.7026 5036.8770 8305.3848 14657.5684 | lr 1.1e-04 | norm 9579.8076 | dt 9.767 +type train | step 4620 | loss 105.2242 223.1755 342.0138 542.6793 807.0380 1155.4792 1615.1311 2277.9485 3157.7344 4729.5439 7712.5327 13662.5566 | lr 1.1e-04 | norm 3960.7212 | dt 9.792 +type train | step 4621 | loss 94.5351 206.4302 328.5279 534.0077 806.0419 1129.2371 1587.1622 2250.0945 3174.4512 4817.5181 7928.3247 14082.6279 | lr 1.1e-04 | norm 8703.9121 | dt 9.801 +type train | step 4622 | loss 100.9159 216.2745 333.6330 529.8170 788.3533 1127.7009 1574.6849 2226.0896 3101.4956 4675.4131 7632.1709 13496.1172 | lr 1.1e-04 | norm 3468.9626 | dt 9.798 +type train | step 4623 | loss 92.3955 195.0639 303.7245 487.5005 740.5550 1059.3483 1507.3959 2139.5566 3020.3159 4532.4360 7384.0444 12982.0137 | lr 1.1e-04 | norm 4382.9907 | dt 9.791 +type train | step 4624 | loss 96.4571 205.8600 319.9102 511.6070 774.5962 1104.7625 1556.0475 2210.9270 3104.6255 4690.2832 7623.9844 13434.5918 | lr 1.1e-04 | norm 3661.4785 | dt 9.801 +type train | step 4625 | loss 108.0922 231.9934 350.0050 550.0113 816.7010 1176.3000 1645.0957 2336.3901 3236.0361 4800.2832 7721.3774 13388.4688 | lr 1.1e-04 | norm 3909.2673 | dt 9.787 +type train | step 4626 | loss 99.8149 212.0688 325.9878 520.8688 784.6368 1129.2809 1585.9863 2249.9382 3146.2598 4724.6621 7644.9180 13417.8135 | lr 1.1e-04 | norm 3311.1194 | dt 9.820 +type train | step 4627 | loss 103.7197 221.4406 337.4623 539.6418 795.8795 1136.6764 1581.9783 2226.6050 3084.2205 4588.3477 7401.9297 12996.9961 | lr 1.1e-04 | norm 3994.4060 | dt 9.792 +type train | step 4628 | loss 99.3029 212.1115 327.1786 525.2692 789.8888 1129.4774 1592.4282 2247.1338 3129.7788 4698.3662 7598.3745 13348.9219 | lr 1.1e-04 | norm 3230.7766 | dt 9.809 +type train | step 4629 | loss 101.9533 216.3464 331.4001 529.3456 789.7321 1130.9908 1587.9109 2249.5955 3148.8674 4749.5601 7787.1328 13863.0361 | lr 1.1e-04 | norm 5084.7822 | dt 9.834 +type train | step 4630 | loss 96.9959 206.1529 320.0801 513.0543 773.4723 1109.9523 1562.8445 2211.3821 3114.9893 4696.2290 7608.0283 13208.3193 | lr 1.1e-04 | norm 3125.6338 | dt 9.825 +type train | step 4631 | loss 99.2849 211.6599 328.0044 527.0800 789.4371 1143.9022 1610.6426 2282.9297 3141.0686 4701.8369 7607.6074 13292.3271 | lr 1.1e-04 | norm 4090.4626 | dt 9.797 +type train | step 4632 | loss 95.8853 205.3292 318.7826 512.1504 776.6381 1110.4270 1572.4854 2233.5586 3125.2551 4683.4707 7612.9512 13483.0469 | lr 1.1e-04 | norm 4152.3496 | dt 9.824 +type train | step 4633 | loss 105.0791 226.6296 342.3622 535.6531 798.8704 1131.5737 1584.6145 2226.2493 3087.9363 4633.1533 7493.9141 13097.7559 | lr 1.1e-04 | norm 3369.4331 | dt 9.809 +type train | step 4634 | loss 100.7075 213.8047 330.2425 527.3564 785.1293 1127.6591 1583.7419 2242.6528 3102.6558 4669.6382 7595.3413 13405.5205 | lr 1.1e-04 | norm 4330.4492 | dt 9.792 +type train | step 4635 | loss 94.4443 200.0346 311.8843 505.0089 762.9932 1105.2695 1569.9724 2243.2163 3138.2693 4744.5752 7752.0913 13708.8838 | lr 1.1e-04 | norm 3817.0256 | dt 9.800 +type train | step 4636 | loss 99.0903 211.6918 327.3683 520.6970 784.0068 1118.3649 1581.1625 2237.0413 3147.0657 4758.5786 7707.3242 13533.4971 | lr 1.1e-04 | norm 3436.6460 | dt 9.799 +type train | step 4637 | loss 102.2435 222.1996 343.6750 551.2322 822.4988 1168.7972 1630.6187 2293.6675 3216.9036 4820.2422 7707.9175 13459.5352 | lr 1.1e-04 | norm 4744.4980 | dt 9.799 +type train | step 4638 | loss 117.3565 256.5195 384.6589 602.1932 865.3113 1186.1532 1587.3805 2141.7529 2929.6980 4273.5557 6733.9272 12009.4355 | lr 1.1e-04 | norm 4974.4805 | dt 9.748 +type train | step 4639 | loss 100.1312 218.3860 332.1805 521.7814 781.4734 1126.9503 1600.4937 2273.7390 3131.3704 4785.5288 7866.3770 14008.5918 | lr 1.1e-04 | norm 7773.7480 | dt 9.793 +type train | step 4640 | loss 101.1128 217.8823 332.6140 527.9033 790.2362 1127.4376 1585.2042 2244.0938 3143.6714 4746.7837 7721.4966 13582.9688 | lr 1.1e-04 | norm 3797.4980 | dt 9.796 +type train | step 4641 | loss 97.1457 206.1696 318.2199 503.1388 759.4307 1079.7791 1523.8765 2162.3508 3053.9963 4601.5894 7495.2725 13122.9951 | lr 1.1e-04 | norm 3176.0991 | dt 9.793 +type train | step 4642 | loss 104.5269 226.1122 342.4539 539.3717 802.9715 1133.7638 1586.4677 2250.1582 3162.2791 4781.3013 7874.9312 13968.5439 | lr 1.1e-04 | norm 6136.6191 | dt 9.788 +type train | step 4643 | loss 99.9618 214.6066 329.7958 525.9689 789.4861 1144.9291 1617.1841 2299.9968 3208.8359 4809.9990 7826.2979 13786.5020 | lr 1.1e-04 | norm 3585.2341 | dt 9.789 +type train | step 4644 | loss 104.0274 224.7747 340.6066 533.4575 791.1467 1131.5925 1589.2310 2242.5750 3119.8425 4626.3550 7442.4321 13163.1582 | lr 1.1e-04 | norm 5174.9805 | dt 9.769 +type train | step 4645 | loss 98.2414 210.1015 322.7487 516.4792 775.4443 1112.8494 1569.7738 2225.8672 3111.8047 4674.6265 7590.3511 13332.1592 | lr 1.1e-04 | norm 3525.6558 | dt 9.970 +type train | step 4646 | loss 105.4009 227.4835 343.0141 542.9664 808.6035 1159.8733 1615.5719 2300.8103 3157.6733 4704.7441 7648.1753 13597.7080 | lr 1.1e-04 | norm 4997.6260 | dt 9.826 +type train | step 4647 | loss 94.7117 203.6583 313.2435 506.8576 765.5302 1101.7427 1562.7885 2222.9775 3105.8281 4697.6831 7671.4424 13435.8457 | lr 1.1e-04 | norm 6411.2144 | dt 9.829 +type train | step 4648 | loss 91.8470 200.4798 311.6043 504.5933 760.9543 1084.3733 1538.6372 2187.7258 3077.6443 4662.7046 7593.6206 13357.3398 | lr 1.1e-04 | norm 4248.3105 | dt 9.826 +type train | step 4649 | loss 94.9727 201.0953 310.2371 498.9851 754.4818 1086.8115 1535.9470 2191.5322 3099.1501 4697.1255 7620.3286 13343.4062 | lr 1.1e-04 | norm 3360.5955 | dt 9.822 +type train | step 4650 | loss 95.8386 206.1599 318.1651 508.7048 768.5345 1099.9086 1552.5806 2197.4729 3086.3486 4642.6836 7479.0957 13179.6162 | lr 1.1e-04 | norm 3824.7969 | dt 9.803 +type train | step 4651 | loss 90.9085 193.5914 301.2206 486.5876 740.0284 1066.6273 1520.3052 2176.2725 3077.2854 4687.1748 7676.4648 13575.8193 | lr 1.1e-04 | norm 3622.4028 | dt 9.790 +type train | step 4652 | loss 99.1087 209.6607 322.6139 518.6619 777.3470 1109.5521 1559.4044 2206.2952 3088.5071 4673.0571 7628.9248 13554.5742 | lr 1.1e-04 | norm 3810.5544 | dt 9.786 +type train | step 4653 | loss 102.6117 217.7267 340.4659 542.8519 808.0135 1151.7156 1610.1355 2268.8176 3150.3533 4719.2241 7635.0820 13373.2295 | lr 1.1e-04 | norm 4365.2651 | dt 9.777 +type train | step 4654 | loss 102.4839 218.8110 336.3833 536.3685 804.6699 1151.3335 1619.4813 2295.4795 3209.2361 4828.1250 7831.0703 13849.4453 | lr 1.1e-04 | norm 4407.6631 | dt 9.775 +type train | step 4655 | loss 97.1700 207.8445 320.7048 512.3787 772.1935 1100.3651 1550.1597 2194.8438 3091.6501 4685.1582 7611.1460 13395.4482 | lr 1.1e-04 | norm 3500.7578 | dt 9.798 +type train | step 4656 | loss 102.0715 217.3631 328.9269 525.3376 787.6219 1134.2571 1589.0864 2262.6543 3183.3376 4791.5049 7729.6426 13510.3545 | lr 1.1e-04 | norm 3677.2356 | dt 9.765 +type train | step 4657 | loss 92.5956 204.1768 325.6642 537.4336 815.3564 1179.0227 1688.1426 2440.0303 3432.9749 5277.6914 8865.4834 16026.0645 | lr 1.1e-04 | norm 9222.4961 | dt 9.765 +type train | step 4658 | loss 99.8736 211.6358 326.2917 525.2340 788.2405 1138.8203 1606.2124 2283.4072 3184.6619 4791.7783 7775.4810 13734.5635 | lr 1.1e-04 | norm 4206.4756 | dt 9.767 +type train | step 4659 | loss 98.1173 208.0027 321.0998 515.6371 773.6336 1105.1218 1554.2894 2209.0549 3077.6450 4660.8906 7628.5630 13553.6904 | lr 1.1e-04 | norm 4283.4087 | dt 9.766 +type train | step 4660 | loss 99.9119 211.7945 323.9210 513.8353 770.6752 1112.6177 1572.0417 2236.4407 3094.6375 4646.3286 7533.3496 13259.0244 | lr 1.1e-04 | norm 3774.3684 | dt 9.786 +type train | step 4661 | loss 111.4221 242.0357 368.2146 581.2922 857.3853 1226.1663 1712.6034 2439.6096 3344.8696 4967.3247 8007.1343 13979.0684 | lr 1.1e-04 | norm 5094.9937 | dt 9.777 +type train | step 4662 | loss 98.2602 211.8488 327.6652 526.4287 789.0927 1129.2007 1589.5126 2242.3005 3154.6406 4731.9629 7656.6362 13471.1738 | lr 1.1e-04 | norm 3668.5117 | dt 9.771 +type train | step 4663 | loss 107.1095 228.0419 347.2593 550.7910 814.5795 1159.2877 1615.3507 2258.4849 3113.3972 4634.6787 7441.7910 12941.5840 | lr 1.1e-04 | norm 3585.2505 | dt 9.775 +type train | step 4664 | loss 98.1409 211.6628 326.8384 521.5259 779.7894 1125.0048 1579.0131 2240.2710 3113.9832 4708.0361 7669.4795 13569.3281 | lr 1.1e-04 | norm 4246.9482 | dt 9.768 +type train | step 4665 | loss 101.6073 215.6661 330.6861 527.3212 783.6435 1122.6305 1563.4366 2199.6519 3061.0981 4601.2109 7474.9941 13204.4482 | lr 1.1e-04 | norm 3591.0745 | dt 9.761 +type train | step 4666 | loss 96.1592 204.2688 317.8014 511.0987 766.3246 1097.2030 1554.1056 2210.9583 3110.8994 4702.1831 7658.2285 13485.5195 | lr 1.1e-04 | norm 3728.6328 | dt 9.790 +type train | step 4667 | loss 97.3000 210.7319 324.0411 514.9757 777.3149 1115.5427 1573.5941 2237.4297 3135.4001 4711.7749 7673.8301 13454.7422 | lr 1.1e-04 | norm 3491.7100 | dt 9.790 +type train | step 4668 | loss 107.8550 232.9055 349.1894 541.3777 810.3234 1148.4153 1603.7393 2258.8835 3138.7268 4716.5898 7646.5972 13399.4883 | lr 1.1e-04 | norm 6622.1963 | dt 9.775 +type train | step 4669 | loss 103.0864 224.7041 340.7102 536.7074 800.5774 1147.3087 1614.1113 2294.7405 3204.4727 4843.3154 7846.6836 13785.5430 | lr 1.1e-04 | norm 4702.1167 | dt 9.776 +type train | step 4670 | loss 102.4198 217.1473 332.9512 532.8952 798.7275 1141.9988 1598.7415 2262.0249 3136.2085 4719.5415 7650.7544 13462.1094 | lr 1.1e-04 | norm 3809.7004 | dt 9.774 +type train | step 4671 | loss 92.2514 195.1691 303.7485 489.8246 743.9440 1065.9062 1515.4739 2167.7261 3079.5684 4677.5015 7646.4219 13484.6182 | lr 1.1e-04 | norm 3465.9497 | dt 9.765 +type train | step 4672 | loss 94.4609 201.6594 312.9010 506.9642 766.3556 1103.8608 1557.0524 2216.8337 3097.8433 4676.4795 7629.2158 13498.8945 | lr 1.1e-04 | norm 3565.7708 | dt 9.757 +type train | step 4673 | loss 100.2139 212.5870 327.2533 520.5753 782.9199 1119.6113 1571.5869 2228.3635 3125.5942 4685.6201 7569.1123 13163.9629 | lr 1.1e-04 | norm 3572.2087 | dt 9.777 +type train | step 4674 | loss 92.1970 200.4481 314.7650 510.7226 784.2164 1131.4141 1605.2147 2301.2327 3260.5837 4966.6162 8056.4385 14138.2109 | lr 1.1e-04 | norm 3898.3479 | dt 9.768 +type train | step 4675 | loss 92.6318 193.0720 301.2485 488.1074 744.2794 1090.3673 1560.1068 2262.0676 3193.3174 4848.7588 7906.3423 13972.8281 | lr 1.1e-04 | norm 3994.0110 | dt 9.769 +type train | step 4676 | loss 100.5225 215.3381 328.0192 520.1923 782.5438 1115.8457 1570.9321 2215.8889 3110.0867 4642.7476 7522.1904 13136.1426 | lr 1.1e-04 | norm 3890.1863 | dt 9.797 +type train | step 4677 | loss 96.3676 203.0789 316.2015 510.2594 764.2381 1099.9056 1552.9669 2205.4688 3108.2852 4702.0532 7677.9570 13507.3096 | lr 1.1e-04 | norm 3454.5044 | dt 9.773 +type train | step 4678 | loss 100.0178 213.8829 330.2882 525.2629 786.7459 1126.9500 1580.0967 2230.8281 3095.4536 4651.7651 7565.9365 13314.8428 | lr 1.1e-04 | norm 3953.1150 | dt 9.777 +type train | step 4679 | loss 96.5797 207.7818 319.5578 510.3446 770.6512 1106.5916 1560.8810 2202.7383 3073.4526 4632.0220 7529.1650 13331.9395 | lr 1.1e-04 | norm 3709.4492 | dt 9.793 +type train | step 4680 | loss 113.7399 244.9740 353.6702 555.3530 821.5755 1171.7761 1637.5525 2289.4834 3150.7007 4705.5791 7633.5024 13422.6172 | lr 1.1e-04 | norm 5675.4897 | dt 9.756 +type train | step 4681 | loss 89.0986 190.4748 300.8326 492.9655 756.2137 1103.6334 1568.6692 2261.3142 3192.9014 4856.2124 7858.1016 13758.3486 | lr 1.1e-04 | norm 3360.5593 | dt 9.774 +type train | step 4682 | loss 94.4746 200.7980 313.1288 503.9575 762.9327 1097.8171 1549.7367 2197.2690 3093.5098 4649.0176 7534.1631 13189.9688 | lr 1.1e-04 | norm 3015.0808 | dt 9.809 +type train | step 4683 | loss 99.2242 212.9739 327.9810 521.2269 784.5947 1120.1932 1579.1814 2244.9026 3145.2048 4732.5146 7705.8599 13551.8848 | lr 1.1e-04 | norm 3458.0066 | dt 9.796 +type train | step 4684 | loss 91.6313 192.0793 296.5076 481.5587 737.7095 1080.0966 1537.0029 2216.9756 3109.2490 4734.2471 7731.7700 13629.5352 | lr 1.1e-04 | norm 5329.2715 | dt 9.803 +type train | step 4685 | loss 92.9597 205.5753 333.9119 553.4445 835.5081 1186.5209 1668.7174 2375.7612 3354.1482 5145.2480 8527.6553 15181.3193 | lr 1.1e-04 | norm 7847.6392 | dt 9.790 +type train | step 4686 | loss 95.3125 214.6024 340.0317 553.5519 832.6260 1176.4620 1651.7045 2339.1216 3316.4294 5073.7051 8329.4033 14718.6855 | lr 1.1e-04 | norm 6355.0479 | dt 9.783 +type train | step 4687 | loss 91.7910 193.2430 303.2421 492.5016 748.0390 1077.8168 1531.4668 2190.9075 3089.9773 4670.6641 7591.5254 13331.7656 | lr 1.1e-04 | norm 3386.7773 | dt 9.764 +type train | step 4688 | loss 91.1016 195.4315 304.5847 493.2402 751.9329 1080.4612 1531.3954 2185.6741 3099.2251 4704.0132 7693.6631 13543.1631 | lr 1.1e-04 | norm 4330.3491 | dt 9.773 +type train | step 4689 | loss 104.7637 224.2488 339.2763 535.7858 794.3892 1138.0281 1587.3070 2239.8359 3097.1792 4623.9990 7485.2925 13114.2266 | lr 1.1e-04 | norm 3458.8081 | dt 9.772 +type train | step 4690 | loss 96.1538 204.3205 316.9514 507.3797 768.5098 1097.6465 1543.4095 2186.7095 3058.6794 4590.4487 7471.1328 13130.7383 | lr 1.1e-04 | norm 4104.7183 | dt 9.759 +type train | step 4691 | loss 95.7657 204.2276 316.7057 511.2006 767.2086 1103.2614 1561.5039 2216.3506 3119.7910 4692.8125 7643.9727 13536.5537 | lr 1.1e-04 | norm 4105.3936 | dt 9.759 +type train | step 4692 | loss 107.5088 230.8980 349.4998 546.0800 809.5991 1156.4724 1618.4812 2270.3647 3151.1943 4732.9277 7644.0713 13391.0654 | lr 1.1e-04 | norm 3958.1077 | dt 9.768 +type train | step 4693 | loss 96.2738 207.2608 320.2077 516.8127 781.1175 1131.8501 1603.0101 2277.7249 3213.9133 4864.7383 7918.8584 13958.2266 | lr 1.1e-04 | norm 4063.8218 | dt 9.758 +type train | step 4694 | loss 97.8034 209.3713 322.6276 516.6235 777.9709 1112.4360 1574.6344 2228.9016 3135.5227 4723.2778 7620.6772 13340.8057 | lr 1.1e-04 | norm 3687.6267 | dt 9.801 +type train | step 4695 | loss 95.3522 203.5944 312.3144 495.8474 748.0356 1075.4972 1522.7540 2173.6909 3069.8071 4630.2324 7504.4746 13103.7402 | lr 1.1e-04 | norm 3315.4138 | dt 9.783 +type train | step 4696 | loss 99.1367 206.6570 318.7322 521.3035 784.4634 1151.4924 1621.3512 2330.1418 3263.1638 4885.6079 7958.8735 14013.2461 | lr 1.1e-04 | norm 5051.7778 | dt 9.760 +type train | step 4697 | loss 89.9125 191.4063 299.0599 489.4218 742.6943 1086.6107 1551.4609 2230.6172 3156.9351 4809.0894 7820.2271 13805.7197 | lr 1.0e-04 | norm 4469.3906 | dt 9.746 +type train | step 4698 | loss 99.9721 217.3622 332.7711 534.4106 804.9490 1148.3635 1624.1530 2306.5037 3259.4070 4924.9463 8038.4150 14190.0996 | lr 1.0e-04 | norm 4415.2354 | dt 9.763 +type train | step 4699 | loss 95.5167 203.5601 316.6568 507.0734 767.2646 1106.2534 1568.8203 2229.1392 3129.0947 4726.4141 7666.8784 13434.4844 | lr 1.0e-04 | norm 3285.5579 | dt 9.757 +type train | step 4700 | loss 92.2523 193.6192 305.3860 493.4236 750.4901 1074.3912 1514.8923 2150.1895 3045.3760 4575.7026 7437.9531 13025.9717 | lr 1.0e-04 | norm 3539.1072 | dt 9.775 +type train | step 4701 | loss 102.1584 217.7353 334.9983 531.6580 788.6727 1118.4810 1555.8719 2180.3301 3021.7944 4529.9087 7298.8882 12958.0713 | lr 1.0e-04 | norm 4783.6812 | dt 9.770 +type train | step 4702 | loss 103.6575 221.5251 340.0830 544.5338 816.5302 1175.7273 1648.3297 2320.4875 3223.5767 4781.4189 7676.7520 13419.3564 | lr 1.0e-04 | norm 3612.3557 | dt 9.779 +type train | step 4703 | loss 97.6425 209.0530 320.0011 508.0049 762.5333 1076.8296 1511.5844 2123.4050 2987.6882 4479.9629 7231.9375 12590.3457 | lr 1.0e-04 | norm 3133.0208 | dt 9.785 +type train | step 4704 | loss 91.2367 194.4292 300.9875 491.1584 744.4773 1074.1979 1537.3384 2184.7263 3084.0103 4659.6406 7572.2158 13296.1660 | lr 1.0e-04 | norm 4836.0776 | dt 9.760 +type train | step 4705 | loss 101.4173 213.8238 328.2676 519.1935 779.7122 1133.3569 1598.0138 2275.5869 3178.9031 4788.4297 7793.4404 13701.1543 | lr 1.0e-04 | norm 3982.0767 | dt 9.784 +type train | step 4706 | loss 95.3152 200.4932 313.6222 502.5731 755.6880 1081.6897 1524.9902 2161.2590 3035.3794 4578.7944 7424.1177 13027.3711 | lr 1.0e-04 | norm 3015.2842 | dt 9.774 +type train | step 4707 | loss 97.5645 205.5674 315.2848 503.5719 758.6243 1102.0809 1558.1001 2227.4426 3121.9814 4697.1445 7631.8159 13410.0664 | lr 1.0e-04 | norm 3342.5713 | dt 9.761 +type train | step 4708 | loss 119.7976 262.7974 400.7137 637.8452 927.6399 1315.8295 1794.2262 2470.7981 3320.8713 4802.4087 7563.7983 13380.0293 | lr 1.0e-04 | norm 6396.0259 | dt 9.744 +type train | step 4709 | loss 94.2399 201.1435 311.3723 502.5172 763.1033 1114.1857 1583.3895 2276.3792 3173.2000 4758.1865 7721.0327 13693.4336 | lr 1.0e-04 | norm 4300.4990 | dt 9.756 +type train | step 4710 | loss 109.7592 233.5765 363.6361 582.6442 864.5343 1229.6964 1703.1093 2393.3259 3325.6719 5009.7349 8107.8701 14300.0967 | lr 1.0e-04 | norm 4622.4053 | dt 9.753 +type train | step 4711 | loss 100.0924 213.5012 329.0144 522.1738 777.8725 1119.5559 1574.6993 2242.9392 3131.5647 4716.8618 7660.0640 13461.1328 | lr 1.0e-04 | norm 3878.6804 | dt 9.753 +type train | step 4712 | loss 103.9453 224.9708 343.7514 542.1340 803.6614 1149.0815 1600.6049 2246.5259 3104.6201 4636.8027 7522.9355 13232.8633 | lr 1.0e-04 | norm 4083.7957 | dt 9.752 +type train | step 4713 | loss 107.0317 231.1086 345.8226 545.6878 806.8989 1153.2091 1607.6692 2258.6072 3103.7075 4644.4424 7593.2192 13509.1445 | lr 1.0e-04 | norm 5661.6890 | dt 9.743 +type train | step 4714 | loss 98.1629 207.5447 320.5858 514.0393 778.6299 1129.7119 1601.5007 2284.7268 3176.6973 4798.5601 7790.1318 13825.4482 | lr 1.0e-04 | norm 4406.6846 | dt 9.766 +type train | step 4715 | loss 106.5360 226.8962 345.2655 543.7095 814.7087 1160.6504 1637.8561 2346.2688 3269.0271 4925.7246 7866.3599 13850.6494 | lr 1.0e-04 | norm 7368.6494 | dt 9.773 +type train | step 4716 | loss 100.8519 212.8603 325.9577 519.7504 780.1593 1118.8232 1572.4188 2233.2466 3122.3657 4701.7690 7601.5605 13319.4678 | lr 1.0e-04 | norm 4018.2148 | dt 9.750 +type train | step 4717 | loss 110.1905 234.6556 357.0958 568.0228 853.9576 1244.5731 1736.3981 2475.1069 3401.9509 5125.7632 8282.9375 14659.2129 | lr 1.0e-04 | norm 7604.7568 | dt 9.748 +type train | step 4718 | loss 97.6389 209.5614 325.1489 521.0012 780.9875 1124.1886 1581.0526 2236.5430 3150.1631 4715.6318 7618.5186 13371.3125 | lr 1.0e-04 | norm 3375.7568 | dt 9.794 +type train | step 4719 | loss 96.5236 209.0073 325.9240 522.5534 788.3607 1128.7251 1590.8506 2260.3274 3174.8896 4793.6646 7784.3325 13640.3457 | lr 1.0e-04 | norm 4112.3457 | dt 9.765 +type train | step 4720 | loss 107.0276 229.4808 349.2968 554.1473 816.5634 1165.3813 1619.1117 2261.3345 3095.5295 4620.7646 7458.1704 13151.4209 | lr 1.0e-04 | norm 3594.7244 | dt 9.762 +type train | step 4721 | loss 97.8497 206.6362 318.4071 511.0148 767.0056 1101.9705 1559.2150 2213.5647 3096.9622 4665.2393 7575.3936 13341.8936 | lr 1.0e-04 | norm 3619.9111 | dt 9.784 +type train | step 4722 | loss 103.6932 222.1385 337.7144 533.8417 795.7662 1119.2219 1568.7810 2212.9685 3114.2690 4689.7153 7596.0366 13324.0205 | lr 1.0e-04 | norm 4038.1418 | dt 9.766 +type train | step 4723 | loss 97.0538 204.7303 315.4216 519.3272 782.4348 1157.3093 1646.8210 2383.4917 3311.6196 4988.0386 8104.1064 14131.6055 | lr 1.0e-04 | norm 5027.5112 | dt 9.756 +type train | step 4724 | loss 103.5750 222.0739 342.1180 540.4667 803.7448 1154.2561 1615.9220 2288.4639 3173.1707 4774.9912 7741.3862 13532.6748 | lr 1.0e-04 | norm 3928.2498 | dt 9.771 +type train | step 4725 | loss 91.0816 193.9886 302.4753 492.6010 752.8757 1090.9906 1554.6971 2229.0562 3138.3135 4747.1562 7681.7207 13501.3398 | lr 1.0e-04 | norm 3835.0786 | dt 9.766 +type train | step 4726 | loss 100.1344 215.5365 329.0951 522.9493 780.9145 1122.9542 1581.5986 2238.5356 3129.6187 4685.5229 7590.4409 13224.1426 | lr 1.0e-04 | norm 3294.9309 | dt 9.771 +type train | step 4727 | loss 100.9242 215.4215 331.7812 528.6320 790.4086 1132.0067 1595.9871 2259.6479 3172.9827 4789.1050 7811.0488 13742.8896 | lr 1.0e-04 | norm 3224.3647 | dt 9.758 +type train | step 4728 | loss 100.0616 215.0068 330.6252 529.4888 796.9321 1160.9205 1639.6460 2344.0063 3277.5476 4944.5732 7991.7861 14098.0801 | lr 1.0e-04 | norm 5447.2861 | dt 9.771 +type train | step 4729 | loss 117.3916 253.1702 379.2868 598.8778 860.3228 1230.3726 1663.6399 2314.8589 3050.6604 4447.9189 7172.3696 13008.3740 | lr 1.0e-04 | norm 9372.1143 | dt 9.725 +type train | step 4730 | loss 102.4368 219.3882 333.6344 526.9879 790.0613 1135.3760 1598.2194 2271.0750 3168.2410 4732.4688 7715.3652 13590.6113 | lr 1.0e-04 | norm 3677.0266 | dt 9.790 +type train | step 4731 | loss 100.6882 219.0108 333.1441 525.6810 786.5306 1116.9487 1563.2997 2197.9124 3067.3040 4620.7168 7521.2646 13344.8672 | lr 1.0e-04 | norm 3939.5229 | dt 9.786 +type train | step 4732 | loss 97.9466 208.5914 321.5269 514.6957 775.2242 1113.9387 1568.8042 2225.4348 3118.0032 4703.5186 7610.5400 13426.9678 | lr 1.0e-04 | norm 3509.9941 | dt 9.790 +type train | step 4733 | loss 95.8469 204.7103 316.5427 502.7280 755.8405 1083.4417 1529.3387 2166.3271 3035.6807 4566.0439 7390.7207 12792.4238 | lr 1.0e-04 | norm 3129.0386 | dt 9.787 +type train | step 4734 | loss 92.7579 193.9384 302.1856 487.6999 750.1981 1083.5979 1546.9470 2216.3296 3131.8381 4757.3647 7719.3193 13567.2979 | lr 1.0e-04 | norm 5618.6938 | dt 9.770 +type train | step 4735 | loss 101.0293 215.7873 335.4899 539.4324 807.9334 1156.9150 1623.0938 2297.7087 3220.0703 4842.9165 7870.6182 13814.1113 | lr 1.0e-04 | norm 3885.7039 | dt 9.781 +type train | step 4736 | loss 102.9213 220.2720 338.9715 537.9878 802.6741 1148.1675 1610.8834 2274.7915 3146.1455 4729.2173 7691.2983 13563.2051 | lr 1.0e-04 | norm 3875.3362 | dt 9.764 +type train | step 4737 | loss 94.0155 201.0968 317.3405 506.5807 767.7830 1100.2585 1566.7510 2232.5742 3160.7720 4796.2207 7840.5117 13906.8848 | lr 1.0e-04 | norm 4459.4834 | dt 9.773 +type train | step 4738 | loss 101.7803 219.6855 332.9873 527.3494 784.3740 1121.6360 1570.4498 2215.2957 3101.8838 4663.9292 7545.3335 13165.0234 | lr 1.0e-04 | norm 3427.8665 | dt 9.782 +type train | step 4739 | loss 104.0107 223.7833 345.4922 543.6276 807.5965 1146.2596 1604.9161 2255.0996 3132.4756 4721.0112 7706.7295 13640.5703 | lr 1.0e-04 | norm 4343.5991 | dt 9.765 +type train | step 4740 | loss 93.2037 198.4730 307.3150 494.4091 747.0514 1076.1237 1529.9487 2185.6265 3082.5962 4664.5669 7608.5825 13360.4512 | lr 1.0e-04 | norm 3304.2925 | dt 9.770 +type train | step 4741 | loss 102.7618 219.4255 336.5119 533.4003 792.7000 1127.8787 1578.5918 2238.2039 3095.3765 4631.0771 7509.5166 13264.9395 | lr 1.0e-04 | norm 3792.6812 | dt 9.755 +type train | step 4742 | loss 102.2025 219.6211 334.7430 525.5269 781.3148 1122.0458 1575.2915 2233.4421 3109.2336 4661.4233 7565.6846 13310.8135 | lr 1.0e-04 | norm 3920.7192 | dt 9.770 +type train | step 4743 | loss 105.6872 230.2655 354.0247 565.0317 844.8784 1206.0950 1685.5696 2389.5298 3332.9385 4989.0767 8070.5259 14278.0322 | lr 1.0e-04 | norm 4771.8018 | dt 9.762 +type train | step 4744 | loss 98.6551 211.1849 324.4301 513.1351 768.6460 1100.0706 1542.0801 2171.0334 3044.0288 4555.2212 7399.3271 13013.0068 | lr 1.0e-04 | norm 3847.3745 | dt 9.770 +type train | step 4745 | loss 104.1458 224.1147 341.1296 538.6086 800.4601 1137.8099 1599.9879 2242.3467 3136.6204 4705.3481 7541.0376 13154.2139 | lr 1.0e-04 | norm 4666.7568 | dt 9.761 +type train | step 4746 | loss 91.7962 193.2067 300.5214 484.3023 736.9669 1063.5497 1513.7936 2159.1992 3044.8472 4606.6514 7464.6797 13266.2656 | lr 1.0e-04 | norm 4681.6924 | dt 9.760 +type train | step 4747 | loss 104.3259 225.0299 339.6750 541.0632 801.8891 1153.4482 1615.0581 2276.7673 3137.5295 4682.2441 7574.0825 13342.3027 | lr 1.0e-04 | norm 3717.6609 | dt 9.777 +type train | step 4748 | loss 98.1408 209.1318 323.8277 518.1975 775.6934 1110.8253 1561.0759 2200.8665 3094.6968 4680.1763 7604.5825 13341.3184 | lr 1.0e-04 | norm 3215.6084 | dt 9.773 +type train | step 4749 | loss 95.7898 205.7472 317.2990 511.0164 767.7931 1101.7679 1556.4667 2207.9673 3115.9070 4686.6021 7637.2588 13404.3193 | lr 1.0e-04 | norm 3210.0046 | dt 9.775 +type train | step 4750 | loss 104.6330 223.0827 339.7686 536.8253 797.6896 1152.8909 1617.3585 2264.3269 3138.6125 4705.5381 7577.9521 13299.9033 | lr 1.0e-04 | norm 3954.5105 | dt 9.775 +type train | step 4751 | loss 100.5119 218.2214 332.8087 532.0822 794.0708 1129.0217 1584.6268 2223.2224 3115.9067 4695.2065 7657.5020 13456.8691 | lr 1.0e-04 | norm 3419.2971 | dt 9.779 +type train | step 4752 | loss 100.1967 214.8393 328.9037 525.8177 787.1089 1139.3959 1608.1925 2285.4714 3184.3096 4751.7358 7723.5703 13520.9375 | lr 1.0e-04 | norm 3242.5085 | dt 9.791 +type train | step 4753 | loss 92.9541 196.3132 303.3598 492.7502 746.2192 1082.0120 1540.9033 2196.1382 3104.3601 4673.4883 7504.8682 13134.1279 | lr 1.0e-04 | norm 3425.3633 | dt 9.770 +type train | step 4754 | loss 95.6296 205.5101 319.5673 511.5888 767.2632 1098.4316 1547.9139 2192.3879 3082.1006 4659.7119 7554.9404 13264.1455 | lr 1.0e-04 | norm 3048.6855 | dt 9.770 +type train | step 4755 | loss 94.7501 201.0948 311.5536 498.5167 749.9897 1071.6178 1513.9673 2144.3608 3020.0691 4554.1045 7419.1499 13035.4678 | lr 1.0e-04 | norm 3039.0684 | dt 9.784 +type train | step 4756 | loss 94.3161 200.9651 311.9128 501.6121 758.6329 1089.1144 1541.2715 2181.0762 3068.7549 4612.6450 7498.4194 13142.9756 | lr 1.0e-04 | norm 3144.7358 | dt 9.766 +type train | step 4757 | loss 100.9036 216.3933 333.9036 540.3262 805.9619 1165.0948 1636.5942 2329.6978 3263.1829 4864.5640 7858.2139 13692.5840 | lr 1.0e-04 | norm 4136.9277 | dt 9.756 +type train | step 4758 | loss 100.8997 218.0275 334.5858 533.8533 795.5912 1124.5314 1572.3938 2212.7231 3087.9045 4636.4751 7488.3301 13144.0996 | lr 1.0e-04 | norm 3417.8435 | dt 9.766 +type train | step 4759 | loss 101.1683 217.0379 324.7625 520.4204 777.3579 1123.7073 1575.1787 2226.3188 3049.5950 4591.3066 7513.7285 13296.1445 | lr 1.0e-04 | norm 6163.0195 | dt 9.751 +type train | step 4760 | loss 93.7862 202.2826 306.3219 500.8221 757.7875 1105.6965 1572.5103 2256.2017 3167.6045 4818.2681 7823.3354 13700.9023 | lr 1.0e-04 | norm 5401.9741 | dt 9.759 +type train | step 4761 | loss 97.5786 205.3809 316.6291 507.6493 762.2474 1094.2939 1543.7177 2189.1716 3075.4355 4637.7905 7502.6973 13099.0195 | lr 1.0e-04 | norm 3526.9646 | dt 9.769 +type train | step 4762 | loss 107.3049 233.3538 354.2288 552.2581 814.0331 1160.0865 1608.7982 2253.9426 3103.7917 4623.0674 7454.6279 13041.2744 | lr 1.0e-04 | norm 3161.6965 | dt 9.775 +type train | step 4763 | loss 112.9596 245.1095 373.0250 584.2335 840.1633 1190.4399 1622.6882 2216.1079 2946.6582 4301.5249 6821.5640 12151.5908 | lr 1.0e-04 | norm 8444.6982 | dt 9.721 +type train | step 4764 | loss 103.0158 218.7169 338.5090 538.7026 798.3130 1144.4879 1606.9973 2271.1406 3169.8049 4773.5605 7734.0322 13588.0820 | lr 1.0e-04 | norm 3833.4919 | dt 9.768 +type train | step 4765 | loss 101.6861 216.5183 331.4547 527.4565 789.4650 1137.7625 1599.2885 2279.1055 3190.3101 4815.6172 7922.2725 14198.6074 | lr 1.0e-04 | norm 5160.9302 | dt 9.755 +type train | step 4766 | loss 99.9306 213.9745 329.3600 523.7476 786.4913 1132.4470 1594.8826 2278.5449 3195.0879 4811.0752 7847.3467 13976.1465 | lr 1.0e-04 | norm 3900.8701 | dt 9.762 +type train | step 4767 | loss 115.6873 247.4474 370.4146 577.7816 857.5924 1205.8566 1666.8225 2329.0864 3209.7053 4814.3252 7763.4487 13582.7793 | lr 1.0e-04 | norm 4287.7466 | dt 9.761 +type train | step 4768 | loss 106.3265 224.8710 342.9058 548.9973 807.1809 1164.6672 1637.3647 2332.4717 3267.8945 4935.3936 8001.0000 14109.1045 | lr 1.0e-04 | norm 5560.1699 | dt 9.745 +type train | step 4769 | loss 96.4728 207.9024 320.7569 510.7171 769.2296 1096.7737 1548.3265 2191.2239 3077.1812 4659.3843 7561.2900 13230.7930 | lr 1.0e-04 | norm 3099.3911 | dt 9.777 +type train | step 4770 | loss 99.0291 214.4267 328.7631 522.5965 781.4984 1119.2898 1581.5959 2239.8188 3148.1611 4746.4175 7714.3198 13543.9297 | lr 1.0e-04 | norm 3882.3389 | dt 9.765 +type train | step 4771 | loss 96.7772 204.4913 317.4961 504.5215 758.6161 1087.8704 1528.2607 2161.0283 3041.1792 4580.3477 7426.5513 13017.9912 | lr 1.0e-04 | norm 3021.4622 | dt 9.769 +type train | step 4772 | loss 97.6040 215.0225 332.3960 529.4240 795.4497 1131.3085 1586.7274 2232.8481 3140.5730 4704.8604 7617.8105 13266.8486 | lr 1.0e-04 | norm 3760.0129 | dt 9.774 +type train | step 4773 | loss 96.7710 207.8219 322.0712 515.3905 776.7031 1127.3588 1596.4634 2280.4448 3181.8008 4800.7983 7813.5415 13747.1055 | lr 1.0e-04 | norm 3623.1663 | dt 9.761 +type train | step 4774 | loss 102.0203 217.0944 333.3145 526.0088 787.7823 1130.3467 1585.7415 2246.2483 3144.1829 4722.0098 7682.3535 13542.5498 | lr 1.0e-04 | norm 3825.0115 | dt 9.762 +type train | step 4775 | loss 97.9009 210.6350 323.2235 517.4760 778.6045 1115.9197 1578.7471 2253.1533 3169.8677 4746.5132 7656.8760 13509.5215 | lr 1.0e-04 | norm 3712.5015 | dt 9.765 +type train | step 4776 | loss 96.5029 207.2959 322.2144 518.4509 778.8980 1130.6478 1597.7262 2267.6970 3167.6733 4773.0688 7799.4438 13712.9326 | lr 1.0e-04 | norm 3894.9832 | dt 9.757 +type train | step 4777 | loss 97.2800 210.0671 322.9142 510.8423 770.4577 1101.1353 1556.5901 2207.7104 3100.6519 4680.7715 7574.9214 13285.8750 | lr 1.0e-04 | norm 3513.2146 | dt 9.771 +type train | step 4778 | loss 105.5458 230.2656 345.1782 544.7507 804.3837 1152.5223 1603.8923 2253.2383 3118.0164 4662.7886 7515.4868 13114.0469 | lr 1.0e-04 | norm 4102.7988 | dt 9.790 +type train | step 4779 | loss 108.3859 230.9661 355.2034 569.3961 838.6684 1229.8315 1721.1704 2448.0801 3334.4683 4959.1455 8073.6543 14502.8936 | lr 1.0e-04 | norm 7710.7388 | dt 9.747 +type train | step 4780 | loss 95.7924 202.0724 313.3601 509.5792 770.6938 1129.0336 1594.7415 2274.9902 3175.5779 4782.0127 7749.1602 13565.1211 | lr 1.0e-04 | norm 4457.0459 | dt 9.766 +type train | step 4781 | loss 92.1122 198.3349 308.8846 497.3713 756.1154 1095.6696 1560.9242 2245.6638 3155.0051 4775.6416 7816.8018 13762.9072 | lr 1.0e-04 | norm 4794.0449 | dt 9.758 +type train | step 4782 | loss 93.3054 196.3099 302.4300 488.7986 743.3188 1066.4448 1515.4636 2173.7490 3058.6628 4662.3672 7612.1553 13309.9561 | lr 1.0e-04 | norm 4210.8706 | dt 9.763 +type train | step 4783 | loss 113.3147 236.1398 346.0546 548.9409 820.9571 1213.8306 1735.8833 2483.9102 3379.8323 5074.3647 8178.6455 14498.1367 | lr 1.0e-04 | norm 6751.6035 | dt 9.752 +type train | step 4784 | loss 89.5089 189.5073 296.3066 482.7826 742.4893 1074.3445 1533.8236 2201.2476 3119.1987 4749.1372 7686.1211 13470.8584 | lr 1.0e-04 | norm 4196.2490 | dt 9.768 +type train | step 4785 | loss 97.8461 210.2620 320.5763 508.2650 764.3874 1099.8173 1547.3079 2190.2637 3060.0220 4621.8418 7533.2490 13282.6426 | lr 1.0e-04 | norm 3923.1067 | dt 9.766 +type train | step 4786 | loss 101.8471 219.4668 335.3640 531.2943 794.2205 1137.2323 1589.4482 2243.3716 3133.1106 4675.5952 7593.0674 13301.5596 | lr 1.0e-04 | norm 3676.2915 | dt 9.769 +type train | step 4787 | loss 93.8801 201.6794 315.2075 505.1005 760.0179 1091.9373 1532.4424 2162.7109 3040.9167 4573.7856 7440.4653 12983.3174 | lr 1.0e-04 | norm 3337.4517 | dt 9.773 +type train | step 4788 | loss 108.9192 234.4245 354.0435 565.1462 827.1298 1185.9955 1644.3455 2302.8198 3115.5137 4632.6880 7492.4419 13142.2217 | lr 1.0e-04 | norm 4678.1904 | dt 9.752 +type train | step 4789 | loss 102.6289 222.9793 338.0391 535.4271 802.7085 1164.6046 1631.4226 2306.0378 3171.3940 4730.6050 7683.4419 13448.0146 | lr 1.0e-04 | norm 5440.4097 | dt 9.773 +type train | step 4790 | loss 94.1249 199.0282 311.0939 501.2964 755.6664 1090.2004 1542.3379 2192.9600 3082.7363 4654.4888 7598.2334 13343.1367 | lr 1.0e-04 | norm 3290.1318 | dt 9.768 +type train | step 4791 | loss 103.8229 219.1006 335.0584 530.8295 786.1879 1127.4908 1575.0801 2223.6021 3067.7495 4594.6050 7452.3716 13241.3496 | lr 1.0e-04 | norm 4688.3936 | dt 9.754 +type train | step 4792 | loss 104.1686 225.5872 344.7252 546.8430 811.0302 1146.7771 1597.6656 2235.9114 3095.4448 4632.2246 7523.7993 13236.3721 | lr 1.0e-04 | norm 3538.3845 | dt 9.765 +type train | step 4793 | loss 102.6213 219.6968 334.8286 534.1248 797.3812 1146.4259 1607.0902 2284.5320 3178.0835 4797.8765 7773.0566 13678.5547 | lr 1.0e-04 | norm 3822.3372 | dt 9.751 +type train | step 4794 | loss 97.5118 207.6655 321.4952 513.6232 773.0522 1112.1860 1568.0946 2234.7749 3122.8757 4700.4546 7654.2969 13464.8867 | lr 1.0e-04 | norm 3948.1638 | dt 9.763 +type train | step 4795 | loss 99.9984 210.9139 324.9655 515.5660 769.8543 1100.2839 1555.5619 2201.7275 3106.6262 4689.7285 7653.4092 13427.9971 | lr 1.0e-04 | norm 3585.6865 | dt 10.601 +type train | step 4796 | loss 96.1808 202.5710 315.3186 507.2228 768.5759 1114.5389 1585.6519 2273.8699 3207.1653 4832.4199 7817.5068 13725.9746 | lr 1.0e-04 | norm 3871.5591 | dt 9.761 +type train | step 4797 | loss 89.9081 188.9161 294.6611 480.3103 730.2778 1056.3556 1503.6351 2153.5989 3062.0459 4637.6919 7519.4790 13181.3691 | lr 1.0e-04 | norm 4144.8506 | dt 9.762 +type train | step 4798 | loss 104.0819 225.7727 342.8318 540.7619 803.1259 1140.8938 1593.5431 2244.8386 3121.0925 4695.1562 7636.3604 13471.3613 | lr 1.0e-04 | norm 3731.9358 | dt 9.757 +type train | step 4799 | loss 100.3344 215.9863 331.9738 526.9275 786.4737 1127.1840 1581.4836 2235.5869 3117.5391 4688.4517 7593.2915 13298.7002 | lr 1.0e-04 | norm 3481.7688 | dt 9.765 +type train | step 4800 | loss 113.8813 242.4313 361.9857 556.5613 812.1377 1136.2262 1565.1791 2167.7642 2983.6311 4482.0698 7257.1445 12848.6064 | lr 1.0e-04 | norm 6956.8545 | dt 9.757 +type train | step 4801 | loss 105.1729 222.8513 342.3144 545.4736 813.3936 1168.5139 1646.4500 2336.6792 3247.1777 4892.0991 7928.6885 13840.1318 | lr 1.0e-04 | norm 4174.5229 | dt 9.768 +type train | step 4802 | loss 102.7221 217.9330 334.2894 530.7161 784.3799 1123.5981 1568.7891 2200.2102 3023.8281 4518.2490 7357.2769 12960.1504 | lr 1.0e-04 | norm 3903.1311 | dt 9.762 +type train | step 4803 | loss 95.2235 202.1435 314.5109 500.7127 752.1542 1073.1166 1505.9314 2124.6704 2986.4998 4489.4956 7268.9805 12715.5283 | lr 1.0e-04 | norm 2944.7422 | dt 9.775 +type train | step 4804 | loss 91.9238 195.4908 301.6737 481.9270 728.6638 1051.0996 1481.7241 2112.9761 2987.6819 4503.2344 7296.8354 12723.4141 | lr 1.0e-04 | norm 3185.4822 | dt 9.771 +type train | step 4805 | loss 95.5157 202.0411 307.2452 487.5291 733.9081 1058.2418 1502.9858 2135.1426 3034.9238 4519.5708 7211.3833 12402.2100 | lr 1.0e-04 | norm 5258.5498 | dt 9.758 +type train | step 4806 | loss 96.0986 206.4327 323.4295 520.9173 786.8378 1131.5952 1594.4048 2263.0098 3190.7305 4811.5015 7795.3604 13723.4043 | lr 1.0e-04 | norm 3464.8015 | dt 9.768 +type train | step 4807 | loss 111.4956 236.0100 354.4790 558.2302 811.1014 1160.0077 1595.1658 2247.8462 3056.3010 4548.7739 7321.3594 12969.3994 | lr 1.0e-04 | norm 5540.3569 | dt 9.732 +type train | step 4808 | loss 96.2321 206.2796 319.1849 506.9745 766.5159 1100.8057 1553.4135 2215.6543 3112.1118 4686.5483 7614.2539 13373.6387 | lr 1.0e-04 | norm 3571.5876 | dt 9.771 +type train | step 4809 | loss 96.8253 205.4811 317.0838 505.1125 761.1897 1087.3787 1537.5809 2177.2317 3079.4653 4630.2808 7479.9858 13140.2012 | lr 1.0e-04 | norm 3256.5720 | dt 9.771 +type train | step 4810 | loss 109.9163 234.9802 359.4573 569.0061 842.0105 1192.5542 1658.4509 2320.0527 3178.8101 4743.4282 7682.8447 13542.1934 | lr 1.0e-04 | norm 5110.5615 | dt 9.760 +type train | step 4811 | loss 102.6208 218.8465 334.5286 531.0331 793.7750 1128.0424 1579.5742 2219.2957 3065.7444 4579.1484 7374.1602 12878.4834 | lr 1.0e-04 | norm 3543.8484 | dt 9.771 +type train | step 4812 | loss 100.9441 219.1951 337.8305 537.4649 802.7971 1141.9513 1601.6046 2246.8530 3138.1326 4707.2671 7652.6626 13438.7285 | lr 1.0e-04 | norm 4011.0208 | dt 9.762 +type train | step 4813 | loss 92.6151 197.9273 310.9031 503.5857 761.2202 1096.1981 1555.7495 2212.2554 3129.1072 4737.4863 7724.2588 13659.5400 | lr 1.0e-04 | norm 4561.9648 | dt 9.765 +type train | step 4814 | loss 98.7129 214.8554 335.7604 541.8184 815.0690 1155.3864 1626.9595 2289.0654 3210.5857 4836.7466 7872.2490 13897.5312 | lr 1.0e-04 | norm 4073.8525 | dt 9.766 +type train | step 4815 | loss 103.1128 226.0388 348.4572 558.5708 826.6131 1192.1251 1679.0588 2394.2810 3303.1541 4955.4424 8276.8760 14829.3066 | lr 1.0e-04 | norm 9085.1318 | dt 9.743 +type train | step 4816 | loss 133.6613 287.1860 415.4806 652.5137 939.1049 1344.4189 1881.8688 2664.3933 3512.0176 5248.1836 8759.4453 16110.9111 | lr 1.0e-04 | norm 17559.7910 | dt 9.737 +type train | step 4817 | loss 98.9937 212.1887 323.8636 518.6777 779.9110 1113.9021 1568.4648 2220.7026 3095.7542 4685.1167 7595.0342 13357.9336 | lr 1.0e-04 | norm 3863.1819 | dt 9.755 +type train | step 4818 | loss 103.4167 218.3719 340.4351 534.7901 785.1227 1111.1899 1545.6451 2161.7188 3003.6299 4503.8242 7258.4639 12837.5137 | lr 1.0e-04 | norm 5075.0132 | dt 9.744 +type train | step 4819 | loss 94.7618 202.3694 313.8785 501.4883 759.5588 1080.0867 1523.0675 2155.2256 3036.7651 4577.8848 7427.2725 12917.8838 | lr 1.0e-04 | norm 4089.0950 | dt 9.767 +type train | step 4820 | loss 97.5053 207.5334 319.9608 510.2925 764.4467 1096.3885 1541.2269 2183.5046 3074.7837 4649.0981 7571.9795 13307.5449 | lr 1.0e-04 | norm 3718.4873 | dt 9.766 +type train | step 4821 | loss 98.8542 208.7299 321.8071 509.8924 766.1292 1102.6901 1549.9938 2202.4316 3063.9656 4649.4033 7589.6514 13492.9941 | lr 1.0e-04 | norm 5601.0864 | dt 9.754 +type train | step 4822 | loss 87.6532 184.8060 289.0483 470.2201 716.9908 1042.0989 1490.0026 2122.7197 2982.4961 4524.2383 7357.1567 13122.7900 | lr 1.0e-04 | norm 6159.7520 | dt 9.755 +type train | step 4823 | loss 97.9515 207.3141 319.7346 506.4406 765.0977 1106.3525 1562.8315 2239.9375 3127.8623 4752.4927 7779.4087 13804.9277 | lr 1.0e-04 | norm 4485.9126 | dt 9.763 +type train | step 4824 | loss 101.9648 218.8489 336.5963 535.4758 798.5195 1134.1594 1586.5178 2226.1738 3084.3967 4628.7378 7539.8706 13334.8311 | lr 1.0e-04 | norm 4592.6484 | dt 9.757 +type train | step 4825 | loss 96.2549 203.2641 315.8480 502.1893 756.1503 1089.6665 1537.2744 2186.8894 3067.9446 4616.4907 7515.0420 13241.9541 | lr 1.0e-04 | norm 3710.2573 | dt 9.771 +type train | step 4826 | loss 97.8175 207.9637 318.1149 510.7925 772.9312 1132.4847 1603.2557 2311.8608 3210.1228 4853.0479 7932.8057 14050.5332 | lr 1.0e-04 | norm 4735.1206 | dt 9.744 +type train | step 4827 | loss 95.4247 202.8894 313.3246 504.2376 762.0779 1101.7505 1560.7982 2239.0684 3133.1797 4721.4883 7646.6924 13383.6240 | lr 1.0e-04 | norm 3945.9172 | dt 9.765 +type train | step 4828 | loss 89.6245 189.5201 297.8125 482.2763 735.0755 1065.6490 1512.3424 2163.3167 3038.0688 4597.5298 7488.6025 13309.7695 | lr 1.0e-04 | norm 5331.1108 | dt 9.754 +type train | step 4829 | loss 98.2735 207.7198 324.4000 515.3820 771.7926 1103.1665 1547.2753 2185.7161 3056.1851 4594.2656 7442.2241 13064.9238 | lr 1.0e-04 | norm 3804.3931 | dt 9.766 +type train | step 4830 | loss 98.6766 209.0804 324.1430 519.4737 770.3015 1119.4138 1574.3451 2228.6418 3120.1150 4691.7300 7635.7500 13537.7441 | lr 1.0e-04 | norm 4277.1636 | dt 9.750 +type train | step 4831 | loss 95.7700 203.2954 313.7209 502.7572 755.3549 1090.9844 1538.3647 2193.0969 3072.1296 4627.6270 7477.9990 13051.5215 | lr 1.0e-04 | norm 3084.4150 | dt 9.774 +type train | step 4832 | loss 102.9360 215.5496 330.3405 526.8452 788.9600 1134.1414 1598.1790 2273.7747 3164.4111 4745.9688 7669.9780 13468.9893 | lr 1.0e-04 | norm 4386.9224 | dt 9.770 +type train | step 4833 | loss 97.7231 209.3946 321.0740 512.4424 768.7884 1108.8552 1562.3271 2226.5393 3117.8926 4690.8867 7593.7222 13364.7324 | lr 1.0e-04 | norm 3428.9290 | dt 9.767 +type train | step 4834 | loss 95.6779 202.5761 315.6764 505.9268 759.6791 1093.6344 1538.7651 2187.0732 3057.3196 4596.8955 7471.0835 13042.1084 | lr 1.0e-04 | norm 3103.3113 | dt 9.763 +type train | step 4835 | loss 93.5022 201.0009 312.5432 503.1800 760.2560 1093.6067 1550.1558 2210.3042 3113.9678 4714.0234 7685.3301 13514.7246 | lr 1.0e-04 | norm 3585.1890 | dt 9.782 +type train | step 4836 | loss 94.0409 197.4944 307.3403 495.5551 749.4933 1092.6125 1546.3384 2215.0522 3112.6589 4715.2158 7719.1904 13593.0586 | lr 1.0e-04 | norm 3702.9661 | dt 9.774 +type train | step 4837 | loss 102.7233 221.0172 334.9063 528.9531 789.0483 1125.8225 1586.9929 2236.0967 3101.8770 4639.6265 7529.3247 13305.2842 | lr 1.0e-04 | norm 3829.0464 | dt 9.774 +type train | step 4838 | loss 98.3725 210.9789 323.2920 511.0980 771.5031 1122.5144 1582.3591 2257.8921 3145.1350 4684.1792 7521.4897 13060.0625 | lr 1.0e-04 | norm 4122.1196 | dt 9.756 +type train | step 4839 | loss 94.1196 203.3398 312.9147 491.5532 742.3159 1064.7887 1533.4423 2196.1558 3094.1182 4648.0542 7498.4541 13236.4102 | lr 1.0e-04 | norm 8424.9062 | dt 9.767 +type train | step 4840 | loss 98.9991 210.8994 322.6356 517.3738 775.9854 1112.0769 1569.7179 2229.9990 3120.1650 4678.9766 7594.8589 13343.8711 | lr 1.0e-04 | norm 4371.8472 | dt 9.761 +type train | step 4841 | loss 91.7893 195.2819 303.3442 492.1096 750.1267 1085.0928 1543.0913 2207.0955 3104.5278 4677.3916 7596.2983 13216.4795 | lr 1.0e-04 | norm 3916.1692 | dt 9.757 +type train | step 4842 | loss 97.1443 206.8216 315.4326 501.9374 754.0317 1089.8259 1537.1115 2190.7620 3060.4365 4568.3203 7400.7173 12911.4004 | lr 1.0e-04 | norm 3442.4678 | dt 9.772 +type train | step 4843 | loss 106.0453 225.5845 338.5150 533.9159 799.8105 1179.3838 1670.3351 2424.9116 3339.8721 4958.8154 7870.5625 13725.2490 | lr 1.0e-04 | norm 4790.4922 | dt 9.738 +type train | step 4844 | loss 103.2617 216.8426 331.5594 522.0057 776.4175 1123.8286 1573.8541 2226.6938 3052.2427 4518.7285 7268.1299 12816.8613 | lr 1.0e-04 | norm 4328.2329 | dt 9.738 +type train | step 4845 | loss 102.8250 218.3946 331.7694 522.2240 779.8532 1120.9537 1580.9208 2242.1270 3122.9626 4702.6152 7602.4546 13457.8926 | lr 1.0e-04 | norm 4963.5620 | dt 9.768 +type train | step 4846 | loss 107.2215 225.9683 343.3666 537.2296 792.5133 1135.3412 1584.4675 2219.2837 3035.3179 4522.0327 7280.5742 12902.6064 | lr 1.0e-04 | norm 4648.9668 | dt 9.751 +type train | step 4847 | loss 98.5473 209.0728 319.1361 509.0921 765.2979 1099.5198 1550.8280 2207.8418 3103.0337 4685.4043 7622.7964 13378.0781 | lr 1.0e-04 | norm 3422.7932 | dt 9.766 +type train | step 4848 | loss 97.9870 210.6430 321.6053 513.5437 766.5519 1098.7697 1544.5133 2197.5728 3095.6687 4674.8320 7617.3286 13374.1895 | lr 1.0e-04 | norm 3483.7988 | dt 9.765 +type train | step 4849 | loss 107.1194 230.9008 347.8795 551.5402 823.9769 1182.6921 1656.0520 2351.4651 3263.8318 4884.2148 7903.0752 13915.8145 | lr 1.0e-04 | norm 3873.1436 | dt 9.760 +type train | step 4850 | loss 97.7118 211.0188 323.6314 514.2456 771.7205 1113.6559 1577.0785 2234.7800 3146.9658 4720.5713 7634.4131 13435.2549 | lr 1.0e-04 | norm 5465.5220 | dt 9.762 +type train | step 4851 | loss 101.5546 217.0253 330.4983 515.0819 770.3027 1103.2997 1548.0715 2184.0903 3039.4382 4557.9902 7394.8784 13024.2217 | lr 1.0e-04 | norm 3473.6274 | dt 9.775 +type train | step 4852 | loss 102.6168 217.8416 333.3260 529.9271 788.0418 1137.8569 1594.8690 2253.2271 3157.4927 4741.1846 7664.9658 13467.3516 | lr 1.0e-04 | norm 4362.0820 | dt 9.773 +type train | step 4853 | loss 93.3513 203.3568 316.8185 506.5424 764.0396 1102.2091 1555.9684 2215.3457 3102.5400 4696.9751 7641.1895 13439.0918 | lr 1.0e-04 | norm 3946.4214 | dt 9.771 +type train | step 4854 | loss 96.9748 206.2409 317.9408 500.9539 751.9518 1083.9570 1524.5354 2163.5154 3027.6250 4555.7065 7402.0967 13034.0996 | lr 1.0e-04 | norm 5105.6636 | dt 9.766 +type train | step 4855 | loss 96.9435 205.5166 315.7396 509.3424 762.3635 1095.9482 1540.9358 2180.0911 3054.2041 4580.5449 7451.4253 13094.5420 | lr 1.0e-04 | norm 3299.3552 | dt 9.768 +type train | step 4856 | loss 94.3753 199.0657 306.5625 491.3909 743.8788 1070.0970 1509.2971 2150.1460 3032.3225 4605.4014 7528.1230 13283.8984 | lr 1.0e-04 | norm 3709.6340 | dt 9.750 +type train | step 4857 | loss 100.2830 215.3638 332.9552 531.8632 791.5646 1133.0398 1584.1814 2235.0122 3120.9690 4688.8750 7627.4844 13420.1992 | lr 1.0e-04 | norm 3406.9575 | dt 9.777 +type train | step 4858 | loss 96.8942 202.8511 314.3972 504.0711 760.9228 1098.7469 1535.8936 2186.8120 3065.0615 4594.5845 7470.1655 13096.2861 | lr 1.0e-04 | norm 3083.0061 | dt 9.769 +type train | step 4859 | loss 96.3650 206.0206 316.1617 503.8828 756.1119 1082.8334 1527.4722 2176.5847 3061.9692 4643.2876 7525.9414 13187.5547 | lr 1.0e-04 | norm 3531.3137 | dt 9.764 +type train | step 4860 | loss 92.5050 198.0173 303.6202 488.9768 741.6143 1075.2789 1530.4226 2184.1523 3071.0632 4682.7607 7691.1123 13686.3965 | lr 1.0e-04 | norm 4233.7256 | dt 9.766 +type train | step 4861 | loss 100.9495 216.6460 331.7462 521.6636 775.8318 1121.7843 1580.2689 2234.6392 3100.7727 4644.4946 7606.8042 13422.6426 | lr 1.0e-04 | norm 3803.2727 | dt 9.765 +type train | step 4862 | loss 94.0967 201.5793 310.7613 497.0644 746.4568 1075.0050 1513.9539 2155.3213 3018.7932 4535.5439 7368.8540 12884.2637 | lr 1.0e-04 | norm 3311.0176 | dt 9.771 +type train | step 4863 | loss 100.0837 215.8548 329.4897 523.4620 785.1910 1119.6300 1576.9510 2221.4873 3100.3784 4628.7192 7511.3354 13205.4863 | lr 1.0e-04 | norm 4439.4819 | dt 9.772 +type train | step 4864 | loss 98.0899 208.7972 320.5311 511.0168 764.1392 1094.7168 1541.1904 2178.8354 3063.5864 4609.3081 7455.2397 13061.4521 | lr 1.0e-04 | norm 3501.5198 | dt 9.774 +type train | step 4865 | loss 89.6373 187.0267 291.2863 472.4393 720.1909 1039.8711 1479.3285 2115.9526 2991.3672 4534.4170 7384.0962 12908.8389 | lr 1.0e-04 | norm 3343.7715 | dt 9.780 +type train | step 4866 | loss 94.0815 200.0645 309.5700 497.2665 751.4457 1084.0785 1537.6655 2180.6606 3048.8828 4573.4126 7407.0381 12943.7090 | lr 1.0e-04 | norm 3369.3369 | dt 9.776 +type train | step 4867 | loss 107.4809 234.1401 352.7897 557.9291 824.0074 1181.1787 1643.8586 2310.6201 3184.0872 4768.5654 7737.6191 13584.0918 | lr 1.0e-04 | norm 3993.2168 | dt 9.767 +type train | step 4868 | loss 100.1722 212.1608 325.5875 517.8558 774.5280 1106.5323 1551.5789 2183.0132 3034.4526 4548.2061 7362.4692 13012.3672 | lr 1.0e-04 | norm 4811.3110 | dt 9.759 +type train | step 4869 | loss 94.0461 203.3568 315.2173 506.1096 763.1118 1098.9399 1549.0281 2208.4333 3105.6582 4689.2822 7626.1401 13345.1543 | lr 1.0e-04 | norm 3428.3098 | dt 9.774 +type train | step 4870 | loss 103.4564 221.3521 336.7496 531.0557 792.4368 1134.7239 1598.1091 2256.9260 3117.8760 4688.3867 7573.0547 13366.9180 | lr 1.0e-04 | norm 4004.9080 | dt 9.769 +type train | step 4871 | loss 96.2712 205.6116 317.2615 508.4126 762.8500 1107.5048 1567.4479 2240.8733 3133.4480 4722.6338 7706.0166 13528.9043 | lr 1.0e-04 | norm 3919.2625 | dt 9.755 +type train | step 4872 | loss 96.9126 205.2221 319.4626 524.1062 789.9493 1138.7897 1615.0569 2308.0376 3214.9883 4809.9902 7837.5410 13775.4277 | lr 1.0e-04 | norm 7482.7793 | dt 9.759 +type train | step 4873 | loss 94.7355 203.1220 311.8854 494.8883 748.3915 1071.9453 1518.4218 2162.8196 3030.0898 4589.5449 7472.1772 13213.6699 | lr 1.0e-04 | norm 3905.2832 | dt 9.750 +type train | step 4874 | loss 166.4087 375.2602 498.9788 743.5493 1069.1824 1612.9502 2289.5339 3091.6138 4089.3127 5696.3276 8528.8877 14664.3672 | lr 1.0e-04 | norm 7354.4624 | dt 9.719 +type train | step 4875 | loss 95.2956 202.9859 311.8947 499.8555 749.9307 1073.7168 1508.7771 2136.6260 3006.7063 4534.8584 7371.0195 12869.6865 | lr 1.0e-04 | norm 3152.0618 | dt 9.764 +type train | step 4876 | loss 93.0831 199.9929 311.5747 503.3411 761.0754 1096.3533 1549.9943 2201.8555 3108.1650 4724.6646 7733.8647 13594.3975 | lr 1.0e-04 | norm 3250.5725 | dt 9.771 +type train | step 4877 | loss 93.6482 197.6872 307.7609 490.1461 741.9096 1070.1853 1512.6650 2154.1929 3033.2219 4573.8882 7462.8643 13029.0518 | lr 1.0e-04 | norm 3206.9702 | dt 9.779 +type train | step 4878 | loss 92.5935 193.9877 304.5356 489.1828 742.7393 1064.9512 1506.2003 2135.8464 3004.5740 4516.6562 7348.5156 12805.9453 | lr 1.0e-04 | norm 3279.6731 | dt 9.775 +type train | step 4879 | loss 97.0642 203.2367 311.4185 502.6130 756.7905 1091.5725 1546.3788 2193.7988 3078.6094 4655.0557 7571.6802 13204.9766 | lr 1.0e-04 | norm 3378.9924 | dt 9.769 +type train | step 4880 | loss 95.2022 201.7263 311.1841 498.8021 753.2419 1076.3157 1515.2489 2152.7734 3021.5935 4566.4814 7430.0991 12984.9980 | lr 1.0e-04 | norm 2968.4590 | dt 9.766 +type train | step 4881 | loss 92.8772 196.5923 302.7807 484.6301 732.7822 1055.4526 1488.3281 2115.5662 2957.6602 4463.1055 7279.6909 12736.6396 | lr 1.0e-04 | norm 3548.9346 | dt 9.766 +type train | step 4882 | loss 91.0536 194.5081 300.4217 483.1028 734.7314 1056.5653 1511.0059 2162.0381 3071.3542 4628.6392 7488.4971 13035.3896 | lr 1.0e-04 | norm 4344.1670 | dt 9.776 +type train | step 4883 | loss 95.2270 202.7175 311.6028 497.8542 754.5662 1086.4882 1537.4680 2184.3562 3088.2605 4661.8604 7564.6250 13228.8701 | lr 1.0e-04 | norm 3372.0913 | dt 9.761 +type train | step 4884 | loss 106.4253 225.7945 344.3618 547.0242 810.8759 1172.0887 1647.3920 2331.2642 3204.3718 4790.2734 7815.3594 13816.5283 | lr 1.0e-04 | norm 5132.7119 | dt 9.759 +type train | step 4885 | loss 96.2068 204.5466 316.1791 508.5108 769.0089 1109.1826 1573.6860 2251.6704 3166.2048 4772.7949 7771.3950 13719.0000 | lr 1.0e-04 | norm 3877.2229 | dt 9.781 +type train | step 4886 | loss 92.3319 193.7005 302.8346 488.4908 739.3910 1062.7188 1503.2794 2137.3181 3002.3726 4544.3779 7383.9561 13022.9727 | lr 1.0e-04 | norm 3427.0811 | dt 9.770 +type train | step 4887 | loss 98.2539 208.1191 321.5350 512.2230 774.4055 1118.5618 1574.4930 2258.6824 3153.0137 4724.1704 7589.9326 13256.5811 | lr 1.0e-04 | norm 5852.0781 | dt 9.742 +type train | step 4888 | loss 90.5204 191.7504 300.7351 486.3367 740.1403 1069.8074 1521.1245 2170.1191 3059.0674 4605.2520 7471.9272 13017.8633 | lr 1.0e-04 | norm 3203.6450 | dt 9.770 +type train | step 4889 | loss 95.0349 201.6775 314.3686 504.6956 760.0939 1093.1504 1545.4512 2203.9360 3091.2905 4707.7021 7673.0186 13483.8486 | lr 1.0e-04 | norm 3712.1843 | dt 9.769 +type train | step 4890 | loss 92.6954 197.1620 303.0527 484.5880 730.4482 1053.5137 1498.0604 2153.0449 3045.2522 4623.6694 7518.9072 13085.9141 | lr 1.0e-04 | norm 3625.4180 | dt 9.772 +type train | step 4891 | loss 98.5946 211.9597 325.6005 517.5275 773.1096 1105.5603 1553.5863 2191.9131 3061.6714 4589.8452 7461.1689 13125.5625 | lr 1.0e-04 | norm 3350.1453 | dt 9.772 +type train | step 4892 | loss 109.1947 232.2496 352.5612 552.4327 811.5476 1155.2062 1611.4421 2256.4124 3118.6125 4662.2383 7485.7407 13028.7070 | lr 1.0e-04 | norm 3331.0786 | dt 9.768 +type train | step 4893 | loss 99.9243 212.3167 323.5728 519.0858 771.3445 1113.3948 1563.0464 2203.8828 3063.1685 4595.8843 7430.2886 13025.5742 | lr 1.0e-04 | norm 3755.3726 | dt 9.754 +type train | step 4894 | loss 98.5922 213.4862 326.8341 517.5023 779.0823 1113.6687 1572.2534 2234.4541 3143.2854 4743.4102 7623.5000 13170.8770 | lr 1.0e-04 | norm 5668.5015 | dt 9.770 +type train | step 4895 | loss 101.3858 215.4467 329.6245 518.3430 765.7933 1093.1996 1517.7059 2140.2097 2936.5210 4388.0962 7053.9897 12474.6338 | lr 1.0e-04 | norm 7185.7412 | dt 9.734 +type train | step 4896 | loss 102.3232 219.5952 339.4284 548.2597 822.3354 1180.8617 1646.8884 2329.2310 3205.7451 4770.0527 7655.0186 13479.9541 | lr 1.0e-04 | norm 6012.4673 | dt 9.740 +type train | step 4897 | loss 95.1239 202.5547 310.3584 494.5929 742.9778 1067.6853 1504.9185 2130.9692 2992.9668 4504.1240 7268.5444 12676.8877 | lr 1.0e-04 | norm 3232.5828 | dt 9.760 +type train | step 4898 | loss 92.7789 195.0851 302.7970 490.4901 746.2892 1079.0508 1531.6747 2189.0269 3082.9490 4652.2007 7565.7012 13303.3525 | lr 1.0e-04 | norm 3579.9387 | dt 9.763 +type train | step 4899 | loss 93.2941 197.1064 305.7776 491.0360 745.9857 1079.1273 1527.9691 2185.0305 3064.2683 4624.1372 7486.2817 13170.3770 | lr 1.0e-04 | norm 4081.2227 | dt 9.760 +type train | step 4900 | loss 95.8748 200.4735 312.5767 505.0299 766.1317 1106.4100 1564.8246 2233.7715 3113.0425 4669.2148 7568.2324 13287.2422 | lr 1.0e-04 | norm 4110.4116 | dt 9.744 +type train | step 4901 | loss 97.9477 209.6262 324.3496 520.4363 779.9393 1123.9661 1598.0450 2278.5747 3194.0344 4840.9150 7925.8931 14017.9346 | lr 1.0e-04 | norm 4425.1255 | dt 9.778 +type train | step 4902 | loss 105.1477 229.6193 346.9561 544.0612 819.4833 1189.9834 1671.6055 2384.4141 3261.9709 4847.1460 7790.6772 13597.7051 | lr 1.0e-04 | norm 4235.3286 | dt 9.752 +type train | step 4903 | loss 98.8966 209.7822 324.4228 516.3281 780.0370 1137.8398 1589.8767 2252.7622 3086.2483 4560.9717 7314.7690 12839.4346 | lr 1.0e-04 | norm 4770.8853 | dt 9.742 +type train | step 4904 | loss 92.5621 198.5873 317.7538 522.1885 786.8063 1133.7003 1599.9912 2272.6729 3207.5220 4858.6816 7894.5176 13750.7148 | lr 1.0e-04 | norm 6337.6919 | dt 9.751 +type train | step 4905 | loss 98.3152 209.6324 324.4001 514.1680 766.4923 1096.9846 1537.0046 2179.7827 3047.5195 4593.6777 7500.7217 13193.9873 | lr 1.0e-04 | norm 3674.3557 | dt 9.752 +type train | step 4906 | loss 97.1571 206.8818 317.4921 504.6027 752.9054 1079.3628 1525.4888 2179.6956 3047.2476 4597.3198 7498.6958 13217.7295 | lr 1.0e-04 | norm 4012.1677 | dt 9.770 +type train | step 4907 | loss 102.2791 219.6892 330.5581 520.1125 774.8320 1109.0564 1556.8066 2202.9905 3074.1726 4648.6475 7626.1118 13403.2051 | lr 1.0e-04 | norm 4173.0327 | dt 9.755 +type train | step 4908 | loss 98.6535 208.5439 324.0193 520.6154 782.7650 1120.3906 1582.3579 2244.4189 3174.9697 4799.6772 7793.2256 13626.8926 | lr 1.0e-04 | norm 3844.4038 | dt 9.760 +type train | step 4909 | loss 102.8191 220.9497 332.9383 529.9258 782.2564 1120.3132 1571.1038 2221.3596 3092.2068 4658.4551 7615.5732 13423.6631 | lr 1.0e-04 | norm 4322.5068 | dt 9.771 +type train | step 4910 | loss 97.3435 210.1675 321.2980 512.1843 765.3008 1105.8535 1575.6597 2242.2852 3128.0190 4708.1743 7715.3403 13648.2305 | lr 1.0e-04 | norm 4638.8794 | dt 9.762 +type train | step 4911 | loss 100.0147 212.5594 326.9327 518.6223 774.6262 1112.0408 1564.4115 2210.0144 3102.5142 4663.9819 7527.6104 13074.2461 | lr 1.0e-04 | norm 3468.9343 | dt 9.772 +type train | step 4912 | loss 94.2466 199.9665 310.8803 501.2538 760.3912 1092.3749 1544.9282 2204.3833 3126.4768 4710.3638 7599.3315 13290.4609 | lr 1.0e-04 | norm 3570.6631 | dt 9.774 +type train | step 4913 | loss 101.8401 217.6984 330.5210 519.6970 779.4916 1110.4043 1566.6284 2211.7686 3106.3213 4654.9907 7527.7148 13194.9326 | lr 1.0e-04 | norm 4000.9072 | dt 9.773 +type train | step 4914 | loss 94.0174 199.8804 310.4837 495.7682 746.3286 1076.4243 1521.3584 2172.6636 3048.7903 4596.9346 7442.2002 12992.3613 | lr 1.0e-04 | norm 3275.2698 | dt 9.759 +type train | step 4915 | loss 94.7981 203.1315 312.8314 498.9770 750.1697 1080.8436 1524.9768 2164.1577 3038.6448 4600.0073 7507.8428 13173.5439 | lr 1.0e-04 | norm 3432.4241 | dt 9.765 +type train | step 4916 | loss 97.5880 207.9395 319.3230 508.2614 761.0902 1098.0083 1543.6493 2186.0139 3053.1111 4568.1089 7385.7007 12900.5293 | lr 1.0e-04 | norm 3341.5999 | dt 9.758 +type train | step 4917 | loss 100.2847 214.1150 328.1656 525.1423 781.5498 1131.9478 1600.3296 2270.7212 3150.5405 4740.8228 7690.5366 13691.2803 | lr 1.0e-04 | norm 4197.4927 | dt 9.761 +type train | step 4918 | loss 100.4979 213.3752 325.0124 517.6257 774.9133 1112.4534 1572.6316 2234.5383 3144.1890 4724.2568 7620.3467 13251.2490 | lr 1.0e-04 | norm 3685.7573 | dt 9.761 +type train | step 4919 | loss 97.1004 206.7519 318.9428 505.1884 760.0135 1098.1044 1546.9772 2204.1621 3089.8757 4698.3901 7663.9761 13445.4336 | lr 1.0e-04 | norm 4275.3647 | dt 9.751 +type train | step 4920 | loss 96.5977 202.4143 310.3593 493.6436 747.2590 1076.9235 1527.9381 2192.1719 3066.7034 4601.2417 7400.0728 12936.6738 | lr 1.0e-04 | norm 4501.2183 | dt 9.767 +type train | step 4921 | loss 96.7217 207.7524 321.6186 510.2976 765.6765 1104.2671 1562.1050 2222.2449 3112.3354 4679.9072 7610.8770 13363.6348 | lr 1.0e-04 | norm 3745.1509 | dt 9.776 +type train | step 4922 | loss 97.5737 206.6621 320.8033 512.5934 768.7810 1098.2612 1549.3983 2190.4102 3067.9768 4606.7754 7473.8784 13118.9863 | lr 1.0e-04 | norm 3128.8865 | dt 9.765 +type train | step 4923 | loss 92.0324 193.8002 303.3356 484.8670 736.8217 1062.5242 1506.8673 2139.7524 3015.5137 4549.4575 7387.0684 12933.2900 | lr 1.0e-04 | norm 3697.8237 | dt 9.765 +type train | step 4924 | loss 95.2157 203.4610 314.0223 504.0950 759.0413 1097.4855 1560.0746 2231.2415 3136.3848 4763.3252 7746.9287 13627.3936 | lr 1.0e-04 | norm 3525.8088 | dt 9.756 +type train | step 4925 | loss 99.7518 212.3545 325.5080 515.8312 771.5042 1108.4160 1551.4304 2209.0403 3056.4951 4593.2681 7500.3242 13370.0840 | lr 1.0e-04 | norm 5261.9297 | dt 9.764 +type train | step 4926 | loss 98.3256 209.0574 324.0615 516.2080 775.1160 1123.3782 1583.8552 2249.6428 3137.5581 4710.1328 7646.6646 13502.0654 | lr 1.0e-04 | norm 4417.7412 | dt 9.752 +type train | step 4927 | loss 103.4056 219.5571 332.9708 527.0590 781.8783 1122.3639 1569.7562 2226.3284 3121.2087 4721.2437 7716.8418 13616.3574 | lr 1.0e-04 | norm 4156.2061 | dt 9.750 +type train | step 4928 | loss 93.7992 201.5020 313.5972 502.6768 756.8522 1085.3542 1530.8447 2175.6016 3068.2930 4631.8779 7518.7251 13143.1562 | lr 1.0e-04 | norm 3075.7524 | dt 9.776 +type train | step 4929 | loss 92.9962 196.9571 306.8462 490.7962 737.2275 1062.7528 1498.2458 2130.3030 3008.9355 4547.6777 7395.4541 12887.7695 | lr 1.0e-04 | norm 2969.0676 | dt 9.761 +type train | step 4930 | loss 99.6129 215.2542 326.2621 515.7961 768.5020 1108.4624 1548.2396 2192.3635 3047.0300 4553.6357 7399.8379 12965.1387 | lr 1.0e-04 | norm 4007.0347 | dt 9.765 +type train | step 4931 | loss 91.1892 191.0720 297.1205 480.4619 729.4236 1053.6648 1491.1376 2124.1870 3009.1201 4542.7466 7413.8462 12931.4180 | lr 1.0e-04 | norm 2991.6780 | dt 9.766 +type train | step 4932 | loss 94.5252 201.9659 310.1481 494.7347 747.8835 1090.2656 1544.8667 2208.2949 3099.9976 4684.3462 7595.9531 13350.1426 | lr 1.0e-04 | norm 3663.7539 | dt 9.758 +type train | step 4933 | loss 97.1159 209.2737 321.8147 511.7275 771.4896 1097.9210 1541.8562 2170.4583 3037.9521 4572.1353 7433.5781 13107.4434 | lr 1.0e-04 | norm 4043.7805 | dt 9.775 +type train | step 4934 | loss 96.2633 206.5762 315.7601 507.9680 763.1134 1093.4800 1541.7534 2172.4038 3037.2258 4570.3926 7403.0298 13076.7842 | lr 1.0e-04 | norm 6095.7935 | dt 9.765 +type train | step 4935 | loss 93.2206 196.4346 304.3018 489.8214 740.4488 1067.8838 1518.4835 2172.8955 3079.6665 4671.8691 7613.8765 13415.8867 | lr 1.0e-04 | norm 4004.4966 | dt 9.759 +type train | step 4936 | loss 94.1885 203.2074 315.0228 505.1993 763.2125 1089.5891 1539.7200 2185.3647 3094.9663 4679.9351 7584.9785 13274.4609 | lr 1.0e-04 | norm 3829.0305 | dt 9.758 +type train | step 4937 | loss 91.5695 193.3163 298.0373 481.6786 727.7911 1048.8772 1483.3882 2113.7188 2976.2935 4499.7349 7351.7065 12922.5684 | lr 1.0e-04 | norm 3319.3076 | dt 9.759 +type train | step 4938 | loss 98.9216 216.3249 327.1497 509.1817 767.5527 1097.8489 1558.2097 2216.8232 3111.3306 4710.4790 7615.8604 13251.3174 | lr 1.0e-04 | norm 6195.8110 | dt 9.754 +type train | step 4939 | loss 96.6562 202.5580 314.0531 502.5264 757.6127 1087.6949 1537.3085 2181.4048 3064.6172 4622.9443 7490.5054 13162.2559 | lr 1.0e-04 | norm 3650.0142 | dt 9.763 +type train | step 4940 | loss 100.9965 216.6298 331.3049 526.4324 786.0602 1127.3438 1585.3875 2243.9355 3142.4214 4711.4980 7637.5928 13384.1377 | lr 1.0e-04 | norm 3928.0322 | dt 9.768 +type train | step 4941 | loss 107.3346 236.6863 360.0030 557.7422 827.7311 1202.4691 1680.3289 2372.0022 3243.1182 4828.0723 7804.6650 13681.5391 | lr 1.0e-04 | norm 5373.2607 | dt 9.753 +type train | step 4942 | loss 100.2413 215.0165 329.8918 524.6191 780.3716 1116.9276 1558.9850 2193.0232 3052.3640 4573.6221 7399.7695 12900.5645 | lr 1.0e-04 | norm 3085.0264 | dt 9.760 +type train | step 4943 | loss 96.9203 206.6984 315.7162 505.6366 759.6419 1107.6564 1576.8762 2254.9070 3147.0762 4733.3770 7641.7510 13360.6367 | lr 1.0e-04 | norm 3492.4648 | dt 9.763 +type train | step 4944 | loss 91.3876 191.3851 299.3484 482.1383 730.2304 1063.5040 1519.2439 2162.8086 3030.7192 4598.6221 7405.8535 13022.3633 | lr 1.0e-04 | norm 6018.1738 | dt 9.752 +type train | step 4945 | loss 104.5904 228.3335 342.5677 543.1052 809.5187 1162.2031 1623.1804 2287.7639 3161.0073 4701.1807 7563.4683 13270.7363 | lr 1.0e-04 | norm 4216.0210 | dt 9.755 +type train | step 4946 | loss 95.6288 203.5015 315.2114 504.9465 756.4979 1091.9723 1537.9880 2183.1309 3055.1343 4582.7920 7429.4844 13026.8193 | lr 1.0e-04 | norm 3067.6042 | dt 9.788 +type train | step 4947 | loss 102.6516 217.1121 334.5332 531.3232 789.7886 1130.0088 1587.8510 2238.3008 3124.5422 4709.9604 7628.0132 13439.8262 | lr 1.0e-04 | norm 4494.3213 | dt 9.759 +type train | step 4948 | loss 101.6035 214.8173 328.8123 521.3031 778.1754 1108.1484 1542.1885 2152.9517 2934.6768 4358.6016 6975.0669 12329.0352 | lr 1.0e-04 | norm 6218.3643 | dt 9.749 +type train | step 4949 | loss 95.5447 200.4147 309.4440 495.8320 741.8663 1060.7863 1488.0576 2099.3994 2927.1235 4389.9355 7121.7637 12511.1768 | lr 1.0e-04 | norm 3413.4202 | dt 9.782 +type train | step 4950 | loss 102.1632 215.7010 328.3917 516.9318 769.5580 1097.5942 1535.0544 2149.1436 2944.6394 4394.0645 7123.7446 12592.5098 | lr 1.0e-04 | norm 3713.6409 | dt 9.742 +type train | step 4951 | loss 97.7222 208.0660 317.5156 510.6913 769.3146 1124.4337 1583.3967 2258.0457 3121.4541 4699.0405 7654.1064 13380.7939 | lr 1.0e-04 | norm 3978.4509 | dt 9.759 +type train | step 4952 | loss 99.3865 210.7926 325.7043 510.0309 763.9963 1090.3767 1533.3628 2161.2051 3014.2100 4513.6685 7300.7949 12810.8193 | lr 1.0e-04 | norm 3878.5464 | dt 9.767 +type train | step 4953 | loss 93.9696 202.4266 310.8107 498.7661 754.5595 1093.7769 1541.8298 2200.2715 3084.6545 4665.3813 7597.1318 13392.2373 | lr 1.0e-04 | norm 3666.7178 | dt 9.769 +type train | step 4954 | loss 94.3495 203.5992 310.4778 492.0619 737.0320 1062.1548 1503.7502 2147.7576 3025.8279 4576.0518 7502.6250 13276.2412 | lr 1.0e-04 | norm 4144.7476 | dt 9.762 +type train | step 4955 | loss 99.4963 213.1937 323.7602 510.1784 765.4006 1117.8026 1577.9026 2245.9053 3119.9902 4701.5342 7653.2388 13491.5488 | lr 1.0e-04 | norm 4649.9927 | dt 9.757 +type train | step 4956 | loss 94.6423 200.0946 308.5870 491.9489 737.7122 1066.6504 1513.5624 2165.4099 3044.9707 4583.3071 7368.2026 12800.0527 | lr 1.0e-04 | norm 3569.5161 | dt 9.759 +type train | step 4957 | loss 102.2929 221.6317 329.5318 530.4027 786.5010 1124.9935 1577.5098 2223.8213 3079.3528 4615.3735 7450.1909 13091.0303 | lr 1.0e-04 | norm 4237.4580 | dt 9.734 +type train | step 4958 | loss 97.3254 210.2561 319.0223 509.3194 763.2928 1091.4897 1528.8911 2149.7786 3011.7930 4536.5576 7316.6572 12802.5928 | lr 1.0e-04 | norm 3009.0208 | dt 9.758 +type train | step 4959 | loss 91.3142 191.5248 299.3503 482.8418 732.9824 1066.8317 1514.4281 2173.9988 3071.7349 4640.5029 7590.7578 13411.5723 | lr 1.0e-04 | norm 3660.1570 | dt 9.756 +type train | step 4960 | loss 95.8003 202.3700 313.0651 499.4367 751.7667 1078.1713 1515.9784 2154.9507 3023.0295 4547.8115 7429.0903 13007.3145 | lr 1.0e-04 | norm 3362.3237 | dt 9.754 +type train | step 4961 | loss 91.2787 192.1906 301.6906 486.4993 735.9613 1064.7263 1511.9771 2163.6616 3044.9810 4587.9609 7458.5942 13011.4141 | lr 1.0e-04 | norm 3136.3274 | dt 9.760 +type train | step 4962 | loss 92.4185 194.1488 302.4896 491.6962 741.7861 1077.4348 1539.9369 2207.8547 3117.8130 4703.6265 7629.1997 13320.6670 | lr 1.0e-04 | norm 3601.3879 | dt 9.753 +type train | step 4963 | loss 98.7014 210.2804 322.5731 514.4964 776.2552 1124.3363 1589.4290 2261.9873 3146.5559 4712.2979 7576.0547 13176.3145 | lr 1.0e-04 | norm 3415.7927 | dt 9.768 +type train | step 4964 | loss 100.5646 213.8146 323.3931 511.5143 770.3521 1104.7629 1553.5277 2212.0251 3078.6934 4666.9336 7584.6172 13381.6016 | lr 1.0e-04 | norm 5256.6436 | dt 9.755 +type train | step 4965 | loss 92.3912 195.0739 303.2667 488.0645 738.3026 1059.1764 1500.7383 2137.3323 3018.8882 4558.2593 7447.7959 13170.0859 | lr 1.0e-04 | norm 3133.1531 | dt 9.766 +type train | step 4966 | loss 95.2124 201.7066 310.1124 497.1652 746.3940 1076.7946 1516.4009 2150.5420 3000.4075 4535.6348 7357.6567 12856.2949 | lr 1.0e-04 | norm 2948.0054 | dt 9.764 +type train | step 4967 | loss 95.8735 203.6333 310.2572 498.3741 748.7056 1079.5150 1524.9260 2182.5063 3071.1230 4666.7012 7637.3882 13468.9092 | lr 1.0e-04 | norm 4458.4927 | dt 9.767 +type train | step 4968 | loss 94.7400 202.2112 312.6729 497.4240 749.4587 1073.6956 1516.1984 2153.9077 3027.8333 4565.6763 7425.1265 12992.4092 | lr 1.0e-04 | norm 3486.8557 | dt 9.768 +type train | step 4969 | loss 96.9501 206.4882 321.0663 511.9574 768.9672 1103.8845 1553.1587 2203.8552 3075.5635 4660.7598 7618.4702 13426.5898 | lr 1.0e-04 | norm 3821.5884 | dt 9.773 +type train | step 4970 | loss 91.2143 195.2208 302.5141 490.0414 741.4841 1072.8772 1519.0795 2161.3171 3053.6057 4618.8491 7550.2290 13280.4629 | lr 1.0e-04 | norm 3602.0005 | dt 9.766 +type train | step 4971 | loss 98.7320 209.8412 322.9285 515.5054 771.3171 1109.8230 1559.8304 2214.5469 3080.2151 4626.4316 7566.7192 13469.3594 | lr 1.0e-04 | norm 5335.3120 | dt 9.747 +type train | step 4972 | loss 93.9872 199.4937 307.8921 493.0770 741.5038 1071.2654 1508.3896 2148.5171 3023.8091 4578.7100 7455.2852 13055.8633 | lr 1.0e-04 | norm 3431.8279 | dt 9.761 +type train | step 4973 | loss 103.5112 226.0929 342.9593 540.0113 797.7300 1128.4030 1560.0074 2186.9609 3022.2969 4509.3345 7325.3037 12824.7168 | lr 1.0e-04 | norm 5219.2080 | dt 9.762 +type train | step 4974 | loss 94.5305 201.1875 311.4254 495.7351 749.8997 1071.7646 1506.1100 2138.4211 2995.8696 4497.8291 7326.5747 12833.9238 | lr 1.0e-04 | norm 3755.9998 | dt 9.755 +type train | step 4975 | loss 94.7701 202.4333 311.9273 499.3002 747.9316 1085.2632 1532.5726 2181.4277 3049.8042 4586.4995 7459.2148 13039.1836 | lr 1.0e-04 | norm 3238.7783 | dt 9.776 +type train | step 4976 | loss 95.8198 204.1956 318.6010 511.3145 771.2528 1113.0109 1570.0988 2233.0203 3139.7861 4723.4624 7653.6558 13420.2207 | lr 1.0e-04 | norm 3742.8621 | dt 9.768 +type train | step 4977 | loss 96.4950 204.5253 314.4466 504.9551 756.6874 1084.0326 1526.2032 2168.9243 3051.9404 4604.3018 7504.6377 13163.8574 | lr 1.0e-04 | norm 3485.5178 | dt 9.769 +type train | step 4978 | loss 101.3296 212.6840 325.9184 518.3841 768.4686 1107.1990 1550.2565 2188.0745 3049.7397 4567.7866 7462.4243 13168.8008 | lr 1.0e-04 | norm 3480.3127 | dt 9.768 +type train | step 4979 | loss 95.6227 211.0694 326.7234 520.4244 789.4061 1143.3899 1616.5032 2296.9971 3226.4578 4904.8359 7997.2109 14051.0049 | lr 1.0e-04 | norm 4584.7886 | dt 9.759 +type train | step 4980 | loss 97.1870 208.8820 318.8658 506.3193 761.0170 1091.3142 1540.1104 2187.5193 3063.8218 4646.1294 7569.1152 13250.6045 | lr 1.0e-04 | norm 3325.5256 | dt 9.769 +type train | step 4981 | loss 101.3720 217.6585 335.3533 531.9778 800.7450 1152.4222 1619.3381 2305.3718 3231.8135 4862.7959 7875.8145 13780.6660 | lr 1.0e-04 | norm 3417.3328 | dt 9.760 +type train | step 4982 | loss 89.0997 189.7263 297.3304 480.1519 725.0739 1049.8544 1493.9517 2128.6748 2995.6709 4497.2661 7287.7266 12771.2324 | lr 1.0e-04 | norm 3677.0432 | dt 9.768 +type train | step 4983 | loss 94.2160 203.0587 318.4128 508.1885 767.0869 1093.3412 1543.9709 2193.4102 3102.1492 4718.0854 7728.7812 13633.1533 | lr 1.0e-04 | norm 3722.5081 | dt 9.775 +type train | step 4984 | loss 92.0788 197.7508 307.6436 499.7830 754.7145 1097.6851 1561.2549 2242.1846 3155.7795 4750.6270 7681.6011 13454.9629 | lr 1.0e-04 | norm 3633.8186 | dt 9.768 +type train | step 4985 | loss 100.0843 217.5054 330.0030 522.9977 783.6390 1129.2080 1581.7312 2246.4053 3131.6716 4737.1904 7722.7847 13624.3535 | lr 1.0e-04 | norm 4561.3892 | dt 9.750 +type train | step 4986 | loss 94.4968 199.7600 308.0242 497.0849 748.2772 1085.3074 1533.7207 2191.5234 3069.9727 4653.4414 7563.3735 13220.3301 | lr 1.0e-04 | norm 3564.4910 | dt 9.761 +type train | step 4987 | loss 94.0624 199.8954 308.0733 492.9686 747.0858 1082.2256 1524.8721 2167.3079 3029.3743 4573.0347 7433.6382 12985.2227 | lr 1.0e-04 | norm 3446.6816 | dt 9.772 +type train | step 4988 | loss 91.7888 197.1666 306.3992 492.6906 745.6402 1085.6631 1539.2036 2203.9482 3109.8010 4709.3740 7660.7812 13335.2324 | lr 1.0e-04 | norm 3567.4241 | dt 9.773 +type train | step 4989 | loss 94.2501 198.0558 305.7074 498.8467 756.9575 1117.7728 1591.2161 2294.0945 3189.7310 4809.1245 7818.6748 13750.5195 | lr 1.0e-04 | norm 4726.4609 | dt 9.759 +type train | step 4990 | loss 92.1422 194.6461 304.0339 486.7797 736.2077 1063.9617 1512.5173 2159.5964 3041.9629 4619.1890 7491.5723 13098.7441 | lr 1.0e-04 | norm 3175.6121 | dt 9.760 +type train | step 4991 | loss 90.2458 191.1103 298.7625 483.1827 733.5520 1067.5620 1520.0168 2174.5542 3051.4956 4594.0181 7460.8594 13108.0654 | lr 1.0e-04 | norm 3974.2739 | dt 9.760 +type train | step 4992 | loss 93.5872 198.4973 307.2269 494.5768 745.7841 1070.6603 1509.6851 2136.7161 3011.0830 4546.6792 7393.1094 12920.7676 | lr 1.0e-04 | norm 3439.8716 | dt 9.754 +type train | step 4993 | loss 93.4301 195.4513 303.3388 489.1938 738.6595 1071.6830 1516.9397 2154.6443 3030.9453 4558.1509 7412.0659 12914.4268 | lr 1.0e-04 | norm 2983.2227 | dt 9.762 +type train | step 4994 | loss 105.8949 234.4228 357.4392 555.7984 823.6488 1168.7141 1632.6268 2304.6858 3222.5125 4899.2427 8069.4531 14368.8994 | lr 1.0e-04 | norm 6284.1357 | dt 9.758 +type train | step 4995 | loss 93.2272 200.4676 311.2415 500.9098 756.6157 1091.9807 1543.2311 2187.8838 3084.4102 4658.9082 7566.2617 13186.1680 | lr 1.0e-04 | norm 3367.1287 | dt 9.768 +type train | step 4996 | loss 93.5940 198.7822 305.0509 492.4804 741.9429 1071.4213 1525.5455 2175.7974 3050.4951 4594.4683 7518.6973 13313.8809 | lr 1.0e-04 | norm 3501.4917 | dt 9.755 +type train | step 4997 | loss 91.8425 195.3858 301.3877 487.8456 736.4054 1065.5884 1514.5289 2166.2700 3063.1987 4628.5479 7557.5347 13224.8945 | lr 1.0e-04 | norm 3314.1194 | dt 9.758 +type train | step 4998 | loss 91.5418 193.3822 302.9422 487.3357 738.2644 1066.3198 1508.7260 2142.6606 3022.5396 4558.4692 7417.6558 13037.0498 | lr 1.0e-04 | norm 3594.0176 | dt 9.763 +type train | step 4999 | loss 89.8166 187.2946 292.2382 476.7094 720.9413 1044.2179 1480.1571 2110.6687 2985.3057 4513.8281 7360.5850 12911.5234 | lr 1.0e-04 | norm 3188.6567 | dt 9.749 +type train | step 5000 | loss 94.3252 197.1413 303.6037 485.4791 733.7152 1058.4918 1504.7180 2135.6118 3001.6458 4535.9478 7413.1982 13064.0625 | lr 1.0e-04 | norm 3770.8826 | dt 9.773