diff --git "a/train.log" "b/train.log" new file mode 100644--- /dev/null +++ "b/train.log" @@ -0,0 +1,5006 @@ +type train | step 10 | loss 6482.1831 11602.6973 21202.7148 32141.3789 36770.9922 41275.7383 47461.5508 57544.8867 70433.5703 95689.1797 164915.6719 639808.3125 | lr 6.7e-06 | norm 479459.0312 | dt 9.798 +type train | step 20 | loss 6377.6406 11419.1543 20782.9648 31550.3477 36290.7539 40784.7812 47065.8867 56562.5898 69509.9453 94517.7188 162167.0000 624869.5625 | lr 1.3e-05 | norm 467622.8125 | dt 9.825 +type train | step 1 | loss 6678.0361 11812.4561 21388.7129 33085.9570 37754.9844 43453.7578 48024.1172 57742.9961 71443.3906 96400.3906 165758.8125 659050.5625 | lr 6.7e-07 | norm 524438.7500 | dt 15.473 +type train | step 2 | loss 6650.9736 11707.6973 21541.0508 33091.6094 37717.4531 43333.0273 48032.8164 57469.7227 71257.3047 96014.1094 164999.4375 642097.4375 | lr 1.3e-06 | norm 511552.9375 | dt 10.650 +type train | step 1 | loss 6679.8257 11795.9326 21488.7949 33373.8398 37992.4844 43707.7500 48323.0312 58341.1133 71125.7656 96985.2344 165311.4062 637961.6250 | lr 6.7e-07 | norm 474953.9062 | dt 39.961 +type train | step 2 | loss 6657.0132 11747.8076 21509.7715 33270.1406 37999.2617 43431.6055 48371.7852 58086.5312 71126.9375 97326.0469 166076.3281 648227.1250 | lr 1.3e-06 | norm 486878.5938 | dt 20.092 +type train | step 1 | loss 6645.8569 11798.7754 21914.6895 32669.7793 37523.4727 42393.0977 48445.3164 57832.0664 71075.9844 97024.6250 166504.9531 660162.1250 | lr 6.7e-07 | norm 507199.0625 | dt 46.954 +type train | step 2 | loss 6606.8867 11706.8115 22097.7051 32382.5625 37414.6328 42065.7539 48331.0234 57551.5898 70869.6953 97059.6484 165171.5625 644522.5000 | lr 1.3e-06 | norm 503578.1250 | dt 9.129 +type train | step 3 | loss 6584.5312 11669.1602 22031.2637 32483.6113 37404.1602 42094.8320 48426.5859 57467.8398 70950.2812 96996.7812 165894.3594 657383.2500 | lr 2.0e-06 | norm 513017.4375 | dt 9.157 +type train | step 4 | loss 6602.1904 11703.4355 22024.0234 32470.4160 37366.3398 42034.8008 48358.9102 57515.0547 70946.6953 97696.2500 167160.8750 665548.6875 | lr 2.7e-06 | norm 524585.0625 | dt 9.141 +type train | step 5 | loss 6503.9922 11559.6836 21892.2070 32245.1445 37166.6641 42135.8047 48283.6758 58006.4648 71380.7500 97089.6562 164162.7656 695452.7500 | lr 3.3e-06 | norm 556403.9375 | dt 9.148 +type train | step 6 | loss 6568.4316 11673.1543 21907.5820 32476.3105 37534.9062 42144.1172 48538.4883 58451.4688 71285.1016 97786.5234 165135.9688 670667.5625 | lr 4.0e-06 | norm 499517.2188 | dt 9.158 +type train | step 7 | loss 6524.0767 11538.5713 21720.1953 32140.3262 37200.2383 41640.0430 47908.8672 57026.3125 70608.5391 96547.6406 163708.5938 658052.5625 | lr 4.7e-06 | norm 511420.3125 | dt 9.227 +type train | step 8 | loss 6540.5425 11599.4375 21835.5215 32298.2441 37149.0391 41944.5391 48397.5312 57686.1562 70599.4453 96994.5469 165126.9844 652427.6250 | lr 5.3e-06 | norm 491396.4062 | dt 9.204 +type train | step 9 | loss 6479.9487 11507.1406 21803.2598 32146.3320 37164.7188 41681.9844 47955.0859 57347.1562 70486.8203 97000.8281 165761.7812 661985.2500 | lr 6.0e-06 | norm 514666.2500 | dt 9.172 +type train | step 10 | loss 6480.5210 11488.7686 21790.2363 32147.8652 37073.4922 41509.1953 47821.5312 56906.5352 70169.5781 96252.8203 164715.7031 656866.5000 | lr 6.7e-06 | norm 507633.0625 | dt 9.172 +type train | step 11 | loss 6498.2114 11542.2070 21630.3086 32133.2539 37009.8125 41627.8516 47681.9141 57024.1719 70126.9531 95485.7656 163394.0938 659944.6875 | lr 7.3e-06 | norm 499414.7812 | dt 9.174 +type train | step 12 | loss 6528.8076 11559.7725 21493.0508 31994.6367 36872.3242 41501.6641 47623.5820 57054.5938 69782.7031 95095.8438 162641.0781 653894.3125 | lr 8.0e-06 | norm 490971.5625 | dt 9.192 +type train | step 13 | loss 6457.5742 11437.1699 21622.8340 32091.9453 36844.0469 41449.3672 47461.4844 56994.1172 69842.6094 95995.4141 163774.3594 643338.6875 | lr 8.7e-06 | norm 491305.5625 | dt 9.183 +type train | step 14 | loss 6463.4258 11452.8955 21650.9258 32019.7949 36860.7734 41176.3164 47434.4961 56878.0938 69878.9219 95605.5078 163101.7188 648804.5000 | lr 9.3e-06 | norm 496875.1250 | dt 9.199 +type train | step 15 | loss 6430.9917 11379.5488 21322.9707 32008.8184 36816.5977 41234.9961 47484.4453 57023.1445 69948.2500 95598.8516 163182.9062 649272.6250 | lr 1.0e-05 | norm 495152.4688 | dt 9.166 +type train | step 16 | loss 6405.0776 11352.5898 21109.5742 31495.5078 36413.7695 40689.7266 47202.8672 56000.0391 69140.6797 94724.5938 161245.7812 641721.2500 | lr 1.1e-05 | norm 486368.7500 | dt 9.201 +type train | step 17 | loss 6356.2930 11229.4404 21472.1289 31649.3398 36441.1016 40900.9219 47032.2852 56338.6445 69374.8594 95386.3438 163291.3438 636406.5625 | lr 1.1e-05 | norm 487349.7188 | dt 9.188 +type train | step 18 | loss 6480.3403 11509.1328 21613.5820 31903.2891 36795.9883 41526.8047 47587.4336 57372.2812 70158.2969 94959.8516 161820.7500 654730.7500 | lr 1.2e-05 | norm 492293.7812 | dt 9.200 +type train | step 19 | loss 6423.4785 11384.1992 21245.9258 31476.4570 36420.3438 40989.2461 47001.9102 56293.1836 69108.9297 94572.4062 161648.9062 656597.9375 | lr 1.3e-05 | norm 498864.4375 | dt 9.179 +type train | step 20 | loss 6382.0771 11303.8750 21233.6445 31673.7012 36372.0391 40825.9531 46937.4844 56168.9570 69429.7188 95069.6328 162286.8906 643388.2500 | lr 1.3e-05 | norm 497439.1562 | dt 9.192 +type train | step 21 | loss 6401.4624 11334.2285 21153.7773 31228.4180 36312.3945 40621.6602 46723.2617 56017.8633 68397.7734 93755.0312 160308.2500 638818.3750 | lr 1.4e-05 | norm 492907.2812 | dt 9.204 +type train | step 22 | loss 6386.1377 11314.4268 21072.6875 31368.9473 36158.8945 40787.9844 46430.7695 56128.5312 69538.9453 94734.8281 162312.5625 671208.8125 | lr 1.5e-05 | norm 516976.2812 | dt 9.183 +type train | step 23 | loss 6425.5454 11405.9893 21170.6895 31406.5684 36131.0234 41022.1055 46281.9336 55518.6914 68395.1406 92693.3047 157768.9688 625641.0625 | lr 1.5e-05 | norm 468421.4062 | dt 9.208 +type train | step 24 | loss 6476.9727 11524.6914 21230.4121 31587.7480 36515.8672 41248.6328 46771.9375 56489.4570 69443.1875 93504.6250 158684.9375 629509.1875 | lr 1.6e-05 | norm 471760.6562 | dt 9.230 +type train | step 25 | loss 6330.4404 11183.7324 20893.4199 31210.3496 36034.6445 40241.3242 45918.3203 55376.9766 68422.3203 93147.3203 160344.3438 645306.6875 | lr 1.7e-05 | norm 510144.6562 | dt 9.200 +type train | step 26 | loss 6270.0010 11050.5996 20742.3574 30871.5938 35732.4961 40159.5781 45598.0547 55160.2148 68259.3594 92948.5703 159288.1250 646386.8125 | lr 1.7e-05 | norm 514378.7188 | dt 9.194 +type train | step 27 | loss 6280.7451 11090.2461 20545.6992 30864.0312 35699.0898 40035.6641 45719.3203 55075.6836 67797.2812 92738.7266 158571.1250 612940.8125 | lr 1.8e-05 | norm 473090.4375 | dt 9.199 +type train | step 28 | loss 6289.5371 11168.7275 20626.5293 31152.0703 36039.7500 40396.2617 45806.5703 55406.3789 68224.3828 92822.1250 158449.7656 613451.7500 | lr 1.9e-05 | norm 458396.6562 | dt 9.213 +type train | step 29 | loss 6228.9736 11034.0186 20546.6992 30682.2754 35649.5039 40021.3828 45498.0391 54789.0781 67214.0781 91889.8828 157205.1094 644796.5000 | lr 1.9e-05 | norm 524548.5000 | dt 9.207 +type train | step 30 | loss 6258.0972 11083.1582 20586.3691 30675.7500 35844.7734 40047.0312 45796.4922 55186.1172 68148.9453 92788.3047 157718.0000 634563.1875 | lr 2.0e-05 | norm 501975.6562 | dt 9.207 +type train | step 31 | loss 6301.4707 11173.2734 20643.8613 30783.9062 35814.4531 40060.3281 45510.7578 55128.3945 67639.2109 91464.5781 155904.9844 603194.1875 | lr 2.1e-05 | norm 448035.4375 | dt 9.207 +type train | step 32 | loss 6266.1533 11109.1475 20446.4121 30574.5586 35579.2383 39672.8242 45441.0391 54782.6836 67459.0625 92042.1406 156988.9375 620977.5000 | lr 2.1e-05 | norm 473479.8125 | dt 9.220 +type train | step 33 | loss 6237.7334 11060.3232 20605.9473 30686.8789 35398.6914 39585.6719 45270.9648 54500.5312 67135.3438 92082.9453 157019.8125 608461.5625 | lr 2.2e-05 | norm 459454.6250 | dt 9.232 +type train | step 34 | loss 6166.4604 10933.7402 20285.0820 30300.7324 35277.8477 39482.6016 45184.4219 54422.0352 67321.8516 92274.5469 158430.4531 630667.0000 | lr 2.3e-05 | norm 482503.6250 | dt 9.200 +type train | step 35 | loss 6203.4883 10995.9014 20249.7344 30219.1465 35030.8594 39344.0898 44999.1953 54210.5078 66719.6484 91356.0312 155025.3750 628989.5625 | lr 2.3e-05 | norm 488609.1875 | dt 9.205 +type train | step 36 | loss 6151.6094 10932.5000 20096.9883 30231.9355 34959.5508 39315.9766 45191.7227 53849.6328 66321.1484 90797.8125 155425.1406 619043.6875 | lr 2.4e-05 | norm 470362.6562 | dt 9.193 +type train | step 37 | loss 6062.7070 10750.4346 19865.5410 29961.6953 34675.2383 38980.8828 44817.1406 53394.2930 66131.9922 91352.6641 156844.6250 621430.0625 | lr 2.5e-05 | norm 474115.4062 | dt 9.196 +type train | step 38 | loss 6200.4863 10992.9492 20218.5918 30181.1758 34897.6406 39250.9961 45000.2188 53739.2852 66102.9375 90778.4219 155382.0469 612831.6875 | lr 2.5e-05 | norm 465193.7188 | dt 9.195 +type train | step 39 | loss 6155.7793 10889.3330 20051.4277 29883.2363 34418.1211 38744.0469 44627.1172 53451.3164 65964.2188 90752.3359 155006.1719 613759.5625 | lr 2.6e-05 | norm 473139.6250 | dt 9.212 +type train | step 40 | loss 6117.0107 10872.8652 19908.7734 29876.8027 34386.2266 38744.6719 44560.2344 53203.5859 65386.5000 89735.5000 154244.4062 604036.6250 | lr 2.7e-05 | norm 466388.4688 | dt 9.218 +type train | step 41 | loss 6134.0659 10865.4561 19821.7070 29786.9023 34480.7188 38846.5391 44705.5898 53338.5000 65709.5781 90088.1406 153335.7656 587947.3750 | lr 2.7e-05 | norm 427550.1250 | dt 9.213 +type train | step 42 | loss 6089.6260 10822.7812 19880.1602 29905.9277 34484.7070 38817.7656 44779.0820 53270.3594 65679.5938 90154.8438 153208.3750 584856.0625 | lr 2.8e-05 | norm 435822.6250 | dt 9.206 +type train | step 43 | loss 6071.2432 10776.6104 19879.1133 29569.0547 34400.0859 38456.4609 44251.3750 52503.6953 64991.1406 89109.9141 152229.2812 608430.8750 | lr 2.9e-05 | norm 461289.5938 | dt 9.209 +type train | step 44 | loss 6050.1621 10731.8457 19802.8594 29564.3320 34217.5508 38504.3555 44587.8203 52954.8281 65227.4648 89564.9219 153304.6562 589490.0625 | lr 2.9e-05 | norm 436229.2188 | dt 9.222 +type train | step 45 | loss 6003.1177 10676.7354 19685.9863 29408.7246 33910.5938 38271.2266 43930.0547 52516.3008 64862.8672 88867.1406 152927.0625 596589.6250 | lr 3.0e-05 | norm 454925.4375 | dt 9.213 +type train | step 46 | loss 5974.2417 10563.8037 19564.9023 29383.6348 33975.1562 38164.7383 44073.0859 52497.1016 65049.9805 89560.1797 153341.5781 585179.3125 | lr 3.1e-05 | norm 428328.0938 | dt 9.219 +type train | step 47 | loss 6003.5771 10641.6309 19739.7773 29325.2422 33821.1445 38167.5352 43809.6484 52549.8789 64990.0547 89113.6172 151887.7188 577592.6875 | lr 3.1e-05 | norm 425992.1875 | dt 9.215 +type train | step 48 | loss 6012.6543 10664.7393 19641.1406 29168.0449 33809.4375 38027.7461 43540.2773 52598.3594 64879.3984 88417.6562 150418.8438 584179.0000 | lr 3.2e-05 | norm 437685.4688 | dt 9.221 +type train | step 49 | loss 5993.4229 10670.3242 19567.7500 29261.0918 34013.4922 38091.8047 43670.3477 52567.8906 64363.9023 87847.9688 149545.4062 577134.0000 | lr 3.3e-05 | norm 418929.6250 | dt 9.232 +type train | step 50 | loss 5912.6685 10506.6572 19500.6211 29009.0742 33663.7070 37792.3438 43166.1992 52385.5859 64277.5039 88129.8438 150849.2969 576920.5000 | lr 3.3e-05 | norm 433883.8125 | dt 9.221 +type train | step 51 | loss 5874.3682 10447.9648 19201.6875 28589.7246 33354.7500 37222.1523 42311.2422 51400.6055 62776.9609 84816.5938 146183.0625 616327.5625 | lr 3.4e-05 | norm 487800.7812 | dt 9.207 +type train | step 52 | loss 5683.7993 10109.7129 18888.9199 28322.7480 32944.5977 37100.0547 42174.5820 51241.3672 63282.3516 86617.5625 150655.6094 693273.8750 | lr 3.5e-05 | norm 637300.7500 | dt 9.162 +type train | step 53 | loss 5800.7314 10316.6016 19137.6523 28456.5059 33352.3203 37358.8477 42716.4141 51447.5859 63629.2305 87420.6328 148855.0625 560479.8125 | lr 3.5e-05 | norm 417234.7812 | dt 9.223 +type train | step 54 | loss 5798.5024 10291.9414 19038.1250 28322.4043 32997.7930 37082.8125 42322.6094 50973.5195 63023.0039 86799.7188 147743.6406 556815.8125 | lr 3.6e-05 | norm 406239.8125 | dt 9.222 +type train | step 55 | loss 5847.8276 10356.6133 19116.6133 28417.0039 32810.0273 36972.7617 42468.0312 50791.5625 62784.0742 85904.3828 146986.9062 559392.5625 | lr 3.7e-05 | norm 430912.7812 | dt 9.230 +type train | step 56 | loss 5764.9067 10236.9287 18819.0273 28034.4121 32582.4023 36590.3555 41912.0586 50303.6367 61968.0742 84939.2422 144881.4062 581258.5000 | lr 3.7e-05 | norm 460857.7812 | dt 9.219 +type train | step 57 | loss 5706.4224 10140.6895 18785.4609 28075.8086 32635.2637 36739.8242 42187.6602 50557.2500 62420.0938 85779.9141 147277.0781 563716.2500 | lr 3.8e-05 | norm 436804.8438 | dt 9.224 +type train | step 58 | loss 5722.7847 10213.4600 18765.1133 28110.8594 32594.2910 36693.6602 42207.5469 50655.3711 62112.2344 85167.6953 145658.6562 560585.6250 | lr 3.9e-05 | norm 421328.1875 | dt 9.212 +type train | step 59 | loss 5702.1143 10159.2949 18698.7031 27912.7109 32410.5039 36580.9766 42079.4297 50174.0977 62087.3398 84974.5547 145320.7656 541456.5000 | lr 3.9e-05 | norm 392100.1562 | dt 9.222 +type train | step 60 | loss 5702.2900 10163.7295 18732.0273 27822.2422 32257.6836 36368.3242 41783.7891 50184.0156 61662.0391 84509.2969 144131.7812 539383.6250 | lr 4.0e-05 | norm 387057.8750 | dt 9.228 +type train | step 61 | loss 5628.9526 10021.1152 18543.1504 27697.8711 32105.2500 36178.3398 41742.0664 49916.4688 61613.6875 84650.9141 145347.5312 563352.3750 | lr 4.1e-05 | norm 424089.6562 | dt 9.228 +type train | step 62 | loss 5574.0303 9893.9531 18364.6348 27450.0176 31702.4023 35800.3828 41114.9766 49474.1875 61147.7070 83897.6094 143910.1250 566056.3125 | lr 4.1e-05 | norm 447988.3125 | dt 9.215 +type train | step 63 | loss 5645.8848 10064.2900 18494.0312 27777.0723 32115.3340 36094.2422 41195.9570 49897.4336 61614.2578 84070.1875 143325.8125 532152.3125 | lr 4.2e-05 | norm 382939.8125 | dt 9.248 +type train | step 64 | loss 5620.4736 10025.8711 18547.2168 27766.5371 32120.6738 36161.2812 41177.5039 50006.9648 61478.5742 83351.7969 142117.7188 538288.0000 | lr 4.3e-05 | norm 385000.8438 | dt 9.222 +type train | step 65 | loss 5523.2090 9845.1387 18248.1523 27299.2441 31653.5586 35583.3906 40581.4141 49209.9297 60619.6797 82862.8047 141426.4219 540499.6875 | lr 4.3e-05 | norm 400536.8750 | dt 9.229 +type train | step 66 | loss 5538.2573 9864.8887 18223.1133 27270.8516 31704.1699 35626.0234 40632.4492 49210.4258 60517.9922 82839.8828 141729.1094 529624.0000 | lr 4.4e-05 | norm 387078.5625 | dt 9.247 +type train | step 67 | loss 5450.9131 9708.6523 18042.0723 26986.0508 31524.4414 35304.5273 40491.1445 48804.5742 60281.7266 82562.3594 141464.3750 521201.1250 | lr 4.5e-05 | norm 381195.5625 | dt 9.236 +type train | step 68 | loss 5460.2271 9760.7852 18106.7266 26946.7129 31312.0918 35168.8984 40348.1836 48834.9961 60114.5625 82444.8516 141363.5000 523827.6875 | lr 4.5e-05 | norm 381848.0625 | dt 9.236 +type train | step 69 | loss 5449.0518 9704.8564 18006.3281 26861.2539 31288.9727 35299.3398 40338.0039 48327.3477 59294.9258 81134.7891 138740.4062 527526.6250 | lr 4.6e-05 | norm 366209.6875 | dt 9.232 +type train | step 70 | loss 5425.8716 9651.0420 17810.4688 26614.3691 31011.8770 34954.2852 40097.9609 48258.9531 59340.4180 81809.5859 140349.9375 533584.7500 | lr 4.7e-05 | norm 392337.5312 | dt 9.206 +type train | step 71 | loss 5329.9209 9464.3711 17596.5957 26425.8105 30750.0371 34766.4727 39998.9766 47676.6484 58718.4727 80747.3438 137641.7188 504229.8750 | lr 4.7e-05 | norm 371022.4062 | dt 9.195 +type train | step 72 | loss 5389.5352 9630.3076 17776.2363 26526.3281 30837.1699 34735.4258 40056.7773 48073.8164 59186.3516 80992.2500 138429.0156 502551.9375 | lr 4.8e-05 | norm 345623.7812 | dt 9.241 +type train | step 73 | loss 5327.6621 9527.1875 17642.6855 26354.9668 30460.4219 34401.9062 39641.2500 47561.5352 58577.0586 80596.0391 138159.0469 510440.5625 | lr 4.9e-05 | norm 360934.5000 | dt 9.239 +type train | step 74 | loss 5321.4614 9509.5938 17581.6641 26210.9922 30273.1484 34439.6055 39495.8359 47525.4727 58705.0234 80501.5938 137815.5469 512704.3125 | lr 4.9e-05 | norm 365402.2500 | dt 9.215 +type train | step 75 | loss 5316.4990 9501.8828 17469.8848 26169.3203 30340.6152 34145.3633 39377.4883 47251.8867 58425.5625 79932.2656 136170.5781 494256.9688 | lr 5.0e-05 | norm 342979.0000 | dt 9.226 +type train | step 76 | loss 5255.2129 9381.0322 17366.3203 26211.9453 30223.2422 34037.7266 38909.1289 47057.5195 58122.0156 79523.5859 136370.1094 506835.1875 | lr 5.1e-05 | norm 370355.0000 | dt 9.250 +type train | step 77 | loss 5180.6226 9302.9365 17288.6172 26060.7871 30063.0547 34170.2227 38900.2422 47223.0898 58302.0977 80276.6328 137538.6094 512316.2188 | lr 5.1e-05 | norm 354916.1250 | dt 9.226 +type train | step 78 | loss 5203.6313 9325.8838 17263.3047 25866.4668 30014.7363 33851.6914 38553.9023 46782.0312 57524.3047 78421.5859 134956.6719 498925.1562 | lr 5.2e-05 | norm 355713.6250 | dt 9.234 +type train | step 79 | loss 5162.1650 9240.7246 17167.8086 25629.3672 29923.3184 33771.7422 38648.1367 46861.9609 57623.1953 78807.1484 134883.0625 493858.4375 | lr 5.3e-05 | norm 342632.5000 | dt 9.242 +type train | step 80 | loss 5121.1880 9168.1270 17101.6992 25433.7793 29562.9766 33584.4570 38510.3477 46713.3750 57679.2305 79057.6562 134472.4844 500837.8125 | lr 5.3e-05 | norm 371442.8750 | dt 9.226 +type train | step 81 | loss 5099.6558 9142.0020 16986.8242 25258.7773 29473.8594 33310.6172 38204.4453 45794.9023 56322.1055 76970.8984 132013.3438 479985.8438 | lr 5.4e-05 | norm 340778.2500 | dt 9.242 +type train | step 82 | loss 5158.3257 9247.6562 17032.8809 25345.6016 29438.6836 33284.2461 38255.1328 45930.0039 56433.1445 76993.6016 131698.0156 476692.1875 | lr 5.5e-05 | norm 330949.6250 | dt 9.246 +type train | step 83 | loss 5074.2339 9068.4590 16864.4082 25065.9160 29178.6309 32882.5664 37747.9023 45358.7852 56011.2734 76565.1406 130348.4375 466932.7812 | lr 5.5e-05 | norm 328444.1562 | dt 9.256 +type train | step 84 | loss 5025.3042 9012.0479 16771.7402 24920.9707 28916.4062 32789.7266 37567.0586 45427.9844 55977.9492 76551.8672 131571.3750 476422.3750 | lr 5.6e-05 | norm 344784.4688 | dt 9.245 +type train | step 85 | loss 5021.6636 9005.4795 16679.1875 24958.0605 28820.0820 32701.9082 37517.4727 45180.3008 55538.8750 75886.0312 130112.5781 468274.5000 | lr 5.7e-05 | norm 327356.3750 | dt 9.240 +type train | step 86 | loss 4955.5815 8868.7803 16518.0664 24823.7031 28561.1738 32419.6035 37050.0547 44686.7070 55164.8828 75664.0391 129645.6562 473084.6875 | lr 5.7e-05 | norm 339035.3125 | dt 9.241 +type train | step 87 | loss 4926.4673 8836.4648 16324.7676 24722.5996 28515.0703 32469.2344 37015.0703 45047.7344 55385.6719 75512.0938 128790.7969 489578.0625 | lr 5.8e-05 | norm 349101.9688 | dt 9.229 +type train | step 88 | loss 4917.5356 8854.9707 16433.7598 24701.2578 28569.3750 32370.2949 37033.2383 44776.9688 55103.7188 74932.8125 127530.7891 469933.5312 | lr 5.9e-05 | norm 325341.8125 | dt 9.244 +type train | step 89 | loss 4899.2139 8809.0449 16325.4014 24488.2969 28429.7305 32102.2793 36653.5273 44521.1367 54641.7070 74600.9922 127870.3906 460591.5625 | lr 5.9e-05 | norm 324621.0000 | dt 9.246 +type train | step 90 | loss 4865.1147 8746.3438 16342.5947 24420.7871 28324.7266 32006.3438 36696.6680 44101.2305 54217.2500 74274.0156 127264.0859 456086.5312 | lr 6.0e-05 | norm 314474.4062 | dt 9.245 +type train | step 91 | loss 4837.7827 8715.7832 16266.2480 24143.7988 28083.3320 31839.7266 36407.2578 43946.6328 54037.0195 73576.3203 126545.9531 463021.3438 | lr 6.1e-05 | norm 322411.3750 | dt 9.240 +type train | step 92 | loss 4729.9458 8523.4541 16021.5957 23856.1660 27894.7148 31272.1270 36170.7773 43347.3828 53707.4609 73661.5156 127113.6250 460321.4375 | lr 6.1e-05 | norm 325213.4688 | dt 9.256 +type train | step 93 | loss 4932.5405 8891.5234 16277.1562 24162.8145 27947.4492 31843.4688 36413.1797 43849.4062 53036.6562 71475.8828 121439.7578 437771.6250 | lr 6.2e-05 | norm 287098.2500 | dt 9.260 +type train | step 94 | loss 4763.3101 8546.0547 15962.5312 23697.2305 27429.5117 31157.9941 35707.0156 43207.0586 53013.2188 72455.0391 124175.6094 464532.4375 | lr 6.3e-05 | norm 327841.3750 | dt 9.238 +type train | step 95 | loss 4738.4556 8532.3984 15836.6973 23779.3047 27503.3184 31184.8145 35851.4219 43117.0039 52957.0078 71829.6875 123248.7031 434738.5000 | lr 6.3e-05 | norm 292347.9062 | dt 9.269 +type train | step 96 | loss 4722.2334 8503.0186 15739.2471 23679.5762 27264.8965 31047.0371 35445.5000 42951.6641 52491.2383 71158.8750 122354.3438 433371.1875 | lr 6.4e-05 | norm 301434.4688 | dt 9.255 +type train | step 97 | loss 4663.2583 8392.5615 15673.4746 23485.4395 27265.2109 30889.9375 35183.4492 42655.7734 52469.0898 72023.4297 123032.2344 431130.5625 | lr 6.5e-05 | norm 298947.3125 | dt 9.250 +type train | step 98 | loss 4613.8379 8332.5762 15573.0146 23266.1094 26937.3477 30645.8379 35047.2070 42525.3789 52414.7188 71326.9609 121621.1641 447192.3125 | lr 6.5e-05 | norm 319818.0938 | dt 9.246 +type train | step 99 | loss 4685.3091 8450.6260 15666.4141 23344.1328 26981.7285 30829.5176 35239.1602 42406.7109 51809.8789 68514.0781 117098.0547 482378.6250 | lr 6.6e-05 | norm 388977.1250 | dt 9.232 +type train | step 100 | loss 4560.6333 8233.2305 15512.3467 22953.2637 26774.7539 30417.0918 34985.8125 41926.8438 51754.0312 69923.7656 120780.9688 463657.3750 | lr 6.7e-05 | norm 332024.6562 | dt 9.236 +type train | step 101 | loss 4566.2334 8225.3965 15472.0537 22971.7012 26788.6113 30170.9199 34649.8711 41755.2969 51375.4570 69894.6875 119586.3594 414353.6875 | lr 6.7e-05 | norm 285961.0312 | dt 9.247 +type train | step 102 | loss 4540.9683 8198.9326 15396.6113 22921.0352 26627.0566 30118.6484 34546.9961 41598.0352 51056.5312 69451.4688 118955.8438 406388.9375 | lr 6.8e-05 | norm 268678.6250 | dt 9.273 +type train | step 103 | loss 4399.7290 7924.5962 15085.2490 22579.2949 26073.9551 29423.9199 33835.4102 40687.3594 50325.6172 68508.4688 118414.8594 425711.6562 | lr 6.9e-05 | norm 303544.2188 | dt 9.238 +type train | step 104 | loss 4353.4785 7840.0420 14914.0488 22488.6797 26019.3887 29587.7617 33867.6250 40901.0625 50559.9141 68973.7266 119453.6562 424023.5312 | lr 6.9e-05 | norm 316423.2812 | dt 9.210 +type train | step 105 | loss 4379.2695 7895.8936 14919.2100 22556.8828 25946.0762 29471.4023 33730.8047 40658.6641 50138.6797 68521.3125 118082.9688 413329.2812 | lr 7.0e-05 | norm 288920.3125 | dt 9.242 +type train | step 106 | loss 4439.0186 8032.9541 14943.8936 22587.3281 26230.1387 29727.8633 34090.7734 41067.3711 50476.8203 68567.2812 116786.2031 397958.1875 | lr 7.1e-05 | norm 250246.9375 | dt 9.278 +type train | step 107 | loss 4382.6743 7926.9468 14893.0029 22303.0293 25659.3535 29168.4355 33346.9141 40217.9844 49698.8906 67475.5547 115825.1562 399076.1250 | lr 7.1e-05 | norm 263034.4062 | dt 9.270 +type train | step 108 | loss 4416.8159 8000.5244 14933.8828 22399.0625 25794.6699 29262.5371 33711.4297 40473.2461 49647.1445 67260.3359 115275.6328 398449.9375 | lr 7.2e-05 | norm 266593.3125 | dt 9.268 +type train | step 109 | loss 4289.8760 7771.0908 14736.1328 21921.1562 25439.4551 28983.5859 33216.1133 39989.7227 49141.8516 66685.8984 114500.3203 393459.5000 | lr 7.3e-05 | norm 253498.8438 | dt 9.252 +type train | step 110 | loss 4303.3579 7799.1455 14681.9639 21973.2109 25460.8887 28907.0430 33221.9883 40008.6836 49039.8672 66078.0156 113223.9688 388504.3125 | lr 7.3e-05 | norm 246736.8594 | dt 9.275 +type train | step 111 | loss 4242.8091 7691.1055 14532.0664 21607.2812 25164.6484 28471.4121 32804.4492 39809.2773 48832.2930 65945.1719 113616.3984 402194.6250 | lr 7.4e-05 | norm 267026.8125 | dt 9.252 +type train | step 112 | loss 4241.5361 7697.6230 14602.1816 21770.2598 25168.4688 28505.9746 32950.8516 39783.4531 48798.9219 66014.2969 113441.9688 390991.0625 | lr 7.5e-05 | norm 253716.0781 | dt 9.270 +type train | step 113 | loss 4221.2451 7642.7046 14381.7100 21688.9902 24955.9922 28297.1211 32494.4688 39052.4609 48236.9219 65311.0078 111526.3203 372496.3438 | lr 7.5e-05 | norm 238434.4844 | dt 9.283 +type train | step 114 | loss 4173.6260 7571.3364 14334.7979 21670.7969 24926.2012 28171.8574 32459.9531 39033.6641 48066.0547 65146.9844 111004.0938 375978.0938 | lr 7.6e-05 | norm 240634.2656 | dt 9.277 +type train | step 115 | loss 4132.6665 7468.1987 14115.2988 21318.5312 24651.0703 27998.9062 32057.5508 38574.8945 47324.3281 64294.0469 110768.3984 380385.4688 | lr 7.7e-05 | norm 255608.2500 | dt 9.252 +type train | step 116 | loss 4147.9829 7545.8086 14171.3291 21441.0332 24707.8223 28064.2188 32129.1738 38456.0469 47136.1914 63594.7812 109323.4141 367192.9062 | lr 7.7e-05 | norm 225501.5156 | dt 9.275 +type train | step 117 | loss 4093.6853 7426.0928 14099.4834 21062.5781 24550.4980 27920.5371 32113.3223 38353.5234 47052.1953 63678.1992 109211.7500 364286.6250 | lr 7.8e-05 | norm 225930.3594 | dt 9.295 +type train | step 118 | loss 4034.2397 7318.1621 14028.3643 20753.9551 24176.3906 27476.2422 31611.1797 38116.6367 46860.8398 63340.2266 108600.8750 370712.9688 | lr 7.9e-05 | norm 237391.7031 | dt 9.268 +type train | step 119 | loss 4120.9121 7462.3076 13999.3379 20983.6523 24222.3223 27492.9180 31617.4902 38159.2188 46729.8242 62851.6914 107738.0000 361757.4062 | lr 7.9e-05 | norm 226986.7500 | dt 9.305 +type train | step 120 | loss 4065.4214 7382.6748 13881.4023 20798.1875 23963.9004 27155.0449 31075.4629 37326.8828 45983.9180 61879.1758 106438.1172 353392.1250 | lr 8.0e-05 | norm 220920.4375 | dt 9.314 +type train | step 121 | loss 4005.2004 7272.7803 13766.4609 20757.7637 23979.4883 27137.9004 31130.6152 37471.2578 46160.4453 62481.5391 106782.8125 351839.6875 | lr 8.1e-05 | norm 215423.0625 | dt 9.291 +type train | step 122 | loss 3925.2686 7149.4487 13669.2432 20580.1738 23801.4375 26733.3477 30999.2109 36969.0469 45525.2891 61572.1562 106157.2109 346845.0000 | lr 8.1e-05 | norm 219137.9375 | dt 9.277 +type train | step 123 | loss 3954.7646 7209.3999 13597.0859 20530.7793 23780.8730 26935.4473 30911.4668 37173.4062 45548.4219 61521.4805 105312.1797 346091.7500 | lr 8.2e-05 | norm 210071.9531 | dt 9.298 +type train | step 124 | loss 3852.9153 7014.3696 13504.6982 20203.4238 23454.2168 26654.3848 30768.8242 36751.0664 45225.5547 60750.1875 103750.5781 338654.2812 | lr 8.3e-05 | norm 205343.2344 | dt 9.286 +type train | step 125 | loss 3851.3223 6990.1240 13311.2510 20047.4414 23155.2539 26377.1191 30250.5820 36456.2891 44956.5078 60614.1914 103935.3984 349376.7812 | lr 8.3e-05 | norm 215811.4219 | dt 9.278 +type train | step 126 | loss 3822.1387 6964.1924 13306.4629 20087.7578 23258.6523 26320.8633 30276.9727 36239.6250 44717.2461 60252.2227 103317.3750 337495.5000 | lr 8.4e-05 | norm 208894.3125 | dt 9.279 +type train | step 127 | loss 3839.7124 7006.8057 13350.6338 20112.3926 23158.9551 26236.7598 30182.6914 36248.5156 44652.3555 60208.8750 103165.8047 345971.0312 | lr 8.5e-05 | norm 216442.0469 | dt 9.297 +type train | step 128 | loss 3820.6294 6958.2891 13203.0342 19942.0117 22933.0195 26037.7266 29918.2402 35976.4766 44060.0078 59472.7227 102584.8125 331836.0938 | lr 8.5e-05 | norm 202561.9844 | dt 9.289 +type train | step 129 | loss 3762.8982 6848.5986 13051.0557 19805.0781 22879.3477 25864.3750 29879.8516 35889.9219 43967.9688 59141.2148 101130.6406 337609.7812 | lr 8.6e-05 | norm 207229.1094 | dt 9.285 +type train | step 130 | loss 3733.4812 6817.0176 13003.6299 19672.0117 22617.2305 25674.1602 29545.9805 35347.6641 43358.5625 58264.8320 101092.9922 335269.6250 | lr 8.7e-05 | norm 211524.4688 | dt 9.300 +type train | step 131 | loss 3703.7168 6755.7358 12940.7686 19556.1992 22548.3340 25591.8359 29496.4688 35628.4336 43401.4492 58448.1055 100864.9219 322980.2812 | lr 8.7e-05 | norm 197620.5938 | dt 9.267 +type train | step 132 | loss 3705.3359 6747.4263 12891.9863 19483.5547 22351.9570 25550.9961 29367.6934 35161.0078 43325.9062 57722.7383 99208.4609 331845.5000 | lr 8.8e-05 | norm 197593.4219 | dt 9.301 +type train | step 133 | loss 3610.0083 6595.4927 12711.7002 19333.6641 22281.5078 25435.1152 29064.1914 34660.2266 42797.5273 57184.9414 97928.3906 316639.9062 | lr 8.9e-05 | norm 182937.7500 | dt 9.285 +type train | step 134 | loss 3619.3201 6611.7817 12716.5977 19204.6523 21934.2422 24956.5918 28804.0957 34432.2266 42683.1328 57357.2773 98623.6328 318563.5938 | lr 8.9e-05 | norm 191127.8594 | dt 9.319 +type train | step 135 | loss 3579.2551 6560.0581 12662.9287 19179.6895 21977.2148 24934.6133 28705.3828 34574.9453 42166.8047 56678.4062 97480.3281 317100.5625 | lr 9.0e-05 | norm 184884.5781 | dt 9.290 +type train | step 136 | loss 3573.7874 6517.7407 12553.1309 19004.2168 21936.1035 24816.7363 28624.0176 34278.1445 42133.1914 56305.7461 96833.6250 308712.2188 | lr 9.1e-05 | norm 177967.3438 | dt 9.318 +type train | step 137 | loss 3569.2817 6547.4204 12620.8574 19053.3926 21872.5039 24861.0977 28786.1758 34406.1641 42485.9023 57078.3828 97796.1641 322663.5938 | lr 9.1e-05 | norm 193258.8906 | dt 9.292 +type train | step 138 | loss 3503.0796 6411.5396 12404.2725 18813.5879 21665.7637 24661.4570 28341.5215 33985.0547 41945.0352 55911.4141 96084.3516 301059.2812 | lr 9.2e-05 | norm 174883.1719 | dt 9.313 +type train | step 139 | loss 3487.7795 6379.8818 12362.5303 18729.9805 21547.8926 24578.8711 28131.5195 33485.0703 41505.0195 55211.0469 95061.7188 304705.2500 | lr 9.3e-05 | norm 175544.6406 | dt 9.298 +type train | step 140 | loss 3447.5601 6320.7227 12279.9033 18514.4141 21369.4473 24254.1504 27902.8594 33380.5000 41046.4102 55154.5938 94711.0156 301767.1250 | lr 9.3e-05 | norm 175360.8281 | dt 9.306 +type train | step 141 | loss 3383.9180 6209.3887 12193.8145 18380.7656 21189.6602 24094.3984 27636.8477 33003.8945 40759.6523 54844.3086 94160.5938 301263.0312 | lr 9.4e-05 | norm 173424.3438 | dt 9.302 +type train | step 142 | loss 3366.5271 6131.0537 11927.3184 18231.1309 20783.4023 23643.8281 27306.8730 32952.8828 40376.5508 53937.9453 93044.2500 328103.8750 | lr 9.5e-05 | norm 227599.2188 | dt 9.241 +type train | step 143 | loss 3332.1233 6100.4199 11917.9453 18137.9902 20748.3730 23500.9824 27327.5898 32722.2012 40113.5312 53638.8047 92275.3047 311903.4062 | lr 9.5e-05 | norm 194090.1094 | dt 9.273 +type train | step 144 | loss 3383.0493 6183.0435 12057.0352 18217.0410 20915.5879 23760.9688 27312.7246 32769.7891 40283.4219 53453.7227 92250.8438 289446.7188 | lr 9.6e-05 | norm 158386.0625 | dt 9.307 +type train | step 145 | loss 3320.3198 6093.2422 11912.2500 18226.6328 20785.4414 23616.4746 26982.0430 32314.0234 40057.0352 53060.5977 91326.0859 286005.6250 | lr 9.7e-05 | norm 161428.9531 | dt 9.314 +type train | step 146 | loss 3300.4768 6054.9717 11911.0244 17991.6035 20703.3262 23506.9707 27045.7949 32343.6914 39839.3750 53212.1602 91099.1172 286455.3438 | lr 9.7e-05 | norm 160636.9531 | dt 9.335 +type train | step 147 | loss 3313.5459 6072.1914 11857.5820 17903.5918 20538.7578 23367.9883 26803.1367 32126.5723 39513.2695 52733.7734 90514.9922 285471.3750 | lr 9.8e-05 | norm 156694.5781 | dt 9.297 +type train | step 148 | loss 3252.8035 5966.8687 11656.4268 17679.1992 20258.7480 22966.6172 26280.0195 31457.5977 38784.9531 51692.4336 89233.7109 275902.6562 | lr 9.9e-05 | norm 152557.1875 | dt 9.319 +type train | step 149 | loss 3275.5088 6022.5806 11601.0566 17726.8398 20236.0254 22894.3125 26386.0352 31459.1094 38744.6992 51149.0859 87781.5156 278562.5625 | lr 9.9e-05 | norm 151792.7656 | dt 9.326 +type train | step 150 | loss 3218.3657 5920.5967 11559.5234 17620.7148 20154.0039 22960.1465 26457.8320 31631.6387 39085.9961 51643.2031 88244.9219 270646.5625 | lr 1.0e-04 | norm 144577.3906 | dt 9.331 +type train | step 151 | loss 3204.7913 5879.9546 11457.1533 17547.8340 19865.6445 22519.2539 25909.4375 30932.7070 38370.9844 50474.2539 86577.6875 271273.9688 | lr 1.0e-04 | norm 142611.2188 | dt 9.336 +type train | step 152 | loss 3183.2202 5842.5674 11418.7793 17416.6641 19972.2051 22562.3945 25872.7090 31011.5352 38184.4531 50605.5664 86472.9844 267227.4688 | lr 1.0e-04 | norm 142189.9375 | dt 9.333 +type train | step 153 | loss 3125.0854 5768.3403 11348.6318 17262.1289 19878.2676 22454.5312 25623.9746 30767.0059 38065.2656 50492.7461 86890.2031 285116.0938 | lr 1.0e-04 | norm 169159.8594 | dt 9.297 +type train | step 154 | loss 3072.5676 5674.2422 11245.9766 17040.6094 19530.4590 22232.7402 25636.5664 30830.0820 38248.6992 50596.0234 86215.3906 280476.5625 | lr 1.0e-04 | norm 166182.4219 | dt 9.283 +type train | step 155 | loss 3088.5376 5671.4692 11139.2891 16891.6094 19340.5625 21956.7031 25299.3398 30112.6426 37148.8555 48974.2148 84285.9922 264992.9688 | lr 1.0e-04 | norm 138005.6875 | dt 9.330 +type train | step 156 | loss 3072.2559 5658.6729 11100.5791 16952.8047 19287.7109 21987.6641 25379.6289 30431.0234 37672.0000 49735.3750 85718.7031 264870.2812 | lr 1.0e-04 | norm 141294.1875 | dt 9.312 +type train | step 157 | loss 3035.9363 5584.8374 10980.3086 16936.5625 19184.2012 21815.7656 25064.9062 29975.2520 36950.1445 48556.2734 83604.7969 259871.2812 | lr 1.0e-04 | norm 134804.1250 | dt 9.335 +type train | step 158 | loss 3023.4333 5572.7700 11013.3555 16859.9688 19275.4160 21765.9355 25071.9023 29939.2129 36766.3672 48754.3672 84093.5156 254603.4062 | lr 1.1e-04 | norm 135167.0469 | dt 9.331 +type train | step 159 | loss 3029.3208 5597.5518 11052.3330 16909.2949 19281.6797 21670.3125 24976.8887 29807.4062 36432.5391 48242.4883 83245.0938 253625.5156 | lr 1.1e-04 | norm 130847.9141 | dt 9.338 +type train | step 160 | loss 2987.5078 5487.0513 10866.5605 16502.5059 18873.3340 21275.0312 24457.6445 29411.1875 36102.3086 47711.1602 82148.6250 254230.5625 | lr 1.1e-04 | norm 134273.0312 | dt 9.333 +type train | step 161 | loss 3001.6384 5535.4082 10836.0693 16533.4941 18923.1172 21367.8145 24672.4824 29458.5664 36360.1641 48001.1211 82572.0938 253113.5312 | lr 1.1e-04 | norm 131041.4688 | dt 9.325 +type train | step 162 | loss 2969.4587 5467.4131 10784.9287 16491.2871 18659.0215 21207.3066 24451.6309 29078.5898 35947.7539 46868.9453 80403.6719 244275.0000 | lr 1.1e-04 | norm 122654.7188 | dt 9.341 +type train | step 163 | loss 2897.7148 5327.4248 10633.8193 16267.4775 18409.7812 20838.9531 23936.7402 28756.4102 35309.2305 46630.4062 80330.3281 247178.2344 | lr 1.1e-04 | norm 133529.4531 | dt 9.313 +type train | step 164 | loss 2914.8169 5379.2227 10745.2012 16375.1426 18636.9434 21018.8691 24219.3633 28889.0840 35369.5273 46795.4180 80241.2578 242119.7812 | lr 1.1e-04 | norm 124348.8672 | dt 9.350 +type train | step 165 | loss 2882.8145 5329.2690 10563.8203 16197.3906 18547.2441 20838.7949 24010.4141 28672.9414 35136.9844 46131.0703 79082.1719 242476.9531 | lr 1.1e-04 | norm 127153.8438 | dt 9.337 +type train | step 166 | loss 2871.0923 5307.4141 10540.5293 16021.8633 18407.0625 20672.2969 23715.3379 28438.4805 35060.7734 46260.6484 79856.1641 241725.0312 | lr 1.1e-04 | norm 121084.8359 | dt 9.331 +type train | step 167 | loss 2814.9316 5191.9072 10388.6230 15830.1094 18022.7520 20411.3184 23453.2656 27872.6953 34776.7930 45275.9297 77455.7266 230451.3906 | lr 1.1e-04 | norm 115617.0000 | dt 9.340 +type train | step 168 | loss 2836.8098 5244.4941 10421.2363 15904.0684 18022.6758 20354.6133 23554.3555 28096.5293 34581.4922 45289.2227 77916.6250 232747.6250 | lr 1.1e-04 | norm 118311.1328 | dt 9.344 +type train | step 169 | loss 2800.5107 5158.2754 10271.8760 15804.2090 17898.7930 20261.6270 23299.3906 27769.7090 34125.5039 44815.6133 77001.4453 232154.9531 | lr 1.1e-04 | norm 118843.7500 | dt 9.345 +type train | step 170 | loss 2791.2261 5155.1367 10250.1729 15882.9746 17870.2695 20321.6699 23338.6855 27858.6992 33971.0273 44694.5898 76676.9922 234477.8750 | lr 1.1e-04 | norm 115375.1172 | dt 9.351 +type train | step 171 | loss 2753.8201 5115.0239 10190.0889 15788.0596 17841.7129 20120.5684 23319.7617 27689.1680 34003.5469 44619.0938 76341.4844 225205.3906 | lr 1.1e-04 | norm 107705.6328 | dt 9.350 +type train | step 172 | loss 2711.8523 5027.4614 10063.4531 15596.7324 17654.8750 19891.2773 23008.6289 27542.7383 33856.6523 44436.8516 76526.4219 225448.0469 | lr 1.1e-04 | norm 111647.1797 | dt 9.328 +type train | step 173 | loss 2703.5125 4987.2485 10036.3301 15320.9951 17356.4883 19539.0664 22603.2012 27020.9785 33355.4062 43500.1992 74703.2969 220979.1094 | lr 1.2e-04 | norm 107282.1875 | dt 9.351 +type train | step 174 | loss 2772.5442 5116.0903 10106.4990 15475.1309 17411.8906 19750.1484 22793.6309 27259.3359 33290.0195 43287.3086 74367.1875 223065.8281 | lr 1.2e-04 | norm 106266.1016 | dt 9.348 +type train | step 175 | loss 2630.9395 4877.5894 9864.7373 15228.4570 17228.0156 19519.5508 22529.4883 27041.7969 33136.3359 43430.7930 74431.3984 220695.5156 | lr 1.2e-04 | norm 107549.5234 | dt 9.345 +type train | step 176 | loss 2635.1565 4886.2686 9878.6777 15335.9492 17196.6934 19481.8750 22487.3652 26915.6992 33078.1523 43431.0156 74710.9531 220303.0156 | lr 1.2e-04 | norm 105972.4062 | dt 9.349 +type train | step 177 | loss 2633.2471 4873.9624 9764.9141 15154.3721 17129.4512 19293.5371 22487.9824 26651.4980 32683.8145 42683.3750 72870.5312 214541.2344 | lr 1.2e-04 | norm 101975.1016 | dt 9.364 +type train | step 178 | loss 2580.6057 4802.1533 9719.5107 14959.0996 17008.9180 19125.5625 22290.1055 26574.3086 32720.7910 42660.5977 73085.0625 212136.0781 | lr 1.2e-04 | norm 98977.1172 | dt 9.357 +type train | step 179 | loss 2642.2744 4882.6836 9759.6055 14964.1455 16928.2617 19085.6074 22182.0586 26556.4590 32430.4395 42247.6055 72803.9922 219572.8125 | lr 1.2e-04 | norm 108153.6562 | dt 9.358 +type train | step 180 | loss 2574.3601 4780.5283 9595.4668 14864.6396 16734.4492 18991.8203 21889.3281 26077.3594 31830.9316 41489.2969 71227.5078 208334.2031 | lr 1.2e-04 | norm 97506.7500 | dt 9.673 +type train | step 181 | loss 2537.2263 4701.1631 9522.0283 14807.8984 16573.7676 18818.8984 21770.3359 25990.0703 31791.0449 41588.2188 70971.9609 207716.8594 | lr 1.2e-04 | norm 97976.0938 | dt 9.350 +type train | step 182 | loss 2532.2861 4690.9609 9525.2715 14715.5771 16508.1680 18766.9922 21814.9688 25933.5879 31699.9844 41200.5547 70143.8672 202489.5781 | lr 1.2e-04 | norm 93923.3281 | dt 9.368 +type train | step 183 | loss 2531.1523 4697.0029 9454.7607 14647.7197 16469.7227 18634.7344 21666.5059 25705.9492 31608.7852 40996.8516 69981.8672 209473.3750 | lr 1.2e-04 | norm 93234.7031 | dt 9.353 +type train | step 184 | loss 2499.7119 4619.0859 9306.0879 14482.8711 16323.7344 18274.2539 21269.6543 25312.9473 31011.6211 40167.3008 68853.6250 200624.2500 | lr 1.2e-04 | norm 94568.3047 | dt 9.356 +type train | step 185 | loss 2465.4785 4576.2329 9250.3613 14398.1846 16179.8848 18307.7891 21163.8320 25306.5488 31007.3555 40588.2812 69438.6172 199473.4219 | lr 1.2e-04 | norm 94520.2891 | dt 9.352 +type train | step 186 | loss 2531.8567 4676.9116 9328.6699 14492.6309 16157.2256 18344.3984 21136.0898 25319.5488 30651.0176 39917.1562 68130.3125 197724.4688 | lr 1.2e-04 | norm 88745.9766 | dt 9.372 +type train | step 187 | loss 2477.7097 4590.0767 9314.3330 14448.4473 16127.7949 18277.5586 21052.6309 25097.1875 30693.4355 39870.0508 67821.7266 191304.0469 | lr 1.2e-04 | norm 87513.4688 | dt 9.379 +type train | step 188 | loss 2425.8042 4520.1099 9208.8096 14225.9326 15871.3281 18025.2539 20962.7363 25016.1738 30685.4512 39950.5312 68434.2891 195252.6562 | lr 1.3e-04 | norm 90784.3438 | dt 9.363 +type train | step 189 | loss 2403.3770 4476.7412 9101.5947 14153.8672 15911.3623 17875.9199 20747.9883 24808.8984 30587.0488 39763.9961 68005.2422 192560.2188 | lr 1.3e-04 | norm 91095.6172 | dt 9.379 +type train | step 190 | loss 2368.9714 4403.2461 8946.4766 14072.6572 15708.0879 17736.2852 20582.5859 24589.1348 30126.0352 39368.8359 67430.4062 191386.2812 | lr 1.3e-04 | norm 90285.9922 | dt 9.366 +type train | step 191 | loss 2380.6626 4426.1016 9046.5811 14115.7305 15688.7266 17863.8594 20594.3438 24598.1348 30126.0312 39490.8086 67667.7812 191247.4375 | lr 1.3e-04 | norm 91404.5156 | dt 9.359 +type train | step 192 | loss 2358.8059 4379.9341 8968.7998 13969.8750 15550.6416 17722.7871 20495.6328 24399.6602 29822.0098 38815.8125 66157.8047 188077.5938 | lr 1.3e-04 | norm 92724.3359 | dt 9.360 +type train | step 193 | loss 2348.2520 4375.6426 8937.2119 13925.3271 15532.9932 17604.7852 20357.3828 24337.4434 29788.8809 38737.1484 66367.2031 186249.5625 | lr 1.3e-04 | norm 86993.9375 | dt 9.371 +type train | step 194 | loss 2333.7065 4345.9927 8877.3506 13806.8652 15391.5264 17426.9180 20216.2988 24094.2656 29459.0820 38295.8672 65469.0156 178381.7812 | lr 1.3e-04 | norm 84821.7969 | dt 9.378 +type train | step 195 | loss 2289.2058 4261.8037 8750.4072 13721.1855 15325.8340 17273.6660 20072.2988 23974.1816 29305.8867 38087.4922 65150.7656 181765.9688 | lr 1.3e-04 | norm 87917.5000 | dt 9.374 +type train | step 196 | loss 2296.4985 4282.3193 8747.2607 13720.8203 15167.9043 17221.9824 19971.6895 23866.7754 29146.7617 38057.7422 65246.3320 182696.0938 | lr 1.3e-04 | norm 86751.5156 | dt 9.367 +type train | step 197 | loss 2251.5283 4220.5146 8745.8311 13657.6914 15132.4541 17314.2012 20177.3672 24068.8105 29627.3984 38587.8516 65927.0078 186968.6875 | lr 1.3e-04 | norm 91659.0781 | dt 9.380 +type train | step 198 | loss 2257.4814 4209.8477 8662.2754 13500.0566 15055.0986 17110.4805 19779.0273 23596.8086 28919.3594 37498.4336 64110.4961 173612.5938 | lr 1.3e-04 | norm 84464.5234 | dt 9.401 +type train | step 199 | loss 2253.8892 4204.2695 8589.6523 13416.7969 14904.2051 16881.1250 19697.4961 23426.9805 28571.3281 37172.6602 63426.1172 171433.7969 | lr 1.3e-04 | norm 84105.9844 | dt 9.400 +type train | step 200 | loss 2261.4221 4210.6230 8571.6250 13411.6094 14880.1328 16871.1816 19558.6992 23340.6055 28335.7832 36871.2656 62987.7422 173236.3594 | lr 1.3e-04 | norm 85683.1875 | dt 9.384 +type train | step 201 | loss 2228.5623 4171.5010 8529.3857 13336.1113 14796.5801 16800.8789 19527.3359 23257.5977 28363.4375 36749.5664 62681.5000 168652.1406 | lr 1.3e-04 | norm 83585.2422 | dt 9.403 +type train | step 202 | loss 2289.7515 4261.4604 8655.0938 13468.9385 14957.4268 16970.7227 19718.0000 23465.5020 28539.5332 36680.3984 62455.8984 167366.9375 | lr 1.3e-04 | norm 79955.7500 | dt 9.416 +type train | step 203 | loss 2185.8398 4093.1533 8428.3789 13129.9268 14618.8359 16622.1895 19269.2129 22963.5742 28024.5098 36208.4766 61848.7461 174518.5156 | lr 1.4e-04 | norm 89389.7188 | dt 9.384 +type train | step 204 | loss 2203.3911 4116.6572 8402.1699 13048.2070 14502.3682 16507.6016 19269.0801 23060.4785 28114.5879 36483.0859 62427.9961 170981.1875 | lr 1.4e-04 | norm 85585.6484 | dt 9.370 +type train | step 205 | loss 2248.7000 4199.1748 8449.2627 13233.7305 14573.4639 16555.9668 19208.3965 22882.1016 27786.6270 36032.6172 61605.1406 167453.6094 | lr 1.4e-04 | norm 84432.4141 | dt 9.358 +type train | step 206 | loss 2164.0376 4053.2314 8339.9102 13043.9180 14492.8623 16382.6914 19034.6289 22678.7656 27697.2910 35896.6250 61186.3008 159181.2031 | lr 1.4e-04 | norm 82115.0156 | dt 9.400 +type train | step 207 | loss 2164.5649 4059.2412 8325.4922 13021.5273 14394.5684 16360.6514 19050.3516 22596.1641 27632.1445 35608.5117 60567.5547 161570.5312 | lr 1.4e-04 | norm 82867.1250 | dt 9.421 +type train | step 208 | loss 2185.4692 4102.9634 8323.8359 12982.6084 14470.8369 16457.9277 19122.1211 22785.1914 27543.2207 35531.0273 60310.3984 160642.7812 | lr 1.4e-04 | norm 81999.7031 | dt 9.420 +type train | step 209 | loss 2097.5530 3950.0068 8173.2070 12780.9336 14186.3545 16060.6074 18768.2422 22438.6270 27392.7734 35466.1602 60340.0898 159114.5938 | lr 1.4e-04 | norm 86317.2578 | dt 9.388 +type train | step 210 | loss 2091.8281 3948.5803 8142.2231 12831.9707 14165.4365 16056.6543 18716.0254 22202.7031 27127.1934 35284.7109 60048.3438 153573.7812 | lr 1.4e-04 | norm 85345.7188 | dt 9.414 +type train | step 211 | loss 2085.7886 3932.5532 8117.2676 12696.6699 14097.8213 15877.0918 18619.6211 21990.1680 26935.8203 34719.6172 58316.9805 149697.1875 | lr 1.4e-04 | norm 85394.5312 | dt 9.397 +type train | step 212 | loss 2055.6094 3883.7468 8029.7920 12646.7617 13974.2275 15798.8564 18488.8652 21975.6406 26937.6445 34668.7617 58932.4570 148036.5312 | lr 1.4e-04 | norm 83918.9141 | dt 9.411 +type train | step 213 | loss 2028.5034 3843.5957 7986.4087 12539.5840 13881.7334 15686.2480 18444.2812 21900.7500 26845.5938 34700.0234 59068.3750 149169.4219 | lr 1.4e-04 | norm 88717.0547 | dt 9.418 +type train | step 214 | loss 2048.9177 3886.8708 8017.6724 12555.5420 13923.3457 15785.9014 18524.6895 21998.1289 26861.5254 34695.1523 59055.6680 150097.0312 | lr 1.4e-04 | norm 84987.7891 | dt 9.429 +type train | step 215 | loss 2011.0754 3819.9480 7898.2524 12505.3701 13789.1016 15588.5410 18223.1094 21681.6406 26434.4023 34248.8398 58175.7500 145672.8438 | lr 1.4e-04 | norm 87980.3672 | dt 9.379 +type train | step 216 | loss 2012.3767 3823.1895 7908.6948 12424.4131 13763.8096 15540.9971 18270.8984 21725.3203 26494.1699 34200.0742 58100.4492 143230.0781 | lr 1.4e-04 | norm 86989.7188 | dt 9.425 +type train | step 217 | loss 2046.2949 3872.0225 7933.5889 12450.7871 13761.3916 15595.5430 18214.5625 21671.1367 26232.4883 33791.9570 57531.0000 140395.2031 | lr 1.4e-04 | norm 90078.7344 | dt 9.439 +type train | step 218 | loss 1990.6926 3777.5059 7807.2227 12269.9541 13565.0732 15367.7607 18002.8184 21383.0840 26095.4395 33771.3398 57385.3477 140827.4688 | lr 1.5e-04 | norm 88738.3047 | dt 9.427 +type train | step 219 | loss 1995.0347 3795.7664 7826.1597 12299.7480 13649.6562 15451.0762 18049.1562 21475.6602 26210.5488 33852.8672 57358.3359 138801.6562 | lr 1.5e-04 | norm 87861.3203 | dt 9.413 +type train | step 220 | loss 1979.8992 3782.0464 7774.5957 12285.8789 13581.9541 15322.2559 17939.7539 21314.8516 26065.8242 33739.8359 57381.9375 137357.8594 | lr 1.5e-04 | norm 89670.4922 | dt 9.419 +type train | step 221 | loss 1972.3989 3763.3464 7772.7939 12203.5166 13481.3115 15309.4326 17986.2363 21572.2617 26157.1816 33778.4531 57742.3125 148621.5156 | lr 1.5e-04 | norm 104122.6719 | dt 9.373 +type train | step 222 | loss 1942.7151 3717.6997 7710.0464 12142.0781 13429.7861 15264.7959 17892.1074 21298.4531 25984.3496 33514.1328 56867.7969 135490.5625 | lr 1.5e-04 | norm 90803.8516 | dt 9.419 +type train | step 223 | loss 1950.5588 3727.1467 7683.5718 12092.9971 13417.7305 15288.3789 17881.7832 21258.0449 25706.5879 33145.3945 55943.6328 136652.1562 | lr 1.5e-04 | norm 90914.4219 | dt 9.406 +type train | step 224 | loss 1894.6039 3627.7231 7563.0308 11933.3262 13235.3369 14994.5312 17551.5391 20840.8418 25436.0117 32936.4414 55861.0195 128355.8047 | lr 1.5e-04 | norm 92452.6484 | dt 9.404 +type train | step 225 | loss 1879.1910 3618.2832 7545.0586 11926.0977 13165.5596 14957.4492 17524.1191 20944.9277 25526.4258 33037.1094 55985.9609 132270.7969 | lr 1.5e-04 | norm 94352.1641 | dt 9.416 +type train | step 226 | loss 1878.3085 3602.6880 7501.2104 11873.9951 13082.5186 14948.3359 17504.3965 20915.2891 25466.5332 32982.6406 56065.1680 133817.8750 | lr 1.5e-04 | norm 94950.5938 | dt 9.399 +type train | step 227 | loss 1833.4193 3532.0513 7438.6577 11811.7559 13041.8545 14795.3887 17318.7617 20637.2559 25147.7207 32635.1016 55227.8594 123407.8984 | lr 1.5e-04 | norm 93393.9688 | dt 9.398 +type train | step 228 | loss 1821.9164 3517.9922 7395.8647 11756.2441 12952.1816 14705.1465 17291.4746 20540.7227 25030.6309 32493.6875 55163.2188 126021.5625 | lr 1.5e-04 | norm 97827.8672 | dt 9.403 +type train | step 229 | loss 1804.8983 3504.8369 7385.0278 11720.5527 13018.3291 14757.3926 17333.3398 20646.9121 25292.3320 32877.1055 55614.5391 127528.7891 | lr 1.5e-04 | norm 99865.9141 | dt 9.398 +type train | step 230 | loss 1776.0442 3450.8555 7323.8198 11601.6758 12883.7119 14620.1875 17125.5977 20357.5293 24824.4453 32268.1367 54990.6016 126248.1406 | lr 1.5e-04 | norm 101770.5625 | dt 9.403 +type train | step 231 | loss 1775.3348 3453.5195 7301.6274 11551.2090 12765.2041 14504.8770 16963.2422 20189.1328 24628.2090 31934.2871 54240.6289 123478.9297 | lr 1.5e-04 | norm 100793.6719 | dt 9.385 +type train | step 232 | loss 1775.6313 3439.4890 7294.0654 11586.2725 12783.3271 14524.3799 16972.0215 20190.9824 24590.0547 31917.2148 54271.3672 118681.6328 | lr 1.5e-04 | norm 96261.6250 | dt 9.389 +type train | step 233 | loss 1732.1445 3375.2253 7193.2490 11430.4346 12676.0146 14399.2939 16904.1367 20110.4258 24481.5605 31843.3613 53972.1367 118303.9922 | lr 1.6e-04 | norm 97963.1953 | dt 9.360 +type train | step 234 | loss 1755.5731 3406.3750 7222.2617 11457.6494 12673.9160 14417.4053 16883.6270 20071.7402 24539.6172 31767.6328 53803.2812 118173.4531 | lr 1.6e-04 | norm 93551.8906 | dt 9.398 +type train | step 235 | loss 1750.0527 3399.5974 7208.5200 11451.4150 12688.7246 14400.2656 16890.1758 20046.0312 24503.7266 31642.0352 53357.6836 115300.6328 | lr 1.6e-04 | norm 95659.3672 | dt 9.397 +type train | step 236 | loss 1752.1545 3413.4817 7187.2773 11425.1592 12639.4727 14386.2217 16865.3125 20086.0488 24455.1758 31582.3320 53255.5352 114802.7891 | lr 1.6e-04 | norm 96431.6953 | dt 9.412 +type train | step 237 | loss 1638.3784 3225.8113 6982.0181 11179.6182 12377.3350 14082.5527 16529.0137 19618.2012 23892.4414 31105.9609 52625.3164 113564.9219 | lr 1.6e-04 | norm 103471.5703 | dt 9.357 +type train | step 238 | loss 1669.5831 3299.4067 7054.6914 11252.6240 12416.1260 14182.3691 16622.1230 19849.8242 24240.1016 31514.6934 53447.8750 117554.9844 | lr 1.6e-04 | norm 104826.7344 | dt 9.339 +type train | step 239 | loss 1665.7789 3274.3057 7005.7812 11212.7725 12375.3438 14116.5801 16526.0195 19649.2070 24085.2344 31219.3203 52748.0781 110831.7422 | lr 1.6e-04 | norm 95746.1016 | dt 9.392 +type train | step 240 | loss 1654.5507 3246.9131 7002.3047 11146.9727 12345.4150 14058.4492 16534.4844 19776.9727 24177.6836 31427.3984 52645.4922 110192.7109 | lr 1.6e-04 | norm 95420.6328 | dt 9.389 +type train | step 241 | loss 1671.2311 3271.3862 6976.8345 11162.8848 12336.9951 13997.4980 16422.1348 19586.6094 23895.1016 31057.6152 52593.1367 108007.6562 | lr 1.6e-04 | norm 98640.5156 | dt 9.390 +type train | step 242 | loss 1657.8235 3252.5559 6972.6621 11124.1045 12310.4199 13999.8359 16491.7461 19590.9238 23819.6250 30868.4473 51945.5508 105045.5703 | lr 1.6e-04 | norm 94454.2734 | dt 9.423 +type train | step 243 | loss 1647.3650 3229.3022 6897.4404 11037.6816 12189.2334 13881.9375 16315.5068 19334.7246 23621.2148 30621.9492 51772.3555 104373.0000 | lr 1.6e-04 | norm 97901.2656 | dt 9.388 +type train | step 244 | loss 1649.1184 3231.7903 6912.9941 11038.3936 12185.4814 13903.4707 16300.1533 19406.9512 23552.0898 30528.9922 51456.2930 103712.6328 | lr 1.6e-04 | norm 92468.3750 | dt 9.370 +type train | step 245 | loss 1611.6736 3170.5403 6843.7212 10920.0469 12083.0850 13799.5537 16156.4980 19244.2617 23539.1543 30546.6797 51438.8672 103133.2734 | lr 1.6e-04 | norm 95844.7891 | dt 9.365 +type train | step 246 | loss 1605.5530 3165.8152 6804.3555 10895.9473 12027.5264 13765.8545 16187.7148 19223.0664 23467.7500 30341.3125 50722.3672 100777.4062 | lr 1.6e-04 | norm 92067.8516 | dt 9.374 +type train | step 247 | loss 1586.5052 3140.3384 6761.1719 10873.3486 12016.0918 13713.5713 16152.8594 19221.0000 23334.7051 30359.4590 50957.5703 101168.7422 | lr 1.6e-04 | norm 98954.1094 | dt 9.360 +type train | step 248 | loss 1571.4503 3106.9927 6740.2471 10828.4082 11927.3740 13607.8066 16077.7471 19076.9258 23323.6035 30257.3711 50918.1406 99174.0703 | lr 1.7e-04 | norm 97013.9453 | dt 9.345 +type train | step 249 | loss 1565.7515 3095.7864 6705.1152 10757.7734 11873.5352 13540.8174 15942.5303 18986.4531 23126.4980 29960.5957 50255.7930 97687.0391 | lr 1.7e-04 | norm 99809.4219 | dt 9.368 +type train | step 250 | loss 1560.2362 3079.0928 6685.2949 10713.1680 11839.1768 13512.8438 15959.3018 18941.4121 23047.5547 29846.3652 50094.0781 95703.6094 | lr 1.7e-04 | norm 96361.2266 | dt 9.343 +type train | step 251 | loss 1464.6599 2996.9285 6578.3350 10586.4062 11684.6602 13417.0312 15906.7812 19176.1191 23465.6758 30763.1250 52339.7383 113902.5000 | lr 1.7e-04 | norm 120926.1406 | dt 9.924 +type train | step 252 | loss 1479.5337 2994.9519 6545.3823 10593.6055 11661.0176 13430.0322 15913.7002 19064.6133 23348.8438 30534.4473 51652.0781 108336.7109 | lr 1.7e-04 | norm 119862.0781 | dt 9.959 +type train | step 253 | loss 1526.0305 3018.9194 6586.0337 10575.5342 11662.8682 13319.7334 15752.5449 18704.1953 22769.4453 29573.2344 49539.0508 93654.4766 | lr 1.7e-04 | norm 95786.7656 | dt 10.027 +type train | step 254 | loss 1527.5516 3014.6265 6524.7925 10471.9648 11573.5439 13303.4170 15676.7783 18779.3691 22849.9434 29555.8613 49673.2812 95955.2734 | lr 1.7e-04 | norm 100334.3672 | dt 9.987 +type train | step 255 | loss 1512.4551 2989.5796 6487.0547 10430.4980 11472.3389 13092.9531 15469.5107 18409.1113 22438.9727 29035.3555 48626.0977 90261.2656 | lr 1.7e-04 | norm 96959.1328 | dt 10.002 +type train | step 256 | loss 1478.3862 2947.8291 6447.1626 10387.7148 11534.4775 13186.9756 15618.8721 18626.2715 22732.2891 29449.3672 49006.3164 92300.9609 | lr 1.7e-04 | norm 86551.0781 | dt 9.979 +type train | step 257 | loss 1494.1047 2974.3755 6454.0459 10388.7744 11472.0264 13144.7500 15585.1855 18478.4258 22464.3535 29026.8145 48519.2461 88584.7031 | lr 1.7e-04 | norm 89010.1562 | dt 10.010 +type train | step 258 | loss 1478.2025 2939.5105 6408.8613 10343.1484 11415.8525 13063.5166 15399.3662 18245.3066 22222.0293 28707.2422 47839.2969 87253.8828 | lr 1.7e-04 | norm 90041.1641 | dt 10.008 +type train | step 259 | loss 1483.4772 2950.1067 6405.3320 10278.6240 11360.0137 13009.8457 15285.9727 18168.5020 22157.3359 28551.6738 47491.3164 85825.2812 | lr 1.7e-04 | norm 90948.8750 | dt 10.030 +type train | step 260 | loss 1462.7716 2909.9500 6367.0635 10214.4316 11330.1318 12924.1729 15274.5215 18133.4980 22084.8164 28621.5840 47424.6875 83041.8906 | lr 1.7e-04 | norm 86584.9453 | dt 10.026 +type train | step 261 | loss 1479.4644 2933.9802 6367.3643 10236.5869 11311.4160 12961.4209 15365.7559 18282.6348 22177.7949 28554.3242 47670.7891 85622.5078 | lr 1.7e-04 | norm 83487.6328 | dt 10.006 +type train | step 262 | loss 1470.9240 2928.0654 6349.5073 10216.1855 11300.8750 12891.4688 15288.8906 18135.6250 22081.8281 28373.1211 47107.6094 82077.3750 | lr 1.7e-04 | norm 83347.6875 | dt 10.015 +type train | step 263 | loss 1422.3889 2835.0950 6227.9614 10039.2949 11139.3291 12759.0381 15091.2500 17968.7871 21961.2734 28414.1035 46906.2812 81990.1250 | lr 1.8e-04 | norm 87650.6875 | dt 9.974 +type train | step 264 | loss 1467.6611 2929.2642 6326.7017 10143.1777 11201.3926 12922.9365 15217.4082 18201.9082 22169.2734 28558.7656 47240.2500 86106.0859 | lr 1.8e-04 | norm 78219.1094 | dt 9.991 +type train | step 265 | loss 1449.6592 2884.7488 6261.2661 10121.4434 11166.7021 12818.4170 15116.9834 17934.1484 21785.6250 27974.4512 46202.1719 79806.1094 | lr 1.8e-04 | norm 84792.9141 | dt 9.988 +type train | step 266 | loss 1410.7051 2822.5649 6167.7139 9990.6611 11028.1074 12614.5088 14943.3516 17760.8281 21596.9609 27753.3750 45891.7422 78675.2422 | lr 1.8e-04 | norm 83083.5938 | dt 9.983 +type train | step 267 | loss 1465.8484 2902.1360 6267.1670 10055.4824 11123.0469 12759.4453 15062.0400 17856.6660 21641.2305 27693.7031 45673.3672 76701.1719 | lr 1.8e-04 | norm 86143.8750 | dt 9.989 +type train | step 268 | loss 1386.9487 2762.5991 6060.8447 9820.5537 10847.3672 12418.6455 14700.4512 17472.9336 21301.6055 27484.7637 45059.6484 74209.0391 | lr 1.8e-04 | norm 80105.7031 | dt 9.970 +type train | step 269 | loss 1353.7825 2718.5261 6020.4102 9772.9795 10821.4053 12362.9883 14632.6123 17354.8438 21299.4258 27618.8496 45360.2344 76464.7266 | lr 1.8e-04 | norm 76922.7891 | dt 9.972 +type train | step 270 | loss 1413.6880 2813.7656 6091.2471 9850.5166 10885.3984 12506.1982 14828.4961 17717.0547 21722.5117 27918.4648 45488.9414 78574.1406 | lr 1.8e-04 | norm 71723.2656 | dt 9.967 +type train | step 271 | loss 1435.0309 2845.3481 6108.1626 9877.6641 10895.5596 12492.8213 14755.2363 17519.3516 21223.5879 27180.2148 44782.3242 74430.7031 | lr 1.8e-04 | norm 80216.0312 | dt 9.966 +type train | step 272 | loss 1317.8411 2639.0227 5840.0166 9560.1953 10543.6777 12097.9600 14416.5059 17137.5469 20978.0586 27213.4805 44758.7852 75282.0469 | lr 1.8e-04 | norm 84106.9453 | dt 9.920 +type train | step 273 | loss 1353.3340 2708.7012 5915.9058 9629.5527 10610.5225 12180.0635 14469.0879 17207.2109 21074.7324 27199.2422 44597.0078 74716.6484 | lr 1.8e-04 | norm 76671.7500 | dt 9.960 +type train | step 274 | loss 1344.9374 2698.3293 5886.2168 9612.3730 10593.3789 12156.0566 14400.8174 17108.4238 20931.4238 27010.2930 43962.0781 71698.3516 | lr 1.8e-04 | norm 72574.2500 | dt 9.960 +type train | step 275 | loss 1349.7410 2694.8049 5874.1562 9533.2021 10494.2676 12133.8252 14397.3955 17224.3301 20989.5957 27098.7383 44402.5586 73728.0156 | lr 1.8e-04 | norm 76805.2656 | dt 9.917 +type train | step 276 | loss 1313.4384 2638.4062 5800.3701 9438.2686 10453.9883 12051.6396 14304.0557 16949.7188 20749.6719 26619.5371 43293.0273 70805.8984 | lr 1.8e-04 | norm 70390.1328 | dt 9.917 +type train | step 277 | loss 1281.8507 2581.9331 5716.7915 9313.3975 10307.0986 11913.1543 14124.9521 16806.8594 20588.8828 26501.8691 43166.3320 70599.0391 | lr 1.8e-04 | norm 68955.7891 | dt 9.919 +type train | step 278 | loss 1301.0205 2608.7375 5727.1279 9316.1660 10245.4736 11851.8516 14149.0137 16808.5879 20529.4004 26427.8750 43217.1055 70350.6562 | lr 1.9e-04 | norm 68748.6172 | dt 9.908 +type train | step 279 | loss 1293.1227 2600.4639 5634.4072 9222.9668 10186.3467 11770.1416 14012.4873 16681.1211 20386.0430 26318.7285 42811.4375 68524.0391 | lr 1.9e-04 | norm 67907.9766 | dt 9.916 +type train | step 280 | loss 1286.5320 2586.7783 5608.4937 9222.9023 10130.3174 11739.9248 13952.3047 16559.3379 20294.2500 26176.0742 42452.2188 69074.5781 | lr 1.9e-04 | norm 65825.2266 | dt 9.908 +type train | step 281 | loss 1272.5342 2564.0427 5537.9541 9099.6914 10054.8281 11645.3506 13901.5830 16504.3438 20277.9336 26106.9531 42202.6367 66773.1641 | lr 1.9e-04 | norm 63095.5352 | dt 9.888 +type train | step 282 | loss 1268.5775 2556.7175 5531.9380 9082.8320 10024.1416 11583.2197 13860.8613 16422.8242 20154.4082 25917.4199 41963.5859 66299.7578 | lr 1.9e-04 | norm 65432.6719 | dt 9.899 +type train | step 283 | loss 1263.5657 2546.0398 5512.3564 9041.2109 9992.7891 11558.4531 13806.4160 16399.4297 20074.8242 25902.5156 41805.5156 65972.7656 | lr 1.9e-04 | norm 62936.2891 | dt 9.900 +type train | step 284 | loss 1247.1104 2520.8584 5466.2046 8992.3994 9900.4102 11475.4629 13735.1406 16329.3926 19914.2617 25674.4844 41256.5195 65323.6484 | lr 1.9e-04 | norm 60419.4922 | dt 9.911 +type train | step 285 | loss 1241.7253 2507.8872 5430.0781 8884.0059 9797.2070 11415.9307 13601.8867 16151.9697 19712.0762 25381.2988 40875.2148 64018.0156 | lr 1.9e-04 | norm 63670.1445 | dt 9.884 +type train | step 286 | loss 1220.5591 2468.7402 5363.2471 8848.2217 9717.0537 11357.2178 13550.0664 16070.9258 19592.4199 25233.2363 40324.8086 63805.6641 | lr 1.9e-04 | norm 60435.0352 | dt 9.878 +type train | step 287 | loss 1240.6208 2494.3174 5374.5918 8799.4502 9628.4473 11282.7715 13448.1982 16006.7754 19565.4648 25272.6719 40393.4922 62574.6562 | lr 1.9e-04 | norm 57818.3945 | dt 9.882 +type train | step 288 | loss 1219.0612 2460.9150 5334.3638 8756.4199 9581.7783 11202.0811 13396.5127 15914.1699 19399.8965 25075.9336 39953.2422 61425.9688 | lr 1.9e-04 | norm 59164.8203 | dt 9.876 +type train | step 289 | loss 1254.8850 2515.9927 5378.7441 8848.5781 9611.9756 11242.8643 13474.6641 15924.6494 19367.6562 24995.5527 39883.8438 60663.8789 | lr 1.9e-04 | norm 58197.6680 | dt 9.869 +type train | step 290 | loss 1208.1628 2437.6956 5262.4717 8650.2314 9433.0322 11040.7998 13261.6387 15747.7158 19277.4902 25094.9570 40133.9766 62697.6016 | lr 1.9e-04 | norm 54859.2422 | dt 9.883 +type train | step 291 | loss 1172.2468 2374.3813 5188.8901 8566.1973 9370.0000 10932.7666 13061.9600 15509.7793 19084.0664 24859.8223 39688.5742 61903.6523 | lr 1.9e-04 | norm 56457.7852 | dt 9.858 +type train | step 292 | loss 1205.6121 2426.4644 5237.4917 8603.9463 9383.9150 10974.8945 13088.9883 15509.1289 18936.3066 24456.2598 38955.4102 58651.2109 | lr 1.9e-04 | norm 58056.4375 | dt 9.852 +type train | step 293 | loss 1190.0551 2415.8696 5211.8457 8560.7734 9334.0107 10914.8467 13050.8506 15566.6797 19017.3359 24790.5430 40066.9570 63559.5898 | lr 2.0e-04 | norm 57718.5117 | dt 9.847 +type train | step 294 | loss 1186.5479 2412.0454 5187.8335 8578.0254 9309.1230 10928.1611 13109.8574 15705.9668 19088.6309 25048.8496 40746.0234 65599.5859 | lr 2.0e-04 | norm 62483.8086 | dt 9.839 +type train | step 295 | loss 1174.1560 2375.5994 5112.6714 8381.4150 9148.3613 10734.4775 12886.2520 15387.8682 18858.7324 24589.9336 39233.1953 60940.7188 | lr 2.0e-04 | norm 53020.0469 | dt 9.857 +type train | step 296 | loss 1163.8502 2349.6289 5101.5493 8345.3633 9093.1230 10621.2969 12640.1211 15008.7314 18442.8105 23887.4141 38106.7617 57823.3516 | lr 2.0e-04 | norm 53719.4219 | dt 9.854 +type train | step 297 | loss 1145.4303 2329.3210 5040.8218 8274.6572 9076.0977 10594.1719 12577.9160 15023.9795 18497.7402 23901.8438 38048.6875 58083.4766 | lr 2.0e-04 | norm 50987.5352 | dt 9.855 +type train | step 298 | loss 1167.2190 2362.5420 5062.4829 8279.4863 9051.2852 10588.0391 12590.9824 15070.5469 18464.1973 23884.7422 38198.2070 58633.6445 | lr 2.0e-04 | norm 49085.0117 | dt 9.860 +type train | step 299 | loss 1112.1682 2269.5164 4971.7954 8164.4810 8943.6807 10443.7236 12380.8545 14753.1934 18186.6934 23564.6562 37451.8203 57086.4766 | lr 2.0e-04 | norm 52233.9492 | dt 9.854 +type train | step 300 | loss 1217.4119 2451.3435 5129.8403 8336.4463 9093.9131 10676.2373 12597.2344 15221.1621 18509.4102 23732.5938 37795.0625 59128.9844 | lr 2.0e-04 | norm 55988.3125 | dt 9.873 +type train | step 301 | loss 1226.3397 2456.4954 5130.1050 8316.7803 9069.3438 10666.2285 12517.9629 15104.1445 18364.4395 23517.2383 37498.9336 58487.8008 | lr 2.0e-04 | norm 61501.3047 | dt 9.889 +type train | step 302 | loss 1223.2471 2456.8672 5114.3271 8275.9922 9024.7266 10560.0635 12416.5986 14975.4775 18149.7129 23224.2773 36929.9258 57115.5547 | lr 2.0e-04 | norm 61777.5352 | dt 9.868 +type train | step 303 | loss 1223.8683 2451.9988 5104.5928 8183.5063 8952.9570 10496.8096 12346.2715 14983.3057 18125.0781 23226.6289 36908.0664 56886.4688 | lr 2.0e-04 | norm 57297.5625 | dt 9.880 +type train | step 304 | loss 1227.7195 2464.3142 5066.8027 8163.7593 8917.9395 10469.3613 12286.5566 14996.9326 18045.1367 23007.0957 36372.3438 55675.3359 | lr 2.0e-04 | norm 55972.8672 | dt 9.854 +type train | step 305 | loss 1124.9518 2277.4180 4843.2334 7911.5166 8675.4414 10093.6719 11941.4551 14373.4268 17605.3496 22785.8145 36231.0898 54724.2344 | lr 2.0e-04 | norm 46901.6484 | dt 9.853 +type train | step 306 | loss 1125.4242 2278.5652 4829.4561 7848.0308 8611.1133 10095.5049 11937.9951 14426.5020 17687.9023 22887.3574 36345.7344 58578.1094 | lr 2.0e-04 | norm 47636.0664 | dt 9.841 +type train | step 307 | loss 1101.1361 2236.1597 4762.3843 7715.9038 8487.6553 9881.2061 11679.9727 14131.6250 17365.6426 22761.0508 36290.7617 55873.7031 | lr 2.0e-04 | norm 50323.1562 | dt 9.834 +type train | step 308 | loss 1078.2882 2195.7156 4696.9746 7623.9023 8406.2383 9816.2881 11597.5254 14037.7930 17225.8555 22500.6562 35778.9375 55223.7773 | lr 2.1e-04 | norm 53872.3477 | dt 9.838 +type train | step 309 | loss 1090.0144 2217.8477 4683.1450 7605.1919 8339.9414 9701.7012 11471.4990 13901.6484 17139.0898 22468.7559 35814.2266 54601.8242 | lr 2.1e-04 | norm 49097.9727 | dt 9.838 +type train | step 310 | loss 1093.3839 2216.4351 4662.7402 7554.7158 8260.9141 9696.3232 11475.1533 13903.9385 17033.1250 22285.4512 35478.3047 54350.0625 | lr 2.1e-04 | norm 48034.0430 | dt 9.818 +type train | step 311 | loss 1069.5417 2170.6553 4604.9663 7449.4922 8145.9863 9564.3994 11321.5918 13703.1094 16875.4043 22145.7891 35235.4766 53619.5312 | lr 2.1e-04 | norm 48421.0977 | dt 9.826 +type train | step 312 | loss 1653.5780 3369.1833 6021.2666 9079.2715 9855.1807 11602.2617 13693.7012 16609.4531 20075.5312 25129.4258 37277.7109 54386.2812 | lr 2.1e-04 | norm 79459.0156 | dt 9.830 +type train | step 313 | loss 1402.7695 2867.9541 5437.9766 8381.7656 9123.8330 10743.6855 12700.8848 15446.1084 18845.5410 24035.5352 36583.5781 54190.6172 | lr 2.1e-04 | norm 59472.5234 | dt 9.846 +type train | step 314 | loss 1013.6898 2074.3853 4466.2158 7209.4780 7916.7295 9345.4609 11082.1719 13481.1816 16797.9512 22263.7305 35562.8086 55478.1211 | lr 2.1e-04 | norm 54701.3555 | dt 9.819 +type train | step 315 | loss 1061.5824 2160.7139 4537.5054 7291.8916 7959.1108 9324.6787 11062.3291 13369.1162 16577.5684 21797.5820 34451.7500 51875.7109 | lr 2.1e-04 | norm 45018.1797 | dt 9.824 +type train | step 316 | loss 1034.3898 2112.4434 4454.2451 7182.2280 7804.4478 9216.6250 10965.0664 13309.5137 16589.6074 21911.8223 34605.0000 52909.3125 | lr 2.1e-04 | norm 45911.5898 | dt 9.824 +type train | step 317 | loss 1036.5983 2120.2625 4453.5137 7113.8862 7759.9995 9123.8457 10877.7852 13176.3350 16385.1660 21644.8770 34177.5195 52167.9336 | lr 2.1e-04 | norm 46403.6797 | dt 9.842 +type train | step 318 | loss 1048.6746 2133.5420 4456.5728 7115.4385 7727.9243 9080.9141 10844.3320 13095.6172 16298.7461 21454.5605 33823.2109 50471.8555 | lr 2.1e-04 | norm 42930.6406 | dt 9.829 +type train | step 319 | loss 1024.1182 2094.9570 4385.9805 7012.3545 7643.6064 8995.1777 10793.7207 13062.8906 16261.3779 21493.1562 33744.1914 50812.2930 | lr 2.1e-04 | norm 43776.3008 | dt 9.829 +type train | step 320 | loss 1026.0658 2093.6191 4329.8730 6951.9575 7536.5317 8880.5469 10673.4141 12925.0771 16113.6162 21390.6445 33914.1875 52008.2930 | lr 2.1e-04 | norm 44289.7656 | dt 9.838 +type train | step 321 | loss 1013.3360 2072.3215 4281.6235 6894.5117 7458.0659 8797.8682 10566.1172 12820.9785 15989.0557 21184.6992 33419.4688 50425.5078 | lr 2.1e-04 | norm 42534.7070 | dt 9.838 +type train | step 322 | loss 1022.8046 2084.4585 4265.5972 6867.9839 7454.2310 8764.5117 10535.9014 12789.3896 15958.0146 21118.4121 33246.5352 49865.0859 | lr 2.1e-04 | norm 41321.5352 | dt 9.837 +type train | step 323 | loss 1002.0275 2052.3564 4203.8838 6792.1919 7371.8906 8676.2168 10437.6162 12704.5449 15849.1924 21000.1719 33013.9844 49903.3008 | lr 2.2e-04 | norm 42088.1680 | dt 9.842 +type train | step 324 | loss 1028.4314 2095.2837 4215.7500 6815.4580 7386.8257 8705.4287 10462.9492 12762.4160 15868.0664 20980.3652 33011.7578 50968.2422 | lr 2.2e-04 | norm 45214.2539 | dt 9.848 +type train | step 325 | loss 1026.6719 2091.4753 4198.4424 6736.9644 7352.1196 8653.2959 10421.5850 12704.9629 15875.0449 21039.2227 33082.7656 51079.3789 | lr 2.2e-04 | norm 42554.4492 | dt 9.843 +type train | step 326 | loss 989.5188 2025.7898 4091.0283 6573.8125 7232.3247 8504.2500 10233.9746 12460.3428 15569.9941 20649.4336 32345.9258 49147.0273 | lr 2.2e-04 | norm 42106.7227 | dt 9.836 +type train | step 327 | loss 1002.6139 2050.7681 4097.5195 6528.3364 7203.4883 8457.4316 10180.1426 12439.8311 15533.3936 20659.1230 32573.0781 49342.3633 | lr 2.2e-04 | norm 42066.9727 | dt 9.826 +type train | step 328 | loss 992.3520 2030.6581 4057.4138 6485.4048 7189.8145 8444.3857 10188.8662 12433.6934 15559.8887 20579.3574 32292.8965 49438.9492 | lr 2.2e-04 | norm 41297.0039 | dt 9.848 +type train | step 329 | loss 976.4224 1996.4849 3998.5349 6357.7671 7079.1338 8316.1162 10030.9248 12282.3867 15463.0156 20572.9883 32293.4883 49219.8047 | lr 2.2e-04 | norm 41209.0703 | dt 9.849 +type train | step 330 | loss 976.2574 2001.6769 3983.1216 6298.4653 7032.8677 8274.8340 9976.6318 12232.7422 15332.5566 20416.4883 32099.9863 49036.4062 | lr 2.2e-04 | norm 40593.9141 | dt 9.845 +type train | step 331 | loss 977.5084 1995.9368 3953.9233 6239.8608 6989.8623 8220.0723 9907.0781 12155.3623 15243.8662 20254.2461 31805.6719 48885.7461 | lr 2.2e-04 | norm 39520.8164 | dt 9.841 +type train | step 332 | loss 990.9239 2020.7791 3961.0112 6243.2734 6996.6621 8242.4980 9917.3984 12166.0566 15232.2090 20185.2910 31566.3789 48302.0781 | lr 2.2e-04 | norm 40249.5078 | dt 9.832 +type train | step 333 | loss 946.1402 1946.8048 3867.5771 6103.3438 6888.0605 8113.9048 9811.5146 12005.8330 15132.6064 20115.9434 31369.3848 48081.2930 | lr 2.2e-04 | norm 39536.8086 | dt 9.826 +type train | step 334 | loss 946.7734 1939.8945 3838.8474 6036.6421 6815.3145 8032.2231 9705.8828 11915.1416 14983.9004 19963.0898 31371.4746 48220.9648 | lr 2.2e-04 | norm 39939.8984 | dt 9.828 +type train | step 335 | loss 956.5811 1954.2010 3835.3293 6021.0366 6799.5908 8039.1406 9681.7598 11903.6934 14924.2607 19834.4570 31163.8281 48852.0234 | lr 2.2e-04 | norm 40253.4609 | dt 9.820 +type train | step 336 | loss 949.0956 1945.1111 3807.0967 5965.1016 6752.9185 7959.1719 9613.4297 11803.5996 14864.7871 19757.5410 30929.9453 47654.0781 | lr 2.2e-04 | norm 38257.6055 | dt 9.828 +type train | step 337 | loss 935.5422 1915.6670 3744.2749 5872.4131 6649.2065 7873.3130 9508.9053 11701.2539 14673.0830 19492.8848 30655.9668 47654.6250 | lr 2.2e-04 | norm 41655.7266 | dt 9.813 +type train | step 338 | loss 927.9305 1906.4471 3730.9863 5840.0137 6623.7168 7816.1836 9424.2334 11577.3984 14529.0430 19339.9023 30339.7930 47731.1172 | lr 2.3e-04 | norm 41283.8281 | dt 9.844 +type train | step 339 | loss 958.7307 1960.4834 3794.2693 5888.3389 6678.0249 7924.3311 9608.9961 11879.3984 14909.6963 19785.5117 30860.4766 48091.7773 | lr 2.3e-04 | norm 37554.7422 | dt 9.828 +type train | step 340 | loss 939.7320 1925.3168 3736.3433 5823.1025 6606.9375 7813.6680 9458.5840 11636.3867 14656.8096 19431.1934 30262.0195 47342.3555 | lr 2.3e-04 | norm 37994.7148 | dt 9.835 +type train | step 341 | loss 918.1859 1881.6633 3662.8198 5725.7163 6511.4912 7726.3057 9361.3896 11547.7324 14517.0967 19374.8477 30341.1562 48165.3594 | lr 2.3e-04 | norm 38730.1133 | dt 9.828 +type train | step 342 | loss 899.8961 1846.8302 3601.1694 5632.7271 6410.9780 7609.2397 9216.7373 11355.5479 14320.9512 19128.1426 29882.4766 47042.2578 | lr 2.3e-04 | norm 37677.5430 | dt 9.826 +type train | step 343 | loss 933.9622 1913.9342 3680.7485 5717.7393 6513.9814 7739.0083 9394.4512 11639.2119 14597.8330 19417.9922 30209.3516 47937.2266 | lr 2.3e-04 | norm 39562.5391 | dt 9.828 +type train | step 344 | loss 890.1755 1826.6621 3554.2058 5557.2544 6311.1582 7464.5439 9057.5049 11159.2285 14096.2549 18863.0000 29505.6641 47077.0000 | lr 2.3e-04 | norm 41254.8906 | dt 9.813 +type train | step 345 | loss 892.0916 1840.4177 3560.8745 5562.5312 6323.7715 7506.1572 9121.8848 11268.6045 14303.2070 19204.0000 30092.6797 48008.0156 | lr 2.3e-04 | norm 38607.9688 | dt 9.817 +type train | step 346 | loss 882.8174 1810.6141 3509.1814 5472.5620 6223.8198 7365.2427 8949.7725 11044.1123 14029.8057 18789.1973 29405.0391 45695.5078 | lr 2.3e-04 | norm 37868.2383 | dt 9.822 +type train | step 347 | loss 911.5185 1855.6884 3535.0701 5486.6523 6232.6382 7414.0137 8994.1143 11133.2607 14052.0410 18735.1172 29301.6680 46800.2812 | lr 2.3e-04 | norm 37014.4453 | dt 9.832 +type train | step 348 | loss 877.2881 1806.5756 3482.7971 5426.0469 6175.5078 7315.0703 8890.8906 10992.2637 13968.8301 18729.7012 29405.9609 46367.7695 | lr 2.3e-04 | norm 37366.7266 | dt 9.825 +type train | step 349 | loss 885.8354 1817.0383 3482.7942 5406.0630 6149.5278 7282.1514 8847.6279 10908.4404 13858.1797 18532.2031 28904.8633 45162.6562 | lr 2.3e-04 | norm 35643.8945 | dt 9.831 +type train | step 350 | loss 867.7924 1782.6157 3420.4187 5324.6406 6070.8086 7216.4287 8787.6670 10879.2949 13768.8105 18439.5801 28731.4551 45661.3711 | lr 2.3e-04 | norm 37347.4766 | dt 9.820 +type train | step 351 | loss 860.4941 1768.4360 3390.6406 5253.8608 5989.5127 7130.8584 8695.6035 10797.7314 13734.9941 18528.1719 28962.2520 46073.4102 | lr 2.3e-04 | norm 37035.9531 | dt 9.822 +type train | step 352 | loss 942.5799 1923.0875 3582.1787 5484.0034 6273.6548 7463.3027 9092.2773 11299.3135 14164.8018 18943.5039 29569.2617 48201.7617 | lr 2.3e-04 | norm 51358.4961 | dt 9.846 +type train | step 353 | loss 875.6134 1797.0573 3404.8684 5261.6465 6014.2266 7155.0107 8720.6406 10801.9570 13676.1914 18321.1797 28520.2109 44946.4609 | lr 2.4e-04 | norm 34352.4180 | dt 9.843 +type train | step 354 | loss 846.9917 1734.8325 3307.5840 5130.7847 5858.5962 6981.5498 8526.8340 10595.1553 13463.6768 18016.4199 28190.3672 44352.8672 | lr 2.4e-04 | norm 36572.6289 | dt 9.822 +type train | step 355 | loss 858.9625 1756.6233 3316.3145 5136.7188 5857.5391 6981.3730 8520.3145 10605.3691 13423.5566 18012.2148 28190.2578 44711.6953 | lr 2.4e-04 | norm 35502.9219 | dt 9.830 +type train | step 356 | loss 849.7299 1743.0735 3286.1667 5086.4683 5801.7661 6906.2734 8424.9688 10448.4756 13319.7949 17931.4746 28070.8691 44181.7891 | lr 2.4e-04 | norm 34799.7734 | dt 9.821 +type train | step 357 | loss 860.5942 1765.8604 3314.2595 5129.7427 5870.7412 6998.3125 8501.4668 10540.1240 13368.1104 17945.1660 28197.4453 45776.5781 | lr 2.4e-04 | norm 37194.8398 | dt 9.833 +type train | step 358 | loss 831.4049 1701.5352 3218.5117 4983.3691 5697.1455 6779.4463 8289.7236 10291.7900 13145.6875 17680.0449 27560.4883 43441.9062 | lr 2.4e-04 | norm 35869.1250 | dt 9.823 +type train | step 359 | loss 814.5412 1667.0236 3174.7163 4927.8496 5648.2256 6728.2144 8239.7100 10255.8154 13082.7637 17638.9004 27603.6250 43727.8594 | lr 2.4e-04 | norm 33889.4258 | dt 9.838 +type train | step 360 | loss 824.3254 1692.1229 3176.8645 4911.1689 5609.9023 6692.0967 8183.0093 10184.7822 12997.7871 17536.8438 27606.2051 44249.0664 | lr 2.4e-04 | norm 37347.0664 | dt 9.822 +type train | step 361 | loss 803.3020 1652.1586 3126.7703 4841.1885 5539.6479 6626.2202 8135.6260 10174.9053 13026.7617 17646.0176 27812.1602 44808.7695 | lr 2.4e-04 | norm 36533.1797 | dt 9.835 +type train | step 362 | loss 771.1500 1610.0233 3068.9631 4744.2817 5440.4243 6465.4590 7962.5439 9965.5566 12980.2256 17832.6211 28508.8027 45663.7969 | lr 2.4e-04 | norm 62639.4727 | dt 9.827 +type train | step 363 | loss 806.1915 1653.6263 3112.6965 4801.3008 5512.6196 6575.0503 8076.9072 10094.4756 12948.0928 17585.2969 27862.8535 44545.4141 | lr 2.4e-04 | norm 35936.0117 | dt 9.845 +type train | step 364 | loss 893.5034 1815.6853 3262.7402 4964.4854 5672.3584 6797.7197 8331.1191 10421.2148 13155.2383 17549.6953 27216.1074 43245.3281 | lr 2.4e-04 | norm 35539.5352 | dt 9.838 +type train | step 365 | loss 835.5399 1706.4103 3133.8511 4808.3892 5514.7554 6592.6143 8088.2539 10101.9531 12840.2295 17345.4629 27214.5078 44209.4336 | lr 2.4e-04 | norm 36232.3086 | dt 9.839 +type train | step 366 | loss 786.2848 1615.8861 3021.2434 4664.3511 5346.3936 6405.0342 7872.5142 9841.4258 12610.4648 17049.4023 26759.5371 42902.6719 | lr 2.4e-04 | norm 34106.1328 | dt 9.833 +type train | step 367 | loss 774.1793 1598.1917 2998.5347 4657.7227 5384.5723 6468.5981 7945.1265 9921.5176 12718.2236 17295.0801 27146.9512 44775.2734 | lr 2.4e-04 | norm 41774.9375 | dt 9.843 +type train | step 368 | loss 795.6274 1626.2725 2994.8599 4602.0400 5268.0156 6306.1045 7758.5308 9690.7588 12415.5293 16731.2578 26326.5840 42241.6016 | lr 2.5e-04 | norm 34323.2656 | dt 9.822 +type train | step 369 | loss 813.5084 1659.1169 3027.5576 4635.7393 5312.1270 6342.8501 7793.2163 9729.9902 12465.6035 16886.1738 26620.0527 42848.6641 | lr 2.5e-04 | norm 35549.9062 | dt 9.827 +type train | step 370 | loss 783.5334 1596.2970 2947.1909 4536.5210 5210.6196 6278.5068 7737.7046 9713.8770 12442.8027 16902.1836 26662.1699 43916.1523 | lr 2.5e-04 | norm 33166.6172 | dt 9.837 +type train | step 371 | loss 799.2198 1625.3444 2961.1807 4525.9062 5212.1299 6271.0967 7721.5195 9734.5625 12462.0684 16906.2734 26733.7617 44257.9414 | lr 2.5e-04 | norm 35122.3164 | dt 9.831 +type train | step 372 | loss 773.8555 1584.7152 2915.8633 4478.0117 5151.0581 6203.5635 7646.0723 9601.1191 12361.4834 16785.2734 26487.6367 42655.2500 | lr 2.5e-04 | norm 31568.9824 | dt 9.853 +type train | step 373 | loss 758.5096 1550.2852 2853.7437 4388.7808 5059.1519 6076.0879 7509.4004 9417.8115 12125.5781 16485.0312 26078.8574 42238.9180 | lr 2.5e-04 | norm 31071.7852 | dt 9.822 +type train | step 374 | loss 770.4705 1572.9944 2862.8335 4396.7812 5070.8110 6105.6621 7536.2305 9473.1328 12175.4619 16581.8652 26176.1895 43524.7500 | lr 2.5e-04 | norm 33758.2344 | dt 9.815 +type train | step 375 | loss 771.2943 1580.2338 2868.5889 4379.4907 5054.6680 6096.2891 7541.8525 9511.1338 12240.3203 16606.8320 26257.0234 43381.4531 | lr 2.5e-04 | norm 32071.5020 | dt 9.839 +type train | step 376 | loss 802.6864 1626.7756 2907.7087 4439.8096 5123.5537 6180.8540 7617.7861 9570.8838 12220.1875 16505.4043 26052.2539 43651.2656 | lr 2.5e-04 | norm 35110.3867 | dt 9.839 +type train | step 377 | loss 790.9540 1613.2263 2873.7114 4397.7383 5105.1782 6182.6504 7633.7363 9638.9102 12375.8760 16808.0820 26635.2930 45903.9180 | lr 2.5e-04 | norm 33128.5664 | dt 9.875 +type train | step 378 | loss 786.5574 1602.1699 2852.0984 4348.5122 5011.3472 6040.6704 7459.0684 9368.7305 12023.7148 16410.3730 26011.5352 43197.8828 | lr 2.5e-04 | norm 35233.6445 | dt 9.814 +type train | step 379 | loss 804.7263 1658.9305 2940.5615 4471.1709 5216.7671 6390.1787 7923.7764 10134.0186 13084.1172 17974.4414 28416.0605 48284.5273 | lr 2.5e-04 | norm 47596.9102 | dt 9.845 +type train | step 380 | loss 782.3831 1594.9034 2826.1748 4294.1055 5011.6865 6104.2061 7597.7695 9667.0869 12471.6582 17005.1055 26719.7598 44812.2461 | lr 2.5e-04 | norm 33640.9922 | dt 9.820 +type train | step 381 | loss 761.2285 1547.4741 2752.1248 4185.5205 4834.6313 5844.3872 7255.2388 9178.4033 11845.7168 16186.3525 25691.8105 42497.8359 | lr 2.5e-04 | norm 31297.2910 | dt 9.867 +type train | step 382 | loss 744.0134 1513.4652 2701.8782 4109.7227 4743.1895 5732.7788 7107.9771 8973.8398 11630.3018 15924.3320 25222.1016 41495.5273 | lr 2.5e-04 | norm 32062.1797 | dt 9.848 +type train | step 383 | loss 742.8718 1513.3668 2686.2449 4078.1587 4720.5117 5703.1504 7063.8550 8916.2861 11600.5078 15892.3057 25296.2246 41636.9375 | lr 2.6e-04 | norm 32045.7695 | dt 9.878 +type train | step 384 | loss 748.7680 1517.5549 2678.9202 4068.4912 4701.8081 5673.6699 7044.5063 8875.6152 11499.7900 15719.7520 25056.3320 41504.8789 | lr 2.6e-04 | norm 30977.2793 | dt 9.860 +type train | step 385 | loss 713.6702 1458.4812 2605.8882 3969.6643 4611.7402 5592.4536 6956.2056 8771.6748 11373.7422 15632.8027 24874.0410 41156.8242 | lr 2.6e-04 | norm 31120.9414 | dt 9.830 +type train | step 386 | loss 724.5878 1471.9219 2603.2505 3955.2231 4593.4199 5579.0518 6954.7412 8822.9883 11471.1602 15755.1084 25064.2812 41369.4805 | lr 2.6e-04 | norm 30422.0078 | dt 9.817 +type train | step 387 | loss 717.1273 1456.8470 2567.8242 3907.2314 4520.1685 5467.1279 6791.5293 8563.3965 11125.6602 15258.6240 24279.5781 40026.0078 | lr 2.6e-04 | norm 29620.6602 | dt 9.828 +type train | step 388 | loss 717.1179 1452.0522 2552.6289 3862.4478 4482.0283 5435.4282 6772.0703 8579.4111 11128.4648 15299.8662 24343.8711 40206.5508 | lr 2.6e-04 | norm 30019.2793 | dt 9.819 +type train | step 389 | loss 713.6681 1444.6790 2532.6606 3845.4331 4470.7568 5436.7275 6791.1016 8645.9395 11254.0469 15513.5732 24742.8555 41470.3867 | lr 2.6e-04 | norm 28941.8672 | dt 9.827 +type train | step 390 | loss 708.8102 1437.3380 2518.4451 3812.4961 4429.8701 5395.8447 6748.0796 8599.1221 11199.7793 15452.5820 24699.8730 41842.0625 | lr 2.6e-04 | norm 29009.6191 | dt 9.840 +type train | step 391 | loss 716.6193 1453.8687 2535.8503 3835.5571 4475.5283 5470.4834 6845.9673 8773.5479 11477.6973 15851.2900 25330.8340 42498.1406 | lr 2.6e-04 | norm 31449.8945 | dt 9.833 +type train | step 392 | loss 706.4199 1430.3304 2491.3335 3757.3689 4368.9224 5312.2051 6646.4629 8467.5439 11090.7012 15431.7402 24807.5117 41297.8047 | lr 2.6e-04 | norm 28763.3008 | dt 9.836 +type train | step 393 | loss 673.5412 1368.1543 2398.6533 3639.8647 4245.2266 5190.2783 6508.3848 8319.7881 10930.5381 15137.9355 24283.5273 40562.7109 | lr 2.6e-04 | norm 29141.1035 | dt 9.819 +type train | step 394 | loss 740.3856 1508.6133 2547.5869 3818.2305 4448.3706 5427.8457 6790.6807 8717.6816 11259.6768 15477.2959 24600.3672 40929.8672 | lr 2.6e-04 | norm 55637.4570 | dt 9.825 +type train | step 395 | loss 722.4338 1459.7283 2478.9590 3722.0330 4342.8208 5319.5474 6657.0361 8515.1475 11068.6191 15280.8184 24239.4531 41368.1992 | lr 2.6e-04 | norm 37811.7500 | dt 9.835 +type train | step 396 | loss 693.2216 1402.0979 2404.6262 3612.2471 4220.1455 5135.9780 6424.8784 8184.9937 10695.4209 14771.6367 23685.6426 39892.7266 | lr 2.6e-04 | norm 29293.6953 | dt 9.833 +type train | step 397 | loss 685.0903 1382.3872 2367.4111 3561.0056 4160.5322 5062.0000 6341.0342 8092.1851 10596.4844 14718.3262 23665.1582 39770.2734 | lr 2.6e-04 | norm 29515.2422 | dt 9.826 +type train | step 398 | loss 681.7615 1382.4972 2358.5461 3551.3457 4158.5332 5083.4712 6400.0474 8186.3926 10712.2051 14876.5908 23809.5508 40188.2109 | lr 2.7e-04 | norm 31347.9512 | dt 9.826 +type train | step 399 | loss 702.2703 1419.9670 2396.4927 3583.4919 4204.4019 5153.6543 6481.2148 8283.2568 10814.3662 15012.6123 24118.3359 41093.0859 | lr 2.7e-04 | norm 28838.1582 | dt 9.824 +type train | step 400 | loss 663.2971 1339.5959 2284.6646 3440.8088 4032.4858 4944.6733 6227.3916 7995.6885 10495.8496 14646.5000 23656.7715 39831.7227 | lr 2.7e-04 | norm 28965.7832 | dt 9.816 +type train | step 401 | loss 676.7528 1365.5864 2307.9971 3462.2144 4055.0938 4992.3760 6302.6230 8146.0132 10732.5488 15009.7598 24176.3809 40904.9961 | lr 2.7e-04 | norm 28400.2871 | dt 9.813 +type train | step 402 | loss 685.9453 1384.8521 2316.8435 3449.6892 4031.1553 4942.9292 6224.3564 7984.2065 10450.2031 14621.6631 23669.6328 40319.4102 | lr 2.7e-04 | norm 28030.2051 | dt 9.811 +type train | step 403 | loss 659.5438 1334.9128 2239.9761 3356.0664 3936.8481 4836.5254 6122.2754 7867.2559 10342.1338 14436.7393 23284.8496 39468.1367 | lr 2.7e-04 | norm 29833.9941 | dt 9.814 +type train | step 404 | loss 666.2924 1344.7211 2242.8965 3339.7549 3928.3484 4845.9048 6123.7705 7877.8813 10322.5967 14416.6367 23149.8086 39299.7422 | lr 2.7e-04 | norm 27033.6797 | dt 9.836 +type train | step 405 | loss 646.7236 1307.8848 2186.7283 3274.3740 3860.8547 4754.6255 6019.4790 7782.7358 10286.5586 14380.8926 23176.8848 39232.5547 | lr 2.7e-04 | norm 26815.1543 | dt 9.819 +type train | step 406 | loss 614.9143 1239.8861 2091.9888 3152.6970 3709.5962 4587.1396 5827.6074 7566.1055 10005.5381 14093.1250 22924.2188 39169.8945 | lr 2.7e-04 | norm 28774.7676 | dt 9.809 +type train | step 407 | loss 658.3193 1323.9464 2187.1052 3250.7278 3823.6892 4729.5020 5990.9609 7763.2935 10208.8105 14256.6826 22880.4590 39186.6602 | lr 2.7e-04 | norm 27878.0664 | dt 9.818 +type train | step 408 | loss 641.8150 1294.5212 2142.3452 3188.6777 3763.3621 4644.5498 5889.6284 7622.6294 10092.4609 14189.4717 22966.9355 39322.7148 | lr 2.7e-04 | norm 26656.9824 | dt 9.836 +type train | step 409 | loss 637.4395 1282.2239 2114.6125 3154.5981 3715.2263 4618.0601 5853.8789 7597.2998 9993.1963 14082.3154 22778.4863 39365.3789 | lr 2.7e-04 | norm 28014.8574 | dt 9.815 +type train | step 410 | loss 631.5621 1268.6447 2092.3655 3111.3730 3681.5664 4539.9141 5775.1348 7458.2949 9890.3086 13863.9990 22381.7676 37913.7891 | lr 2.7e-04 | norm 25721.9785 | dt 9.822 +type train | step 411 | loss 641.2603 1288.4028 2101.5234 3111.6223 3678.5229 4534.7090 5741.8057 7399.8428 9752.0938 13684.8770 22229.6289 38020.1758 | lr 2.7e-04 | norm 29885.8613 | dt 9.813 +type train | step 412 | loss 638.0305 1279.7703 2082.5142 3086.5930 3653.7332 4536.4277 5791.1377 7563.9004 9962.4756 14053.4561 22731.4102 38862.6367 | lr 2.7e-04 | norm 27732.0801 | dt 9.820 +type train | step 413 | loss 618.6291 1242.8237 2022.6061 3003.0693 3565.7502 4426.1982 5643.3149 7329.8066 9732.6631 13750.7363 22450.7871 38541.1953 | lr 2.8e-04 | norm 25003.1582 | dt 9.819 +type train | step 414 | loss 665.5699 1338.8986 2133.6450 3142.2134 3723.6501 4625.5801 5858.9595 7611.5205 9988.5312 14026.3936 22661.2129 39807.4453 | lr 2.8e-04 | norm 27163.4062 | dt 9.820 +type train | step 415 | loss 617.9265 1240.1266 2010.5004 2978.3120 3548.7537 4391.1191 5602.3560 7259.9048 9670.6982 13657.9365 22199.6152 37924.7695 | lr 2.8e-04 | norm 24479.8223 | dt 9.814 +type train | step 416 | loss 630.3783 1259.6443 2011.4703 2956.9727 3502.3616 4361.8154 5565.4463 7270.2832 9630.7480 13633.8555 22332.3203 38716.1680 | lr 2.8e-04 | norm 24459.4629 | dt 9.814 +type train | step 417 | loss 664.2697 1336.2864 2108.5652 3082.7292 3696.3975 4627.7676 5882.1123 7636.9424 10025.7197 14111.1348 22830.0488 39672.3555 | lr 2.8e-04 | norm 26587.6465 | dt 9.832 +type train | step 418 | loss 636.5701 1280.8225 2028.9310 2979.5989 3564.4597 4450.0371 5692.3013 7457.9058 9919.6094 14060.7266 22856.2227 39568.8945 | lr 2.8e-04 | norm 25976.0996 | dt 9.814 +type train | step 419 | loss 622.0769 1246.4813 1972.2872 2895.0811 3465.8911 4343.0996 5539.3193 7259.7266 9627.4160 13623.4033 22050.4648 38535.4219 | lr 2.8e-04 | norm 24439.2676 | dt 9.816 +type train | step 420 | loss 604.3691 1209.3621 1920.3176 2830.9604 3374.5225 4216.9863 5395.4673 7055.8638 9441.7197 13432.3770 22004.2734 38438.5234 | lr 2.8e-04 | norm 24736.6621 | dt 9.814 +type train | step 421 | loss 619.7012 1241.0905 1939.8127 2829.5112 3377.3628 4246.4160 5416.4248 7110.9126 9451.0801 13341.3301 21609.3516 37575.9141 | lr 2.8e-04 | norm 23863.8340 | dt 9.812 +type train | step 422 | loss 650.8149 1297.1110 1988.9799 2883.8960 3432.9473 4295.9526 5491.1436 7220.7808 9540.1152 13513.8447 22013.8672 38753.7617 | lr 2.8e-04 | norm 29118.3750 | dt 9.815 +type train | step 423 | loss 596.8796 1194.1873 1864.2729 2728.4177 3270.6387 4107.8203 5278.7129 6933.6060 9277.5791 13208.8066 21592.5781 37427.6641 | lr 2.8e-04 | norm 23680.8848 | dt 9.812 +type train | step 424 | loss 619.5325 1237.9587 1910.0940 2776.4075 3330.7617 4181.0020 5357.3652 7051.0396 9439.8643 13501.0127 22173.6035 38698.7266 | lr 2.8e-04 | norm 25485.3730 | dt 9.803 +type train | step 425 | loss 606.3721 1207.2340 1865.4673 2705.0923 3242.9609 4055.1445 5198.2793 6807.3447 9118.3145 13025.5449 21362.3477 36971.6328 | lr 2.8e-04 | norm 22712.4043 | dt 9.820 +type train | step 426 | loss 592.4269 1188.5658 1865.0037 2740.2007 3332.9214 4231.7681 5458.1816 7219.6675 9590.1074 13656.7041 22233.2129 38758.6680 | lr 2.8e-04 | norm 29370.5215 | dt 9.837 +type train | step 427 | loss 605.2604 1212.7609 1863.4625 2710.4646 3272.6704 4124.8701 5299.7109 6998.8901 9325.7295 13290.1602 21570.3516 37813.3867 | lr 2.8e-04 | norm 22448.3438 | dt 9.824 +type train | step 428 | loss 571.9625 1148.8684 1776.3010 2579.0305 3117.9753 3915.6382 5038.2656 6639.0732 8936.8438 12785.3564 20899.2734 36298.3398 | lr 2.9e-04 | norm 21908.6094 | dt 9.820 +type train | step 429 | loss 580.0013 1161.7385 1771.6848 2572.6069 3108.2732 3920.7244 5042.1387 6679.6294 8980.3379 12896.6758 21187.7109 37052.3125 | lr 2.9e-04 | norm 21425.4355 | dt 9.813 +type train | step 430 | loss 607.5325 1216.1116 1833.4435 2639.5234 3189.5271 4029.1123 5183.1074 6861.1914 9108.5146 12974.4355 21207.5703 37435.0273 | lr 2.9e-04 | norm 23279.2227 | dt 9.815 +type train | step 431 | loss 585.0210 1163.9467 1759.6824 2543.3596 3076.6147 3870.4829 4974.6724 6554.7305 8835.3164 12655.9160 20789.5000 36440.8164 | lr 2.9e-04 | norm 20965.7422 | dt 9.802 +type train | step 432 | loss 585.5145 1167.4368 1758.0906 2524.6531 3062.6582 3873.0535 4995.3174 6609.4277 8862.1201 12730.5371 20828.0117 36639.8008 | lr 2.9e-04 | norm 20784.7676 | dt 9.809 +type train | step 433 | loss 550.1061 1101.6237 1678.1128 2436.3123 2964.1484 3766.1924 4884.4351 6476.8945 8757.7783 12635.4473 20750.4805 36151.4766 | lr 2.9e-04 | norm 22825.0801 | dt 9.836 +type train | step 434 | loss 613.6407 1221.4257 1807.8776 2575.5295 3127.7612 3974.3972 5120.9082 6764.2998 9027.0166 12849.4121 20910.7637 36420.2109 | lr 2.9e-04 | norm 21326.2109 | dt 9.812 +type train | step 435 | loss 572.0940 1144.5323 1707.3107 2453.5422 2995.4277 3788.3198 4893.4448 6489.8555 8736.6250 12639.7744 20833.0195 36636.0508 | lr 2.9e-04 | norm 19179.0430 | dt 9.822 +type train | step 436 | loss 552.4201 1110.5310 1666.4067 2405.1443 2925.8174 3730.9341 4826.8604 6432.2505 8657.5889 12534.0781 20648.1738 36632.5938 | lr 2.9e-04 | norm 27052.6836 | dt 9.800 +type train | step 437 | loss 559.6957 1120.5839 1665.8090 2394.4216 2928.1770 3733.7000 4850.6504 6487.2285 8793.1865 12769.5996 21073.9805 37172.7031 | lr 2.9e-04 | norm 20131.6152 | dt 9.816 +type train | step 438 | loss 533.9238 1079.3881 1614.2606 2335.0491 2867.2100 3676.9521 4794.9858 6496.4878 8892.9902 13079.5811 21946.4844 39598.7148 | lr 2.9e-04 | norm 30403.1699 | dt 9.811 +type train | step 439 | loss 564.2450 1122.4095 1649.8770 2353.7207 2886.7756 3688.0764 4773.5127 6369.0200 8584.1396 12468.9180 20648.6230 37168.0156 | lr 2.9e-04 | norm 22868.0312 | dt 9.807 +type train | step 440 | loss 557.8401 1106.3792 1616.1514 2310.1687 2823.7434 3598.4133 4654.4463 6190.3926 8386.1582 12241.5312 20223.7891 35847.6289 | lr 2.9e-04 | norm 21412.0449 | dt 9.818 +type train | step 441 | loss 560.4804 1118.6010 1633.4244 2331.8130 2860.0525 3658.4995 4738.8901 6312.1904 8529.6094 12396.7529 20504.9590 36529.4922 | lr 2.9e-04 | norm 18774.2539 | dt 9.815 +type train | step 442 | loss 558.3077 1114.1486 1622.1105 2311.4043 2837.0452 3619.3306 4689.7188 6231.9556 8465.0381 12261.8838 20317.2461 35883.4609 | lr 2.9e-04 | norm 18447.9375 | dt 9.809 +type train | step 443 | loss 536.0371 1069.5540 1561.6470 2229.4958 2754.7517 3537.1052 4613.4844 6188.2046 8407.4287 12259.1826 20231.6836 35989.3125 | lr 3.0e-04 | norm 18377.0938 | dt 9.827 +type train | step 444 | loss 550.8151 1102.1459 1591.9404 2264.7874 2813.4299 3650.9546 4763.2808 6456.2051 8738.0527 12688.9365 20746.1660 36690.3477 | lr 3.0e-04 | norm 18018.8945 | dt 9.823 +type train | step 445 | loss 520.5602 1040.6903 1506.7051 2143.9822 2659.0073 3425.5154 4489.3599 6032.9512 8237.8154 12045.1387 19880.6152 35253.5234 | lr 3.0e-04 | norm 21443.4141 | dt 9.805 +type train | step 446 | loss 532.7736 1061.9923 1531.6097 2176.4641 2700.6514 3469.7351 4519.8545 6079.4766 8257.5811 12064.9775 19886.8145 34965.6484 | lr 3.0e-04 | norm 17066.8633 | dt 9.826 +type train | step 447 | loss 542.0586 1076.1509 1538.0649 2175.4885 2703.2285 3461.3264 4511.4023 6051.9673 8230.8906 12066.6396 20037.5039 35584.5781 | lr 3.0e-04 | norm 18613.6660 | dt 9.812 +type train | step 448 | loss 553.9962 1100.1877 1558.5020 2191.2405 2716.3928 3479.5569 4526.5469 6069.3940 8265.7012 12082.4199 19898.7832 35467.8984 | lr 3.0e-04 | norm 17527.2227 | dt 9.812 +type train | step 449 | loss 520.6175 1036.1367 1484.9408 2106.6941 2631.1338 3382.7717 4414.6636 5958.0186 8136.2241 11962.6865 19819.2988 34986.2930 | lr 3.0e-04 | norm 16740.4707 | dt 9.833 +type train | step 450 | loss 542.6963 1073.7803 1518.1943 2137.8472 2660.7593 3419.0227 4440.7612 5968.4561 8131.4580 11882.0605 19705.3340 35422.9922 | lr 3.0e-04 | norm 21350.3242 | dt 9.801 +type train | step 451 | loss 560.8123 1106.6434 1541.6736 2162.1873 2695.2983 3475.1421 4516.1284 6074.0938 8230.5146 12012.9004 19989.2383 36257.5273 | lr 3.0e-04 | norm 18818.5508 | dt 9.805 +type train | step 452 | loss 521.1217 1028.6030 1452.1340 2051.3625 2575.7302 3328.6047 4346.1006 5827.0605 7933.7651 11637.8076 19307.5742 34460.7500 | lr 3.0e-04 | norm 18047.4473 | dt 9.815 +type train | step 453 | loss 506.4514 1004.8065 1413.7936 2003.5879 2520.4080 3278.4319 4299.4326 5823.3867 7933.3477 11635.7393 19252.8281 33960.1094 | lr 3.0e-04 | norm 20740.8145 | dt 9.806 +type train | step 454 | loss 501.1455 1000.7159 1406.7627 1991.5027 2521.1235 3244.4819 4253.2876 5744.8911 7897.2500 11683.7393 19414.4395 34496.3125 | lr 3.0e-04 | norm 18647.5332 | dt 9.832 +type train | step 455 | loss 530.6194 1051.2267 1461.4198 2043.5933 2566.8152 3306.8403 4315.4849 5817.6792 7942.9678 11718.7607 19437.8027 34609.5469 | lr 3.0e-04 | norm 17961.8145 | dt 9.825 +type train | step 456 | loss 520.6084 1032.1117 1429.2537 2009.3439 2539.0479 3310.9536 4342.6694 5878.8218 8009.7466 11847.6885 19661.4746 35293.3984 | lr 3.0e-04 | norm 16685.9570 | dt 9.815 +type train | step 457 | loss 509.5355 1010.2092 1400.3408 1961.7363 2483.2507 3217.5342 4212.8594 5692.5117 7803.5220 11526.7637 19073.3203 34042.6523 | lr 3.0e-04 | norm 15892.0381 | dt 9.806 +type train | step 458 | loss 514.5513 1026.1437 1413.6339 1980.9363 2501.9536 3247.5447 4250.7432 5750.9448 7874.8975 11666.2676 19429.9531 34632.1445 | lr 3.1e-04 | norm 15040.9131 | dt 9.802 +type train | step 459 | loss 489.7745 972.3246 1348.2917 1892.8184 2409.3181 3133.7446 4113.9194 5589.3140 7672.0479 11384.4209 18985.9082 34039.0742 | lr 3.1e-04 | norm 16979.6133 | dt 9.813 +type train | step 460 | loss 520.6502 1030.5619 1392.9785 1932.4119 2449.2319 3184.2881 4151.0522 5616.0942 7664.2246 11339.2715 18888.8164 34134.8750 | lr 3.1e-04 | norm 17262.4629 | dt 9.800 +type train | step 461 | loss 514.9644 1018.2628 1377.6438 1911.5944 2429.0181 3195.2739 4190.7881 5739.5850 7806.0352 11526.6113 19009.8438 34459.7891 | lr 3.1e-04 | norm 17101.9785 | dt 9.808 +type train | step 462 | loss 485.8420 958.8745 1309.0546 1836.7593 2353.1880 3091.5249 4056.1211 5565.8242 7628.4521 11387.0752 19010.1133 34574.7578 | lr 3.1e-04 | norm 17819.4004 | dt 9.794 +type train | step 463 | loss 484.9053 961.5283 1322.8652 1855.6996 2381.6301 3116.8728 4112.3433 5620.3945 7767.1494 11598.0986 19275.8691 34492.1094 | lr 3.1e-04 | norm 15440.0479 | dt 9.856 +type train | step 464 | loss 488.8723 970.6274 1326.0692 1852.3333 2384.8994 3117.3914 4082.3618 5564.7295 7619.1826 11330.6992 18980.8320 34415.3828 | lr 3.1e-04 | norm 19630.9980 | dt 9.818 +type train | step 465 | loss 490.2667 972.8608 1326.5112 1847.2913 2371.2017 3097.9966 4074.3416 5550.2720 7665.5400 11433.3779 18967.9609 33947.7422 | lr 3.1e-04 | norm 15646.3740 | dt 9.820 +type train | step 466 | loss 484.0954 958.5508 1301.4314 1818.0427 2343.4785 3084.4373 4056.2161 5551.0981 7630.8501 11397.9629 19028.1855 34723.7227 | lr 3.1e-04 | norm 14634.2090 | dt 9.813 +type train | step 467 | loss 471.9276 932.7384 1272.8597 1782.1310 2313.2043 3044.6294 4005.0903 5456.2256 7544.6104 11200.3828 18588.0332 33361.7734 | lr 3.1e-04 | norm 15363.7471 | dt 9.811 +type train | step 468 | loss 476.6948 944.4189 1270.8407 1774.7002 2301.7461 3041.8782 3998.6541 5478.7451 7516.2495 11250.8389 18828.0469 34122.5352 | lr 3.1e-04 | norm 13731.6494 | dt 9.803 +type train | step 469 | loss 471.8457 943.3897 1287.0786 1804.6016 2342.1143 3102.1304 4100.1289 5681.7354 7870.0283 11886.1270 19917.7461 36363.1523 | lr 3.1e-04 | norm 19058.0391 | dt 9.805 +type train | step 470 | loss 474.1833 936.8092 1266.4386 1760.9673 2292.9229 3026.2700 3977.6853 5445.2271 7513.7085 11272.7285 18764.7344 33900.2773 | lr 3.1e-04 | norm 12596.2227 | dt 9.817 +type train | step 471 | loss 477.6287 942.6275 1267.0096 1756.8927 2281.4937 2991.7515 3924.3918 5343.5967 7371.1318 11025.7324 18440.3789 33201.4531 | lr 3.1e-04 | norm 12448.0645 | dt 9.816 +type train | step 472 | loss 464.6244 914.8378 1230.7491 1718.9440 2242.6904 2960.4902 3901.4458 5327.4238 7351.2212 10975.3398 18248.4570 32785.4492 | lr 3.1e-04 | norm 13599.7236 | dt 9.799 +type train | step 473 | loss 487.1030 962.4412 1282.4137 1771.2893 2303.7371 3043.0127 3999.6362 5537.6030 7599.6196 11346.7656 18704.2383 33865.7148 | lr 3.2e-04 | norm 14213.1445 | dt 9.802 +type train | step 474 | loss 474.0185 935.8026 1247.7076 1724.1180 2250.6584 2961.8325 3903.3386 5352.8271 7399.1587 11087.8428 18390.6895 33419.2734 | lr 3.2e-04 | norm 11680.2256 | dt 9.825 +type train | step 475 | loss 465.4006 919.9782 1227.9353 1703.0127 2229.4009 2931.0613 3853.3091 5278.2622 7273.5054 10924.1377 18149.3086 32556.1465 | lr 3.2e-04 | norm 10936.0439 | dt 9.811 +type train | step 476 | loss 454.9023 899.0313 1200.9408 1688.3140 2229.4868 2971.5889 3936.3428 5451.3813 7557.1025 11457.1211 19149.9668 34914.6211 | lr 3.2e-04 | norm 18777.6367 | dt 9.807 +type train | step 477 | loss 449.9284 888.0546 1184.6428 1646.4077 2166.9219 2861.5996 3775.3289 5171.6919 7184.7544 10863.4121 18155.8594 32879.9805 | lr 3.2e-04 | norm 12470.3057 | dt 9.800 +type train | step 478 | loss 421.2812 838.1953 1152.8765 1623.9375 2166.7014 2910.6072 3914.7837 5494.9800 7702.7412 11865.7900 20040.3281 36021.9922 | lr 3.2e-04 | norm 35201.3398 | dt 9.801 +type train | step 479 | loss 465.8265 922.3538 1242.9028 1726.1730 2270.2253 3015.5364 3968.3384 5489.4512 7542.8970 11388.4697 18977.7695 34564.9727 | lr 3.2e-04 | norm 20328.3164 | dt 9.793 +type train | step 480 | loss 457.2722 895.5276 1192.6915 1649.6421 2179.9172 2879.9668 3800.5647 5245.5244 7261.9468 10962.7236 18261.1172 33312.3828 | lr 3.2e-04 | norm 14224.1592 | dt 9.811 +type train | step 481 | loss 476.0638 941.8358 1260.9089 1756.0005 2311.4343 3079.6663 4056.3975 5604.5439 7680.9443 11474.0488 18922.6699 34580.7383 | lr 3.2e-04 | norm 15996.4395 | dt 9.811 +type train | step 482 | loss 430.9039 853.4219 1141.8817 1593.9030 2118.1460 2805.3176 3705.1987 5100.7349 7057.6914 10734.0898 17953.4375 32712.5078 | lr 3.2e-04 | norm 17895.6016 | dt 9.811 +type train | step 483 | loss 487.3304 959.9241 1259.7286 1727.8730 2272.6074 3004.1333 3924.2695 5348.5288 7281.6050 10907.6855 18108.2871 32733.3496 | lr 3.2e-04 | norm 13088.4463 | dt 9.814 +type train | step 484 | loss 481.2189 947.3573 1243.0762 1704.3258 2232.3262 2935.5227 3844.8462 5251.2871 7236.8481 10954.0605 18211.6445 33050.6172 | lr 3.2e-04 | norm 14686.4395 | dt 9.815 +type train | step 485 | loss 496.4295 977.0355 1279.1646 1752.1067 2293.8755 3013.6492 3928.8474 5344.7271 7268.6191 10931.7119 18050.9180 32874.9531 | lr 3.2e-04 | norm 15436.0020 | dt 9.818 +type train | step 486 | loss 435.6070 861.9056 1149.8217 1607.0542 2147.1309 2861.0425 3779.3198 5204.9736 7162.4932 10865.1338 18270.6641 33153.4609 | lr 3.2e-04 | norm 13962.2139 | dt 9.796 +type train | step 487 | loss 450.0595 902.8823 1237.0791 1747.3387 2345.0288 3090.2820 4065.0647 5614.6040 7815.2417 12058.3643 20231.4023 36910.1680 | lr 3.2e-04 | norm 33795.5938 | dt 9.820 +type train | step 488 | loss 480.6252 951.6232 1274.5325 1782.5106 2374.4119 3162.2903 4188.8247 5748.3613 7834.2744 11730.7100 19165.4863 35064.1328 | lr 3.3e-04 | norm 15299.7012 | dt 9.804 +type train | step 489 | loss 444.9775 879.2631 1172.9011 1636.9082 2181.4968 2906.0081 3823.3870 5273.2832 7242.4937 10953.5312 18220.1816 32807.9688 | lr 3.3e-04 | norm 13729.7217 | dt 9.822 +type train | step 490 | loss 458.3962 903.4348 1202.0814 1667.9764 2211.5537 2941.0105 3857.9941 5289.8691 7265.1074 10976.8096 18233.9727 33223.1250 | lr 3.3e-04 | norm 12296.7520 | dt 9.806 +type train | step 491 | loss 436.1012 855.3430 1131.8098 1577.4714 2106.3296 2788.2585 3664.3738 5029.3057 6933.6611 10414.1816 17311.3945 31414.7910 | lr 3.3e-04 | norm 13226.7080 | dt 9.798 +type train | step 492 | loss 488.2105 958.9183 1253.9578 1726.2471 2273.7688 3031.2239 3969.1372 5482.4277 7410.3428 11166.3652 18480.6875 33871.0547 | lr 3.3e-04 | norm 18802.7402 | dt 9.810 +type train | step 493 | loss 439.2873 865.6631 1151.8019 1604.8567 2135.0544 2839.5447 3729.1594 5117.2471 7048.2866 10646.0098 17724.1777 32388.6523 | lr 3.3e-04 | norm 13318.3643 | dt 9.812 +type train | step 494 | loss 428.7500 846.8781 1134.2126 1590.0551 2125.3943 2827.2529 3722.6619 5132.9868 7096.8018 10775.8730 17968.2109 32548.0469 | lr 3.3e-04 | norm 12913.0566 | dt 9.806 +type train | step 495 | loss 438.9863 861.7861 1146.2041 1601.3800 2132.9446 2825.5776 3712.7568 5091.8828 7013.1211 10627.8105 17650.3867 32035.0977 | lr 3.3e-04 | norm 10985.4590 | dt 9.804 +type train | step 496 | loss 436.7589 860.4553 1140.2745 1595.2059 2125.0928 2817.8479 3697.7500 5089.5889 6990.2935 10579.3125 17646.1230 32324.6582 | lr 3.3e-04 | norm 12062.2617 | dt 9.813 +type train | step 497 | loss 441.8644 867.4376 1147.6178 1594.5303 2122.1641 2807.6938 3667.8945 5020.5342 6912.4116 10472.6953 17455.9980 31850.1406 | lr 3.3e-04 | norm 11497.9551 | dt 9.811 +type train | step 498 | loss 417.4490 824.7565 1098.1967 1542.9868 2066.5898 2755.5732 3626.3796 4993.2393 6874.9102 10418.1172 17426.3418 32058.5742 | lr 3.3e-04 | norm 11088.4814 | dt 9.805 +type train | step 499 | loss 437.7215 856.8441 1135.7725 1581.3108 2105.7722 2791.1692 3663.5859 5035.9751 6960.7495 10543.1201 17697.4688 32424.0918 | lr 3.3e-04 | norm 12219.0498 | dt 10.150 +type train | step 500 | loss 417.6641 820.6252 1097.7600 1537.9197 2061.6072 2730.5642 3612.4932 4962.3647 6878.8940 10432.3506 17409.7109 31512.1348 | lr 3.3e-04 | norm 11831.0234 | dt 9.805 +type train | step 501 | loss 424.1005 833.3592 1116.7330 1564.7162 2092.7568 2792.9900 3689.1145 5074.6548 7035.8281 10681.9639 17821.6094 32602.2422 | lr 3.3e-04 | norm 11948.8125 | dt 9.795 +type train | step 502 | loss 403.6665 794.6534 1064.9895 1498.5842 2011.7538 2684.8535 3553.1492 4897.0869 6781.2500 10327.4297 17241.5352 31559.9492 | lr 3.3e-04 | norm 14105.3965 | dt 9.783 +type train | step 503 | loss 430.0190 842.8690 1123.1550 1564.8093 2087.7444 2767.3623 3639.1890 5004.3447 6894.9658 10438.2754 17414.3672 31712.0605 | lr 3.4e-04 | norm 11861.0430 | dt 9.788 +type train | step 504 | loss 424.6945 835.1481 1114.5417 1557.2115 2081.7124 2762.3596 3648.5117 5033.5459 6959.5518 10570.0527 17583.7461 31932.7578 | lr 3.4e-04 | norm 11706.0371 | dt 9.798 +type train | step 505 | loss 442.4142 871.6021 1155.4091 1598.1149 2126.1377 2815.9319 3676.8479 5075.7754 6955.6758 10567.5684 17774.6387 33202.9141 | lr 3.4e-04 | norm 28569.9316 | dt 9.780 +type train | step 506 | loss 445.5984 875.0208 1152.1611 1601.9814 2131.4766 2835.9316 3714.7334 5079.1821 6938.7231 10423.6777 17415.2578 31931.8047 | lr 3.4e-04 | norm 12955.2197 | dt 9.798 +type train | step 507 | loss 404.0167 795.0577 1069.4235 1512.4843 2037.2576 2752.9600 3639.3965 5044.9604 6933.9585 10561.5586 17501.3867 32008.6621 | lr 3.4e-04 | norm 13202.1660 | dt 9.811 +type train | step 508 | loss 395.4645 777.0071 1045.3529 1472.1096 1982.6128 2644.1772 3503.9539 4834.4824 6736.9302 10220.7256 17092.1797 31379.1406 | lr 3.4e-04 | norm 13790.3760 | dt 9.806 +type train | step 509 | loss 392.9635 772.9859 1039.3093 1470.8000 1975.5861 2626.7256 3478.4001 4785.3667 6643.6348 10120.6328 16881.6875 30707.8047 | lr 3.4e-04 | norm 15170.0576 | dt 9.819 +type train | step 510 | loss 400.0348 786.2742 1055.7520 1493.9419 2005.4514 2664.7402 3526.3540 4850.9199 6746.4702 10295.0771 17250.3164 31182.8730 | lr 3.4e-04 | norm 13481.2471 | dt 9.842 +type train | step 511 | loss 404.1112 797.0980 1065.6759 1503.5167 2018.4803 2689.9617 3544.5288 4881.0942 6749.8271 10246.0625 17113.2109 31317.4648 | lr 3.4e-04 | norm 11958.2217 | dt 9.826 +type train | step 512 | loss 408.3788 800.7231 1075.2151 1513.2732 2031.7148 2707.5286 3573.5144 4925.0405 6847.1035 10362.6670 17322.3066 31518.5137 | lr 3.4e-04 | norm 11310.9961 | dt 9.800 +type train | step 513 | loss 406.0971 795.0264 1059.2380 1493.7068 2009.0953 2686.0027 3565.9561 4932.4473 6807.8423 10325.3330 17140.9609 30934.7539 | lr 3.4e-04 | norm 13053.5234 | dt 9.810 +type train | step 514 | loss 388.0174 758.5822 1023.7356 1449.0273 1958.3401 2607.4231 3457.3311 4769.3408 6627.8384 10091.6064 16903.7461 30616.0488 | lr 3.4e-04 | norm 10246.0615 | dt 9.807 +type train | step 515 | loss 382.7799 756.1818 1022.4401 1458.5327 1974.2878 2660.8271 3540.4639 4930.3521 6826.8062 10429.6348 17410.5723 31562.0176 | lr 3.4e-04 | norm 13528.1162 | dt 9.795 +type train | step 516 | loss 380.8099 748.4211 1005.6473 1425.3236 1923.3925 2575.8767 3416.1953 4714.7734 6560.7080 9986.2607 16697.5684 30341.7520 | lr 3.4e-04 | norm 9652.4453 | dt 9.801 +type train | step 517 | loss 486.6981 971.4888 1290.2393 1797.4393 2349.1252 3116.0076 4052.4180 5508.7256 7432.5073 10965.0078 17782.4980 31785.3828 | lr 3.4e-04 | norm 15477.2900 | dt 9.796 +type train | step 518 | loss 465.5169 923.2747 1227.3323 1704.0228 2246.4387 2994.2971 3913.2173 5387.4731 7304.4321 10908.9268 17988.9629 32778.8398 | lr 3.5e-04 | norm 22582.2871 | dt 9.800 +type train | step 519 | loss 408.4849 803.7477 1072.6488 1511.4734 2028.7689 2695.2092 3552.5488 4873.9761 6759.0122 10284.5400 17152.7324 31179.3340 | lr 3.5e-04 | norm 12136.7793 | dt 9.816 +type train | step 520 | loss 363.7470 724.7910 993.5417 1423.2893 1936.7970 2595.2751 3451.3872 4775.8120 6673.7886 10180.4824 17057.7617 30956.6973 | lr 3.5e-04 | norm 12340.2051 | dt 9.815 +type train | step 521 | loss 385.7349 754.8307 1017.0033 1446.4324 1943.7585 2610.8660 3467.9299 4814.4863 6687.5078 10162.6826 16926.8496 30912.6816 | lr 3.5e-04 | norm 13196.7686 | dt 9.803 +type train | step 522 | loss 408.9633 797.4169 1068.7623 1506.6324 2018.1018 2701.6201 3569.2061 4922.5332 6785.9653 10275.3164 17054.7539 31068.2520 | lr 3.5e-04 | norm 12456.3936 | dt 9.805 +type train | step 523 | loss 413.8590 803.5466 1073.5208 1505.6932 2001.0306 2662.6643 3515.3101 4843.7427 6718.3037 10271.3877 17384.9258 32269.0020 | lr 3.5e-04 | norm 15859.4512 | dt 9.792 +type train | step 524 | loss 385.2357 755.8121 1018.4343 1440.2206 1939.8522 2576.6240 3403.5486 4671.4028 6484.9702 9893.6318 16601.5996 30085.8379 | lr 3.5e-04 | norm 12439.9424 | dt 9.805 +type train | step 525 | loss 368.9228 720.5878 972.5391 1379.5101 1865.5833 2493.0942 3308.6782 4550.2227 6335.1895 9646.1406 16111.2363 29378.4629 | lr 3.5e-04 | norm 13393.9697 | dt 9.791 +type train | step 526 | loss 392.1454 770.5962 1032.3479 1459.6230 1955.9984 2629.4153 3471.8179 4796.2319 6662.6475 10138.6445 16934.8359 30848.9961 | lr 3.5e-04 | norm 15473.8828 | dt 9.809 +type train | step 527 | loss 391.0968 767.3099 1034.0181 1467.8569 1975.5791 2659.5286 3520.9900 4870.0786 6702.1914 10127.7480 16817.5117 30601.1641 | lr 3.5e-04 | norm 16127.0801 | dt 9.806 +type train | step 528 | loss 386.4374 762.2058 1030.6270 1461.2374 1975.0242 2641.9866 3507.5862 4858.4243 6725.3193 10298.6650 17214.5762 31140.9707 | lr 3.5e-04 | norm 17735.6172 | dt 9.811 +type train | step 529 | loss 382.2605 745.9815 999.8982 1419.9358 1915.9276 2573.3333 3418.8049 4752.0444 6602.1074 10052.9189 16761.0078 30598.8711 | lr 3.5e-04 | norm 13612.0654 | dt 9.806 +type train | step 530 | loss 396.3901 785.0364 1054.3925 1488.8567 1994.3859 2651.9172 3498.8752 4800.4287 6615.0352 10019.1572 16657.2871 30660.3457 | lr 3.5e-04 | norm 15128.1191 | dt 9.806 +type train | step 531 | loss 395.6210 771.9077 1030.6893 1446.5266 1944.1251 2597.0974 3457.7029 4778.3154 6600.9189 10133.9023 16864.0742 30278.6191 | lr 3.5e-04 | norm 33181.5938 | dt 9.810 +type train | step 532 | loss 385.9851 754.8369 1013.5177 1431.4954 1930.1898 2581.2209 3436.0757 4744.2959 6556.1343 10041.7412 16818.9648 30216.6406 | lr 3.5e-04 | norm 21820.7305 | dt 9.813 +type train | step 533 | loss 376.0765 739.4021 988.6454 1402.5807 1893.0900 2542.4353 3374.1426 4682.0112 6501.6919 10022.3896 16917.4277 31114.7129 | lr 3.6e-04 | norm 16235.1777 | dt 9.813 +type train | step 534 | loss 387.4833 756.7199 1015.2477 1431.1346 1928.8464 2600.4629 3441.4043 4777.0928 6550.0439 9892.7041 16458.4102 29937.7734 | lr 3.6e-04 | norm 13954.7197 | dt 9.804 +type train | step 535 | loss 383.1071 748.7642 1002.2866 1413.0807 1907.6588 2562.5903 3402.3501 4713.5034 6608.7246 10103.0439 16796.8262 30494.8379 | lr 3.6e-04 | norm 15894.3574 | dt 9.806 +type train | step 536 | loss 358.0359 707.7368 968.9180 1385.6620 1877.8801 2527.0696 3365.9900 4677.0376 6572.4077 9993.6426 16642.5703 30154.7891 | lr 3.6e-04 | norm 16039.7100 | dt 9.803 +type train | step 537 | loss 351.5416 696.8371 956.5417 1370.7018 1858.8062 2502.1316 3336.3955 4651.1123 6546.5723 9993.6699 16790.5996 30574.0898 | lr 3.6e-04 | norm 15270.6445 | dt 9.795 +type train | step 538 | loss 387.7007 758.2889 1028.4585 1461.7988 1961.7893 2636.5891 3484.7668 4837.7344 6626.0737 10173.2871 17281.5840 32365.0020 | lr 3.6e-04 | norm 32001.5938 | dt 9.805 +type train | step 539 | loss 388.9999 764.2430 1032.5223 1473.5640 1989.4070 2682.9001 3549.0039 4870.0283 6699.1533 10108.9785 16728.7559 30659.8457 | lr 3.6e-04 | norm 15008.5654 | dt 9.799 +type train | step 540 | loss 370.3116 725.0308 977.5867 1386.4543 1874.5135 2499.5952 3314.6873 4591.3750 6365.0566 9768.1191 16337.5830 29671.0742 | lr 3.6e-04 | norm 13619.1572 | dt 9.804 +type train | step 541 | loss 346.5160 676.8328 920.5370 1323.2864 1805.6639 2433.9548 3258.5464 4534.3809 6334.4126 9671.6680 16146.5576 29200.8613 | lr 3.6e-04 | norm 12700.5938 | dt 9.803 +type train | step 542 | loss 373.1269 727.8390 981.1334 1394.8248 1884.4779 2529.6035 3346.1838 4623.7100 6374.3931 9690.7773 16243.0752 29768.6191 | lr 3.6e-04 | norm 12145.9971 | dt 9.809 +type train | step 543 | loss 359.8579 709.2924 969.7844 1390.7988 1886.8699 2529.8093 3359.7451 4646.7344 6490.5635 9908.3506 16573.7363 29946.5742 | lr 3.6e-04 | norm 11940.8672 | dt 9.815 +type train | step 544 | loss 358.1959 700.0860 953.4718 1363.9127 1847.7639 2496.5764 3323.3867 4625.6587 6428.7275 9846.0156 16420.1562 30246.4375 | lr 3.6e-04 | norm 17497.7090 | dt 9.807 +type train | step 545 | loss 359.3676 705.6011 946.2667 1345.3153 1820.0344 2505.3472 3353.5334 4697.4492 6462.0942 9861.6924 16488.5605 30828.6973 | lr 3.6e-04 | norm 24189.7539 | dt 9.779 +type train | step 546 | loss 351.9620 689.0649 938.2462 1342.3326 1824.3727 2448.0613 3262.8198 4515.0928 6260.8374 9538.7822 15862.5498 28909.4316 | lr 3.6e-04 | norm 11055.0781 | dt 9.809 +type train | step 547 | loss 390.1699 762.8269 1017.8832 1439.9393 1925.3108 2593.4939 3434.4834 4760.6885 6511.3916 9911.7324 16481.4863 30644.6523 | lr 3.6e-04 | norm 19670.1934 | dt 9.803 +type train | step 548 | loss 346.0385 677.4855 923.5042 1322.8838 1794.1744 2411.4634 3217.7708 4461.7012 6220.8677 9506.4492 15871.2666 28898.7227 | lr 3.7e-04 | norm 11235.1504 | dt 9.801 +type train | step 549 | loss 351.7876 692.9859 940.2922 1344.2197 1828.3718 2460.0608 3265.1116 4520.1143 6262.6294 9578.2197 16017.6816 29433.4297 | lr 3.7e-04 | norm 12871.1660 | dt 9.796 +type train | step 550 | loss 365.7446 718.9623 966.7756 1368.7878 1852.5323 2473.5452 3276.8000 4533.6748 6301.5640 9610.3154 16122.5068 29387.2031 | lr 3.7e-04 | norm 11311.0762 | dt 9.815 +type train | step 551 | loss 328.1354 643.0663 880.7188 1270.0760 1739.4282 2347.9873 3143.8723 4352.9736 6106.3496 9331.5781 15635.8809 28352.1465 | lr 3.7e-04 | norm 10996.4775 | dt 9.804 +type train | step 552 | loss 338.4734 661.8862 903.5477 1296.4843 1763.8292 2373.2170 3165.9050 4378.9165 6118.7949 9398.2959 15728.9570 28551.3809 | lr 3.7e-04 | norm 11359.1953 | dt 9.819 +type train | step 553 | loss 346.6738 678.6688 925.5814 1325.9773 1805.4720 2424.3269 3220.8130 4447.5669 6208.0845 9492.0850 15820.2744 28617.1191 | lr 3.7e-04 | norm 9894.5537 | dt 9.811 +type train | step 554 | loss 331.7697 647.2062 877.4620 1261.3781 1727.1089 2347.9104 3158.4365 4434.6836 6219.1934 9549.2764 15966.2734 28968.7383 | lr 3.7e-04 | norm 11451.7783 | dt 9.805 +type train | step 555 | loss 348.6276 685.5454 935.5736 1342.1797 1811.8372 2432.1980 3231.0869 4465.0449 6225.8193 9486.7197 15957.7617 29393.6406 | lr 3.7e-04 | norm 11835.4883 | dt 9.797 +type train | step 556 | loss 340.7369 685.3607 938.1767 1343.0219 1823.1909 2447.2209 3253.4558 4532.9175 6389.3379 9880.9619 16805.4805 31263.7109 | lr 3.7e-04 | norm 19042.1367 | dt 9.799 +type train | step 557 | loss 331.4893 703.5146 972.9038 1393.2915 1895.4084 2534.2212 3327.8228 4690.5596 6732.9800 10492.5508 18159.1914 34260.9297 | lr 3.7e-04 | norm 45779.6250 | dt 9.789 +type train | step 558 | loss 332.3473 656.3593 899.4182 1288.6279 1759.1858 2369.2131 3160.5029 4376.2607 6119.9902 9355.6758 15682.5938 28528.5410 | lr 3.7e-04 | norm 11217.3887 | dt 9.799 +type train | step 559 | loss 349.1590 684.8644 927.9838 1322.6631 1789.4650 2410.6687 3211.2520 4452.5767 6202.0151 9494.2559 15942.5020 29132.0430 | lr 3.7e-04 | norm 12283.7852 | dt 9.804 +type train | step 560 | loss 350.3643 686.5663 922.2984 1312.4127 1779.0790 2407.7014 3212.8984 4456.9194 6159.8765 9391.2705 15660.8281 28874.1016 | lr 3.7e-04 | norm 13433.0859 | dt 9.794 +type train | step 561 | loss 337.1425 657.1763 889.7098 1276.0232 1737.7084 2352.3950 3138.1843 4343.4360 6056.4468 9274.0117 15539.9160 28568.9980 | lr 3.7e-04 | norm 12607.7178 | dt 9.795 +type train | step 562 | loss 341.7288 672.3906 922.4711 1330.1163 1816.0134 2456.1631 3281.3171 4568.4248 6363.5098 9770.4082 16376.1465 30030.2227 | lr 3.7e-04 | norm 13951.7285 | dt 9.811 +type train | step 563 | loss 332.5908 651.9076 895.8154 1286.9515 1760.2021 2368.9883 3165.6289 4413.2935 6179.9385 9469.1670 15876.7705 28904.6113 | lr 3.8e-04 | norm 13908.1152 | dt 9.809 +type train | step 564 | loss 313.4786 613.1726 846.7943 1229.9070 1687.4934 2287.2896 3065.3250 4262.8584 5999.5020 9183.3711 15378.2656 27840.1504 | lr 3.8e-04 | norm 11312.1963 | dt 9.808 +type train | step 565 | loss 330.8791 644.0435 880.6663 1270.3413 1736.3060 2344.8311 3134.0813 4344.1514 6043.5757 9264.7178 15526.2773 28317.4336 | lr 3.8e-04 | norm 10861.1250 | dt 9.805 +type train | step 566 | loss 335.6407 652.3414 885.5375 1267.5854 1721.9042 2326.0159 3105.7898 4312.8940 6006.9595 9227.4824 15394.6445 28187.7344 | lr 3.8e-04 | norm 11804.4795 | dt 9.805 +type train | step 567 | loss 327.4259 641.0163 873.3436 1255.3914 1709.7585 2299.5830 3066.2703 4263.2109 5974.9561 9148.9893 15227.0371 27627.3086 | lr 3.8e-04 | norm 11891.9424 | dt 9.814 +type train | step 568 | loss 319.0511 620.9635 849.0662 1226.7742 1672.6250 2266.3540 3027.7654 4221.4180 5899.9424 9083.0107 15383.1357 28498.3828 | lr 3.8e-04 | norm 11440.3506 | dt 9.789 +type train | step 569 | loss 341.4929 667.2274 906.7357 1299.3225 1760.9548 2366.7356 3143.4966 4345.3838 6026.0688 9221.7529 15518.0205 28590.0078 | lr 3.8e-04 | norm 12630.8057 | dt 9.807 +type train | step 570 | loss 331.6074 649.3368 879.4988 1264.2407 1723.0250 2334.5356 3121.6802 4333.8579 6004.9814 9207.8252 15398.5010 28556.7949 | lr 3.8e-04 | norm 15790.2871 | dt 9.793 +type train | step 571 | loss 341.6119 665.7495 897.8720 1276.2534 1732.5956 2335.3857 3103.0920 4299.4277 5962.6611 9147.1992 15249.7666 27972.1445 | lr 3.8e-04 | norm 11197.1533 | dt 9.811 +type train | step 572 | loss 325.8825 637.8618 870.1844 1247.7629 1695.6403 2291.6702 3058.0981 4251.0669 5902.0239 9024.3652 15165.8379 27776.7441 | lr 3.8e-04 | norm 10921.6465 | dt 9.812 +type train | step 573 | loss 327.2515 639.4503 872.5198 1257.0148 1718.0410 2325.9236 3092.9377 4272.2505 5955.4351 9104.0312 15273.5869 28051.3906 | lr 3.8e-04 | norm 12092.1973 | dt 9.804 +type train | step 574 | loss 321.5302 630.0248 860.8794 1237.6311 1698.5760 2296.7798 3075.4746 4281.7241 6012.3682 9250.3184 15428.2070 27972.8203 | lr 3.8e-04 | norm 12687.2129 | dt 9.812 +type train | step 575 | loss 319.2953 623.8130 856.9341 1236.7179 1695.9590 2298.5200 3057.9697 4234.7422 5884.5156 9000.8105 15056.4238 27722.4922 | lr 3.8e-04 | norm 10876.3369 | dt 9.806 +type train | step 576 | loss 337.0091 660.1719 897.9963 1280.9625 1733.5880 2342.0356 3114.9624 4324.9946 6014.7266 9228.2578 15538.6621 28697.3301 | lr 3.8e-04 | norm 14127.1289 | dt 9.810 +type train | step 577 | loss 311.5263 610.8190 835.6055 1206.8379 1652.2802 2237.5586 3004.1011 4179.6362 5829.0322 8923.5117 14870.5654 26933.1055 | lr 3.8e-04 | norm 12786.1016 | dt 9.800 +type train | step 578 | loss 326.8901 637.9961 869.7759 1247.0370 1704.5756 2278.8149 3033.9902 4187.4268 5850.4844 8922.6367 14927.2617 27156.7480 | lr 3.9e-04 | norm 11424.2070 | dt 9.802 +type train | step 579 | loss 313.3152 608.8129 835.5504 1210.5779 1664.5061 2259.9380 3046.7900 4265.0806 5957.6309 9148.8643 15227.9980 27393.0469 | lr 3.9e-04 | norm 11614.3721 | dt 9.809 +type train | step 580 | loss 339.3048 662.5187 900.5718 1281.8381 1744.0554 2337.8430 3111.5659 4306.7686 5999.1748 9143.3955 15210.4082 27694.9102 | lr 3.9e-04 | norm 16699.6562 | dt 9.811 +type train | step 581 | loss 327.4193 644.4182 882.8378 1268.5031 1723.4038 2333.3293 3108.5879 4316.7783 5990.9409 9164.6973 15277.8203 27948.6328 | lr 3.9e-04 | norm 12501.4365 | dt 9.809 +type train | step 582 | loss 319.0077 627.0958 854.0345 1226.3627 1677.8545 2280.2188 3050.4983 4264.2109 5902.7100 9064.8975 15183.4121 27897.5879 | lr 3.9e-04 | norm 10808.1084 | dt 9.803 +type train | step 583 | loss 329.4767 647.2103 878.1443 1257.6129 1711.6744 2322.0884 3098.5366 4303.3677 5962.7754 9105.2939 15127.6006 27504.8086 | lr 3.9e-04 | norm 9722.7295 | dt 9.813 +type train | step 584 | loss 315.4181 622.2606 857.3634 1240.3000 1698.9039 2327.4766 3138.0417 4395.1519 6114.9448 9407.0234 15708.1777 28557.5234 | lr 3.9e-04 | norm 10962.8613 | dt 9.801 +type train | step 585 | loss 354.6193 697.0198 946.6558 1349.1296 1840.2773 2477.7134 3286.9875 4550.7324 6232.5952 9524.0918 15776.5938 28868.8770 | lr 3.9e-04 | norm 15962.4307 | dt 9.814 +type train | step 586 | loss 325.2105 637.6517 872.0658 1255.7559 1710.7406 2320.4971 3108.9185 4349.3623 6046.7007 9285.3105 15516.3242 28267.6387 | lr 3.9e-04 | norm 15268.9639 | dt 9.803 +type train | step 587 | loss 316.8460 622.0490 848.4503 1224.9144 1677.1516 2272.3604 3048.2786 4252.1470 5953.6831 9157.0488 15324.4941 27889.0020 | lr 3.9e-04 | norm 11465.4121 | dt 9.820 +type train | step 588 | loss 319.5678 629.1600 857.9123 1233.8137 1681.6517 2301.0605 3090.5156 4349.3882 6039.8511 9250.1064 15481.7910 28358.5332 | lr 3.9e-04 | norm 12184.6299 | dt 9.823 +type train | step 589 | loss 310.6210 606.8576 827.2107 1194.4620 1645.8027 2234.7354 3001.0825 4193.6074 5848.8726 8973.8682 14946.9590 27077.0059 | lr 3.9e-04 | norm 12918.2373 | dt 9.808 +type train | step 590 | loss 310.0836 607.5946 830.6261 1206.3875 1655.2096 2263.2559 3042.4365 4270.0459 5956.3442 9223.2412 15493.8867 28456.4062 | lr 3.9e-04 | norm 14289.8623 | dt 9.804 +type train | step 591 | loss 307.3993 601.3992 825.2602 1198.8606 1647.0723 2242.9365 2995.1631 4161.3872 5744.2974 8759.8408 14498.5088 26636.1992 | lr 3.9e-04 | norm 14289.1201 | dt 9.810 +type train | step 592 | loss 299.9921 591.0967 815.1111 1180.2175 1610.9690 2197.9482 2960.0850 4156.7407 5819.1494 8955.8447 14999.0088 27477.8008 | lr 3.9e-04 | norm 11700.6611 | dt 9.811 +type train | step 593 | loss 307.5919 602.4040 829.9906 1201.3568 1648.5964 2250.3462 3031.2227 4240.9199 5908.4160 9057.2441 14989.5283 27203.9766 | lr 4.0e-04 | norm 11407.6055 | dt 9.820 +type train | step 594 | loss 301.5105 592.5714 819.6661 1187.2726 1627.0248 2216.5054 2986.2529 4185.4004 5850.6162 9008.2676 15160.8525 27729.6387 | lr 4.0e-04 | norm 11958.2080 | dt 9.828 +type train | step 595 | loss 310.4803 606.6265 823.2311 1179.3586 1618.4337 2189.0105 2920.0508 4058.3389 5663.1426 8728.3633 14600.7090 26540.5176 | lr 4.0e-04 | norm 11576.0557 | dt 9.820 +type train | step 596 | loss 301.8381 591.3105 816.9796 1182.3156 1623.7430 2209.4905 2965.2537 4143.7632 5764.3213 8915.7793 14970.3096 27316.5234 | lr 4.0e-04 | norm 10640.3594 | dt 9.823 +type train | step 597 | loss 301.7907 588.5367 804.4056 1156.7616 1591.1682 2184.0730 2945.3296 4130.3286 5771.8896 8926.5029 14930.7656 27256.4297 | lr 4.0e-04 | norm 10266.6641 | dt 9.818 +type train | step 598 | loss 297.0988 577.4037 788.8815 1138.0502 1557.8375 2111.6389 2820.5059 3911.2317 5489.9907 8481.1221 14351.5410 26381.0352 | lr 4.0e-04 | norm 10397.1904 | dt 9.791 +type train | step 599 | loss 281.7325 546.0345 754.2917 1100.1993 1518.8981 2072.2812 2800.1792 3956.6833 5544.3857 8508.9443 14075.6699 25440.5723 | lr 4.0e-04 | norm 16240.6484 | dt 9.801 +type train | step 600 | loss 289.9316 568.4343 783.4362 1138.3334 1573.7826 2166.6907 2934.2051 4134.4355 5813.4463 8948.8398 14943.8193 27144.3457 | lr 4.0e-04 | norm 11419.2236 | dt 9.799 +type train | step 601 | loss 333.0677 652.5061 888.9255 1272.3953 1724.0938 2371.6472 3164.7839 4441.8374 6087.1284 9254.4053 15272.8711 27896.6543 | lr 4.0e-04 | norm 14147.1396 | dt 9.816 +type train | step 602 | loss 302.1083 598.6720 830.2004 1201.4663 1655.3240 2277.3120 3058.1572 4310.2661 6020.1240 9216.0225 15424.4414 28673.8613 | lr 4.0e-04 | norm 14381.3447 | dt 9.809 +type train | step 603 | loss 308.4189 604.4344 827.5826 1193.9738 1640.3109 2247.6165 3024.3035 4240.7759 5891.7393 9005.3389 14969.6729 27326.6289 | lr 4.0e-04 | norm 11584.0566 | dt 9.818 +type train | step 604 | loss 314.0201 616.7161 840.0884 1212.5436 1649.2520 2251.1331 3005.3208 4184.5713 5817.4824 8934.7930 14986.8613 27620.6719 | lr 4.0e-04 | norm 14147.5879 | dt 9.799 +type train | step 605 | loss 278.4492 541.3828 746.2139 1086.9883 1504.7194 2057.9443 2775.4438 3892.6323 5487.4980 8489.3086 14250.6406 26014.6602 | lr 4.0e-04 | norm 10243.8574 | dt 9.806 +type train | step 606 | loss 277.8303 546.9017 759.0339 1105.8203 1528.6206 2082.4688 2812.1709 3943.7754 5563.7065 8578.2480 14336.2617 26002.4629 | lr 4.0e-04 | norm 10300.0303 | dt 9.815 +type train | step 607 | loss 296.4192 579.5569 793.2500 1145.3451 1570.7539 2149.3130 2881.9524 4036.7051 5641.2290 8684.1201 14549.3320 26941.2363 | lr 4.0e-04 | norm 9415.8135 | dt 9.823 +type train | step 608 | loss 300.0113 590.5905 814.3196 1184.0570 1623.0334 2227.7229 2994.8130 4209.5308 5868.7808 9027.1934 15068.1660 27660.4355 | lr 4.1e-04 | norm 11191.7207 | dt 9.793 +type train | step 609 | loss 270.5114 527.7837 729.3581 1070.8391 1491.0007 2073.4375 2815.4707 3977.8479 5593.8438 8663.7939 14476.9238 26442.5469 | lr 4.1e-04 | norm 12804.0039 | dt 9.816 +type train | step 610 | loss 246.9753 479.4568 670.3802 1002.8661 1418.0482 2003.6051 2736.5129 3914.1541 5465.6426 8448.5303 13955.7461 25436.0039 | lr 4.1e-04 | norm 22560.7285 | dt 9.783 +type train | step 611 | loss 266.2065 514.0740 710.8099 1041.4480 1452.6619 2023.7697 2737.8330 3871.0803 5393.0508 8387.0127 13962.9111 25582.1172 | lr 4.1e-04 | norm 23409.6641 | dt 9.795 +type train | step 612 | loss 290.2214 567.7666 777.9153 1130.4924 1563.2434 2176.4351 2934.9062 4144.5811 5754.6694 8818.1084 14598.2480 26830.6641 | lr 4.1e-04 | norm 13947.5879 | dt 9.791 +type train | step 613 | loss 285.2002 559.2175 766.7979 1104.5081 1519.3583 2070.4219 2780.6001 3908.8301 5461.9463 8429.9102 14140.4150 26343.8613 | lr 4.1e-04 | norm 16325.1611 | dt 9.792 +type train | step 614 | loss 280.1574 552.0993 756.2247 1095.7461 1510.3766 2057.3364 2769.8867 3876.9775 5436.0093 8413.2617 14169.9355 26059.5508 | lr 4.1e-04 | norm 14701.3291 | dt 9.812 +type train | step 615 | loss 298.9924 589.7518 805.9302 1172.4358 1607.3092 2234.1853 3008.8235 4289.7334 5906.8931 8981.8232 15097.1592 28709.3535 | lr 4.1e-04 | norm 19517.7637 | dt 9.793 +type train | step 616 | loss 280.1349 544.0983 757.3547 1101.5836 1525.2660 2076.0430 2788.1958 3893.3684 5465.9126 8414.7598 14115.4824 25849.8027 | lr 4.1e-04 | norm 15406.0938 | dt 9.806 +type train | step 617 | loss 277.3507 542.5004 750.6950 1092.1226 1512.6096 2088.0933 2830.5952 4013.3027 5598.9336 8658.2471 14427.0771 26272.1016 | lr 4.1e-04 | norm 14135.9141 | dt 9.818 +type train | step 618 | loss 291.3268 568.8205 777.9643 1130.4421 1552.7452 2130.0901 2866.1882 4021.0034 5574.1206 8630.5068 14475.3271 26566.3516 | lr 4.1e-04 | norm 14877.2314 | dt 9.808 +type train | step 619 | loss 263.3694 525.1309 745.7197 1102.9584 1525.8250 2100.2583 2843.4558 4046.5728 5692.5991 8905.7842 14996.6475 27667.6934 | lr 4.1e-04 | norm 17077.0371 | dt 9.800 +type train | step 620 | loss 310.9996 606.0049 821.3060 1175.4540 1603.5326 2186.3523 2919.5608 4108.5596 5652.9414 8710.4844 14613.8271 27107.1367 | lr 4.1e-04 | norm 12001.1045 | dt 9.809 +type train | step 621 | loss 300.1328 588.0906 805.5615 1160.3015 1583.9915 2157.7427 2887.2852 4059.5293 5585.9351 8580.0195 14363.1387 26550.4219 | lr 4.1e-04 | norm 13284.4424 | dt 9.817 +type train | step 622 | loss 298.5357 584.4333 799.6981 1150.4706 1575.9183 2152.3872 2880.6787 4059.3240 5596.5195 8633.6523 14385.1162 26326.1465 | lr 4.1e-04 | norm 14225.8945 | dt 9.817 +type train | step 623 | loss 309.6786 609.3569 840.1319 1207.9943 1654.5311 2243.2690 3003.7732 4204.9263 5753.2705 8783.2041 14650.0615 26922.2363 | lr 4.2e-04 | norm 15438.4072 | dt 9.807 +type train | step 624 | loss 290.8282 569.8713 779.6715 1127.9877 1548.4293 2115.3386 2845.7139 4030.9011 5580.6572 8560.6553 14268.8164 26180.8145 | lr 4.2e-04 | norm 12930.8154 | dt 9.818 +type train | step 625 | loss 259.6705 509.0517 712.8623 1059.2009 1477.6993 2035.6730 2761.5242 3944.6392 5543.1421 8656.2344 14603.2305 27037.1406 | lr 4.2e-04 | norm 18213.4023 | dt 9.805 +type train | step 626 | loss 287.9868 567.7755 788.8665 1143.0422 1566.5719 2131.3086 2845.2947 4025.8545 5515.9600 8496.9590 14235.9219 26040.6172 | lr 4.2e-04 | norm 13143.8066 | dt 9.799 +type train | step 627 | loss 297.4787 580.6248 797.1009 1143.2592 1570.5646 2123.0808 2836.4575 4011.0603 5523.1758 8547.1768 14308.6309 26095.8730 | lr 4.2e-04 | norm 13125.2900 | dt 9.827 +type train | step 628 | loss 283.8181 552.7648 760.5043 1106.5436 1530.2361 2099.8916 2826.2715 4011.2012 5539.9536 8500.5918 14144.0791 25656.9062 | lr 4.2e-04 | norm 11833.4141 | dt 9.823 +type train | step 629 | loss 271.2285 535.8633 741.5869 1085.3262 1502.5969 2070.5046 2809.5388 4023.6812 5548.5698 8583.8545 14355.2422 26308.8691 | lr 4.2e-04 | norm 11408.9961 | dt 9.806 +type train | step 630 | loss 300.5902 593.9731 818.7997 1180.7372 1622.9238 2230.7886 2978.8669 4257.7798 5797.7427 8839.4307 14521.0645 26957.0742 | lr 4.2e-04 | norm 14177.0215 | dt 9.802 +type train | step 631 | loss 289.0502 564.3512 778.4021 1129.2124 1551.2141 2110.3330 2833.2314 4001.5864 5514.7188 8490.1045 14150.0957 25809.3711 | lr 4.2e-04 | norm 9961.0146 | dt 9.810 +type train | step 632 | loss 292.9688 571.3948 796.1084 1153.1876 1583.2706 2153.2463 2896.6077 4105.7466 5697.6890 8859.3604 14911.1514 27374.2246 | lr 4.2e-04 | norm 15679.2646 | dt 9.808 +type train | step 633 | loss 292.3526 573.2833 788.6641 1139.3811 1566.2340 2127.2244 2847.6860 4004.7327 5505.2041 8459.8936 14114.0576 25922.2285 | lr 4.2e-04 | norm 11252.0723 | dt 9.810 +type train | step 634 | loss 286.6721 561.9134 774.0197 1125.6592 1546.2981 2107.8064 2830.9617 4007.6538 5544.7524 8568.1074 14313.7959 26296.8359 | lr 4.2e-04 | norm 10205.2266 | dt 9.807 +type train | step 635 | loss 284.6956 561.9075 773.4086 1125.8927 1547.2552 2117.4631 2832.4395 3984.2000 5501.7314 8485.9941 14234.2930 26581.4434 | lr 4.2e-04 | norm 14811.7637 | dt 9.816 +type train | step 636 | loss 288.5741 562.4809 772.4116 1119.7422 1537.8566 2129.3311 2870.2654 4082.6870 5610.5918 8555.0830 14139.8916 25898.5664 | lr 4.2e-04 | norm 10249.5674 | dt 9.817 +type train | step 637 | loss 272.6800 536.5422 739.7516 1071.5377 1484.5112 2034.1239 2736.3665 3872.1655 5371.9575 8297.5234 13914.8652 25587.0566 | lr 4.2e-04 | norm 10988.4609 | dt 9.808 +type train | step 638 | loss 269.6457 526.0856 724.9648 1059.4790 1469.5107 2026.7346 2734.6812 3912.0349 5447.9502 8426.8145 14104.1699 25862.2344 | lr 4.3e-04 | norm 10237.3535 | dt 9.803 +type train | step 639 | loss 289.5794 569.4428 782.0125 1126.3005 1560.5608 2116.1934 2832.5271 4013.9941 5546.2656 8503.9707 14209.4355 26091.7168 | lr 4.3e-04 | norm 10956.6660 | dt 9.830 +type train | step 640 | loss 334.0922 647.7921 861.5898 1218.7849 1649.7959 2213.3628 2915.1382 4018.1826 5440.1362 8292.1016 13710.6309 25575.3477 | lr 4.3e-04 | norm 14436.1592 | dt 9.796 +type train | step 641 | loss 295.3622 581.0894 795.1610 1149.1600 1577.4592 2162.1160 2902.0979 4111.2646 5620.3506 8674.5391 14498.2559 26502.4824 | lr 4.3e-04 | norm 9698.5264 | dt 9.811 +type train | step 642 | loss 273.8551 533.0321 737.4796 1071.7701 1482.6636 2012.9442 2698.4585 3794.8755 5274.2046 8165.7148 13665.1797 25027.1465 | lr 4.3e-04 | norm 9639.5166 | dt 9.863 +type train | step 643 | loss 278.2855 545.5660 755.0154 1096.8981 1508.4169 2063.8552 2771.2588 3906.9536 5431.2061 8413.0078 14058.1572 25683.0195 | lr 4.3e-04 | norm 9893.7109 | dt 9.832 +type train | step 644 | loss 239.5814 468.0774 656.4575 972.9178 1378.3927 1906.7882 2620.4651 3800.1628 5314.7036 8293.6406 13792.9336 25257.0410 | lr 4.3e-04 | norm 15244.7910 | dt 9.816 +type train | step 645 | loss 254.2565 493.8717 685.8726 1007.7684 1406.6145 1945.7965 2647.9060 3794.8423 5278.1616 8231.5010 13766.4062 25196.7090 | lr 4.3e-04 | norm 10187.1699 | dt 9.818 +type train | step 646 | loss 270.1180 530.4150 733.3336 1065.4131 1482.1943 2016.8865 2710.5522 3820.6138 5302.0142 8198.6738 13704.4414 25224.8164 | lr 4.3e-04 | norm 8902.0293 | dt 9.831 +type train | step 647 | loss 268.6560 529.7822 735.4150 1078.8429 1500.3314 2081.1406 2811.3359 4026.3423 5566.8130 8527.9014 14127.2822 26066.2852 | lr 4.3e-04 | norm 10867.4873 | dt 9.815 +type train | step 648 | loss 293.5492 572.3817 782.1933 1125.2698 1539.2123 2113.0237 2812.6318 3978.6243 5426.3408 8345.0518 13949.2578 26118.8047 | lr 4.3e-04 | norm 14411.9463 | dt 9.808 +type train | step 649 | loss 285.9803 557.4735 763.4778 1101.8278 1503.2792 2067.9272 2784.9583 3969.1921 5499.5576 8502.2812 14171.0000 26078.6113 | lr 4.3e-04 | norm 12267.7910 | dt 9.824 +type train | step 650 | loss 287.2563 559.8847 766.9957 1106.3247 1519.1011 2079.0359 2792.9729 3942.0576 5410.4502 8327.1797 13919.6553 25693.3320 | lr 4.3e-04 | norm 11461.6494 | dt 9.815 +type train | step 651 | loss 272.1753 531.7222 726.8747 1055.3123 1455.8009 1994.5599 2691.4792 3809.7566 5270.7441 8171.5723 13787.1572 25242.3086 | lr 4.3e-04 | norm 11512.5352 | dt 9.813 +type train | step 652 | loss 277.9634 542.2712 744.9263 1078.0747 1490.6050 2043.6636 2753.8418 3919.9250 5414.1396 8345.2822 13960.4658 25675.4434 | lr 4.3e-04 | norm 12012.2148 | dt 9.820 +type train | step 653 | loss 271.9470 529.5013 731.0781 1065.8442 1492.6108 2034.2350 2734.2341 3870.0325 5372.3955 8295.2354 13784.3721 25366.3965 | lr 4.4e-04 | norm 13724.4648 | dt 9.829 +type train | step 654 | loss 267.6028 525.3110 735.0872 1073.0609 1481.8533 2029.6869 2729.9346 3861.4561 5377.1108 8360.7109 14004.1270 25788.7480 | lr 4.4e-04 | norm 12053.6357 | dt 9.797 +type train | step 655 | loss 261.6838 511.2733 703.0861 1025.7777 1419.9878 1964.0453 2657.0466 3783.1870 5268.3213 8170.6919 13701.3301 25316.2656 | lr 4.4e-04 | norm 11007.8125 | dt 9.806 +type train | step 656 | loss 264.3679 513.0909 708.4654 1033.1348 1423.2330 1962.2399 2648.4290 3753.4607 5226.6953 8141.9443 13738.0156 25458.3613 | lr 4.4e-04 | norm 9939.0869 | dt 9.816 +type train | step 657 | loss 261.5953 509.5247 702.5471 1021.3395 1420.9049 1943.3378 2618.9138 3701.2939 5148.1797 7942.3008 13249.7588 24177.3184 | lr 4.4e-04 | norm 9926.2129 | dt 9.819 +type train | step 658 | loss 253.1570 493.3199 688.9568 1011.9451 1413.0377 1946.1549 2633.1636 3725.9399 5191.1128 8039.9580 13463.1621 24719.8477 | lr 4.4e-04 | norm 9280.2529 | dt 9.815 +type train | step 659 | loss 258.1044 505.8318 712.5028 1048.4241 1448.3300 2015.4418 2724.1450 3887.7329 5400.8672 8385.7021 14085.7930 26265.4668 | lr 4.4e-04 | norm 15153.1367 | dt 9.801 +type train | step 660 | loss 248.5201 484.2993 676.5674 998.8527 1410.7246 1928.3558 2606.5249 3682.6375 5192.8853 8120.1304 13614.8105 25045.3320 | lr 4.4e-04 | norm 11088.1211 | dt 9.825 +type train | step 661 | loss 271.2130 527.8489 730.6265 1063.9586 1477.6213 2031.8533 2736.7886 3873.6221 5395.7573 8358.5654 13991.5459 25571.4883 | lr 4.4e-04 | norm 11809.2295 | dt 9.820 +type train | step 662 | loss 279.6495 542.7121 745.7145 1076.1475 1478.8827 2013.9504 2697.0747 3785.8533 5213.8359 8009.0571 13452.6777 24948.9863 | lr 4.4e-04 | norm 13019.2979 | dt 9.813 +type train | step 663 | loss 255.4857 497.2973 691.2145 1011.9397 1409.6293 1926.2760 2596.8752 3659.6467 5132.4819 7980.4072 13388.9482 24559.2168 | lr 4.4e-04 | norm 10256.7051 | dt 9.822 +type train | step 664 | loss 260.6543 505.7696 699.5635 1018.5338 1416.3987 1929.9800 2596.9011 3667.9609 5085.7612 7864.7324 13187.6123 24510.6602 | lr 4.4e-04 | norm 11991.4453 | dt 9.806 +type train | step 665 | loss 256.8224 503.5476 699.2304 1023.4809 1420.5253 1961.2264 2644.1714 3753.7974 5213.2246 8079.7158 13502.9277 24988.8711 | lr 4.4e-04 | norm 11012.1055 | dt 9.807 +type train | step 666 | loss 263.0231 519.0414 706.3791 1022.6609 1415.6500 1984.7489 2682.3643 3854.9805 5279.0122 8227.7432 13910.7383 26814.3105 | lr 4.4e-04 | norm 30135.5938 | dt 9.794 +type train | step 667 | loss 259.1411 507.3374 703.6025 1021.7531 1423.3455 1949.1152 2621.2192 3708.4475 5145.5596 7957.5527 13313.7168 24574.7773 | lr 4.4e-04 | norm 10276.6455 | dt 9.846 +type train | step 668 | loss 257.2609 503.0531 696.2715 1018.1823 1420.0192 1967.1891 2674.5134 3796.3823 5296.1196 8236.1875 13709.2812 25300.3145 | lr 4.5e-04 | norm 14408.3535 | dt 9.826 +type train | step 669 | loss 263.5649 510.4241 702.5884 1017.5900 1410.6299 1948.3053 2619.6199 3709.8735 5161.3564 7993.9424 13326.6201 24566.5176 | lr 4.5e-04 | norm 11275.6074 | dt 9.812 +type train | step 670 | loss 253.2768 493.3199 684.5186 1000.5798 1398.3881 1902.7346 2561.1602 3613.3987 5046.2451 7817.4531 13097.9805 24202.8320 | lr 4.5e-04 | norm 11143.4258 | dt 9.835 +type train | step 671 | loss 254.5720 514.4105 725.7918 1076.9233 1496.8055 2037.5105 2739.6855 3869.1108 5384.9727 8360.3350 14032.1250 26633.2441 | lr 4.5e-04 | norm 21832.0586 | dt 9.819 +type train | step 672 | loss 267.9155 537.6653 757.0822 1125.6714 1547.8322 2123.6621 2847.2786 4012.1716 5558.3008 8572.9951 14258.4102 26659.0547 | lr 4.5e-04 | norm 28021.6641 | dt 9.802 +type train | step 673 | loss 252.6454 494.2577 686.6472 1005.2158 1405.0010 1913.5190 2572.6768 3648.2573 5098.0557 7935.8027 13333.7002 24972.3125 | lr 4.5e-04 | norm 11652.9307 | dt 9.819 +type train | step 674 | loss 237.1924 462.3959 650.5478 963.6113 1365.3094 1872.4924 2538.6826 3595.9651 5041.6152 7830.0942 13112.3740 24331.5332 | lr 4.5e-04 | norm 12427.9863 | dt 9.803 +type train | step 675 | loss 250.9080 489.7567 680.6484 995.0510 1401.4197 1902.0850 2564.9819 3629.8240 5079.1973 7881.0864 13185.9082 24413.3242 | lr 4.5e-04 | norm 12456.8516 | dt 9.814 +type train | step 676 | loss 251.0045 487.9925 671.5952 977.3159 1376.1665 1853.5243 2504.8625 3539.9822 4949.8164 7701.3799 12946.8408 23989.9629 | lr 4.5e-04 | norm 12356.6973 | dt 9.823 +type train | step 677 | loss 247.1749 481.1547 668.0612 976.9365 1376.9382 1875.8818 2526.2444 3573.9866 5009.5859 7832.1265 13150.1738 24509.1934 | lr 4.5e-04 | norm 11690.7197 | dt 9.816 +type train | step 678 | loss 262.3052 513.7106 708.3254 1030.4048 1440.4470 1968.2971 2653.9148 3760.2278 5189.8970 8014.4741 13279.2734 24501.6445 | lr 4.5e-04 | norm 12934.7861 | dt 9.816 +type train | step 679 | loss 252.6257 494.9946 692.6072 1013.7904 1435.0767 1941.0828 2616.5796 3709.0979 5165.5884 7985.2554 13303.2568 24375.3438 | lr 4.5e-04 | norm 10798.8848 | dt 9.840 +type train | step 680 | loss 259.0792 509.4126 710.2590 1036.6919 1449.6631 1951.1788 2622.0842 3705.1169 5168.4814 8001.7686 13387.2090 24585.9492 | lr 4.5e-04 | norm 10257.2627 | dt 9.816 +type train | step 681 | loss 258.3666 502.0171 702.4648 1026.4248 1446.7025 1944.7351 2619.8848 3691.9539 5149.1528 8021.0459 13462.0879 24746.6035 | lr 4.5e-04 | norm 10918.8730 | dt 9.828 +type train | step 682 | loss 252.1954 489.2456 677.3977 990.4637 1398.6074 1902.6953 2566.0298 3630.1995 5046.9238 7845.1211 13128.9688 24145.6211 | lr 4.5e-04 | norm 9596.6357 | dt 9.823 +type train | step 683 | loss 245.5135 477.7909 664.0157 968.3354 1368.8516 1848.8625 2497.5774 3538.3674 4952.5439 7736.5259 12987.1484 23840.7852 | lr 4.6e-04 | norm 10591.9805 | dt 9.822 +type train | step 684 | loss 246.3421 482.9601 672.2302 983.5171 1402.1309 1912.4950 2594.2288 3690.7915 5132.4912 7952.4824 13320.8857 24632.3281 | lr 4.6e-04 | norm 12028.8945 | dt 9.823 +type train | step 685 | loss 240.1073 467.7131 652.0911 961.9287 1363.8160 1892.8186 2580.5291 3704.3762 5120.0591 7969.1562 13488.7012 24985.4590 | lr 4.6e-04 | norm 13056.7441 | dt 9.823 +type train | step 686 | loss 231.8536 454.4483 643.7511 953.9418 1350.4089 1852.5349 2523.4182 3609.4307 5081.9751 7910.6240 13258.8955 24401.8906 | lr 4.6e-04 | norm 10154.4180 | dt 9.820 +type train | step 687 | loss 249.3843 486.5248 672.6429 982.3893 1400.5503 1885.3529 2552.8430 3628.1421 5064.6431 7894.0273 13231.0098 24377.9102 | lr 4.6e-04 | norm 10171.6289 | dt 9.820 +type train | step 688 | loss 251.3423 487.1833 665.4887 964.9174 1360.3901 1842.7277 2510.5210 3582.5762 5001.8037 7773.9375 12945.4932 23587.7910 | lr 4.6e-04 | norm 9934.1240 | dt 9.823 +type train | step 689 | loss 250.6755 486.0154 675.4617 987.3375 1388.0239 1887.5874 2546.8555 3593.1584 5020.3135 7808.3477 13091.4678 24082.4727 | lr 4.6e-04 | norm 9876.7227 | dt 9.825 +type train | step 690 | loss 253.6252 506.3001 707.0504 1039.3804 1449.3407 1974.4963 2645.0986 3747.5249 5271.2583 8159.7910 13786.1289 25671.4316 | lr 4.6e-04 | norm 13116.7002 | dt 9.820 +type train | step 691 | loss 235.9988 460.8584 642.5178 949.1701 1361.4196 1862.1920 2528.3899 3613.9597 5065.3584 7898.0474 13211.9160 24308.9648 | lr 4.6e-04 | norm 10880.0811 | dt 9.814 +type train | step 692 | loss 256.8031 499.6234 690.8505 1006.1855 1429.6812 1911.8000 2557.5884 3610.6721 4988.3887 7686.9756 12908.6797 24253.2832 | lr 4.6e-04 | norm 12822.8643 | dt 9.822 +type train | step 693 | loss 252.8329 490.5384 676.9892 983.8710 1380.6039 1889.5203 2546.7200 3621.1941 5025.7358 7781.0312 13069.3857 24323.0352 | lr 4.6e-04 | norm 11443.9092 | dt 9.809 +type train | step 694 | loss 245.2112 476.7321 660.2725 961.0610 1356.1011 1849.5925 2498.5425 3552.5876 4965.2051 7749.5400 12967.4980 23959.2109 | lr 4.6e-04 | norm 10261.7695 | dt 9.812 +type train | step 695 | loss 233.1704 451.9772 631.2278 927.8131 1309.6370 1782.8202 2409.1589 3415.4043 4808.7612 7479.9043 12552.3984 23243.0332 | lr 4.6e-04 | norm 10299.2393 | dt 9.821 +type train | step 696 | loss 241.2696 467.1218 648.5900 948.9346 1338.5917 1814.8411 2446.0488 3464.6392 4856.9111 7579.3423 12776.8887 23634.4375 | lr 4.6e-04 | norm 9833.4521 | dt 9.807 +type train | step 697 | loss 243.1402 473.3414 658.7346 967.2028 1356.3467 1851.1814 2494.8552 3557.3486 4954.6865 7736.6636 13007.7588 24071.5625 | lr 4.6e-04 | norm 10432.2939 | dt 9.817 +type train | step 698 | loss 255.6569 494.9205 687.5118 1002.9280 1401.8639 1928.1501 2614.0479 3726.9963 5198.0127 8081.1523 13662.1123 25411.0684 | lr 4.7e-04 | norm 10576.3809 | dt 9.826 +type train | step 699 | loss 248.7116 480.2279 663.7151 977.6603 1375.8062 1863.8635 2523.5347 3578.8994 5001.1187 7765.8740 12983.6143 23637.5039 | lr 4.7e-04 | norm 10983.7949 | dt 9.830 +type train | step 700 | loss 282.8438 552.9052 755.5986 1094.4978 1501.1157 2044.4764 2711.2747 3805.3347 5203.7529 7949.3604 13363.3447 25093.3086 | lr 4.7e-04 | norm 13089.1621 | dt 9.812 +type train | step 701 | loss 241.5978 474.9542 661.5562 978.5671 1378.6731 1875.5486 2527.2034 3612.7229 5045.9268 7754.6504 13025.4453 24368.5312 | lr 4.7e-04 | norm 12784.0098 | dt 9.831 +type train | step 702 | loss 232.7242 469.6402 682.5768 1102.5223 1629.8646 2305.5679 3150.3091 4649.0659 6328.0923 9452.3594 15243.0391 29422.0859 | lr 4.7e-04 | norm 27541.6055 | dt 9.787 +type train | step 703 | loss 250.6419 498.4804 712.1252 1101.2349 1590.6450 2226.2859 3025.8630 4381.0234 6028.4590 9162.1191 14998.4951 28203.3145 | lr 4.7e-04 | norm 19884.6250 | dt 9.809 +type train | step 704 | loss 251.5722 488.2858 672.3688 973.7686 1369.8132 1859.3525 2510.4351 3564.8521 4994.6094 7742.6987 13056.7080 24431.7051 | lr 4.7e-04 | norm 12381.8838 | dt 9.814 +type train | step 705 | loss 242.3014 470.8193 653.4380 955.5185 1347.5947 1828.1709 2464.1040 3478.0190 4879.2451 7571.0376 12751.6133 23697.9707 | lr 4.7e-04 | norm 11072.4873 | dt 9.831 +type train | step 706 | loss 220.4231 425.5617 597.8474 885.1726 1259.8357 1722.0292 2333.0720 3323.7888 4682.6001 7314.6509 12393.8447 23138.5449 | lr 4.7e-04 | norm 12007.3457 | dt 9.809 +type train | step 707 | loss 262.5355 512.5234 710.4650 1031.2849 1439.0349 1970.6802 2655.4058 3798.6824 5233.5610 8067.8999 13425.0283 24971.2930 | lr 4.7e-04 | norm 12609.2998 | dt 9.806 +type train | step 708 | loss 244.9053 476.1539 660.7238 968.1036 1374.7554 1886.0701 2555.0649 3646.5918 5081.3389 7860.4648 13148.5547 24403.4160 | lr 4.7e-04 | norm 9952.7920 | dt 9.816 +type train | step 709 | loss 232.5513 449.7904 631.5447 933.2329 1330.6724 1828.2888 2492.5391 3582.1672 4996.1997 7804.9443 13098.3145 24328.6406 | lr 4.7e-04 | norm 12623.2568 | dt 9.833 +type train | step 710 | loss 243.1562 472.4066 655.4296 966.0526 1358.1031 1865.1593 2517.2012 3590.3140 5033.4263 7753.6343 12944.7012 23932.3828 | lr 4.7e-04 | norm 11151.1260 | dt 9.818 +type train | step 711 | loss 251.3535 491.9970 685.5174 1006.4017 1413.9082 1931.8235 2595.4016 3688.0974 5118.1875 7848.8525 13036.2168 23967.9746 | lr 4.7e-04 | norm 15123.4297 | dt 9.834 +type train | step 712 | loss 227.9063 444.6113 628.1028 922.9260 1308.7820 1790.8116 2426.6042 3458.5515 4847.3232 7513.9600 12620.5508 23474.2441 | lr 4.7e-04 | norm 10797.8408 | dt 9.819 +type train | step 713 | loss 238.3537 463.1089 646.4385 947.7740 1337.4047 1822.5840 2452.5845 3494.2959 4877.3418 7593.1357 12800.0176 23820.4531 | lr 4.8e-04 | norm 9930.5049 | dt 9.823 +type train | step 714 | loss 243.3835 477.8003 663.5400 972.0943 1367.6744 1861.2383 2515.1550 3576.4028 4966.8916 7648.2822 12748.5479 23682.7012 | lr 4.8e-04 | norm 10423.0977 | dt 9.829 +type train | step 715 | loss 249.3580 480.0630 667.1627 981.1562 1380.1079 1909.9558 2579.4785 3676.6606 5136.9409 7891.0073 13176.7559 24804.2305 | lr 4.8e-04 | norm 11311.1738 | dt 9.839 +type train | step 716 | loss 243.8066 473.8755 657.6240 962.4316 1347.7100 1840.7699 2482.7808 3527.1509 4922.3076 7592.9219 12687.2637 23454.2031 | lr 4.8e-04 | norm 8598.9941 | dt 9.858 +type train | step 717 | loss 219.8406 427.7786 594.9990 884.2227 1256.3729 1733.2856 2373.4587 3402.8340 4777.0093 7417.8657 12427.8350 22911.5098 | lr 4.8e-04 | norm 12609.7754 | dt 9.838 +type train | step 718 | loss 224.1968 433.4484 607.2618 897.2858 1274.0992 1760.8290 2390.9031 3425.8059 4788.3193 7467.9956 12542.1377 23339.0742 | lr 4.8e-04 | norm 9917.6689 | dt 9.842 +type train | step 719 | loss 227.5892 440.2017 618.5149 920.0178 1301.4916 1786.3644 2420.4600 3446.1772 4849.7358 7546.7397 12646.2227 23500.5820 | lr 4.8e-04 | norm 10277.4238 | dt 9.833 +type train | step 720 | loss 225.9860 438.5108 622.3838 925.7354 1311.5267 1791.4834 2422.6355 3440.0872 4854.1641 7538.5269 12661.8926 23511.0195 | lr 4.8e-04 | norm 9582.5020 | dt 9.839 +type train | step 721 | loss 237.2408 460.2733 637.7614 940.6271 1319.6501 1799.3750 2428.2754 3438.2119 4785.8813 7391.0742 12284.8887 22551.2188 | lr 4.8e-04 | norm 9958.9746 | dt 9.836 +type train | step 722 | loss 237.5221 464.2578 646.6696 952.6647 1345.0023 1859.5234 2519.8513 3600.0830 4982.9312 7636.3901 12739.8916 23961.4805 | lr 4.8e-04 | norm 11590.3770 | dt 9.834 +type train | step 723 | loss 242.1984 476.5883 670.3055 982.5711 1374.9108 1885.6450 2557.8496 3697.0957 5111.7607 8036.5967 13474.9980 25203.9844 | lr 4.8e-04 | norm 16485.2344 | dt 9.850 +type train | step 724 | loss 232.9351 452.0095 634.6843 942.4514 1329.3442 1817.1324 2453.2148 3502.0908 4906.7480 7585.6035 12693.3770 23341.2734 | lr 4.8e-04 | norm 9593.6475 | dt 9.847 +type train | step 725 | loss 226.6348 440.3562 617.7739 922.0825 1293.8846 1766.0723 2393.4517 3424.2205 4795.2173 7415.8281 12360.5674 22614.6465 | lr 4.8e-04 | norm 8801.7412 | dt 9.851 +type train | step 726 | loss 225.9747 439.1207 610.2839 915.4181 1281.5751 1757.3890 2378.5349 3377.4971 4743.0454 7419.0503 12478.3994 23260.2461 | lr 4.8e-04 | norm 11072.0498 | dt 9.810 +type train | step 727 | loss 260.8197 508.5521 685.5839 1008.0246 1396.5496 1942.7388 2654.3696 3855.4883 5389.3892 8319.0654 13761.2021 25356.5938 | lr 4.8e-04 | norm 12927.6191 | dt 9.822 +type train | step 728 | loss 220.0741 425.2296 594.1763 892.9546 1257.3064 1720.1090 2332.8064 3335.7888 4669.5347 7275.7476 12187.0205 22433.0938 | lr 4.9e-04 | norm 9912.2783 | dt 9.832 +type train | step 729 | loss 230.3384 445.4133 622.3093 928.1996 1298.8171 1772.2719 2389.9443 3399.6729 4771.9556 7351.6064 12296.3721 22987.4453 | lr 4.9e-04 | norm 10975.6992 | dt 9.820 +type train | step 730 | loss 234.1842 451.0297 628.4891 931.5383 1304.7793 1781.6753 2414.1362 3449.8027 4851.9077 7521.9067 12633.6221 23342.5859 | lr 4.9e-04 | norm 9787.5146 | dt 9.811 +type train | step 731 | loss 241.1977 465.9996 642.3206 961.6836 1338.8356 1852.8314 2511.0227 3599.9805 5009.8555 7703.5522 12858.7529 23997.3945 | lr 4.9e-04 | norm 10818.8145 | dt 9.823 +type train | step 732 | loss 222.5489 430.5244 603.3170 896.3185 1266.7717 1727.1818 2345.2993 3337.1602 4705.4009 7307.3667 12287.8457 22922.2129 | lr 4.9e-04 | norm 9799.9697 | dt 9.825 +type train | step 733 | loss 227.6752 438.0678 605.7781 897.6722 1261.4792 1725.5363 2334.6038 3334.8818 4689.6206 7281.2915 12247.1016 22861.4277 | lr 4.9e-04 | norm 10758.5771 | dt 9.825 +type train | step 734 | loss 228.0547 441.6812 612.7545 903.9501 1274.3666 1749.0999 2375.7864 3411.4353 4792.5952 7437.6450 12429.5010 22928.9316 | lr 4.9e-04 | norm 9111.7314 | dt 9.832 +type train | step 735 | loss 247.0419 475.8167 665.7685 987.5696 1364.6356 1866.2607 2514.0513 3621.5947 5010.3638 7699.6074 12885.2246 24105.6211 | lr 4.9e-04 | norm 11431.2100 | dt 9.816 +type train | step 736 | loss 218.4155 422.4241 597.7357 901.3647 1260.3561 1731.9756 2355.6423 3391.4695 4743.3413 7399.8545 12435.6875 23290.8516 | lr 4.9e-04 | norm 10649.3838 | dt 9.835 +type train | step 737 | loss 215.1625 415.7641 586.8133 888.7871 1251.0271 1720.4220 2336.3394 3360.9771 4686.6855 7295.6313 12210.5439 22655.4414 | lr 4.9e-04 | norm 8685.3291 | dt 9.820 +type train | step 738 | loss 228.4865 449.5317 639.5006 967.2725 1345.7784 1845.6588 2497.3235 3588.1008 5020.3823 7823.9312 13113.2373 24457.6562 | lr 4.9e-04 | norm 10864.6211 | dt 9.841 +type train | step 739 | loss 207.9533 405.1852 576.6802 887.1880 1234.9360 1717.4288 2343.9082 3404.7146 4750.5439 7408.1851 12337.5801 22770.6094 | lr 4.9e-04 | norm 8786.5127 | dt 9.830 +type train | step 740 | loss 213.8292 416.0010 588.4915 893.9182 1252.8618 1723.0266 2345.2722 3421.9182 4776.9741 7485.6289 12684.1152 23881.3672 | lr 4.9e-04 | norm 12743.4629 | dt 9.870 +type train | step 741 | loss 214.6964 414.2887 585.2194 886.2939 1248.2429 1703.6125 2310.6523 3351.9219 4664.4385 7325.8545 12374.4658 23089.3320 | lr 4.9e-04 | norm 11117.1865 | dt 9.838 +type train | step 742 | loss 222.2764 430.9288 596.8066 896.4333 1258.7064 1746.9635 2370.2266 3439.4016 4758.5376 7338.1289 12234.4619 22756.3438 | lr 4.9e-04 | norm 9943.6670 | dt 9.841 +type train | step 743 | loss 209.7339 407.3136 570.8915 862.3391 1222.2921 1678.6917 2294.0439 3340.9736 4656.4595 7293.5757 12287.2881 22849.8008 | lr 5.0e-04 | norm 10466.7793 | dt 9.847 +type train | step 744 | loss 221.9040 429.6324 601.9034 902.8452 1269.0938 1743.6018 2367.2910 3426.2808 4729.7314 7375.9365 12371.3740 22783.2793 | lr 5.0e-04 | norm 10471.7295 | dt 9.852 +type train | step 745 | loss 227.7690 440.6438 614.9280 907.3255 1276.3967 1745.1754 2353.6191 3398.3669 4682.7397 7257.1499 12170.1680 22454.4922 | lr 5.0e-04 | norm 9205.1064 | dt 9.868 +type train | step 746 | loss 220.1344 425.8362 596.9954 904.4322 1263.5288 1731.5281 2350.0757 3391.6396 4709.6733 7347.8896 12400.8818 22993.8809 | lr 5.0e-04 | norm 10485.3008 | dt 9.894 +type train | step 747 | loss 249.6922 481.0676 663.0199 981.4141 1361.8778 1867.9941 2495.9812 3578.1890 4866.0093 7488.3882 12442.1602 23087.0410 | lr 5.0e-04 | norm 11244.8242 | dt 9.851 +type train | step 748 | loss 244.3695 471.0036 651.9468 961.0690 1345.2568 1852.3267 2498.4858 3606.0784 4887.1519 7489.0356 12247.9404 22518.9863 | lr 5.0e-04 | norm 8477.8154 | dt 9.847 +type train | step 749 | loss 229.2692 447.1880 630.3172 942.7042 1332.1462 1828.7054 2476.8701 3578.7949 4927.3638 7617.2627 12679.6973 23478.6758 | lr 5.0e-04 | norm 10375.0889 | dt 9.852 +type train | step 750 | loss 230.0056 445.8500 630.6804 948.3000 1327.9027 1817.5023 2450.6482 3542.4849 4891.4424 7570.5176 12634.0635 23561.0488 | lr 5.0e-04 | norm 12352.3799 | dt 9.845 +type train | step 751 | loss 241.7237 471.4248 665.2672 998.0479 1378.0210 1881.7787 2548.5601 3673.8677 5064.9897 7764.3311 12975.9072 24366.2402 | lr 5.0e-04 | norm 18063.3965 | dt 9.818 +type train | step 752 | loss 264.2103 509.3258 701.6077 1037.4882 1425.6866 1946.8167 2620.7866 3753.9839 5095.4014 7889.7549 13122.8945 24485.7383 | lr 5.0e-04 | norm 13278.6074 | dt 9.826 +type train | step 753 | loss 222.5017 436.0449 615.3348 927.9874 1297.1675 1773.9006 2403.7700 3479.0369 4844.9424 7505.1836 12578.5713 23436.4941 | lr 5.0e-04 | norm 10790.8594 | dt 9.829 +type train | step 754 | loss 224.4400 435.7727 614.3815 929.4906 1299.6072 1789.1222 2429.1145 3510.0166 4872.9170 7623.2666 12781.9238 23970.2227 | lr 5.0e-04 | norm 11383.0742 | dt 9.835 +type train | step 755 | loss 215.4314 418.4901 590.6251 891.7642 1253.9705 1727.1946 2345.5344 3388.0669 4734.1758 7384.4150 12418.6162 23248.0469 | lr 5.0e-04 | norm 10367.8955 | dt 9.823 +type train | step 756 | loss 225.3634 441.3843 629.3486 959.5195 1337.6476 1837.9255 2482.0991 3582.3994 4998.0127 7724.8965 12912.9570 24101.8828 | lr 5.0e-04 | norm 12217.9805 | dt 9.835 +type train | step 757 | loss 223.4173 437.1578 615.0251 927.4044 1299.7952 1793.5149 2434.4443 3525.1323 4870.8530 7562.8271 12712.1328 23663.0312 | lr 5.0e-04 | norm 12266.7568 | dt 9.833 +type train | step 758 | loss 240.4125 465.4918 648.8787 969.8342 1352.6926 1863.4338 2520.4324 3629.0688 5017.2080 7723.0371 12863.9492 23837.5684 | lr 5.0e-04 | norm 10021.3438 | dt 9.858 +type train | step 759 | loss 234.0689 454.7201 635.2244 951.5175 1322.8969 1805.8247 2431.4695 3501.4155 4846.5767 7520.3965 12673.0527 23832.6328 | lr 5.0e-04 | norm 11072.1211 | dt 9.833 +type train | step 760 | loss 228.9650 444.2213 623.6307 931.4315 1297.6417 1769.6007 2375.1836 3403.5623 4713.2485 7235.6523 12108.9453 22520.9941 | lr 5.0e-04 | norm 8300.2080 | dt 9.840 +type train | step 761 | loss 233.9339 456.9649 641.3419 965.4002 1326.1852 1806.5759 2418.9773 3470.0447 4781.5576 7384.9312 12412.0000 23299.5508 | lr 5.0e-04 | norm 9905.4102 | dt 9.834 +type train | step 762 | loss 231.7768 453.1221 633.1371 932.0886 1293.4937 1766.7760 2362.2312 3384.3223 4676.7271 7306.3428 12461.7969 23950.6582 | lr 5.0e-04 | norm 23090.2637 | dt 9.816 +type train | step 763 | loss 217.8800 423.4642 596.7493 898.6622 1266.4468 1739.6844 2358.4854 3418.1252 4743.7583 7345.3809 12315.3867 22803.7148 | lr 5.0e-04 | norm 9727.1807 | dt 9.844 +type train | step 764 | loss 233.7790 456.8379 637.4441 951.5181 1334.3008 1812.7643 2445.9226 3520.7969 4876.6543 7469.3579 12420.7998 23023.8438 | lr 5.0e-04 | norm 9612.7627 | dt 9.852 +type train | step 765 | loss 208.4729 407.5400 581.8013 880.7767 1257.4866 1747.3159 2383.4409 3472.1157 4822.3491 7392.6216 12133.2725 22363.4199 | lr 5.0e-04 | norm 14656.7617 | dt 9.827 +type train | step 766 | loss 231.5060 451.8902 633.4790 944.9615 1335.8270 1792.3265 2405.0537 3445.4412 4767.5015 7359.5005 12356.7012 22943.2773 | lr 5.0e-04 | norm 8603.3779 | dt 9.865 +type train | step 767 | loss 224.9740 436.5598 609.8847 919.5371 1303.3446 1767.8717 2400.2090 3444.4712 4779.3618 7433.3506 12562.6572 23449.2617 | lr 5.0e-04 | norm 9693.1416 | dt 9.842 +type train | step 768 | loss 217.6548 421.6716 596.3525 896.6822 1291.9905 1733.1245 2349.3447 3393.5374 4702.9385 7291.2393 12184.8438 22574.2832 | lr 5.0e-04 | norm 10004.3535 | dt 9.837 +type train | step 769 | loss 222.0584 425.8102 597.8246 901.7529 1279.2218 1738.7644 2359.3445 3403.9780 4751.5439 7324.3604 12224.3135 22801.2461 | lr 5.0e-04 | norm 8746.0488 | dt 9.836 +type train | step 770 | loss 232.2273 451.2706 633.0187 945.0198 1330.7472 1811.3237 2449.3257 3522.9336 4877.6934 7471.0957 12459.0635 23058.1816 | lr 5.0e-04 | norm 8660.1523 | dt 9.840 +type train | step 771 | loss 221.1381 439.1440 618.1143 936.3504 1333.5051 1798.6907 2413.4536 3472.7256 4812.2129 7390.7725 12365.8379 23064.3340 | lr 5.0e-04 | norm 15187.4639 | dt 9.832 +type train | step 772 | loss 227.7465 440.6459 619.6508 929.6437 1322.5077 1793.4268 2439.7180 3515.0378 4899.1060 7572.9951 12592.5996 23256.3730 | lr 5.0e-04 | norm 9463.0361 | dt 9.848 +type train | step 773 | loss 208.7408 405.8148 574.9877 870.4460 1257.6826 1702.2253 2318.0298 3360.7087 4692.1274 7301.8877 12270.5801 22855.8066 | lr 5.0e-04 | norm 9429.0537 | dt 9.825 +type train | step 774 | loss 228.0927 441.9095 615.4825 919.1221 1295.1643 1742.7195 2340.2847 3355.4363 4622.6963 7129.0415 11954.2090 22333.4336 | lr 5.0e-04 | norm 9573.6113 | dt 9.830 +type train | step 775 | loss 207.6202 420.7759 609.7706 949.3423 1354.8394 1823.4811 2470.3953 3595.3013 5091.6157 8043.4121 13761.3984 26701.1484 | lr 5.0e-04 | norm 21368.4004 | dt 9.822 +type train | step 776 | loss 215.9254 418.2450 589.1647 884.9656 1251.6722 1694.9008 2290.1899 3298.1628 4594.4365 7177.0640 12104.6104 22584.7480 | lr 5.0e-04 | norm 9769.8271 | dt 9.835 +type train | step 777 | loss 208.2341 403.5692 573.1778 858.9402 1241.6136 1663.7655 2251.0071 3234.6689 4529.7930 7036.2437 11783.4766 21941.1836 | lr 5.0e-04 | norm 10654.8320 | dt 9.830 +type train | step 778 | loss 239.4107 465.3921 659.1064 981.4652 1395.0587 1870.9303 2513.8108 3613.7251 5003.7046 7707.8545 13064.7451 24782.7656 | lr 5.0e-04 | norm 17026.8945 | dt 9.827 +type train | step 779 | loss 243.0986 474.2370 661.2663 980.0992 1387.5405 1839.0564 2457.1650 3523.7432 4852.0571 7451.9092 12561.9824 23728.7012 | lr 5.0e-04 | norm 15206.5557 | dt 9.819 +type train | step 780 | loss 215.7979 419.1707 595.1230 899.2338 1288.5371 1726.8646 2333.5632 3340.7935 4680.6992 7211.1675 11995.5010 22443.0859 | lr 5.0e-04 | norm 11791.1309 | dt 9.854 +type train | step 781 | loss 220.5176 428.4091 600.5073 901.0228 1283.6952 1724.9926 2334.1414 3333.5461 4644.4316 7199.3115 12115.0791 22818.7598 | lr 5.0e-04 | norm 11750.7256 | dt 9.842 +type train | step 782 | loss 218.0065 421.3384 605.6353 924.7827 1334.5005 1819.6198 2480.2285 3585.5518 5007.9614 7630.4204 12662.1436 23757.0137 | lr 5.0e-04 | norm 13194.2959 | dt 9.849 +type train | step 783 | loss 211.2746 412.3956 586.1281 886.1448 1265.9647 1708.3677 2311.2400 3319.2646 4639.6357 7149.5356 12033.1631 22635.4609 | lr 5.0e-04 | norm 11081.5508 | dt 9.853 +type train | step 784 | loss 240.0911 467.1449 644.0596 952.1649 1350.6008 1828.3656 2467.1694 3553.8503 4911.9336 7453.8003 12358.6973 22902.2930 | lr 5.0e-04 | norm 11333.6426 | dt 9.851 +type train | step 785 | loss 222.6156 432.0741 608.1810 911.9263 1303.0378 1771.3677 2400.3525 3448.3059 4775.5137 7335.8228 12198.2988 22720.6191 | lr 5.0e-04 | norm 9846.1172 | dt 9.853 +type train | step 786 | loss 207.4223 411.6030 600.2567 932.6203 1349.6423 1838.3418 2517.5996 3631.4290 5087.0933 7971.2090 13616.4199 26221.3105 | lr 5.0e-04 | norm 23053.5605 | dt 9.829 +type train | step 787 | loss 199.0637 393.0753 564.7584 872.7293 1263.4596 1700.6720 2312.6011 3349.4885 4789.1265 7389.2466 12556.3125 23930.5898 | lr 5.0e-04 | norm 14340.6855 | dt 9.826 +type train | step 788 | loss 229.6159 444.9911 620.9221 923.2085 1310.5348 1761.4863 2354.1238 3364.9751 4675.6855 7109.9062 11834.8525 22221.4082 | lr 5.0e-04 | norm 10566.5566 | dt 9.839 +type train | step 789 | loss 222.2760 425.8596 591.5859 887.0798 1277.9760 1700.4297 2309.4399 3311.5476 4645.7744 7071.8560 11797.2822 22148.9199 | lr 5.0e-04 | norm 14519.5605 | dt 9.838 +type train | step 790 | loss 208.2955 410.3820 585.0084 884.2663 1275.0887 1720.0311 2330.5381 3352.1201 4743.1270 7221.9800 12094.1240 22703.2539 | lr 5.0e-04 | norm 12565.9248 | dt 9.846 +type train | step 791 | loss 208.6931 402.0181 567.3700 859.6735 1237.9329 1662.0157 2259.2410 3233.0005 4527.0371 6980.4351 11736.5371 21967.3594 | lr 5.0e-04 | norm 11146.2002 | dt 9.845 +type train | step 792 | loss 214.0299 415.3706 583.7293 878.2880 1263.8462 1694.7401 2295.5300 3302.2559 4621.5703 7088.2109 11866.3271 22132.6016 | lr 5.0e-04 | norm 11335.6504 | dt 9.846 +type train | step 793 | loss 215.4096 416.8559 586.9607 883.7449 1264.5898 1716.4160 2326.8052 3360.9868 4752.3594 7321.0190 12120.3623 22743.6191 | lr 5.0e-04 | norm 12117.1914 | dt 9.836 +type train | step 794 | loss 205.6047 402.2085 569.3611 865.8217 1254.5425 1696.9368 2308.5303 3351.3955 4685.2588 7227.6138 12172.7236 23108.8223 | lr 5.0e-04 | norm 11130.9219 | dt 9.829 +type train | step 795 | loss 209.8912 406.7837 570.4067 865.9019 1257.5046 1684.5038 2280.3835 3280.7244 4611.0391 7135.8413 11970.5254 22358.1074 | lr 5.0e-04 | norm 9301.2607 | dt 9.855 +type train | step 796 | loss 214.2004 420.3664 593.9219 897.0300 1286.6377 1720.2832 2326.9700 3345.7698 4710.4707 7258.6240 12273.2285 23196.5176 | lr 5.0e-04 | norm 9986.4512 | dt 9.850 +type train | step 797 | loss 203.7632 398.1813 567.4987 865.2079 1250.8840 1706.2350 2326.8164 3373.3142 4692.8481 7214.5820 11990.2002 22516.1719 | lr 5.0e-04 | norm 9128.9189 | dt 9.849 +type train | step 798 | loss 224.3296 437.6812 608.3469 912.7743 1305.4680 1769.1155 2392.4331 3457.2993 4761.1279 7346.6738 12344.8701 23251.8086 | lr 5.0e-04 | norm 10915.1348 | dt 9.831 +type train | step 799 | loss 203.8725 393.3755 547.4387 834.1721 1199.1804 1652.6545 2263.8250 3305.0933 4567.6509 7098.4678 12007.1729 22735.6719 | lr 5.0e-04 | norm 16337.1865 | dt 9.822 +type train | step 800 | loss 207.6910 405.1270 569.8812 859.1633 1245.9130 1667.6760 2268.8975 3268.9290 4598.3789 7086.0005 11841.5342 22119.9805 | lr 5.0e-04 | norm 10557.0674 | dt 9.844 +type train | step 801 | loss 212.4905 409.6904 580.7898 870.1743 1252.4480 1673.2307 2260.1853 3244.2100 4558.1016 7033.5879 11807.7773 22435.4219 | lr 5.0e-04 | norm 14184.0957 | dt 9.830 +type train | step 802 | loss 204.7276 394.8683 556.8162 841.3157 1216.9265 1647.5333 2245.0479 3250.3171 4573.3906 7089.8271 11905.7490 22384.2734 | lr 5.0e-04 | norm 10718.4092 | dt 9.866 +type train | step 803 | loss 209.5462 401.8653 568.4821 863.2774 1245.6414 1676.9797 2272.3538 3267.2612 4580.0850 7075.7783 11788.8467 22021.9746 | lr 5.0e-04 | norm 9582.8105 | dt 9.849 +type train | step 804 | loss 235.2746 459.8262 648.2696 980.5148 1397.3763 1905.4497 2580.6426 3709.0996 5148.6343 7879.8403 13081.8398 24421.2715 | lr 5.0e-04 | norm 10647.0215 | dt 9.849 +type train | step 805 | loss 222.9310 431.0604 600.9108 904.9058 1298.2876 1772.2714 2399.0266 3469.0984 4794.1943 7305.5283 12152.8135 22915.7969 | lr 5.0e-04 | norm 9755.9492 | dt 9.839 +type train | step 806 | loss 204.6492 394.1568 560.0820 845.6623 1224.4315 1645.0258 2235.2688 3214.9546 4508.8428 6992.0083 11760.9268 22006.2305 | lr 5.0e-04 | norm 9395.0762 | dt 9.840 +type train | step 807 | loss 212.4874 410.6888 576.1520 867.5693 1252.9354 1695.2264 2296.4146 3319.7217 4620.9834 7067.9429 11724.1289 21924.6914 | lr 5.0e-04 | norm 10129.0859 | dt 9.835 +type train | step 808 | loss 212.3699 410.5433 577.3259 869.2767 1237.7985 1666.4863 2235.9136 3208.5557 4453.8413 6816.0742 11349.3242 21603.3301 | lr 5.0e-04 | norm 12054.9619 | dt 9.828 +type train | step 809 | loss 217.2622 417.4296 585.3319 888.2753 1259.1086 1708.7719 2308.9419 3306.5469 4598.0649 6986.0615 11622.4658 21776.9004 | lr 5.0e-04 | norm 10229.0283 | dt 9.850 +type train | step 810 | loss 221.8983 428.1758 588.3770 873.5285 1246.4927 1674.1880 2257.0410 3267.5090 4501.7744 6973.9624 11681.6768 22050.2695 | lr 5.0e-04 | norm 17398.1406 | dt 9.830 +type train | step 811 | loss 220.8848 427.0692 598.7925 898.1520 1278.5670 1709.3289 2308.1646 3300.0081 4606.8472 7136.2480 11871.8418 21948.1562 | lr 5.0e-04 | norm 12699.1973 | dt 9.851 +type train | step 812 | loss 221.7564 430.2477 596.8842 892.1346 1267.2733 1708.9922 2310.8008 3317.7634 4606.1338 7095.7300 11912.0518 22412.7363 | lr 5.0e-04 | norm 10062.6914 | dt 9.849 +type train | step 813 | loss 215.0307 415.1708 581.8213 880.5218 1263.7006 1701.5566 2304.5234 3306.5959 4629.7891 7099.1289 11778.4307 21906.7305 | lr 5.0e-04 | norm 9132.7715 | dt 9.839 +type train | step 814 | loss 213.5418 410.4753 572.7587 869.4038 1241.5460 1694.1223 2293.8779 3304.9478 4587.6792 7040.5435 11777.2705 21978.7852 | lr 5.0e-04 | norm 10113.1963 | dt 9.837 +type train | step 815 | loss 201.2159 388.7137 548.3591 843.0204 1195.2727 1617.6414 2193.6614 3167.4116 4443.0767 6808.5083 11216.1543 20816.4141 | lr 5.0e-04 | norm 9620.5811 | dt 9.848 +type train | step 816 | loss 211.6765 408.3445 573.5858 884.1887 1240.9253 1697.9130 2293.0293 3323.9204 4602.8320 7071.8003 11810.9395 22374.7461 | lr 5.0e-04 | norm 14901.8965 | dt 9.830 +type train | step 817 | loss 217.8429 419.4521 587.3187 896.8630 1264.7053 1704.6783 2297.5415 3307.4116 4604.1772 7053.3345 11659.8271 21610.6367 | lr 5.0e-04 | norm 8541.4395 | dt 9.848 +type train | step 818 | loss 208.9371 397.9072 551.5260 843.2433 1185.9949 1610.8942 2172.7041 3110.6848 4357.2339 6744.4375 11327.2705 21368.9941 | lr 5.0e-04 | norm 9538.4180 | dt 9.840 +type train | step 819 | loss 207.7691 402.8201 570.3513 876.8133 1240.2375 1677.9449 2269.6633 3262.7078 4562.4478 7016.3540 11807.4453 22446.0801 | lr 5.0e-04 | norm 10550.8760 | dt 9.845 +type train | step 820 | loss 204.5027 395.1715 563.6333 868.7339 1241.2711 1673.2412 2271.2878 3259.4292 4541.9287 7010.9702 11756.8164 22162.5918 | lr 5.0e-04 | norm 10627.0801 | dt 9.837 +type train | step 821 | loss 204.0714 394.0695 557.2037 863.3292 1214.6913 1651.5741 2233.9465 3193.9868 4485.6831 6926.1201 11579.7979 21611.3516 | lr 5.0e-04 | norm 9037.2168 | dt 9.860 +type train | step 822 | loss 220.2074 424.1330 598.2878 920.8436 1291.4211 1765.8749 2384.7676 3444.2607 4766.5679 7298.1455 12235.0088 23227.9355 | lr 5.0e-04 | norm 11662.1543 | dt 9.841 +type train | step 823 | loss 195.5853 384.2285 553.5580 870.6672 1227.7822 1656.7784 2256.4512 3245.1868 4586.1138 7050.0215 11843.9668 22459.4023 | lr 5.0e-04 | norm 10041.7031 | dt 9.839 +type train | step 824 | loss 204.8971 397.4820 561.7638 866.3262 1218.5586 1650.3269 2230.8882 3210.0398 4519.1143 6951.6943 11577.6709 21576.7402 | lr 5.0e-04 | norm 9733.7266 | dt 9.850 +type train | step 825 | loss 207.4740 400.3727 565.2194 876.8803 1225.8595 1654.8993 2229.7368 3195.5261 4500.5693 6886.8999 11511.3301 21635.0508 | lr 5.0e-04 | norm 9515.6074 | dt 9.854 +type train | step 826 | loss 217.6811 419.1515 585.0238 892.5895 1244.7296 1682.8811 2267.6350 3245.6909 4522.4282 6964.8901 11688.8848 21974.3477 | lr 5.0e-04 | norm 9784.0693 | dt 9.840 +type train | step 827 | loss 203.7763 390.8137 552.2969 850.7589 1197.2445 1629.2916 2205.0247 3156.8066 4430.4648 6848.9199 11421.8135 21331.7500 | lr 5.0e-04 | norm 9184.5762 | dt 9.848 +type train | step 828 | loss 209.6611 404.1075 565.5272 877.3376 1220.7761 1637.1122 2209.3516 3166.4404 4445.6509 6839.2114 11516.4551 21455.6328 | lr 5.0e-04 | norm 12633.5410 | dt 9.836 +type train | step 829 | loss 214.4118 411.9192 571.5332 882.5820 1219.3988 1642.0472 2201.7168 3147.6299 4398.5459 6719.0850 11216.2988 20973.9941 | lr 5.0e-04 | norm 9233.8057 | dt 9.843 +type train | step 830 | loss 189.0156 378.1720 547.1121 871.7986 1220.9835 1639.1969 2228.1641 3236.0415 4638.9048 7210.6982 12307.6055 23837.5156 | lr 5.0e-04 | norm 22332.4473 | dt 9.824 +type train | step 831 | loss 203.6240 391.9346 557.8912 888.6439 1241.1311 1675.1610 2266.7361 3264.0132 4606.7061 7120.0029 11977.3896 22585.7383 | lr 5.0e-04 | norm 11229.8994 | dt 9.843 +type train | step 832 | loss 189.5665 362.3174 516.1539 814.7909 1152.0353 1569.1768 2145.3645 3102.7280 4377.8813 6786.6816 11442.0986 21244.6543 | lr 5.0e-04 | norm 9885.2842 | dt 9.841 +type train | step 833 | loss 202.1404 390.1644 552.0167 869.3565 1208.9561 1648.2739 2228.3474 3210.7463 4515.2070 6951.3315 11634.4854 21669.1074 | lr 5.0e-04 | norm 8850.2412 | dt 9.859 +type train | step 834 | loss 213.7362 415.6044 573.3843 887.1714 1227.6530 1681.1443 2255.8374 3231.2717 4486.0820 6900.0547 11554.8467 21693.8027 | lr 5.0e-04 | norm 9139.2852 | dt 9.843 +type train | step 835 | loss 202.5920 389.9274 549.1956 859.0464 1193.3689 1616.7388 2184.2410 3128.3123 4370.2319 6760.6772 11368.6016 21382.7559 | lr 5.0e-04 | norm 8075.3516 | dt 9.849 +type train | step 836 | loss 204.1452 392.0291 552.9145 853.3312 1201.0232 1625.6204 2174.2268 3110.9819 4366.9824 6708.0703 11239.9209 21023.5449 | lr 5.0e-04 | norm 9934.5977 | dt 9.853 +type train | step 837 | loss 198.7289 382.5269 544.8687 847.3788 1198.9423 1646.7073 2189.7517 3152.2158 4441.6675 6867.5679 11554.9570 21415.2598 | lr 5.0e-04 | norm 7602.8950 | dt 9.861 +type train | step 838 | loss 213.9717 409.8936 565.1752 878.9195 1219.7074 1645.5543 2221.2280 3175.9739 4432.4678 6901.9609 11652.3223 21991.8555 | lr 5.0e-04 | norm 10988.7324 | dt 9.837 +type train | step 839 | loss 205.1219 397.0889 563.6980 877.4692 1235.2854 1696.2991 2275.6514 3278.7734 4603.6807 7051.0181 11687.8379 21778.9629 | lr 5.0e-04 | norm 9029.3389 | dt 9.849 +type train | step 840 | loss 214.6116 415.2499 584.6688 898.1920 1251.7609 1712.1929 2282.5742 3294.4312 4541.0117 6984.8081 11712.8848 21940.1719 | lr 5.0e-04 | norm 10742.9043 | dt 9.849 +type train | step 841 | loss 210.4138 406.3440 570.4240 882.3510 1228.9260 1679.8499 2251.2742 3224.5120 4481.7715 6865.0361 11457.6104 21297.6582 | lr 5.0e-04 | norm 9167.5078 | dt 9.843 +type train | step 842 | loss 195.0853 373.1715 530.4446 829.9686 1166.7419 1606.8662 2150.2229 3075.8835 4351.8237 6726.5942 11310.5225 21230.8945 | lr 5.0e-04 | norm 8902.7637 | dt 9.886 +type train | step 843 | loss 207.9987 397.5261 556.4301 867.8685 1214.6963 1677.8226 2252.1750 3233.3042 4523.5869 6998.1338 11850.4463 22361.9922 | lr 5.0e-04 | norm 10564.9404 | dt 9.859 +type train | step 844 | loss 208.6053 398.4942 568.3505 895.8378 1239.2805 1729.5553 2330.9224 3388.1643 4677.0117 7245.8477 12163.8271 23149.9102 | lr 5.0e-04 | norm 14225.7646 | dt 9.835 +type train | step 845 | loss 186.6357 362.9447 518.9076 818.9739 1158.5195 1583.8671 2129.4517 3075.0547 4361.7109 6759.6069 11469.0332 21545.0273 | lr 5.0e-04 | norm 10511.9854 | dt 9.844 +type train | step 846 | loss 211.8418 403.5570 567.9048 875.4272 1220.1288 1661.7000 2197.2100 3142.5793 4337.7012 6698.7925 11188.2412 20830.3281 | lr 5.0e-04 | norm 14337.1133 | dt 9.847 +type train | step 847 | loss 191.6707 368.4070 525.5857 836.8414 1162.9182 1617.8839 2165.5405 3120.3618 4392.3359 6766.9404 11300.7236 20966.7285 | lr 5.0e-04 | norm 8696.5361 | dt 9.851 +type train | step 848 | loss 197.9789 382.2846 541.0480 858.1689 1190.0720 1646.1547 2182.5869 3152.6672 4414.0132 6816.0137 11471.0303 21306.2656 | lr 5.0e-04 | norm 8786.5332 | dt 9.849 +type train | step 849 | loss 204.0767 391.5995 555.2713 870.8404 1204.5789 1660.1464 2199.4504 3202.4192 4404.2256 6791.0347 11428.8496 21539.4590 | lr 5.0e-04 | norm 8422.9854 | dt 9.851 +type train | step 850 | loss 208.8321 404.8846 565.6591 873.5549 1214.1537 1680.1379 2222.8765 3255.9697 4421.9980 6698.7461 10936.2266 20235.1816 | lr 5.0e-04 | norm 10617.2285 | dt 9.842 +type train | step 851 | loss 190.6066 366.2421 517.7440 817.8503 1150.1919 1590.3412 2131.3069 3121.7378 4330.8428 6691.8154 11146.6279 20681.7090 | lr 5.0e-04 | norm 9574.4219 | dt 9.871 +type train | step 852 | loss 209.7105 403.5836 563.3860 879.1364 1215.6118 1684.3730 2227.9053 3255.4285 4438.2358 6840.1479 11448.5957 21557.7109 | lr 5.0e-04 | norm 10867.9746 | dt 9.837 +type train | step 853 | loss 194.2976 370.2402 522.0104 828.0121 1150.8231 1622.0114 2129.2256 3111.2925 4268.4238 6591.2773 11081.7012 20851.6016 | lr 5.0e-04 | norm 10168.3066 | dt 9.828 +type train | step 854 | loss 188.9789 364.0439 516.2275 821.8795 1151.2856 1602.8678 2152.5754 3168.9685 4408.4258 6848.5967 11399.0352 21065.2754 | lr 5.0e-04 | norm 10018.3818 | dt 9.849 +type train | step 855 | loss 194.1805 375.0705 529.5399 837.4241 1165.7760 1598.6528 2139.6633 3116.3569 4335.1064 6700.5977 11219.6396 21012.3125 | lr 5.0e-04 | norm 9163.0498 | dt 9.850 +type train | step 856 | loss 204.8156 393.6961 553.4334 862.7173 1198.6309 1665.5441 2215.3979 3212.9800 4442.2402 6882.2974 11546.6094 21660.0859 | lr 5.0e-04 | norm 9214.9111 | dt 9.845 +type train | step 857 | loss 188.9678 363.2045 518.1276 821.4510 1152.3240 1600.6814 2141.7415 3135.0430 4357.0576 6745.4214 11291.5986 21070.2090 | lr 5.0e-04 | norm 9264.4961 | dt 9.869 +type train | step 858 | loss 206.6785 397.1845 561.3039 876.4730 1214.1520 1704.4716 2260.0095 3282.5974 4509.6035 6927.4707 11541.5801 21816.1484 | lr 5.0e-04 | norm 9055.4023 | dt 9.841 +type train | step 859 | loss 195.3699 376.0074 527.8726 830.0255 1159.2003 1610.0896 2142.6536 3101.0835 4332.7539 6676.3281 11258.9824 21073.0820 | lr 5.0e-04 | norm 9702.5625 | dt 9.850 +type train | step 860 | loss 187.7196 361.8656 512.3148 807.2242 1126.4283 1571.3934 2092.2039 3032.4558 4255.0859 6584.3320 11142.2393 20726.0566 | lr 5.0e-04 | norm 8809.4727 | dt 9.835 +type train | step 861 | loss 199.6609 384.1971 541.3306 847.5461 1179.4266 1622.3751 2166.7676 3134.6960 4331.4434 6704.9146 11251.7217 20841.4277 | lr 5.0e-04 | norm 8294.2881 | dt 10.173 +type train | step 862 | loss 179.7968 345.2015 493.5278 785.9889 1108.6095 1563.8811 2095.9241 3067.2334 4299.8838 6688.0366 11265.8477 21071.7051 | lr 5.0e-04 | norm 11178.5361 | dt 9.844 +type train | step 863 | loss 188.7427 362.6784 517.6396 819.4847 1147.7485 1597.8885 2130.9268 3095.7493 4314.7178 6763.6177 11366.3379 21317.2148 | lr 5.0e-04 | norm 10381.6113 | dt 9.824 +type train | step 864 | loss 196.9586 375.4345 532.3145 830.5411 1155.7073 1606.9172 2145.7068 3108.8999 4309.1787 6632.5571 11143.8506 20866.5918 | lr 5.0e-04 | norm 8625.3389 | dt 9.856 +type train | step 865 | loss 175.2030 335.3587 481.9267 770.2726 1100.7589 1545.4945 2077.5771 3038.0068 4267.9053 6698.7031 11370.5938 21543.5352 | lr 5.0e-04 | norm 11724.1807 | dt 9.844 +type train | step 866 | loss 205.8174 396.5577 553.8007 861.5355 1194.9403 1647.1090 2175.2983 3150.8462 4299.4009 6573.8711 11027.0693 20375.2852 | lr 5.0e-04 | norm 10485.0605 | dt 9.847 +type train | step 867 | loss 175.5811 336.3821 487.5822 781.0657 1112.0593 1544.5602 2078.2107 3044.6252 4269.7603 6622.8267 11199.2803 20701.1621 | lr 5.0e-04 | norm 9759.8232 | dt 9.837 +type train | step 868 | loss 203.1170 391.3936 553.0909 865.2234 1205.1401 1660.8757 2220.4441 3231.9109 4420.0381 6792.3032 11408.7275 21198.6152 | lr 5.0e-04 | norm 8706.9385 | dt 9.869 +type train | step 869 | loss 175.8606 337.4219 488.9774 787.0909 1112.6891 1541.9242 2082.4043 3045.1323 4262.4404 6620.6372 11161.0215 20849.9258 | lr 5.0e-04 | norm 9012.2441 | dt 9.861 +type train | step 870 | loss 213.1329 411.3047 568.9244 874.7092 1213.9263 1676.8967 2241.6267 3231.6421 4434.2207 6777.0933 11249.3115 20795.2598 | lr 5.0e-04 | norm 9160.1045 | dt 9.838 +type train | step 871 | loss 199.9819 384.5510 546.6362 855.8860 1187.7676 1659.3301 2215.3135 3248.3428 4435.9951 6761.0752 11303.7100 20752.1113 | lr 5.0e-04 | norm 8374.0723 | dt 9.851 +type train | step 872 | loss 206.4053 396.2226 554.0091 860.8724 1190.3713 1634.0454 2173.5513 3129.2112 4331.5078 6636.5840 11168.2314 20689.7441 | lr 5.0e-04 | norm 8784.4922 | dt 9.864 +type train | step 873 | loss 182.2585 350.1317 504.6178 795.1724 1125.4199 1556.2800 2086.1497 3016.0417 4227.3711 6573.6826 11065.8350 20583.7305 | lr 5.0e-04 | norm 8337.9658 | dt 9.863 +type train | step 874 | loss 179.7804 343.6347 488.0532 779.2809 1100.7692 1529.9834 2065.9001 2993.5164 4197.3516 6525.9365 10966.9639 20550.4277 | lr 5.0e-04 | norm 10996.5537 | dt 9.846 +type train | step 875 | loss 229.3666 439.6446 606.6550 926.9374 1284.1165 1803.9482 2419.6711 3499.5151 4779.6270 7178.1294 11809.5566 21601.7969 | lr 5.0e-04 | norm 9761.5576 | dt 9.832 +type train | step 876 | loss 187.2388 359.5499 511.2431 808.7037 1131.5049 1575.8540 2111.7065 3068.7383 4245.1938 6538.4404 11000.5439 20598.4062 | lr 5.0e-04 | norm 10545.9248 | dt 9.846 +type train | step 877 | loss 225.5845 430.5893 605.4155 931.4330 1283.9155 1762.4464 2345.2373 3405.2207 4625.4717 7033.7471 11688.2451 21626.9238 | lr 5.0e-04 | norm 11617.3301 | dt 9.865 +type train | step 878 | loss 192.3932 368.7247 524.4954 828.2234 1159.5430 1613.9431 2171.3438 3158.9001 4386.9531 6785.1255 11544.8564 21683.4180 | lr 5.0e-04 | norm 9933.2959 | dt 9.847 +type train | step 879 | loss 199.8055 379.9936 537.2587 843.9091 1177.4354 1634.3531 2186.7832 3151.6348 4347.2788 6731.8066 11394.5771 21552.6289 | lr 5.0e-04 | norm 9955.8535 | dt 9.842 +type train | step 880 | loss 187.6477 357.6353 509.2983 791.7755 1116.3777 1541.0699 2070.9548 3010.1213 4192.7500 6498.9829 10955.9004 20267.2559 | lr 5.0e-04 | norm 9431.1455 | dt 9.850 +type train | step 881 | loss 194.0115 373.7217 530.5413 832.6990 1156.4991 1598.2097 2134.0830 3073.6948 4269.7578 6594.7324 11146.3242 20762.4824 | lr 5.0e-04 | norm 7672.7876 | dt 9.859 +type train | step 882 | loss 182.4323 349.1400 496.5665 787.7292 1116.3135 1564.5930 2116.9211 3112.1577 4334.0005 6759.4673 11399.9150 21228.3164 | lr 5.0e-04 | norm 9773.6855 | dt 9.837 +type train | step 883 | loss 189.1441 364.0312 515.6304 811.6824 1136.8726 1564.3442 2103.2844 3025.9646 4215.4009 6529.7690 10943.0117 20355.6992 | lr 5.0e-04 | norm 7701.8135 | dt 9.861 +type train | step 884 | loss 203.1631 390.4691 552.6684 874.4916 1220.4883 1708.9083 2263.5376 3295.1597 4503.1382 7011.5127 11946.0488 22747.5156 | lr 5.0e-04 | norm 15139.6885 | dt 9.837 +type train | step 885 | loss 182.5666 356.3260 512.6634 805.6581 1135.1428 1559.9935 2098.3147 3065.4998 4260.7031 6545.3589 11114.8066 20888.3301 | lr 5.0e-04 | norm 11045.5771 | dt 9.840 +type train | step 886 | loss 192.3786 374.7018 528.2359 825.7924 1165.4032 1588.4404 2123.5146 3120.1189 4269.7021 6472.6538 10984.3018 20683.6602 | lr 5.0e-04 | norm 16359.5654 | dt 9.830 +type train | step 887 | loss 225.6509 431.7909 609.2747 938.0087 1317.7344 1836.1267 2441.5237 3509.8032 4712.2383 6998.2861 11168.5439 20308.0273 | lr 5.0e-04 | norm 15147.5107 | dt 9.837 +type train | step 888 | loss 181.2500 344.7030 494.7144 781.8320 1106.0028 1539.6381 2090.0249 3049.5935 4264.7622 6630.9717 11164.7549 20893.0898 | lr 5.0e-04 | norm 11353.6650 | dt 9.850 +type train | step 889 | loss 189.0545 364.0664 514.5319 803.5775 1134.2430 1572.8771 2113.5986 3060.5586 4243.8252 6567.1450 11088.1582 20779.6055 | lr 5.0e-04 | norm 11259.5508 | dt 9.850 +type train | step 890 | loss 189.9877 365.2976 519.2570 810.8727 1148.0748 1583.8619 2126.8831 3066.6477 4257.4653 6579.3477 11078.2754 20599.2598 | lr 5.0e-04 | norm 9901.7090 | dt 9.865 +type train | step 891 | loss 193.9847 371.4168 528.1437 821.6589 1151.8456 1600.6859 2143.5547 3094.0972 4302.8237 6634.9185 11123.1484 20750.5254 | lr 5.0e-04 | norm 9357.7402 | dt 9.866 +type train | step 892 | loss 182.1818 349.0892 499.6961 784.2527 1109.5291 1533.6875 2075.0249 2992.6899 4184.8511 6491.7139 10948.6680 20322.1172 | lr 5.0e-04 | norm 9024.0498 | dt 9.861 +type train | step 893 | loss 179.9091 343.4025 487.9290 769.4066 1083.2629 1510.4596 2034.4070 2950.6687 4119.0576 6441.9463 10908.7109 20399.9609 | lr 5.0e-04 | norm 8703.4307 | dt 9.845 +type train | step 894 | loss 205.8124 395.2076 555.6831 849.7852 1178.5715 1616.6106 2150.7751 3081.4255 4264.7959 6505.0815 10946.8984 20570.8594 | lr 5.0e-04 | norm 9065.8496 | dt 9.846 +type train | step 895 | loss 191.1605 366.3624 524.4738 824.6071 1151.4775 1603.8197 2141.7864 3087.4773 4311.5107 6644.4492 11187.7158 20841.8047 | lr 5.0e-04 | norm 8338.7188 | dt 9.863 +type train | step 896 | loss 189.1753 363.2414 511.9641 798.4619 1116.2534 1546.7137 2064.1592 2977.8015 4121.7930 6324.5767 10533.1191 19600.5039 | lr 5.0e-04 | norm 9007.6270 | dt 9.843 +type train | step 897 | loss 168.1415 322.3055 467.6962 747.2002 1063.6571 1502.0038 2031.4099 2977.8225 4149.5078 6464.3774 10872.4072 20331.1309 | lr 5.0e-04 | norm 9457.0293 | dt 9.840 +type train | step 898 | loss 185.9391 355.2917 509.5320 800.9454 1127.1895 1549.4758 2081.6560 2995.4885 4203.0747 6481.4482 10872.2012 20144.5449 | lr 5.0e-04 | norm 8878.7891 | dt 9.849 +type train | step 899 | loss 194.8301 370.6126 514.0773 794.5782 1117.1403 1543.9426 2076.9924 3021.4634 4168.2349 6423.7319 10831.3369 20348.3223 | lr 5.0e-04 | norm 10449.3320 | dt 9.856 +type train | step 900 | loss 195.3022 377.7788 537.0691 850.7420 1186.9872 1663.2700 2224.7192 3241.0378 4498.4316 6923.1831 11608.2764 21703.7598 | lr 5.0e-04 | norm 8880.2764 | dt 9.850 +type train | step 901 | loss 197.4888 381.6526 535.2870 836.1418 1160.1860 1605.9426 2155.4404 3117.0027 4283.2178 6563.8105 10991.4014 20487.2539 | lr 5.0e-04 | norm 12488.1650 | dt 9.841 +type train | step 902 | loss 181.5984 344.5186 490.3042 780.0095 1101.5385 1523.5288 2068.4919 3013.5710 4221.0962 6543.4980 11041.0576 20688.4785 | lr 5.0e-04 | norm 10914.0664 | dt 9.850 +type train | step 903 | loss 190.6705 362.9234 514.2762 806.0037 1141.9149 1574.0818 2113.8081 3026.6445 4230.7769 6516.7300 10936.5205 20315.7910 | lr 5.0e-04 | norm 9858.9648 | dt 9.865 +type train | step 904 | loss 169.5732 324.6225 467.2680 754.4226 1065.6316 1505.8525 2046.7100 2984.7861 4164.8345 6440.5161 10829.8125 20313.7832 | lr 5.0e-04 | norm 11247.1699 | dt 9.833 +type train | step 905 | loss 196.3565 372.0399 525.1976 815.8932 1134.1422 1596.4279 2154.4226 3144.1765 4304.8501 6532.4478 10979.5215 20802.3457 | lr 5.0e-04 | norm 12150.2529 | dt 9.838 +type train | step 906 | loss 196.0694 376.0649 529.3224 823.1418 1158.9323 1606.8647 2169.4866 3137.2720 4361.3926 6632.7754 10997.7666 20468.3828 | lr 5.0e-04 | norm 11271.1006 | dt 9.852 +type train | step 907 | loss 184.4766 352.5347 497.2288 778.6375 1095.1718 1521.1617 2044.4128 2957.0464 4139.5107 6394.9297 10807.7090 20188.3125 | lr 5.0e-04 | norm 9445.8975 | dt 9.842 +type train | step 908 | loss 187.1474 358.6322 508.7223 790.6521 1115.0714 1539.3417 2071.5796 2993.8647 4182.9624 6444.9292 10792.6289 19991.7227 | lr 5.0e-04 | norm 8325.6396 | dt 9.856 +type train | step 909 | loss 188.8260 361.7233 513.0662 799.3785 1131.5642 1570.4463 2116.1123 3047.3894 4274.8135 6538.8540 10931.0332 20118.0742 | lr 5.0e-04 | norm 7806.1470 | dt 9.869 +type train | step 910 | loss 191.1912 367.3290 519.5588 808.4362 1131.4556 1563.4021 2097.6851 3032.6157 4228.1064 6496.5005 10902.0566 20485.5547 | lr 5.0e-04 | norm 10536.2002 | dt 9.848 +type train | step 911 | loss 184.1472 351.8780 499.7154 784.3637 1111.1622 1539.2300 2078.6497 3015.4187 4220.0986 6570.8042 11248.6660 21522.8262 | lr 5.0e-04 | norm 15160.9141 | dt 9.827 +type train | step 912 | loss 198.9092 380.0733 533.3062 821.9747 1149.3389 1576.9597 2106.0105 3044.6897 4221.4639 6468.8521 10834.3604 20144.7832 | lr 5.0e-04 | norm 8216.6309 | dt 9.862 +type train | step 913 | loss 182.5548 347.7086 494.0097 766.9617 1084.8999 1503.0768 2028.2883 2932.3340 4107.7134 6372.1904 10687.9590 19954.1406 | lr 5.0e-04 | norm 8681.0889 | dt 9.849 +type train | step 914 | loss 183.8513 350.1527 501.8036 786.8887 1107.2953 1543.4241 2080.9658 3015.1338 4208.8779 6487.1733 10861.0449 20101.2734 | lr 5.0e-04 | norm 8086.2915 | dt 9.859 +type train | step 915 | loss 191.8512 367.2844 518.9670 801.8381 1130.7213 1550.9657 2072.9673 2970.5737 4152.8057 6380.3179 10689.5459 19931.2285 | lr 5.0e-04 | norm 7810.4932 | dt 9.885 +type train | step 916 | loss 195.0339 371.5883 521.8627 818.5245 1137.6505 1566.4110 2089.5693 3013.1111 4201.9150 6394.0933 10708.3818 20033.3516 | lr 5.0e-04 | norm 9521.5781 | dt 9.851 +type train | step 917 | loss 190.4202 363.2426 515.1481 806.5284 1128.3004 1572.4302 2121.0344 3085.6270 4300.8013 6541.5620 10961.4219 20380.5664 | lr 5.0e-04 | norm 7881.8975 | dt 9.859 +type train | step 918 | loss 198.1215 378.9948 538.3810 841.4008 1176.5448 1647.4252 2222.7573 3228.5901 4481.6367 6862.5347 11422.3770 21334.3906 | lr 5.0e-04 | norm 9863.5361 | dt 9.841 +type train | step 919 | loss 180.1776 346.7926 493.6482 782.1902 1101.6122 1529.2850 2051.9226 2979.3960 4180.4478 6444.7573 10827.0352 20437.3027 | lr 5.0e-04 | norm 8527.5508 | dt 9.849 +type train | step 920 | loss 183.7395 351.4712 500.2635 788.1305 1105.9990 1536.4910 2063.5203 2991.2515 4187.5049 6442.4702 10756.2490 19980.2227 | lr 5.0e-04 | norm 7854.4414 | dt 9.858 +type train | step 921 | loss 192.5646 367.2874 520.4109 809.0864 1130.7340 1571.3921 2112.9097 3068.6938 4294.2681 6590.0366 11075.0352 20735.0293 | lr 5.0e-04 | norm 9611.2305 | dt 9.847 +type train | step 922 | loss 179.1983 344.8953 492.0512 775.6672 1098.7966 1550.2444 2091.8145 3048.9805 4245.5259 6512.2168 10909.2031 20481.2559 | lr 5.0e-04 | norm 8880.0664 | dt 9.840 +type train | step 923 | loss 194.6567 370.7611 527.0161 819.9155 1147.0999 1597.8230 2145.3569 3094.5322 4289.6250 6592.5132 11075.1670 20813.5996 | lr 5.0e-04 | norm 9371.0332 | dt 9.856 +type train | step 924 | loss 191.2181 368.9784 523.5732 816.8120 1141.6218 1593.2919 2125.9072 3065.1226 4258.4941 6508.3228 10916.0820 20236.4004 | lr 5.0e-04 | norm 7858.3706 | dt 9.849 +type train | step 925 | loss 183.7085 353.1943 501.3623 790.3042 1106.6775 1539.1454 2064.4827 2973.4390 4198.5278 6465.8140 10951.3877 20463.9570 | lr 5.0e-04 | norm 8338.8848 | dt 9.852 +type train | step 926 | loss 175.4746 335.1252 479.7787 756.0286 1069.1625 1493.4565 2028.8124 2956.3730 4147.0762 6421.4204 10829.9580 20244.6426 | lr 5.0e-04 | norm 8642.0840 | dt 9.842 +type train | step 927 | loss 186.6425 356.9119 502.6578 783.2193 1100.8856 1533.8699 2061.0339 2983.6914 4172.5088 6431.7583 10841.7910 20318.0703 | lr 5.0e-04 | norm 8934.3457 | dt 9.853 +type train | step 928 | loss 178.8800 342.0366 490.1515 771.4318 1090.6514 1523.9735 2065.0457 3027.7771 4245.5063 6531.8423 10963.8438 20419.5625 | lr 5.0e-04 | norm 7944.5112 | dt 9.862 +type train | step 929 | loss 192.0890 367.7032 513.8273 803.5844 1128.5603 1578.1505 2111.9045 3069.5156 4283.1763 6535.5449 10966.0137 20629.5352 | lr 5.0e-04 | norm 9275.0078 | dt 9.856 +type train | step 930 | loss 173.6563 332.8171 480.9007 761.8712 1085.2921 1515.7129 2042.5208 2979.3064 4222.5581 6492.4624 10940.5400 20412.0293 | lr 5.0e-04 | norm 8443.8672 | dt 9.863 +type train | step 931 | loss 171.5308 327.5854 466.7455 738.2200 1048.6843 1470.9912 1989.9106 2895.7698 4108.2217 6341.7773 10613.4404 19774.2285 | lr 5.0e-04 | norm 8822.5537 | dt 9.843 +type train | step 932 | loss 176.4509 339.0034 488.0292 769.1161 1086.3136 1500.4840 2025.1130 2929.9451 4123.8418 6360.8037 10690.4268 19913.5000 | lr 5.0e-04 | norm 8359.3877 | dt 9.848 +type train | step 933 | loss 180.1125 340.5781 488.7653 764.7485 1080.9990 1513.5182 2044.4165 2949.8372 4150.3350 6374.6221 10700.6963 19789.8672 | lr 5.0e-04 | norm 7286.7080 | dt 9.854 +type train | step 934 | loss 200.6147 385.0146 543.0114 848.3940 1176.8469 1613.1377 2155.8228 3092.9470 4287.6260 6538.2544 11035.6689 20649.7773 | lr 5.0e-04 | norm 9880.3467 | dt 9.865 +type train | step 935 | loss 179.2801 340.2188 488.7048 773.5346 1095.1675 1528.6736 2060.7400 2984.6814 4194.4282 6473.8672 10873.7783 20285.7695 | lr 5.0e-04 | norm 8027.2402 | dt 9.864 +type train | step 936 | loss 184.6072 353.8708 500.8658 787.4783 1108.3325 1551.1355 2089.5457 3035.8083 4230.3589 6489.1367 10895.1836 20352.2715 | lr 5.0e-04 | norm 8608.7461 | dt 9.847 +type train | step 937 | loss 158.5162 301.0430 443.2484 713.7167 1022.3085 1434.7007 1961.0354 2865.8208 4063.8250 6288.2964 10651.2979 20072.5195 | lr 5.0e-04 | norm 10316.9512 | dt 9.843 +type train | step 938 | loss 171.6948 329.4893 475.2231 748.1841 1065.3997 1485.1674 1989.0179 2868.7253 4039.7092 6200.7490 10344.7773 19174.8379 | lr 5.0e-04 | norm 8888.6006 | dt 9.852 +type train | step 939 | loss 170.9458 324.8944 463.3754 729.9969 1043.6710 1451.9218 1959.7047 2839.5522 3994.9456 6149.5703 10327.7793 19131.0176 | lr 5.0e-04 | norm 7545.4609 | dt 9.852 +type train | step 940 | loss 186.4665 355.1794 502.3907 778.9491 1098.1700 1532.0863 2058.4563 2988.4583 4168.3652 6413.0562 10689.6309 19708.0703 | lr 5.0e-04 | norm 9409.4375 | dt 9.872 +type train | step 941 | loss 180.3633 342.4350 490.6675 772.0681 1087.8751 1511.8970 2023.9733 2921.4329 4080.7800 6264.0239 10495.8125 19478.9453 | lr 5.0e-04 | norm 7612.7148 | dt 9.851 +type train | step 942 | loss 186.9761 356.0201 499.7396 780.1897 1096.8218 1518.0818 2033.9921 2920.0791 4044.3210 6171.7451 10270.2080 19006.9258 | lr 5.0e-04 | norm 9180.2490 | dt 9.833 +type train | step 943 | loss 179.6212 340.8520 490.0428 775.1757 1097.2279 1526.2749 2047.8984 2957.6155 4155.0171 6408.8682 10793.9512 20208.5957 | lr 5.0e-04 | norm 8163.2197 | dt 9.859 +type train | step 944 | loss 171.9468 323.4929 463.6535 740.6759 1047.5396 1458.6995 1951.1525 2810.9158 3937.4905 6102.6841 10340.3740 19514.6816 | lr 5.0e-04 | norm 13625.0713 | dt 9.838 +type train | step 945 | loss 166.7124 317.1281 460.0772 725.2054 1036.0999 1457.9390 1976.4910 2893.6130 4068.8088 6276.3574 10544.0146 19854.8945 | lr 5.0e-04 | norm 9112.0977 | dt 9.851 +type train | step 946 | loss 171.7014 328.9499 473.7124 745.0911 1060.6061 1492.4417 2010.9698 2921.0430 4079.8850 6246.0654 10433.9902 19483.4648 | lr 5.0e-04 | norm 8905.4473 | dt 9.864 +type train | step 947 | loss 181.2813 348.4403 497.2842 771.7469 1091.3789 1520.8718 2051.1675 2972.5166 4125.9819 6384.1543 10725.6514 20099.5977 | lr 5.0e-04 | norm 8734.2598 | dt 9.855 +type train | step 948 | loss 169.7297 327.2436 472.0685 750.1512 1067.5366 1498.2579 2036.1968 2983.6592 4164.6294 6461.9888 10832.1797 20169.2109 | lr 5.0e-04 | norm 9387.6309 | dt 9.865 +type train | step 949 | loss 170.8240 325.7119 465.7223 733.1933 1049.0278 1453.3550 1970.1837 2855.4075 4004.3406 6210.4458 10497.0576 19574.8750 | lr 5.0e-04 | norm 8424.8643 | dt 9.867 +type train | step 950 | loss 180.2061 343.5500 486.5668 758.7949 1072.6227 1530.2681 2053.6079 3012.9722 4190.2588 6433.1865 10762.8574 19887.3184 | lr 5.0e-04 | norm 7168.8301 | dt 9.853 +type train | step 951 | loss 189.7599 363.8266 510.8781 796.7819 1110.3734 1562.8994 2060.3135 2990.0557 4117.4648 6318.3423 10572.8486 19711.9805 | lr 5.0e-04 | norm 7590.0537 | dt 9.848 +type train | step 952 | loss 178.6666 339.2441 480.5508 754.7686 1062.0826 1512.4050 2035.3085 2983.4324 4109.1055 6344.7358 10598.3057 19750.3809 | lr 5.0e-04 | norm 7848.8462 | dt 9.851 +type train | step 953 | loss 169.3489 323.1288 461.5344 728.8443 1041.9000 1477.2870 1987.2319 2916.8396 4065.5796 6263.6699 10400.4844 19343.6797 | lr 5.0e-04 | norm 8763.3848 | dt 9.848 +type train | step 954 | loss 176.6156 334.3199 473.6429 747.1822 1056.9865 1511.0229 2036.0432 2962.5569 4104.1699 6335.6982 10658.5879 19906.8828 | lr 5.0e-04 | norm 8015.0107 | dt 9.851 +type train | step 955 | loss 176.3413 335.7728 477.9565 749.4948 1062.3479 1506.2499 2018.3999 2903.5349 4062.6577 6270.5811 10518.3779 19765.7070 | lr 5.0e-04 | norm 9210.6260 | dt 9.849 +type train | step 956 | loss 169.8650 320.6763 461.1639 726.1170 1037.9387 1467.8153 1990.8508 2878.6646 4015.5913 6177.1465 10392.9121 19346.9473 | lr 5.0e-04 | norm 8329.5771 | dt 9.859 +type train | step 957 | loss 171.3284 323.8844 463.9807 726.6783 1037.0748 1469.7223 1989.6565 2859.1650 4012.8767 6239.4424 10494.5391 19454.9473 | lr 5.0e-04 | norm 7943.1548 | dt 9.851 +type train | step 958 | loss 177.0378 339.9218 488.3262 764.1246 1091.8606 1589.8826 2134.5686 3074.4692 4280.5254 6557.6167 10826.2695 19960.8574 | lr 5.0e-04 | norm 8295.8916 | dt 9.875 +type train | step 959 | loss 171.6411 326.7609 467.8066 733.9727 1043.9468 1466.6860 1992.7048 2833.9272 3996.0012 6149.9473 10265.8574 18973.1191 | lr 5.0e-04 | norm 7381.5005 | dt 9.874 +type train | step 960 | loss 191.3799 367.2137 526.6456 818.8586 1148.3206 1610.5291 2165.8047 3065.7893 4279.5996 6516.1494 10855.7432 20151.6016 | lr 5.0e-04 | norm 9675.8740 | dt 9.859 +type train | step 961 | loss 175.3610 333.4584 475.9854 749.7939 1063.9119 1507.7626 2025.3419 2905.6096 4011.9077 6163.1396 10334.5215 19268.6445 | lr 5.0e-04 | norm 8474.9053 | dt 9.858 +type train | step 962 | loss 187.5192 355.5325 496.1001 777.3242 1088.4674 1552.3821 2115.8257 3069.2163 4174.8955 6352.0112 10602.0098 20129.8477 | lr 5.0e-04 | norm 12397.2539 | dt 9.828 +type train | step 963 | loss 196.9942 374.7209 523.8510 809.1625 1130.8431 1597.6619 2156.8267 3073.8804 4133.0464 6259.4360 10348.3555 19395.4453 | lr 5.0e-04 | norm 9134.3320 | dt 9.864 +type train | step 964 | loss 163.1966 312.5005 448.1240 713.6683 1020.4966 1454.2594 1981.7124 2833.7920 3975.6562 6135.7715 10316.3545 19317.8750 | lr 5.0e-04 | norm 9102.2471 | dt 9.856 +type train | step 965 | loss 175.7114 334.7141 476.6862 745.6080 1059.8477 1502.5190 2023.4857 2922.8887 4059.3313 6218.0537 10379.9141 19195.6836 | lr 5.0e-04 | norm 8034.1636 | dt 9.853 +type train | step 966 | loss 176.0448 337.3383 486.2708 766.2861 1094.9833 1544.6650 2102.2847 3019.5095 4204.9912 6449.9043 10758.8857 20070.5215 | lr 5.0e-04 | norm 9702.7480 | dt 9.854 +type train | step 967 | loss 188.8595 361.8216 516.1016 800.1652 1134.6018 1581.9211 2136.9973 3017.7771 4207.9595 6475.5571 10874.3193 20265.3691 | lr 5.0e-04 | norm 10196.7051 | dt 9.862 +type train | step 968 | loss 163.1433 309.7037 447.9034 707.7232 1015.5706 1482.8033 2000.1243 2862.0349 4010.1377 6178.0903 10311.4629 19046.4961 | lr 5.0e-04 | norm 7861.4053 | dt 9.857 +type train | step 969 | loss 174.4076 332.2883 479.8505 754.9288 1076.5299 1545.2188 2060.1284 2939.7012 4081.5889 6255.3252 10441.7773 19400.0684 | lr 5.0e-04 | norm 7745.9365 | dt 9.856 +type train | step 970 | loss 178.8384 345.1068 492.8477 769.7836 1091.8190 1566.2950 2104.2332 3007.5522 4174.5073 6300.0005 10423.9619 19238.1270 | lr 5.0e-04 | norm 9427.7109 | dt 9.835 +type train | step 971 | loss 194.3203 373.8691 531.3033 816.5219 1139.7377 1627.4429 2182.5596 3076.7417 4236.6733 6378.2061 10520.6221 19410.8594 | lr 5.0e-04 | norm 7989.0781 | dt 9.869 +type train | step 972 | loss 165.7021 316.4030 460.2963 733.1646 1043.4769 1494.4785 2024.7791 2909.5298 4082.4482 6303.8306 10584.2461 19630.7656 | lr 5.0e-04 | norm 7468.8027 | dt 9.865 +type train | step 973 | loss 173.9395 332.0032 469.5496 728.4134 1040.1057 1478.2097 2018.3838 2865.3496 3992.6074 6133.6968 10242.0176 18929.7715 | lr 5.0e-04 | norm 7578.5659 | dt 9.859 +type train | step 974 | loss 161.9680 310.7019 449.7259 712.2484 1011.7526 1433.8468 1958.3502 2796.3049 3911.9067 6016.0684 10137.7803 18849.3906 | lr 5.0e-04 | norm 7064.5210 | dt 9.858 +type train | step 975 | loss 157.6279 301.2335 432.9079 683.7913 983.9838 1409.7563 1929.9434 2774.9421 3889.4426 6029.7407 10099.6543 18845.1875 | lr 5.0e-04 | norm 7638.3691 | dt 9.858 +type train | step 976 | loss 168.3477 320.8510 462.4194 729.1752 1041.7833 1477.2656 2027.3667 2916.7183 4080.8938 6282.2817 10459.3701 19445.5020 | lr 5.0e-04 | norm 7043.6401 | dt 9.861 +type train | step 977 | loss 170.2359 324.2424 465.2307 726.6577 1040.2139 1502.1803 2040.1433 2920.7964 4053.5642 6240.8774 10481.0107 19418.1094 | lr 5.0e-04 | norm 7951.1870 | dt 9.849 +type train | step 978 | loss 187.3250 355.8241 501.6699 779.6707 1094.2666 1534.6602 2098.6990 2935.9463 4038.6304 6114.1377 10157.0801 18915.7188 | lr 5.0e-04 | norm 8531.7871 | dt 9.843 +type train | step 979 | loss 187.1800 356.2162 502.1332 772.9348 1087.9625 1556.5952 2103.3750 2951.1787 4061.1672 6167.9082 10315.0078 19299.0605 | lr 5.0e-04 | norm 9072.9219 | dt 9.840 +type train | step 980 | loss 182.1109 347.1895 493.4008 765.7311 1084.6439 1538.3096 2093.3596 2945.0137 4077.1631 6217.7690 10382.7305 19307.8262 | lr 5.0e-04 | norm 8141.6055 | dt 9.858 +type train | step 981 | loss 212.4671 414.1154 567.1526 861.7155 1208.2341 1697.1550 2319.7490 3234.0662 4475.2510 6723.7100 10963.4629 19761.8359 | lr 5.0e-04 | norm 10717.7656 | dt 9.837 +type train | step 982 | loss 167.4386 319.1454 462.1852 724.4606 1032.9547 1475.8342 2019.6252 2833.5264 3973.3047 6112.2041 10260.2842 18912.5059 | lr 5.0e-04 | norm 8148.8535 | dt 9.850 +type train | step 983 | loss 142.4379 270.2837 396.1807 641.1968 938.7556 1357.6844 1916.7922 2718.3054 3871.8997 6041.3770 10175.8125 19060.0020 | lr 5.0e-04 | norm 9962.2158 | dt 9.835 +type train | step 984 | loss 161.3765 307.5065 445.3110 702.8616 1007.7583 1442.8021 1996.3727 2807.5166 3943.8931 6040.4863 10120.2832 18811.1562 | lr 5.0e-04 | norm 7792.7935 | dt 9.854 +type train | step 985 | loss 165.4481 314.0487 452.5426 711.1392 1010.8914 1445.0889 1977.9392 2799.8376 3928.9009 5995.1084 10044.0693 18533.0371 | lr 5.0e-04 | norm 7405.3179 | dt 9.859 +type train | step 986 | loss 172.9432 326.9303 472.0695 739.8923 1055.0247 1513.5686 2067.8376 2896.1484 4067.8145 6204.6968 10345.9551 19057.3555 | lr 5.0e-04 | norm 6848.9971 | dt 9.872 +type train | step 987 | loss 192.7507 365.9554 526.3365 824.2275 1164.0630 1673.8909 2310.0642 3240.6470 4447.2983 6779.0454 11325.7012 21293.5215 | lr 5.0e-04 | norm 11613.3857 | dt 9.846 +type train | step 988 | loss 197.6298 374.6150 524.0654 805.5607 1121.4014 1604.7098 2183.8267 3021.6973 4142.3770 6234.4224 10304.0205 19105.4570 | lr 5.0e-04 | norm 8640.7803 | dt 9.851 +type train | step 989 | loss 175.6515 335.8451 479.3912 749.6442 1062.1581 1521.1167 2057.7754 2895.4880 4040.1086 6155.2246 10265.8779 19118.2051 | lr 5.0e-04 | norm 7736.7827 | dt 9.856 +type train | step 990 | loss 183.3454 348.0327 490.4821 758.8354 1071.4620 1529.6763 2079.4834 2918.8132 4038.2292 6164.2563 10264.8848 19036.2461 | lr 5.0e-04 | norm 7677.9146 | dt 9.864 +type train | step 991 | loss 170.1350 323.0396 461.6551 719.9326 1028.5028 1470.5493 2028.0983 2857.4893 3955.3596 6019.4189 10066.2754 18762.9844 | lr 5.0e-04 | norm 8661.8838 | dt 9.858 +type train | step 992 | loss 169.8659 322.9156 458.8350 723.0156 1022.2800 1479.9048 2010.2092 2870.8145 3994.8831 6171.3501 10443.7334 19550.1465 | lr 5.0e-04 | norm 11289.4521 | dt 9.843 +type train | step 993 | loss 185.0544 348.1484 494.0792 768.5109 1080.4387 1533.0763 2080.5640 2897.3062 3970.0916 6016.4668 9961.2900 18557.7109 | lr 5.0e-04 | norm 8724.5713 | dt 9.849 +type train | step 994 | loss 164.2151 309.7575 446.9784 705.9797 1012.2200 1469.0958 2006.5244 2835.8242 3993.9607 6134.5786 10322.2227 19207.1426 | lr 5.0e-04 | norm 8893.7686 | dt 9.851 +type train | step 995 | loss 169.7660 321.9418 463.2425 728.3380 1037.6346 1499.8280 2015.5980 2848.3896 4010.2432 6158.1157 10325.8564 19170.5254 | lr 5.0e-04 | norm 9022.2012 | dt 9.851 +type train | step 996 | loss 166.6721 317.8495 459.4933 727.9615 1042.2949 1521.1715 2091.2219 2982.8604 4161.7236 6389.8872 10770.4863 20190.4844 | lr 5.0e-04 | norm 9352.4609 | dt 9.852 +type train | step 997 | loss 155.2018 296.7737 431.2991 681.7874 985.7675 1425.1469 1941.7715 2767.3635 3920.3877 6063.8799 10166.4082 19026.8164 | lr 5.0e-04 | norm 10459.1631 | dt 9.848 +type train | step 998 | loss 166.8237 318.1572 463.1292 735.4460 1052.9283 1547.5599 2085.7344 2949.1660 4138.2505 6312.5322 10550.0654 19544.0430 | lr 5.0e-04 | norm 8122.2007 | dt 9.866 +type train | step 999 | loss 170.7395 325.1429 469.6977 740.4888 1050.9857 1536.1099 2070.4131 2927.7256 4103.5684 6300.9204 10511.8682 19434.3105 | lr 5.0e-04 | norm 7679.4512 | dt 9.842 +type train | step 1000 | loss 181.9575 348.1122 490.5294 760.1145 1073.6658 1545.0112 2066.6008 2927.0312 4057.6536 6182.6025 10285.1045 19042.6348 | lr 5.0e-04 | norm 8159.7080 | dt 9.856 +type train | step 1001 | loss 178.2688 336.1434 478.0582 744.9851 1057.5078 1540.4161 2058.9561 2959.1372 4086.1719 6222.9297 10360.6895 19094.2852 | lr 5.0e-04 | norm 7286.8369 | dt 9.854 +type train | step 1002 | loss 177.6628 335.9584 475.0268 736.8401 1045.9817 1520.2609 2030.7906 2881.2766 3990.7129 6116.2671 10183.3408 18863.5703 | lr 5.0e-04 | norm 7400.5723 | dt 9.848 +type train | step 1003 | loss 164.0310 314.4008 452.5878 707.4447 1011.4261 1478.9490 1976.3665 2811.9536 3953.9014 6078.4277 10186.1270 18817.4512 | lr 5.0e-04 | norm 7583.8911 | dt 9.842 +type train | step 1004 | loss 165.6214 314.6584 453.3624 715.2743 1020.0094 1466.3894 1974.4724 2796.8616 3920.3303 6043.8882 10102.9648 18669.7832 | lr 5.0e-04 | norm 7649.5967 | dt 9.853 +type train | step 1005 | loss 175.1098 331.9512 480.4680 750.2330 1068.0760 1545.9795 2063.8123 2921.3152 4095.8662 6314.8369 10529.0234 19482.4238 | lr 5.0e-04 | norm 8075.3525 | dt 9.862 +type train | step 1006 | loss 169.5089 325.1688 463.1993 727.1414 1030.1757 1488.1572 1984.4376 2823.2026 3966.8267 6108.3999 10180.7158 18851.2168 | lr 5.0e-04 | norm 6755.3403 | dt 9.862 +type train | step 1007 | loss 153.7613 291.0852 426.4679 684.7645 988.6731 1437.3738 1949.9373 2815.0132 3990.8752 6177.1704 10333.5654 19278.1250 | lr 5.0e-04 | norm 11822.7217 | dt 9.842 +type train | step 1008 | loss 164.5030 314.0244 456.6341 721.0613 1037.7601 1495.3950 2018.5627 2878.5444 4046.4375 6261.8848 10453.7314 19348.1367 | lr 5.0e-04 | norm 9547.8447 | dt 9.844 +type train | step 1009 | loss 170.4053 322.3235 460.2225 726.6428 1034.5194 1515.3506 2021.3126 2897.6245 4015.1023 6132.4209 10189.1885 18924.0781 | lr 5.0e-04 | norm 8858.1475 | dt 9.853 +type train | step 1010 | loss 178.9106 337.7199 478.9543 744.6104 1053.4521 1524.9381 2050.7969 2910.5259 4027.2913 6142.9717 10220.6904 18934.6250 | lr 5.0e-04 | norm 7717.7925 | dt 9.851 +type train | step 1011 | loss 166.9143 314.8451 451.5009 703.4456 1006.8492 1461.5214 1955.5183 2798.1230 3899.4011 6037.3154 10177.5283 19034.5762 | lr 5.0e-04 | norm 9098.4775 | dt 9.844 +type train | step 1012 | loss 179.7852 342.8349 490.6535 765.1326 1087.8900 1562.1726 2073.9204 2940.9951 4084.9690 6243.4854 10354.5146 19097.2930 | lr 5.0e-04 | norm 8944.0645 | dt 9.867 +type train | step 1013 | loss 171.0522 330.7062 474.7431 752.8326 1069.8568 1541.2585 2085.5383 2964.7346 4147.5542 6418.4634 10759.7441 19995.0801 | lr 5.0e-04 | norm 8783.7930 | dt 9.838 +type train | step 1014 | loss 162.4378 309.4486 448.9454 706.0175 1015.9938 1464.8783 1972.6302 2787.2559 3933.3064 6059.0542 10146.7490 18736.5176 | lr 5.0e-04 | norm 7368.5806 | dt 9.869 +type train | step 1015 | loss 166.9128 317.4889 458.5947 717.6511 1021.6931 1470.4657 1971.6241 2779.1619 3896.5840 5958.6235 9850.1309 18141.7188 | lr 5.0e-04 | norm 7429.5366 | dt 9.859 +type train | step 1016 | loss 162.0498 307.9906 442.0329 694.2590 996.7948 1457.7783 1954.2695 2808.6038 3908.5854 6007.6470 10107.9160 18614.1816 | lr 5.0e-04 | norm 7353.1001 | dt 9.858 +type train | step 1017 | loss 161.0305 306.2183 442.2466 706.6075 1000.2276 1449.9005 1949.5026 2788.2661 3914.6650 6010.3174 10056.7998 18561.3828 | lr 5.0e-04 | norm 7443.3984 | dt 9.862 +type train | step 1018 | loss 153.1318 290.4462 425.0374 677.9257 972.7348 1408.6056 1905.2693 2721.2415 3848.7830 5943.9946 9976.8135 18320.9160 | lr 5.0e-04 | norm 8035.1343 | dt 9.873 +type train | step 1019 | loss 169.1840 320.3860 457.7313 714.4482 1018.2946 1464.9209 1965.8304 2792.2437 3919.2402 6031.1323 10071.0762 18454.8105 | lr 5.0e-04 | norm 7812.8452 | dt 9.857 +type train | step 1020 | loss 160.3386 305.7045 444.9176 704.0303 1009.5970 1475.8812 1996.4147 2850.4985 4002.9993 6186.4941 10416.5498 19104.1738 | lr 5.0e-04 | norm 7495.4834 | dt 9.872 +type train | step 1021 | loss 147.5604 280.0460 414.2977 665.5152 957.1104 1400.1780 1902.6921 2715.7263 3874.9646 6035.4634 10199.8779 18978.4297 | lr 5.0e-04 | norm 8594.0850 | dt 9.851 +type train | step 1022 | loss 160.9845 306.3381 441.3067 703.9240 1000.1090 1469.2014 1962.6298 2794.9292 3944.2065 6124.1445 10278.5518 18914.1387 | lr 5.0e-04 | norm 7598.1333 | dt 9.854 +type train | step 1023 | loss 160.7558 305.7895 441.2256 713.2833 991.3785 1440.5500 1927.8407 2732.4719 3833.4045 5916.8862 9829.0186 18048.5664 | lr 5.0e-04 | norm 7469.7969 | dt 9.861 +type train | step 1024 | loss 172.2683 326.6343 468.7272 738.3551 1046.8386 1530.9866 2008.6396 2850.0681 3953.4690 6055.3921 10140.8145 18617.0820 | lr 5.0e-04 | norm 11375.6055 | dt 9.840 +type train | step 1025 | loss 156.5893 299.2669 434.4162 692.4949 1003.1227 1528.0240 2052.7715 2959.4238 4163.8276 6460.8418 10709.0264 19687.0938 | lr 5.0e-04 | norm 8588.6357 | dt 9.861 +type train | step 1026 | loss 156.2154 296.9992 431.0266 690.9791 983.1287 1434.1655 1938.8531 2734.2534 3858.5403 5977.1729 10074.8262 18776.0898 | lr 5.0e-04 | norm 9780.2910 | dt 9.865 +type train | step 1027 | loss 168.0186 317.1700 452.9893 721.7916 1007.1484 1476.2488 1973.3340 2799.9626 3899.7390 5964.3232 9995.5205 18445.9668 | lr 5.0e-04 | norm 8842.4336 | dt 9.861 +type train | step 1028 | loss 156.3239 297.1100 431.4899 686.9050 978.7682 1439.5189 1923.7340 2736.9036 3851.6763 6019.3359 10033.1846 18525.7246 | lr 5.0e-04 | norm 8330.1934 | dt 9.867 +type train | step 1029 | loss 172.5038 328.4816 472.0736 748.4301 1041.0682 1510.2043 2004.6395 2837.7715 3966.7886 6169.7407 10212.6387 18788.2363 | lr 5.0e-04 | norm 7667.3232 | dt 9.872 +type train | step 1030 | loss 170.3365 325.3302 468.8367 772.0131 1047.3539 1507.1532 1997.3262 2831.6152 3927.6423 6085.9941 10119.0381 18752.8164 | lr 5.0e-04 | norm 7459.4658 | dt 9.851 +type train | step 1031 | loss 168.4842 317.1824 453.9014 737.3162 1012.6963 1479.2443 1980.4131 2809.9429 3895.0518 5997.7671 9902.5820 18324.7637 | lr 5.0e-04 | norm 7806.0562 | dt 9.847 +type train | step 1032 | loss 157.1556 298.7278 434.4424 717.4406 997.0493 1470.4034 1959.6919 2800.0601 3933.0244 6128.4253 10120.5732 18523.5684 | lr 5.0e-04 | norm 7449.5435 | dt 9.856 +type train | step 1033 | loss 155.8033 298.2742 434.1456 709.3843 989.0263 1444.7705 1932.0394 2767.4626 3894.5767 6103.0220 10131.3066 18653.2500 | lr 5.0e-04 | norm 7252.4067 | dt 9.857 +type train | step 1034 | loss 161.0154 307.3048 446.6566 736.0205 1009.3310 1470.2823 1965.2684 2794.7715 3957.9099 6147.0430 10152.4531 18607.4863 | lr 5.0e-04 | norm 7304.6880 | dt 9.857 +type train | step 1035 | loss 173.5057 328.3403 470.0992 752.3893 1037.4147 1508.6544 2019.9137 2849.3970 3963.5613 6110.3374 10043.9775 18458.0547 | lr 5.0e-04 | norm 7514.2139 | dt 9.852 +type train | step 1036 | loss 163.5553 310.6778 447.7438 744.7388 1001.0131 1479.1000 1945.1650 2732.6106 3837.7041 5957.8965 9830.4951 18074.9336 | lr 5.0e-04 | norm 7576.3457 | dt 9.860 +type train | step 1037 | loss 166.5097 315.1164 452.4991 743.9752 1009.6218 1478.3643 1957.2495 2781.1606 3894.3958 6073.3540 10098.4639 18636.4219 | lr 5.0e-04 | norm 7172.2920 | dt 9.870 +type train | step 1038 | loss 172.3482 328.2365 473.5240 773.2382 1048.0482 1529.3318 2044.1040 2887.7654 4011.6948 6164.5059 10187.0332 18720.5078 | lr 5.0e-04 | norm 6936.8516 | dt 9.859 +type train | step 1039 | loss 157.5255 303.6721 441.5042 744.6332 1006.7057 1469.2629 1989.9910 2848.9412 3986.5200 6253.0542 10499.3848 19646.7031 | lr 5.0e-04 | norm 10074.5684 | dt 9.862 +type train | step 1040 | loss 155.0076 294.3698 424.8671 709.5565 967.4700 1416.4469 1913.5209 2710.6943 3816.7817 6006.5024 9998.0811 18491.0430 | lr 5.0e-04 | norm 7764.8105 | dt 9.875 +type train | step 1041 | loss 162.6570 310.4423 453.7295 739.6396 1025.3191 1498.5068 2017.6044 2897.9104 4061.3401 6302.8862 10364.8496 18880.7637 | lr 5.0e-04 | norm 8177.5713 | dt 9.871 +type train | step 1042 | loss 179.6178 349.5727 504.0229 825.9019 1122.9910 1629.3353 2179.1135 3089.5129 4241.5039 6482.3711 10635.3994 19744.7207 | lr 5.0e-04 | norm 10038.5605 | dt 9.855 +type train | step 1043 | loss 180.3625 341.6711 481.5609 776.4756 1050.5615 1537.8845 2027.6826 2847.9536 3915.7170 6006.2046 9820.1377 17927.9727 | lr 5.0e-04 | norm 8161.5552 | dt 9.861 +type train | step 1044 | loss 160.6526 303.2519 438.1139 730.7526 995.5030 1464.0751 1969.6116 2801.7122 3923.8037 6093.6294 10104.9131 18618.5469 | lr 5.0e-04 | norm 7877.3740 | dt 9.867 +type train | step 1045 | loss 153.8329 292.4223 427.2828 711.1290 982.3127 1437.0859 1939.6217 2724.0469 3811.2854 5958.9258 9919.7305 18456.0156 | lr 5.0e-04 | norm 8515.5732 | dt 9.846 +type train | step 1046 | loss 169.7572 319.9180 462.5491 744.4183 1027.5365 1486.5940 1994.3053 2805.4626 3916.2886 6133.2959 10028.9668 18573.3340 | lr 5.0e-04 | norm 8585.3271 | dt 9.854 +type train | step 1047 | loss 163.3139 308.5502 443.0349 723.3905 991.2038 1441.9293 1921.8235 2711.9441 3822.0525 5983.3389 9816.8809 18054.7598 | lr 5.0e-04 | norm 7709.1138 | dt 9.871 +type train | step 1048 | loss 164.3380 311.9209 448.9496 728.9240 1009.5760 1476.2338 1972.3484 2786.7200 3922.6604 6139.8828 10143.0176 18557.0117 | lr 5.0e-04 | norm 7470.3857 | dt 9.881 +type train | step 1049 | loss 158.8209 300.1391 437.2049 718.7396 996.1788 1443.7169 1927.6213 2733.8625 3842.3271 5980.2529 9794.6797 18003.1348 | lr 5.0e-04 | norm 10453.6719 | dt 9.863 +type train | step 1050 | loss 160.5230 305.7660 445.0581 725.3274 1007.8361 1473.1765 1993.6873 2827.3923 3986.4600 6268.0649 10301.9414 18922.8262 | lr 5.0e-04 | norm 9713.0557 | dt 9.854 +type train | step 1051 | loss 160.7133 306.2633 445.5068 719.7407 999.4106 1457.6448 1959.1915 2793.5752 3921.0630 6118.1743 10087.1875 18606.1895 | lr 5.0e-04 | norm 8019.6968 | dt 9.857 +type train | step 1052 | loss 182.2250 344.5479 492.0381 790.4005 1089.4884 1558.1973 2100.9395 2944.2463 4114.4038 6474.5977 10759.4863 20032.1230 | lr 5.0e-04 | norm 11410.6045 | dt 9.874 +type train | step 1053 | loss 148.5018 283.9622 419.1141 689.6726 970.6749 1421.0447 1934.7886 2776.8357 3937.9539 6174.6816 10170.3682 18660.2852 | lr 5.0e-04 | norm 11909.1260 | dt 9.850 +type train | step 1054 | loss 160.1317 306.6550 446.2668 727.7579 1012.6035 1478.1736 2022.1003 2858.7559 4018.8840 6326.4448 10549.2402 19426.4805 | lr 4.9e-04 | norm 14577.1318 | dt 9.863 +type train | step 1055 | loss 186.9040 353.4631 499.7747 794.1558 1089.7545 1563.8594 2096.2043 2932.4878 4026.7378 6166.6064 10090.3623 18446.4023 | lr 4.9e-04 | norm 10151.5654 | dt 9.856 +type train | step 1056 | loss 173.9722 331.8950 474.6042 768.5992 1052.9728 1531.3002 2061.5815 2913.7810 4071.0911 6315.6226 10324.0957 19082.7852 | lr 4.9e-04 | norm 10026.7227 | dt 9.880 +type train | step 1057 | loss 154.0776 290.7046 421.0229 714.3616 958.3770 1409.0864 1910.9845 2708.4094 3807.7908 5959.6743 9903.3262 18306.5684 | lr 4.9e-04 | norm 10330.7236 | dt 9.852 +type train | step 1058 | loss 169.1729 322.3438 461.8006 771.7387 1030.7806 1505.0066 2050.5247 2890.0188 4017.3657 6208.8628 10112.2861 18722.2344 | lr 4.9e-04 | norm 10294.9414 | dt 9.863 +type train | step 1059 | loss 168.4390 318.6630 458.3797 759.3307 1015.9515 1473.7573 1997.0936 2824.4009 3948.9902 6177.3149 10209.3926 19027.6582 | lr 4.9e-04 | norm 9707.5693 | dt 9.872 +type train | step 1060 | loss 152.5982 288.0086 421.5528 698.8179 963.4769 1385.9377 1892.0400 2669.8135 3789.9128 5938.4199 9905.8223 18269.1191 | lr 4.9e-04 | norm 7859.3218 | dt 9.863 +type train | step 1061 | loss 163.4765 312.3138 452.0825 744.7266 1021.1946 1484.2917 2015.1638 2823.7793 3954.3750 6158.6221 10238.0332 19011.0352 | lr 4.9e-04 | norm 9054.5117 | dt 9.875 +type train | step 1062 | loss 159.4018 301.9300 438.7124 719.7388 995.8379 1471.8207 1983.5247 2797.0549 3926.3306 6129.7109 10096.7832 18583.9531 | lr 4.9e-04 | norm 7381.2651 | dt 9.858 +type train | step 1063 | loss 159.4781 302.8620 447.7645 753.8300 1020.4041 1499.4659 2023.0951 2856.3130 4009.1189 6270.4092 10398.4453 19265.6855 | lr 4.9e-04 | norm 10087.7109 | dt 9.845 +type train | step 1064 | loss 161.0222 304.4832 436.5101 718.7521 979.5585 1432.5565 1919.6135 2701.6057 3801.9912 5915.9766 9837.7285 18166.2129 | lr 4.9e-04 | norm 9760.1572 | dt 9.864 +type train | step 1065 | loss 155.7619 296.1617 429.2423 700.6614 976.1150 1423.1935 1936.1604 2718.1050 3814.1533 5921.3057 9770.3447 18018.7246 | lr 4.9e-04 | norm 7874.2329 | dt 9.860 +type train | step 1066 | loss 169.8614 319.7869 456.7883 746.8177 1013.0958 1487.6641 1965.6179 2761.5508 3810.8018 5905.1440 9753.4297 17958.0859 | lr 4.9e-04 | norm 8721.8740 | dt 9.880 +type train | step 1067 | loss 155.9806 295.7196 429.8857 703.0423 977.5824 1426.8826 1921.6503 2711.0381 3800.7036 5893.4990 9762.1318 17988.5312 | lr 4.9e-04 | norm 7810.8340 | dt 9.864 +type train | step 1068 | loss 156.6875 296.3925 430.1571 710.9090 979.7675 1430.8560 1926.7247 2723.3645 3834.1575 6029.5723 9915.3271 18212.7891 | lr 4.9e-04 | norm 8763.0684 | dt 9.861 +type train | step 1069 | loss 156.6030 298.5045 440.4707 734.9587 1007.2029 1453.3900 1988.3080 2791.8384 3921.5276 6142.8384 10243.9209 19086.8965 | lr 4.9e-04 | norm 8428.7822 | dt 9.856 +type train | step 1070 | loss 161.5473 315.8756 468.6395 777.7412 1075.5422 1553.6760 2122.5483 2991.8826 4180.9790 6541.4150 10838.0039 20156.7949 | lr 4.9e-04 | norm 9531.3311 | dt 9.852 +type train | step 1071 | loss 150.9894 288.3376 423.8347 706.3577 967.4730 1430.3776 1974.3378 2788.2927 3904.8103 6142.1914 10260.9863 19323.4375 | lr 4.9e-04 | norm 9536.4482 | dt 9.847 +type train | step 1072 | loss 173.3959 326.7622 463.7878 744.8856 1020.7383 1474.4977 1989.2593 2769.6399 3848.9429 5994.4287 9959.3809 18573.6680 | lr 4.9e-04 | norm 8493.8154 | dt 9.856 +type train | step 1073 | loss 158.1360 301.7110 440.5639 718.9161 1007.1932 1472.9078 1987.1667 2798.3538 3930.1797 6160.1709 10167.1982 18657.6270 | lr 4.9e-04 | norm 8357.5488 | dt 9.864 +type train | step 1074 | loss 156.0299 296.1567 434.0915 706.2237 1007.5972 1469.1171 2013.4519 2837.9583 3988.5386 6232.1787 10322.5127 18979.0703 | lr 4.9e-04 | norm 11032.1787 | dt 9.859 +type train | step 1075 | loss 165.2574 314.8551 452.0637 728.5054 1011.9835 1476.5873 1988.1621 2814.1821 3927.3059 6073.5444 9986.1738 18282.3965 | lr 4.9e-04 | norm 8241.0332 | dt 9.857 +type train | step 1076 | loss 171.2399 324.5396 463.7881 741.2354 1021.1224 1505.0077 2031.8884 2844.7505 3953.9092 6083.6440 9931.8848 17989.4629 | lr 4.9e-04 | norm 8722.1270 | dt 9.970 +type train | step 1077 | loss 152.2438 290.4016 421.7229 691.5831 957.2693 1408.1880 1906.3009 2675.4966 3772.2085 5901.5610 9805.8438 18145.7676 | lr 4.9e-04 | norm 8519.6289 | dt 9.876 +type train | step 1078 | loss 167.7164 317.6583 457.3928 738.1153 1032.1013 1524.8657 2060.5078 2905.2869 4049.1655 6301.5391 10382.3955 19180.0586 | lr 4.9e-04 | norm 7910.8687 | dt 9.883 +type train | step 1079 | loss 157.8718 299.8467 436.8279 712.6655 988.0260 1455.2795 1976.6646 2778.2251 3905.5972 6103.5088 10112.8262 18638.2988 | lr 4.9e-04 | norm 7988.4136 | dt 9.886 +type train | step 1080 | loss 157.0634 300.2084 439.9343 726.1553 1012.0145 1467.1166 1991.1663 2793.5103 3933.2827 6145.8525 10277.1992 19303.1836 | lr 4.9e-04 | norm 10633.0898 | dt 9.901 +type train | step 1081 | loss 159.2579 300.0704 436.5911 711.4540 983.6942 1454.4056 1962.3574 2764.6741 3864.7898 6100.7969 10217.5586 19287.6289 | lr 4.9e-04 | norm 16066.2393 | dt 9.893 +type train | step 1082 | loss 170.2454 326.2947 461.8646 744.1597 1023.7184 1502.4807 2013.7593 2815.6729 3905.5591 6077.7773 9982.7891 18527.0215 | lr 4.9e-04 | norm 9386.7168 | dt 9.871 +type train | step 1083 | loss 166.3615 316.8680 456.4201 731.7539 1013.7185 1475.0293 1975.3346 2788.3127 3875.8628 5994.9507 9852.2070 18174.4746 | lr 4.9e-04 | norm 8738.8975 | dt 9.870 +type train | step 1084 | loss 155.5309 294.9012 428.7883 693.8660 970.2676 1423.3013 1916.9008 2705.1021 3801.3088 5966.0967 9927.6787 18364.0430 | lr 4.9e-04 | norm 8437.9258 | dt 9.883 +type train | step 1085 | loss 164.5918 312.5300 452.1158 729.0027 1023.3354 1499.9603 2042.3778 2921.7158 4041.2373 6309.4414 10503.8281 19479.4258 | lr 4.9e-04 | norm 10533.8232 | dt 9.874 +type train | step 1086 | loss 153.7926 294.9957 427.9316 688.5347 970.6755 1419.9296 1934.2605 2730.4888 3837.8115 5972.0269 9786.0742 17958.1660 | lr 4.9e-04 | norm 9021.2588 | dt 9.853 +type train | step 1087 | loss 149.9953 284.0806 420.2448 689.2148 966.4186 1427.4172 1936.7422 2740.7688 3854.5513 6039.4751 10020.2432 18553.2188 | lr 4.9e-04 | norm 8795.2959 | dt 9.878 +type train | step 1088 | loss 164.0475 311.0975 452.3771 725.7343 1012.6626 1479.5890 2029.1980 2825.5762 3940.5852 6126.8862 10112.3887 18619.1367 | lr 4.9e-04 | norm 7592.7852 | dt 9.867 +type train | step 1089 | loss 160.7152 303.2791 435.9672 701.3275 980.0202 1427.5841 1946.9259 2702.1340 3790.9846 5900.3936 9758.6201 17910.2305 | lr 4.9e-04 | norm 7169.4438 | dt 9.868 +type train | step 1090 | loss 154.3324 293.1860 426.9142 689.9999 971.5190 1429.3306 1955.5270 2719.8643 3805.8296 5962.7188 9885.9121 18285.8262 | lr 4.9e-04 | norm 8215.5859 | dt 9.864 +type train | step 1091 | loss 153.2040 290.4023 423.3754 678.4799 963.5961 1391.4386 1914.1873 2663.6150 3768.9519 5895.4399 9676.1807 17739.6875 | lr 4.9e-04 | norm 7085.0283 | dt 9.877 +type train | step 1092 | loss 157.3331 299.2049 437.4908 705.3347 997.4520 1471.3347 2013.4752 2816.6963 3953.0994 6195.7378 10191.3906 18780.1191 | lr 4.9e-04 | norm 7283.3765 | dt 9.867 +type train | step 1093 | loss 161.8134 307.6515 445.0249 718.2299 1011.5338 1514.6263 2084.3184 2959.8835 4086.0586 6368.3071 10445.0713 19261.9082 | lr 4.9e-04 | norm 8152.7954 | dt 9.880 +type train | step 1094 | loss 169.4232 322.7231 460.8221 733.4407 1025.1772 1509.4736 2049.4709 2833.6963 3899.2080 6013.7720 9818.0049 17989.6250 | lr 4.9e-04 | norm 7430.0830 | dt 9.887 +type train | step 1095 | loss 199.8562 388.5422 533.3511 824.9892 1140.9423 1650.0981 2228.8098 3071.8250 4187.4526 6318.2402 10220.7881 18478.6328 | lr 4.9e-04 | norm 10905.8174 | dt 9.868 +type train | step 1096 | loss 151.5245 291.1705 423.3509 677.9954 961.8730 1443.7316 1983.4053 2801.4163 3917.5117 6181.8809 10255.1309 19007.6191 | lr 4.9e-04 | norm 12845.9707 | dt 9.839 +type train | step 1097 | loss 155.8305 297.3401 431.2766 693.4590 979.1818 1429.1758 1958.7472 2739.4812 3852.0845 6049.6953 9925.7500 18410.9609 | lr 4.9e-04 | norm 8561.9434 | dt 9.860 +type train | step 1098 | loss 167.6858 318.8593 455.1354 730.7817 1011.6062 1469.3561 1994.7711 2742.0898 3838.1436 5999.2935 9837.3574 18320.8457 | lr 4.9e-04 | norm 8550.7949 | dt 9.861 +type train | step 1099 | loss 164.9532 310.5878 444.7870 713.6974 994.6605 1472.1843 2012.7483 2783.9246 3898.7849 6107.7261 10040.1328 18684.1406 | lr 4.9e-04 | norm 8677.2129 | dt 9.855 +type train | step 1100 | loss 163.2754 310.6758 446.9903 720.2899 997.9803 1471.3466 2003.1893 2787.5967 3893.8677 6064.5322 10141.9824 19020.0918 | lr 4.9e-04 | norm 8376.9092 | dt 9.877 +type train | step 1101 | loss 156.2930 294.9823 429.4758 690.8760 964.2479 1408.4009 1921.6304 2680.3767 3767.2766 5873.6646 9667.5713 17817.0488 | lr 4.9e-04 | norm 7540.8359 | dt 9.873 +type train | step 1102 | loss 152.8385 291.0344 426.6746 693.0762 975.8341 1434.6006 1961.8762 2759.1626 3863.5671 6065.2520 10029.9727 18546.1484 | lr 4.9e-04 | norm 7648.1504 | dt 9.869 +type train | step 1103 | loss 164.2508 311.3891 449.8944 722.8660 1006.9572 1474.7648 2007.2061 2793.1450 3904.6719 6123.5093 10126.6836 18728.0918 | lr 4.9e-04 | norm 7154.0278 | dt 9.872 +type train | step 1104 | loss 156.6774 299.2072 433.2819 699.2111 979.8800 1434.0101 1962.8119 2723.5681 3830.8994 6001.9561 9870.9473 18227.1211 | lr 4.9e-04 | norm 7774.5654 | dt 9.863 +type train | step 1105 | loss 156.5697 296.9354 426.4093 689.4247 964.9478 1415.9028 1935.8441 2701.4688 3792.8860 5965.8379 9853.7207 18242.4531 | lr 4.9e-04 | norm 8186.2632 | dt 9.854 +type train | step 1106 | loss 146.4478 278.7488 406.7042 662.3530 933.4524 1384.5029 1908.4349 2671.8044 3761.4946 5947.5840 9871.7041 18304.8984 | lr 4.9e-04 | norm 8270.0469 | dt 9.857 +type train | step 1107 | loss 171.8630 328.8416 472.6789 748.2914 1050.6818 1521.0188 2064.9084 2867.3442 4027.3477 6223.9937 10139.9092 18565.1387 | lr 4.9e-04 | norm 8331.6699 | dt 9.868 +type train | step 1108 | loss 157.0750 297.2463 426.9765 684.3957 964.0327 1419.9795 1930.2986 2710.0293 3816.2327 6015.9985 9909.1680 18382.4102 | lr 4.9e-04 | norm 9081.1250 | dt 9.856 +type train | step 1109 | loss 157.6249 296.2882 426.0698 681.4973 954.6609 1386.0991 1879.3488 2621.7229 3682.1060 5746.4634 9506.2520 17604.2168 | lr 4.9e-04 | norm 7731.5186 | dt 9.859 +type train | step 1110 | loss 149.5054 280.7363 410.8640 668.6894 955.7498 1405.7931 1923.4635 2697.6089 3793.3784 5917.3975 9775.2100 17959.0684 | lr 4.9e-04 | norm 7414.6060 | dt 9.860 +type train | step 1111 | loss 131.2449 248.5490 370.4843 609.6525 883.4943 1318.2308 1825.9734 2581.0400 3687.7410 5804.0244 9539.1611 17498.2363 | lr 4.9e-04 | norm 8698.6396 | dt 9.863 +type train | step 1112 | loss 149.5617 280.4167 410.4168 661.9236 938.5407 1390.0277 1902.6581 2666.5281 3739.9871 5874.5483 9655.8516 17827.4180 | lr 4.9e-04 | norm 7083.8330 | dt 9.884 +type train | step 1113 | loss 161.8992 307.1186 443.7615 709.4576 990.8378 1448.2994 1969.8079 2764.2781 3879.7358 6059.1016 10021.3252 18773.4492 | lr 4.9e-04 | norm 10986.2061 | dt 9.865 +type train | step 1114 | loss 158.6009 303.0228 438.1609 704.7440 987.6488 1446.0679 1962.7233 2722.4807 3809.9319 5933.7891 9719.6602 17805.3828 | lr 4.9e-04 | norm 7276.2788 | dt 9.870 +type train | step 1115 | loss 145.6905 276.0629 406.4759 660.6792 942.1011 1385.4657 1892.3638 2644.5100 3731.7395 5902.8569 9684.8896 18031.3398 | lr 4.9e-04 | norm 9829.0918 | dt 9.875 +type train | step 1116 | loss 153.4124 288.9982 424.7012 682.0280 968.7172 1437.7965 1961.4299 2744.7400 3835.0957 6051.0034 10034.4512 18947.3828 | lr 4.9e-04 | norm 10369.6289 | dt 9.847 +type train | step 1117 | loss 151.8532 285.5445 414.9852 669.6206 947.4413 1393.5762 1913.1676 2669.2344 3748.6135 5884.6299 9662.7393 17851.9473 | lr 4.9e-04 | norm 7352.6060 | dt 9.861 +type train | step 1118 | loss 158.2143 300.5649 432.7505 689.5231 975.4890 1420.3180 1940.0426 2708.4126 3777.7083 5914.7051 9660.7637 17764.7344 | lr 4.9e-04 | norm 8055.6724 | dt 9.858 +type train | step 1119 | loss 149.4419 279.3303 411.1663 670.4275 939.7104 1375.4398 1878.8666 2624.2644 3683.2788 5812.9062 9500.0664 17437.5371 | lr 4.9e-04 | norm 7284.6626 | dt 9.870 +type train | step 1120 | loss 152.9739 292.3318 423.7647 684.3125 965.4276 1418.2422 1929.3505 2695.1755 3775.5012 5934.4380 9748.5293 17895.2598 | lr 4.9e-04 | norm 10371.4512 | dt 9.860 +type train | step 1121 | loss 148.9803 280.8807 413.9825 671.3626 949.1871 1389.9055 1908.7935 2658.0046 3760.5381 5952.9746 9849.7773 18296.3398 | lr 4.9e-04 | norm 7609.8159 | dt 9.862 +type train | step 1122 | loss 144.1795 283.1416 427.2224 710.7685 1011.9244 1461.6543 1972.9111 2817.5667 4021.3574 6286.0972 10349.1221 19260.6289 | lr 4.9e-04 | norm 12976.9277 | dt 9.870 +type train | step 1123 | loss 159.9063 304.0444 441.4016 713.0131 995.3279 1451.1434 1965.8281 2730.3770 3791.7637 5901.3857 9661.9824 17823.2129 | lr 4.9e-04 | norm 7959.0103 | dt 9.863 +type train | step 1124 | loss 185.1446 352.3055 493.0880 776.2324 1063.7627 1548.0604 2071.4951 2863.4595 3869.7390 5959.3940 9593.6514 17753.9102 | lr 4.9e-04 | norm 10079.4961 | dt 9.831 +type train | step 1125 | loss 159.8993 304.8373 436.0378 688.2594 967.1959 1412.4426 1914.3384 2669.3413 3708.0020 5804.8481 9534.8184 17683.6426 | lr 4.9e-04 | norm 10102.7793 | dt 9.872 +type train | step 1126 | loss 155.2689 295.3703 427.6234 682.4781 961.8126 1398.0569 1902.8920 2653.6870 3701.7024 5798.0938 9614.2451 17763.6719 | lr 4.9e-04 | norm 8085.9805 | dt 9.875 +type train | step 1127 | loss 146.6504 278.2811 409.4583 664.2102 944.0002 1372.0455 1870.4020 2627.3699 3688.3586 5814.1406 9571.0938 17811.1152 | lr 4.9e-04 | norm 8726.8848 | dt 9.868 +type train | step 1128 | loss 147.5221 279.4436 410.3861 665.7798 939.1543 1373.4647 1871.0726 2625.0100 3696.8333 5817.9678 9517.3867 17566.6777 | lr 4.9e-04 | norm 7052.8223 | dt 9.871 +type train | step 1129 | loss 145.1504 275.2914 402.5853 646.3752 916.6497 1331.7397 1837.8179 2577.2053 3640.6816 5721.8135 9407.1533 17405.4531 | lr 4.9e-04 | norm 7581.9414 | dt 9.871 +type train | step 1130 | loss 142.4435 267.4228 393.2492 635.4769 908.6646 1335.5870 1832.2992 2558.7527 3611.5400 5685.1372 9373.6270 17413.2461 | lr 4.9e-04 | norm 6336.5454 | dt 9.858 +type train | step 1131 | loss 146.9966 278.4923 407.9771 660.0044 931.4854 1359.8623 1855.5126 2602.9014 3676.4084 5770.8506 9501.9658 17436.4062 | lr 4.9e-04 | norm 6892.5903 | dt 9.873 +type train | step 1132 | loss 158.4586 296.7718 429.1608 689.8611 965.0804 1410.6185 1938.9309 2722.1775 3814.1470 5972.2676 9775.9141 17975.4121 | lr 4.9e-04 | norm 6867.2578 | dt 9.870 +type train | step 1133 | loss 151.9376 286.2349 410.8038 681.0774 939.2351 1390.5770 1902.4435 2675.0366 3743.5234 5894.0410 9725.3818 18066.4941 | lr 4.9e-04 | norm 7504.3716 | dt 9.854 +type train | step 1134 | loss 142.5455 269.9843 397.1942 659.1446 923.8613 1358.6298 1863.2410 2618.5913 3684.7952 5811.2212 9586.2988 17716.1250 | lr 4.9e-04 | norm 7605.6787 | dt 9.854 +type train | step 1135 | loss 147.4770 278.7575 406.3469 666.9780 936.3505 1369.1116 1880.4884 2625.3394 3708.2964 5781.9556 9463.3477 17539.2598 | lr 4.9e-04 | norm 7915.3232 | dt 9.864 +type train | step 1136 | loss 136.3674 259.2072 382.6642 627.3682 891.0494 1312.9359 1804.2634 2530.6208 3576.8833 5645.3403 9301.1953 17142.2402 | lr 4.9e-04 | norm 6980.4380 | dt 9.863 +type train | step 1137 | loss 165.8547 313.3696 448.0600 724.3669 996.6495 1485.5750 2023.8007 2837.5247 3908.2832 6032.7612 9799.9648 17903.8340 | lr 4.9e-04 | norm 8292.4180 | dt 9.858 +type train | step 1138 | loss 155.3842 296.5420 435.4303 694.0322 977.0333 1408.3710 1919.7535 2666.4158 3743.8945 5862.5820 9636.0869 17833.8965 | lr 4.9e-04 | norm 6668.8120 | dt 9.886 +type train | step 1139 | loss 142.8857 270.8030 406.8937 670.1044 959.4146 1427.6230 1974.6548 2805.8845 3988.9131 6288.4370 10283.1035 19105.5938 | lr 4.9e-04 | norm 9426.7480 | dt 9.878 +type train | step 1140 | loss 147.3644 276.8861 403.3477 657.4059 915.3130 1345.0922 1840.7356 2576.4824 3630.1792 5700.7339 9401.0400 17507.6738 | lr 4.9e-04 | norm 8318.6025 | dt 9.871 +type train | step 1141 | loss 135.8724 258.2886 379.7652 623.4938 882.3407 1300.6227 1790.7131 2524.2812 3576.1367 5663.8545 9291.3887 17122.1270 | lr 4.9e-04 | norm 8111.0024 | dt 9.861 +type train | step 1142 | loss 158.3324 299.2861 430.2607 698.6906 962.8407 1413.1030 1928.1224 2725.9761 3819.3833 5993.0264 9951.4668 18859.8984 | lr 4.9e-04 | norm 14185.0176 | dt 9.868 +type train | step 1143 | loss 154.7221 291.7048 420.8150 675.8738 944.3235 1385.4031 1881.1602 2628.9714 3682.1953 5766.3291 9435.0430 17506.4844 | lr 4.9e-04 | norm 7622.0972 | dt 9.872 +type train | step 1144 | loss 163.7561 311.6045 443.7040 705.7226 980.5780 1422.6620 1943.7433 2723.1614 3771.4702 5896.5249 9599.2363 17655.7129 | lr 4.9e-04 | norm 9710.9141 | dt 9.879 +type train | step 1145 | loss 150.6307 285.9923 419.2567 679.2816 949.6586 1391.9755 1900.3284 2654.3635 3730.2957 5867.1494 9641.2363 17885.1758 | lr 4.9e-04 | norm 7658.5947 | dt 9.862 +type train | step 1146 | loss 157.6958 299.6989 432.0348 693.1741 963.0483 1403.3942 1900.2299 2643.0688 3679.0244 5715.6211 9289.7090 17040.9766 | lr 4.9e-04 | norm 8027.9253 | dt 9.876 +type train | step 1147 | loss 151.8345 288.2244 419.7222 690.2934 955.9098 1412.5934 1943.1479 2749.3447 3834.3369 5940.6367 9719.9912 17907.6172 | lr 4.9e-04 | norm 7548.5308 | dt 9.858 +type train | step 1148 | loss 151.2850 285.5236 415.4613 681.7983 942.6689 1373.9435 1879.8199 2642.8804 3689.8171 5785.5908 9509.7695 17504.4199 | lr 4.9e-04 | norm 8576.9863 | dt 9.871 +type train | step 1149 | loss 153.3358 290.7716 420.3816 688.0858 945.1332 1374.1825 1877.6356 2642.4390 3705.4290 5809.5229 9526.5605 17609.7383 | lr 4.9e-04 | norm 7040.1553 | dt 9.869 +type train | step 1150 | loss 151.4304 284.0627 411.5316 683.9915 940.4836 1373.5702 1888.2473 2656.8088 3720.4585 5814.8052 9568.7852 17773.5234 | lr 4.9e-04 | norm 7552.6055 | dt 9.858 +type train | step 1151 | loss 155.6540 295.0886 420.8736 692.9240 944.0048 1378.7089 1886.2220 2670.7170 3725.7510 5861.1367 9663.1191 18056.0879 | lr 4.9e-04 | norm 9158.2510 | dt 9.874 +type train | step 1152 | loss 156.7957 298.8365 430.7235 703.0506 960.4697 1390.1104 1884.0837 2621.3230 3676.8796 5730.6553 9381.0254 17448.1055 | lr 4.9e-04 | norm 8242.8311 | dt 9.878 +type train | step 1153 | loss 148.9607 282.7651 412.9902 679.0092 935.6520 1348.4994 1836.7958 2557.3757 3601.2021 5619.8696 9197.0596 16874.8496 | lr 4.9e-04 | norm 6546.7222 | dt 9.847 +type train | step 1154 | loss 152.8189 291.3344 419.9711 692.9406 952.4995 1402.4670 1920.6686 2694.4082 3766.2305 5890.4111 9700.2158 18000.7148 | lr 4.9e-04 | norm 7515.6167 | dt 9.856 +type train | step 1155 | loss 161.2093 307.7191 434.8309 711.3608 972.8976 1426.5520 1935.1125 2696.2839 3721.8936 5769.9878 9366.8535 17281.6172 | lr 4.9e-04 | norm 7315.9487 | dt 9.852 +type train | step 1156 | loss 152.7261 287.4346 419.7323 693.4214 949.2223 1384.5723 1894.5640 2660.5811 3732.7393 5848.3662 9638.9355 17853.9043 | lr 4.9e-04 | norm 7297.1504 | dt 9.863 +type train | step 1157 | loss 156.6178 298.8730 430.4916 708.6423 959.3684 1387.4795 1888.2090 2646.2476 3689.6145 5798.8667 9506.6143 17628.3418 | lr 4.9e-04 | norm 7013.5513 | dt 9.862 +type train | step 1158 | loss 145.7608 277.3221 404.5384 678.1864 925.5518 1341.5494 1851.5729 2602.3542 3678.4460 5822.1133 9574.1953 17754.5430 | lr 4.9e-04 | norm 7011.0498 | dt 9.893 +type train | step 1159 | loss 158.4432 302.4566 442.9691 733.3007 994.5184 1437.7604 1954.7592 2728.0024 3805.0740 5934.4478 9742.6260 18144.0156 | lr 4.9e-04 | norm 7625.2095 | dt 9.879 +type train | step 1160 | loss 138.6673 263.3977 386.3698 656.5310 900.0336 1317.9937 1817.6593 2564.5513 3608.4399 5661.8242 9307.3682 17275.8770 | lr 4.9e-04 | norm 7315.0361 | dt 9.867 +type train | step 1161 | loss 137.4390 259.7129 382.4833 653.2659 892.7805 1315.5278 1808.3408 2564.7241 3621.0728 5737.4463 9459.7031 17562.9004 | lr 4.9e-04 | norm 7207.2852 | dt 9.875 +type train | step 1162 | loss 152.1702 285.9308 416.3541 687.2101 936.1567 1362.0112 1865.0883 2651.6055 3666.6985 5737.7134 9568.7871 18354.3594 | lr 4.9e-04 | norm 12446.4824 | dt 9.875 +type train | step 1163 | loss 158.9101 305.3837 438.3214 721.9854 966.6931 1395.4795 1901.6049 2660.1545 3707.9248 5794.2305 9468.7900 17627.3770 | lr 4.9e-04 | norm 8029.0054 | dt 9.861 +type train | step 1164 | loss 147.6202 280.8146 409.9114 689.8212 935.3579 1369.1997 1874.5579 2619.9697 3656.6663 5735.6504 9439.5273 17564.3086 | lr 4.9e-04 | norm 7420.9106 | dt 9.857 +type train | step 1165 | loss 145.6886 273.6901 399.6807 668.7647 911.2112 1324.0824 1812.7914 2536.6267 3571.3513 5592.3721 9201.3770 17024.7930 | lr 4.9e-04 | norm 6946.7715 | dt 9.867 +type train | step 1166 | loss 144.1263 271.0338 397.6326 669.2555 915.5598 1335.9509 1828.4557 2558.1997 3599.0295 5692.5693 9404.6895 17465.8320 | lr 4.9e-04 | norm 6583.7578 | dt 9.869 +type train | step 1167 | loss 139.1227 264.2578 394.1715 661.2309 907.1899 1320.6202 1809.6238 2556.5042 3587.3447 5662.0732 9301.5137 17405.8477 | lr 4.9e-04 | norm 9255.7822 | dt 9.864 +type train | step 1168 | loss 135.8329 256.0438 379.4132 646.3140 892.2407 1301.0232 1785.0354 2512.3889 3567.6487 5593.7651 9151.0840 16783.1484 | lr 4.9e-04 | norm 6714.5059 | dt 9.862 +type train | step 1169 | loss 146.0793 275.6524 402.7403 669.2281 918.0794 1339.7612 1835.7017 2578.2830 3619.6340 5692.5220 9354.1689 17359.5723 | lr 4.9e-04 | norm 6350.8291 | dt 9.855 +type train | step 1170 | loss 140.9083 264.3654 391.0883 652.0121 903.1523 1315.1377 1805.9700 2538.4590 3562.1257 5580.8081 9124.3936 16864.4297 | lr 4.9e-04 | norm 6810.8696 | dt 9.899 +type train | step 1171 | loss 143.0841 270.7724 398.7159 670.7079 926.1192 1356.2159 1844.2416 2595.3481 3668.3872 5772.1001 9534.5410 17672.8301 | lr 4.9e-04 | norm 7194.1982 | dt 9.875 +type train | step 1172 | loss 148.2549 280.5771 406.9910 673.6854 921.3613 1359.4532 1862.8430 2663.0151 3701.9109 5776.5850 9484.7178 17409.1426 | lr 4.9e-04 | norm 6833.5054 | dt 9.866 +type train | step 1173 | loss 161.3290 304.4910 433.5984 701.0495 959.5402 1389.2175 1881.0659 2648.1208 3683.2102 5722.3438 9329.9336 17174.0742 | lr 4.9e-04 | norm 6660.9663 | dt 9.876 +type train | step 1174 | loss 153.5779 291.9618 421.7439 697.3768 951.9564 1371.3243 1862.6232 2613.6504 3640.4412 5676.5947 9353.7598 17348.6250 | lr 4.9e-04 | norm 7154.1128 | dt 9.873 +type train | step 1175 | loss 141.6434 268.8881 399.2280 668.0216 921.3356 1348.2556 1860.8953 2632.1677 3713.0869 5835.5693 9645.6064 17833.7324 | lr 4.9e-04 | norm 7237.3970 | dt 9.895 +type train | step 1176 | loss 149.8363 281.8742 412.7764 677.9164 928.3043 1351.3395 1851.3127 2601.4822 3642.2739 5704.3359 9337.9443 17295.2441 | lr 4.9e-04 | norm 7541.0967 | dt 9.896 +type train | step 1177 | loss 148.8793 281.8569 411.9545 682.4202 937.6818 1360.8710 1871.1838 2622.4702 3665.6055 5747.8384 9394.2236 17404.8184 | lr 4.9e-04 | norm 9295.7119 | dt 9.882 +type train | step 1178 | loss 151.2492 284.8184 411.4598 683.3597 934.4891 1362.0302 1869.9907 2627.2844 3670.1289 5721.4663 9320.0957 17265.8730 | lr 4.9e-04 | norm 7389.3110 | dt 9.867 +type train | step 1179 | loss 147.9700 279.3907 404.6634 673.7412 915.8146 1327.8187 1817.7802 2555.8848 3602.3799 5678.0947 9326.8232 17344.8730 | lr 4.9e-04 | norm 7214.2690 | dt 9.882 +type train | step 1180 | loss 148.4494 283.7265 423.4545 712.5386 969.6161 1423.1162 1954.8677 2761.1187 3841.1123 6070.3462 10089.3301 19120.2207 | lr 4.9e-04 | norm 11051.4678 | dt 9.850 +type train | step 1181 | loss 157.1926 299.4924 432.6527 708.1520 961.2302 1379.2319 1867.2875 2613.6614 3636.4648 5668.5586 9305.7988 17263.1621 | lr 4.9e-04 | norm 7522.5229 | dt 9.867 +type train | step 1182 | loss 146.5259 279.0574 409.9137 689.7775 942.9908 1380.6056 1886.8140 2677.6497 3780.4421 5928.9883 9729.5010 18144.1230 | lr 4.9e-04 | norm 12416.3975 | dt 9.843 +type train | step 1183 | loss 147.8588 283.7546 412.9817 687.1445 943.3389 1360.9419 1871.7401 2643.1765 3728.5420 5834.0039 9540.9268 17683.7539 | lr 4.9e-04 | norm 9067.4941 | dt 9.865 +type train | step 1184 | loss 150.8519 285.1717 415.9030 687.8118 940.8990 1352.2126 1838.8516 2573.7742 3604.6582 5700.3857 9439.7969 17536.3945 | lr 4.9e-04 | norm 7879.0796 | dt 9.860 +type train | step 1185 | loss 132.3943 251.4673 376.8220 634.5131 882.7361 1283.5829 1769.4113 2515.9817 3563.8601 5598.8701 9244.3193 17194.5293 | lr 4.9e-04 | norm 9038.0879 | dt 9.870 +type train | step 1186 | loss 148.5391 282.9716 415.5564 684.1961 944.1548 1379.8762 1901.0522 2717.3235 3805.5881 5926.3291 9863.3721 18513.3223 | lr 4.9e-04 | norm 10074.2100 | dt 9.848 +type train | step 1187 | loss 138.4464 261.9580 387.7029 651.5587 900.8503 1308.4371 1785.3301 2525.5837 3572.4097 5599.5786 9238.0195 17074.3613 | lr 4.9e-04 | norm 7233.2461 | dt 9.868 +type train | step 1188 | loss 149.9405 284.9222 415.0061 687.8863 954.8619 1396.6780 1923.1824 2750.1060 3822.0857 5945.8745 9690.7773 17841.3184 | lr 4.9e-04 | norm 7899.6104 | dt 9.867 +type train | step 1189 | loss 140.8178 265.5161 389.9203 646.6572 898.4394 1303.0592 1787.0574 2518.5308 3547.6318 5603.6709 9272.4824 17280.2539 | lr 4.9e-04 | norm 7457.1855 | dt 9.861 +type train | step 1190 | loss 145.4713 274.7887 398.7997 664.7322 913.4214 1338.6620 1838.4427 2612.5649 3658.4580 5716.2031 9402.3525 17564.2520 | lr 4.9e-04 | norm 7590.1646 | dt 9.863 +type train | step 1191 | loss 138.8703 262.7754 392.5202 662.9105 917.8156 1336.1777 1839.4211 2610.9541 3686.8347 5804.4634 9586.2402 17946.4727 | lr 4.9e-04 | norm 7645.5225 | dt 9.853 +type train | step 1192 | loss 133.3891 253.3692 376.9492 636.3293 880.5309 1291.1097 1782.3606 2539.3623 3585.6812 5665.4414 9321.3184 17270.7422 | lr 4.9e-04 | norm 6877.7334 | dt 9.854 +type train | step 1193 | loss 158.8644 300.0548 434.1976 711.8304 969.0684 1405.9685 1912.2238 2690.7456 3717.4658 5753.4639 9420.9932 17591.3750 | lr 4.9e-04 | norm 7670.7354 | dt 9.849 +type train | step 1194 | loss 147.1877 278.1161 405.3627 666.5863 917.7730 1323.1873 1806.2959 2548.5198 3581.8708 5623.5444 9283.2598 17265.0000 | lr 4.9e-04 | norm 6930.4316 | dt 9.873 +type train | step 1195 | loss 138.9673 260.5977 384.8499 641.5648 885.3125 1286.6947 1763.9910 2503.9531 3527.8870 5544.7954 9153.1172 17064.8809 | lr 4.9e-04 | norm 7204.8130 | dt 9.863 +type train | step 1196 | loss 138.9747 262.5394 386.8123 646.0643 902.8959 1318.1661 1822.5531 2565.1423 3617.4607 5653.0352 9260.7979 17098.5840 | lr 4.9e-04 | norm 7014.2007 | dt 9.879 +type train | step 1197 | loss 135.8477 255.7015 380.8157 638.5996 888.5704 1297.9836 1789.4309 2538.1145 3606.7358 5651.3398 9275.5283 17154.8477 | lr 4.9e-04 | norm 6585.3833 | dt 9.861 +type train | step 1198 | loss 147.5868 281.5464 414.5855 687.1319 950.3057 1361.7905 1865.9143 2624.4482 3714.4331 5806.1074 9522.3887 17621.7969 | lr 4.9e-04 | norm 6858.1323 | dt 9.870 +type train | step 1199 | loss 157.8583 300.1628 430.1329 694.0107 949.6580 1370.3723 1872.2474 2607.4734 3612.2461 5587.8438 9092.9023 16684.4297 | lr 4.9e-04 | norm 6306.4438 | dt 9.876 +type train | step 1200 | loss 141.6667 268.8247 391.4474 647.3762 891.5736 1294.4390 1780.3092 2502.6538 3520.0681 5525.9492 9059.9707 16808.3711 | lr 4.9e-04 | norm 6820.9214 | dt 9.871 +type train | step 1201 | loss 138.3054 263.0913 386.8741 642.8653 895.0758 1311.0664 1816.0244 2578.0835 3642.4431 5729.4116 9465.6973 17488.7539 | lr 4.9e-04 | norm 10251.6279 | dt 9.871 +type train | step 1202 | loss 152.3531 285.9047 417.3503 683.0412 948.8597 1383.2656 1898.4191 2686.8977 3733.8901 5752.0503 9246.2217 16879.9141 | lr 4.9e-04 | norm 7864.7441 | dt 9.864 +type train | step 1203 | loss 146.6898 278.4331 408.6886 670.1714 926.7093 1335.0630 1824.1445 2553.0635 3595.1096 5597.8506 9143.7090 16877.5703 | lr 4.9e-04 | norm 6867.1094 | dt 9.884 +type train | step 1204 | loss 147.1736 278.9203 404.8022 661.4064 914.8376 1333.0035 1828.0393 2581.2595 3600.6421 5619.1802 9214.8203 17079.4121 | lr 4.9e-04 | norm 6899.4912 | dt 9.868 +type train | step 1205 | loss 148.6820 281.3348 410.0627 670.0756 928.5991 1354.0325 1853.5631 2630.5078 3681.3586 5735.6689 9420.8867 17429.9297 | lr 4.9e-04 | norm 6988.5088 | dt 9.876 +type train | step 1206 | loss 164.2497 317.6306 453.5750 737.0055 1008.5293 1464.7766 1984.7209 2812.6558 3874.0708 5989.4263 9812.7119 18312.4766 | lr 4.9e-04 | norm 8764.9707 | dt 9.847 +type train | step 1207 | loss 151.6394 286.4833 420.9486 693.2067 958.5897 1419.8259 1946.0864 2765.6880 3846.9946 6015.9653 9899.0273 18490.1953 | lr 4.9e-04 | norm 8659.1240 | dt 9.842 +type train | step 1208 | loss 157.3917 300.6944 432.8333 702.8656 964.6177 1394.1609 1903.6945 2674.1892 3711.4136 5785.0942 9491.9893 17730.2051 | lr 4.9e-04 | norm 8386.2236 | dt 9.864 +type train | step 1209 | loss 148.7428 280.4430 402.8310 665.1439 915.0352 1334.4169 1815.9017 2576.5728 3585.1675 5636.4292 9275.8516 17351.8477 | lr 4.9e-04 | norm 9041.5723 | dt 9.863 +type train | step 1210 | loss 151.1587 286.3335 411.7685 675.0895 925.9210 1347.5823 1840.3402 2594.5515 3583.9707 5576.6387 9154.6953 17045.1680 | lr 4.9e-04 | norm 9053.8496 | dt 9.863 +type train | step 1211 | loss 137.9557 260.8501 382.8535 634.9654 883.3950 1272.8973 1751.1849 2466.0581 3476.2402 5448.6147 8918.7900 16594.0742 | lr 4.9e-04 | norm 6997.0718 | dt 9.865 +type train | step 1212 | loss 143.9122 271.1450 394.2788 653.9984 907.3282 1327.8853 1814.0781 2577.8694 3604.7014 5637.1704 9247.5527 17178.7305 | lr 4.9e-04 | norm 7905.0308 | dt 9.852 +type train | step 1213 | loss 142.9600 269.1686 393.0987 650.1880 897.2720 1304.5858 1787.9119 2548.2300 3580.0542 5620.8867 9248.3896 17114.8555 | lr 4.9e-04 | norm 6502.8223 | dt 9.860 +type train | step 1214 | loss 150.2722 282.9171 415.8734 686.9812 954.0604 1394.4868 1905.6726 2717.7476 3771.5371 5856.6084 9594.9932 17745.5098 | lr 4.9e-04 | norm 8045.6934 | dt 9.865 +type train | step 1215 | loss 145.7770 274.4181 397.5451 649.5001 905.2692 1310.6881 1791.3611 2530.6460 3552.6021 5572.5889 9171.5137 17056.4453 | lr 4.9e-04 | norm 6164.8765 | dt 9.867 +type train | step 1216 | loss 138.9880 261.5495 387.3242 642.8024 893.1276 1304.8812 1790.8018 2539.9143 3578.9065 5625.5229 9311.5156 17381.3340 | lr 4.9e-04 | norm 7778.0669 | dt 9.866 +type train | step 1217 | loss 134.2278 253.8911 377.2032 636.7921 884.3588 1286.4795 1780.0658 2518.1497 3574.8062 5593.4829 9229.2656 17149.0703 | lr 4.9e-04 | norm 6889.8467 | dt 9.861 +type train | step 1218 | loss 145.0860 275.1479 401.1655 657.8521 908.3623 1316.2390 1795.1003 2553.6702 3597.8335 5597.2837 9182.3301 17023.5020 | lr 4.9e-04 | norm 6677.5967 | dt 10.193 +type train | step 1219 | loss 134.8989 253.6835 373.9434 619.8214 871.8940 1274.8174 1743.8823 2474.4053 3496.1934 5494.4932 9025.7031 16640.7969 | lr 4.9e-04 | norm 6254.4497 | dt 9.850 +type train | step 1220 | loss 148.5146 280.5273 412.9228 682.0607 941.8943 1413.4316 1941.0126 2781.2188 3822.6663 5953.5127 9822.2451 18415.0977 | lr 4.9e-04 | norm 12811.4072 | dt 9.833 +type train | step 1221 | loss 144.3304 273.1548 399.5466 661.4666 916.3301 1323.6273 1822.4211 2580.9465 3623.2168 5620.3574 9230.9424 17150.0449 | lr 4.9e-04 | norm 7051.1567 | dt 9.866 +type train | step 1222 | loss 141.7482 267.7113 392.5178 649.3999 899.8375 1298.1523 1789.7780 2515.1091 3549.4939 5550.7939 9135.0215 16931.3867 | lr 4.9e-04 | norm 6840.5190 | dt 9.867 +type train | step 1223 | loss 132.9359 248.2894 365.4507 609.9139 851.7064 1244.3104 1718.9653 2441.4287 3457.7683 5450.2241 8999.2549 16705.1465 | lr 4.9e-04 | norm 6899.6128 | dt 9.877 +type train | step 1224 | loss 140.5608 266.1627 393.7424 654.0677 914.3102 1323.2340 1810.2191 2546.5327 3601.2881 5639.4697 9255.5273 17260.8008 | lr 4.9e-04 | norm 8278.9111 | dt 9.873 +type train | step 1225 | loss 138.3651 263.0056 390.5570 645.4012 902.5933 1316.9385 1813.3954 2566.5081 3628.1995 5656.6787 9351.8340 17390.2500 | lr 4.9e-04 | norm 6830.3296 | dt 9.870 +type train | step 1226 | loss 144.5861 273.5192 400.1042 653.8034 911.4067 1318.2485 1809.9663 2560.6152 3593.4907 5641.1943 9284.4473 17214.5723 | lr 4.9e-04 | norm 7250.1626 | dt 9.865 +type train | step 1227 | loss 144.2936 280.8419 414.8647 688.7336 948.2423 1354.0250 1832.8552 2582.1411 3684.2920 5794.9839 9644.3574 18148.0527 | lr 4.9e-04 | norm 12043.1367 | dt 9.864 +type train | step 1228 | loss 136.5464 259.3829 381.6324 632.0927 879.2186 1278.3678 1770.4381 2517.2803 3558.6121 5594.7964 9264.1709 17373.3496 | lr 4.9e-04 | norm 7159.6392 | dt 9.877 +type train | step 1229 | loss 142.4126 269.9255 394.5060 650.1731 907.4081 1318.2126 1802.2506 2553.7249 3584.6892 5590.3315 9167.2500 16972.0605 | lr 4.9e-04 | norm 6977.0278 | dt 9.884 +type train | step 1230 | loss 140.6676 265.6995 388.6263 637.6647 893.6630 1294.0538 1770.5123 2504.8552 3541.5208 5523.6567 9006.9043 16614.1230 | lr 4.9e-04 | norm 6922.4956 | dt 9.883 +type train | step 1231 | loss 146.1724 274.9664 402.2890 657.4401 914.5708 1336.1241 1826.0779 2599.8230 3650.0503 5723.3281 9425.0488 17628.4922 | lr 4.9e-04 | norm 8585.1602 | dt 9.856 +type train | step 1232 | loss 180.2788 343.6286 478.9337 754.9345 1026.0999 1524.9514 2072.2737 2938.1770 3946.2395 6099.6802 9971.9189 18592.2422 | lr 4.9e-04 | norm 14390.4395 | dt 9.836 +type train | step 1233 | loss 141.0312 266.3198 388.2171 639.6423 887.0170 1292.3523 1756.0250 2480.8093 3501.8193 5467.1919 9024.9902 16736.5234 | lr 4.9e-04 | norm 7384.9790 | dt 9.892 +type train | step 1234 | loss 142.5186 267.7874 392.1576 645.6855 900.8369 1300.9843 1784.0942 2519.4373 3541.2456 5536.9023 9120.9209 17062.7188 | lr 4.9e-04 | norm 7162.7622 | dt 9.874 +type train | step 1235 | loss 139.2239 264.0533 386.4565 635.9699 889.4438 1305.7123 1804.3947 2576.6672 3622.8540 5671.4932 9369.1895 17531.1641 | lr 4.9e-04 | norm 7705.5273 | dt 9.901 +type train | step 1236 | loss 136.8844 257.6054 378.1528 623.1405 866.5507 1256.3523 1738.4902 2466.6462 3495.1353 5470.7695 9013.2324 16820.7246 | lr 4.9e-04 | norm 7377.7480 | dt 9.859 +type train | step 1237 | loss 139.7238 265.2883 388.4244 636.6182 883.6214 1276.6555 1745.7965 2454.2646 3454.6545 5394.0088 8868.6045 16455.3047 | lr 4.9e-04 | norm 6274.1123 | dt 9.868 +type train | step 1238 | loss 155.8457 300.0434 439.9256 714.8917 985.6875 1432.5039 1958.2825 2778.9329 3836.0630 5948.2827 9675.1992 17978.3047 | lr 4.9e-04 | norm 8303.4141 | dt 9.856 +type train | step 1239 | loss 138.3338 261.1266 380.7728 629.2672 874.9750 1285.3027 1767.7114 2516.6926 3528.6338 5531.1504 9084.6035 16847.6641 | lr 4.9e-04 | norm 6238.0518 | dt 9.860 +type train | step 1240 | loss 136.7853 259.2835 383.6663 637.7885 892.0059 1300.1074 1783.7267 2527.4148 3582.8389 5592.8027 9167.1777 17009.4863 | lr 4.9e-04 | norm 6038.2539 | dt 9.864 +type train | step 1241 | loss 131.6965 248.6199 368.4469 613.2570 863.7720 1263.9797 1739.0118 2476.1008 3478.7441 5459.8643 9053.9297 16935.8008 | lr 4.9e-04 | norm 6625.9863 | dt 9.854 +type train | step 1242 | loss 136.9819 258.9309 381.9122 630.4623 879.5490 1279.8195 1755.1260 2487.4539 3487.1345 5453.9990 8998.7627 16820.2266 | lr 4.9e-04 | norm 7901.6172 | dt 9.864 +type train | step 1243 | loss 147.5804 282.1479 419.5106 699.8276 963.5829 1417.7874 1937.5492 2765.2808 3871.0315 6054.1157 9955.4756 18703.9414 | lr 4.9e-04 | norm 8475.4951 | dt 9.862 +type train | step 1244 | loss 162.4800 308.2991 439.6297 711.7023 971.9234 1401.8428 1891.2822 2663.7046 3652.1040 5695.4707 9318.5508 17534.0684 | lr 4.9e-04 | norm 9469.8721 | dt 9.841 +type train | step 1245 | loss 142.3203 270.1074 397.4455 657.1239 915.6760 1331.0276 1822.5172 2581.4329 3630.5012 5694.1187 9360.2158 17552.8809 | lr 4.9e-04 | norm 7123.9951 | dt 9.859 +type train | step 1246 | loss 152.2599 288.5290 424.3715 689.5156 958.7770 1368.1350 1869.8798 2629.5654 3676.6951 5717.6997 9427.1895 17608.6309 | lr 4.9e-04 | norm 8468.9385 | dt 9.872 +type train | step 1247 | loss 142.0628 270.3499 396.7039 650.4968 917.0531 1321.8198 1808.0244 2568.8931 3621.7048 5639.9907 9224.3438 16992.3066 | lr 4.9e-04 | norm 7433.4404 | dt 9.880 +type train | step 1248 | loss 148.3759 278.4884 404.0514 653.5509 909.5243 1316.6677 1793.9817 2532.5833 3518.0205 5474.4761 8906.1094 16453.1309 | lr 4.9e-04 | norm 6804.4380 | dt 9.857 +type train | step 1249 | loss 145.0692 274.3058 403.3008 658.3666 921.3622 1336.1931 1821.1111 2571.2070 3609.6948 5620.6665 9254.9424 17174.8379 | lr 4.9e-04 | norm 6322.0039 | dt 9.880 +type train | step 1250 | loss 173.6714 331.7158 469.5089 739.9810 1011.0009 1449.9343 1953.1077 2727.2021 3702.2578 5686.4111 9156.1240 16730.0898 | lr 4.9e-04 | norm 6790.5430 | dt 9.850 +type train | step 1251 | loss 141.0515 264.8239 387.3998 631.2247 889.6573 1289.4298 1767.0728 2501.1992 3518.4407 5514.0386 9095.0518 16992.6895 | lr 4.9e-04 | norm 6404.6279 | dt 9.854 +type train | step 1252 | loss 154.5974 295.6945 423.5305 676.5127 939.6588 1355.4215 1844.7742 2613.2046 3624.8176 5626.1201 9217.1875 17221.9512 | lr 4.9e-04 | norm 7212.7754 | dt 9.864 +type train | step 1253 | loss 131.9861 251.2781 376.9680 626.7524 882.1437 1282.3441 1770.4177 2521.9307 3576.1406 5623.9297 9244.4258 17246.4297 | lr 4.9e-04 | norm 6746.3442 | dt 9.862 +type train | step 1254 | loss 137.2032 259.7538 388.1154 641.9521 899.4174 1295.4932 1779.9021 2509.0725 3548.2634 5575.4224 9209.0986 17232.1406 | lr 4.9e-04 | norm 8263.6846 | dt 9.856 +type train | step 1255 | loss 140.4197 266.3085 391.5109 638.8278 897.2616 1295.7690 1775.0314 2498.1084 3520.2080 5507.6094 9086.4238 16981.8984 | lr 4.9e-04 | norm 6512.3691 | dt 9.871 +type train | step 1256 | loss 132.6463 252.0755 372.8378 611.4122 863.8843 1261.8240 1736.0322 2464.1162 3491.4468 5472.4434 9000.2861 16794.1406 | lr 4.9e-04 | norm 7172.4976 | dt 9.853 +type train | step 1257 | loss 130.6025 245.9467 361.8903 598.4092 846.0190 1228.1763 1682.7043 2387.3843 3365.4229 5281.1465 8737.0557 16295.8145 | lr 4.9e-04 | norm 6273.0088 | dt 9.868 +type train | step 1258 | loss 135.6074 255.7292 382.5548 634.9801 900.5417 1312.7434 1800.4064 2561.4634 3607.9333 5658.1953 9365.1807 17488.7148 | lr 4.9e-04 | norm 6148.4819 | dt 9.852 +type train | step 1259 | loss 137.6745 259.2445 380.7212 620.2750 880.2432 1272.1815 1744.7551 2467.4097 3485.1863 5472.0840 9023.7461 16681.0059 | lr 4.9e-04 | norm 6024.6475 | dt 9.862 +type train | step 1260 | loss 144.4808 273.1871 401.9936 653.9893 914.8192 1311.8063 1784.5308 2502.5291 3497.3477 5401.9170 8851.8965 16435.8145 | lr 4.9e-04 | norm 7247.6792 | dt 9.862 +type train | step 1261 | loss 143.6610 272.0635 395.8612 649.8733 907.2289 1317.4628 1797.1541 2528.7705 3501.9175 5440.7012 8910.5869 16608.2305 | lr 4.9e-04 | norm 7917.8506 | dt 9.854 +type train | step 1262 | loss 138.4397 260.8402 383.0768 626.6063 878.8033 1274.5231 1748.7843 2482.9312 3494.4880 5508.5278 9056.8135 16946.0059 | lr 4.9e-04 | norm 7121.4644 | dt 9.849 +type train | step 1263 | loss 138.9115 261.1789 380.2949 621.1287 871.6946 1248.5872 1708.0895 2409.0784 3406.6230 5333.5459 8806.2695 16437.3008 | lr 4.9e-04 | norm 7412.1763 | dt 9.870 +type train | step 1264 | loss 145.1510 273.3541 397.8830 643.4432 904.1327 1310.3756 1795.4934 2555.3687 3574.4851 5558.6221 9098.4736 16888.3789 | lr 4.9e-04 | norm 6477.5449 | dt 9.869 +type train | step 1265 | loss 145.4149 273.6467 398.6050 643.0857 907.6777 1313.4563 1808.8934 2566.9902 3593.9888 5601.5889 9219.8066 17254.4043 | lr 4.9e-04 | norm 7299.4189 | dt 9.878 +type train | step 1266 | loss 146.0154 275.6769 403.4123 653.3190 912.7940 1325.5045 1812.6947 2569.0081 3573.3206 5581.8838 9193.9199 17109.8750 | lr 4.9e-04 | norm 6950.6841 | dt 9.871 +type train | step 1267 | loss 133.6617 255.0864 378.4090 622.5058 886.8147 1293.8802 1787.0835 2556.4512 3598.1694 5605.5801 9200.0967 17052.8926 | lr 4.9e-04 | norm 6433.7031 | dt 9.852 +type train | step 1268 | loss 138.5811 260.4109 383.9521 629.6616 886.4808 1284.8336 1763.5759 2505.6953 3516.6489 5498.3311 9105.6914 17004.0078 | lr 4.9e-04 | norm 6385.2505 | dt 9.861 +type train | step 1269 | loss 139.0701 264.7677 392.0774 643.8767 908.8724 1317.9476 1817.8347 2596.8096 3650.7849 5725.6665 9445.5986 17672.4297 | lr 4.9e-04 | norm 6892.2173 | dt 9.874 +type train | step 1270 | loss 145.6591 277.9471 410.6895 663.2308 931.0178 1342.5120 1843.4778 2610.5840 3653.6072 5669.1562 9311.8535 17296.0469 | lr 4.9e-04 | norm 6576.4897 | dt 9.854 +type train | step 1271 | loss 147.7253 278.7995 406.3072 658.6741 923.2524 1331.7380 1816.7694 2573.8359 3587.7568 5619.2070 9248.9170 17260.7891 | lr 4.9e-04 | norm 7918.4116 | dt 9.851 +type train | step 1272 | loss 144.1292 268.5807 393.6836 640.1973 899.5435 1304.8724 1790.7910 2540.0891 3562.3735 5577.2539 9179.5420 16935.2402 | lr 4.9e-04 | norm 7188.9805 | dt 9.870 +type train | step 1273 | loss 139.8540 263.6997 389.9046 635.6611 897.4222 1296.6609 1778.2078 2519.0879 3555.9705 5584.3623 9159.7500 16925.9492 | lr 4.9e-04 | norm 6624.1406 | dt 9.869 +type train | step 1274 | loss 134.0851 253.3258 376.8034 621.2194 878.0181 1277.9762 1763.7651 2512.4773 3545.3210 5567.8916 9171.9531 17064.9727 | lr 4.9e-04 | norm 6524.8691 | dt 9.870 +type train | step 1275 | loss 136.9807 260.2793 384.7101 628.9034 887.3006 1281.7352 1753.3726 2477.8298 3506.2412 5490.8623 9009.8477 16627.8809 | lr 4.9e-04 | norm 5748.8066 | dt 9.874 +type train | step 1276 | loss 133.0349 250.7212 371.3053 611.7365 863.2525 1252.1624 1722.9010 2445.2986 3456.3618 5417.4116 8949.0801 16734.4199 | lr 4.9e-04 | norm 6211.3047 | dt 9.868 +type train | step 1277 | loss 135.7788 256.8639 379.5507 619.2978 876.0651 1264.9489 1741.7964 2474.2319 3484.9934 5458.7803 8945.6729 16671.8145 | lr 4.9e-04 | norm 6510.0659 | dt 9.866 +type train | step 1278 | loss 130.5390 247.4504 369.4634 614.6487 875.8342 1264.0186 1751.0065 2500.3323 3538.0752 5583.1035 9193.0488 17160.1172 | lr 4.8e-04 | norm 9193.4521 | dt 9.867 +type train | step 1279 | loss 133.7800 253.2000 378.3896 618.9922 880.5801 1284.8192 1773.7751 2532.5017 3567.5283 5609.2827 9205.3945 17091.9238 | lr 4.8e-04 | norm 6940.0264 | dt 9.867 +type train | step 1280 | loss 130.8469 245.0294 363.8797 597.1251 848.5118 1230.1658 1703.9396 2426.3809 3445.6799 5417.5259 8911.4385 16568.0078 | lr 4.8e-04 | norm 7027.1719 | dt 9.861 +type train | step 1281 | loss 135.6280 256.6823 383.2988 625.6866 886.2875 1277.0759 1752.8583 2489.1538 3525.7739 5508.4810 9040.0703 16773.6523 | lr 4.8e-04 | norm 6355.6167 | dt 9.861 +type train | step 1282 | loss 143.0104 272.9810 422.3628 691.6058 970.3685 1400.3303 1922.9001 2724.6721 3797.5884 5992.2437 9983.5293 19033.2773 | lr 4.8e-04 | norm 11732.8379 | dt 9.849 +type train | step 1283 | loss 133.7793 250.4951 370.1664 606.8051 859.6219 1232.8048 1696.4294 2392.8206 3385.1653 5287.7231 8642.0742 16016.6934 | lr 4.8e-04 | norm 6724.5981 | dt 9.869 +type train | step 1284 | loss 148.4214 283.8478 412.7042 666.8611 935.9420 1350.3237 1856.8733 2631.2307 3649.2412 5691.2896 9350.4277 17610.0234 | lr 4.8e-04 | norm 6680.4771 | dt 9.854 +type train | step 1285 | loss 139.9747 262.6570 384.6105 623.0356 880.6815 1272.1785 1755.9067 2492.3242 3506.5239 5468.9790 8926.3252 16575.6016 | lr 4.8e-04 | norm 7684.7988 | dt 9.867 +type train | step 1286 | loss 137.3126 259.1997 383.4937 623.9330 882.8884 1275.8037 1757.7277 2488.8403 3497.2400 5483.5566 9013.6094 16796.1406 | lr 4.8e-04 | norm 6296.8564 | dt 9.869 +type train | step 1287 | loss 146.5114 275.3724 400.4118 642.6385 906.2980 1304.8875 1784.2638 2540.8159 3552.5195 5584.6899 9228.0566 17196.8672 | lr 4.8e-04 | norm 8137.6499 | dt 9.879 +type train | step 1288 | loss 138.5258 260.5782 386.6134 627.6202 884.6749 1270.7561 1742.9541 2454.5073 3456.6531 5404.4175 8890.0166 16593.9277 | lr 4.8e-04 | norm 6251.9092 | dt 9.856 +type train | step 1289 | loss 140.5933 266.0257 387.5853 625.7672 886.1528 1277.9143 1759.6012 2477.5383 3454.1892 5383.1191 8877.0156 16489.5117 | lr 4.8e-04 | norm 7177.3096 | dt 9.871 +type train | step 1290 | loss 139.3863 263.1759 389.4600 638.2178 904.7109 1311.6023 1793.4751 2553.6892 3592.3948 5605.4902 9194.4873 17131.6777 | lr 4.8e-04 | norm 6149.2866 | dt 9.866 +type train | step 1291 | loss 130.7152 248.5280 370.5596 607.8200 863.5941 1257.3698 1730.2762 2450.9788 3487.8521 5427.9160 8870.8320 16445.1406 | lr 4.8e-04 | norm 6016.5537 | dt 9.868 +type train | step 1292 | loss 129.0534 245.4047 363.6958 596.9791 848.7838 1236.6554 1710.3949 2428.7747 3437.0444 5398.7607 8901.8418 16617.2109 | lr 4.8e-04 | norm 5963.1221 | dt 9.864 +type train | step 1293 | loss 136.7396 257.3182 380.6521 620.5495 874.9169 1272.2578 1748.7401 2479.6240 3482.5510 5430.0776 8961.0312 16662.8477 | lr 4.8e-04 | norm 5762.8154 | dt 9.866 +type train | step 1294 | loss 145.8436 277.2970 405.7271 651.3224 914.7476 1322.6909 1811.2375 2557.9290 3578.4331 5551.2090 9030.9102 16780.2852 | lr 4.8e-04 | norm 5999.2754 | dt 9.868 +type train | step 1295 | loss 134.8522 256.3088 378.1406 621.3918 874.7341 1267.4435 1746.8347 2492.7905 3520.0325 5532.0796 9159.7646 17176.4492 | lr 4.8e-04 | norm 6195.3599 | dt 9.849 +type train | step 1296 | loss 138.0741 259.8806 386.3258 629.3508 894.5052 1302.9591 1787.0632 2533.7739 3529.1960 5459.3330 8953.8965 16661.1680 | lr 4.8e-04 | norm 6252.7192 | dt 9.872 +type train | step 1297 | loss 148.6448 280.6076 412.9236 666.1815 939.1827 1364.1436 1872.4247 2667.1147 3717.6897 5771.2515 9475.1133 17650.5176 | lr 4.8e-04 | norm 7071.7153 | dt 9.860 +type train | step 1298 | loss 131.2043 248.8418 371.9791 619.8270 879.4576 1277.6045 1756.2448 2484.9329 3522.1045 5553.2915 9217.8203 17170.4160 | lr 4.8e-04 | norm 7464.5317 | dt 9.862 +type train | step 1299 | loss 137.4282 257.3907 378.4113 617.9525 875.7549 1267.0435 1744.2759 2470.2993 3484.9866 5444.5977 8927.9688 16553.4941 | lr 4.8e-04 | norm 6774.5991 | dt 9.864 +type train | step 1300 | loss 129.0003 242.1206 359.9750 589.6631 845.2477 1218.5172 1686.1921 2392.8899 3381.8306 5304.4893 8749.5195 16290.9785 | lr 4.8e-04 | norm 6548.4360 | dt 9.868 +type train | step 1301 | loss 137.8459 260.8470 384.6501 624.5887 881.0561 1284.5667 1772.9087 2516.2112 3505.2810 5449.5381 8933.1562 16684.1367 | lr 4.8e-04 | norm 6491.9136 | dt 9.871 +type train | step 1302 | loss 132.4740 251.2506 371.0710 604.9008 867.6462 1245.5486 1720.1399 2441.8027 3456.0139 5427.0068 8910.3945 16603.7578 | lr 4.8e-04 | norm 6174.5352 | dt 9.873 +type train | step 1303 | loss 146.4898 276.9683 398.5332 640.2562 898.8307 1304.8967 1793.9471 2539.2107 3536.1953 5499.8872 8982.1094 16839.5605 | lr 4.8e-04 | norm 7719.6309 | dt 9.872 +type train | step 1304 | loss 125.9362 237.1892 354.2706 581.9434 831.0693 1215.5116 1681.7031 2394.2107 3405.5305 5352.4702 8828.0996 16488.4609 | lr 4.8e-04 | norm 6839.9102 | dt 9.849 +type train | step 1305 | loss 138.0171 260.2812 381.7078 618.9978 880.5435 1282.3044 1777.7183 2545.4634 3573.9204 5613.7720 9180.4834 17130.6289 | lr 4.8e-04 | norm 7098.7290 | dt 9.853 +type train | step 1306 | loss 141.4578 269.6900 391.4407 635.2047 897.2785 1299.8538 1790.7386 2544.1448 3554.3818 5539.8706 9099.9258 16983.7324 | lr 4.8e-04 | norm 7718.1304 | dt 9.864 +type train | step 1307 | loss 147.2364 278.6761 406.2294 656.7152 924.6722 1355.5784 1843.7682 2654.7300 3660.8071 5675.1021 9231.7188 17276.5742 | lr 4.8e-04 | norm 7798.0332 | dt 9.846 +type train | step 1308 | loss 136.0503 258.8204 383.4237 628.6581 885.9052 1282.5804 1759.1805 2500.3867 3507.5981 5494.8428 9087.5039 17005.9336 | lr 4.8e-04 | norm 7468.8848 | dt 9.865 +type train | step 1309 | loss 141.2361 266.1482 387.2202 626.9188 882.6839 1277.5179 1746.8174 2484.7715 3473.1060 5421.4121 8947.3057 16746.5703 | lr 4.8e-04 | norm 7854.6504 | dt 9.870 +type train | step 1310 | loss 142.1348 268.4173 390.8003 622.0132 877.1648 1244.4698 1696.3895 2397.3074 3392.5974 5336.9873 8740.4248 16416.6855 | lr 4.8e-04 | norm 11782.2168 | dt 9.857 +type train | step 1311 | loss 149.6292 282.7722 410.6240 659.9415 927.9041 1345.4456 1834.0328 2612.0518 3619.6465 5597.3940 9106.0967 16972.0801 | lr 4.8e-04 | norm 6734.5879 | dt 9.881 +type train | step 1312 | loss 138.8450 262.0564 380.5184 613.5402 866.8197 1248.4332 1709.5259 2422.2307 3406.9575 5324.9126 8762.8516 16391.5195 | lr 4.8e-04 | norm 7341.6626 | dt 9.852 +type train | step 1313 | loss 147.7743 280.3033 410.6826 658.7084 936.1663 1354.0024 1856.6321 2649.9639 3721.4109 5795.1938 9533.2734 17786.9570 | lr 4.8e-04 | norm 7523.9009 | dt 9.861 +type train | step 1314 | loss 131.4050 250.2141 377.9413 620.7385 896.9255 1301.0114 1801.7401 2582.6440 3665.8269 5815.6543 9572.8242 17818.5078 | lr 4.8e-04 | norm 10058.4092 | dt 9.866 +type train | step 1315 | loss 130.2512 245.3713 364.4328 597.7028 862.3570 1246.6095 1724.3881 2454.1045 3454.8215 5383.6055 8732.9131 16076.2617 | lr 4.8e-04 | norm 9169.0186 | dt 9.872 +type train | step 1316 | loss 138.5500 260.7392 379.4012 612.2503 865.3676 1250.9601 1721.3130 2444.0999 3425.7275 5370.4253 8836.9160 16666.7070 | lr 4.8e-04 | norm 8389.5400 | dt 9.875 +type train | step 1317 | loss 131.4530 247.5527 370.1479 602.2660 861.5243 1248.8060 1724.3149 2445.2690 3459.9136 5428.9946 8933.4355 16666.8945 | lr 4.8e-04 | norm 7002.9863 | dt 9.882 +type train | step 1318 | loss 142.4998 269.9969 394.7451 632.6191 893.4829 1303.7874 1781.8586 2550.9307 3565.4526 5550.9873 9129.2754 16959.2363 | lr 4.8e-04 | norm 7491.2056 | dt 9.854 +type train | step 1319 | loss 146.1364 276.0542 405.3889 650.4380 916.0048 1327.1835 1809.6475 2579.2532 3591.1396 5589.3970 9120.7734 17145.6367 | lr 4.8e-04 | norm 7306.7505 | dt 9.861 +type train | step 1320 | loss 136.3207 257.4664 380.7819 615.7599 875.1087 1263.4962 1730.4117 2456.7588 3470.9905 5430.1914 8948.8027 16766.1602 | lr 4.8e-04 | norm 6747.8579 | dt 9.866 +type train | step 1321 | loss 145.3427 274.8442 400.4286 639.5777 905.1541 1304.9414 1787.0929 2538.7595 3547.4197 5502.8823 8940.7100 16562.1172 | lr 4.8e-04 | norm 7142.9253 | dt 9.870 +type train | step 1322 | loss 135.4977 256.0163 378.0141 609.9053 862.3185 1241.2878 1706.0691 2428.6567 3407.6858 5332.7881 8786.3867 16456.6309 | lr 4.8e-04 | norm 6368.7124 | dt 9.870 +type train | step 1323 | loss 131.7663 247.8611 368.5889 601.2079 858.6315 1250.7290 1728.8376 2469.7600 3504.0999 5468.5137 8983.1855 16746.5039 | lr 4.8e-04 | norm 6471.6821 | dt 9.880 +type train | step 1324 | loss 139.2935 264.2064 380.7919 611.3287 865.9824 1252.2853 1722.2703 2449.3044 3438.3193 5409.4185 8895.8467 16695.9629 | lr 4.8e-04 | norm 7268.7310 | dt 9.856 +type train | step 1325 | loss 125.0576 235.4198 354.7817 585.5300 837.4282 1213.5919 1689.0217 2411.9824 3417.8291 5354.0547 8784.8066 16441.2305 | lr 4.8e-04 | norm 7458.6035 | dt 9.857 +type train | step 1326 | loss 134.0214 251.0210 366.4464 594.5195 852.3369 1245.8994 1733.9268 2482.6318 3474.1875 5444.5996 8941.2402 17026.3262 | lr 4.8e-04 | norm 10026.2246 | dt 9.867 +type train | step 1327 | loss 134.6307 255.4731 378.5995 619.7070 879.2559 1272.1228 1771.1476 2528.9739 3598.9788 5658.4863 9222.1387 17120.1719 | lr 4.8e-04 | norm 8303.4326 | dt 9.865 +type train | step 1328 | loss 138.3885 263.0443 387.2039 632.3787 896.0691 1295.7526 1775.8092 2521.2603 3545.5747 5542.5908 9097.7695 17014.1094 | lr 4.8e-04 | norm 7544.4346 | dt 9.860 +type train | step 1329 | loss 129.4933 243.1878 360.1606 591.8503 841.6271 1217.9293 1682.1562 2391.6575 3379.8154 5341.0366 8836.6836 16682.9766 | lr 4.8e-04 | norm 7418.4790 | dt 9.863 +type train | step 1330 | loss 142.2368 271.4040 396.9832 642.9754 915.3965 1323.1108 1815.5557 2586.6545 3603.1050 5621.5952 9232.4912 17372.3242 | lr 4.8e-04 | norm 7774.4390 | dt 9.851 +type train | step 1331 | loss 138.2531 259.1677 378.7238 611.1838 868.7333 1262.8544 1732.6650 2461.2549 3431.3428 5308.1626 8690.7969 16145.8984 | lr 4.8e-04 | norm 7142.3936 | dt 9.858 +type train | step 1332 | loss 129.2176 242.3731 359.9951 587.8030 841.5886 1210.2161 1667.6060 2375.2144 3346.4014 5247.5322 8641.6318 16285.8633 | lr 4.8e-04 | norm 6608.7183 | dt 9.866 +type train | step 1333 | loss 135.5009 256.9651 376.3573 608.5146 868.8197 1265.0289 1748.3999 2485.4521 3486.7971 5436.3628 8915.6250 16578.4316 | lr 4.8e-04 | norm 6151.8901 | dt 9.860 +type train | step 1334 | loss 130.6593 246.8108 366.2513 593.1667 850.2162 1224.8059 1701.8802 2423.1868 3426.5876 5374.2773 8851.7510 16570.1309 | lr 4.8e-04 | norm 6199.5229 | dt 9.858 +type train | step 1335 | loss 138.8727 262.8144 388.5333 625.0265 888.9738 1270.8577 1747.8479 2464.9531 3485.1880 5441.9482 8957.3584 16798.9434 | lr 4.8e-04 | norm 6873.3828 | dt 9.866 +type train | step 1336 | loss 148.9305 280.1127 408.5555 653.9101 927.8272 1322.8059 1807.8777 2551.7292 3596.1157 5506.6704 8952.4873 16962.8887 | lr 4.8e-04 | norm 9196.4678 | dt 9.856 +type train | step 1337 | loss 133.1106 247.4550 368.2237 596.4316 847.7300 1231.7927 1705.9152 2421.1174 3428.4724 5386.2559 8845.3994 16635.3066 | lr 4.8e-04 | norm 7446.6255 | dt 9.852 +type train | step 1338 | loss 128.8019 243.8055 361.5306 587.3408 843.8234 1215.6964 1683.8940 2401.3918 3408.2334 5376.6665 8879.1953 16711.1289 | lr 4.8e-04 | norm 7145.2588 | dt 9.869 +type train | step 1339 | loss 140.0983 262.2838 381.2689 614.3663 872.4445 1255.3760 1720.4136 2437.5425 3425.9277 5306.5625 8614.2402 16053.0498 | lr 4.8e-04 | norm 6565.2935 | dt 9.869 +type train | step 1340 | loss 129.8006 241.7961 358.6051 587.8967 841.5228 1223.9861 1693.0402 2399.2686 3371.5088 5309.6914 8795.8691 16493.5723 | lr 4.8e-04 | norm 6665.4199 | dt 9.866 +type train | step 1341 | loss 130.2584 247.3962 361.7665 589.5503 843.7830 1230.3767 1702.2125 2448.4397 3446.8149 5418.7080 8881.0684 16638.7461 | lr 4.8e-04 | norm 6637.8589 | dt 9.854 +type train | step 1342 | loss 124.9310 236.4134 351.4314 576.2877 827.5133 1207.1804 1668.8665 2389.9705 3376.5383 5288.7861 8693.7383 16185.8008 | lr 4.8e-04 | norm 6061.9365 | dt 9.869 +type train | step 1343 | loss 144.7991 275.3989 403.2703 645.0942 910.1971 1297.8644 1776.4680 2508.4189 3522.0881 5485.2861 9001.7090 16800.1504 | lr 4.8e-04 | norm 6929.5361 | dt 9.853 +type train | step 1344 | loss 127.7724 241.0759 357.4283 579.7652 827.6419 1199.0159 1647.6692 2336.9844 3299.4087 5179.5889 8508.4434 15770.2715 | lr 4.8e-04 | norm 5831.4336 | dt 9.884 +type train | step 1345 | loss 138.3571 261.1070 386.2378 622.5372 884.5976 1286.3695 1765.8339 2516.8633 3544.5713 5528.8428 9015.7139 16790.4902 | lr 4.8e-04 | norm 7371.4575 | dt 9.887 +type train | step 1346 | loss 134.2096 251.3520 368.2733 598.2708 857.9539 1250.1523 1734.8708 2477.3237 3484.9089 5494.0850 9104.0840 17034.8281 | lr 4.8e-04 | norm 6523.4141 | dt 9.870 +type train | step 1347 | loss 127.9901 240.8916 356.8680 582.0336 829.3514 1205.9459 1673.4564 2377.6252 3380.6479 5348.1978 8807.8848 16443.7500 | lr 4.8e-04 | norm 7430.3242 | dt 9.858 +type train | step 1348 | loss 131.7619 253.2202 384.1804 633.4285 901.9585 1303.8125 1796.3623 2572.3318 3635.9509 5641.2710 9243.5342 17111.9277 | lr 4.8e-04 | norm 11455.5703 | dt 9.852 +type train | step 1349 | loss 128.2855 240.5330 357.1251 583.6784 833.7039 1215.5286 1686.0081 2410.2603 3392.7661 5324.6748 8788.0977 16572.2324 | lr 4.8e-04 | norm 7857.1987 | dt 9.862 +type train | step 1350 | loss 141.8110 266.3787 392.4152 629.5055 891.8896 1288.4375 1769.2714 2509.9492 3510.9631 5457.2339 8958.8076 16637.1797 | lr 4.8e-04 | norm 6722.5381 | dt 9.866 +type train | step 1351 | loss 137.1594 262.0268 384.7599 619.7891 886.9699 1280.7510 1766.8970 2523.8931 3535.7429 5539.4629 9141.4268 17153.6211 | lr 4.8e-04 | norm 6863.9473 | dt 9.869 +type train | step 1352 | loss 128.3923 247.5388 374.9475 612.8524 876.4849 1271.4901 1744.2909 2483.8281 3504.4062 5443.3018 8969.9785 16761.1191 | lr 4.8e-04 | norm 7589.4146 | dt 9.873 +type train | step 1353 | loss 124.1211 233.1759 345.9042 566.2249 816.0092 1189.7526 1646.4395 2361.7422 3347.8867 5265.6758 8661.1533 16241.6328 | lr 4.8e-04 | norm 6044.9561 | dt 9.877 +type train | step 1354 | loss 131.0888 247.5721 366.9076 596.7682 851.5292 1236.8854 1704.5310 2422.8269 3386.3467 5275.7871 8672.5430 16213.2510 | lr 4.8e-04 | norm 6827.0127 | dt 9.871 +type train | step 1355 | loss 130.8307 247.2576 368.6805 606.3521 864.8772 1256.6019 1732.3461 2458.9951 3464.7686 5406.7788 8892.5449 16495.5371 | lr 4.8e-04 | norm 6529.8521 | dt 9.874 +type train | step 1356 | loss 131.1178 246.2678 362.9882 591.9454 838.9615 1209.4906 1668.4718 2369.2852 3333.6143 5211.9351 8597.4902 16188.4512 | lr 4.8e-04 | norm 6476.6465 | dt 9.881 +type train | step 1357 | loss 140.9718 267.6546 394.3024 641.5277 912.3178 1330.3046 1830.4121 2617.3796 3667.0898 5729.7490 9447.0312 17822.4883 | lr 4.8e-04 | norm 7336.8994 | dt 9.851 +type train | step 1358 | loss 142.7123 270.3591 397.0052 638.1909 898.3194 1301.8521 1787.8801 2537.1687 3551.3342 5547.0244 9131.5957 17164.1133 | lr 4.8e-04 | norm 6556.8071 | dt 9.857 +type train | step 1359 | loss 133.8520 252.5408 369.5638 597.6855 850.1345 1227.7087 1696.0632 2415.3679 3411.8975 5352.6089 8819.7041 16586.0625 | lr 4.8e-04 | norm 6784.4238 | dt 9.860 +type train | step 1360 | loss 132.4916 248.5362 364.1785 593.3377 847.2952 1219.4653 1691.3477 2402.0842 3392.3735 5303.8262 8653.4561 16094.9736 | lr 4.8e-04 | norm 6396.5830 | dt 9.878 +type train | step 1361 | loss 130.5591 245.7177 367.1685 594.7574 852.1064 1230.7731 1696.2882 2425.2649 3408.4409 5338.7168 8772.3145 16364.5820 | lr 4.8e-04 | norm 5494.0293 | dt 9.883 +type train | step 1362 | loss 133.7091 252.9489 373.8120 601.6756 855.8478 1239.0449 1700.3977 2417.6338 3405.8374 5295.1523 8678.9971 16154.4639 | lr 4.8e-04 | norm 5808.4634 | dt 9.875 +type train | step 1363 | loss 126.1527 237.7493 354.5309 581.4778 839.3072 1220.4923 1692.4342 2428.6792 3434.3950 5404.4517 8917.1855 16711.6367 | lr 4.8e-04 | norm 6431.2344 | dt 9.860 +type train | step 1364 | loss 151.4260 282.7362 412.1307 649.7792 919.1904 1328.1160 1813.9806 2539.7778 3511.5864 5413.4058 8720.6924 16129.9033 | lr 4.8e-04 | norm 6613.7891 | dt 9.871 +type train | step 1365 | loss 121.1801 227.5276 347.3404 565.3730 821.3235 1193.8112 1667.5328 2396.3318 3396.6162 5345.2969 8798.4707 16454.4551 | lr 4.8e-04 | norm 6017.6074 | dt 9.870 +type train | step 1366 | loss 134.1330 250.9906 368.9186 597.3768 851.6786 1242.9409 1710.0071 2434.9417 3407.8467 5360.4414 8903.7754 16745.0352 | lr 4.8e-04 | norm 6346.9556 | dt 9.866 +type train | step 1367 | loss 137.4771 258.5087 385.4617 618.4746 881.0684 1270.7751 1747.1697 2482.4397 3456.9802 5395.4336 8881.4141 16693.2656 | lr 4.8e-04 | norm 6873.2139 | dt 9.868 +type train | step 1368 | loss 135.0300 255.9062 377.8164 612.3055 870.0514 1282.8794 1781.1704 2561.6653 3577.3179 5586.3735 9250.0713 17451.5820 | lr 4.8e-04 | norm 7193.4868 | dt 9.854 +type train | step 1369 | loss 128.1006 241.2133 358.0986 582.4062 838.4828 1221.4364 1679.9722 2403.5796 3397.6846 5328.5977 8762.9932 16337.6006 | lr 4.8e-04 | norm 5768.9434 | dt 9.865 +type train | step 1370 | loss 133.4408 253.0851 370.8299 603.0743 861.6453 1243.6324 1708.3456 2429.3462 3394.4207 5286.5903 8678.5537 16180.0010 | lr 4.8e-04 | norm 6988.2397 | dt 9.867 +type train | step 1371 | loss 124.6997 233.7899 348.9289 569.3255 831.8712 1178.2697 1631.5677 2327.0198 3296.1880 5187.7568 8590.2383 16221.5840 | lr 4.8e-04 | norm 6321.5664 | dt 9.856 +type train | step 1372 | loss 125.6097 236.1679 350.8355 571.9006 826.9276 1203.8655 1665.6355 2382.8535 3370.0237 5327.8535 8809.7314 16543.2637 | lr 4.8e-04 | norm 7105.2461 | dt 9.865 +type train | step 1373 | loss 127.1755 243.1440 362.3163 592.6407 851.8613 1237.1960 1715.3311 2445.2996 3460.4849 5444.5215 8942.3555 16821.6719 | lr 4.8e-04 | norm 6409.5449 | dt 9.861 +type train | step 1374 | loss 132.2840 249.1857 368.4184 598.0872 876.6086 1240.0999 1712.9220 2438.0295 3440.1860 5400.8716 8934.7090 16842.7363 | lr 4.8e-04 | norm 6525.2842 | dt 9.866 +type train | step 1375 | loss 135.0461 257.0222 378.3354 611.6883 913.0271 1262.4469 1739.7478 2478.8984 3465.6226 5404.6211 8908.7305 16739.0312 | lr 4.8e-04 | norm 7291.4272 | dt 9.853 +type train | step 1376 | loss 127.9902 240.8953 357.4192 580.8969 845.7693 1223.9746 1692.7424 2437.3735 3426.3894 5358.4326 8767.7217 16328.0186 | lr 4.8e-04 | norm 6350.0229 | dt 9.867 +type train | step 1377 | loss 134.2830 255.7043 375.6913 604.1874 882.5614 1232.8101 1696.6700 2401.7571 3377.1843 5299.0879 8716.2598 16120.9307 | lr 4.8e-04 | norm 6741.1040 | dt 9.870 +type train | step 1378 | loss 124.7810 235.4460 352.6878 577.2591 861.2009 1204.9803 1666.0811 2377.9919 3385.3242 5315.2432 8740.4014 16266.7559 | lr 4.8e-04 | norm 6306.6709 | dt 9.864 +type train | step 1379 | loss 132.8568 252.6285 371.6644 598.7275 900.0000 1232.7745 1696.6799 2407.5469 3400.0554 5340.6128 8771.0029 16358.9141 | lr 4.8e-04 | norm 6181.7451 | dt 9.865 +type train | step 1380 | loss 128.9797 240.7017 357.1375 579.2397 871.0300 1216.4373 1680.8623 2406.7925 3400.8169 5329.7578 8788.5508 16582.8223 | lr 4.8e-04 | norm 6448.0527 | dt 9.858 +type train | step 1381 | loss 131.2488 249.8441 370.0267 597.3738 886.3590 1239.7141 1713.5065 2437.1504 3419.2087 5330.3032 8785.9346 16477.7090 | lr 4.8e-04 | norm 6608.6133 | dt 9.879 +type train | step 1382 | loss 133.2572 252.7810 369.7615 590.7023 872.8301 1239.5701 1708.0486 2448.4856 3411.3186 5363.6309 8829.5479 16574.7773 | lr 4.8e-04 | norm 7146.6099 | dt 9.871 +type train | step 1383 | loss 127.8869 240.7287 355.9742 575.9784 853.8292 1204.9464 1659.4961 2361.0061 3326.5854 5204.3540 8543.7051 15947.0039 | lr 4.8e-04 | norm 5818.3652 | dt 9.860 +type train | step 1384 | loss 127.1905 241.7371 358.3474 574.0333 873.6063 1196.6296 1654.7983 2368.5605 3336.5527 5196.2500 8479.8662 15703.8125 | lr 4.8e-04 | norm 5895.3281 | dt 9.878 +type train | step 1385 | loss 134.8580 255.3305 378.4873 608.9772 901.8676 1240.9243 1718.9805 2453.9827 3488.2390 5447.2886 8868.0312 16579.8945 | lr 4.8e-04 | norm 7035.6392 | dt 9.872 +type train | step 1386 | loss 125.5593 236.4471 350.2827 569.3326 864.5873 1191.7859 1653.5695 2367.8323 3353.4866 5233.8760 8527.6182 15770.5488 | lr 4.8e-04 | norm 6479.3774 | dt 9.857 +type train | step 1387 | loss 133.5043 253.3623 372.2859 602.9529 893.8253 1245.7660 1711.4496 2430.4995 3399.1836 5290.6133 8670.7129 16244.5869 | lr 4.8e-04 | norm 6912.5908 | dt 9.872 +type train | step 1388 | loss 136.9477 259.9450 380.0651 604.3409 898.9012 1246.3131 1716.7944 2446.2175 3417.3550 5314.4087 8653.2734 16232.3682 | lr 4.8e-04 | norm 6968.8428 | dt 9.862 +type train | step 1389 | loss 120.7364 224.7472 340.7956 561.9526 848.5592 1194.0498 1675.0625 2408.0227 3420.7434 5409.2891 9003.0527 17048.2441 | lr 4.8e-04 | norm 8192.8535 | dt 9.857 +type train | step 1390 | loss 137.1756 260.6479 384.8010 620.8818 916.1540 1274.7375 1750.3228 2484.1899 3490.0728 5443.1523 8987.3848 16789.3926 | lr 4.8e-04 | norm 6349.7686 | dt 9.881 +type train | step 1391 | loss 140.9943 269.1602 392.1017 624.6352 931.0544 1277.1224 1753.6965 2483.1479 3463.4514 5376.2109 8807.4150 16511.5762 | lr 4.8e-04 | norm 6852.3286 | dt 9.868 +type train | step 1392 | loss 139.5055 262.7384 384.8088 615.1860 909.0658 1269.0151 1744.1886 2481.7131 3426.4656 5243.1968 8491.3652 15673.3301 | lr 4.8e-04 | norm 6488.3193 | dt 9.859 +type train | step 1393 | loss 127.3661 241.8984 358.0084 581.5525 861.2526 1203.2261 1667.3521 2381.6597 3352.1328 5266.6587 8651.8877 16156.8506 | lr 4.8e-04 | norm 7071.8867 | dt 9.906 +type train | step 1394 | loss 132.9331 252.4731 368.2964 590.4717 878.0138 1238.2780 1709.4917 2440.7634 3439.3115 5384.7764 8839.2324 16541.3359 | lr 4.8e-04 | norm 6251.8145 | dt 9.874 +type train | step 1395 | loss 135.0488 262.0429 390.2802 633.7751 935.5619 1311.0326 1793.3867 2565.4170 3602.8579 5596.6899 9172.4980 17217.9219 | lr 4.8e-04 | norm 11561.1387 | dt 9.870 +type train | step 1396 | loss 131.0466 250.1004 365.1132 590.2134 870.0864 1225.3375 1690.5959 2409.9116 3365.0981 5248.1396 8564.5537 15942.1309 | lr 4.8e-04 | norm 6373.2051 | dt 9.870 +type train | step 1397 | loss 133.8330 252.4117 372.5268 603.7103 889.3657 1249.6320 1719.8390 2465.6926 3461.8743 5413.9692 8887.3701 16638.7891 | lr 4.8e-04 | norm 6556.2412 | dt 9.866 +type train | step 1398 | loss 127.8524 241.6207 361.2557 590.4229 878.4248 1229.5933 1698.6921 2425.1216 3417.9265 5374.8296 8847.0186 16520.4648 | lr 4.8e-04 | norm 6725.1528 | dt 9.874 +type train | step 1399 | loss 130.7262 245.9772 365.4151 593.3912 870.0331 1226.2346 1690.9080 2417.7859 3407.7842 5292.3848 8705.2090 16227.3926 | lr 4.8e-04 | norm 7267.1875 | dt 9.865 +type train | step 1400 | loss 139.1451 262.3542 383.7268 613.8370 901.2562 1248.7661 1710.5956 2415.2205 3397.2036 5284.1919 8718.9668 16401.8555 | lr 4.8e-04 | norm 6609.2666 | dt 9.877 +type train | step 1401 | loss 141.6249 268.4014 388.4522 623.5817 919.5079 1281.6420 1757.8479 2518.4785 3483.2371 5457.5156 9033.2236 17134.2090 | lr 4.8e-04 | norm 8017.2217 | dt 9.854 +type train | step 1402 | loss 132.6419 249.9885 372.3831 603.0280 905.2631 1263.4017 1742.5696 2481.1243 3472.0676 5408.7012 8832.4062 16430.1016 | lr 4.8e-04 | norm 6401.8579 | dt 9.879 +type train | step 1403 | loss 133.5641 254.3871 374.2585 601.1074 893.1758 1247.8156 1721.4104 2447.5581 3424.9387 5328.7041 8769.9883 16496.3906 | lr 4.8e-04 | norm 6463.3716 | dt 9.876 +type train | step 1404 | loss 128.6105 240.7984 360.0443 580.9681 868.3685 1204.7894 1670.0844 2378.5913 3339.1416 5231.4019 8655.6172 16383.4648 | lr 4.8e-04 | norm 7366.5757 | dt 9.865 +type train | step 1405 | loss 134.9606 253.4168 380.3755 612.6177 904.3520 1271.1194 1758.2177 2501.6404 3488.8357 5454.2979 8949.9521 16953.2949 | lr 4.8e-04 | norm 6616.0093 | dt 9.869 +type train | step 1406 | loss 162.5329 309.7205 445.0648 691.7692 1009.4704 1391.9426 1884.3314 2680.0811 3637.2168 5507.5161 8831.8926 16454.5723 | lr 4.8e-04 | norm 8620.6123 | dt 9.850 +type train | step 1407 | loss 126.4491 238.6010 356.3372 577.6383 874.2438 1194.0665 1648.6417 2339.3254 3305.2061 5143.5078 8441.3936 15832.3359 | lr 4.8e-04 | norm 7166.4990 | dt 9.886 +type train | step 1408 | loss 119.9579 226.0136 343.3139 562.8796 852.0923 1190.9886 1668.4944 2409.5498 3439.7822 5430.9272 9030.5518 17110.4473 | lr 4.8e-04 | norm 9008.6533 | dt 9.877 +type train | step 1409 | loss 141.7899 267.4197 385.1503 614.4868 925.4164 1289.5825 1768.0228 2543.4756 3525.7283 5465.7666 8983.2979 16824.2812 | lr 4.8e-04 | norm 7032.7002 | dt 9.868 +type train | step 1410 | loss 126.7262 238.6972 356.3516 576.2885 864.7951 1201.7051 1656.0814 2369.4390 3347.2454 5254.1357 8691.6465 16368.8076 | lr 4.8e-04 | norm 6870.9253 | dt 9.857 +type train | step 1411 | loss 138.6837 259.8530 379.6304 603.4990 894.1724 1243.8237 1718.1239 2450.9873 3419.5176 5342.5068 8759.4238 16421.2637 | lr 4.8e-04 | norm 6852.4297 | dt 9.880 +type train | step 1412 | loss 141.2820 268.5555 390.7517 627.3522 914.6553 1287.6674 1760.2882 2522.7937 3482.0593 5437.4292 9052.9180 17151.3398 | lr 4.8e-04 | norm 9416.7061 | dt 9.849 +type train | step 1413 | loss 136.9554 260.6270 384.1177 617.4698 924.2981 1266.2891 1737.4573 2469.2361 3466.0654 5421.3975 8899.2393 16636.9863 | lr 4.8e-04 | norm 6783.2173 | dt 9.863 +type train | step 1414 | loss 139.0512 270.3799 401.6738 643.5460 945.3124 1310.5955 1787.0989 2535.3223 3543.0203 5522.3882 9145.7363 17429.0000 | lr 4.8e-04 | norm 8797.1660 | dt 9.853 +type train | step 1415 | loss 122.8040 233.7078 351.3607 576.6123 865.0389 1215.5890 1700.4846 2448.2029 3505.7297 5493.8301 8977.2686 16836.0059 | lr 4.8e-04 | norm 7192.3135 | dt 9.869 +type train | step 1416 | loss 138.7757 261.0139 384.8866 617.3260 918.4917 1284.3176 1780.3483 2549.0198 3594.1743 5617.7520 9226.5420 17329.3789 | lr 4.8e-04 | norm 7623.7856 | dt 9.868 +type train | step 1417 | loss 133.2304 251.9589 370.3719 593.5079 880.8256 1228.2418 1691.0061 2405.6555 3362.5513 5229.0278 8608.3525 16229.8574 | lr 4.8e-04 | norm 7294.6494 | dt 9.878 +type train | step 1418 | loss 129.3085 244.4412 357.7732 576.0154 865.6478 1203.1464 1655.4860 2364.4463 3337.5930 5216.5801 8563.9355 15925.3301 | lr 4.8e-04 | norm 6398.8135 | dt 9.856 +type train | step 1419 | loss 123.1258 231.1854 345.6222 569.2948 849.4206 1202.4492 1672.9401 2394.7683 3388.8423 5332.1445 8855.4092 16770.7734 | lr 4.8e-04 | norm 7110.3525 | dt 9.858 +type train | step 1420 | loss 131.6485 252.6009 381.7418 618.9785 919.4503 1278.4012 1755.0309 2517.0891 3542.5828 5581.2603 9252.9697 17674.5117 | lr 4.8e-04 | norm 9989.4766 | dt 9.862 +type train | step 1421 | loss 140.3120 274.5015 415.0966 671.6001 1005.8650 1391.5872 1921.3843 2729.1936 3785.8267 5822.9121 9467.8887 17651.1562 | lr 4.8e-04 | norm 6898.0327 | dt 9.881 +type train | step 1422 | loss 124.2177 234.8332 350.3736 569.7035 859.3452 1186.1206 1651.4106 2358.8931 3332.6138 5218.1768 8589.8359 16188.3076 | lr 4.8e-04 | norm 6387.4688 | dt 9.871 +type train | step 1423 | loss 127.0405 242.6693 363.7909 591.4517 896.6812 1231.1469 1705.2826 2423.2805 3434.0505 5365.6602 8876.4580 16616.9961 | lr 4.8e-04 | norm 6728.2178 | dt 9.870 +type train | step 1424 | loss 117.8708 222.1113 335.4203 552.4637 833.0680 1171.7457 1627.2134 2330.9387 3303.0239 5213.1880 8598.0078 16222.1230 | lr 4.8e-04 | norm 6783.4458 | dt 9.860 +type train | step 1425 | loss 143.3108 271.0306 400.4705 640.2369 943.3206 1310.2457 1779.2788 2521.7024 3485.6250 5381.1177 8725.6006 16257.7734 | lr 4.8e-04 | norm 6962.3511 | dt 9.869 +type train | step 1426 | loss 124.2152 233.1554 347.7879 566.3067 845.8507 1192.9650 1656.4506 2364.6560 3333.5139 5194.9175 8498.8711 15877.3652 | lr 4.8e-04 | norm 5979.5449 | dt 9.886 +type train | step 1427 | loss 139.5245 266.0126 390.0186 626.2523 916.3353 1290.0040 1771.3845 2504.6033 3492.8516 5413.1597 8836.0566 16528.8262 | lr 4.8e-04 | norm 7387.3257 | dt 9.873 +type train | step 1428 | loss 133.3347 252.5335 373.5915 596.0049 880.7537 1238.2690 1714.5704 2450.3447 3441.7327 5371.9668 8803.4238 16484.9414 | lr 4.8e-04 | norm 6313.6167 | dt 9.865 +type train | step 1429 | loss 119.9234 225.0335 342.4590 555.4138 828.0437 1175.0397 1639.7406 2359.6428 3342.0278 5268.7520 8675.1914 16269.0684 | lr 4.8e-04 | norm 7051.7446 | dt 9.868 +type train | step 1430 | loss 142.5801 268.8810 395.7498 632.2013 926.5232 1311.7004 1795.6877 2553.4036 3507.9563 5392.1812 8738.6816 16234.3711 | lr 4.8e-04 | norm 6828.0928 | dt 9.877 +type train | step 1431 | loss 140.3497 267.3833 388.5941 619.9214 907.7751 1256.7147 1724.4335 2440.0144 3392.1201 5247.5420 8568.0635 16137.1162 | lr 4.8e-04 | norm 8085.1655 | dt 9.869 +type train | step 1432 | loss 123.5586 234.3697 352.2554 564.6826 843.7466 1179.9100 1628.4542 2328.1558 3296.9900 5193.9658 8602.4805 16018.5508 | lr 4.8e-04 | norm 6797.8525 | dt 9.858 +type train | step 1433 | loss 120.2432 229.0911 345.5923 567.0928 843.8204 1191.6689 1647.2966 2360.5305 3332.4570 5262.9043 8727.8691 16400.0117 | lr 4.8e-04 | norm 6822.6958 | dt 9.874 +type train | step 1434 | loss 121.4364 232.0445 353.8520 587.7222 876.0821 1236.1765 1721.4706 2470.4075 3498.4402 5528.7632 9118.7354 17352.6914 | lr 4.7e-04 | norm 10331.0098 | dt 9.863 +type train | step 1435 | loss 151.7440 299.6954 435.3646 686.9614 994.7758 1416.2018 1938.8978 2743.2300 3793.9260 5856.2065 9517.0518 17615.9473 | lr 4.7e-04 | norm 7406.3164 | dt 9.857 +type train | step 1436 | loss 130.2011 246.6140 365.9888 592.0165 889.2408 1235.4299 1704.3367 2428.2024 3408.3577 5307.9517 8698.1807 16311.8926 | lr 4.7e-04 | norm 6284.9917 | dt 9.887 +type train | step 1437 | loss 162.5875 310.3638 458.1290 723.0336 1054.3041 1542.6893 2114.4543 3049.6182 4001.9915 6035.4497 9720.5918 17980.5508 | lr 4.7e-04 | norm 15701.5801 | dt 9.812 +type train | step 1438 | loss 135.7286 255.2354 377.2377 612.3115 903.8801 1272.6725 1749.7811 2503.4458 3478.8767 5388.1499 8847.0361 16626.2676 | lr 4.7e-04 | norm 6854.0317 | dt 9.858 +type train | step 1439 | loss 127.9781 239.8661 355.6595 578.4120 861.1886 1205.9836 1667.5691 2392.9539 3366.1355 5277.8008 8712.7139 16368.3926 | lr 4.7e-04 | norm 6907.3198 | dt 9.876 +type train | step 1440 | loss 139.2250 262.3137 386.0941 615.7979 905.8612 1257.2793 1715.9679 2425.4683 3358.5732 5198.6836 8493.4707 15956.4785 | lr 4.7e-04 | norm 6500.7715 | dt 9.856 +type train | step 1441 | loss 131.8809 250.6724 370.2376 597.3569 878.2747 1235.8052 1698.0750 2423.0840 3411.0610 5365.6299 8968.4863 17019.3945 | lr 4.7e-04 | norm 6590.8232 | dt 9.868 +type train | step 1442 | loss 147.7066 280.4224 410.1947 634.3463 923.0080 1307.6179 1792.4510 2550.1589 3533.5537 5421.5522 8806.0957 16279.7617 | lr 4.7e-04 | norm 6464.3179 | dt 9.868 +type train | step 1443 | loss 128.7458 245.3081 363.5118 581.9836 861.7048 1214.3101 1681.5808 2407.1782 3382.1707 5265.7114 8651.3438 16221.0625 | lr 4.7e-04 | norm 6695.4287 | dt 9.868 +type train | step 1444 | loss 133.6902 255.2210 380.8123 612.0043 904.8373 1297.3125 1802.4133 2611.8594 3640.6790 5656.7017 9320.9854 17541.6660 | lr 4.7e-04 | norm 7629.0303 | dt 9.856 +type train | step 1445 | loss 127.7549 241.7307 362.2275 586.0948 864.8790 1241.5150 1730.2977 2482.1138 3457.7871 5408.3760 8893.2783 16741.4121 | lr 4.7e-04 | norm 7111.8193 | dt 9.868 +type train | step 1446 | loss 125.2812 235.4173 356.0478 569.7761 849.2968 1188.9860 1641.9048 2337.7261 3295.8345 5155.3965 8481.0254 15922.4062 | lr 4.7e-04 | norm 6186.0879 | dt 9.876 +type train | step 1447 | loss 146.1079 276.6821 403.4630 644.8186 940.8119 1325.7955 1812.4812 2597.0825 3566.5044 5492.2920 8976.0410 16799.5566 | lr 4.7e-04 | norm 7324.7979 | dt 9.853 +type train | step 1448 | loss 128.5022 241.8540 365.5941 587.8203 872.2308 1251.8558 1736.2919 2498.5649 3506.5686 5419.2070 8847.7100 16512.6719 | lr 4.7e-04 | norm 8250.5508 | dt 9.878 +type train | step 1449 | loss 116.1351 219.0121 336.8151 551.8184 822.1622 1178.5853 1636.3273 2347.9854 3314.4934 5226.7451 8747.6826 16723.3828 | lr 4.7e-04 | norm 9318.7344 | dt 9.850 +type train | step 1450 | loss 132.1491 248.0073 375.5300 594.3057 875.1737 1252.1235 1727.9843 2487.2136 3456.7639 5405.2808 8937.1045 16813.5566 | lr 4.7e-04 | norm 7098.5620 | dt 9.861 +type train | step 1451 | loss 126.0559 238.6264 358.3922 576.2195 870.3104 1205.0054 1673.2974 2395.3081 3377.5273 5297.2603 8691.7510 16376.5400 | lr 4.7e-04 | norm 6835.5347 | dt 9.874 +type train | step 1452 | loss 120.5781 230.8580 357.3159 585.4618 880.4335 1243.7493 1739.6652 2508.4949 3541.0479 5542.6465 9187.5771 17638.3301 | lr 4.7e-04 | norm 8840.7861 | dt 9.873 +type train | step 1453 | loss 128.3775 240.5748 358.5957 572.9548 852.7762 1183.2362 1632.9791 2326.5591 3286.0940 5136.1587 8435.4590 15724.0742 | lr 4.7e-04 | norm 6773.8262 | dt 9.877 +type train | step 1454 | loss 119.1986 226.5743 348.7799 565.2984 848.7968 1213.9163 1695.9854 2457.8792 3476.3357 5474.4805 9177.5312 17531.4395 | lr 4.7e-04 | norm 12919.1992 | dt 9.868 +type train | step 1455 | loss 142.4655 274.8440 408.3044 639.0042 935.1844 1296.7919 1777.7651 2518.9353 3491.1594 5406.2842 8842.3496 16511.8184 | lr 4.7e-04 | norm 8040.0371 | dt 9.881 +type train | step 1456 | loss 146.9586 287.6376 454.0467 671.6307 969.8959 1333.4320 1809.2899 2543.2610 3458.4653 5301.0234 8659.3730 16264.1953 | lr 4.7e-04 | norm 13187.5557 | dt 9.858 +type train | step 1457 | loss 127.5444 241.0715 384.8596 581.2655 874.5381 1217.2476 1680.7898 2405.5520 3405.4294 5316.6025 8745.8672 16456.0156 | lr 4.7e-04 | norm 7511.1870 | dt 9.874 +type train | step 1458 | loss 132.6299 251.4813 401.2203 597.5679 882.3368 1240.5599 1706.1278 2429.3533 3400.1348 5295.5239 8653.6074 16154.5625 | lr 4.7e-04 | norm 6831.8682 | dt 9.871 +type train | step 1459 | loss 126.1210 239.1119 384.3401 576.9283 860.0153 1200.0745 1665.3268 2371.8865 3351.1716 5209.1538 8541.1494 16060.4375 | lr 4.7e-04 | norm 6674.9971 | dt 9.882 +type train | step 1460 | loss 133.6051 249.3571 395.2691 589.1079 865.8630 1220.4720 1674.5020 2393.4915 3395.1445 5314.6597 8710.5166 16420.7715 | lr 4.7e-04 | norm 7231.9170 | dt 9.866 +type train | step 1461 | loss 136.0440 255.6618 400.6569 603.2139 892.3055 1260.7290 1742.4761 2498.7988 3491.1006 5458.6514 9027.7031 17052.0000 | lr 4.7e-04 | norm 6945.4414 | dt 9.874 +type train | step 1462 | loss 127.4251 241.8226 384.2708 578.4595 850.1942 1212.3297 1672.5905 2399.3562 3371.1895 5274.7344 8678.0010 16264.5293 | lr 4.7e-04 | norm 6415.4736 | dt 9.859 +type train | step 1463 | loss 126.1752 238.8011 373.1352 570.6006 848.9875 1196.9852 1647.8739 2358.1802 3312.6677 5155.6084 8415.8691 15759.3652 | lr 4.7e-04 | norm 6004.5132 | dt 9.870 +type train | step 1464 | loss 124.6955 237.8281 375.8399 575.1422 853.0565 1207.2795 1677.6937 2397.6853 3366.1631 5226.4136 8586.6836 16126.0039 | lr 4.7e-04 | norm 6918.1606 | dt 9.875 +type train | step 1465 | loss 131.0595 248.6726 383.1464 590.5587 868.1019 1217.8596 1677.4556 2401.2319 3352.2456 5227.3838 8589.1738 16170.5996 | lr 4.7e-04 | norm 6933.3979 | dt 9.889 +type train | step 1466 | loss 129.0835 243.0974 387.8281 597.3871 885.5814 1250.8936 1728.3250 2479.1704 3497.1484 5481.0547 9075.7090 17064.4258 | lr 4.7e-04 | norm 6589.9614 | dt 9.875 +type train | step 1467 | loss 130.7900 251.9593 391.6382 610.5521 912.5023 1254.4412 1724.2167 2446.1089 3448.0989 5323.7979 8735.0596 16412.9824 | lr 4.7e-04 | norm 8471.7871 | dt 9.868 +type train | step 1468 | loss 124.6701 233.9613 380.7214 573.0260 866.5837 1203.3567 1674.8890 2409.1233 3389.9277 5302.7197 8756.5557 16493.4473 | lr 4.7e-04 | norm 8259.0967 | dt 9.861 +type train | step 1469 | loss 127.8714 241.7796 388.4035 577.0715 861.4722 1205.2191 1675.2183 2389.0225 3366.5913 5278.3926 8710.6377 16544.8652 | lr 4.7e-04 | norm 6638.4678 | dt 9.859 +type train | step 1470 | loss 126.1271 239.0672 383.9909 573.7927 859.4982 1198.4989 1660.9548 2368.1821 3353.2261 5249.0947 8632.4297 16072.0605 | lr 4.7e-04 | norm 6616.9927 | dt 9.873 +type train | step 1471 | loss 121.3390 228.2009 374.2085 551.1010 822.9273 1145.5242 1590.4070 2267.9766 3207.0913 5026.4565 8240.0840 15497.8037 | lr 4.7e-04 | norm 6563.9575 | dt 9.856 +type train | step 1472 | loss 136.1187 256.4703 402.1926 598.3641 892.8818 1220.7346 1672.0446 2373.9963 3334.7295 5187.0620 8472.4551 15836.0078 | lr 4.7e-04 | norm 6222.8530 | dt 9.872 +type train | step 1473 | loss 127.5676 241.4514 389.1341 585.5352 878.1557 1218.1913 1682.7380 2409.0547 3368.4202 5268.3984 8684.3213 16408.5156 | lr 4.7e-04 | norm 6378.6494 | dt 9.862 +type train | step 1474 | loss 131.4581 244.4461 380.3072 575.5963 849.3912 1194.5942 1645.0566 2351.3901 3284.8494 5138.5610 8506.6318 16072.7266 | lr 4.7e-04 | norm 6309.5127 | dt 9.853 +type train | step 1475 | loss 132.1145 248.6577 390.7934 589.7239 878.6838 1221.8157 1683.3176 2394.6584 3337.3635 5178.6660 8467.6465 15977.7607 | lr 4.7e-04 | norm 6558.9180 | dt 9.863 +type train | step 1476 | loss 123.2192 233.5979 373.2208 569.0515 857.9817 1187.6544 1642.2587 2348.5330 3313.4541 5171.0713 8533.8525 16075.4580 | lr 4.7e-04 | norm 5916.0566 | dt 9.887 +type train | step 1477 | loss 126.4109 242.9122 375.9855 577.5169 868.2704 1206.5291 1664.8186 2384.9600 3351.3169 5232.7021 8619.9297 16074.7939 | lr 4.7e-04 | norm 5465.6274 | dt 9.861 +type train | step 1478 | loss 129.8057 246.6312 384.9865 596.0797 892.8044 1250.1583 1715.4834 2454.9329 3450.7734 5374.1201 8866.7031 16679.7168 | lr 4.7e-04 | norm 7181.3872 | dt 9.857 +type train | step 1479 | loss 130.5958 247.3813 391.7942 592.2527 885.0385 1226.1494 1687.9081 2412.5544 3373.4939 5256.8398 8639.7090 16161.2432 | lr 4.7e-04 | norm 5957.9629 | dt 9.876 +type train | step 1480 | loss 126.1968 236.6034 378.0685 572.5420 861.7864 1204.1125 1668.0890 2397.2649 3370.6069 5278.9316 8742.1943 16401.0488 | lr 4.7e-04 | norm 7283.2817 | dt 9.864 +type train | step 1481 | loss 129.5659 245.8963 389.8910 584.6302 878.6110 1234.0969 1712.3907 2460.9490 3450.8113 5372.3369 8805.7012 16524.3086 | lr 4.7e-04 | norm 6402.2925 | dt 9.872 +type train | step 1482 | loss 142.5249 267.7806 407.5680 620.8955 909.2802 1282.3374 1761.2816 2520.2852 3501.9702 5438.2075 8941.4043 16756.1289 | lr 4.7e-04 | norm 6985.2285 | dt 9.878 +type train | step 1483 | loss 129.1751 246.1017 378.3276 594.2697 889.5034 1229.1927 1696.7667 2402.3032 3385.8872 5279.3687 8682.0430 16304.2969 | lr 4.7e-04 | norm 6490.8784 | dt 9.872 +type train | step 1484 | loss 130.1177 256.4666 407.3718 643.5659 966.5536 1325.4269 1819.6473 2578.6858 3672.3198 5711.7026 9458.1650 17853.6250 | lr 4.7e-04 | norm 9941.8896 | dt 9.865 +type train | step 1485 | loss 134.8294 258.5323 398.9840 612.1081 911.7392 1256.6672 1726.1974 2435.8757 3414.7224 5252.5918 8620.0215 16103.8232 | lr 4.7e-04 | norm 6082.2329 | dt 9.878 +type train | step 1486 | loss 126.7849 243.8989 386.9265 603.5829 912.4750 1265.2076 1751.6498 2507.6421 3570.9275 5536.1670 9027.0215 16867.1973 | lr 4.7e-04 | norm 6517.2412 | dt 9.870 +type train | step 1487 | loss 128.7003 246.5782 381.6327 602.3657 907.3742 1254.1504 1731.2429 2471.6396 3484.4419 5425.7173 8897.5078 16753.2285 | lr 4.7e-04 | norm 6455.0928 | dt 9.872 +type train | step 1488 | loss 125.3637 239.6681 373.9037 589.4581 889.1245 1244.1818 1729.3406 2480.6191 3506.5393 5478.0273 9002.4092 16810.5508 | lr 4.7e-04 | norm 7123.0278 | dt 9.870 +type train | step 1489 | loss 125.3572 238.9865 376.3758 590.1029 893.4077 1240.5425 1722.7538 2462.2637 3497.7239 5470.6138 9073.6562 16993.1055 | lr 4.7e-04 | norm 6512.0664 | dt 9.872 +type train | step 1490 | loss 130.1648 248.9786 384.3370 595.3353 890.8411 1234.5204 1713.1660 2442.5039 3460.9348 5431.9082 8963.5908 17055.6191 | lr 4.7e-04 | norm 7433.5610 | dt 9.879 +type train | step 1491 | loss 134.4207 258.0081 395.6403 610.3170 906.4290 1254.5768 1723.9056 2444.5352 3447.8750 5336.7437 8811.3281 16462.7285 | lr 4.7e-04 | norm 5914.7739 | dt 9.900 +type train | step 1492 | loss 142.7578 274.3440 419.7897 634.3849 938.7834 1289.3475 1767.6292 2505.8560 3518.8738 5495.9736 9076.3477 17112.3105 | lr 4.7e-04 | norm 6914.2373 | dt 9.870 +type train | step 1493 | loss 131.6986 248.2556 379.8571 591.1656 885.9270 1238.8080 1714.2686 2462.3652 3452.2773 5418.9629 9007.9121 17281.6035 | lr 4.7e-04 | norm 10298.2822 | dt 9.872 +type train | step 1494 | loss 134.3703 251.6928 392.8489 598.1104 896.1796 1251.3889 1725.5482 2452.9985 3421.9746 5293.9902 8709.0547 16341.8281 | lr 4.7e-04 | norm 7077.4932 | dt 9.860 +type train | step 1495 | loss 129.5155 246.7596 396.8186 595.6825 887.7803 1225.5731 1685.7820 2387.7278 3376.3262 5247.7061 8575.8770 15960.4141 | lr 4.7e-04 | norm 6034.0537 | dt 9.885 +type train | step 1496 | loss 141.5900 271.2181 426.2157 635.2454 943.6575 1291.2123 1770.3458 2506.5002 3499.7844 5395.8057 8828.6992 16633.8594 | lr 4.7e-04 | norm 6600.6558 | dt 9.907 +type train | step 1497 | loss 140.1532 268.5851 422.8078 635.2397 945.6063 1288.3131 1763.0928 2476.2476 3479.4319 5391.0044 8894.3164 16856.4355 | lr 4.7e-04 | norm 7478.3569 | dt 9.887 +type train | step 1498 | loss 128.2236 244.0004 387.6191 591.9554 887.9492 1241.2169 1718.7147 2451.3125 3434.1807 5338.4487 8785.9463 16437.2324 | lr 4.7e-04 | norm 5916.0796 | dt 9.874 +type train | step 1499 | loss 135.8422 261.9785 416.6795 629.3215 937.7939 1291.9370 1780.7778 2529.7859 3569.3723 5605.9326 9248.8037 17438.6133 | lr 4.7e-04 | norm 8227.2129 | dt 9.890 +type train | step 1500 | loss 124.6165 236.5891 369.1356 569.3495 856.5676 1181.1924 1625.1069 2302.3406 3250.5911 5070.4238 8316.0684 15653.2021 | lr 4.7e-04 | norm 6586.8364 | dt 9.875 +type train | step 1501 | loss 140.8594 271.0627 421.5188 635.3376 939.9286 1318.2637 1805.8163 2576.6040 3563.5154 5443.2036 8845.3721 16296.8574 | lr 4.7e-04 | norm 5876.0059 | dt 9.862 +type train | step 1502 | loss 126.1033 240.6461 380.9122 578.9781 865.6378 1195.5320 1652.1492 2361.3086 3326.7693 5180.2070 8479.5527 16027.0879 | lr 4.7e-04 | norm 8333.4170 | dt 9.854 +type train | step 1503 | loss 133.6852 255.2471 409.2602 611.1604 914.3131 1262.2894 1749.1238 2492.6938 3523.5291 5498.4648 9026.2324 16937.6035 | lr 4.7e-04 | norm 7269.4082 | dt 9.870 +type train | step 1504 | loss 130.5137 247.9137 391.7804 597.0802 899.5063 1228.3967 1691.3043 2404.7769 3397.5554 5302.8457 8685.5967 16261.0859 | lr 4.7e-04 | norm 6791.0200 | dt 9.860 +type train | step 1505 | loss 132.3504 257.2617 397.1332 603.4058 905.5689 1278.1628 1758.5931 2543.1011 3548.4253 5480.6831 8880.0039 16499.1562 | lr 4.7e-04 | norm 7617.7134 | dt 9.847 +type train | step 1506 | loss 131.0786 247.6694 391.0724 595.6431 890.0676 1233.2292 1694.5549 2431.1953 3411.2295 5299.1704 8732.4512 16413.6895 | lr 4.7e-04 | norm 7808.8525 | dt 9.855 +type train | step 1507 | loss 134.7366 255.8238 397.2687 607.6733 903.9264 1243.3562 1713.8278 2421.0481 3388.5542 5232.5996 8584.9629 16297.0762 | lr 4.7e-04 | norm 7238.5234 | dt 9.874 +type train | step 1508 | loss 153.0093 296.6997 483.9225 691.0200 1013.3886 1377.3398 1875.8660 2613.7122 3637.1321 5527.8359 9111.9395 17073.1484 | lr 4.7e-04 | norm 12623.5303 | dt 9.868 +type train | step 1509 | loss 137.5090 261.9266 416.7939 629.7770 933.4548 1295.7449 1776.3990 2514.1162 3537.9607 5488.3022 9030.5674 17040.6133 | lr 4.7e-04 | norm 6960.4946 | dt 9.868 +type train | step 1510 | loss 123.9695 235.1629 380.7599 577.8681 869.1542 1214.4360 1685.5701 2410.3962 3407.8096 5307.2246 8749.8076 16639.3535 | lr 4.7e-04 | norm 7408.1294 | dt 9.866 +type train | step 1511 | loss 131.4180 249.4398 397.4908 597.6763 893.1022 1234.9906 1698.8773 2426.1841 3413.2866 5274.2710 8641.4717 16279.0410 | lr 4.7e-04 | norm 7258.6948 | dt 9.865 +type train | step 1512 | loss 132.6728 254.7831 414.1113 617.4374 919.9569 1269.6591 1749.9547 2483.4434 3512.2275 5414.4648 8870.4209 16684.9941 | lr 4.7e-04 | norm 6076.1509 | dt 9.876 +type train | step 1513 | loss 128.6234 243.4247 395.2350 586.7486 880.9626 1217.2693 1683.1598 2390.0076 3389.4551 5262.5879 8718.9980 16367.5400 | lr 4.7e-04 | norm 6847.7310 | dt 9.880 +type train | step 1514 | loss 135.6632 258.3020 418.0513 612.1537 913.9995 1276.2139 1757.5098 2505.0061 3514.3528 5403.7212 8843.9170 16425.8027 | lr 4.7e-04 | norm 5826.5967 | dt 9.882 +type train | step 1515 | loss 132.4719 256.2848 415.4244 615.6989 913.4365 1281.1658 1763.2233 2505.6533 3504.6868 5457.7163 8965.5293 16944.7559 | lr 4.7e-04 | norm 7510.5337 | dt 9.874 +type train | step 1516 | loss 121.6872 231.8357 380.7457 565.3423 853.2726 1193.5831 1655.4242 2375.9502 3364.8923 5239.1387 8621.1895 16086.4189 | lr 4.7e-04 | norm 5815.9033 | dt 9.881 +type train | step 1517 | loss 130.4912 253.0341 413.3589 626.6354 932.3404 1298.5131 1802.1321 2566.6243 3610.6416 5641.8809 9387.6074 17683.7168 | lr 4.7e-04 | norm 7157.0366 | dt 9.865 +type train | step 1518 | loss 127.9586 247.5241 407.9141 595.3854 896.7191 1232.7805 1701.1265 2426.9045 3434.5493 5343.7554 8841.1152 16746.5625 | lr 4.7e-04 | norm 7284.0376 | dt 9.869 +type train | step 1519 | loss 128.5804 243.8865 404.9094 583.4891 873.6286 1218.8779 1682.1259 2400.7156 3379.6235 5261.3086 8689.1436 16391.3730 | lr 4.7e-04 | norm 7508.1348 | dt 9.863 +type train | step 1520 | loss 153.6736 287.5280 453.7821 652.1893 945.6065 1311.9150 1782.3540 2518.0210 3431.5874 5271.2490 8623.2402 16126.5127 | lr 4.7e-04 | norm 9719.7549 | dt 9.871 +type train | step 1521 | loss 165.2974 307.0876 479.4200 677.9204 969.4838 1335.4991 1795.1174 2507.7004 3335.3850 5040.0518 8088.3599 14966.2363 | lr 4.7e-04 | norm 9483.7559 | dt 9.842 +type train | step 1522 | loss 132.9721 254.0616 424.2990 604.5844 895.9707 1245.9670 1712.9924 2436.7668 3407.8940 5267.0298 8601.7441 16070.3721 | lr 4.7e-04 | norm 6257.5830 | dt 9.870 +type train | step 1523 | loss 121.7091 232.5788 387.4514 566.6600 851.9080 1187.1327 1646.2202 2350.6465 3344.3770 5222.4536 8586.3125 16089.9697 | lr 4.7e-04 | norm 7055.6436 | dt 9.871 +type train | step 1524 | loss 127.9038 242.5546 397.2674 580.2393 863.0792 1196.2856 1646.8472 2341.6802 3319.3574 5210.2754 8620.8184 16204.1230 | lr 4.7e-04 | norm 6568.3076 | dt 9.868 +type train | step 1525 | loss 127.3407 242.0648 399.1536 585.3173 873.8797 1236.8120 1712.8256 2466.2832 3473.6543 5410.1553 8927.7256 16725.5195 | lr 4.7e-04 | norm 6809.3354 | dt 9.872 +type train | step 1526 | loss 129.4325 245.4567 398.8241 583.1023 866.8638 1214.2014 1679.6914 2394.0078 3360.0525 5226.4517 8577.8779 16066.1943 | lr 4.7e-04 | norm 6881.7329 | dt 9.859 +type train | step 1527 | loss 133.9380 255.1746 413.6802 604.7690 893.9924 1237.4846 1702.2814 2415.7749 3380.3418 5259.4565 8657.5166 16171.9277 | lr 4.7e-04 | norm 6401.7012 | dt 9.858 +type train | step 1528 | loss 142.8630 270.0842 434.0907 626.8033 919.8295 1283.1133 1756.6284 2509.6177 3453.7427 5351.5464 8836.4180 16696.2930 | lr 4.7e-04 | norm 7235.7598 | dt 9.863 +type train | step 1529 | loss 134.3914 256.4027 417.8815 602.3561 894.8575 1250.5001 1725.8972 2480.8228 3466.1919 5401.9634 8816.9492 16618.5039 | lr 4.7e-04 | norm 7180.7661 | dt 9.861 +type train | step 1530 | loss 128.0691 242.4553 397.6296 586.0109 875.9056 1240.4171 1723.7278 2490.3369 3472.8457 5454.7559 8980.9639 16859.8340 | lr 4.7e-04 | norm 7185.4180 | dt 9.847 +type train | step 1531 | loss 136.8097 261.8421 420.1459 612.1023 900.2748 1256.0620 1719.6462 2431.1782 3393.4995 5233.9731 8554.9131 15939.9980 | lr 4.7e-04 | norm 8220.2295 | dt 9.884 +type train | step 1532 | loss 129.5652 247.5991 410.3313 595.7730 885.0966 1228.6537 1691.2761 2398.1357 3386.1011 5259.1621 8657.2188 16287.6396 | lr 4.7e-04 | norm 6472.2515 | dt 9.883 +type train | step 1533 | loss 131.7577 251.0034 408.1795 599.4745 896.7206 1259.3140 1739.0145 2481.6555 3486.3057 5409.8628 8878.9102 16837.9883 | lr 4.7e-04 | norm 7909.5947 | dt 9.856 +type train | step 1534 | loss 129.2424 246.3999 401.8961 589.7729 878.4775 1223.4041 1688.3347 2410.4536 3395.3110 5297.4790 8748.2559 16449.7832 | lr 4.7e-04 | norm 5986.6533 | dt 9.897 +type train | step 1535 | loss 126.3063 240.4973 389.9121 582.6752 875.5759 1231.4888 1712.6094 2447.8479 3461.3069 5376.4624 8784.8730 16373.7080 | lr 4.7e-04 | norm 6751.6655 | dt 9.862 +type train | step 1536 | loss 129.7582 251.8368 415.1522 607.8412 901.1531 1260.6915 1742.2098 2498.1790 3503.3916 5464.1694 8983.4980 16860.5938 | lr 4.7e-04 | norm 6304.7671 | dt 9.886 +type train | step 1537 | loss 137.9231 261.6192 424.0761 615.8322 913.8257 1266.1947 1735.6907 2462.3801 3442.1555 5255.0166 8493.2061 15697.7598 | lr 4.7e-04 | norm 6499.8022 | dt 9.860 +type train | step 1538 | loss 126.7804 240.0986 396.1756 582.3198 869.0992 1215.0182 1681.5819 2400.3535 3385.9995 5281.3076 8739.1436 16611.8145 | lr 4.7e-04 | norm 7736.3486 | dt 9.891 +type train | step 1539 | loss 131.1157 249.2188 399.7525 591.1835 878.9811 1232.8840 1693.2955 2421.3689 3377.0227 5217.6123 8613.5977 16178.3037 | lr 4.7e-04 | norm 6936.4512 | dt 9.894 +type train | step 1540 | loss 121.9393 235.3353 394.8505 581.1578 876.6841 1226.7280 1694.5969 2431.7349 3475.2715 5508.2305 9266.2773 17782.3672 | lr 4.7e-04 | norm 13153.9229 | dt 9.846 +type train | step 1541 | loss 124.3266 237.3091 389.3870 571.5024 853.6058 1197.0609 1648.1696 2347.7998 3308.9260 5147.6313 8472.2480 16085.9258 | lr 4.7e-04 | norm 7469.0181 | dt 9.879 +type train | step 1542 | loss 133.7287 254.6597 409.9053 607.7519 897.0316 1251.0280 1715.5819 2435.5127 3425.8701 5317.7188 8695.0254 16298.5752 | lr 4.7e-04 | norm 6293.0269 | dt 9.873 +type train | step 1543 | loss 127.5719 243.6800 396.1710 584.9940 870.8502 1215.1831 1679.2931 2388.4866 3365.2812 5250.5039 8682.3496 16357.8223 | lr 4.7e-04 | norm 6585.0845 | dt 9.872 +type train | step 1544 | loss 126.0898 240.8802 389.4496 570.8595 852.6550 1203.5790 1668.4840 2377.0352 3359.3079 5219.7212 8584.9043 16127.0391 | lr 4.7e-04 | norm 7648.3906 | dt 9.860 +type train | step 1545 | loss 129.8206 247.4996 399.2049 585.4836 867.7565 1210.0026 1670.4475 2371.3652 3335.9299 5129.6875 8371.4336 15705.2500 | lr 4.7e-04 | norm 6098.7266 | dt 9.869 +type train | step 1546 | loss 125.0946 236.4501 389.5968 576.7075 859.8981 1198.1350 1652.9229 2353.6409 3320.1868 5143.8823 8460.4941 15820.5156 | lr 4.7e-04 | norm 6089.5908 | dt 9.875 +type train | step 1547 | loss 143.7717 275.1249 430.4466 643.3004 941.3285 1325.2134 1818.4794 2607.5354 3595.5496 5561.1123 9166.4639 17223.5156 | lr 4.7e-04 | norm 7245.2002 | dt 9.872 +type train | step 1548 | loss 115.9072 217.3215 355.9303 546.6194 834.2540 1171.8617 1648.7218 2370.1128 3363.1653 5248.1772 8845.0156 17006.5332 | lr 4.7e-04 | norm 14173.9092 | dt 9.852 +type train | step 1549 | loss 125.1873 240.2406 390.7652 590.0081 877.8364 1230.7244 1702.0537 2447.6570 3446.1045 5398.0488 8956.8379 17043.8770 | lr 4.7e-04 | norm 7145.0898 | dt 9.868 +type train | step 1550 | loss 132.0139 252.3700 408.2568 603.7922 900.5240 1276.9348 1767.4369 2523.2766 3519.7622 5418.8608 8811.6807 16430.4844 | lr 4.7e-04 | norm 6687.9766 | dt 9.878 +type train | step 1551 | loss 118.7615 228.0934 384.4348 576.3221 872.0084 1217.6670 1694.4187 2431.8667 3484.3193 5492.1382 9211.3105 17689.3086 | lr 4.7e-04 | norm 7991.6826 | dt 9.864 +type train | step 1552 | loss 132.6103 249.9571 398.8672 590.5833 877.8189 1232.3522 1705.8239 2437.2925 3411.6997 5284.9707 8707.6221 16331.4619 | lr 4.7e-04 | norm 7524.0991 | dt 9.882 +type train | step 1553 | loss 119.7017 225.2237 364.8242 551.5075 830.3427 1162.8301 1613.4001 2301.4551 3251.7339 5044.6870 8266.7217 15449.9102 | lr 4.7e-04 | norm 6954.8931 | dt 9.866 +type train | step 1554 | loss 119.7139 230.2095 380.6479 577.4795 869.0198 1216.9316 1691.3311 2429.4570 3453.9541 5391.9180 8862.9932 16627.8164 | lr 4.7e-04 | norm 7083.9976 | dt 9.861 +type train | step 1555 | loss 120.6962 231.9182 379.1309 566.6832 852.9515 1202.8285 1673.8352 2407.3308 3403.9785 5312.0796 8717.4268 16300.7617 | lr 4.7e-04 | norm 6376.2007 | dt 9.872 +type train | step 1556 | loss 131.6439 251.9675 399.0066 590.3837 873.0879 1209.5316 1653.5605 2343.1477 3297.2476 5114.8115 8374.2559 15704.4326 | lr 4.7e-04 | norm 6154.1226 | dt 9.879 +type train | step 1557 | loss 131.2758 253.5594 406.7725 595.8995 886.1574 1224.2236 1684.9567 2393.3516 3382.9880 5243.9731 8607.2832 16092.9561 | lr 4.7e-04 | norm 6122.5493 | dt 9.880 +type train | step 1558 | loss 128.3309 241.8814 393.4008 585.2614 867.2938 1212.2446 1676.8414 2374.0356 3328.6685 5144.0610 8416.4229 15750.7178 | lr 4.7e-04 | norm 6739.2832 | dt 9.869 +type train | step 1559 | loss 128.8572 246.9352 399.2705 589.9893 872.6828 1225.1387 1686.6547 2407.4509 3383.8955 5237.5747 8570.5635 15944.2793 | lr 4.7e-04 | norm 5530.3657 | dt 9.873 +type train | step 1560 | loss 123.4064 235.1078 380.7641 569.0341 857.0706 1201.5909 1668.3251 2382.6646 3350.8608 5216.1426 8590.2178 16112.9033 | lr 4.7e-04 | norm 5772.2690 | dt 9.885 +type train | step 1561 | loss 126.7187 246.1021 403.2643 598.9562 890.8719 1248.2513 1722.5714 2456.0200 3475.3630 5386.9102 8807.7773 16453.4746 | lr 4.7e-04 | norm 5690.3628 | dt 9.870 +type train | step 1562 | loss 127.2340 244.2413 395.3004 595.6210 887.1035 1236.9781 1707.5876 2445.6060 3461.0500 5370.3389 8915.0342 16767.2930 | lr 4.7e-04 | norm 7194.5830 | dt 9.867 +type train | step 1563 | loss 130.3731 250.2094 401.1599 598.5621 885.6072 1227.2010 1688.4114 2400.5530 3336.6008 5176.5396 8467.1748 15908.6836 | lr 4.6e-04 | norm 6018.0444 | dt 9.889 +type train | step 1564 | loss 138.9900 262.4852 413.3050 601.5944 885.0368 1238.9689 1692.4014 2411.9082 3351.3894 5176.1182 8499.0420 15962.7773 | lr 4.6e-04 | norm 6570.2339 | dt 9.887 +type train | step 1565 | loss 127.2816 240.4916 386.5811 572.1964 855.6511 1202.5028 1662.5026 2360.9719 3309.9812 5152.6655 8460.0459 15906.9883 | lr 4.6e-04 | norm 7855.6504 | dt 9.858 +type train | step 1566 | loss 124.8214 238.6196 388.0199 578.7383 862.5140 1212.0101 1671.5886 2385.2751 3368.6475 5249.6763 8585.2734 16167.3867 | lr 4.6e-04 | norm 7237.4434 | dt 9.857 +type train | step 1567 | loss 127.0307 241.6075 391.7971 585.6703 869.6271 1213.4385 1670.6415 2371.9937 3358.9724 5212.8872 8612.3037 16264.8926 | lr 4.6e-04 | norm 6743.7612 | dt 9.866 +type train | step 1568 | loss 136.6512 261.1154 415.8329 615.9808 905.1821 1289.5052 1771.4369 2523.1377 3509.7954 5369.9644 8792.1299 16319.1523 | lr 4.6e-04 | norm 6673.8008 | dt 10.162 +type train | step 1569 | loss 138.5708 264.8296 420.1255 627.0411 918.0353 1292.7642 1769.6997 2518.8594 3461.0452 5315.2573 8749.3398 16509.3027 | lr 4.6e-04 | norm 7763.6113 | dt 9.864 +type train | step 1570 | loss 124.5142 234.2326 382.1160 585.8137 877.3973 1213.7513 1682.9319 2398.7925 3379.6367 5311.7432 9067.7988 17856.3418 | lr 4.6e-04 | norm 19189.5410 | dt 9.847 +type train | step 1571 | loss 133.7715 254.1752 410.2620 617.4963 914.4019 1279.0743 1770.8738 2534.0608 3546.9219 5494.7656 9113.6914 17227.5059 | lr 4.6e-04 | norm 8058.1016 | dt 9.856 +type train | step 1572 | loss 131.5205 251.3923 403.7759 596.6064 889.6832 1239.9456 1711.7498 2421.4666 3429.8394 5337.0430 8759.6729 16382.3652 | lr 4.6e-04 | norm 6990.5513 | dt 9.888 +type train | step 1573 | loss 141.6510 268.9058 418.5444 624.4556 917.6442 1326.0273 1829.5159 2657.7566 3642.7786 5647.2070 9279.2910 17388.0703 | lr 4.6e-04 | norm 11318.8125 | dt 9.864 +type train | step 1574 | loss 118.7670 227.4924 374.2069 562.4146 840.6179 1181.1571 1642.6689 2342.6765 3315.8269 5177.1733 8566.2666 16172.9248 | lr 4.6e-04 | norm 7384.4214 | dt 9.875 +type train | step 1575 | loss 120.7228 230.6374 372.0187 566.3181 846.4646 1182.0157 1637.7268 2332.6484 3297.1707 5139.7065 8446.8965 15809.4023 | lr 4.6e-04 | norm 7478.9263 | dt 9.886 +type train | step 1576 | loss 128.7171 244.9202 392.0091 584.9135 867.3012 1212.9480 1668.5101 2363.7073 3328.3164 5150.0376 8427.2295 15675.9590 | lr 4.6e-04 | norm 7079.6274 | dt 9.885 +type train | step 1577 | loss 127.8974 244.3217 392.5120 588.6514 873.3189 1226.4163 1688.0460 2402.1548 3368.6277 5207.2734 8555.8359 16001.8574 | lr 4.6e-04 | norm 5944.6763 | dt 9.878 +type train | step 1578 | loss 125.1685 238.1574 384.6727 578.5525 855.6883 1201.0286 1657.1543 2363.3193 3335.8926 5216.2036 8663.9902 16359.3184 | lr 4.6e-04 | norm 5808.8472 | dt 9.875 +type train | step 1579 | loss 133.8734 256.9492 406.4001 608.4155 889.1077 1258.0326 1735.3778 2473.2778 3467.1123 5371.4497 8821.7930 16492.1484 | lr 4.6e-04 | norm 5781.6377 | dt 9.864 +type train | step 1580 | loss 131.3210 250.5993 404.6613 619.5906 914.2656 1302.7612 1804.7137 2585.0500 3631.0215 5646.3950 9285.4248 17607.5664 | lr 4.6e-04 | norm 8394.8594 | dt 9.838 +type train | step 1581 | loss 129.8444 248.2051 395.6129 596.4961 875.9949 1225.3304 1688.8036 2399.3899 3379.2969 5241.5688 8604.6797 16131.4551 | lr 4.6e-04 | norm 6247.5303 | dt 9.871 +type train | step 1582 | loss 126.4083 238.8455 382.6046 582.0967 863.9631 1221.2310 1693.1061 2433.6035 3414.6118 5292.3208 8776.5049 16726.3379 | lr 4.6e-04 | norm 6989.6484 | dt 9.875 +type train | step 1583 | loss 141.5203 272.0366 421.5125 627.9183 916.5881 1282.7562 1746.4515 2478.2559 3418.8398 5215.8179 8462.7090 15887.9697 | lr 4.6e-04 | norm 6521.0391 | dt 9.897 +type train | step 1584 | loss 144.2098 280.7952 433.9333 646.2537 934.0932 1325.0398 1788.0189 2515.3992 3400.8855 5101.9429 8151.1123 15281.6523 | lr 4.6e-04 | norm 10888.5254 | dt 9.860 +type train | step 1585 | loss 119.8395 230.9869 373.3048 558.2936 830.7043 1199.8584 1662.0869 2453.6401 3429.7368 5427.3291 9040.6055 17193.5352 | lr 4.6e-04 | norm 12391.8936 | dt 9.848 +type train | step 1586 | loss 125.6420 242.6388 387.6879 583.6855 865.9697 1237.3036 1707.9728 2494.1169 3474.2996 5451.4985 9072.3994 17164.7734 | lr 4.6e-04 | norm 9463.3721 | dt 9.882 +type train | step 1587 | loss 123.3035 234.8824 376.2123 568.4492 841.8398 1180.6586 1631.3849 2320.0698 3290.1179 5117.5264 8438.6250 15855.9951 | lr 4.6e-04 | norm 6538.1558 | dt 9.893 +type train | step 1588 | loss 131.4014 247.6738 395.1586 596.6057 879.6743 1234.0725 1700.4755 2427.9556 3405.9822 5283.8174 8716.4678 16535.1523 | lr 4.6e-04 | norm 7226.2280 | dt 9.904 +type train | step 1589 | loss 130.0717 248.4724 398.2028 599.6722 885.2486 1239.3610 1705.3300 2425.0930 3406.1614 5260.5815 8625.5039 16188.8174 | lr 4.6e-04 | norm 6656.6069 | dt 9.889 +type train | step 1590 | loss 123.9560 236.8203 374.2339 566.5307 838.1425 1172.8483 1617.0487 2301.3242 3247.8591 5046.8423 8295.3936 15549.7783 | lr 4.6e-04 | norm 6407.1084 | dt 9.892 +type train | step 1591 | loss 120.0062 227.4734 366.1494 566.9104 845.8561 1215.4487 1695.4193 2449.7019 3421.0864 5348.6924 8928.2080 16870.4336 | lr 4.6e-04 | norm 8985.2959 | dt 9.869 +type train | step 1592 | loss 130.8999 247.2530 394.5495 597.9805 882.6143 1269.9380 1761.5092 2526.1162 3526.2114 5473.8013 9081.5654 17201.7344 | lr 4.6e-04 | norm 8660.3145 | dt 9.887 +type train | step 1593 | loss 120.6139 228.1441 365.4519 554.6027 825.9094 1168.2463 1631.0326 2337.5825 3293.5359 5150.5601 8511.5400 16154.1113 | lr 4.6e-04 | norm 9454.1123 | dt 9.891 +type train | step 1594 | loss 127.2283 242.2128 387.5604 582.1987 866.1180 1209.8024 1671.7881 2384.3862 3365.8235 5251.5264 8687.4961 16372.7988 | lr 4.6e-04 | norm 7840.4419 | dt 9.890 +type train | step 1595 | loss 132.8251 255.7327 399.9398 602.2692 877.7535 1235.1556 1702.7749 2404.8164 3354.1133 5215.6860 8627.3379 16249.3379 | lr 4.6e-04 | norm 7032.4355 | dt 9.879 +type train | step 1596 | loss 135.1043 261.6324 412.4441 617.6584 913.8186 1284.0786 1758.4806 2499.6826 3492.4565 5338.6904 8691.4600 16172.4180 | lr 4.6e-04 | norm 6224.8193 | dt 9.877 +type train | step 1597 | loss 128.8267 244.7709 385.7245 586.6572 862.3085 1228.5315 1694.6527 2422.3784 3369.8606 5244.1001 8661.5420 16375.6641 | lr 4.6e-04 | norm 7322.9229 | dt 9.861 +type train | step 1598 | loss 123.6166 235.3024 378.6879 570.5151 851.2921 1195.2684 1654.3428 2372.6660 3346.7417 5239.7451 8682.1582 16412.8828 | lr 4.6e-04 | norm 6488.3164 | dt 9.888 +type train | step 1599 | loss 117.4672 228.8824 377.2396 581.7617 868.9745 1217.9099 1691.7926 2431.7092 3443.3833 5428.8164 9120.8623 17458.7773 | lr 4.6e-04 | norm 9130.8037 | dt 9.924 +type train | step 1600 | loss 129.2911 247.6243 396.9427 599.4408 892.2639 1253.5459 1734.0696 2468.5210 3458.1106 5349.3755 8823.8057 16654.3047 | lr 4.6e-04 | norm 6193.2461 | dt 9.877 +type train | step 1601 | loss 125.0837 241.6530 395.8655 603.0174 902.8265 1298.3511 1798.2914 2596.8462 3620.5073 5708.6543 9637.0830 18560.4355 | lr 4.6e-04 | norm 14172.0850 | dt 9.840 +type train | step 1602 | loss 123.8853 234.8995 375.5302 570.8682 845.0983 1187.4844 1635.7039 2326.6096 3294.0154 5135.2788 8518.8145 16082.3086 | lr 4.6e-04 | norm 6014.3081 | dt 9.870 +type train | step 1603 | loss 125.9279 240.3355 386.5220 586.0307 865.3447 1229.4895 1702.0483 2440.5840 3389.9678 5211.7041 8534.5635 15912.9502 | lr 4.6e-04 | norm 8424.7900 | dt 9.889 +type train | step 1604 | loss 127.7447 246.6143 393.4078 595.8367 885.0078 1253.2399 1729.9910 2462.7805 3484.8870 5388.0889 8801.6611 16380.7354 | lr 4.6e-04 | norm 6533.8521 | dt 9.872 +type train | step 1605 | loss 137.9670 264.5881 417.0150 625.5667 919.8955 1270.6313 1739.1919 2442.2256 3440.4604 5330.4033 8779.7480 16557.4258 | lr 4.6e-04 | norm 7647.9932 | dt 9.876 +type train | step 1606 | loss 123.2409 234.5658 369.9225 565.4491 839.3480 1174.7504 1628.9796 2320.1316 3296.6851 5139.2466 8476.0879 15922.8955 | lr 4.6e-04 | norm 6303.0732 | dt 9.861 +type train | step 1607 | loss 123.2112 237.4951 373.5087 568.0849 841.0838 1190.6266 1643.8752 2343.3340 3309.4702 5150.0078 8475.0557 15907.5771 | lr 4.6e-04 | norm 5664.9233 | dt 9.893 +type train | step 1608 | loss 149.1382 281.0459 438.1925 650.4866 941.5162 1326.4385 1806.4822 2557.7964 3460.8596 5260.9395 8484.6387 15819.5254 | lr 4.6e-04 | norm 8028.0557 | dt 9.850 +type train | step 1609 | loss 135.1492 258.0243 404.6189 612.6041 901.4872 1266.8071 1738.6532 2449.8022 3421.5938 5267.3843 8584.6543 16015.9170 | lr 4.6e-04 | norm 6748.0225 | dt 9.878 +type train | step 1610 | loss 133.0708 251.3830 393.1219 595.0872 869.1385 1218.5229 1671.4396 2378.2720 3304.0559 5137.6763 8547.8945 16436.8320 | lr 4.6e-04 | norm 7645.2090 | dt 9.868 +type train | step 1611 | loss 122.0895 231.1787 370.5231 557.6019 830.5173 1166.2246 1608.4713 2294.9065 3234.2937 5018.8340 8231.3496 15495.8203 | lr 4.6e-04 | norm 6029.8721 | dt 9.897 +type train | step 1612 | loss 121.5396 228.8944 359.3837 550.1353 818.8831 1162.2684 1609.5825 2299.8762 3207.4739 4978.7222 8312.6865 15860.4883 | lr 4.6e-04 | norm 8650.7305 | dt 9.869 +type train | step 1613 | loss 126.9133 241.8399 382.7849 587.2283 876.1245 1243.6760 1731.5233 2483.7205 3481.8979 5379.4590 8733.3926 16235.3350 | lr 4.6e-04 | norm 6171.4399 | dt 9.886 +type train | step 1614 | loss 126.3887 243.4038 384.4088 588.8222 867.5806 1228.0883 1707.1449 2446.4165 3439.3145 5331.5918 8762.0322 16496.4590 | lr 4.6e-04 | norm 6074.9829 | dt 9.886 +type train | step 1615 | loss 135.7377 259.4901 406.8725 609.8363 892.4294 1261.9242 1743.2112 2491.0454 3453.2766 5341.3662 8770.3965 16604.7344 | lr 4.6e-04 | norm 6713.2109 | dt 9.873 +type train | step 1616 | loss 139.5210 265.7753 416.7261 613.0867 890.7962 1238.0555 1686.4586 2381.7078 3291.1091 5063.6841 8254.7900 15538.7607 | lr 4.6e-04 | norm 7428.9121 | dt 9.882 +type train | step 1617 | loss 125.2964 238.6488 377.4619 569.4261 847.9345 1182.8160 1629.3944 2313.8938 3272.7012 5079.1045 8317.7793 15531.6045 | lr 4.6e-04 | norm 6831.6982 | dt 9.880 +type train | step 1618 | loss 131.4112 250.8490 396.8878 601.0041 885.2583 1244.8325 1711.3179 2438.0593 3405.5994 5258.2046 8605.7969 16132.2793 | lr 4.6e-04 | norm 6392.1748 | dt 9.855 +type train | step 1619 | loss 126.8701 242.6959 379.4353 576.1384 849.9338 1196.9202 1659.8362 2373.5830 3334.1108 5153.6138 8442.6807 15864.6592 | lr 4.6e-04 | norm 5998.5811 | dt 9.870 +type train | step 1620 | loss 120.2581 228.2789 369.0706 567.4479 842.3287 1190.8345 1645.4844 2341.6890 3300.0393 5120.7046 8403.4170 15893.7324 | lr 4.6e-04 | norm 7914.2842 | dt 9.844 +type train | step 1621 | loss 125.6204 239.8947 379.4561 579.2200 851.3333 1194.1277 1635.8293 2322.5933 3257.4946 5048.6562 8301.5244 15629.1240 | lr 4.6e-04 | norm 6096.9429 | dt 9.882 +type train | step 1622 | loss 118.3849 225.3896 365.2069 562.5291 838.9553 1186.9698 1644.3589 2353.4658 3300.3013 5149.9395 8493.0078 15934.1719 | lr 4.6e-04 | norm 6238.6924 | dt 9.870 +type train | step 1623 | loss 122.3939 233.1623 369.4762 565.2866 840.0246 1178.3927 1633.2167 2324.5269 3288.5737 5131.9365 8425.7900 15740.9609 | lr 4.6e-04 | norm 6161.2822 | dt 9.895 +type train | step 1624 | loss 124.1653 238.3210 380.7632 581.8610 864.2280 1220.1902 1684.6466 2410.0808 3392.8062 5251.2520 8649.5664 16145.6895 | lr 4.6e-04 | norm 6323.2739 | dt 9.877 +type train | step 1625 | loss 129.9622 247.8176 390.1760 597.0981 877.0278 1232.9692 1694.4915 2411.8916 3375.9438 5215.9678 8584.1758 16089.7480 | lr 4.6e-04 | norm 5175.2212 | dt 9.871 +type train | step 1626 | loss 131.0119 250.0705 392.1982 591.7937 870.5715 1224.1840 1690.7366 2401.0593 3360.4331 5173.7012 8455.8896 15704.7832 | lr 4.6e-04 | norm 5198.7900 | dt 9.883 +type train | step 1627 | loss 116.5416 222.8607 363.4284 561.0524 840.7057 1208.9500 1703.2474 2474.5730 3480.5444 5407.9541 8841.2314 16566.1484 | lr 4.6e-04 | norm 7120.3950 | dt 9.864 +type train | step 1628 | loss 121.2931 230.9410 368.5688 564.3123 837.3727 1180.0081 1635.2092 2342.6360 3315.5085 5179.8320 8562.4316 16137.9414 | lr 4.6e-04 | norm 5775.4243 | dt 9.873 +type train | step 1629 | loss 126.3340 239.6962 378.4099 578.0204 852.1627 1223.0165 1701.7458 2450.4106 3433.3760 5330.1128 8792.7812 16467.6875 | lr 4.6e-04 | norm 6151.6626 | dt 9.859 +type train | step 1630 | loss 126.5806 244.1384 384.4897 586.9149 871.3766 1233.4089 1708.2161 2451.9556 3445.7351 5305.2241 8666.9668 16088.9551 | lr 4.6e-04 | norm 5842.0508 | dt 9.870 +type train | step 1631 | loss 125.7890 239.5574 384.3452 583.9119 862.8432 1216.4232 1667.6406 2365.3696 3309.6934 5141.3965 8490.7920 15920.1074 | lr 4.6e-04 | norm 6020.2817 | dt 9.862 +type train | step 1632 | loss 121.5913 231.8203 371.2045 564.3517 834.9803 1174.2930 1627.1530 2327.5698 3294.4792 5129.9331 8500.4961 16005.2803 | lr 4.6e-04 | norm 6015.8564 | dt 9.880 +type train | step 1633 | loss 130.5590 246.8611 386.7392 581.5636 860.9734 1212.9755 1673.5952 2376.1213 3317.7917 5124.7852 8374.6084 15703.8379 | lr 4.6e-04 | norm 5732.2832 | dt 9.867 +type train | step 1634 | loss 123.1552 234.2999 370.2889 566.6697 837.1897 1175.9131 1631.6520 2329.0471 3298.5728 5136.8521 8509.3809 16058.7451 | lr 4.6e-04 | norm 6350.4341 | dt 9.888 +type train | step 1635 | loss 134.0689 255.4253 396.2009 598.6503 873.4657 1228.1057 1681.7190 2405.6121 3349.7407 5178.9019 8533.1641 16049.8525 | lr 4.6e-04 | norm 7868.7520 | dt 9.854 +type train | step 1636 | loss 125.7606 240.1016 379.7248 579.8164 857.1296 1202.6455 1655.6423 2346.1782 3303.3108 5121.2593 8445.2480 15812.8457 | lr 4.6e-04 | norm 5767.2529 | dt 9.872 +type train | step 1637 | loss 111.6218 212.7299 345.9237 535.7331 804.4610 1134.7476 1581.0608 2264.5576 3247.1780 5059.2104 8311.2080 15487.4199 | lr 4.6e-04 | norm 5623.3193 | dt 9.878 +type train | step 1638 | loss 125.0744 238.1090 377.3322 578.0474 852.9478 1199.2488 1653.6343 2363.8425 3338.5488 5201.8638 8555.4922 15987.8779 | lr 4.6e-04 | norm 5609.4194 | dt 9.893 +type train | step 1639 | loss 122.7383 232.1945 369.9269 563.5651 836.2660 1168.3955 1615.4363 2297.9536 3251.1619 5077.3486 8381.9512 15730.7217 | lr 4.6e-04 | norm 6134.0029 | dt 9.876 +type train | step 1640 | loss 126.5862 240.2234 374.5724 566.4581 841.8904 1171.9178 1619.3160 2292.5095 3235.0349 4997.1699 8158.6084 15239.6045 | lr 4.6e-04 | norm 5983.6782 | dt 9.865 +type train | step 1641 | loss 123.1172 233.1602 372.9650 570.2864 847.1743 1199.8655 1661.9889 2384.2847 3372.4712 5235.2710 8583.4902 16063.2373 | lr 4.6e-04 | norm 5229.3623 | dt 9.872 +type train | step 1642 | loss 121.7530 231.9950 370.8826 563.5330 840.1953 1184.4045 1637.5531 2341.9324 3313.5254 5135.3135 8499.8594 16018.1777 | lr 4.6e-04 | norm 6291.0156 | dt 9.867 +type train | step 1643 | loss 123.3873 234.5919 378.3060 583.3149 868.4860 1230.5200 1707.2927 2453.7310 3460.4673 5377.4053 8888.5020 16691.3301 | lr 4.6e-04 | norm 5964.0176 | dt 9.883 +type train | step 1644 | loss 123.9326 238.1736 376.7193 573.8397 848.9554 1200.4702 1657.0673 2372.3420 3349.4177 5212.5771 8577.7227 16172.1035 | lr 4.6e-04 | norm 6275.3125 | dt 9.861 +type train | step 1645 | loss 124.7340 239.9150 381.6334 582.0593 860.9932 1205.0563 1658.2345 2361.8103 3324.4932 5154.7915 8482.9365 15808.7002 | lr 4.6e-04 | norm 6340.8945 | dt 9.870 +type train | step 1646 | loss 127.8302 242.1900 379.8886 586.6340 867.0697 1225.4675 1702.9575 2446.3386 3464.5012 5408.8320 8873.1348 16771.3301 | lr 4.6e-04 | norm 8719.4561 | dt 9.867 +type train | step 1647 | loss 122.3378 235.2302 376.3444 579.3557 864.9003 1225.5193 1703.6869 2445.9893 3450.9160 5340.6431 8812.8955 16568.7812 | lr 4.6e-04 | norm 8168.0474 | dt 9.868 +type train | step 1648 | loss 126.7198 243.8168 383.5824 587.2761 871.9236 1234.3312 1704.5687 2425.7085 3421.3608 5274.0464 8671.2539 16250.5293 | lr 4.6e-04 | norm 5631.7354 | dt 9.881 +type train | step 1649 | loss 125.7791 241.7261 383.0275 584.7153 868.3981 1227.0531 1701.2877 2432.5505 3422.1418 5332.6289 8787.5879 16515.4805 | lr 4.6e-04 | norm 6935.9614 | dt 9.865 +type train | step 1650 | loss 129.6862 244.8940 383.7643 586.7642 866.0022 1227.7603 1700.5972 2421.5679 3363.0249 5191.8281 8587.2490 16297.3193 | lr 4.6e-04 | norm 8717.2549 | dt 9.864 +type train | step 1651 | loss 121.4076 230.8452 358.4829 557.9246 826.7260 1176.0350 1633.2063 2342.9944 3288.0393 5100.9238 8394.0498 15748.4785 | lr 4.6e-04 | norm 6357.9263 | dt 9.858 +type train | step 1652 | loss 128.3607 244.9467 384.0306 592.7852 870.3037 1220.5758 1685.3352 2393.4399 3361.9895 5233.6621 8653.4648 16175.8926 | lr 4.6e-04 | norm 6628.6084 | dt 9.870 +type train | step 1653 | loss 106.4514 214.8008 352.8105 561.3638 851.7833 1222.2671 1723.7842 2515.3743 3641.5452 5689.7886 9330.5039 17298.7109 | lr 4.6e-04 | norm 13679.2109 | dt 9.839 +type train | step 1654 | loss 103.5966 211.1747 354.2784 565.4290 865.0770 1257.9951 1797.7332 2631.1138 3815.5967 5994.1245 9788.5859 17851.0820 | lr 4.6e-04 | norm 16239.1621 | dt 9.828 +type train | step 1655 | loss 122.8003 235.9106 373.9944 571.9708 848.3754 1202.6200 1674.6539 2401.1328 3391.1133 5251.1841 8611.8145 16082.6689 | lr 4.6e-04 | norm 6201.1689 | dt 9.875 +type train | step 1656 | loss 121.2119 234.6326 374.2105 579.6776 863.7631 1220.5149 1690.2224 2421.1504 3415.1094 5322.0566 8749.5508 16360.6738 | lr 4.6e-04 | norm 7413.9702 | dt 9.867 +type train | step 1657 | loss 124.3211 238.9509 375.6761 580.9324 858.4609 1209.2513 1675.7646 2387.9895 3362.5945 5224.0669 8668.6523 16363.3301 | lr 4.6e-04 | norm 7562.8076 | dt 9.875 +type train | step 1658 | loss 126.9227 248.0461 391.5041 597.6877 879.3690 1244.5597 1705.6245 2423.6221 3393.9089 5240.1885 8575.2793 16075.3438 | lr 4.6e-04 | norm 7388.1978 | dt 9.873 +type train | step 1659 | loss 116.9998 224.0337 361.2655 563.0458 835.1435 1181.8041 1641.9927 2356.9409 3335.3242 5226.2344 8652.4082 16319.9600 | lr 4.6e-04 | norm 7733.5405 | dt 9.861 +type train | step 1660 | loss 127.7481 246.3436 386.0911 591.0065 873.3362 1224.5999 1684.8901 2392.7053 3386.8015 5233.2104 8579.8994 15968.9453 | lr 4.6e-04 | norm 6619.8516 | dt 9.884 +type train | step 1661 | loss 121.1947 240.9024 390.9363 617.2665 911.3112 1294.3066 1809.6970 2596.4460 3693.1250 5750.2246 9534.3389 18115.2969 | lr 4.6e-04 | norm 7220.5698 | dt 9.876 +type train | step 1662 | loss 119.3347 230.2018 359.9691 555.2429 820.0547 1154.6447 1605.0490 2298.5757 3253.5479 5086.9785 8447.1689 15977.2227 | lr 4.6e-04 | norm 6820.6382 | dt 9.873 +type train | step 1663 | loss 118.6727 226.5705 360.2848 557.0303 828.5020 1176.3988 1629.7208 2321.6208 3269.6858 5081.1611 8371.0889 15738.6543 | lr 4.6e-04 | norm 6063.3784 | dt 9.876 +type train | step 1664 | loss 128.8076 249.7095 392.4184 610.0045 899.5047 1266.6147 1743.3203 2480.2273 3486.0208 5402.2217 8998.3975 17051.6133 | lr 4.6e-04 | norm 7493.1650 | dt 9.879 +type train | step 1665 | loss 127.0473 240.7081 380.5457 585.2604 865.5260 1216.9386 1677.9948 2398.1106 3380.5349 5229.4082 8620.5605 16212.3379 | lr 4.6e-04 | norm 8750.1143 | dt 9.863 +type train | step 1666 | loss 126.8038 244.8162 381.2493 583.6727 854.6803 1197.1868 1651.7113 2348.2793 3290.1550 5079.1484 8327.0928 15548.7773 | lr 4.6e-04 | norm 6385.7656 | dt 9.871 +type train | step 1667 | loss 128.4137 245.2403 382.1588 586.3010 863.9033 1221.5806 1687.5120 2431.2427 3393.2190 5214.4248 8595.2324 16130.3945 | lr 4.6e-04 | norm 7354.7134 | dt 9.871 +type train | step 1668 | loss 126.8014 245.4266 380.5116 581.5160 850.1425 1192.9773 1641.9132 2341.3984 3278.5188 5064.0352 8349.6992 15824.5996 | lr 4.6e-04 | norm 7258.2007 | dt 9.875 +type train | step 1669 | loss 123.9473 236.7732 372.0493 571.2748 841.3633 1197.1918 1656.4111 2353.3105 3319.2397 5156.8228 8433.9434 15793.3887 | lr 4.6e-04 | norm 6496.7412 | dt 9.862 +type train | step 1670 | loss 121.6479 232.4586 364.7611 564.4940 836.5166 1191.1753 1653.8876 2383.4443 3374.5901 5274.3496 8727.8271 16340.4023 | lr 4.6e-04 | norm 6472.6274 | dt 9.867 +type train | step 1671 | loss 118.6979 226.9535 359.0871 557.3691 822.8004 1163.1586 1610.7717 2306.1960 3270.5217 5086.1787 8363.2461 15642.3750 | lr 4.6e-04 | norm 6159.6660 | dt 9.875 +type train | step 1672 | loss 119.5102 230.1963 365.2563 579.4976 858.9702 1233.1351 1708.1724 2475.3357 3459.6191 5427.4180 8946.9189 16992.6895 | lr 4.6e-04 | norm 8729.7803 | dt 9.865 +type train | step 1673 | loss 121.1893 230.5544 362.8983 562.3256 828.6272 1182.9612 1636.4177 2335.7761 3278.2026 5105.6865 8417.3057 15779.5957 | lr 4.6e-04 | norm 5569.6558 | dt 9.872 +type train | step 1674 | loss 137.1030 262.1096 413.3242 631.7677 923.9896 1299.9170 1799.3693 2566.4478 3600.4839 5587.7646 9244.0000 17605.4941 | lr 4.6e-04 | norm 8831.0557 | dt 9.876 +type train | step 1675 | loss 122.7116 235.0048 368.0822 569.4585 840.2823 1194.5948 1655.4512 2375.8416 3356.3445 5216.6362 8551.7363 16013.2148 | lr 4.6e-04 | norm 5420.7227 | dt 9.868 +type train | step 1676 | loss 125.7032 239.1862 374.3871 577.6000 853.6260 1213.0496 1679.2607 2407.8467 3395.7720 5268.5459 8684.4346 16269.1895 | lr 4.5e-04 | norm 5829.9131 | dt 9.873 +type train | step 1677 | loss 119.3560 227.9388 354.6442 549.6379 814.5276 1151.5780 1596.6644 2280.4263 3217.3418 4993.3491 8209.8291 15410.7197 | lr 4.5e-04 | norm 5712.0063 | dt 9.883 +type train | step 1678 | loss 127.2796 242.1507 378.3633 581.6274 856.4163 1213.7793 1675.8038 2391.8447 3356.9512 5172.7979 8479.7549 15784.4414 | lr 4.5e-04 | norm 5257.3579 | dt 9.874 +type train | step 1679 | loss 117.0363 222.9986 351.8742 547.6554 816.6623 1159.6223 1614.1395 2309.2590 3262.4302 5072.6382 8349.7109 15631.1719 | lr 4.5e-04 | norm 5322.8613 | dt 9.894 +type train | step 1680 | loss 127.3926 243.3495 381.5275 586.9085 863.8442 1203.7902 1658.3971 2361.7163 3331.3293 5146.6157 8462.4336 15733.1748 | lr 4.5e-04 | norm 7375.8340 | dt 9.881 +type train | step 1681 | loss 116.7609 223.3562 354.5059 551.0854 821.7585 1168.2450 1620.0989 2332.4766 3312.7141 5172.6758 8464.0850 15785.1875 | lr 4.5e-04 | norm 6145.4766 | dt 9.876 +type train | step 1682 | loss 122.8173 235.2006 365.2090 566.8168 841.5057 1206.7920 1682.7336 2421.5513 3404.9934 5284.6465 8718.5781 16408.2285 | lr 4.5e-04 | norm 6172.4995 | dt 9.863 +type train | step 1683 | loss 124.3311 237.3834 369.0811 566.9628 842.5790 1192.8496 1658.0183 2385.2026 3373.3904 5281.1348 8702.2314 16217.3340 | lr 4.5e-04 | norm 5572.5586 | dt 9.879 +type train | step 1684 | loss 109.4588 208.5269 334.5775 524.5224 791.9760 1140.2346 1604.0278 2315.1133 3300.1453 5131.8711 8431.6406 15781.4707 | lr 4.5e-04 | norm 5892.3003 | dt 9.896 +type train | step 1685 | loss 127.4879 243.5028 368.4166 568.1527 832.9356 1168.8760 1609.2810 2299.8984 3229.7300 5006.2700 8200.4766 15361.3447 | lr 4.5e-04 | norm 8826.7920 | dt 9.868 +type train | step 1686 | loss 131.8565 253.3322 393.9438 605.1799 883.9079 1244.6669 1701.7114 2408.2949 3328.1992 5084.1499 8213.8623 15289.1035 | lr 4.5e-04 | norm 6081.1294 | dt 9.870 +type train | step 1687 | loss 138.9829 266.3192 405.4582 622.3950 901.6780 1268.3954 1733.4260 2450.4871 3390.2051 5230.9502 8585.8066 16030.4033 | lr 4.5e-04 | norm 5961.1416 | dt 9.868 +type train | step 1688 | loss 117.8020 223.0602 350.2263 548.2170 817.9774 1175.4489 1635.0044 2370.8025 3350.3940 5211.1616 8579.7607 16033.0244 | lr 4.5e-04 | norm 6084.1821 | dt 9.866 +type train | step 1689 | loss 140.7812 269.1190 409.1159 623.1462 906.7334 1281.1360 1766.8142 2514.8848 3484.2603 5364.2832 8783.4238 16422.4531 | lr 4.5e-04 | norm 5704.8594 | dt 9.878 +type train | step 1690 | loss 118.4203 225.5134 356.5817 556.4626 828.9412 1194.5839 1664.4436 2413.9265 3391.7202 5272.9692 8648.0215 16199.5527 | lr 4.5e-04 | norm 6307.7676 | dt 9.868 +type train | step 1691 | loss 124.4879 239.6576 370.5985 580.3951 855.2637 1215.1630 1680.2405 2416.6677 3404.5205 5304.8799 8733.6748 16441.7715 | lr 4.5e-04 | norm 6584.9824 | dt 9.845 +type train | step 1692 | loss 121.1342 230.2982 359.9189 557.5873 829.3121 1185.1882 1664.9651 2404.9558 3396.8918 5280.4917 8649.0205 16139.1240 | lr 4.5e-04 | norm 6245.6914 | dt 9.882 +type train | step 1693 | loss 168.6895 321.4387 464.0881 686.6326 971.8384 1367.5864 1869.0000 2622.6016 3532.2092 5345.0986 8533.2090 15848.2930 | lr 4.5e-04 | norm 11324.2793 | dt 9.842 +type train | step 1694 | loss 118.7526 229.1445 361.8231 565.0796 833.7582 1178.1107 1638.6272 2348.6482 3333.3127 5203.8086 8627.9307 16331.4746 | lr 4.5e-04 | norm 6486.9185 | dt 9.864 +type train | step 1695 | loss 121.3225 231.4057 362.1158 559.6865 826.5991 1168.1761 1620.5299 2310.9841 3257.3035 5056.4893 8314.3232 15535.3555 | lr 4.5e-04 | norm 6232.4912 | dt 9.891 +type train | step 1696 | loss 118.7530 225.3679 354.7493 550.8239 813.2687 1146.5533 1582.9807 2256.4014 3208.6187 4999.7236 8232.9736 15432.2441 | lr 4.5e-04 | norm 5377.5928 | dt 9.874 +type train | step 1697 | loss 111.3268 212.7250 335.3176 526.5272 788.6490 1125.7313 1569.6661 2250.6511 3204.1108 5011.7612 8267.9209 15532.5625 | lr 4.5e-04 | norm 5372.5918 | dt 9.886 +type train | step 1698 | loss 123.5082 237.5345 368.3298 573.3287 848.2499 1196.3022 1652.4232 2375.2510 3370.9656 5277.1465 8737.7754 16477.5000 | lr 4.5e-04 | norm 6548.1909 | dt 9.868 +type train | step 1699 | loss 127.6161 244.8932 377.4301 579.5035 853.0892 1206.0012 1660.0198 2369.2195 3331.9048 5165.5972 8503.1025 15903.9688 | lr 4.5e-04 | norm 6159.5229 | dt 9.881 +type train | step 1700 | loss 127.2769 246.4794 384.7193 594.5881 869.3253 1220.3800 1673.2994 2363.7034 3293.0439 5083.4438 8347.7754 15721.0918 | lr 4.5e-04 | norm 5700.7549 | dt 9.886 +type train | step 1701 | loss 123.2695 239.6660 376.5356 589.3238 867.0696 1221.2588 1681.5361 2387.6492 3368.0432 5168.8218 8521.2949 16039.8027 | lr 4.5e-04 | norm 6768.0879 | dt 9.874 +type train | step 1702 | loss 136.2826 257.0762 399.2838 617.5513 896.3026 1260.4979 1733.0237 2456.3696 3428.6763 5252.7178 8629.4082 16281.2686 | lr 4.5e-04 | norm 7092.6519 | dt 9.869 +type train | step 1703 | loss 117.0227 223.2260 350.1025 548.0379 816.8762 1159.9464 1618.5515 2322.7610 3284.8955 5103.0083 8350.4814 15555.3828 | lr 4.5e-04 | norm 5800.1079 | dt 9.871 +type train | step 1704 | loss 132.8717 251.8002 390.2186 605.1512 883.3359 1250.7660 1713.8335 2430.9658 3373.4795 5176.0830 8534.5156 16016.9658 | lr 4.5e-04 | norm 6524.3604 | dt 9.858 +type train | step 1705 | loss 115.0579 220.6157 347.5035 539.3787 803.0934 1140.2755 1577.9725 2272.9006 3231.0815 5039.4209 8338.5879 15668.2939 | lr 4.5e-04 | norm 6256.3467 | dt 9.869 +type train | step 1706 | loss 134.3516 252.8987 389.5471 605.1779 874.8932 1240.1442 1694.5046 2395.0273 3315.1514 5111.8716 8361.3691 15655.5361 | lr 4.5e-04 | norm 5957.1406 | dt 9.854 +type train | step 1707 | loss 112.2251 214.8520 344.3425 542.2189 811.6151 1153.8040 1603.8049 2304.1904 3275.1223 5121.9839 8460.4395 15970.1260 | lr 4.5e-04 | norm 5687.5278 | dt 9.860 +type train | step 1708 | loss 120.1394 228.5383 358.6857 560.9991 827.5355 1167.7262 1616.8254 2305.2422 3253.7830 5077.9385 8333.3633 15645.1143 | lr 4.5e-04 | norm 5747.8081 | dt 9.893 +type train | step 1709 | loss 115.6431 221.7880 349.4269 551.2940 820.8443 1179.3420 1644.9185 2380.9128 3355.2275 5242.0298 8632.7266 16211.5215 | lr 4.5e-04 | norm 7607.3257 | dt 9.882 +type train | step 1710 | loss 129.6954 251.8952 389.6088 598.1011 883.0726 1244.3040 1734.4910 2489.0947 3513.7844 5506.2715 9078.8623 17166.6289 | lr 4.5e-04 | norm 9578.8457 | dt 9.860 +type train | step 1711 | loss 145.9260 280.3669 441.9099 677.6136 982.1892 1354.1937 1855.2937 2606.6123 3687.5249 5694.3662 9451.7393 18094.6699 | lr 4.5e-04 | norm 11460.2012 | dt 9.860 +type train | step 1712 | loss 129.0468 249.0746 378.8125 580.0518 851.0294 1200.4305 1643.1460 2333.5234 3244.7842 5003.8428 8189.3022 15392.9902 | lr 4.5e-04 | norm 8895.5967 | dt 9.880 +type train | step 1713 | loss 117.3164 227.0681 357.0266 558.3271 833.1573 1177.1433 1633.8690 2343.8203 3354.1592 5224.3516 8569.6270 16085.4121 | lr 4.5e-04 | norm 7362.0552 | dt 9.867 +type train | step 1714 | loss 124.8977 239.6858 369.4167 568.7842 833.4465 1183.1937 1637.9351 2332.6128 3277.4290 5055.9878 8236.3711 15358.2266 | lr 4.5e-04 | norm 6695.5962 | dt 9.896 +type train | step 1715 | loss 115.8848 222.9587 354.8065 554.2120 823.4171 1178.4800 1638.2941 2369.9661 3333.4778 5166.7305 8525.1846 15988.6719 | lr 4.5e-04 | norm 7264.8594 | dt 9.888 +type train | step 1716 | loss 120.4506 229.2376 358.1457 556.8112 823.3492 1170.7639 1623.9038 2326.5315 3272.6580 5065.3911 8299.1924 15515.7559 | lr 4.5e-04 | norm 5934.7651 | dt 9.870 +type train | step 1717 | loss 117.4588 225.2600 356.5306 563.3593 839.9759 1205.2234 1682.5642 2423.8340 3458.1113 5429.0933 8941.5234 16955.3105 | lr 4.5e-04 | norm 6828.8774 | dt 9.872 +type train | step 1718 | loss 115.8954 221.1812 351.6968 546.6295 810.0759 1146.3951 1592.8381 2282.0593 3228.1733 5045.3491 8339.4629 15583.0820 | lr 4.5e-04 | norm 5807.3916 | dt 9.858 +type train | step 1719 | loss 127.8596 245.0209 380.0981 589.3778 859.7141 1218.8357 1675.8435 2393.2021 3323.8804 5137.3374 8425.1279 15805.4863 | lr 4.5e-04 | norm 6287.7739 | dt 9.873 +type train | step 1720 | loss 112.3497 214.3748 338.1437 529.7040 792.5629 1130.8513 1574.8289 2258.5110 3202.1931 5010.8115 8198.3564 15347.4316 | lr 4.5e-04 | norm 5702.9419 | dt 9.864 +type train | step 1721 | loss 114.0377 216.7271 342.1276 536.4846 796.5355 1141.9237 1592.0105 2293.8325 3256.9155 5080.7163 8321.0137 15544.2930 | lr 4.5e-04 | norm 6730.7329 | dt 9.871 +type train | step 1722 | loss 128.6223 243.5137 375.7464 582.4055 852.1705 1211.0768 1668.6079 2365.6172 3293.4534 5048.9917 8295.9746 15565.6348 | lr 4.5e-04 | norm 6519.2207 | dt 9.880 +type train | step 1723 | loss 124.6524 238.3797 369.5226 572.8605 843.0716 1196.4348 1655.7155 2361.6018 3337.1753 5149.3970 8452.1436 15832.8672 | lr 4.5e-04 | norm 5691.9570 | dt 9.885 +type train | step 1724 | loss 122.1258 233.7325 363.6136 563.5162 831.6427 1182.3927 1635.1934 2343.0374 3306.5178 5152.1558 8508.6777 15925.1729 | lr 4.5e-04 | norm 5152.9067 | dt 9.860 +type train | step 1725 | loss 123.9401 237.4303 366.1206 567.7578 838.1601 1189.9401 1652.4833 2366.8496 3317.1978 5132.6904 8421.3145 15767.5156 | lr 4.5e-04 | norm 6261.2080 | dt 9.877 +type train | step 1726 | loss 120.6610 231.0174 363.3340 568.1625 837.9483 1188.7505 1642.1328 2341.9377 3320.4883 5150.9160 8459.7549 15836.3330 | lr 4.5e-04 | norm 5361.8896 | dt 9.884 +type train | step 1727 | loss 116.7354 224.6480 350.1228 547.6613 813.8477 1168.7026 1628.1516 2341.1230 3303.2432 5093.5449 8358.9082 15615.5508 | lr 4.5e-04 | norm 6127.4326 | dt 9.846 +type train | step 1728 | loss 118.4125 227.4141 355.4157 554.5985 823.9214 1170.6323 1627.3574 2322.6372 3270.4944 5070.8120 8350.3555 15601.9893 | lr 4.5e-04 | norm 6020.0635 | dt 9.855 +type train | step 1729 | loss 115.1588 219.4738 347.1884 545.6696 818.1682 1176.3533 1636.2572 2359.4866 3329.5889 5154.7158 8417.2334 15712.0703 | lr 4.5e-04 | norm 5086.9448 | dt 9.869 +type train | step 1730 | loss 119.2429 228.3755 354.0573 550.3844 813.2953 1164.9568 1626.2180 2337.8411 3294.9092 5121.8628 8386.1113 15616.5488 | lr 4.5e-04 | norm 4825.0996 | dt 9.877 +type train | step 1731 | loss 124.1986 239.5764 372.7010 582.4193 854.9385 1210.4869 1672.7532 2386.8789 3350.1567 5211.7710 8565.0850 16003.8535 | lr 4.5e-04 | norm 6006.6089 | dt 9.885 +type train | step 1732 | loss 129.5831 245.3889 377.2642 588.5556 861.8501 1231.2542 1693.2437 2420.1914 3377.6797 5217.8213 8592.8594 16184.9648 | lr 4.5e-04 | norm 6327.5049 | dt 9.868 +type train | step 1733 | loss 120.1178 230.2854 359.8926 561.8636 830.2258 1179.8625 1630.4911 2330.9785 3292.3857 5096.4336 8364.0752 15612.5371 | lr 4.5e-04 | norm 5833.1606 | dt 9.875 +type train | step 1734 | loss 129.2694 245.7144 379.6508 594.4290 866.1085 1234.0022 1696.7480 2414.4314 3357.9133 5178.6270 8488.4404 15949.2266 | lr 4.5e-04 | norm 5969.2852 | dt 9.882 +type train | step 1735 | loss 127.2226 240.9371 374.8308 586.8688 852.5060 1214.1593 1663.6487 2382.3843 3301.9978 5133.0732 8475.8242 16108.3789 | lr 4.5e-04 | norm 6342.7178 | dt 9.864 +type train | step 1736 | loss 114.8156 220.2324 347.4235 543.5808 808.3726 1153.5790 1602.2196 2290.9636 3238.4106 5030.7197 8272.6748 15421.3750 | lr 4.5e-04 | norm 5275.7275 | dt 9.879 +type train | step 1737 | loss 122.3283 232.9134 361.1203 560.9928 826.3715 1172.9609 1620.3341 2314.2432 3264.2581 5041.9751 8318.5732 15581.0244 | lr 4.5e-04 | norm 5030.6436 | dt 9.886 +type train | step 1738 | loss 129.3283 246.3567 384.5691 593.6223 868.7328 1223.7584 1680.1205 2388.0107 3304.8474 5090.6108 8238.5879 15495.9648 | lr 4.5e-04 | norm 5921.1406 | dt 9.888 +type train | step 1739 | loss 127.5017 244.0925 377.1957 591.0777 862.7048 1230.2161 1690.5054 2406.5439 3352.8711 5188.0625 8550.6875 16092.6768 | lr 4.5e-04 | norm 5688.7539 | dt 9.881 +type train | step 1740 | loss 116.1227 224.4043 352.1037 548.7608 815.1290 1160.8448 1608.9435 2299.3601 3247.2539 5036.8594 8280.8428 15559.5234 | lr 4.5e-04 | norm 6412.4238 | dt 9.869 +type train | step 1741 | loss 120.4889 234.8852 365.5977 565.5043 832.5341 1184.7207 1644.0753 2368.7549 3304.5234 5096.1104 8305.5850 15481.8047 | lr 4.5e-04 | norm 5133.1963 | dt 9.881 +type train | step 1742 | loss 109.0404 208.1672 327.2613 517.0797 773.6319 1118.9048 1571.4712 2277.0369 3226.0237 5051.3042 8345.5098 15754.6777 | lr 4.5e-04 | norm 6144.0386 | dt 9.879 +type train | step 1743 | loss 120.0521 227.3453 349.1253 545.3528 810.9372 1163.7463 1619.6199 2330.7312 3281.7117 5079.6855 8287.8164 15354.8262 | lr 4.5e-04 | norm 5162.8315 | dt 9.873 +type train | step 1744 | loss 127.6743 243.9554 379.0944 587.5389 853.9354 1216.6416 1668.3682 2360.3684 3276.2253 5037.1538 8256.2275 15507.0312 | lr 4.5e-04 | norm 5456.9165 | dt 9.861 +type train | step 1745 | loss 130.4036 244.9347 377.4545 591.7460 864.0508 1249.1082 1722.8025 2479.3169 3399.8247 5289.1816 8741.5664 16637.3262 | lr 4.5e-04 | norm 8711.3398 | dt 9.856 +type train | step 1746 | loss 126.2238 242.5924 371.8402 572.2016 842.1241 1194.7751 1651.4955 2361.1550 3320.9631 5121.1250 8395.2236 15600.0537 | lr 4.5e-04 | norm 5525.2178 | dt 9.887 +type train | step 1747 | loss 123.6168 241.5098 378.9200 594.0400 871.7894 1245.1644 1719.5856 2467.3865 3443.1865 5299.5132 8709.0205 16309.7764 | lr 4.5e-04 | norm 6238.6025 | dt 9.882 +type train | step 1748 | loss 131.0724 253.5891 391.6797 606.0159 888.0545 1279.2499 1787.5048 2600.1746 3621.4099 5549.6997 9035.4824 16643.8828 | lr 4.5e-04 | norm 6646.9297 | dt 9.872 +type train | step 1749 | loss 122.2844 235.2923 364.2798 564.9793 833.2977 1178.8011 1629.7834 2316.5264 3260.0496 5029.3086 8227.3574 15330.5674 | lr 4.5e-04 | norm 5126.2158 | dt 9.877 +type train | step 1750 | loss 119.5308 230.9095 365.3437 576.9286 847.7821 1219.1438 1701.8801 2451.1472 3465.4041 5346.6025 8784.2812 16342.1924 | lr 4.5e-04 | norm 5653.2612 | dt 9.852 +type train | step 1751 | loss 131.8918 252.0339 381.4017 586.5184 859.4399 1224.2440 1688.7966 2415.9805 3364.5107 5164.3477 8393.9004 15519.6543 | lr 4.5e-04 | norm 5397.5698 | dt 9.857 +type train | step 1752 | loss 116.7657 220.4986 352.1237 556.0739 825.3064 1186.1343 1664.1219 2386.4731 3363.2805 5232.4692 8700.8750 16518.3301 | lr 4.5e-04 | norm 8940.9033 | dt 9.857 +type train | step 1753 | loss 154.1063 291.2641 440.7488 662.1106 937.4284 1307.1746 1749.7844 2439.8813 3228.7581 4780.4043 7484.9697 13776.4229 | lr 4.5e-04 | norm 9157.8672 | dt 9.816 +type train | step 1754 | loss 123.1278 235.1943 369.4506 573.5802 846.7103 1204.4968 1664.9108 2370.4119 3325.6145 5108.3696 8331.1660 15613.5908 | lr 4.5e-04 | norm 6102.0176 | dt 9.872 +type train | step 1755 | loss 113.5035 217.5043 344.0722 540.9318 802.0292 1133.5808 1573.0647 2251.7349 3201.5425 5002.6289 8291.3379 15615.7695 | lr 4.5e-04 | norm 5483.2998 | dt 9.868 +type train | step 1756 | loss 116.4384 221.7323 348.0417 550.6714 811.8384 1151.6974 1595.0493 2270.1387 3206.3960 4960.5132 8159.7178 15207.2520 | lr 4.5e-04 | norm 5700.7690 | dt 9.882 +type train | step 1757 | loss 124.6794 238.2114 366.7671 573.0012 842.1221 1188.8267 1646.0323 2348.6733 3310.8708 5141.2393 8467.8438 15955.7363 | lr 4.5e-04 | norm 5580.7666 | dt 9.877 +type train | step 1758 | loss 120.2905 230.8438 361.5554 569.0681 837.9868 1199.0630 1661.1047 2389.9658 3377.1689 5218.4951 8575.7119 15989.8047 | lr 4.5e-04 | norm 5420.2642 | dt 9.867 +type train | step 1759 | loss 107.9723 204.7689 321.1501 508.4146 760.2806 1089.9318 1528.0669 2202.8872 3135.9143 4906.3604 8111.1670 15168.6992 | lr 4.5e-04 | norm 5960.3916 | dt 9.868 +type train | step 1760 | loss 118.5257 226.6429 350.3802 546.0800 805.7379 1150.1926 1602.5457 2297.2927 3250.7314 5070.5000 8376.6934 15636.6387 | lr 4.5e-04 | norm 4823.4961 | dt 9.866 +type train | step 1761 | loss 111.5813 214.2987 337.4386 531.4987 792.3148 1128.8944 1573.2369 2263.8425 3218.7200 5008.0630 8280.4307 15478.2852 | lr 4.5e-04 | norm 5157.0327 | dt 9.863 +type train | step 1762 | loss 113.7232 217.5894 340.2973 542.3005 805.6572 1165.8804 1629.2748 2359.5103 3334.2217 5169.1226 8466.2539 15798.0059 | lr 4.5e-04 | norm 5330.2261 | dt 9.877 +type train | step 1763 | loss 114.5966 218.9617 343.3604 545.4899 809.7486 1155.3680 1609.7649 2321.3657 3280.3701 5149.8398 8562.9102 16226.3730 | lr 4.5e-04 | norm 7144.3120 | dt 9.869 +type train | step 1764 | loss 117.9156 229.5602 359.6788 566.6514 840.3662 1264.7029 1780.3374 2647.2454 3706.1946 5655.3682 9214.4180 17223.3379 | lr 4.5e-04 | norm 8510.4727 | dt 9.836 +type train | step 1765 | loss 123.4792 238.9508 371.8904 573.6373 843.8259 1187.8346 1646.5155 2356.2227 3326.5559 5146.1821 8406.0078 15613.1035 | lr 4.5e-04 | norm 5344.7188 | dt 9.879 +type train | step 1766 | loss 116.7330 224.9943 357.1969 559.7111 835.5739 1189.4343 1657.6412 2381.4961 3375.7781 5237.5781 8546.4736 15869.2227 | lr 4.5e-04 | norm 5785.0259 | dt 9.880 +type train | step 1767 | loss 117.1874 224.3385 350.2423 546.3995 811.1706 1150.3624 1603.3597 2307.8125 3255.6079 5076.3760 8320.4990 15561.3418 | lr 4.5e-04 | norm 5536.6685 | dt 9.878 +type train | step 1768 | loss 115.8915 225.2299 359.7025 571.5233 849.4763 1244.4727 1739.3838 2519.8093 3525.4031 5445.3945 8968.7012 17062.6484 | lr 4.5e-04 | norm 7295.8721 | dt 9.872 +type train | step 1769 | loss 121.0904 233.6697 362.4712 562.6283 829.8560 1175.7750 1633.7665 2326.5796 3279.2446 5071.6777 8347.1611 15589.0176 | lr 4.5e-04 | norm 5333.4624 | dt 9.867 +type train | step 1770 | loss 118.0909 227.9644 359.4043 564.4374 835.7431 1208.9014 1682.6919 2428.4600 3384.3105 5258.3115 8694.7803 16503.9238 | lr 4.5e-04 | norm 7641.4810 | dt 9.869 +type train | step 1771 | loss 116.3855 223.5625 348.8288 547.5804 810.6735 1149.2657 1602.1859 2285.5918 3237.7395 5025.0234 8224.0928 15330.2354 | lr 4.5e-04 | norm 5455.7769 | dt 9.886 +type train | step 1772 | loss 132.3436 251.5207 381.7974 591.8159 858.1208 1224.7417 1689.3926 2405.5005 3328.8447 5105.6289 8329.8926 15639.4004 | lr 4.5e-04 | norm 6543.3589 | dt 9.868 +type train | step 1773 | loss 139.8054 265.9052 402.5477 614.3655 886.8318 1261.6980 1730.4246 2456.5120 3354.4146 5106.9966 8194.9893 15282.2139 | lr 4.5e-04 | norm 7009.9268 | dt 9.863 +type train | step 1774 | loss 123.8003 238.6110 369.6231 573.7715 840.9191 1198.4059 1658.0021 2360.9690 3299.9695 5108.6221 8386.4961 15678.8379 | lr 4.5e-04 | norm 6444.5771 | dt 9.868 +type train | step 1775 | loss 119.7648 225.8010 353.4758 556.3321 821.6266 1174.8867 1638.4292 2356.6440 3316.0508 5127.4346 8427.7568 15746.2744 | lr 4.5e-04 | norm 5523.9346 | dt 9.875 +type train | step 1776 | loss 115.2931 219.2528 338.6103 532.9078 794.8655 1141.4294 1593.9852 2290.0327 3238.2844 5022.0674 8267.6953 15501.5977 | lr 4.5e-04 | norm 6407.8887 | dt 9.886 +type train | step 1777 | loss 116.4398 222.7448 350.5006 553.4964 817.3347 1179.6079 1636.8600 2377.8027 3362.3357 5221.7310 8525.3037 15793.8066 | lr 4.5e-04 | norm 5806.5991 | dt 9.861 +type train | step 1778 | loss 120.2815 228.8378 352.3873 552.6225 814.5676 1168.7012 1626.6315 2329.7063 3269.0789 5063.3511 8345.8262 15705.4121 | lr 4.4e-04 | norm 5854.1440 | dt 9.876 +type train | step 1779 | loss 127.1432 244.3445 376.4430 587.7842 861.0223 1222.5010 1687.5051 2416.0894 3367.5239 5205.3433 8569.4072 16169.4238 | lr 4.4e-04 | norm 6260.2266 | dt 9.861 +type train | step 1780 | loss 119.3799 228.2750 355.9735 561.0948 826.0945 1167.0817 1610.6426 2277.3066 3209.3950 4924.0596 8125.1143 15210.9854 | lr 4.4e-04 | norm 6394.9316 | dt 9.862 +type train | step 1781 | loss 113.3903 216.5543 342.9229 534.3224 792.5753 1133.1622 1572.2715 2250.7903 3179.2544 4949.8716 8111.0029 15204.7256 | lr 4.4e-04 | norm 8246.7285 | dt 9.864 +type train | step 1782 | loss 120.3282 229.4645 357.4962 557.4498 824.2999 1178.5310 1631.3325 2341.5327 3300.1899 5101.9810 8386.0449 15581.4668 | lr 4.4e-04 | norm 5554.4170 | dt 9.874 +type train | step 1783 | loss 115.2266 219.5752 342.7601 535.7775 793.6315 1129.2933 1576.6445 2255.8638 3196.1067 4992.8145 8252.7461 15649.2363 | lr 4.4e-04 | norm 6195.8677 | dt 9.883 +type train | step 1784 | loss 116.0565 225.1992 348.6749 548.0126 811.8163 1167.3723 1624.7328 2336.7275 3302.3350 5121.8828 8446.8652 15840.4971 | lr 4.4e-04 | norm 5472.2964 | dt 9.885 +type train | step 1785 | loss 120.7825 230.3012 357.4356 559.5674 823.0093 1171.6350 1621.1560 2312.7043 3251.9819 5022.3662 8262.1377 15449.3389 | lr 4.4e-04 | norm 5331.0928 | dt 9.888 +type train | step 1786 | loss 114.5141 217.1874 341.0329 538.2376 798.3438 1145.7246 1598.4326 2292.5876 3261.2388 5077.7983 8366.9062 15623.0488 | lr 4.4e-04 | norm 5576.3516 | dt 9.869 +type train | step 1787 | loss 143.0486 268.2477 404.5880 616.6074 878.3314 1225.2919 1670.0854 2346.3167 3234.8940 4963.1582 8164.9692 15479.5391 | lr 4.4e-04 | norm 12034.3105 | dt 9.852 +type train | step 1788 | loss 116.8933 222.9786 351.0770 547.0877 804.7823 1147.7545 1596.8905 2298.0798 3264.7705 5077.9390 8480.0020 15983.3184 | lr 4.4e-04 | norm 7306.5981 | dt 9.866 +type train | step 1789 | loss 120.4024 231.9818 355.5684 555.9580 817.7068 1169.9030 1621.3142 2323.6514 3257.0161 5040.6870 8298.2236 15515.9629 | lr 4.4e-04 | norm 6057.6250 | dt 9.864 +type train | step 1790 | loss 117.4889 222.2489 347.5717 544.3530 804.1492 1138.7688 1578.8417 2258.0957 3218.4885 4989.3574 8214.4287 15467.7441 | lr 4.4e-04 | norm 6827.8926 | dt 9.859 +type train | step 1791 | loss 125.2243 239.1816 368.6183 572.4630 842.9963 1196.2120 1658.5225 2363.4978 3314.1040 5119.3350 8417.9951 15736.4375 | lr 4.4e-04 | norm 6095.6826 | dt 9.866 +type train | step 1792 | loss 120.4764 231.5114 359.2715 559.0191 823.5950 1174.3555 1635.8640 2349.5168 3315.5012 5140.2163 8475.2637 15872.5527 | lr 4.4e-04 | norm 6489.6665 | dt 9.879 +type train | step 1793 | loss 116.5640 222.5746 347.6054 543.3052 806.5911 1144.5959 1591.0945 2276.0486 3219.5830 5026.0220 8277.3408 15542.9658 | lr 4.4e-04 | norm 5574.0186 | dt 9.913 +type train | step 1794 | loss 118.2659 228.2067 352.6466 551.0659 812.7360 1157.6686 1610.7266 2322.1169 3278.6858 5096.9111 8355.5566 15671.0322 | lr 4.4e-04 | norm 5044.5610 | dt 9.892 +type train | step 1795 | loss 131.2184 251.0167 378.6223 585.5079 851.0168 1198.6423 1651.5135 2333.8372 3245.4478 4984.7017 8110.0371 15088.9482 | lr 4.4e-04 | norm 5677.0171 | dt 9.891 +type train | step 1796 | loss 108.3054 207.3413 327.7205 521.5082 776.5258 1117.2717 1560.6605 2254.2363 3183.3796 4957.0762 8180.1147 15305.3477 | lr 4.4e-04 | norm 5330.4883 | dt 9.887 +type train | step 1797 | loss 114.0897 219.2226 342.4165 536.9820 796.5445 1139.8666 1590.4707 2312.5457 3258.2598 5071.6626 8394.8184 15793.8564 | lr 4.4e-04 | norm 6095.3159 | dt 9.891 +type train | step 1798 | loss 114.4337 218.3691 339.8982 540.1237 800.5164 1155.1207 1612.6050 2323.9580 3273.4197 5119.8179 8462.3779 15957.0352 | lr 4.4e-04 | norm 5913.7070 | dt 9.877 +type train | step 1799 | loss 115.4016 219.5515 344.8815 541.0147 804.4280 1160.7134 1615.4342 2341.2874 3274.5083 5073.1792 8364.4277 15772.4980 | lr 4.4e-04 | norm 6670.6982 | dt 9.933 +type train | step 1800 | loss 113.3793 220.2770 347.7566 550.6389 817.3918 1164.5696 1617.2644 2313.9338 3271.8962 5057.3037 8348.1543 15571.8730 | lr 4.4e-04 | norm 5760.8677 | dt 9.910 +type train | step 1801 | loss 123.5019 236.8451 362.3836 565.4855 830.4257 1179.1296 1630.9606 2319.5603 3269.4424 5039.0933 8228.3184 15300.1211 | lr 4.4e-04 | norm 5622.6294 | dt 9.898 +type train | step 1802 | loss 128.8188 248.9372 382.6602 601.0172 877.3185 1245.9536 1710.0873 2422.8413 3358.6536 5137.2437 8355.9805 15780.7119 | lr 4.4e-04 | norm 6981.2476 | dt 9.872 +type train | step 1803 | loss 112.3923 214.2395 338.7171 532.7153 789.5359 1127.1842 1567.2952 2251.0090 3197.8105 4988.2451 8262.1777 15491.2910 | lr 4.4e-04 | norm 5527.8271 | dt 9.905 +type train | step 1804 | loss 109.7959 210.6174 326.0694 517.7280 772.6022 1111.5630 1562.5403 2254.7266 3205.7888 5020.9204 8321.2920 15764.5996 | lr 4.4e-04 | norm 6570.1069 | dt 9.908 +type train | step 1805 | loss 122.7599 230.9591 358.1646 559.9742 825.6120 1175.0012 1636.3846 2325.6733 3261.7419 5025.5747 8253.8652 15497.2744 | lr 4.4e-04 | norm 7180.4810 | dt 9.916 +type train | step 1806 | loss 117.7983 226.6548 348.1368 544.7808 803.0936 1147.5421 1591.7015 2294.0679 3229.1589 5019.5771 8271.9570 15583.3164 | lr 4.4e-04 | norm 5546.6123 | dt 9.888 +type train | step 1807 | loss 115.5694 220.5679 341.5003 538.9305 798.6830 1145.6327 1589.3480 2277.5603 3215.8862 4989.9590 8223.8809 15319.0664 | lr 4.4e-04 | norm 5474.2632 | dt 9.880 +type train | step 1808 | loss 111.3047 213.1439 334.3931 531.9869 792.4019 1140.0596 1592.3096 2289.2837 3249.4536 5057.3750 8310.5889 15544.2490 | lr 4.4e-04 | norm 5645.4839 | dt 9.878 +type train | step 1809 | loss 118.5191 224.6325 347.3686 543.2772 800.7230 1143.8582 1587.7471 2270.5505 3195.2700 4910.4321 8045.5371 14958.8574 | lr 4.4e-04 | norm 5456.1816 | dt 9.873 +type train | step 1810 | loss 112.2799 215.7897 336.4070 532.1022 789.9517 1131.6993 1575.1785 2262.3149 3200.2922 4976.0981 8167.2676 15257.6445 | lr 4.4e-04 | norm 5055.8774 | dt 9.891 +type train | step 1811 | loss 125.5928 239.0639 367.3070 574.2963 836.8408 1185.3104 1627.1077 2303.1040 3186.5969 4917.0498 8068.9097 15127.8525 | lr 4.4e-04 | norm 5288.4414 | dt 9.865 +type train | step 1812 | loss 120.4195 230.5287 356.0903 558.7741 821.2329 1175.0586 1624.1963 2332.2588 3244.4500 4990.5591 8209.1738 15280.9785 | lr 4.4e-04 | norm 5602.5894 | dt 9.869 +type train | step 1813 | loss 114.7282 221.8766 345.4973 547.6986 805.1675 1143.8912 1583.4202 2265.2734 3184.6272 4918.0132 8029.2031 14864.5234 | lr 4.4e-04 | norm 6030.1255 | dt 9.859 +type train | step 1814 | loss 118.1699 227.1163 350.5894 549.9528 811.8174 1148.4088 1592.8256 2272.3755 3202.6013 4997.3994 8216.4092 15607.2139 | lr 4.4e-04 | norm 7346.3779 | dt 9.867 +type train | step 1815 | loss 113.3517 214.5181 336.8754 531.8605 790.3708 1131.8101 1568.8877 2266.3369 3191.4097 4977.4253 8165.3198 15313.9502 | lr 4.4e-04 | norm 8281.3750 | dt 9.870 +type train | step 1816 | loss 130.0353 248.9341 373.6483 579.6646 844.0933 1205.3456 1658.8284 2367.0535 3284.2202 5091.0303 8407.1270 15811.6309 | lr 4.4e-04 | norm 6040.5781 | dt 9.868 +type train | step 1817 | loss 116.1331 222.0573 341.1929 539.1791 795.7669 1133.6160 1571.0306 2244.1138 3170.0481 4926.8223 8116.7798 15168.2852 | lr 4.4e-04 | norm 5528.8276 | dt 9.868 +type train | step 1818 | loss 112.5900 214.4760 340.0735 543.6169 803.8635 1173.5150 1637.8474 2380.6826 3324.0684 5203.2856 8648.9570 16438.7715 | lr 4.4e-04 | norm 9969.4834 | dt 9.845 +type train | step 1819 | loss 123.7235 235.1884 365.3111 576.7535 847.9795 1231.7871 1707.0590 2457.5146 3426.1313 5317.7739 8737.3447 16409.5293 | lr 4.4e-04 | norm 7262.0391 | dt 9.857 +type train | step 1820 | loss 123.1169 235.9137 361.4427 565.7841 830.2587 1186.5059 1637.4895 2344.3086 3276.8982 5084.1963 8365.3857 15712.1162 | lr 4.4e-04 | norm 5487.3652 | dt 9.883 +type train | step 1821 | loss 110.0025 209.3628 330.6106 524.5776 781.4413 1120.4915 1566.0381 2249.7202 3192.1550 4975.7393 8251.0879 15546.9355 | lr 4.4e-04 | norm 5243.3403 | dt 9.882 +type train | step 1822 | loss 131.3580 249.2584 380.5985 591.9051 851.2218 1207.6003 1647.0953 2318.3918 3208.5103 4921.2998 8083.1592 15237.9648 | lr 4.4e-04 | norm 6044.6958 | dt 9.863 +type train | step 1823 | loss 121.4412 235.1450 367.0526 575.5912 842.0989 1201.2886 1657.0287 2360.9453 3270.5613 5075.5527 8342.0322 15871.5703 | lr 4.4e-04 | norm 7774.3271 | dt 9.867 +type train | step 1824 | loss 130.3284 246.4142 373.7239 586.2195 844.5174 1213.2352 1665.6194 2378.3516 3273.2900 5047.7026 8306.9570 15644.3945 | lr 4.4e-04 | norm 6421.5146 | dt 9.861 +type train | step 1825 | loss 123.8732 239.2607 366.5290 568.2755 829.0773 1168.8615 1612.1729 2290.8896 3225.9871 4954.4775 8155.2368 15273.6016 | lr 4.4e-04 | norm 5750.3511 | dt 9.898 +type train | step 1826 | loss 116.1802 222.7268 346.4678 546.2590 806.4958 1156.1245 1606.1217 2304.8438 3266.6582 5065.2119 8353.9082 15513.3779 | lr 4.4e-04 | norm 5656.2671 | dt 9.879 +type train | step 1827 | loss 116.7170 222.8668 343.4827 542.7700 801.4689 1149.5964 1598.3787 2287.7795 3227.1812 5006.2710 8221.0215 15347.7686 | lr 4.4e-04 | norm 5421.6177 | dt 9.881 +type train | step 1828 | loss 118.2677 224.7429 349.7076 549.7093 809.9602 1150.2804 1592.7640 2264.1069 3198.9207 4963.6660 8175.1606 15307.3066 | lr 4.4e-04 | norm 5476.6782 | dt 9.902 +type train | step 1829 | loss 117.9353 227.3964 350.1882 551.1270 807.8042 1145.1500 1591.6443 2277.1873 3208.2500 4967.0664 8161.3647 15223.6367 | lr 4.4e-04 | norm 6944.2627 | dt 9.864 +type train | step 1830 | loss 115.5745 219.7887 341.0591 540.3638 800.8668 1142.7831 1587.1282 2258.8501 3180.8948 4932.0298 8104.1929 15232.1436 | lr 4.4e-04 | norm 4704.0063 | dt 9.878 +type train | step 1831 | loss 118.4917 226.1596 348.1292 548.5543 803.4507 1153.2092 1600.4417 2294.8372 3217.5327 5008.3940 8293.1104 15644.9619 | lr 4.4e-04 | norm 6377.5122 | dt 9.873 +type train | step 1832 | loss 144.9521 276.3594 408.7394 631.0359 910.8705 1313.8989 1798.9702 2583.7041 3511.6465 5236.4438 8472.5752 15744.3965 | lr 4.4e-04 | norm 7633.9917 | dt 9.858 +type train | step 1833 | loss 149.7373 284.6019 416.6554 636.6323 920.2160 1343.6929 1834.4315 2670.6934 3613.5229 5311.3491 8506.7285 15375.7090 | lr 4.4e-04 | norm 9531.0391 | dt 9.837 +type train | step 1834 | loss 115.8432 221.6458 347.5618 547.1446 808.9914 1147.4001 1600.5427 2295.3662 3257.6487 5064.9512 8367.8379 15743.3438 | lr 4.4e-04 | norm 6028.7822 | dt 9.895 +type train | step 1835 | loss 119.8885 230.4851 358.1435 562.3737 827.4194 1184.2792 1637.4213 2347.1145 3321.2314 5145.4873 8468.5723 15816.8066 | lr 4.4e-04 | norm 5983.8164 | dt 9.878 +type train | step 1836 | loss 113.0349 216.7092 340.5506 536.5781 796.5332 1140.0859 1594.9612 2289.2891 3236.7800 5031.9922 8293.3721 15511.9414 | lr 4.4e-04 | norm 6035.8398 | dt 9.871 +type train | step 1837 | loss 120.0140 230.3917 355.7250 559.8983 824.6484 1175.3427 1621.0034 2321.3970 3264.1758 5055.2656 8299.4453 15536.1797 | lr 4.4e-04 | norm 5208.3701 | dt 9.879 +type train | step 1838 | loss 115.7750 222.1312 344.3734 547.4831 808.4986 1152.4822 1595.8672 2275.6213 3231.7219 5012.6318 8273.2139 15531.9922 | lr 4.4e-04 | norm 5296.0601 | dt 9.871 +type train | step 1839 | loss 122.7582 237.8621 364.3445 566.4388 830.4313 1194.7966 1666.2351 2406.8188 3370.5779 5233.7573 8571.1553 15949.7393 | lr 4.4e-04 | norm 7556.1157 | dt 9.856 +type train | step 1840 | loss 116.4878 221.5821 345.4570 547.8713 812.0945 1170.5225 1627.6456 2338.5552 3294.2751 5069.6821 8353.2803 15592.4111 | lr 4.4e-04 | norm 5466.9746 | dt 9.876 +type train | step 1841 | loss 120.6110 231.9402 356.4866 557.1414 821.5252 1172.5095 1627.5983 2326.5322 3277.4985 5087.4551 8393.4258 15635.3096 | lr 4.4e-04 | norm 4982.8955 | dt 9.875 +type train | step 1842 | loss 105.8645 215.4137 358.2161 596.6126 886.7744 1272.8114 1779.3518 2576.4246 3663.8872 5787.2998 9592.1436 18131.4355 | lr 4.4e-04 | norm 12794.8271 | dt 9.862 +type train | step 1843 | loss 140.0265 271.3756 411.4504 640.6509 930.9357 1306.8861 1786.8273 2504.8552 3468.2646 5245.6138 8499.5645 15632.6582 | lr 4.4e-04 | norm 8583.4102 | dt 9.856 +type train | step 1844 | loss 119.8860 229.9348 352.3555 551.9745 813.7332 1166.8938 1616.9426 2328.8481 3255.8059 5021.6240 8217.6104 15344.7256 | lr 4.4e-04 | norm 5444.6016 | dt 9.891 +type train | step 1845 | loss 126.8072 241.5825 371.1443 581.1180 844.8025 1197.2694 1640.8627 2325.2583 3232.4614 4961.7617 8104.3955 15113.8389 | lr 4.4e-04 | norm 5684.9229 | dt 9.870 +type train | step 1846 | loss 123.3422 237.4276 366.7522 573.9490 840.7496 1191.8496 1652.4203 2354.4585 3312.6196 5121.4414 8428.8271 15816.3164 | lr 4.4e-04 | norm 6079.9360 | dt 9.877 +type train | step 1847 | loss 113.8896 218.0329 337.3641 531.0628 783.1564 1121.8586 1555.5612 2231.4199 3157.6790 4889.6841 8043.3398 15003.3799 | lr 4.4e-04 | norm 5366.6196 | dt 9.881 +type train | step 1848 | loss 119.5183 228.3048 353.9720 553.4663 813.2784 1170.6711 1626.8273 2339.1558 3270.1423 5076.1079 8341.1592 15510.2070 | lr 4.4e-04 | norm 5254.1064 | dt 9.879 +type train | step 1849 | loss 111.9204 214.4728 334.7744 530.2404 785.8188 1122.3069 1560.3180 2229.2620 3158.8384 4899.9189 8075.9990 15024.5576 | lr 4.4e-04 | norm 4464.1899 | dt 9.886 +type train | step 1850 | loss 124.0328 238.0992 364.2172 573.5426 840.1118 1203.8759 1665.6561 2382.2524 3319.5942 5140.5254 8415.8125 15645.1055 | lr 4.4e-04 | norm 5985.0874 | dt 9.888 +type train | step 1851 | loss 116.4707 224.4391 350.3608 552.4800 815.9720 1157.0630 1610.9359 2301.6875 3269.8984 5073.9834 8343.9277 15557.9062 | lr 4.4e-04 | norm 5234.7529 | dt 9.877 +type train | step 1852 | loss 127.2342 243.3073 376.0353 595.5673 864.2164 1283.0493 1782.6503 2607.8752 3546.1248 5434.1201 9009.4199 17006.5703 | lr 4.4e-04 | norm 9794.8789 | dt 9.854 +type train | step 1853 | loss 124.4980 237.3725 366.5752 573.9023 831.5652 1204.4861 1655.2205 2380.5938 3277.2178 5060.7871 8397.3193 15917.8105 | lr 4.4e-04 | norm 8091.6602 | dt 9.847 +type train | step 1854 | loss 117.8972 226.3925 350.8972 550.3829 810.2764 1160.8680 1617.2802 2322.5288 3267.9612 5082.5410 8331.3291 15534.9424 | lr 4.4e-04 | norm 5608.8140 | dt 9.878 +type train | step 1855 | loss 116.3229 223.8247 347.1234 544.6229 805.0294 1159.4371 1610.7638 2312.7468 3259.8496 5031.6353 8268.4355 15433.1221 | lr 4.4e-04 | norm 6142.5029 | dt 9.879 +type train | step 1856 | loss 121.7886 232.7985 355.7307 561.9441 821.4055 1168.8185 1615.4165 2295.3982 3203.3755 4935.5225 8102.9521 15177.6895 | lr 4.4e-04 | norm 6294.2036 | dt 9.881 +type train | step 1857 | loss 119.3290 228.3189 353.2029 553.1985 814.6262 1155.2484 1609.0542 2293.0242 3252.2876 5052.2622 8314.0527 15514.4189 | lr 4.4e-04 | norm 6222.5527 | dt 9.876 +type train | step 1858 | loss 117.5360 225.6066 355.7662 572.5861 840.5657 1209.5502 1678.7139 2415.8069 3362.1460 5174.7783 8488.5811 15885.8389 | lr 4.4e-04 | norm 7330.4082 | dt 9.869 +type train | step 1859 | loss 116.0627 222.5820 344.0856 543.3156 804.4272 1145.7408 1594.4730 2275.2341 3211.3840 4964.9019 8158.2930 15156.2256 | lr 4.4e-04 | norm 5229.6992 | dt 9.877 +type train | step 1860 | loss 115.7758 219.1835 337.3259 534.2338 790.1161 1128.9856 1565.0972 2240.1499 3139.5369 4883.0293 8124.3916 15353.3691 | lr 4.4e-04 | norm 5341.3438 | dt 9.873 +type train | step 1861 | loss 113.6629 214.9871 339.9692 539.0377 797.3984 1135.2527 1581.5212 2306.7700 3259.9331 5102.4121 8458.3027 15785.4609 | lr 4.4e-04 | norm 6623.4453 | dt 9.868 +type train | step 1862 | loss 119.2040 228.1073 352.6337 558.0441 820.1096 1170.5179 1627.8385 2338.9497 3308.9429 5121.6372 8406.1338 15721.9756 | lr 4.4e-04 | norm 5324.4302 | dt 9.895 +type train | step 1863 | loss 109.3293 210.3341 330.5510 524.7969 780.2606 1121.0681 1571.1467 2271.6475 3224.6667 5031.0142 8284.4805 15394.6484 | lr 4.4e-04 | norm 4832.1528 | dt 9.869 +type train | step 1864 | loss 112.5023 214.7379 337.2381 534.4353 793.2328 1134.4219 1577.5638 2262.1567 3188.0884 4951.2119 8117.1455 15178.8623 | lr 4.4e-04 | norm 5310.9780 | dt 9.878 +type train | step 1865 | loss 110.1609 210.3034 327.3597 520.7139 775.2238 1111.4711 1546.2946 2220.0327 3149.1350 4882.6079 8049.8130 15012.2295 | lr 4.4e-04 | norm 4775.7583 | dt 9.885 +type train | step 1866 | loss 117.0420 224.8682 350.4905 555.9760 827.9441 1194.2905 1664.5250 2376.3093 3342.5806 5101.1855 8329.3535 15453.4512 | lr 4.4e-04 | norm 6277.4229 | dt 9.868 +type train | step 1867 | loss 128.7732 251.0305 396.4403 628.1793 938.9948 1333.5225 1852.2590 2620.5244 3737.0610 5685.0898 9274.0176 17023.2051 | lr 4.4e-04 | norm 8288.4551 | dt 9.885 +type train | step 1868 | loss 111.4514 212.4955 331.2181 528.6360 783.7150 1135.9927 1589.7673 2308.4795 3264.1841 5070.2461 8320.6904 15571.2178 | lr 4.4e-04 | norm 5513.6943 | dt 9.874 +type train | step 1869 | loss 114.3118 218.8073 338.5337 530.6707 782.7247 1123.0221 1560.2871 2249.6362 3166.7830 4929.3638 8131.5674 15332.1855 | lr 4.4e-04 | norm 6036.2871 | dt 9.869 +type train | step 1870 | loss 116.7550 224.4052 344.7526 538.7498 794.6583 1124.2837 1556.9650 2218.8613 3131.8879 4819.4517 7900.1460 14690.3359 | lr 4.4e-04 | norm 5632.0234 | dt 9.870 +type train | step 1871 | loss 111.8027 213.4499 330.8893 524.8866 780.1388 1117.7870 1554.7598 2229.3579 3157.6873 4916.9678 8102.8525 15122.3604 | lr 4.4e-04 | norm 5466.9639 | dt 9.873 +type train | step 1872 | loss 117.3867 226.7027 349.8123 550.9871 806.8970 1144.4923 1586.0245 2265.5002 3209.2363 4988.1953 8254.7842 15484.9521 | lr 4.4e-04 | norm 5855.3857 | dt 9.885 +type train | step 1873 | loss 117.7188 224.9835 348.7521 547.4827 803.9612 1157.9948 1611.9557 2315.1516 3250.6323 5065.9404 8413.9863 15747.6367 | lr 4.3e-04 | norm 6110.3013 | dt 9.861 +type train | step 1874 | loss 105.3836 200.9965 319.2842 509.2261 759.3746 1086.8154 1524.4041 2188.0002 3120.0002 4846.1406 7925.4370 14773.4141 | lr 4.3e-04 | norm 4676.0791 | dt 9.869 +type train | step 1875 | loss 110.8410 210.9281 331.0139 523.7607 779.1216 1125.8541 1571.3268 2266.8569 3205.4104 4974.1436 8176.3618 15179.9062 | lr 4.3e-04 | norm 5000.2212 | dt 9.859 +type train | step 1876 | loss 111.9301 224.6089 353.3338 559.9214 827.4680 1167.3834 1619.5621 2312.1313 3291.3096 5099.6445 8430.3223 15873.1318 | lr 4.3e-04 | norm 8686.6641 | dt 9.849 +type train | step 1877 | loss 115.0982 234.5574 365.3830 576.5212 849.4744 1184.2532 1627.9712 2321.5105 3318.3093 5111.4707 8428.4111 15792.5449 | lr 4.3e-04 | norm 10051.0127 | dt 9.865 +type train | step 1878 | loss 115.8515 221.6487 344.0106 545.2531 805.2782 1161.6387 1619.2751 2332.1353 3283.2107 5094.2202 8432.6357 15688.9326 | lr 4.3e-04 | norm 5329.2622 | dt 9.876 +type train | step 1879 | loss 111.8172 213.8854 330.1137 522.0594 773.4875 1113.3145 1552.3394 2226.1052 3128.8530 4868.2900 8049.5420 15151.0000 | lr 4.3e-04 | norm 6414.9312 | dt 9.861 +type train | step 1880 | loss 106.7464 203.7063 317.4788 505.4452 753.2214 1087.3759 1523.7103 2195.8882 3119.5593 4858.0742 7995.1362 14914.1895 | lr 4.3e-04 | norm 5678.0288 | dt 9.876 +type train | step 1881 | loss 118.5322 228.5874 354.3850 555.4136 817.4869 1167.5488 1626.2148 2321.0955 3274.3516 5060.9805 8334.7432 15638.9873 | lr 4.3e-04 | norm 5552.6509 | dt 9.876 +type train | step 1882 | loss 115.9266 222.3186 340.1452 541.2484 796.0720 1143.6501 1594.1643 2285.6777 3205.4270 5018.9346 8329.1729 15874.2852 | lr 4.3e-04 | norm 6543.2261 | dt 9.877 +type train | step 1883 | loss 118.5637 228.0017 352.7469 553.4568 814.2149 1159.3889 1597.9584 2283.3699 3222.9802 5027.8828 8276.4990 15500.4375 | lr 4.3e-04 | norm 5260.0850 | dt 9.893 +type train | step 1884 | loss 110.7126 212.7523 327.2060 519.4214 770.1472 1103.3237 1543.2118 2225.5042 3155.5496 4910.7334 8119.5957 15169.2988 | lr 4.3e-04 | norm 4515.9917 | dt 9.870 +type train | step 1885 | loss 124.2201 232.0251 357.8724 569.0472 827.0916 1176.1898 1641.6558 2349.6040 3347.2637 5262.0396 8761.5908 16958.3789 | lr 4.3e-04 | norm 9574.3369 | dt 9.852 +type train | step 1886 | loss 106.3603 206.9635 328.1787 531.5828 787.7239 1129.7687 1580.5981 2288.4541 3253.4016 5060.0532 8305.4814 15567.4082 | lr 4.3e-04 | norm 7589.4814 | dt 9.860 +type train | step 1887 | loss 108.8318 207.5140 322.3818 511.8303 760.3069 1098.5073 1531.7015 2210.9917 3118.5828 4830.1875 7940.3672 14764.1172 | lr 4.3e-04 | norm 5414.8081 | dt 9.875 +type train | step 1888 | loss 112.2836 213.7395 335.6245 539.2148 799.1415 1145.4841 1594.9340 2290.9116 3258.0962 5060.3799 8358.1045 15686.6836 | lr 4.3e-04 | norm 6255.1133 | dt 9.862 +type train | step 1889 | loss 114.4136 219.0887 336.7108 536.7944 789.9067 1136.7375 1586.9440 2286.4080 3207.8772 4979.6421 8268.1914 15595.1924 | lr 4.3e-04 | norm 5491.9551 | dt 9.862 +type train | step 1890 | loss 117.5252 223.5231 347.6771 553.0201 814.1849 1165.9014 1614.1106 2299.9683 3209.2620 4944.7661 8165.9507 15387.6230 | lr 4.3e-04 | norm 6729.2490 | dt 9.860 +type train | step 1891 | loss 114.0316 216.4611 334.1342 531.9319 785.6807 1130.9082 1573.7336 2257.8281 3182.8660 4944.2695 8199.1533 15352.1582 | lr 4.3e-04 | norm 5470.9429 | dt 9.879 +type train | step 1892 | loss 114.1227 217.1527 335.6435 529.9785 784.4397 1121.7598 1559.1990 2232.0112 3140.8030 4860.4263 8010.7837 14953.6641 | lr 4.3e-04 | norm 5304.6270 | dt 9.868 +type train | step 1893 | loss 114.1757 218.8927 336.2764 529.4716 776.4918 1106.6572 1537.9011 2199.3333 3106.6936 4836.0439 8008.0435 15070.8838 | lr 4.3e-04 | norm 5420.8501 | dt 9.883 +type train | step 1894 | loss 114.8833 219.5455 338.5532 538.3478 793.3823 1128.9852 1566.7112 2245.3743 3162.4678 4887.5576 8075.4673 15156.0107 | lr 4.3e-04 | norm 5873.3892 | dt 9.875 +type train | step 1895 | loss 112.4719 213.4133 332.5916 525.5782 782.9404 1122.4602 1568.0422 2255.1128 3190.9036 4961.8340 8204.3418 15362.3008 | lr 4.3e-04 | norm 5276.8589 | dt 9.867 +type train | step 1896 | loss 119.3135 232.5331 355.2420 560.6267 820.0215 1203.7687 1683.5786 2449.1562 3404.4377 5236.8232 8578.1328 15917.2158 | lr 4.3e-04 | norm 5722.2173 | dt 9.868 +type train | step 1897 | loss 120.3708 235.0562 368.4194 581.4371 846.8315 1207.4976 1664.6031 2374.2654 3312.0361 5100.6865 8406.2070 15674.0957 | lr 4.3e-04 | norm 7059.6582 | dt 9.878 +type train | step 1898 | loss 108.7647 210.3530 328.2510 520.2593 770.4149 1102.2552 1531.7817 2194.9990 3118.4084 4855.8003 8059.1758 15141.7441 | lr 4.3e-04 | norm 5434.5405 | dt 9.875 +type train | step 1899 | loss 108.8558 207.7012 322.1823 512.3373 758.3952 1095.5417 1525.7196 2209.7271 3118.3130 4857.2119 8050.8428 15159.9873 | lr 4.3e-04 | norm 5947.3945 | dt 9.866 +type train | step 1900 | loss 112.5434 215.3655 335.2112 535.6271 789.1782 1131.1693 1569.0720 2261.1580 3179.5242 4916.9619 8110.0850 15167.5273 | lr 4.3e-04 | norm 5422.8984 | dt 9.876 +type train | step 1901 | loss 108.8472 208.3983 321.3332 514.8513 760.9078 1093.1759 1527.6958 2191.2505 3114.4268 4857.4165 8051.3525 15060.6709 | lr 4.3e-04 | norm 5406.7915 | dt 9.875 +type train | step 1902 | loss 110.9695 210.9984 326.4694 515.5718 764.5236 1094.9301 1529.2501 2189.6912 3110.0828 4844.1396 8007.4302 14943.4219 | lr 4.3e-04 | norm 4912.2510 | dt 9.874 +type train | step 1903 | loss 115.2832 221.4461 340.5628 537.0839 789.0270 1132.1731 1577.5010 2256.6514 3173.5520 4947.8325 8157.3325 15263.3633 | lr 4.3e-04 | norm 5124.5278 | dt 9.893 +type train | step 1904 | loss 110.3224 213.2694 334.7703 533.9466 796.9236 1142.4045 1606.2378 2311.7383 3282.7036 5079.9629 8326.7158 15594.7012 | lr 4.3e-04 | norm 7005.0908 | dt 9.872 +type train | step 1905 | loss 111.2335 212.8805 331.8893 528.2918 788.7225 1134.7979 1593.0781 2298.4995 3265.7908 5082.7402 8353.5791 15603.5859 | lr 4.3e-04 | norm 7404.6304 | dt 9.884 +type train | step 1906 | loss 111.5990 211.1432 327.1819 517.3876 765.1457 1100.9701 1530.1456 2200.7922 3108.8928 4840.3306 8021.8359 14948.7988 | lr 4.3e-04 | norm 5257.4268 | dt 9.880 +type train | step 1907 | loss 117.6467 224.5111 345.3266 546.6307 804.1180 1147.2102 1595.0374 2285.0422 3215.5627 5011.5127 8258.8457 15317.8672 | lr 4.3e-04 | norm 5599.5933 | dt 9.880 +type train | step 1908 | loss 115.1950 220.0495 339.1077 537.5640 791.9546 1141.1440 1584.3677 2265.2561 3187.7322 4921.3174 8107.2422 15118.7422 | lr 4.3e-04 | norm 5232.3540 | dt 9.873 +type train | step 1909 | loss 109.5264 209.6168 328.3835 522.0591 775.0961 1118.0044 1564.7322 2260.9324 3204.5603 4990.8677 8227.1475 15414.6748 | lr 4.3e-04 | norm 5429.8735 | dt 9.868 +type train | step 1910 | loss 109.5003 211.8984 332.8121 530.6803 789.2742 1152.7664 1617.7390 2364.1685 3358.0198 5230.4604 8594.8037 16113.8682 | lr 4.3e-04 | norm 6307.3062 | dt 9.871 +type train | step 1911 | loss 118.5100 229.4995 350.7283 548.1285 806.4992 1156.4658 1605.0569 2294.4458 3210.7805 4989.7041 8266.1348 15504.8516 | lr 4.3e-04 | norm 7327.2188 | dt 9.875 +type train | step 1912 | loss 125.8192 239.8119 368.6006 576.5341 833.8679 1199.8777 1650.3953 2358.6082 3273.8767 5000.4106 8232.3994 15252.2383 | lr 4.3e-04 | norm 6449.8853 | dt 9.873 +type train | step 1913 | loss 112.4750 216.8087 335.4126 527.4594 776.8509 1115.5414 1556.0168 2240.5630 3148.6812 4881.9951 8081.7100 15080.6250 | lr 4.3e-04 | norm 5216.6597 | dt 9.883 +type train | step 1914 | loss 117.4738 227.2405 348.8357 549.4844 809.5892 1152.7817 1606.7010 2305.2188 3253.9980 5029.5830 8254.3555 15295.5684 | lr 4.3e-04 | norm 5732.8062 | dt 9.884 +type train | step 1915 | loss 121.6944 231.7583 354.8877 557.6682 818.0902 1166.9739 1612.9099 2298.3452 3195.5088 4917.2754 8045.0557 14924.7510 | lr 4.3e-04 | norm 5110.3276 | dt 9.875 +type train | step 1916 | loss 108.6820 206.2843 323.4160 519.2047 773.6112 1119.1431 1567.5682 2254.4116 3183.1997 4918.6289 8036.9478 14864.8701 | lr 4.3e-04 | norm 4920.8467 | dt 9.882 +type train | step 1917 | loss 108.2069 207.4683 321.8303 508.9223 754.8726 1077.4021 1500.2520 2142.9500 3033.6924 4720.0337 7799.5356 14607.4619 | lr 4.3e-04 | norm 4468.2632 | dt 9.895 +type train | step 1918 | loss 125.0611 237.8594 366.2667 572.7787 832.6895 1187.6891 1639.7413 2333.0505 3252.2744 4973.0166 8130.9678 15155.4121 | lr 4.3e-04 | norm 6009.5698 | dt 9.875 +type train | step 1919 | loss 130.4344 244.7450 374.2282 585.6532 854.1591 1206.2705 1647.0643 2342.4136 3279.5925 5018.9482 8176.1543 15132.5146 | lr 4.3e-04 | norm 8606.5830 | dt 9.857 +type train | step 1920 | loss 126.7112 240.5078 365.3543 572.3989 838.9868 1199.4618 1659.6232 2362.6924 3320.5457 5125.3457 8415.3633 15637.4414 | lr 4.3e-04 | norm 6798.4473 | dt 9.867 +type train | step 1921 | loss 109.7209 211.8327 329.6088 525.3268 777.5436 1116.6344 1559.9160 2243.8005 3182.7988 4948.2817 8169.3037 15328.1836 | lr 4.3e-04 | norm 5651.3960 | dt 9.890 +type train | step 1922 | loss 108.8477 207.6225 323.3543 520.8493 770.7972 1112.7589 1551.5973 2234.6226 3172.1555 4937.9966 8174.6035 15298.1348 | lr 4.3e-04 | norm 5869.6240 | dt 9.865 +type train | step 1923 | loss 112.5905 217.9693 338.9849 538.9419 791.2416 1133.7678 1583.2386 2265.9331 3209.7725 4979.1787 8299.6709 15469.0361 | lr 4.3e-04 | norm 5836.7754 | dt 9.886 +type train | step 1924 | loss 107.5596 207.8658 325.5397 521.6208 773.1879 1117.7512 1569.0531 2251.0361 3184.0544 4951.6880 8153.8496 15228.3613 | lr 4.3e-04 | norm 5756.2539 | dt 9.872 +type train | step 1925 | loss 117.4954 227.7378 358.3970 579.4225 847.5550 1224.2837 1712.1338 2478.0327 3506.8960 5496.8374 9221.0996 17357.7070 | lr 4.3e-04 | norm 8246.9131 | dt 9.848 +type train | step 1926 | loss 112.7878 215.1030 334.9323 532.7653 788.3014 1142.3802 1591.4246 2292.1001 3203.4280 4973.9561 8228.3057 15416.7588 | lr 4.3e-04 | norm 6408.9473 | dt 9.868 +type train | step 1927 | loss 115.3668 219.0699 339.0963 532.9850 783.9244 1120.0183 1550.8440 2221.1665 3116.0354 4837.8145 7958.8496 14890.6484 | lr 4.3e-04 | norm 5697.3052 | dt 10.195 +type train | step 1928 | loss 117.1484 225.7555 344.5959 545.4062 804.1354 1163.6443 1620.1963 2326.0840 3247.9541 4982.3013 8147.9780 15124.6025 | lr 4.3e-04 | norm 5699.6338 | dt 9.861 +type train | step 1929 | loss 114.7738 218.4229 337.3673 534.5317 786.5412 1126.1576 1572.7496 2239.9326 3165.4084 4887.7021 8030.8672 14991.8438 | lr 4.3e-04 | norm 5252.5615 | dt 9.891 +type train | step 1930 | loss 114.2385 217.4682 335.5729 531.0344 784.7641 1124.4998 1567.4098 2256.4146 3171.0989 4938.2983 8145.4028 15251.2773 | lr 4.3e-04 | norm 5574.8154 | dt 9.881 +type train | step 1931 | loss 111.4180 214.3315 333.4825 528.0813 781.2404 1122.0714 1564.5217 2248.4390 3183.5793 4914.5850 8062.4287 14885.4111 | lr 4.3e-04 | norm 4830.3491 | dt 9.885 +type train | step 1932 | loss 113.7099 214.7510 329.1531 519.2264 766.0093 1097.9442 1522.8647 2194.6169 3091.8442 4780.5596 7859.3286 14584.7773 | lr 4.3e-04 | norm 5198.6880 | dt 9.868 +type train | step 1933 | loss 111.5441 212.0403 324.5440 519.3312 767.6158 1109.7976 1550.5809 2238.0200 3144.6997 4914.0078 8126.4419 15241.0762 | lr 4.3e-04 | norm 6229.4795 | dt 9.860 +type train | step 1934 | loss 117.6935 224.3438 344.6159 542.4803 799.6761 1141.5784 1592.7971 2294.7266 3232.8518 5050.7119 8345.5547 15603.9688 | lr 4.3e-04 | norm 6282.5913 | dt 9.869 +type train | step 1935 | loss 112.9043 214.5997 332.1783 527.7810 784.5587 1118.4037 1561.3882 2232.3594 3172.5776 4936.6187 8184.9243 15337.9082 | lr 4.3e-04 | norm 6514.7383 | dt 9.876 +type train | step 1936 | loss 125.8783 240.9032 364.2819 573.8766 841.0114 1193.2239 1644.0934 2348.9065 3278.2800 5080.2627 8377.5195 15742.1797 | lr 4.3e-04 | norm 7473.8086 | dt 9.860 +type train | step 1937 | loss 111.5804 212.0664 329.7351 526.3024 776.0784 1115.1560 1554.2454 2235.6221 3143.0781 4884.9785 8043.9722 15128.4932 | lr 4.3e-04 | norm 6498.9507 | dt 9.881 +type train | step 1938 | loss 107.0721 204.1893 318.2555 511.3165 756.8665 1101.7134 1540.7234 2218.0522 3117.7827 4798.1294 7845.3711 14551.3691 | lr 4.3e-04 | norm 6260.6123 | dt 9.879 +type train | step 1939 | loss 107.4113 205.0690 314.0179 512.0566 758.6054 1116.1665 1576.0236 2296.8416 3185.6250 4889.3594 8040.2832 15167.6016 | lr 4.3e-04 | norm 11537.9268 | dt 9.827 +type train | step 1940 | loss 109.2132 208.3605 326.5007 520.6984 770.6462 1104.1586 1543.0581 2207.7407 3132.5664 4871.4473 8074.4365 15056.5020 | lr 4.3e-04 | norm 5528.5088 | dt 9.892 +type train | step 1941 | loss 113.1643 218.3481 335.6666 530.0466 778.5773 1119.2909 1564.9523 2253.8970 3186.4409 4968.6929 8212.0938 15371.8359 | lr 4.3e-04 | norm 5441.4912 | dt 9.887 +type train | step 1942 | loss 114.5962 217.7216 337.9669 539.4664 790.3268 1127.1138 1561.8135 2242.6616 3137.8789 4868.8721 8048.9834 15084.4170 | lr 4.3e-04 | norm 5718.7607 | dt 9.870 +type train | step 1943 | loss 102.9915 196.5542 309.9099 498.3910 743.2516 1065.4255 1485.3879 2129.5767 3035.9185 4706.0137 7734.0615 14335.8350 | lr 4.3e-04 | norm 5050.9160 | dt 9.879 +type train | step 1944 | loss 109.5522 207.2648 327.1719 521.0201 770.5861 1116.5541 1565.3297 2265.4375 3199.9739 4978.4375 8250.7617 15415.8242 | lr 4.3e-04 | norm 6126.6987 | dt 9.875 +type train | step 1945 | loss 114.6273 221.5482 346.3932 548.1861 805.8520 1142.5974 1584.5554 2269.7334 3197.2021 4951.4399 8156.9194 15219.6650 | lr 4.3e-04 | norm 5403.9912 | dt 9.874 +type train | step 1946 | loss 111.1260 211.8326 327.5095 520.2437 769.0068 1107.3114 1540.1260 2210.3835 3127.9578 4852.0332 8004.5122 14935.1816 | lr 4.3e-04 | norm 4966.2993 | dt 9.873 +type train | step 1947 | loss 118.3851 226.6205 344.1478 544.8893 798.6936 1143.9768 1582.6599 2262.3516 3171.4512 4898.5068 8092.4297 15118.3750 | lr 4.3e-04 | norm 6022.2383 | dt 9.872 +type train | step 1948 | loss 121.2796 234.5099 353.3795 554.1619 802.7933 1142.8630 1576.4617 2243.3674 3119.1804 4787.4736 7841.8687 14591.1553 | lr 4.3e-04 | norm 6321.7910 | dt 9.866 +type train | step 1949 | loss 110.6251 212.9572 332.3037 531.1416 783.3668 1129.3014 1578.3086 2263.7371 3189.5723 4955.4097 8192.2334 15269.2480 | lr 4.3e-04 | norm 4914.3291 | dt 9.886 +type train | step 1950 | loss 126.3009 242.6644 374.8710 585.3127 839.3876 1195.9352 1623.6229 2284.8335 3125.1753 4774.0303 7724.5938 14409.8252 | lr 4.3e-04 | norm 6911.4028 | dt 9.851 +type train | step 1951 | loss 118.7210 227.2244 347.2166 548.6718 801.9828 1151.6427 1601.4000 2281.4673 3194.9407 4945.8071 8125.8628 15155.6543 | lr 4.3e-04 | norm 5422.3584 | dt 9.872 +type train | step 1952 | loss 112.6058 214.9654 336.4511 535.3974 788.7861 1125.3014 1568.3916 2242.9453 3183.7124 4922.6851 8067.9707 14947.5195 | lr 4.3e-04 | norm 4889.7529 | dt 9.874 +type train | step 1953 | loss 109.3434 207.4836 325.7611 521.1152 770.5466 1116.3195 1562.5696 2259.6621 3183.0317 4951.1182 8182.7451 15175.3604 | lr 4.3e-04 | norm 6271.3350 | dt 9.882 +type train | step 1954 | loss 104.2522 199.9431 311.6707 499.9777 742.3979 1076.1150 1508.8704 2185.4126 3094.6123 4853.7920 8030.1792 15038.0859 | lr 4.3e-04 | norm 6462.1885 | dt 9.893 +type train | step 1955 | loss 118.2527 228.8102 350.3900 555.7672 812.6707 1165.4033 1627.2748 2332.7075 3275.0957 5046.0581 8294.3398 15356.7676 | lr 4.3e-04 | norm 5369.6577 | dt 9.868 +type train | step 1956 | loss 108.2870 206.3384 321.2411 508.6379 758.6196 1119.4202 1589.5474 2337.6267 3267.9888 5083.5474 8395.3984 15683.2324 | lr 4.3e-04 | norm 8118.8521 | dt 9.852 +type train | step 1957 | loss 108.8820 208.7829 323.8069 516.9081 764.6227 1101.0559 1545.6038 2228.4954 3164.4241 4913.4292 8125.9243 15171.9258 | lr 4.3e-04 | norm 5350.2510 | dt 9.874 +type train | step 1958 | loss 108.0548 207.1173 321.2512 510.9792 756.7415 1085.8271 1515.7782 2177.6011 3097.0823 4833.1641 7952.1479 14801.7510 | lr 4.3e-04 | norm 5341.2173 | dt 9.880 +type train | step 1959 | loss 133.3541 262.0244 390.3070 601.5525 868.0868 1239.2323 1707.2720 2411.7886 3345.5186 5096.2764 8308.8184 15303.0762 | lr 4.3e-04 | norm 5963.4390 | dt 9.883 +type train | step 1960 | loss 113.4726 217.9159 337.0072 538.8380 800.2698 1155.9949 1626.5015 2367.8293 3314.2446 5180.8047 8573.9482 16127.7109 | lr 4.3e-04 | norm 6772.1963 | dt 9.884 +type train | step 1961 | loss 119.6924 233.9081 362.4409 573.0428 837.4478 1212.9275 1692.2175 2414.6045 3359.3743 5178.1611 8537.9756 15962.5029 | lr 4.3e-04 | norm 6871.0425 | dt 9.886 +type train | step 1962 | loss 114.8309 223.4284 345.3233 550.5855 809.7798 1157.7479 1610.2168 2304.8430 3230.7432 5019.5229 8334.9521 15595.1963 | lr 4.2e-04 | norm 7509.4229 | dt 9.883 +type train | step 1963 | loss 105.5885 203.7742 319.5527 515.6564 771.4741 1113.8777 1563.1432 2268.1262 3217.6250 4995.0830 8215.7480 15272.0811 | lr 4.2e-04 | norm 5719.9810 | dt 9.887 +type train | step 1964 | loss 117.1050 226.6997 349.3592 556.5244 815.7164 1175.1066 1636.7864 2352.3501 3320.6174 5143.0146 8505.6250 15966.9609 | lr 4.2e-04 | norm 6288.3286 | dt 9.863 +type train | step 1965 | loss 130.7401 250.7347 371.2884 581.3188 846.2220 1208.3965 1666.7072 2384.1987 3321.2241 5135.5918 8538.3408 16127.4316 | lr 4.2e-04 | norm 7849.1094 | dt 9.881 +type train | step 1966 | loss 116.8570 222.0555 343.9394 544.3124 794.2758 1140.3302 1579.1707 2262.4209 3152.2051 4886.1279 8045.2520 15182.7744 | lr 4.2e-04 | norm 6053.4043 | dt 9.878 +type train | step 1967 | loss 110.9724 213.7197 334.3808 537.2705 794.1666 1157.7111 1609.3074 2337.0781 3289.0813 5092.5625 8474.0586 15914.6406 | lr 4.2e-04 | norm 8217.4482 | dt 9.862 +type train | step 1968 | loss 116.7592 222.7925 341.8071 538.4869 790.8928 1135.9954 1583.9258 2265.8936 3184.7466 4921.4644 8073.7485 14979.1016 | lr 4.2e-04 | norm 5389.3223 | dt 9.888 +type train | step 1969 | loss 137.8924 249.6791 367.1233 579.5698 839.3853 1215.2977 1701.7218 2480.3254 3469.0476 5346.0293 8793.1221 16308.9531 | lr 4.2e-04 | norm 7627.4448 | dt 9.854 +type train | step 1970 | loss 109.9110 210.2754 325.5166 517.7008 766.7740 1102.2041 1536.1487 2213.5769 3129.8569 4849.0415 8006.5449 14961.5361 | lr 4.2e-04 | norm 5452.3096 | dt 9.879 +type train | step 1971 | loss 116.5264 222.2214 337.8314 535.4417 784.5419 1122.6149 1559.3375 2244.8918 3166.1760 4919.8394 8165.0015 15307.1592 | lr 4.2e-04 | norm 6446.9961 | dt 9.888 +type train | step 1972 | loss 121.5039 233.8159 364.8470 579.6387 851.0550 1245.7665 1765.1785 2565.6870 3605.2639 5633.3564 9389.7383 18028.7559 | lr 4.2e-04 | norm 15686.0820 | dt 9.833 +type train | step 1973 | loss 112.9278 216.6810 335.8535 534.2083 787.6582 1126.9229 1568.8799 2238.0593 3167.2539 4907.9790 8078.5752 15043.3584 | lr 4.2e-04 | norm 5296.3076 | dt 9.886 +type train | step 1974 | loss 117.6353 226.3578 349.3951 547.8492 802.2783 1152.3865 1601.5219 2293.0508 3238.7383 5008.8906 8301.5889 15532.5127 | lr 4.2e-04 | norm 5225.4390 | dt 9.875 +type train | step 1975 | loss 113.0889 215.5272 331.5315 526.4987 773.5524 1109.7096 1544.8735 2217.4712 3128.3901 4849.6821 7984.7163 14861.7471 | lr 4.2e-04 | norm 5098.2700 | dt 9.878 +type train | step 1976 | loss 114.7590 218.9803 335.8642 526.6675 772.7132 1103.2910 1532.4492 2196.9265 3083.5381 4775.3384 7832.0840 14572.8037 | lr 4.2e-04 | norm 5172.3374 | dt 9.889 +type train | step 1977 | loss 111.5526 212.3121 327.4930 518.7096 765.1722 1099.8237 1532.1267 2196.8135 3105.0244 4844.8340 8077.8037 15150.9062 | lr 4.2e-04 | norm 5185.7783 | dt 9.882 +type train | step 1978 | loss 113.2452 217.5243 334.7315 530.9739 785.7648 1131.8873 1582.6171 2272.3960 3214.1912 4979.1318 8176.4468 15057.4404 | lr 4.2e-04 | norm 4995.3896 | dt 9.887 +type train | step 1979 | loss 106.8668 202.5243 316.0107 508.7919 756.9399 1094.0310 1529.1311 2198.6970 3109.4802 4836.5166 8030.2153 14942.4678 | lr 4.2e-04 | norm 5336.4390 | dt 9.871 +type train | step 1980 | loss 127.9690 248.2339 374.8447 587.5040 850.9351 1217.1527 1691.4731 2428.7715 3410.7166 5344.9980 8978.7354 16952.4238 | lr 4.2e-04 | norm 10010.0293 | dt 9.854 +type train | step 1981 | loss 111.1280 214.0867 334.4146 534.2228 786.9291 1135.6410 1584.7301 2281.9995 3224.2434 5032.9316 8368.8887 15653.2676 | lr 4.2e-04 | norm 5193.5938 | dt 9.860 +type train | step 1982 | loss 108.1636 207.2862 321.4482 511.2476 759.6688 1089.5210 1525.2207 2192.4363 3094.4058 4799.6958 7907.1689 14737.0195 | lr 4.2e-04 | norm 5150.9819 | dt 9.884 +type train | step 1983 | loss 109.1580 209.3733 321.1967 510.8616 754.4907 1090.6501 1522.6044 2185.6436 3085.8455 4766.8569 7843.1357 14537.4355 | lr 4.2e-04 | norm 5309.4580 | dt 9.865 +type train | step 1984 | loss 104.6582 198.4792 309.3912 500.6334 746.9405 1095.9838 1541.3950 2241.3538 3164.4534 4938.2505 8137.8677 15050.6152 | lr 4.2e-04 | norm 5653.4165 | dt 9.876 +type train | step 1985 | loss 115.4611 218.3948 333.7411 524.5138 769.8533 1101.8086 1533.6500 2193.4058 3084.2966 4768.7065 7807.1279 14520.7539 | lr 4.2e-04 | norm 5402.7002 | dt 9.883 +type train | step 1986 | loss 114.6687 217.0623 335.0266 531.1621 774.8599 1111.0879 1535.8853 2201.4092 3087.8833 4765.8032 7884.9644 14705.9980 | lr 4.2e-04 | norm 6182.6851 | dt 9.870 +type train | step 1987 | loss 108.3371 207.8038 319.7462 508.7317 752.0587 1079.4363 1512.1982 2175.9846 3108.1436 4820.7827 7926.4150 14691.0830 | lr 4.2e-04 | norm 4746.4180 | dt 9.881 +type train | step 1988 | loss 118.8834 227.1130 342.3762 539.7772 786.3462 1117.9412 1546.3115 2196.6213 3086.5476 4740.5518 7826.9082 14577.0664 | lr 4.2e-04 | norm 4923.8379 | dt 9.871 +type train | step 1989 | loss 108.9313 209.0056 322.3173 513.5770 759.0813 1088.8322 1514.6449 2167.1182 3063.8091 4756.1724 7846.1621 14504.8955 | lr 4.2e-04 | norm 4816.5693 | dt 9.879 +type train | step 1990 | loss 108.4773 207.0122 321.0513 512.5530 758.3285 1088.9275 1522.0869 2191.8892 3119.6572 4850.0928 7967.5903 14724.2188 | lr 4.2e-04 | norm 4878.4717 | dt 9.902 +type train | step 1991 | loss 105.6739 202.0634 317.5274 511.8760 761.7834 1101.3337 1545.1260 2245.8706 3200.7925 4953.4087 8173.2231 15149.3291 | lr 4.2e-04 | norm 8332.4570 | dt 9.871 +type train | step 1992 | loss 109.8744 211.0363 325.5791 518.3849 765.3844 1097.7698 1531.1635 2209.8743 3126.1377 4871.0879 8065.0679 14989.5928 | lr 4.2e-04 | norm 4974.6689 | dt 9.862 +type train | step 1993 | loss 105.5270 202.0002 317.3069 512.1071 763.1210 1121.4521 1588.6831 2323.7930 3272.8525 5129.7939 8508.1631 15927.5625 | lr 4.2e-04 | norm 6220.0762 | dt 9.873 +type train | step 1994 | loss 115.7939 224.2093 350.7164 560.3750 824.2010 1199.1901 1675.0879 2422.7009 3401.8679 5228.7773 8582.9980 15913.8955 | lr 4.2e-04 | norm 7023.7905 | dt 9.869 +type train | step 1995 | loss 119.8955 229.3528 351.0436 553.3737 807.5530 1160.6415 1609.7469 2288.0396 3181.1562 4933.6445 8180.8848 15305.0615 | lr 4.2e-04 | norm 6025.4756 | dt 9.873 +type train | step 1996 | loss 132.7370 248.8656 379.4569 599.8021 871.5837 1266.6567 1766.0472 2537.2473 3493.9121 5397.5557 8907.1885 16768.4492 | lr 4.2e-04 | norm 7757.2920 | dt 9.878 +type train | step 1997 | loss 122.4218 235.4078 357.3263 561.1183 816.5726 1180.3909 1632.9908 2340.6213 3248.6560 4969.3550 8049.6064 14912.3047 | lr 4.2e-04 | norm 5769.6147 | dt 9.868 +type train | step 1998 | loss 111.0844 213.0546 330.8696 524.9580 773.4360 1115.0332 1562.8982 2260.6562 3184.7869 4984.4922 8290.9111 15466.7109 | lr 4.2e-04 | norm 5668.5850 | dt 9.866 +type train | step 1999 | loss 116.1200 222.2164 338.8914 540.2416 793.2281 1147.0624 1602.4303 2308.1675 3228.0186 4986.9702 8278.0479 15475.2158 | lr 4.2e-04 | norm 5511.6226 | dt 9.887 +type train | step 2000 | loss 119.5794 226.1698 341.1961 537.2181 791.5993 1160.3904 1625.1864 2357.6699 3285.5688 5069.6167 8379.2686 15667.3516 | lr 4.2e-04 | norm 5617.4585 | dt 9.863 +type train | step 2001 | loss 112.9121 214.7878 330.4510 527.0707 775.9327 1123.0497 1565.2090 2244.5947 3146.1187 4862.9546 8049.5381 14930.4990 | lr 4.2e-04 | norm 4874.9604 | dt 9.861 +type train | step 2002 | loss 111.1507 211.8025 331.1072 530.4414 778.8472 1121.9126 1559.6084 2240.0618 3156.0457 4896.3394 8053.8096 15023.3096 | lr 4.2e-04 | norm 5567.8374 | dt 9.869 +type train | step 2003 | loss 108.6688 208.3722 328.3730 528.2082 780.9670 1120.2114 1565.4695 2254.7212 3211.6423 4968.1211 8184.2012 15196.3789 | lr 4.2e-04 | norm 5484.4263 | dt 9.873 +type train | step 2004 | loss 117.0932 229.6793 359.8174 577.0814 846.3580 1211.7039 1679.2529 2396.5332 3344.6035 5124.2251 8376.8828 15575.8623 | lr 4.2e-04 | norm 5976.4692 | dt 9.877 +type train | step 2005 | loss 106.4839 203.6498 316.9790 505.7662 749.8655 1086.1417 1517.0564 2179.3418 3078.3618 4794.1382 7950.7617 14749.2939 | lr 4.2e-04 | norm 5465.9785 | dt 9.873 +type train | step 2006 | loss 118.3266 227.9755 349.1310 552.7953 812.3925 1168.2888 1621.5623 2323.4597 3235.7151 4978.7432 8153.9971 15107.0596 | lr 4.2e-04 | norm 5269.1802 | dt 9.875 +type train | step 2007 | loss 108.5158 207.2937 322.2657 519.6069 769.4203 1119.5018 1577.8616 2280.1079 3212.6826 4993.7041 8296.4629 15561.3828 | lr 4.2e-04 | norm 6225.4380 | dt 9.858 +type train | step 2008 | loss 110.6332 211.5292 327.8923 520.1831 765.2031 1100.1794 1528.2169 2178.8340 3064.4033 4746.2007 7842.1455 14644.7871 | lr 4.2e-04 | norm 5574.0420 | dt 9.879 +type train | step 2009 | loss 115.5335 225.1317 343.1848 539.3715 785.1139 1118.2074 1549.9879 2206.9309 3090.9351 4767.0151 7831.4536 14563.1953 | lr 4.2e-04 | norm 5678.7905 | dt 9.882 +type train | step 2010 | loss 126.6519 243.9409 369.3694 579.8625 838.4074 1191.5879 1638.8947 2334.8169 3227.4617 4969.6948 8146.0938 15150.2051 | lr 4.2e-04 | norm 5955.3853 | dt 9.890 +type train | step 2011 | loss 112.1924 214.5561 330.2413 526.8633 774.3363 1104.1829 1531.1440 2183.3918 3085.3958 4787.2783 7926.4917 14706.2285 | lr 4.2e-04 | norm 5029.7827 | dt 9.875 +type train | step 2012 | loss 108.7442 206.7475 322.8596 512.3181 754.1329 1081.7500 1506.2917 2160.1384 3049.6865 4734.6084 7814.6421 14450.1826 | lr 4.2e-04 | norm 4923.6909 | dt 9.884 +type train | step 2013 | loss 122.3764 235.6984 362.3586 578.1793 836.4202 1207.2891 1664.3018 2386.9133 3299.8035 5085.4263 8356.4961 15454.5830 | lr 4.2e-04 | norm 6273.2734 | dt 9.857 +type train | step 2014 | loss 114.8240 223.8021 338.1950 539.6647 789.9193 1136.6410 1579.7556 2262.2092 3169.4832 4894.4712 8003.2437 14824.0205 | lr 4.2e-04 | norm 7314.4355 | dt 9.862 +type train | step 2015 | loss 115.5614 223.0061 342.2129 548.2219 802.1599 1166.4470 1619.1122 2340.7288 3239.1462 4997.1089 8297.6602 15345.1729 | lr 4.2e-04 | norm 7414.9854 | dt 9.856 +type train | step 2016 | loss 110.1208 212.7254 329.7972 525.2494 778.2494 1126.2292 1573.8805 2279.8618 3219.5107 4994.2734 8210.4521 15177.2129 | lr 4.2e-04 | norm 5565.6421 | dt 9.881 +type train | step 2017 | loss 114.6424 218.4232 335.3253 532.3177 781.5731 1137.3993 1585.8008 2289.7769 3182.9321 4919.6113 8164.9683 15222.0742 | lr 4.2e-04 | norm 7460.3271 | dt 9.857 +type train | step 2018 | loss 107.7374 207.8700 321.2129 513.0945 756.7811 1098.5186 1533.7947 2205.7463 3133.3840 4873.9863 8078.7656 15141.5771 | lr 4.2e-04 | norm 5752.2593 | dt 9.891 +type train | step 2019 | loss 135.9934 261.2429 385.5071 591.0206 852.3970 1206.3054 1651.5000 2323.2783 3209.8369 4917.2100 8102.2871 15119.2139 | lr 4.2e-04 | norm 8226.5537 | dt 9.869 +type train | step 2020 | loss 106.0426 202.2655 314.5774 508.7455 755.3019 1097.4340 1538.9127 2224.6992 3147.9678 4899.5532 8086.9897 14926.4082 | lr 4.2e-04 | norm 5165.9395 | dt 9.881 +type train | step 2021 | loss 109.5622 213.5675 329.6239 523.8686 774.2595 1126.3400 1578.6907 2276.2100 3187.4341 4894.8809 7968.1836 14700.5625 | lr 4.2e-04 | norm 5286.7354 | dt 9.871 +type train | step 2022 | loss 118.0904 222.5955 342.8764 542.0321 789.8022 1125.7596 1557.8992 2211.4360 3080.1558 4714.9902 7687.5483 14096.8916 | lr 4.2e-04 | norm 4965.5205 | dt 9.885 +type train | step 2023 | loss 109.5419 208.8142 321.6484 514.6839 762.7446 1098.5227 1536.0923 2214.8208 3138.9214 4864.3032 8062.7178 14987.5098 | lr 4.2e-04 | norm 5720.0356 | dt 9.884 +type train | step 2024 | loss 107.2126 214.0812 337.4197 543.5184 803.7922 1156.9817 1624.7253 2354.8311 3314.5754 5184.3271 8622.6201 16076.8555 | lr 4.2e-04 | norm 7327.1758 | dt 9.877 +type train | step 2025 | loss 114.7321 219.5123 335.5307 537.8262 784.0583 1135.2429 1575.0195 2257.2012 3146.5278 4840.6826 8009.4155 14932.1699 | lr 4.2e-04 | norm 6133.8535 | dt 9.877 +type train | step 2026 | loss 107.6026 205.0306 319.0923 508.9247 754.3915 1093.6122 1531.2894 2209.7290 3126.5132 4836.5361 8003.9795 14812.9072 | lr 4.2e-04 | norm 5197.2622 | dt 9.873 +type train | step 2027 | loss 109.4436 210.4263 325.6852 520.0333 768.5977 1110.3027 1556.1539 2238.6611 3157.4302 4866.7485 8013.8101 14735.0059 | lr 4.2e-04 | norm 5365.2456 | dt 9.894 +type train | step 2028 | loss 112.0196 214.4618 332.1927 526.0841 771.2744 1110.0850 1552.5923 2237.0842 3158.0525 4904.5215 8060.0059 15020.6191 | lr 4.2e-04 | norm 5883.0811 | dt 9.882 +type train | step 2029 | loss 110.7330 208.9388 327.0682 522.3539 765.8109 1100.0996 1532.5028 2205.3984 3102.6362 4830.4995 7990.9336 14863.6416 | lr 4.2e-04 | norm 6812.0889 | dt 9.864 +type train | step 2030 | loss 133.9655 256.5476 380.6817 586.5963 847.5276 1204.6938 1673.6544 2407.9790 3289.5815 4991.7539 8082.9233 14927.3828 | lr 4.2e-04 | norm 6539.1089 | dt 9.862 +type train | step 2031 | loss 107.0546 204.3183 320.4055 518.3126 765.7692 1110.0474 1548.3079 2236.3823 3165.6646 4941.5908 8254.3486 15340.1465 | lr 4.2e-04 | norm 6860.5864 | dt 9.857 +type train | step 2032 | loss 103.3551 199.1121 313.1811 505.0215 752.8175 1090.4795 1533.5277 2208.2927 3139.1743 4857.5317 7971.3003 14645.3262 | lr 4.2e-04 | norm 4767.3530 | dt 9.890 +type train | step 2033 | loss 108.2755 211.1221 327.5444 526.0751 783.9078 1157.3225 1635.6625 2373.6689 3306.1758 5079.4512 8342.6348 15381.0703 | lr 4.2e-04 | norm 6626.5933 | dt 9.857 +type train | step 2034 | loss 110.2584 210.0031 324.2950 519.9636 767.3556 1107.8767 1545.7023 2225.9451 3124.6016 4835.7686 7968.2900 14716.8486 | lr 4.2e-04 | norm 5588.8745 | dt 9.875 +type train | step 2035 | loss 108.0970 207.1645 318.9691 514.7906 763.9169 1103.1887 1539.8583 2207.8127 3101.0439 4820.2754 7999.0029 14972.6191 | lr 4.2e-04 | norm 6269.2681 | dt 9.867 +type train | step 2036 | loss 109.3776 208.0982 323.6274 517.7697 767.6783 1106.5093 1546.0323 2235.0095 3152.8105 4882.5684 8038.6597 14852.1279 | lr 4.2e-04 | norm 5112.2354 | dt 9.872 +type train | step 2037 | loss 113.8502 219.2786 338.5175 539.1108 791.8511 1147.5905 1587.8693 2270.0750 3180.1060 4875.3857 8019.4033 14811.9961 | lr 4.2e-04 | norm 5661.1318 | dt 9.879 +type train | step 2038 | loss 122.1633 237.6768 360.6630 564.4849 819.6036 1164.8718 1613.4611 2299.3350 3235.3896 4991.1504 8169.0127 15066.9248 | lr 4.2e-04 | norm 5403.5547 | dt 9.879 +type train | step 2039 | loss 110.2649 213.0803 325.0363 521.8359 768.1774 1110.3070 1556.5227 2246.3550 3169.7974 4919.1748 8115.8379 15093.5381 | lr 4.2e-04 | norm 4853.6147 | dt 9.874 +type train | step 2040 | loss 103.1258 199.0969 310.9732 500.5165 740.6259 1084.7947 1530.6405 2208.7441 3137.8401 4903.8276 8146.4082 15117.4355 | lr 4.2e-04 | norm 4946.0986 | dt 9.862 +type train | step 2041 | loss 109.5068 210.4809 322.5090 511.4576 756.0817 1093.0488 1533.7223 2218.3777 3144.0820 4896.8999 8088.6978 14875.2324 | lr 4.2e-04 | norm 4895.0474 | dt 9.875 +type train | step 2042 | loss 111.2982 213.8898 330.6903 526.0713 778.1208 1121.7489 1567.5906 2259.4656 3193.7454 4936.9756 8116.1572 14862.8818 | lr 4.2e-04 | norm 5371.1509 | dt 9.892 +type train | step 2043 | loss 110.4540 212.8854 327.5853 522.5087 767.5939 1104.2489 1540.6598 2214.8237 3110.3767 4828.3994 7997.7451 14780.5312 | lr 4.2e-04 | norm 5045.3149 | dt 9.878 +type train | step 2044 | loss 112.8081 221.8833 339.6942 540.8259 788.5937 1142.0664 1583.1085 2262.6416 3182.6643 4916.4590 8096.4561 14916.3916 | lr 4.2e-04 | norm 5756.6875 | dt 9.866 +type train | step 2045 | loss 104.3036 198.2461 311.4249 501.7694 743.7409 1076.8547 1512.8483 2184.4023 3109.2629 4880.5625 8073.7734 15037.7412 | lr 4.2e-04 | norm 6059.1880 | dt 9.885 +type train | step 2046 | loss 110.0449 210.7637 327.3816 520.2019 766.8113 1106.0242 1539.2188 2207.3335 3107.5608 4843.6914 8086.6533 15181.9932 | lr 4.2e-04 | norm 5323.2109 | dt 9.884 +type train | step 2047 | loss 134.9527 261.8963 392.7976 608.7466 880.5814 1274.1261 1761.5217 2524.2471 3498.2656 5339.1553 8670.4863 15808.6973 | lr 4.1e-04 | norm 6499.0923 | dt 9.860 +type train | step 2048 | loss 109.8607 211.8077 334.2727 537.1769 791.8824 1132.6018 1582.6992 2263.8357 3221.4617 5011.2183 8377.5205 15555.1855 | lr 4.1e-04 | norm 5778.5781 | dt 9.874 +type train | step 2049 | loss 117.5277 228.8772 348.7954 549.2711 805.1190 1159.2577 1599.5247 2289.7302 3172.6855 4881.2383 8007.2671 14686.0664 | lr 4.1e-04 | norm 5952.4067 | dt 9.866 +type train | step 2050 | loss 107.1123 205.4020 319.9613 513.4849 764.6495 1105.1853 1545.9358 2216.6284 3130.8284 4840.5254 7949.7725 14551.0664 | lr 4.1e-04 | norm 5249.8086 | dt 9.887 +type train | step 2051 | loss 108.9791 205.0131 319.4144 514.6307 757.8622 1092.7195 1525.6285 2188.7517 3079.8792 4770.8359 7866.6787 14518.1377 | lr 4.1e-04 | norm 5289.6758 | dt 9.868 +type train | step 2052 | loss 111.4966 214.2874 327.3393 520.0271 764.9286 1102.0953 1539.6503 2211.8914 3115.9224 4822.2275 7963.5649 14666.5693 | lr 4.1e-04 | norm 5083.3623 | dt 9.900 +type train | step 2053 | loss 115.9628 222.6945 339.9221 536.5813 785.1476 1116.4669 1546.0961 2204.6658 3101.2783 4780.3765 7844.1001 14403.4414 | lr 4.1e-04 | norm 4421.0215 | dt 9.883 +type train | step 2054 | loss 109.2574 210.8316 325.6940 520.4061 766.6846 1108.8208 1547.1923 2219.3438 3135.4463 4861.5146 8043.2637 14819.8828 | lr 4.1e-04 | norm 5143.2095 | dt 9.868 +type train | step 2055 | loss 110.6222 212.4212 327.6697 525.9296 774.4064 1122.2035 1566.4288 2260.2097 3181.3252 4889.4907 8099.8726 14926.3252 | lr 4.1e-04 | norm 5687.3164 | dt 9.890 +type train | step 2056 | loss 106.9109 205.2796 324.1950 519.9478 761.3638 1103.9640 1545.7406 2238.4951 3153.4045 4882.5073 8069.6133 14973.5869 | lr 4.1e-04 | norm 7094.6465 | dt 9.847 +type train | step 2057 | loss 109.8849 209.4486 321.9057 512.2622 759.5590 1082.3142 1508.7356 2169.8616 3071.5400 4754.3384 7788.6416 14320.7422 | lr 4.1e-04 | norm 5211.5044 | dt 9.881 +type train | step 2058 | loss 110.2049 211.0743 324.0301 519.1402 766.2355 1114.6616 1563.4952 2261.3772 3165.0049 4859.9800 7959.3237 14555.8066 | lr 4.1e-04 | norm 5880.2114 | dt 9.882 +type train | step 2059 | loss 115.2210 218.9492 335.4514 530.0057 774.5397 1108.3074 1541.4592 2201.8889 3100.2510 4767.2163 7777.5962 14331.4746 | lr 4.1e-04 | norm 5938.4185 | dt 9.871 +type train | step 2060 | loss 108.4072 207.8594 321.0392 514.5054 760.1699 1088.7585 1520.0430 2195.1980 3104.4995 4855.1230 8023.3799 14889.9512 | lr 4.1e-04 | norm 5917.5957 | dt 9.868 +type train | step 2061 | loss 106.2587 207.6093 335.5107 543.6125 799.9348 1145.5154 1593.3032 2285.6746 3210.8413 4915.5474 8019.3218 14670.4697 | lr 4.1e-04 | norm 8086.5376 | dt 9.864 +type train | step 2062 | loss 104.0952 198.6116 309.5422 496.1747 738.7913 1072.8085 1500.0908 2166.4983 3081.1387 4819.5010 8012.2412 14847.7236 | lr 4.1e-04 | norm 6047.3755 | dt 9.870 +type train | step 2063 | loss 113.8427 218.7996 335.5049 533.2317 781.3714 1131.1050 1569.2391 2260.8120 3162.8672 4866.5840 7981.2788 14655.0557 | lr 4.1e-04 | norm 5048.9526 | dt 9.872 +type train | step 2064 | loss 106.7240 203.4928 313.8324 500.3589 741.2148 1074.7308 1505.6074 2182.1550 3093.2698 4804.8452 7954.5918 14631.4580 | lr 4.1e-04 | norm 5133.3696 | dt 9.873 +type train | step 2065 | loss 113.5631 220.6929 336.8165 535.2564 783.0939 1124.7968 1567.0752 2237.5977 3148.6514 4841.8950 7956.3506 14618.9619 | lr 4.1e-04 | norm 4962.2920 | dt 9.885 +type train | step 2066 | loss 113.2606 217.9778 334.2595 530.3069 780.3399 1127.5239 1572.7097 2251.8582 3166.0786 4891.6772 8059.5200 14800.6348 | lr 4.1e-04 | norm 5188.4570 | dt 9.885 +type train | step 2067 | loss 88.1169 167.8274 272.9743 453.0124 693.8901 1025.0295 1473.1770 2162.6021 3128.4600 4858.8003 7873.4434 14369.0234 | lr 4.1e-04 | norm 8305.9375 | dt 9.863 +type train | step 2068 | loss 110.0602 210.6035 322.2804 514.4969 755.1393 1097.3719 1533.2209 2199.6287 3091.4553 4747.0405 7806.2471 14280.5654 | lr 4.1e-04 | norm 5080.4731 | dt 9.858 +type train | step 2069 | loss 114.6916 218.5247 335.0191 533.9527 781.3387 1125.8087 1568.3042 2252.2783 3168.1235 4921.5337 8151.4600 15025.7402 | lr 4.1e-04 | norm 5194.5464 | dt 9.864 +type train | step 2070 | loss 102.6964 195.4303 308.9530 500.8306 746.4369 1088.9847 1526.2375 2218.8655 3136.3503 4861.4907 8046.8374 14843.7617 | lr 4.1e-04 | norm 5410.8159 | dt 9.876 +type train | step 2071 | loss 103.5149 196.7511 308.4342 495.8516 732.7388 1059.0074 1487.9479 2148.2175 3058.1057 4774.7329 7915.5835 14607.5293 | lr 4.1e-04 | norm 5123.1904 | dt 9.880 +type train | step 2072 | loss 104.9798 201.9395 310.0799 494.8853 737.6587 1065.1979 1492.6929 2163.8423 3051.1426 4755.8867 7910.8887 14529.9766 | lr 4.1e-04 | norm 5910.4814 | dt 9.871 +type train | step 2073 | loss 110.9155 212.9354 325.1314 518.4836 764.3392 1109.6547 1551.4303 2226.3503 3133.9060 4850.8013 8022.4087 14780.9492 | lr 4.1e-04 | norm 5206.8691 | dt 9.882 +type train | step 2074 | loss 111.3784 212.7547 328.7509 525.5392 778.6314 1117.5769 1553.9957 2209.7729 3102.9016 4798.1255 7907.3076 14538.9277 | lr 4.1e-04 | norm 4792.3896 | dt 9.877 +type train | step 2075 | loss 127.7459 243.7144 372.7866 592.8887 855.0735 1228.7930 1703.5476 2429.7314 3400.7913 5234.7817 8677.4805 16227.9902 | lr 4.1e-04 | norm 7527.6709 | dt 9.870 +type train | step 2076 | loss 109.7504 207.0242 318.6446 507.0545 748.5577 1089.9519 1522.1191 2199.7493 3105.8762 4858.9141 8111.1631 15086.9951 | lr 4.1e-04 | norm 5717.3369 | dt 9.864 +type train | step 2077 | loss 103.5152 198.2935 311.1508 502.3214 745.5726 1081.4698 1514.4430 2188.7722 3105.9402 4795.5781 7907.0283 14442.8574 | lr 4.1e-04 | norm 4919.9448 | dt 9.864 +type train | step 2078 | loss 106.5851 202.8804 311.8933 501.9195 743.7975 1079.6334 1521.0630 2193.6848 3094.7688 4796.8750 7921.0015 14588.6611 | lr 4.1e-04 | norm 5181.2051 | dt 9.869 +type train | step 2079 | loss 107.4009 204.9550 318.5490 510.1381 752.4259 1089.5066 1528.4019 2216.3428 3114.3008 4829.9399 7969.5898 14637.2363 | lr 4.1e-04 | norm 5050.3081 | dt 9.883 +type train | step 2080 | loss 120.1839 230.9852 355.5153 571.6553 844.6699 1225.9539 1720.1606 2487.6516 3474.3010 5353.4775 8849.5557 16340.0195 | lr 4.1e-04 | norm 7609.5493 | dt 9.868 +type train | step 2081 | loss 113.6867 216.3685 329.0350 520.5974 768.3376 1119.5367 1565.2262 2259.4888 3166.0010 4909.3184 8090.7192 14861.1738 | lr 4.1e-04 | norm 5766.2866 | dt 9.883 +type train | step 2082 | loss 108.0544 206.5042 317.6649 507.2622 749.5545 1084.8767 1520.3191 2197.7671 3088.5874 4764.9131 7826.3042 14313.7695 | lr 4.1e-04 | norm 5846.1045 | dt 9.866 +type train | step 2083 | loss 111.1188 211.9346 327.2235 525.2800 772.4793 1120.0144 1556.5063 2241.7012 3143.9756 4861.6738 8001.6895 14568.4932 | lr 4.1e-04 | norm 5461.1504 | dt 9.886 +type train | step 2084 | loss 117.7138 224.7233 336.9320 531.7335 773.8358 1124.2555 1553.9088 2233.7332 3105.1206 4784.7588 7859.4336 14351.9541 | lr 4.1e-04 | norm 5289.2065 | dt 9.867 +type train | step 2085 | loss 128.8350 248.5755 378.7794 592.0113 850.3505 1231.2001 1712.3655 2449.0911 3388.7505 5214.1211 8468.3184 15367.4619 | lr 4.1e-04 | norm 6802.3599 | dt 9.862 +type train | step 2086 | loss 109.2649 209.1268 324.0144 521.3013 768.6460 1109.0498 1542.0618 2214.4412 3135.2510 4849.7285 7973.7212 14583.4746 | lr 4.1e-04 | norm 5092.5815 | dt 9.893 +type train | step 2087 | loss 111.4864 213.0170 327.8821 520.1377 770.0807 1116.0483 1558.8899 2235.6577 3152.4082 4891.6182 8071.1953 14828.9932 | lr 4.1e-04 | norm 6074.8984 | dt 9.868 +type train | step 2088 | loss 117.6844 226.6876 343.1438 538.8680 784.9523 1121.4121 1551.2980 2224.0134 3134.4431 4849.0137 7975.4248 14665.3281 | lr 4.1e-04 | norm 7352.0801 | dt 9.867 +type train | step 2089 | loss 107.3698 207.0853 323.5508 521.5205 772.6773 1111.3385 1558.1331 2235.6758 3155.8445 4880.4365 8034.1694 14689.4668 | lr 4.1e-04 | norm 5165.8555 | dt 9.888 +type train | step 2090 | loss 110.8759 211.3322 323.7134 514.3453 762.1686 1105.2366 1547.6584 2236.5596 3144.7297 4900.6924 8129.4502 14958.2734 | lr 4.1e-04 | norm 5491.6211 | dt 9.874 +type train | step 2091 | loss 103.7711 198.2184 306.2107 494.1759 732.3550 1055.9225 1477.8065 2136.9084 3038.2253 4729.5967 7802.8877 14328.0918 | lr 4.1e-04 | norm 5312.1284 | dt 9.884 +type train | step 2092 | loss 111.1883 212.9655 325.9376 518.1924 760.4022 1102.0610 1538.0721 2204.8582 3087.6465 4763.5249 7835.2676 14445.2188 | lr 4.1e-04 | norm 6064.1665 | dt 9.882 +type train | step 2093 | loss 107.7796 203.9961 315.6518 505.7067 747.6660 1078.3187 1509.2439 2172.4082 3082.5459 4776.1646 7917.8481 14508.0459 | lr 4.1e-04 | norm 4830.8076 | dt 9.865 +type train | step 2094 | loss 109.6517 210.4953 323.6984 513.5340 756.6368 1091.1884 1524.9462 2195.9314 3094.8201 4799.2578 7940.9072 14623.4717 | lr 4.1e-04 | norm 5326.9609 | dt 9.876 +type train | step 2095 | loss 113.3324 216.4390 331.5893 528.5634 777.4363 1117.4504 1555.2614 2229.2515 3113.6670 4826.1328 7976.1357 14701.2178 | lr 4.1e-04 | norm 5307.3179 | dt 9.878 +type train | step 2096 | loss 115.4431 220.0340 332.7585 527.0628 772.4572 1104.6797 1525.3644 2180.1294 3023.6262 4639.0459 7557.5894 13844.5361 | lr 4.1e-04 | norm 6067.3848 | dt 9.879 +type train | step 2097 | loss 109.4773 206.2165 320.2961 511.5702 760.6504 1112.7444 1562.7610 2276.4844 3208.1682 4987.1943 8181.8823 14994.5576 | lr 4.1e-04 | norm 5202.2793 | dt 9.871 +type train | step 2098 | loss 101.7387 194.6620 304.9529 491.0010 730.2201 1066.8517 1502.5663 2165.7673 3071.3694 4748.4829 7834.9658 14283.9512 | lr 4.1e-04 | norm 4776.7012 | dt 9.876 +type train | step 2099 | loss 114.4358 218.9360 334.9767 532.0624 783.2477 1144.2300 1597.8220 2317.5159 3222.6614 4971.7407 8194.2188 15087.7646 | lr 4.1e-04 | norm 5999.4971 | dt 9.874 +type train | step 2100 | loss 110.3317 210.2898 325.0262 519.7658 764.3147 1115.7979 1564.3419 2254.2974 3164.6597 4884.0000 8093.2031 14953.6777 | lr 4.1e-04 | norm 5201.5020 | dt 9.884 +type train | step 2101 | loss 110.5414 210.1979 329.5977 532.4807 783.6731 1142.4344 1589.4528 2285.8899 3178.9519 4915.5483 8132.7598 15065.8154 | lr 4.1e-04 | norm 6451.2510 | dt 9.877 +type train | step 2102 | loss 117.4685 226.7145 343.2763 544.3182 798.3023 1146.5830 1590.7103 2278.2139 3184.7446 4919.0249 8125.4922 14849.2959 | lr 4.1e-04 | norm 6714.5552 | dt 9.877 +type train | step 2103 | loss 116.5763 223.9740 336.0782 530.0197 773.9944 1117.7041 1557.8132 2257.8191 3174.6401 4949.4053 8256.1572 15295.7051 | lr 4.1e-04 | norm 6092.7949 | dt 9.854 +type train | step 2104 | loss 98.3811 188.0280 297.5923 480.0521 718.6335 1047.6395 1471.8702 2133.2952 3045.6702 4746.4878 7870.6245 14497.2422 | lr 4.1e-04 | norm 5066.7896 | dt 9.867 +type train | step 2105 | loss 119.9337 228.8398 358.1344 571.2327 839.8804 1220.3340 1699.6694 2473.9812 3439.2178 5352.3789 8881.0430 16615.4766 | lr 4.1e-04 | norm 10394.4355 | dt 9.842 +type train | step 2106 | loss 110.1770 208.7874 324.6272 525.9825 775.9070 1140.2642 1600.6335 2322.9714 3241.1748 5052.0176 8334.6787 15214.3848 | lr 4.1e-04 | norm 6465.5303 | dt 9.855 +type train | step 2107 | loss 111.2463 213.7956 327.1749 521.0828 767.4884 1116.8939 1563.3038 2259.4250 3157.7422 4895.8340 8071.7075 14774.9648 | lr 4.1e-04 | norm 5516.3564 | dt 9.882 +type train | step 2108 | loss 105.3443 202.2174 313.0694 504.1730 749.3594 1085.1880 1527.9524 2226.8284 3160.6885 4909.5088 8124.3135 14959.1025 | lr 4.1e-04 | norm 6282.6802 | dt 9.875 +type train | step 2109 | loss 110.8744 215.6516 332.5934 528.4442 778.2921 1132.1344 1580.9176 2283.4143 3215.7849 4993.7817 8283.7695 15222.4941 | lr 4.1e-04 | norm 5621.5947 | dt 9.872 +type train | step 2110 | loss 108.9089 204.8169 316.8412 508.3780 750.5684 1095.8103 1540.3529 2234.8940 3146.4016 4874.4868 8046.9941 14724.6846 | lr 4.1e-04 | norm 5878.4775 | dt 9.871 +type train | step 2111 | loss 114.6141 224.2001 352.5181 567.2051 831.9573 1204.9275 1673.7727 2413.7231 3349.0940 5189.9043 8562.4082 15758.3174 | lr 4.1e-04 | norm 7752.0723 | dt 9.869 +type train | step 2112 | loss 107.2089 204.7808 312.5716 502.7005 742.7872 1080.4617 1509.8055 2173.6226 3043.7581 4717.7734 7790.8584 14356.4746 | lr 4.1e-04 | norm 5517.8794 | dt 9.865 +type train | step 2113 | loss 108.2723 206.4583 315.7375 503.9980 747.4437 1101.7378 1558.5347 2252.8301 3159.8420 4904.0259 8115.2266 14979.7734 | lr 4.1e-04 | norm 5754.0205 | dt 9.866 +type train | step 2114 | loss 112.2005 212.9910 328.7532 531.3306 776.0491 1126.1163 1562.4357 2236.8264 3124.4568 4814.9663 7889.2656 14529.2451 | lr 4.1e-04 | norm 6957.2852 | dt 9.851 +type train | step 2115 | loss 100.9227 192.9240 299.7762 485.0030 724.0153 1046.8325 1471.3094 2122.4578 3014.0742 4706.2646 7790.7656 14231.9727 | lr 4.1e-04 | norm 5132.4053 | dt 9.878 +type train | step 2116 | loss 111.1850 210.9577 324.4507 513.7158 753.1901 1083.6162 1504.4812 2154.2720 3034.1724 4677.4185 7740.5898 14216.9404 | lr 4.1e-04 | norm 4634.9795 | dt 9.867 +type train | step 2117 | loss 110.6834 212.4470 326.8074 519.9412 764.6003 1100.5770 1534.4326 2209.4285 3121.6660 4839.2358 7958.2007 14517.8496 | lr 4.1e-04 | norm 4605.6035 | dt 9.883 +type train | step 2118 | loss 105.3853 200.8788 313.6026 505.8949 740.0585 1075.0117 1501.8240 2162.0410 3037.1902 4724.6982 7898.7021 14637.9629 | lr 4.1e-04 | norm 6352.4893 | dt 9.871 +type train | step 2119 | loss 106.5765 203.8957 319.9812 512.7329 756.3174 1091.4553 1525.6545 2193.9241 3114.7671 4835.4897 8055.4810 14769.0732 | lr 4.1e-04 | norm 5823.4194 | dt 9.879 +type train | step 2120 | loss 103.0531 197.4851 310.8312 504.2209 749.4500 1091.7946 1533.6047 2213.6672 3139.1440 4895.2178 8144.8564 14967.9541 | lr 4.1e-04 | norm 5492.7090 | dt 9.874 +type train | step 2121 | loss 118.8815 228.3634 347.0967 547.3555 796.0364 1142.1140 1588.3044 2269.7815 3178.3225 4905.2021 8122.8525 14990.1133 | lr 4.1e-04 | norm 5529.9082 | dt 9.880 +type train | step 2122 | loss 106.4977 203.9990 314.7570 506.2487 750.8193 1094.6617 1532.6936 2213.7415 3117.7739 4824.3721 7996.2603 14630.8057 | lr 4.1e-04 | norm 5300.1318 | dt 9.853 +type train | step 2123 | loss 113.7761 217.8107 331.9203 530.0391 776.8890 1123.0016 1570.9592 2278.2837 3161.9390 4897.0200 8092.3184 14825.6719 | lr 4.1e-04 | norm 6139.7207 | dt 9.855 +type train | step 2124 | loss 110.6471 211.5988 322.4226 516.2562 757.5236 1095.2715 1530.6006 2215.1912 3134.2109 4893.2778 8088.2690 14832.7559 | lr 4.1e-04 | norm 5287.5488 | dt 9.885 +type train | step 2125 | loss 109.9307 210.9423 324.9100 518.1271 763.3602 1106.2152 1550.5135 2230.8367 3153.5210 4879.0068 8032.6348 14549.4502 | lr 4.1e-04 | norm 5236.0581 | dt 9.869 +type train | step 2126 | loss 121.8723 238.4195 369.4880 583.0844 857.7657 1229.2695 1727.1091 2479.7383 3521.3530 5334.2593 8531.3447 15238.3701 | lr 4.1e-04 | norm 9808.1270 | dt 9.877 +type train | step 2127 | loss 122.8248 236.3825 364.4511 576.9853 839.8530 1198.8126 1651.1841 2348.2769 3276.6304 5007.0718 8226.4844 15060.9746 | lr 4.1e-04 | norm 9835.6855 | dt 9.855 +type train | step 2128 | loss 111.4195 215.2915 333.6943 532.4416 782.3225 1122.3995 1559.1780 2235.9670 3128.3149 4827.5679 7962.1509 14539.8906 | lr 4.0e-04 | norm 5644.3291 | dt 9.880 +type train | step 2129 | loss 100.9355 194.2372 307.4555 503.3150 748.3351 1096.9375 1553.7173 2259.5476 3214.9431 5020.4937 8307.6475 15229.6641 | lr 4.0e-04 | norm 7587.5049 | dt 9.856 +type train | step 2130 | loss 102.2397 197.3770 306.8987 491.5662 729.8083 1062.4349 1490.5818 2163.0557 3077.8320 4835.0220 8021.7847 14755.0508 | lr 4.0e-04 | norm 6398.8667 | dt 9.862 +type train | step 2131 | loss 111.9000 211.2043 314.7472 493.1341 734.1023 1063.1964 1502.7214 2182.3669 3060.4949 4730.8184 7682.7661 14152.1445 | lr 4.0e-04 | norm 12490.1436 | dt 9.859 +type train | step 2132 | loss 115.9977 224.9726 344.4704 548.4692 796.6039 1144.1226 1581.6910 2251.4739 3156.1650 4914.4829 8103.8105 14908.7549 | lr 4.0e-04 | norm 6373.6406 | dt 9.862 +type train | step 2133 | loss 108.4943 207.5294 319.6865 512.2073 752.4313 1088.2047 1520.4163 2191.7632 3082.4104 4817.9209 8042.5801 14820.7021 | lr 4.0e-04 | norm 5944.1328 | dt 9.876 +type train | step 2134 | loss 108.7220 209.9369 325.0927 523.9029 777.3990 1130.9023 1585.8575 2286.0366 3208.4209 4957.1665 8154.0615 14857.7129 | lr 4.0e-04 | norm 5442.9390 | dt 9.869 +type train | step 2135 | loss 107.8334 206.1115 320.8700 518.7897 769.3889 1134.3018 1587.7939 2312.6907 3261.3064 5071.3569 8437.5684 15494.2432 | lr 4.0e-04 | norm 6559.6270 | dt 9.864 +type train | step 2136 | loss 105.6923 202.5102 311.8307 501.8973 745.7740 1075.6104 1508.2365 2166.0054 3065.7888 4740.2773 7847.2275 14282.9844 | lr 4.0e-04 | norm 5218.1968 | dt 9.879 +type train | step 2137 | loss 101.0768 193.4671 303.4908 491.0490 730.4511 1074.9802 1517.4951 2209.6379 3125.8926 4856.4595 8025.7559 14686.2529 | lr 4.0e-04 | norm 5461.4429 | dt 9.862 +type train | step 2138 | loss 102.1840 197.3728 310.0319 501.4246 744.2652 1079.3297 1520.6195 2194.6533 3125.3928 4828.9243 7902.9004 14376.9658 | lr 4.0e-04 | norm 5618.8594 | dt 9.873 +type train | step 2139 | loss 113.1744 218.0346 333.5463 533.4387 788.1153 1150.2866 1611.2014 2330.2507 3280.4836 5080.5649 8339.7217 15100.2949 | lr 4.0e-04 | norm 5159.8843 | dt 9.882 +type train | step 2140 | loss 100.3261 192.5307 301.9037 490.6834 731.1349 1063.1501 1497.0861 2167.0347 3088.4675 4821.3472 7947.6562 14472.8584 | lr 4.0e-04 | norm 4982.2393 | dt 9.875 +type train | step 2141 | loss 101.9967 194.3344 303.1804 490.5446 724.2500 1059.6234 1490.3496 2164.7671 3059.1111 4743.3896 7809.7729 14191.2461 | lr 4.0e-04 | norm 4589.7275 | dt 9.884 +type train | step 2142 | loss 128.6010 248.2892 368.6195 578.0098 825.9880 1168.8340 1618.7218 2303.0591 3236.9878 4963.8193 8125.6338 14751.5762 | lr 4.0e-04 | norm 13957.4736 | dt 9.863 +type train | step 2143 | loss 120.9745 235.3878 358.8725 566.9868 817.7805 1156.9463 1602.1248 2280.1086 3212.4229 4942.7119 8089.8784 14679.4717 | lr 4.0e-04 | norm 10129.9092 | dt 9.869 +type train | step 2144 | loss 105.6057 202.8511 315.6115 508.2881 751.7412 1083.4288 1516.8584 2174.3020 3077.0759 4778.8594 7928.4893 14546.2803 | lr 4.0e-04 | norm 5810.0181 | dt 9.878 +type train | step 2145 | loss 109.0763 210.3421 319.9405 510.8596 755.2230 1098.7714 1537.8229 2226.2766 3129.1458 4838.4844 7998.4097 14568.4688 | lr 4.0e-04 | norm 5734.4810 | dt 9.881 +type train | step 2146 | loss 107.9405 206.0777 318.5254 509.2345 750.3199 1087.6827 1518.3221 2187.7361 3088.5483 4773.5669 7851.6064 14352.6250 | lr 4.0e-04 | norm 5597.7212 | dt 9.884 +type train | step 2147 | loss 107.6885 207.0830 318.5237 513.0440 752.2079 1085.1641 1507.6538 2157.0962 3044.6006 4721.6377 7791.3633 14175.0859 | lr 4.0e-04 | norm 5455.5420 | dt 9.885 +type train | step 2148 | loss 102.4382 195.8692 307.7214 496.3199 735.8164 1067.8525 1497.2100 2158.1606 3059.3152 4754.5005 7850.5415 14332.4062 | lr 4.0e-04 | norm 5078.3286 | dt 9.880 +type train | step 2149 | loss 98.8449 189.5499 297.0229 483.3083 720.0454 1072.3264 1525.9934 2243.8552 3169.2529 4938.8062 8263.4189 15276.6670 | lr 4.0e-04 | norm 6030.5156 | dt 9.848 +type train | step 2150 | loss 102.1788 195.0596 303.6041 487.8112 722.0077 1038.9698 1461.6664 2098.6631 2976.9275 4624.2266 7664.9590 14057.0439 | lr 4.0e-04 | norm 4981.1021 | dt 9.869 +type train | step 2151 | loss 113.6037 217.9373 333.9398 527.6079 776.0844 1135.1564 1590.3665 2312.9187 3235.1355 5062.2734 8343.9707 15164.2432 | lr 4.0e-04 | norm 6320.8071 | dt 9.865 +type train | step 2152 | loss 116.8921 222.8889 337.8126 532.8168 778.2225 1114.2190 1551.5773 2215.5735 3126.4426 4852.3301 8039.3115 14738.5859 | lr 4.0e-04 | norm 5628.1143 | dt 9.882 +type train | step 2153 | loss 105.9511 202.4146 313.5352 498.8735 737.2034 1063.7620 1487.8953 2150.2239 3042.1743 4730.9619 7847.3535 14342.8906 | lr 4.0e-04 | norm 5161.3223 | dt 9.861 +type train | step 2154 | loss 94.7444 197.0105 322.2115 536.8797 803.9343 1148.1377 1613.9397 2324.1619 3349.0159 5228.2764 8622.0811 15906.6328 | lr 4.0e-04 | norm 10658.1641 | dt 9.856 +type train | step 2155 | loss 99.4988 207.6885 340.4605 563.0925 838.3581 1186.5488 1655.2095 2365.7495 3427.4436 5332.6821 8813.3545 16123.9297 | lr 4.0e-04 | norm 11778.0352 | dt 9.862 +type train | step 2156 | loss 103.4443 198.0253 311.7722 508.5766 751.4661 1105.0874 1546.7358 2268.8198 3162.6367 4906.5986 8177.7041 14997.2207 | lr 4.0e-04 | norm 7995.6753 | dt 9.870 +type train | step 2157 | loss 108.5009 211.1140 323.8186 517.4476 764.1797 1123.1365 1585.3669 2319.1931 3251.5493 5037.8350 8337.0322 15299.0029 | lr 4.0e-04 | norm 8003.4482 | dt 9.855 +type train | step 2158 | loss 109.2229 211.4150 326.0729 519.1794 762.2543 1094.7584 1529.7186 2186.0117 3080.2993 4756.5132 7863.1006 14298.3535 | lr 4.0e-04 | norm 6024.8687 | dt 9.880 +type train | step 2159 | loss 102.6684 196.6826 303.4301 489.3495 729.0126 1057.5104 1490.3053 2151.5552 3063.1807 4754.7363 7841.9453 14311.3877 | lr 4.0e-04 | norm 5943.8696 | dt 9.882 +type train | step 2160 | loss 119.0037 229.9858 349.7764 552.8447 808.0840 1160.8494 1602.7362 2269.6025 3151.1965 4801.5771 7866.5654 14275.1758 | lr 4.0e-04 | norm 7350.8950 | dt 9.868 +type train | step 2161 | loss 104.4257 200.5221 310.9110 502.1659 743.3167 1076.1647 1508.9966 2169.1938 3066.4724 4743.8994 7846.5474 14253.0576 | lr 4.0e-04 | norm 5224.7261 | dt 9.910 +type train | step 2162 | loss 103.7775 197.7449 306.3442 496.2966 736.2700 1077.8417 1517.2400 2198.3728 3127.5510 4902.2598 8144.5566 14896.5781 | lr 4.0e-04 | norm 6036.8076 | dt 9.893 +type train | step 2163 | loss 116.7835 222.5029 336.0424 533.7532 775.1021 1122.1028 1557.6957 2243.5002 3146.7134 4882.4458 8076.9785 14860.6240 | lr 4.0e-04 | norm 5326.0405 | dt 9.878 +type train | step 2164 | loss 121.3206 233.2245 353.2223 554.7300 807.2949 1170.9042 1621.5203 2322.4775 3225.1548 4955.9390 8142.3447 14733.5527 | lr 4.0e-04 | norm 5345.4141 | dt 9.906 +type train | step 2165 | loss 107.1407 208.0529 323.6010 523.6567 769.3807 1105.7461 1539.8934 2210.1562 3140.7583 4883.4849 8088.8335 14855.4785 | lr 4.0e-04 | norm 6591.7559 | dt 9.866 +type train | step 2166 | loss 96.5338 183.9238 292.6676 482.2314 721.2934 1055.7258 1492.8011 2168.3892 3092.0129 4839.8833 8087.9438 14838.1182 | lr 4.0e-04 | norm 6245.3872 | dt 9.871 +type train | step 2167 | loss 105.0498 200.1664 308.4622 496.1678 732.4376 1067.4310 1499.5775 2161.4502 3062.2341 4778.6924 7924.4795 14580.4854 | lr 4.0e-04 | norm 5889.5669 | dt 9.870 +type train | step 2168 | loss 110.3630 213.1920 326.2770 524.1078 768.6336 1116.5107 1557.8175 2249.8333 3144.6433 4895.2832 8154.4531 15034.4717 | lr 4.0e-04 | norm 6771.8330 | dt 9.865 +type train | step 2169 | loss 116.2304 219.7659 338.6674 543.8277 790.1195 1155.0972 1602.8220 2308.3811 3197.6165 4978.4058 8262.2686 15357.6250 | lr 4.0e-04 | norm 7504.0498 | dt 9.883 +type train | step 2170 | loss 119.8538 229.3246 337.9641 536.1332 790.3568 1148.5186 1608.6395 2321.0110 3254.0989 5012.0508 8188.0210 14625.0771 | lr 4.0e-04 | norm 6032.2070 | dt 9.927 +type train | step 2171 | loss 114.3993 220.0952 337.0732 534.9291 781.9694 1130.3214 1573.1282 2262.1763 3167.2661 4856.3037 7979.9795 14435.0869 | lr 4.0e-04 | norm 5507.6323 | dt 9.993 +type train | step 2172 | loss 99.0302 190.0748 296.0703 481.5320 716.6793 1033.9290 1456.3882 2097.8972 2991.1628 4636.2959 7639.4102 13867.1572 | lr 4.0e-04 | norm 4615.0830 | dt 9.897 +type train | step 2173 | loss 109.4044 209.4899 318.4034 507.9519 749.3548 1094.4031 1539.5803 2225.3987 3126.1924 4814.8594 7895.1929 14286.4795 | lr 4.0e-04 | norm 4689.2637 | dt 9.867 +type train | step 2174 | loss 117.7497 228.0500 343.4396 541.3130 796.4680 1187.3752 1675.5778 2411.9500 3324.6016 5032.0264 8239.1914 15028.0117 | lr 4.0e-04 | norm 6212.8184 | dt 9.859 +type train | step 2175 | loss 111.9564 214.4196 334.1533 541.1387 792.1107 1136.8628 1582.8151 2266.0876 3177.0872 4918.7417 8119.2300 14944.1514 | lr 4.0e-04 | norm 5637.1235 | dt 9.886 +type train | step 2176 | loss 112.3651 215.0383 327.3099 523.1904 769.1138 1103.1638 1532.9115 2187.6675 3069.4299 4727.1133 7770.0967 14045.5850 | lr 4.0e-04 | norm 6355.2383 | dt 9.885 +type train | step 2177 | loss 103.8196 197.8105 307.9827 496.6134 738.1334 1064.0638 1489.5074 2145.4604 3030.2939 4681.1187 7717.5176 13990.3643 | lr 4.0e-04 | norm 5238.6890 | dt 9.894 +type train | step 2178 | loss 112.4436 215.8025 325.5327 518.1022 758.3557 1109.9120 1555.9921 2271.2964 3189.5903 4943.2407 8223.6455 14993.9551 | lr 4.0e-04 | norm 6058.9321 | dt 9.868 +type train | step 2179 | loss 111.3123 214.1903 327.6752 526.2770 772.5251 1117.3741 1560.0088 2253.9670 3169.3020 4860.6577 7994.5049 14487.2646 | lr 4.0e-04 | norm 5539.9756 | dt 9.881 +type train | step 2180 | loss 105.6591 202.2640 312.9821 503.6571 744.3307 1082.0066 1514.7112 2187.4431 3087.1558 4798.7393 7943.0415 14553.9238 | lr 4.0e-04 | norm 5393.9497 | dt 9.870 +type train | step 2181 | loss 107.1408 206.7350 321.8105 517.3698 763.0515 1094.4401 1530.2931 2193.1218 3117.8501 4833.7974 8027.4600 14624.7090 | lr 4.0e-04 | norm 4990.2368 | dt 9.874 +type train | step 2182 | loss 106.2976 203.2700 317.0360 511.1854 751.8458 1093.5808 1528.9603 2199.2070 3095.0347 4763.3447 7868.4912 14273.9307 | lr 4.0e-04 | norm 4790.0703 | dt 9.877 +type train | step 2183 | loss 109.7294 210.8054 323.9766 516.2294 759.5282 1108.1608 1549.8004 2249.2141 3138.3838 4867.0049 8088.5601 14893.8262 | lr 4.0e-04 | norm 5440.8623 | dt 9.871 +type train | step 2184 | loss 114.0099 218.4840 335.3923 531.0616 771.4832 1118.0574 1550.4923 2219.9956 3087.6621 4774.0723 7923.8018 14582.1641 | lr 4.0e-04 | norm 6222.9492 | dt 9.875 +type train | step 2185 | loss 108.0943 208.6249 320.8887 513.8987 757.2316 1100.1880 1534.7668 2215.2375 3134.7051 4850.8359 8036.0947 14581.9258 | lr 4.0e-04 | norm 4723.4023 | dt 9.877 +type train | step 2186 | loss 107.0570 205.4871 312.9136 501.0428 739.1206 1082.9828 1514.8887 2201.3538 3118.1714 4820.6514 7953.8633 14455.2822 | lr 4.0e-04 | norm 5219.8311 | dt 9.872 +type train | step 2187 | loss 96.5678 182.6091 288.3271 468.2795 700.5739 1014.5535 1431.8507 2065.1597 2937.9927 4549.4053 7526.7808 13681.7041 | lr 4.0e-04 | norm 5115.5430 | dt 9.873 +type train | step 2188 | loss 112.0262 215.3300 326.7747 525.6008 771.6671 1124.9036 1574.0487 2262.6824 3183.8091 4894.7188 8082.5347 14745.5088 | lr 4.0e-04 | norm 5002.1528 | dt 9.869 +type train | step 2189 | loss 119.9392 231.2558 360.5641 590.0954 863.8577 1271.2446 1759.9703 2542.1614 3453.3359 5263.1353 8553.8418 15618.0830 | lr 4.0e-04 | norm 8531.4814 | dt 9.847 +type train | step 2190 | loss 108.0601 208.7589 323.7139 519.0518 767.9509 1111.9750 1557.6216 2240.6284 3165.5747 4914.7847 8153.4570 14798.8701 | lr 4.0e-04 | norm 5200.2490 | dt 9.873 +type train | step 2191 | loss 107.5356 203.6875 314.5020 508.0698 746.3257 1085.0134 1522.5332 2202.0503 3086.6768 4761.1353 7874.1748 14385.6133 | lr 4.0e-04 | norm 6059.2866 | dt 9.881 +type train | step 2192 | loss 110.0121 215.0159 329.7908 524.9695 766.0338 1110.8916 1549.9353 2227.7422 3118.5581 4820.7261 7982.3418 14607.7568 | lr 4.0e-04 | norm 5446.8203 | dt 9.887 +type train | step 2193 | loss 116.5690 222.3862 339.3617 539.5702 786.4825 1155.9143 1620.2548 2359.4065 3278.1172 5066.7095 8461.1143 15649.2646 | lr 4.0e-04 | norm 6478.8691 | dt 9.879 +type train | step 2194 | loss 107.4329 205.9458 314.7550 502.7633 739.5050 1061.7585 1476.2196 2100.3787 2966.9297 4556.7529 7495.6924 13603.3750 | lr 4.0e-04 | norm 4797.1553 | dt 9.870 +type train | step 2195 | loss 114.9959 220.9723 334.1142 527.9346 768.9415 1111.0862 1544.8812 2225.5708 3102.1606 4774.4268 7869.1885 14247.5664 | lr 4.0e-04 | norm 4815.4648 | dt 9.887 +type train | step 2196 | loss 115.5612 220.1443 337.5680 534.2789 776.6302 1109.8208 1525.6516 2162.1790 2992.7527 4574.2725 7547.0254 13749.4082 | lr 4.0e-04 | norm 5935.6040 | dt 9.853 +type train | step 2197 | loss 106.7530 204.7919 313.8665 502.3554 738.3205 1066.6370 1491.1176 2147.8708 3026.2490 4680.2451 7724.1792 14026.4434 | lr 4.0e-04 | norm 4746.1523 | dt 9.878 +type train | step 2198 | loss 105.0379 200.1841 310.2320 497.6047 735.4166 1064.6898 1504.3926 2191.0828 3118.6809 4820.6343 7917.5186 14358.4951 | lr 4.0e-04 | norm 5417.2515 | dt 9.888 +type train | step 2199 | loss 107.6307 206.9145 323.0523 519.9522 765.8361 1111.4160 1546.8656 2218.1350 3127.9851 4807.8813 7958.8057 14388.4414 | lr 4.0e-04 | norm 5771.3062 | dt 9.885 +type train | step 2200 | loss 125.7394 241.5552 359.7261 564.2527 810.4734 1184.3706 1632.0955 2340.5857 3200.2915 4868.5718 7956.6670 14431.7383 | lr 4.0e-04 | norm 5845.5947 | dt 9.857 +type train | step 2201 | loss 110.7320 211.7984 327.9041 525.5541 771.6943 1117.3395 1558.4504 2233.1951 3153.8062 4889.1870 8050.2026 14736.4043 | lr 4.0e-04 | norm 5471.8691 | dt 9.870 +type train | step 2202 | loss 105.2766 201.6825 310.6961 499.7256 738.9426 1078.1918 1507.9349 2183.6292 3079.1543 4783.4365 7948.3604 14430.2451 | lr 4.0e-04 | norm 4738.0977 | dt 9.874 +type train | step 2203 | loss 103.4774 201.9211 317.7046 508.6598 762.7930 1105.8942 1553.0636 2251.9707 3228.0833 5048.3770 8398.2256 15145.5078 | lr 4.0e-04 | norm 10426.1553 | dt 9.861 +type train | step 2204 | loss 118.3926 229.4871 346.8499 544.8551 791.6350 1155.1592 1603.4595 2287.3567 3187.1230 4859.9062 7924.6646 14305.7363 | lr 4.0e-04 | norm 5157.7383 | dt 9.883 +type train | step 2205 | loss 106.4526 209.5818 328.4964 531.1130 780.3611 1133.8030 1574.9695 2269.9478 3193.7573 4944.3486 8236.0449 15179.7178 | lr 4.0e-04 | norm 7332.9238 | dt 9.880 +type train | step 2206 | loss 106.7996 207.2500 319.4921 515.4611 758.5921 1101.5140 1543.3625 2227.2849 3141.8445 4876.5054 8114.8320 14848.7373 | lr 3.9e-04 | norm 5810.5957 | dt 9.897 +type train | step 2207 | loss 115.5624 222.1900 333.4867 525.6930 771.4122 1112.3314 1545.3160 2227.0125 3120.0037 4786.1270 7845.2788 14119.8105 | lr 3.9e-04 | norm 6390.4614 | dt 9.877 +type train | step 2208 | loss 102.8196 198.2315 311.2016 506.6944 748.5746 1092.8356 1533.7003 2227.4070 3155.9365 4923.9277 8255.0674 15200.3154 | lr 3.9e-04 | norm 6786.3892 | dt 9.879 +type train | step 2209 | loss 98.2723 186.6045 297.0209 484.5600 720.5771 1055.5135 1488.0115 2164.5537 3073.5745 4795.9312 7965.2671 14481.5254 | lr 3.9e-04 | norm 4909.6094 | dt 9.894 +type train | step 2210 | loss 100.1893 192.8895 304.1959 490.5343 726.9470 1054.3678 1475.4463 2134.9866 3035.7715 4706.4590 7789.1465 14146.3818 | lr 3.9e-04 | norm 5077.6685 | dt 9.876 +type train | step 2211 | loss 99.4771 190.2219 298.4080 484.7521 721.3582 1051.9584 1481.4529 2145.6870 3045.9089 4732.6763 7838.3447 14257.8574 | lr 3.9e-04 | norm 5784.6709 | dt 9.878 +type train | step 2212 | loss 109.8173 211.2523 327.1136 523.9677 771.2391 1116.3448 1561.4353 2242.7659 3164.2856 4879.0225 8056.0332 14576.0303 | lr 3.9e-04 | norm 4646.1816 | dt 9.879 +type train | step 2213 | loss 105.3717 199.8892 311.8886 504.2654 745.7099 1087.2401 1535.6278 2232.2598 3146.6211 4895.7974 8099.5918 14770.5254 | lr 3.9e-04 | norm 5669.3022 | dt 9.872 +type train | step 2214 | loss 105.3096 201.4939 309.1067 494.6332 732.6657 1071.6876 1507.4991 2186.5251 3084.9812 4765.1919 7906.1943 14381.9482 | lr 3.9e-04 | norm 5211.2949 | dt 9.868 +type train | step 2215 | loss 105.6424 201.8185 316.3827 512.8725 763.1773 1108.5265 1565.6213 2261.5701 3196.2007 4951.8740 8184.4204 14973.9863 | lr 3.9e-04 | norm 6347.9863 | dt 9.886 +type train | step 2216 | loss 111.3413 211.6100 326.9431 522.9959 768.9952 1112.4257 1542.9124 2200.4678 3075.9856 4746.8569 7836.6738 14347.0283 | lr 3.9e-04 | norm 6811.7397 | dt 9.884 +type train | step 2217 | loss 114.1179 217.3222 332.1508 531.1061 773.9164 1115.9813 1547.7943 2205.9150 3095.1697 4731.7769 7778.9116 14110.4814 | lr 3.9e-04 | norm 4922.0503 | dt 9.865 +type train | step 2218 | loss 106.4237 202.3879 312.3014 501.5611 741.3434 1073.3645 1506.6187 2177.1011 3084.3640 4794.8091 7959.5708 14426.9902 | lr 3.9e-04 | norm 5648.2725 | dt 9.895 +type train | step 2219 | loss 111.0901 209.1799 317.2029 506.5209 739.5142 1069.0948 1489.3417 2145.6125 2991.2666 4640.4434 7734.1675 14210.4658 | lr 3.9e-04 | norm 6451.5947 | dt 9.863 +type train | step 2220 | loss 97.2252 186.0586 293.5620 481.2951 717.7996 1052.5188 1482.3612 2151.1062 3057.7607 4727.0518 7806.6089 14132.7217 | lr 3.9e-04 | norm 4877.3491 | dt 9.879 +type train | step 2221 | loss 101.0031 192.0024 300.1310 489.2789 724.1420 1054.1161 1486.5151 2149.5442 3037.8049 4708.7627 7805.4253 14271.6055 | lr 3.9e-04 | norm 5093.1221 | dt 9.877 +type train | step 2222 | loss 102.5222 196.6568 309.0519 497.6359 736.8809 1058.2312 1485.1234 2134.0205 3029.2966 4697.2524 7800.4087 14262.4170 | lr 3.9e-04 | norm 5143.3682 | dt 9.876 +type train | step 2223 | loss 110.1310 212.1787 325.4362 520.3696 762.3127 1107.7191 1550.6805 2221.9634 3117.2859 4794.5986 7937.5122 14435.6611 | lr 3.9e-04 | norm 5117.5029 | dt 9.885 +type train | step 2224 | loss 102.7566 200.7707 318.9758 521.3232 771.2814 1122.7855 1571.9202 2272.1726 3229.9785 4998.6685 8242.0752 15033.3936 | lr 3.9e-04 | norm 6860.9043 | dt 9.865 +type train | step 2225 | loss 104.7353 199.8654 311.2567 508.4779 754.1396 1105.2444 1560.1947 2279.5356 3213.9578 5007.3384 8285.8164 15072.8682 | lr 3.9e-04 | norm 6182.4561 | dt 9.850 +type train | step 2226 | loss 98.2160 186.7726 291.8778 475.2213 706.7856 1028.5392 1447.0554 2094.2300 2967.9709 4625.3965 7685.3149 13949.2568 | lr 3.9e-04 | norm 4784.3857 | dt 9.856 +type train | step 2227 | loss 105.7121 203.4885 312.9313 504.4760 744.7968 1076.1111 1518.2266 2190.4241 3086.2566 4768.2710 7898.6196 14293.1777 | lr 3.9e-04 | norm 4874.0386 | dt 9.892 +type train | step 2228 | loss 112.7799 219.0923 334.0202 527.0369 767.3683 1111.9695 1547.1807 2217.2637 3125.9824 4858.5850 8029.8623 14567.3496 | lr 3.9e-04 | norm 4796.4082 | dt 9.879 +type train | step 2229 | loss 103.1237 196.8861 306.4481 493.5490 732.0735 1064.5222 1500.6499 2174.9436 3078.7883 4800.9380 7963.0488 14458.3369 | lr 3.9e-04 | norm 4923.9805 | dt 9.871 +type train | step 2230 | loss 106.6323 206.2652 317.7134 509.8587 750.1339 1080.8789 1507.4601 2164.9587 3047.5068 4709.4912 7785.4683 14109.3496 | lr 3.9e-04 | norm 4460.5054 | dt 9.882 +type train | step 2231 | loss 97.6760 187.1943 294.6423 477.4515 714.6295 1040.4094 1472.9365 2133.4429 3034.3113 4711.9653 7787.5581 14261.2285 | lr 3.9e-04 | norm 5126.6631 | dt 9.871 +type train | step 2232 | loss 111.3078 216.1942 335.8334 533.8044 784.9788 1132.6748 1575.8491 2245.8464 3160.5107 4877.2573 8047.1470 14624.8164 | lr 3.9e-04 | norm 5782.4048 | dt 9.886 +type train | step 2233 | loss 108.2473 207.6095 321.4553 518.9613 760.9871 1097.5570 1529.0552 2191.0928 3091.4563 4757.7935 7886.5361 14352.7793 | lr 3.9e-04 | norm 4605.0063 | dt 9.889 +type train | step 2234 | loss 109.6146 209.8285 322.7902 518.8585 760.0538 1102.8248 1543.5603 2216.6213 3110.8594 4845.4126 8082.2856 14866.3721 | lr 3.9e-04 | norm 5242.9346 | dt 9.877 +type train | step 2235 | loss 112.1785 216.8047 332.6877 534.9315 783.4568 1139.3676 1589.5045 2273.8721 3188.0076 4905.0020 8158.7861 14933.3535 | lr 3.9e-04 | norm 5238.9854 | dt 9.897 +type train | step 2236 | loss 116.6711 227.2572 348.8827 550.2966 802.2197 1158.0609 1605.3115 2306.1631 3210.6682 4889.1782 8022.1382 14631.9014 | lr 3.9e-04 | norm 6553.6426 | dt 9.870 +type train | step 2237 | loss 109.8941 215.3107 333.1781 536.0070 787.7286 1130.3134 1576.5638 2255.0942 3205.0420 4982.2046 8321.0625 15278.9336 | lr 3.9e-04 | norm 5381.1113 | dt 9.880 +type train | step 2238 | loss 127.6783 246.4683 368.2481 579.1593 844.8495 1232.7400 1726.3312 2482.1968 3428.5176 5246.1450 8724.1172 16042.2510 | lr 3.9e-04 | norm 8696.3271 | dt 9.852 +type train | step 2239 | loss 131.5358 255.3838 383.3479 600.6894 878.5501 1293.0745 1812.8734 2628.6672 3541.7388 5359.0288 8918.9141 16204.1055 | lr 3.9e-04 | norm 12208.8438 | dt 9.836 +type train | step 2240 | loss 104.7364 202.7230 317.5037 516.8559 762.5599 1100.5081 1538.6044 2201.3167 3126.5557 4837.2031 8053.3574 14641.0469 | lr 3.9e-04 | norm 5327.7974 | dt 9.893 +type train | step 2241 | loss 112.4926 217.9034 335.3696 534.6793 780.2533 1127.4337 1561.0317 2232.9868 3138.2412 4806.8232 7952.8447 14458.5059 | lr 3.9e-04 | norm 5347.7524 | dt 9.893 +type train | step 2242 | loss 112.6840 218.1030 333.6708 531.8236 776.5861 1123.4780 1568.7681 2260.6440 3194.7256 4947.7861 8250.2305 15247.8145 | lr 3.9e-04 | norm 7179.3130 | dt 9.851 +type train | step 2243 | loss 112.9067 219.0970 334.1777 535.2740 784.4070 1133.2867 1578.9122 2252.6316 3140.6777 4852.7378 8020.0278 14649.9023 | lr 3.9e-04 | norm 5716.2075 | dt 9.887 +type train | step 2244 | loss 111.6216 214.1277 330.7048 529.4952 776.0996 1116.0212 1555.1823 2209.6484 3104.9106 4777.1431 7896.4014 14359.7646 | lr 3.9e-04 | norm 4752.3228 | dt 9.888 +type train | step 2245 | loss 121.6599 234.8981 350.0544 552.8290 801.3475 1167.9043 1619.6992 2319.0493 3211.2759 4965.9136 8237.2744 14998.0479 | lr 3.9e-04 | norm 6553.6733 | dt 9.881 +type train | step 2246 | loss 114.2938 220.8786 337.4770 537.7213 783.7761 1121.4725 1556.3995 2221.7305 3109.8533 4777.8540 7905.4058 14446.5332 | lr 3.9e-04 | norm 5038.5586 | dt 9.879 +type train | step 2247 | loss 125.9321 242.2737 362.0020 573.3574 828.3375 1225.7968 1712.8846 2486.6897 3355.7078 5127.3833 8498.9531 15773.7764 | lr 3.9e-04 | norm 10085.3076 | dt 9.875 +type train | step 2248 | loss 116.3569 224.8130 339.8929 541.1989 792.9188 1165.2866 1630.3395 2358.4001 3295.2964 5052.6865 8335.8809 15275.0195 | lr 3.9e-04 | norm 6112.0654 | dt 9.878 +type train | step 2249 | loss 108.7435 210.5658 325.6482 520.5950 768.4205 1116.7144 1558.1549 2234.4731 3160.0874 4871.1040 8085.6313 14738.7617 | lr 3.9e-04 | norm 5725.7207 | dt 9.881 +type train | step 2250 | loss 110.6212 215.8692 337.6446 546.6810 801.5213 1167.4760 1621.8191 2326.0754 3250.5237 4997.8701 8283.3516 15116.3076 | lr 3.9e-04 | norm 6286.5483 | dt 9.885 +type train | step 2251 | loss 109.7926 211.5584 325.8419 521.8058 763.7302 1099.5713 1539.3123 2201.9128 3103.7292 4799.4512 7978.3555 14474.5723 | lr 3.9e-04 | norm 5363.6782 | dt 9.872 +type train | step 2252 | loss 113.7264 219.9122 335.9065 535.6917 784.0039 1135.3516 1584.4468 2276.2710 3201.0120 4928.1182 8145.4395 14762.6299 | lr 3.9e-04 | norm 5382.7856 | dt 9.871 +type train | step 2253 | loss 109.8612 213.1687 334.4039 547.6096 802.4387 1165.7617 1638.7256 2339.3342 3328.0908 5213.7090 8792.1885 16571.4961 | lr 3.9e-04 | norm 12217.8115 | dt 9.872 +type train | step 2254 | loss 112.0094 216.7329 335.0187 538.6659 794.3776 1156.3624 1619.9852 2325.0798 3261.6531 4972.4873 8109.0767 14580.4648 | lr 3.9e-04 | norm 6387.0737 | dt 9.880 +type train | step 2255 | loss 111.3540 217.0648 334.6356 534.9595 784.4265 1125.3840 1563.7781 2226.2527 3151.9170 4828.5693 7897.1255 14187.4980 | lr 3.9e-04 | norm 4369.9038 | dt 9.892 +type train | step 2256 | loss 114.8532 226.9582 350.3483 561.9315 822.1711 1180.2332 1633.1538 2330.5063 3268.5881 5018.5474 8316.0527 15159.0635 | lr 3.9e-04 | norm 5716.2290 | dt 9.884 +type train | step 2257 | loss 111.5899 217.4988 334.5305 535.4332 783.9760 1132.2681 1565.1104 2235.7473 3128.1499 4817.7695 7924.6787 14329.5537 | lr 3.9e-04 | norm 4805.4951 | dt 9.874 +type train | step 2258 | loss 106.6704 206.2536 320.3558 518.0585 765.4776 1108.9808 1557.3588 2244.4661 3166.9453 4893.9287 7999.2925 14450.0615 | lr 3.9e-04 | norm 5276.6289 | dt 9.888 +type train | step 2259 | loss 112.9748 218.5379 341.2823 547.0822 802.3945 1155.3082 1606.1774 2295.7979 3236.9268 4953.2197 8129.9673 14669.8916 | lr 3.9e-04 | norm 4625.6118 | dt 9.885 +type train | step 2260 | loss 108.2701 213.5584 335.5560 544.7491 801.4980 1142.6725 1589.8900 2287.2834 3229.7849 4984.4297 8351.3789 15239.9785 | lr 3.9e-04 | norm 6638.6309 | dt 9.861 +type train | step 2261 | loss 115.3461 224.3509 344.1663 548.4747 804.5027 1144.3424 1590.7496 2254.0430 3164.4265 4850.5742 8064.5874 14732.2793 | lr 3.9e-04 | norm 6760.9243 | dt 9.875 +type train | step 2262 | loss 114.3008 225.4465 348.2906 555.4316 808.6553 1152.2916 1593.2504 2261.4978 3204.2834 4928.2451 8174.3291 14830.6074 | lr 3.9e-04 | norm 6095.5669 | dt 9.894 +type train | step 2263 | loss 106.9964 222.9362 364.7847 600.0520 877.8755 1251.8422 1746.1118 2522.8921 3605.6875 5611.0957 9296.2998 16861.1953 | lr 3.9e-04 | norm 16748.0098 | dt 9.858 +type train | step 2264 | loss 99.2140 199.5261 318.9913 527.0406 779.9534 1132.5814 1589.2229 2332.5132 3319.6211 5219.6431 8689.1895 15805.8652 | lr 3.9e-04 | norm 9046.9141 | dt 9.853 +type train | step 2265 | loss 110.9687 214.4580 331.2474 531.1415 778.0352 1118.9248 1556.8037 2218.6318 3110.2410 4781.2651 7863.5039 14261.3770 | lr 3.9e-04 | norm 5608.8154 | dt 9.877 +type train | step 2266 | loss 113.0622 218.4782 334.4877 528.0976 772.1064 1108.9006 1542.3096 2205.0625 3101.1914 4777.8848 7896.8618 14325.8750 | lr 3.9e-04 | norm 6077.9834 | dt 9.882 +type train | step 2267 | loss 107.4960 211.5936 329.1588 528.4334 781.9449 1142.9312 1599.8391 2315.4375 3259.4993 5017.9678 8303.8711 15156.8086 | lr 3.9e-04 | norm 6610.1279 | dt 9.882 +type train | step 2268 | loss 113.0202 220.3769 341.8401 544.2849 800.3672 1169.4897 1630.3235 2360.7324 3276.0872 5079.9976 8368.6553 15202.9717 | lr 3.9e-04 | norm 9001.6396 | dt 9.867 +type train | step 2269 | loss 113.8450 220.8078 341.5337 543.8085 793.7301 1137.8406 1583.4626 2261.3735 3181.0029 4905.4277 8133.1987 14880.3691 | lr 3.9e-04 | norm 6553.4551 | dt 9.887 +type train | step 2270 | loss 109.9516 210.9530 326.8787 521.7698 764.2548 1097.8312 1531.3188 2194.9976 3101.0437 4770.5762 7892.6177 14341.6602 | lr 3.9e-04 | norm 5428.3354 | dt 9.898 +type train | step 2271 | loss 111.9274 217.9989 335.8886 535.6458 783.8079 1121.6265 1553.1219 2216.0310 3127.3716 4795.8071 7928.6162 14380.0889 | lr 3.9e-04 | norm 5694.2588 | dt 9.883 +type train | step 2272 | loss 112.8343 217.2277 332.1149 530.2347 775.6201 1123.5055 1566.0032 2242.9399 3140.3665 4837.6045 8015.7578 14604.9434 | lr 3.9e-04 | norm 4936.7656 | dt 9.889 +type train | step 2273 | loss 118.6084 232.8393 357.4019 568.3772 821.5966 1186.5737 1640.5448 2343.3909 3256.8584 4992.7979 8301.3896 15116.4189 | lr 3.9e-04 | norm 5437.9556 | dt 9.885 +type train | step 2274 | loss 126.0498 245.6345 368.8356 576.9553 838.9281 1214.3887 1686.7195 2419.5432 3340.7776 5044.9443 8246.5342 14732.1875 | lr 3.9e-04 | norm 6816.0723 | dt 9.889 +type train | step 2275 | loss 115.7221 223.9960 346.6932 555.6589 810.7950 1169.8643 1631.1229 2333.1179 3273.5771 5051.9927 8391.5215 15425.3750 | lr 3.9e-04 | norm 6176.8364 | dt 9.889 +type train | step 2276 | loss 104.9746 203.2010 320.0443 521.3417 767.9661 1132.5634 1598.1631 2313.0854 3266.6377 5075.4575 8390.1025 15342.6699 | lr 3.9e-04 | norm 6391.8906 | dt 9.874 +type train | step 2277 | loss 108.4297 211.9957 327.3478 525.5869 771.9207 1117.2695 1564.2521 2240.4382 3152.8074 4826.2397 7907.7046 14334.9189 | lr 3.9e-04 | norm 6082.0601 | dt 9.885 +type train | step 2278 | loss 109.4297 211.5094 327.4478 523.8759 764.5401 1108.9583 1544.2402 2217.6096 3114.2075 4789.7700 7957.5986 14564.0840 | lr 3.9e-04 | norm 5378.0449 | dt 9.885 +type train | step 2279 | loss 116.9724 227.4074 347.0242 552.1990 801.2521 1149.5907 1592.7515 2277.3484 3170.1870 4868.6611 8075.9062 14747.8320 | lr 3.9e-04 | norm 6296.0430 | dt 10.181 +type train | step 2280 | loss 111.8631 213.8162 328.6898 526.0608 769.2120 1110.5125 1542.4916 2201.0430 3081.1738 4746.1587 7880.1157 14422.0928 | lr 3.9e-04 | norm 5046.2646 | dt 9.887 +type train | step 2281 | loss 106.0199 207.1183 320.1305 514.1230 758.5265 1094.0132 1531.1277 2204.0144 3113.0066 4795.8345 7907.9336 14349.0605 | lr 3.9e-04 | norm 5191.9185 | dt 9.886 +type train | step 2282 | loss 104.9139 203.6783 318.7214 516.4209 762.8066 1108.2794 1553.4408 2222.8584 3135.5320 4826.1333 7974.6396 14418.9258 | lr 3.8e-04 | norm 4689.8779 | dt 9.876 +type train | step 2283 | loss 113.7915 222.8389 346.5753 556.2977 811.0931 1179.3593 1642.3816 2363.2898 3286.5769 5077.9375 8453.2734 15297.2480 | lr 3.8e-04 | norm 5338.4775 | dt 9.879 +type train | step 2284 | loss 125.4724 238.5822 361.3409 566.4525 814.8696 1177.3584 1635.6693 2313.9978 3187.2705 4888.1602 8080.0664 14758.8418 | lr 3.8e-04 | norm 6813.8076 | dt 9.864 +type train | step 2285 | loss 111.6087 214.9243 328.1990 524.2407 766.9683 1110.3325 1540.6383 2209.5833 3101.3333 4763.0049 7877.8843 14249.3301 | lr 3.8e-04 | norm 5000.6904 | dt 9.884 +type train | step 2286 | loss 109.6113 215.0721 327.9398 521.4899 764.4487 1100.2710 1535.6899 2199.8550 3107.3130 4811.6753 7977.9316 14499.0869 | lr 3.8e-04 | norm 5572.5513 | dt 9.879 +type train | step 2287 | loss 113.2561 217.8337 340.8706 544.9020 796.4969 1158.5203 1618.1570 2315.7808 3215.9651 4974.7822 8316.2119 15174.1641 | lr 3.8e-04 | norm 6412.9707 | dt 9.881 +type train | step 2288 | loss 103.8186 200.7182 310.4843 506.2175 751.9117 1108.0138 1568.6862 2281.7905 3188.9988 4907.0986 8068.2324 14553.3672 | lr 3.8e-04 | norm 6142.9331 | dt 9.859 +type train | step 2289 | loss 111.5824 214.8045 327.9892 524.7180 766.6326 1104.4611 1544.9104 2223.9587 3128.8149 4818.9438 7947.3447 14344.1143 | lr 3.8e-04 | norm 5469.6699 | dt 9.869 +type train | step 2290 | loss 115.7770 225.4252 340.3677 539.8599 787.0815 1127.7341 1573.0350 2251.9287 3156.0171 4847.0815 7958.5396 14337.5293 | lr 3.8e-04 | norm 5916.7466 | dt 9.888 +type train | step 2291 | loss 103.0406 197.7889 310.9994 503.6049 746.4586 1083.1144 1523.3326 2195.7290 3114.5735 4819.0938 7967.6123 14484.5322 | lr 3.8e-04 | norm 5480.7456 | dt 9.876 +type train | step 2292 | loss 110.2500 210.0595 321.8730 517.5479 758.3674 1102.8533 1548.1143 2218.3652 3093.7146 4746.6631 7843.3525 14294.3994 | lr 3.8e-04 | norm 5772.9229 | dt 9.866 +type train | step 2293 | loss 108.5816 210.2336 326.1568 521.2471 768.1545 1098.4618 1532.4735 2196.0002 3102.7327 4787.9541 7889.1855 14338.3828 | lr 3.8e-04 | norm 4747.0396 | dt 9.890 +type train | step 2294 | loss 99.2490 193.6241 307.2397 499.7811 750.2092 1087.6056 1542.9443 2230.8828 3197.8538 4918.7583 8020.5532 14403.9033 | lr 3.8e-04 | norm 6877.5879 | dt 9.902 +type train | step 2295 | loss 120.0284 226.3062 343.2271 550.4378 801.2721 1173.0884 1624.6155 2334.6819 3237.4216 4971.3950 8181.3169 14844.3643 | lr 3.8e-04 | norm 6319.0327 | dt 9.876 +type train | step 2296 | loss 110.3714 213.6258 329.9276 531.5789 780.3848 1122.7030 1561.9288 2232.4087 3127.6902 4767.1572 7835.6929 14285.1543 | lr 3.8e-04 | norm 5465.5991 | dt 9.872 +type train | step 2297 | loss 111.5719 216.5118 332.5018 533.1198 779.8773 1131.8759 1570.7104 2253.9060 3173.7783 4893.4810 8119.4365 14684.3477 | lr 3.8e-04 | norm 5252.4131 | dt 9.898 +type train | step 2298 | loss 116.0541 228.6609 359.2419 590.4088 856.7558 1277.8500 1786.0127 2591.4854 3532.0361 5385.0200 8898.8896 16318.7832 | lr 3.8e-04 | norm 9945.5010 | dt 9.845 +type train | step 2299 | loss 101.6237 196.2024 309.6004 505.4229 747.8956 1084.1117 1518.9347 2173.7502 3081.2000 4765.0684 7919.3794 14355.6699 | lr 3.8e-04 | norm 4838.7476 | dt 9.885 +type train | step 2300 | loss 108.8309 210.0088 320.5296 517.0523 757.9630 1096.6371 1537.9309 2213.3252 3132.3694 4840.6123 8048.0273 14716.3457 | lr 3.8e-04 | norm 5915.8628 | dt 9.866 +type train | step 2301 | loss 104.8532 205.2031 321.2248 522.6658 773.8995 1113.8032 1557.1683 2228.7678 3155.4868 4864.9600 8046.0977 14610.2979 | lr 3.8e-04 | norm 6047.0127 | dt 9.879 +type train | step 2302 | loss 107.5081 210.6196 323.7033 519.7833 763.3538 1100.5704 1532.4475 2193.7642 3098.6104 4806.8271 7975.7012 14448.7129 | lr 3.8e-04 | norm 5738.8901 | dt 9.871 +type train | step 2303 | loss 118.0279 229.8951 351.8799 562.4162 815.9531 1170.5194 1612.2872 2299.1555 3198.1787 4873.6201 8008.7397 14541.6768 | lr 3.8e-04 | norm 7439.7734 | dt 9.882 +type train | step 2304 | loss 107.7315 209.3334 326.9796 525.1660 774.2471 1108.8420 1548.0431 2214.3625 3143.8650 4826.0537 7979.8242 14465.1592 | lr 3.8e-04 | norm 5530.8994 | dt 9.873 +type train | step 2305 | loss 108.4584 209.1361 325.1760 524.3777 770.1323 1109.2539 1544.6587 2205.3333 3109.8855 4783.5400 7902.6973 14352.4258 | lr 3.8e-04 | norm 5466.7471 | dt 9.881 +type train | step 2306 | loss 105.5406 201.9598 318.7396 518.4321 764.3837 1105.7200 1546.2196 2219.5203 3134.7466 4812.8745 7931.9365 14448.9150 | lr 3.8e-04 | norm 5230.5874 | dt 9.867 +type train | step 2307 | loss 98.3010 193.2193 311.2117 513.3022 765.4731 1111.8060 1566.3372 2272.1145 3261.5283 5075.1021 8437.9980 15318.3018 | lr 3.8e-04 | norm 7493.8657 | dt 9.870 +type train | step 2308 | loss 111.1533 212.8264 325.9196 521.1342 767.2627 1101.3658 1538.7723 2203.0955 3101.5266 4777.9229 7959.1855 14543.0781 | lr 3.8e-04 | norm 7023.4272 | dt 9.869 +type train | step 2309 | loss 119.3239 233.0107 358.3170 569.2374 827.1596 1181.8975 1650.8168 2349.7239 3279.9077 5025.6011 8348.8242 15349.1133 | lr 3.8e-04 | norm 6557.7007 | dt 9.877 +type train | step 2310 | loss 112.5764 219.0804 336.9467 536.5710 783.7213 1120.2108 1553.5264 2206.9380 3114.1433 4792.6611 7945.8496 14448.3398 | lr 3.8e-04 | norm 5035.3965 | dt 9.894 +type train | step 2311 | loss 112.2421 215.2364 330.6278 525.3492 770.3280 1109.8840 1547.7693 2196.8684 3066.8550 4704.1001 7751.3613 14018.5732 | lr 3.8e-04 | norm 5364.2095 | dt 9.891 +type train | step 2312 | loss 111.7088 214.5137 331.5407 535.7183 783.1100 1134.8829 1588.7905 2270.5032 3195.9377 4957.1982 8227.7705 15098.6221 | lr 3.8e-04 | norm 6026.6035 | dt 9.881 +type train | step 2313 | loss 107.9984 209.0079 326.4159 523.8679 769.2029 1102.9531 1536.0522 2192.5378 3103.3547 4789.5518 7955.9170 14514.3115 | lr 3.8e-04 | norm 6172.8057 | dt 9.884 +type train | step 2314 | loss 106.6488 207.2176 323.4126 522.8291 772.0889 1113.0814 1565.6188 2249.1472 3209.7446 4940.4819 8167.5869 14768.2969 | lr 3.8e-04 | norm 5290.3774 | dt 9.879 +type train | step 2315 | loss 110.5500 218.1445 338.8712 546.5257 797.6318 1149.9047 1599.4342 2287.3044 3217.7417 4942.5005 8142.5918 14615.9062 | lr 3.8e-04 | norm 5629.8477 | dt 9.882 +type train | step 2316 | loss 107.7362 208.5058 323.3964 521.1955 766.6311 1108.6838 1544.2129 2221.1826 3120.9971 4794.3672 7955.8760 14420.6914 | lr 3.8e-04 | norm 4945.1675 | dt 9.875 +type train | step 2317 | loss 106.8438 209.0742 326.5993 529.4713 776.3635 1135.3451 1588.3645 2290.7991 3205.9861 4963.6157 8310.8213 15308.2500 | lr 3.8e-04 | norm 5744.3203 | dt 9.875 +type train | step 2318 | loss 117.9293 229.0896 346.7229 550.2464 798.2494 1161.8462 1614.3893 2321.9868 3215.6665 4899.6880 8019.7129 14518.5244 | lr 3.8e-04 | norm 4556.7646 | dt 9.877 +type train | step 2319 | loss 103.3646 201.3176 316.6301 507.9724 755.3931 1093.7622 1533.3491 2207.0205 3127.4053 4852.7715 8015.3760 14426.8076 | lr 3.8e-04 | norm 5705.9033 | dt 9.883 +type train | step 2320 | loss 108.7887 212.4106 323.0751 518.6367 759.4994 1095.0685 1527.5671 2190.4922 3094.8003 4767.8647 7900.2441 14339.0107 | lr 3.8e-04 | norm 4981.4009 | dt 9.872 +type train | step 2321 | loss 113.1437 219.7267 335.8527 540.1059 791.4139 1152.2491 1605.6847 2314.0120 3265.6653 5018.6128 8275.0381 14901.5391 | lr 3.8e-04 | norm 5145.2275 | dt 9.891 +type train | step 2322 | loss 114.9349 220.7516 334.2697 530.4721 772.5376 1115.3438 1555.8771 2224.7671 3130.5222 4820.8311 7952.0718 14437.9248 | lr 3.8e-04 | norm 5508.0742 | dt 9.897 +type train | step 2323 | loss 110.2640 214.0297 327.4658 526.2339 769.2307 1106.0017 1544.6345 2207.7307 3108.0654 4796.1621 7927.1606 14398.9961 | lr 3.8e-04 | norm 4919.6382 | dt 9.904 +type train | step 2324 | loss 111.3472 213.1326 331.9640 536.9507 786.6637 1152.8516 1602.6233 2321.0271 3226.6675 4907.7539 8076.5098 14674.9746 | lr 3.8e-04 | norm 6464.4722 | dt 9.874 +type train | step 2325 | loss 103.6857 199.9996 310.8321 503.0661 745.3136 1086.8461 1526.6997 2208.3169 3080.3413 4755.0688 7884.5254 14607.3174 | lr 3.8e-04 | norm 8627.4639 | dt 9.882 +type train | step 2326 | loss 105.7126 208.0826 325.4255 528.0424 777.6408 1122.1035 1569.1042 2253.8040 3179.4131 4919.0938 8127.2080 14689.7666 | lr 3.8e-04 | norm 6177.6558 | dt 9.871 +type train | step 2327 | loss 116.3583 225.3072 345.7770 550.9981 807.6467 1168.8958 1626.6493 2339.9788 3281.0801 5022.0728 8273.0000 14897.3838 | lr 3.8e-04 | norm 5296.7739 | dt 9.890 +type train | step 2328 | loss 107.9820 210.1120 326.2061 526.0013 775.3847 1118.0078 1561.1395 2248.4370 3165.8259 4890.8066 8038.6104 14463.2441 | lr 3.8e-04 | norm 5051.6519 | dt 9.884 +type train | step 2329 | loss 114.1758 222.1104 338.6708 541.1470 784.5676 1124.8898 1559.8169 2225.4653 3101.6316 4754.2817 7882.7119 14323.5215 | lr 3.8e-04 | norm 6022.4600 | dt 9.876 +type train | step 2330 | loss 104.7220 202.4051 312.4100 501.7379 744.3116 1076.3608 1512.6221 2169.8562 3055.7334 4704.0967 7724.6948 14023.0000 | lr 3.8e-04 | norm 5516.2124 | dt 9.880 +type train | step 2331 | loss 106.4406 205.2479 318.2806 512.9615 755.3212 1099.6799 1547.9075 2239.3093 3133.5479 4830.3262 7927.9185 14302.6035 | lr 3.8e-04 | norm 5739.0903 | dt 9.870 +type train | step 2332 | loss 115.9407 221.8822 339.0168 536.9830 785.3447 1135.0629 1581.0498 2275.2822 3183.9541 4906.0874 8078.9888 14701.6318 | lr 3.8e-04 | norm 5439.0801 | dt 9.890 +type train | step 2333 | loss 99.8138 195.1002 306.0078 504.6490 747.8093 1106.1488 1567.9935 2284.3398 3212.7239 5026.5166 8440.7549 15650.5527 | lr 3.8e-04 | norm 7716.9453 | dt 9.860 +type train | step 2334 | loss 106.5202 205.5148 320.1124 513.5005 754.6506 1082.1321 1513.1266 2163.9187 3059.3013 4729.8848 7801.0034 14084.9082 | lr 3.8e-04 | norm 4757.4580 | dt 9.891 +type train | step 2335 | loss 111.2172 216.4465 331.6247 534.5895 784.7037 1143.4862 1596.8246 2302.3049 3218.0564 4949.5044 8141.4600 14707.9961 | lr 3.8e-04 | norm 5302.3965 | dt 9.869 +type train | step 2336 | loss 111.1268 213.4554 327.4977 528.6132 774.6918 1119.4216 1552.9152 2219.3818 3092.0159 4745.9971 7811.4961 14099.4346 | lr 3.8e-04 | norm 5104.1050 | dt 9.886 +type train | step 2337 | loss 110.7446 213.6623 328.3808 524.4076 767.6500 1110.2815 1544.9324 2215.9756 3112.4592 4772.1592 7875.0132 14207.8457 | lr 3.8e-04 | norm 4467.6812 | dt 9.893 +type train | step 2338 | loss 113.6553 223.1542 348.7206 560.9073 818.0260 1189.2146 1656.1410 2370.1421 3298.1387 5048.4619 8358.0352 15198.4023 | lr 3.8e-04 | norm 5595.2925 | dt 9.889 +type train | step 2339 | loss 111.1039 216.5484 338.0789 548.4608 801.5883 1166.9899 1635.8370 2359.9067 3305.6943 5103.4639 8446.8174 15302.7158 | lr 3.8e-04 | norm 5847.9414 | dt 9.871 +type train | step 2340 | loss 106.9548 207.6264 321.3852 517.1045 758.2679 1097.5192 1535.6647 2211.1208 3123.5359 4847.2207 8000.4175 14435.1123 | lr 3.8e-04 | norm 4796.5713 | dt 9.889 +type train | step 2341 | loss 108.1935 209.0687 323.1645 521.3218 766.0024 1108.2849 1546.2006 2222.9026 3123.3059 4801.2407 7952.3154 14353.0371 | lr 3.8e-04 | norm 4890.8364 | dt 9.874 +type train | step 2342 | loss 109.9350 210.7342 326.4369 525.6061 768.9784 1103.1575 1528.9048 2175.0049 3052.7507 4676.0928 7692.8428 13891.7070 | lr 3.8e-04 | norm 4431.9604 | dt 9.881 +type train | step 2343 | loss 106.1908 204.8502 317.2543 513.2534 756.0620 1101.1473 1545.5718 2230.7078 3159.1882 4852.9985 8038.7280 14577.6797 | lr 3.8e-04 | norm 5081.9829 | dt 9.885 +type train | step 2344 | loss 98.5207 189.9966 298.2232 489.6031 731.2823 1061.2122 1497.0764 2160.5715 3081.2205 4781.9316 7853.7104 14141.7041 | lr 3.8e-04 | norm 5176.1362 | dt 9.887 +type train | step 2345 | loss 105.4996 202.2652 316.0310 510.9264 753.2842 1089.8253 1531.3689 2218.4492 3141.7825 4869.8916 8103.8906 14769.8496 | lr 3.8e-04 | norm 5192.5137 | dt 9.866 +type train | step 2346 | loss 112.2148 219.1106 332.8513 534.0238 781.7362 1135.7240 1582.4731 2270.0933 3185.3064 4892.7627 8082.9067 14599.6494 | lr 3.8e-04 | norm 4162.4707 | dt 9.886 +type train | step 2347 | loss 109.0070 212.3060 328.4482 526.8055 769.7241 1108.0604 1540.4866 2205.6565 3101.7808 4787.4990 7970.9307 14505.7676 | lr 3.8e-04 | norm 4272.5991 | dt 9.882 +type train | step 2348 | loss 114.5714 220.9384 335.7227 533.6312 779.8947 1122.5881 1563.7275 2237.9507 3132.2405 4819.8110 7975.2476 14454.7500 | lr 3.8e-04 | norm 5977.9995 | dt 9.876 +type train | step 2349 | loss 105.6118 206.4069 321.3002 519.4951 762.5216 1103.6771 1547.6543 2220.3469 3156.1152 4873.3740 8075.2803 14589.1123 | lr 3.8e-04 | norm 5501.3921 | dt 9.893 +type train | step 2350 | loss 101.5363 198.7571 310.9443 508.7907 756.1366 1099.8687 1549.8796 2250.2090 3200.1519 4948.8599 8240.2461 14916.0127 | lr 3.8e-04 | norm 5679.1519 | dt 9.879 +type train | step 2351 | loss 115.2148 222.7611 341.2776 543.7194 789.8198 1126.1556 1556.6746 2212.0901 3104.9592 4754.8853 7897.4736 14311.6768 | lr 3.8e-04 | norm 4701.7197 | dt 9.874 +type train | step 2352 | loss 107.0092 207.8126 322.0688 516.1318 758.0999 1090.8549 1523.7910 2177.3506 3074.2727 4729.0166 7812.4199 14162.3369 | lr 3.8e-04 | norm 4913.7676 | dt 9.900 +type train | step 2353 | loss 105.7132 205.4579 317.9020 510.8512 752.7022 1082.9109 1514.5625 2167.5994 3067.8599 4743.3804 7835.2588 14188.9951 | lr 3.8e-04 | norm 4980.3257 | dt 9.901 +type train | step 2354 | loss 113.8811 220.2842 334.3723 529.4839 773.0828 1113.8008 1549.2336 2216.1511 3102.7446 4749.2378 7821.6812 14163.5176 | lr 3.8e-04 | norm 5005.2578 | dt 9.880 +type train | step 2355 | loss 107.6008 208.2903 323.7073 522.1322 767.3140 1114.7568 1558.2100 2232.0325 3136.7153 4826.8989 7949.8862 14286.0830 | lr 3.7e-04 | norm 4415.2026 | dt 9.878 +type train | step 2356 | loss 107.1313 209.5372 328.7067 534.0980 788.5027 1136.9369 1590.0459 2278.0166 3212.4504 4913.7568 8094.8672 14587.8574 | lr 3.7e-04 | norm 5021.5054 | dt 9.889 +type train | step 2357 | loss 104.1929 201.4295 314.2309 509.4953 750.8624 1085.2505 1521.6335 2187.1025 3093.1968 4754.3403 7878.4849 14274.1191 | lr 3.7e-04 | norm 5029.2280 | dt 9.894 +type train | step 2358 | loss 116.4193 224.5855 342.8760 548.0011 793.3516 1141.9678 1578.7268 2242.4966 3107.3181 4729.5640 7772.3442 14002.8066 | lr 3.7e-04 | norm 4816.5449 | dt 9.881 +type train | step 2359 | loss 106.9680 211.0449 334.0033 540.7825 794.9701 1143.5908 1586.6217 2265.4573 3201.6418 4903.4937 8085.7100 14573.3506 | lr 3.7e-04 | norm 4922.0640 | dt 9.874 +type train | step 2360 | loss 107.3856 206.5151 322.1085 519.9120 762.7026 1104.3058 1547.3385 2218.6084 3117.0144 4783.5137 7944.3633 14527.6494 | lr 3.7e-04 | norm 5467.3999 | dt 9.876 +type train | step 2361 | loss 108.4875 208.7001 322.8498 517.4108 758.9971 1093.4290 1525.6957 2184.5933 3087.1458 4772.1963 7885.0415 14336.2627 | lr 3.7e-04 | norm 4950.9600 | dt 9.881 +type train | step 2362 | loss 96.5484 184.3951 291.0213 482.8461 718.7744 1050.8259 1490.6232 2152.3545 3068.9917 4731.4824 7783.4385 14000.7793 | lr 3.7e-04 | norm 7568.2637 | dt 9.861 +type train | step 2363 | loss 112.6097 217.6107 338.6492 542.3517 795.8724 1151.1450 1611.9542 2311.7559 3237.3801 4988.3813 8294.7539 15029.9307 | lr 3.7e-04 | norm 4966.3008 | dt 9.889 +type train | step 2364 | loss 110.9196 216.5278 334.1899 536.4908 786.6226 1139.2493 1602.4346 2302.8726 3266.2747 5032.3672 8296.6904 15002.4180 | lr 3.7e-04 | norm 5168.3267 | dt 9.896 +type train | step 2365 | loss 100.9783 194.3125 306.2744 499.4958 742.5789 1074.7565 1505.9449 2166.9111 3085.6013 4782.2544 7886.3081 14208.5938 | lr 3.7e-04 | norm 4561.6216 | dt 9.890 +type train | step 2366 | loss 104.4826 201.9141 312.8197 506.4364 744.9130 1074.7982 1499.5587 2169.0020 3074.1792 4788.3218 7942.8540 14459.0859 | lr 3.7e-04 | norm 5857.8296 | dt 9.879 +type train | step 2367 | loss 111.4420 214.2464 332.0526 533.7758 780.6132 1122.8220 1564.3479 2235.6926 3144.7874 4817.0645 7919.6147 14265.1992 | lr 3.7e-04 | norm 4201.9702 | dt 9.888 +type train | step 2368 | loss 110.5356 213.2342 329.9078 529.4122 776.6714 1108.5129 1542.2750 2193.1104 3106.3594 4776.4688 7855.1548 14178.5020 | lr 3.7e-04 | norm 4693.4326 | dt 9.889 +type train | step 2369 | loss 108.9783 216.6639 339.8882 553.8410 812.1191 1174.1410 1633.6545 2335.9321 3264.4314 4972.4863 8187.3091 14772.6807 | lr 3.7e-04 | norm 5895.9263 | dt 9.888 +type train | step 2370 | loss 106.3533 209.6045 327.0953 527.5320 776.5359 1119.8989 1567.9294 2250.0024 3188.7026 4921.3560 8147.7593 14695.1670 | lr 3.7e-04 | norm 5602.3306 | dt 9.886 +type train | step 2371 | loss 107.3529 211.2434 326.2868 524.2532 765.4119 1112.2579 1548.8881 2225.7407 3120.9941 4816.7544 7949.8979 14289.2354 | lr 3.7e-04 | norm 4917.6421 | dt 9.871 +type train | step 2372 | loss 108.1519 207.8405 321.7187 516.2894 758.3780 1101.1350 1540.9877 2214.3152 3118.2664 4819.1191 7965.3628 14413.8398 | lr 3.7e-04 | norm 6017.1035 | dt 9.877 +type train | step 2373 | loss 114.2352 221.2657 336.5781 540.1696 785.2474 1127.8553 1565.4250 2236.8521 3121.2021 4821.7090 8024.7822 14594.3711 | lr 3.7e-04 | norm 6219.4917 | dt 9.880 +type train | step 2374 | loss 103.8544 203.8924 322.8568 525.8022 773.1001 1119.6288 1576.0303 2283.7639 3225.8333 5062.5762 8423.1514 15504.3721 | lr 3.7e-04 | norm 8070.6421 | dt 9.861 +type train | step 2375 | loss 106.5805 206.5426 318.8258 510.3051 752.9395 1094.2738 1536.0439 2204.1123 3119.8545 4796.8760 7906.3936 14203.0420 | lr 3.7e-04 | norm 4666.8599 | dt 9.889 +type train | step 2376 | loss 106.1114 204.3978 317.1959 511.4719 753.5298 1092.9583 1526.8463 2189.6211 3087.6494 4756.2964 7881.5122 14214.1543 | lr 3.7e-04 | norm 5293.6494 | dt 9.882 +type train | step 2377 | loss 121.3212 233.5121 354.8084 561.0297 817.0487 1150.5975 1602.8180 2268.5869 3200.7102 4868.9351 8013.2690 14457.3496 | lr 3.7e-04 | norm 7828.5566 | dt 9.921 +type train | step 2378 | loss 120.8233 235.5461 356.4237 563.5624 817.5051 1160.1873 1608.0056 2280.7568 3201.6392 4856.0972 7964.9038 14333.3203 | lr 3.7e-04 | norm 5921.7925 | dt 9.899 +type train | step 2379 | loss 107.8286 206.1395 317.7335 512.4799 755.3340 1086.3448 1515.8192 2190.8213 3122.2437 4853.8276 8068.7007 14825.4277 | lr 3.7e-04 | norm 10158.6299 | dt 9.873 +type train | step 2380 | loss 110.2645 213.8051 329.3730 525.0024 767.8783 1103.9962 1533.4318 2191.8921 3099.0981 4753.6958 7865.9111 14223.8730 | lr 3.7e-04 | norm 4871.3013 | dt 9.895 +type train | step 2381 | loss 105.3286 205.5529 318.5157 514.3807 755.9316 1095.5284 1533.9104 2206.1011 3118.3169 4806.9536 7936.4150 14255.7002 | lr 3.7e-04 | norm 4911.2300 | dt 9.889 +type train | step 2382 | loss 101.3316 198.3492 309.4677 506.6228 751.0643 1092.6196 1539.6879 2232.0620 3166.5054 4900.1973 8119.7197 14623.8359 | lr 3.7e-04 | norm 5062.4131 | dt 9.893 +type train | step 2383 | loss 112.6825 217.6622 332.5598 531.7939 774.0889 1124.3035 1568.3615 2251.4148 3146.5388 4855.1035 8015.5322 14634.6309 | lr 3.7e-04 | norm 5303.6206 | dt 9.886 +type train | step 2384 | loss 106.9214 207.4943 324.9321 524.7112 773.2915 1118.5461 1565.5120 2243.9634 3163.7654 4844.2231 7982.1133 14357.7158 | lr 3.7e-04 | norm 4782.5034 | dt 9.876 +type train | step 2385 | loss 107.1284 207.5526 316.6714 515.1508 761.1478 1112.2761 1560.8838 2264.3354 3214.5500 4959.7710 8212.0107 14973.1660 | lr 3.7e-04 | norm 7357.0640 | dt 9.855 +type train | step 2386 | loss 111.8235 218.1009 331.6780 531.1251 780.8096 1132.5863 1581.5806 2271.8054 3183.0801 4866.6504 7976.3252 14283.9160 | lr 3.7e-04 | norm 5230.1484 | dt 9.880 +type train | step 2387 | loss 104.2944 202.0029 316.0063 509.9708 751.0155 1085.1736 1518.3547 2179.5977 3090.7983 4793.3550 7954.8501 14391.0059 | lr 3.7e-04 | norm 5457.4683 | dt 9.889 +type train | step 2388 | loss 103.8206 202.2650 318.5271 516.8946 759.7184 1101.4709 1548.1858 2221.0034 3129.7568 4811.2192 7951.8174 14218.6504 | lr 3.7e-04 | norm 4948.6592 | dt 9.893 +type train | step 2389 | loss 109.5055 218.9116 344.2618 550.7764 805.6818 1160.7173 1624.0938 2336.4688 3309.4197 5131.3018 8549.4346 15565.6074 | lr 3.7e-04 | norm 7520.5483 | dt 9.874 +type train | step 2390 | loss 107.6606 210.1855 326.8158 526.6166 772.5120 1112.2457 1555.3744 2222.8748 3143.3086 4844.6328 8022.7920 14536.5605 | lr 3.7e-04 | norm 5252.2910 | dt 9.905 +type train | step 2391 | loss 103.0248 200.8960 310.7243 502.3283 742.3829 1074.0864 1509.7686 2177.7598 3088.6050 4777.8306 7893.8633 14132.8809 | lr 3.7e-04 | norm 4949.8149 | dt 9.869 +type train | step 2392 | loss 111.1282 218.9331 337.7676 546.0137 796.0603 1147.6028 1587.3716 2281.3550 3208.9783 4947.5649 8229.2734 14936.7695 | lr 3.7e-04 | norm 6953.9160 | dt 9.880 +type train | step 2393 | loss 108.3258 211.5670 326.5053 527.6597 772.4613 1108.7140 1539.1903 2198.0168 3077.5654 4724.9336 7775.4282 14101.1924 | lr 3.7e-04 | norm 5736.3569 | dt 9.893 +type train | step 2394 | loss 113.9846 218.6927 335.0766 536.6523 778.9733 1115.7172 1546.1425 2206.7717 3070.0613 4699.6934 7833.8853 14299.8760 | lr 3.7e-04 | norm 5402.2812 | dt 9.877 +type train | step 2395 | loss 119.5642 232.4158 350.2780 553.4232 804.9517 1159.7449 1610.4302 2294.0562 3160.7861 4801.6035 7885.9126 14292.1787 | lr 3.7e-04 | norm 5865.4790 | dt 9.885 +type train | step 2396 | loss 104.1064 203.0467 315.3397 512.5609 759.1248 1098.7061 1538.4166 2212.8257 3136.0500 4794.4175 7852.5674 14021.8525 | lr 3.7e-04 | norm 7652.1421 | dt 9.881 +type train | step 2397 | loss 111.9305 213.2309 322.6742 517.0624 755.8934 1099.2201 1533.6223 2199.9595 3072.5134 4733.0186 7861.0977 14185.5371 | lr 3.7e-04 | norm 5880.7964 | dt 9.878 +type train | step 2398 | loss 129.3094 244.6220 362.8454 574.8564 830.8734 1208.2288 1672.3206 2382.8191 3264.5930 4985.6646 8223.2598 14951.7939 | lr 3.7e-04 | norm 7688.0225 | dt 9.857 +type train | step 2399 | loss 114.4377 224.2562 340.5496 540.0458 785.2795 1145.2017 1596.7397 2302.4155 3210.4700 4947.3027 8111.1157 14557.2539 | lr 3.7e-04 | norm 6685.4717 | dt 9.877 +type train | step 2400 | loss 110.1725 213.2964 326.7642 521.7987 760.8116 1090.9011 1514.0126 2156.6704 3031.8647 4662.0840 7699.1230 13969.5488 | lr 3.7e-04 | norm 5306.0298 | dt 9.900 +type train | step 2401 | loss 110.4352 213.5619 330.2169 533.3066 781.6681 1123.1898 1565.0684 2239.9622 3162.3315 4829.7866 7955.8345 14355.8975 | lr 3.7e-04 | norm 5716.1553 | dt 9.889 +type train | step 2402 | loss 104.4331 205.1360 321.1959 523.1846 770.1778 1113.3079 1558.8420 2234.5835 3141.5283 4843.9927 7983.5083 14502.9482 | lr 3.7e-04 | norm 6277.6099 | dt 9.880 +type train | step 2403 | loss 108.1666 211.0181 326.8944 523.6956 767.8900 1099.9133 1526.7421 2167.9998 3060.4351 4700.2939 7739.1880 13962.1328 | lr 3.7e-04 | norm 4814.6406 | dt 9.894 +type train | step 2404 | loss 105.4713 208.8765 321.6842 522.8803 769.7928 1117.4194 1556.5580 2226.4802 3115.5571 4782.6172 7891.7061 14280.5664 | lr 3.7e-04 | norm 5253.1504 | dt 9.885 +type train | step 2405 | loss 111.4328 217.5315 338.4016 541.5034 789.7200 1151.5736 1617.8999 2328.1377 3264.4792 5004.5205 8235.2090 14833.6465 | lr 3.7e-04 | norm 5023.1431 | dt 9.879 +type train | step 2406 | loss 108.4269 212.5340 328.2670 531.3979 776.3859 1125.8695 1576.6777 2271.8748 3174.1821 4868.9917 8006.1748 14393.0020 | lr 3.7e-04 | norm 4773.9419 | dt 9.898 +type train | step 2407 | loss 110.4961 215.8552 329.9385 526.1302 764.1317 1107.6313 1539.1340 2196.7825 3056.2534 4675.4385 7663.5474 13744.5244 | lr 3.7e-04 | norm 5054.3252 | dt 9.879 +type train | step 2408 | loss 113.3184 218.7483 331.0853 532.7745 778.6158 1124.4857 1553.8652 2219.4834 3078.8054 4654.3096 7682.9297 13833.9785 | lr 3.7e-04 | norm 8568.6582 | dt 9.906 +type train | step 2409 | loss 120.1228 234.2997 353.4676 561.3411 809.4125 1171.9569 1625.5349 2343.6714 3270.9697 4994.7222 8212.5850 14723.3955 | lr 3.7e-04 | norm 6196.3433 | dt 9.867 +type train | step 2410 | loss 110.2159 215.3627 330.3960 526.2401 769.5092 1103.2023 1543.4812 2209.0645 3132.9280 4840.6396 7985.3755 14435.1826 | lr 3.7e-04 | norm 5122.8887 | dt 9.893 +type train | step 2411 | loss 106.0746 205.1476 314.9171 508.3298 749.0027 1077.5779 1507.6824 2144.3508 3025.1021 4637.0244 7696.1504 13914.5586 | lr 3.7e-04 | norm 5226.7856 | dt 9.894 +type train | step 2412 | loss 104.0451 201.0769 314.6097 511.4926 753.8777 1087.7032 1516.4919 2172.5469 3066.4858 4714.5679 7732.8374 13878.3037 | lr 3.7e-04 | norm 4947.0356 | dt 9.888 +type train | step 2413 | loss 112.6459 217.3639 333.6472 535.7524 778.2463 1112.5321 1546.1411 2198.5908 3066.1956 4705.3369 7718.5024 13916.3730 | lr 3.7e-04 | norm 5318.8892 | dt 9.882 +type train | step 2414 | loss 102.3758 199.5147 309.9940 501.6625 738.8666 1081.9889 1523.1907 2199.1995 3102.0654 4785.4839 7915.3921 14294.5928 | lr 3.7e-04 | norm 4736.9370 | dt 9.898 +type train | step 2415 | loss 104.5890 203.3870 320.2319 520.2668 766.7980 1121.1880 1578.2867 2285.8472 3225.3030 5014.1353 8355.4316 15251.0244 | lr 3.7e-04 | norm 5980.8301 | dt 9.885 +type train | step 2416 | loss 112.0033 220.2548 339.8834 542.6301 793.7429 1152.1493 1598.4050 2290.3188 3193.9856 4925.3672 8175.5498 14820.0879 | lr 3.7e-04 | norm 6253.6465 | dt 9.876 +type train | step 2417 | loss 102.3338 198.9343 309.7833 502.0322 739.6041 1066.2579 1490.0000 2132.2598 3016.1533 4660.3164 7721.5703 13887.1562 | lr 3.7e-04 | norm 4466.8022 | dt 9.891 +type train | step 2418 | loss 99.0125 191.5835 300.5521 490.8663 732.2919 1064.2628 1510.5762 2180.8931 3108.2029 4822.5059 7957.6465 14336.1299 | lr 3.7e-04 | norm 5510.9995 | dt 9.884 +type train | step 2419 | loss 102.4586 196.5401 307.8881 501.9548 738.6506 1070.5304 1503.9402 2163.7041 3050.9731 4696.1582 7787.4072 13973.3574 | lr 3.7e-04 | norm 4735.8228 | dt 9.879 +type train | step 2420 | loss 102.3226 198.7162 310.6071 500.9690 737.3942 1069.5500 1499.4209 2148.5784 3032.2554 4664.9307 7732.4033 13855.2549 | lr 3.7e-04 | norm 4935.9404 | dt 9.880 +type train | step 2421 | loss 101.5645 196.7766 309.1856 502.2126 743.7919 1084.9470 1523.2480 2197.6021 3105.5547 4797.1108 7924.9341 14259.3066 | lr 3.7e-04 | norm 5236.3633 | dt 9.879 +type train | step 2422 | loss 105.3768 204.6234 316.3947 508.3766 746.2230 1073.9437 1485.0265 2117.5552 2977.9087 4494.3755 7257.0298 12775.7539 | lr 3.7e-04 | norm 5150.6538 | dt 9.855 +type train | step 2423 | loss 116.2128 227.6890 352.6997 567.9719 829.0893 1228.1833 1743.2205 2565.0759 3546.3271 5374.1606 8648.7852 15192.7578 | lr 3.7e-04 | norm 5232.8950 | dt 9.853 +type train | step 2424 | loss 102.4831 198.5478 306.5601 496.3099 736.9562 1073.6282 1506.6005 2170.2969 3064.2939 4724.6826 7747.7446 13875.3438 | lr 3.7e-04 | norm 5575.8257 | dt 9.883 +type train | step 2425 | loss 114.0239 225.0666 342.7819 541.7728 791.9833 1135.9241 1577.4274 2243.7751 3137.1279 4817.4058 7879.1484 14006.2227 | lr 3.7e-04 | norm 6311.1631 | dt 9.883 +type train | step 2426 | loss 107.0618 207.6454 322.4527 518.8922 762.9657 1111.8092 1557.0894 2238.0151 3153.5779 4834.9111 8005.4834 14483.5977 | lr 3.7e-04 | norm 5646.2095 | dt 9.892 +type train | step 2427 | loss 101.5306 195.6457 304.9828 494.2044 731.5942 1069.2454 1507.0663 2174.7634 3081.7300 4746.6055 7821.4355 14030.3027 | lr 3.7e-04 | norm 5267.3188 | dt 9.877 +type train | step 2428 | loss 106.1277 207.5295 320.0654 517.3506 763.4248 1116.2742 1563.1733 2254.3967 3149.5850 4842.5396 8049.5879 14588.1797 | lr 3.6e-04 | norm 5502.9009 | dt 9.887 +type train | step 2429 | loss 105.9153 205.5735 319.1408 515.5671 751.7815 1091.3481 1525.0133 2187.6692 3078.6956 4753.6538 7889.3193 14220.5732 | lr 3.6e-04 | norm 5302.8530 | dt 9.891 +type train | step 2430 | loss 110.3311 214.8235 332.9738 535.6716 785.2386 1139.4863 1587.7333 2264.0244 3180.0037 4873.4653 7994.0161 14366.3672 | lr 3.6e-04 | norm 5005.6812 | dt 9.883 +type train | step 2431 | loss 106.1992 207.2500 319.3908 518.3695 765.2067 1123.9362 1592.2834 2315.3657 3257.3926 5001.1094 8207.9033 14711.4717 | lr 3.6e-04 | norm 5507.5947 | dt 9.875 +type train | step 2432 | loss 102.5194 201.6292 314.8779 511.7939 758.1329 1109.7455 1559.5485 2255.2510 3168.3516 4858.0874 7928.6665 14116.5107 | lr 3.6e-04 | norm 4627.8154 | dt 9.895 +type train | step 2433 | loss 104.7056 203.7139 314.5958 508.6867 749.2682 1085.2052 1515.6313 2176.4502 3050.8604 4699.0410 7752.0059 13853.1943 | lr 3.6e-04 | norm 4246.3516 | dt 9.879 +type train | step 2434 | loss 104.3482 202.8620 310.4013 502.4000 744.4642 1085.8280 1531.0391 2209.2415 3124.0671 4824.7832 7960.9312 14253.3193 | lr 3.6e-04 | norm 4540.4248 | dt 9.877 +type train | step 2435 | loss 100.1269 193.7278 302.8486 493.8342 729.7518 1061.8916 1494.7263 2156.6448 3056.1343 4734.9419 7828.7139 13994.9248 | lr 3.6e-04 | norm 4297.0156 | dt 9.875 +type train | step 2436 | loss 100.1200 193.9411 306.2403 500.6233 741.7965 1088.2563 1546.3668 2249.0735 3167.4880 4922.9463 8213.8594 14924.7021 | lr 3.6e-04 | norm 5404.7344 | dt 9.883 +type train | step 2437 | loss 99.6418 192.8261 305.3175 496.7723 737.8936 1074.4165 1516.1444 2188.2166 3108.9973 4869.9038 8124.0757 14877.0430 | lr 3.6e-04 | norm 6820.3384 | dt 9.867 +type train | step 2438 | loss 110.4648 216.1118 335.2217 537.3252 788.2220 1146.6680 1598.7235 2290.4019 3222.7231 4898.0435 8077.7017 14433.1514 | lr 3.6e-04 | norm 5121.4404 | dt 9.880 +type train | step 2439 | loss 101.4369 198.1282 310.2408 505.3420 746.2092 1073.3839 1501.7716 2150.0254 3046.5044 4679.4102 7686.9751 13647.0732 | lr 3.6e-04 | norm 4837.9883 | dt 9.881 +type train | step 2440 | loss 104.4056 201.7641 313.1788 505.7377 745.8689 1080.5662 1509.6716 2163.4341 3069.6543 4700.6841 7739.8843 13885.5928 | lr 3.6e-04 | norm 4518.8315 | dt 9.881 +type train | step 2441 | loss 121.0439 234.3870 351.7228 562.3638 816.2661 1190.7106 1664.6254 2401.7610 3272.2251 4979.2056 8293.7695 15163.2930 | lr 3.6e-04 | norm 11791.1367 | dt 9.867 +type train | step 2442 | loss 107.1621 207.0574 321.5399 519.4327 759.6320 1103.7335 1544.5977 2229.2434 3128.1685 4803.5869 7919.1699 14196.9883 | lr 3.6e-04 | norm 4815.3208 | dt 9.882 +type train | step 2443 | loss 110.0834 213.3421 328.5189 528.6710 778.3268 1131.5061 1578.1267 2262.9343 3176.6931 4868.0947 7954.0391 14283.5791 | lr 3.6e-04 | norm 5239.2368 | dt 9.869 +type train | step 2444 | loss 104.7057 205.2892 321.5542 524.4102 772.5197 1138.6991 1597.6698 2310.2927 3245.8076 4975.0571 8195.2383 14705.9053 | lr 3.6e-04 | norm 5229.2969 | dt 9.887 +type train | step 2445 | loss 105.7376 205.2321 316.2586 512.1975 749.0037 1082.1575 1510.2819 2167.2129 3054.9890 4696.5811 7771.3223 14023.1338 | lr 3.6e-04 | norm 4893.7466 | dt 9.890 +type train | step 2446 | loss 106.5937 208.2246 320.1637 513.1167 757.0015 1097.7266 1540.4410 2219.0044 3120.2913 4820.2407 7990.9648 14280.4736 | lr 3.6e-04 | norm 5463.1841 | dt 9.887 +type train | step 2447 | loss 98.0599 189.3894 300.0139 491.9827 729.5080 1061.8414 1494.5291 2158.9270 3088.6211 4762.8613 7863.4966 14040.6963 | lr 3.6e-04 | norm 5024.4976 | dt 9.896 +type train | step 2448 | loss 117.4358 228.6575 346.8686 554.9360 801.0325 1161.2242 1615.9824 2301.6055 3206.3462 4893.6382 8016.5898 14379.6875 | lr 3.6e-04 | norm 5537.4263 | dt 9.875 +type train | step 2449 | loss 107.0808 205.2236 316.8142 507.0500 744.1441 1088.1498 1530.4005 2207.7583 3121.0884 4786.3359 7856.4961 13987.4092 | lr 3.6e-04 | norm 6034.5942 | dt 9.889 +type train | step 2450 | loss 105.8029 205.0241 315.3268 512.6149 752.8672 1093.8831 1529.5366 2203.0146 3097.1470 4747.2129 7818.9253 14013.2646 | lr 3.6e-04 | norm 4809.3550 | dt 9.885 +type train | step 2451 | loss 108.6060 210.4084 328.0934 531.0182 772.9688 1113.4895 1542.7747 2203.5461 3044.0583 4668.7705 7659.4849 13821.4102 | lr 3.6e-04 | norm 6487.1382 | dt 9.867 +type train | step 2452 | loss 116.4429 226.7207 346.1707 550.2172 794.8334 1136.7518 1568.1299 2241.8704 3135.3154 4818.6362 7953.0547 14342.0713 | lr 3.6e-04 | norm 5217.9067 | dt 9.882 +type train | step 2453 | loss 102.4467 194.1126 305.8660 501.2580 746.4947 1082.4863 1522.0420 2204.7324 3131.4097 4878.4810 8046.5601 14510.7520 | lr 3.6e-04 | norm 7082.7002 | dt 9.871 +type train | step 2454 | loss 107.5427 209.7938 321.7323 514.2700 758.3663 1102.8923 1548.9723 2234.6230 3151.5657 4832.1001 7934.6543 14124.4307 | lr 3.6e-04 | norm 5262.5044 | dt 9.882 +type train | step 2455 | loss 125.1700 241.4739 359.7241 565.3477 820.7476 1221.2678 1688.5123 2426.4497 3308.3926 5003.6675 8212.9570 14853.4307 | lr 3.6e-04 | norm 10347.5000 | dt 9.862 +type train | step 2456 | loss 113.4285 220.0754 337.8810 539.6875 786.3031 1136.9894 1592.3499 2276.4983 3197.1675 4885.4639 8115.6943 14640.5850 | lr 3.6e-04 | norm 7285.6309 | dt 9.877 +type train | step 2457 | loss 118.2793 230.4432 349.4830 553.6390 804.3167 1154.3789 1607.9833 2295.7822 3210.4153 4892.5649 8023.3711 14286.4961 | lr 3.6e-04 | norm 6184.3853 | dt 9.889 +type train | step 2458 | loss 109.6206 209.2774 323.2333 523.8748 762.0807 1095.6689 1534.0695 2202.1543 3078.0269 4739.2651 7804.5527 14042.3232 | lr 3.6e-04 | norm 5502.3037 | dt 9.879 +type train | step 2459 | loss 103.8122 200.8112 309.8949 499.2894 734.1750 1070.2240 1504.9208 2168.5725 3078.1863 4731.0151 7884.7085 14198.4258 | lr 3.6e-04 | norm 5321.3164 | dt 9.870 +type train | step 2460 | loss 110.4796 213.2581 328.6814 526.2595 771.4598 1122.5437 1567.3354 2252.0356 3152.9270 4814.9531 7912.5059 14077.6543 | lr 3.6e-04 | norm 4857.4390 | dt 9.888 +type train | step 2461 | loss 100.8697 197.2162 308.0950 497.7790 733.7657 1059.5984 1488.0400 2137.0417 3023.3596 4683.9873 7804.7217 14159.6348 | lr 3.6e-04 | norm 5279.2397 | dt 9.891 +type train | step 2462 | loss 111.3348 217.4020 331.3375 531.7770 774.7543 1125.5280 1570.1692 2259.4580 3164.3196 4876.3350 8067.3965 14422.2539 | lr 3.6e-04 | norm 4874.2764 | dt 9.871 +type train | step 2463 | loss 106.4426 206.4782 320.3022 519.4751 763.2897 1107.4237 1553.3245 2221.2168 3114.9932 4765.9375 7895.2241 14285.6533 | lr 3.6e-04 | norm 5192.0654 | dt 9.878 +type train | step 2464 | loss 109.6642 212.2594 328.3812 527.8536 777.6849 1135.8040 1589.2169 2288.3086 3214.7117 4946.3877 8129.9180 14554.5547 | lr 3.6e-04 | norm 4528.6875 | dt 9.898 +type train | step 2465 | loss 105.7355 206.4917 319.2267 517.6205 761.7362 1105.3867 1548.1476 2227.8865 3127.6282 4790.7109 7872.2275 14048.1631 | lr 3.6e-04 | norm 4570.2163 | dt 9.884 +type train | step 2466 | loss 104.9959 205.2979 318.4437 518.9476 767.4307 1118.4702 1561.6199 2249.6377 3169.3005 4881.3101 8008.6460 14221.5781 | lr 3.6e-04 | norm 4740.2534 | dt 9.885 +type train | step 2467 | loss 115.1534 221.3581 332.4769 529.5527 771.5921 1109.4893 1535.1178 2201.7007 3066.6589 4690.8667 7756.5532 13940.4316 | lr 3.6e-04 | norm 6036.6611 | dt 9.888 +type train | step 2468 | loss 108.5388 208.3498 321.6054 517.6094 758.2744 1098.0063 1534.6465 2211.5732 3074.6511 4698.2417 7681.4175 13712.8594 | lr 3.6e-04 | norm 4579.5044 | dt 9.872 +type train | step 2469 | loss 101.6980 197.7196 306.9825 498.0524 732.0599 1065.5986 1495.7423 2153.5750 3041.9431 4684.4541 7752.1313 13923.3711 | lr 3.6e-04 | norm 4516.2485 | dt 9.869 +type train | step 2470 | loss 102.0446 197.6900 303.9078 495.2186 728.8993 1058.8191 1485.6509 2133.6401 3005.9778 4653.8042 7684.0312 13821.1855 | lr 3.6e-04 | norm 5331.5791 | dt 9.873 +type train | step 2471 | loss 100.6891 198.0824 306.4599 499.0413 740.0191 1086.9551 1538.1719 2238.6411 3165.3108 4925.0845 8108.4824 14476.6045 | lr 3.6e-04 | norm 6045.8281 | dt 9.878 +type train | step 2472 | loss 101.2723 198.5026 313.3781 510.2702 756.5827 1097.5226 1550.2725 2233.8171 3171.4473 4899.2778 8049.8477 14417.9707 | lr 3.6e-04 | norm 4756.2363 | dt 9.891 +type train | step 2473 | loss 93.8358 186.4041 303.5926 503.9134 749.2723 1085.7468 1524.7449 2204.1711 3139.5593 4840.0688 8057.6821 14530.2021 | lr 3.6e-04 | norm 6889.0083 | dt 9.875 +type train | step 2474 | loss 110.0500 211.4384 325.2813 528.9576 767.9953 1104.8068 1535.9319 2183.0088 3027.5100 4643.4902 7646.7393 13780.3701 | lr 3.6e-04 | norm 5412.1479 | dt 9.873 +type train | step 2475 | loss 112.4228 215.2698 328.1870 530.1656 774.4985 1113.7552 1546.3645 2211.3687 3066.0933 4676.5581 7658.5107 13720.7314 | lr 3.6e-04 | norm 5379.4497 | dt 9.866 +type train | step 2476 | loss 107.0249 209.9187 322.6189 516.6625 755.4415 1084.5281 1515.9799 2175.6924 3074.7119 4739.6309 7856.9834 14138.4766 | lr 3.6e-04 | norm 5363.8081 | dt 9.878 +type train | step 2477 | loss 99.4236 193.0674 303.8795 498.8112 740.3411 1080.2886 1520.7788 2199.9141 3120.1777 4830.7500 7964.5850 14292.4561 | lr 3.6e-04 | norm 4898.3979 | dt 9.868 +type train | step 2478 | loss 108.1185 208.2441 318.9282 512.7466 750.6147 1099.0825 1536.5826 2216.4946 3045.1743 4627.8066 7564.8208 13519.8398 | lr 3.6e-04 | norm 6277.4678 | dt 9.849 +type train | step 2479 | loss 98.5827 192.6483 301.4843 487.9910 724.5162 1054.4409 1483.7073 2139.6794 3050.9055 4714.5977 7778.1782 13870.4258 | lr 3.6e-04 | norm 4626.8955 | dt 9.890 +type train | step 2480 | loss 112.7981 216.7843 335.3007 535.5584 778.7049 1120.7017 1553.1556 2218.8540 3097.9727 4718.9912 7762.2656 13881.9990 | lr 3.6e-04 | norm 5262.1040 | dt 9.869 +type train | step 2481 | loss 115.9550 223.1429 341.0303 547.6779 789.3934 1137.0482 1568.3379 2233.0862 3094.7649 4720.7510 7768.1333 13996.7100 | lr 3.6e-04 | norm 5370.3369 | dt 9.881 +type train | step 2482 | loss 101.5309 195.2200 302.4315 490.4882 726.6881 1050.3408 1472.0356 2115.6865 2993.2380 4629.0625 7645.0278 13701.7920 | lr 3.6e-04 | norm 5952.8516 | dt 9.875 +type train | step 2483 | loss 105.8506 207.5559 320.5111 518.6298 764.7800 1105.5958 1546.3564 2218.1201 3124.8677 4779.4082 7843.8857 14002.2764 | lr 3.6e-04 | norm 4696.6382 | dt 9.887 +type train | step 2484 | loss 100.6569 198.1521 309.7822 499.1299 739.7496 1076.4642 1513.3136 2190.0264 3104.3745 4769.1890 7758.5498 13690.5791 | lr 3.6e-04 | norm 5936.2690 | dt 9.887 +type train | step 2485 | loss 100.9930 204.1790 326.0401 535.1600 787.8151 1160.4810 1635.2474 2374.7454 3361.9988 5150.7280 8472.6377 15001.1201 | lr 3.6e-04 | norm 9576.4092 | dt 9.870 +type train | step 2486 | loss 101.4042 198.7722 312.9863 503.6675 740.9117 1063.6785 1497.3350 2152.1411 3055.6968 4745.6704 7836.7192 14012.6641 | lr 3.6e-04 | norm 4486.8101 | dt 9.891 +type train | step 2487 | loss 120.0733 233.0304 352.9318 561.3330 812.4986 1172.7778 1624.7069 2327.0083 3206.6450 4901.6748 8047.7412 14485.5264 | lr 3.6e-04 | norm 7106.4912 | dt 9.864 +type train | step 2488 | loss 108.3264 207.6131 323.5486 520.9006 765.5137 1110.0421 1551.9093 2237.3179 3136.4219 4834.5688 7954.4873 14185.4521 | lr 3.6e-04 | norm 5241.2456 | dt 9.878 +type train | step 2489 | loss 95.9415 187.3570 294.1303 484.1905 718.9041 1046.9075 1476.2889 2135.9045 3052.7285 4704.3833 7752.9448 13782.6309 | lr 3.6e-04 | norm 5376.6450 | dt 9.876 +type train | step 2490 | loss 100.1543 197.6454 311.5762 504.8966 754.4342 1101.7455 1564.1069 2270.1833 3221.4341 4986.1860 8234.6416 14770.1709 | lr 3.6e-04 | norm 5219.5112 | dt 9.880 +type train | step 2491 | loss 104.2605 203.7972 315.0585 507.9179 750.5254 1089.6381 1531.9617 2210.9944 3128.2512 4818.6006 7931.4434 14183.9629 | lr 3.6e-04 | norm 4537.1304 | dt 9.893 +type train | step 2492 | loss 106.0091 209.9937 322.4670 516.2838 753.9948 1076.6554 1499.8042 2133.3320 3036.9409 4675.1938 7769.0986 14023.0586 | lr 3.6e-04 | norm 5331.7812 | dt 9.879 +type train | step 2493 | loss 98.7410 190.9190 303.6186 500.6793 743.4425 1091.2721 1534.4180 2232.0657 3142.1455 4901.9824 8170.6763 14875.7344 | lr 3.6e-04 | norm 6892.7124 | dt 9.861 +type train | step 2494 | loss 111.7715 218.4230 336.7144 540.1950 782.9088 1142.0737 1587.5823 2265.9209 3122.3293 4755.0088 7793.4463 13966.5664 | lr 3.6e-04 | norm 5502.0156 | dt 9.858 +type train | step 2495 | loss 99.6742 193.6861 304.7539 499.3276 739.3624 1080.6145 1522.5062 2210.8311 3113.0176 4850.1597 8028.9331 14469.1250 | lr 3.6e-04 | norm 5585.7300 | dt 9.885 +type train | step 2496 | loss 100.9625 196.6001 308.4461 503.9229 745.5486 1078.3341 1513.5498 2175.4602 3084.6272 4777.1343 7961.2769 14291.7959 | lr 3.6e-04 | norm 5012.8193 | dt 9.886 +type train | step 2497 | loss 116.5593 226.4826 343.3759 548.7492 797.8091 1148.2856 1596.3333 2262.9641 3121.3452 4747.7393 7750.7012 13788.2041 | lr 3.6e-04 | norm 5238.7705 | dt 9.876 +type train | step 2498 | loss 108.9241 208.3292 322.0220 521.2980 760.7396 1096.7638 1524.5007 2169.8770 3024.7012 4622.5264 7607.7583 13643.9551 | lr 3.6e-04 | norm 4797.9575 | dt 9.881 +type train | step 2499 | loss 101.8148 197.8901 308.4210 502.2535 741.2254 1078.9404 1523.1957 2200.1213 3112.7446 4786.2490 7868.9312 14041.0986 | lr 3.5e-04 | norm 4974.5967 | dt 9.872 +type train | step 2500 | loss 111.4929 218.0735 330.3987 528.5441 765.7305 1098.2649 1536.7319 2200.3071 3080.9392 4704.7539 7713.5562 13818.5498 | lr 3.5e-04 | norm 6789.4741 | dt 9.865 +type train | step 2501 | loss 108.2418 211.2704 327.0962 527.1880 774.2311 1127.2617 1575.4060 2263.4065 3158.0869 4850.1821 8062.9478 14553.0410 | lr 3.5e-04 | norm 5463.7104 | dt 9.864 +type train | step 2502 | loss 102.9987 202.8146 312.6045 509.8213 748.0421 1095.1543 1539.4578 2222.9072 3127.3491 4816.2002 7936.7290 14171.7549 | lr 3.5e-04 | norm 4722.7554 | dt 9.875 +type train | step 2503 | loss 116.3386 225.7077 331.8683 542.8275 790.4608 1155.7693 1631.3625 2363.9104 3285.9424 5043.7241 8260.4668 14814.2598 | lr 3.5e-04 | norm 7226.8140 | dt 9.843 +type train | step 2504 | loss 112.9158 217.5910 332.2437 532.0370 776.4539 1125.5920 1558.2114 2220.6738 3100.3606 4737.3887 7738.1353 13804.3096 | lr 3.5e-04 | norm 5140.0220 | dt 9.875 +type train | step 2505 | loss 107.4847 207.5879 318.5999 508.9953 746.8402 1071.7184 1495.3049 2138.1667 3019.6667 4638.2393 7614.2886 13604.4307 | lr 3.5e-04 | norm 5025.7964 | dt 9.888 +type train | step 2506 | loss 99.9713 196.5702 309.8059 505.2245 745.4828 1078.2704 1511.9663 2167.5278 3078.4260 4752.3735 7887.9971 14103.6553 | lr 3.5e-04 | norm 4907.4448 | dt 9.894 +type train | step 2507 | loss 107.9526 209.1145 320.7228 516.3248 756.1789 1097.1313 1533.1294 2199.3347 3096.8691 4777.1328 7914.1802 14132.8643 | lr 3.5e-04 | norm 4703.2808 | dt 9.873 +type train | step 2508 | loss 107.7906 210.8855 325.4895 526.6696 765.7574 1099.4647 1524.5999 2163.7114 3042.3367 4685.9702 7788.9868 13976.7725 | lr 3.5e-04 | norm 5041.8940 | dt 9.889 +type train | step 2509 | loss 119.5347 233.0282 326.8195 528.9148 780.0055 1159.4482 1657.6274 2415.1453 3375.1733 5187.0171 8473.6562 14823.6514 | lr 3.5e-04 | norm 7574.0791 | dt 9.853 +type train | step 2510 | loss 103.5549 201.9216 314.2722 507.3197 746.2553 1083.8154 1521.5748 2190.8828 3088.6846 4743.8018 7847.9419 14150.0352 | lr 3.5e-04 | norm 5246.9619 | dt 9.901 +type train | step 2511 | loss 111.9248 222.1168 337.8311 534.4243 784.0068 1125.8379 1574.2976 2272.2327 3218.5630 4878.8584 7897.7671 13990.9189 | lr 3.5e-04 | norm 4760.3711 | dt 9.882 +type train | step 2512 | loss 102.4790 200.1426 311.9323 506.5558 750.3477 1083.7867 1520.6631 2185.9417 3099.3230 4780.7485 7853.4932 13989.3877 | lr 3.5e-04 | norm 4697.3208 | dt 9.903 +type train | step 2513 | loss 106.3671 207.5066 323.2413 519.4743 768.6307 1105.4065 1549.7373 2216.8037 3149.5288 4858.0381 8036.8398 14435.4580 | lr 3.5e-04 | norm 6976.9399 | dt 9.898 +type train | step 2514 | loss 111.7522 216.7592 336.2243 541.3297 800.8077 1170.0530 1634.0859 2364.9741 3260.4836 4984.0684 8337.1826 14938.7031 | lr 3.5e-04 | norm 7246.9014 | dt 9.877 +type train | step 2515 | loss 105.1640 204.1353 320.0532 516.2255 761.1684 1103.5282 1542.6055 2201.5579 3094.0166 4783.0601 7881.3447 14070.3438 | lr 3.5e-04 | norm 5028.1362 | dt 9.886 +type train | step 2516 | loss 108.4768 210.3313 324.3464 519.4091 755.9236 1085.9143 1515.0066 2158.1199 3025.2058 4654.8452 7682.5811 13892.0527 | lr 3.5e-04 | norm 5591.7739 | dt 9.880 +type train | step 2517 | loss 102.4422 198.2524 310.9943 505.5132 744.8950 1095.6466 1551.4437 2245.1838 3132.3325 4818.7861 8025.1460 14643.5879 | lr 3.5e-04 | norm 7769.9370 | dt 9.875 +type train | step 2518 | loss 109.8091 214.3702 330.9706 532.8909 780.6457 1126.4913 1573.1798 2242.2783 3116.2356 4717.5371 7766.6548 13789.6631 | lr 3.5e-04 | norm 7793.1528 | dt 9.881 +type train | step 2519 | loss 101.2353 199.0027 311.5406 507.5723 747.4965 1090.0544 1524.7571 2191.5374 3091.9482 4779.6021 7953.7441 14263.9111 | lr 3.5e-04 | norm 5308.6064 | dt 9.884 +type train | step 2520 | loss 112.6202 220.3079 341.5049 546.2957 789.6801 1136.7119 1584.2899 2274.5229 3156.8743 4860.9717 7960.4170 14381.8936 | lr 3.5e-04 | norm 5672.9155 | dt 9.876 +type train | step 2521 | loss 147.5305 285.8249 430.5415 673.9340 963.0856 1384.8477 1894.5797 2651.1560 3559.6484 5297.6875 8576.8975 15261.9463 | lr 3.5e-04 | norm 8282.8936 | dt 9.870 +type train | step 2522 | loss 105.0462 203.0141 312.8104 509.1829 751.7089 1096.3445 1538.5706 2219.1355 3112.6401 4786.6885 7910.8608 14250.2617 | lr 3.5e-04 | norm 5331.1450 | dt 9.914 +type train | step 2523 | loss 113.0655 219.7231 335.5735 542.0070 797.0432 1183.1451 1648.5687 2407.4199 3337.2800 5021.2852 8125.0718 14410.6572 | lr 3.5e-04 | norm 6082.8101 | dt 9.862 +type train | step 2524 | loss 106.0262 204.0107 313.7266 508.0104 743.8405 1079.0011 1511.4478 2161.0127 3026.0884 4691.3032 7824.9614 14175.7695 | lr 3.5e-04 | norm 6404.2905 | dt 9.879 +type train | step 2525 | loss 107.9850 210.4340 325.1512 523.9016 770.1622 1111.5547 1547.0896 2209.9202 3118.7449 4789.7876 7900.1753 14078.4375 | lr 3.5e-04 | norm 5206.6084 | dt 9.898 +type train | step 2526 | loss 104.7644 203.8282 315.1357 506.9713 744.0016 1078.7627 1517.4692 2187.5698 3096.2593 4795.7344 7972.1973 14373.7891 | lr 3.5e-04 | norm 4628.2676 | dt 9.868 +type train | step 2527 | loss 106.8022 208.3471 324.8534 528.3011 777.4127 1141.3313 1604.8038 2322.4583 3253.8889 5025.3887 8308.1680 14934.7568 | lr 3.5e-04 | norm 5597.3662 | dt 9.875 +type train | step 2528 | loss 114.6721 220.7876 336.2497 540.5560 781.0282 1127.6947 1560.6409 2215.1345 3051.0105 4644.0781 7627.4111 13657.7373 | lr 3.5e-04 | norm 4980.9634 | dt 9.876 +type train | step 2529 | loss 145.0387 287.8607 438.7587 694.7204 977.1286 1388.1877 1920.0459 2726.1724 3905.6191 5786.0083 9673.1631 17751.3789 | lr 3.5e-04 | norm 13996.2988 | dt 9.866 +type train | step 2530 | loss 118.2799 232.0442 357.8632 575.1743 831.0671 1195.4512 1667.8995 2388.1621 3402.7341 5214.3843 8750.8916 15997.5771 | lr 3.5e-04 | norm 6827.7314 | dt 9.883 +type train | step 2531 | loss 102.7189 200.2924 307.8085 501.3824 740.0186 1076.0984 1509.1696 2171.4480 3046.5801 4742.9834 7903.1807 14202.0059 | lr 3.5e-04 | norm 8609.7305 | dt 9.882 +type train | step 2532 | loss 104.1102 201.9624 313.3567 512.2299 752.0063 1091.9003 1531.0238 2197.9072 3110.9939 4818.0303 7987.8042 14308.1191 | lr 3.5e-04 | norm 5279.3950 | dt 9.888 +type train | step 2533 | loss 111.6384 215.2928 328.5108 531.7075 771.6368 1111.9824 1545.0033 2208.7253 3082.5090 4734.3564 7805.6294 14031.0859 | lr 3.5e-04 | norm 5763.8535 | dt 9.886 +type train | step 2534 | loss 108.9520 211.3885 327.6797 527.8116 769.1196 1111.3981 1547.0784 2198.8611 3075.0342 4718.6201 7789.0938 13988.4590 | lr 3.5e-04 | norm 5000.2095 | dt 9.879 +type train | step 2535 | loss 117.1107 227.3134 351.1390 559.3523 808.4589 1161.2343 1607.2264 2294.5903 3177.5171 4868.5830 8033.4160 14529.4512 | lr 3.5e-04 | norm 6113.6733 | dt 9.869 +type train | step 2536 | loss 108.6397 210.7113 321.1171 516.3968 756.9518 1087.9596 1516.7091 2161.4805 3049.6621 4687.4727 7681.8618 13709.4590 | lr 3.5e-04 | norm 4783.3501 | dt 9.872 +type train | step 2537 | loss 103.3669 205.0181 322.6246 523.7563 771.8132 1134.1117 1588.5291 2309.9429 3236.9211 4996.5024 8304.4727 15010.1982 | lr 3.5e-04 | norm 6159.8306 | dt 9.884 +type train | step 2538 | loss 102.9548 201.3757 312.7309 508.1270 751.1984 1097.1901 1531.7880 2209.8621 3110.5745 4808.3364 8025.9897 14403.2334 | lr 3.5e-04 | norm 6299.0645 | dt 9.870 +type train | step 2539 | loss 102.9584 200.3627 310.6778 503.8437 742.0762 1080.5481 1512.6851 2179.0627 3077.2273 4741.0972 7835.7031 13999.6914 | lr 3.5e-04 | norm 5162.3257 | dt 9.871 +type train | step 2540 | loss 97.5339 189.7274 298.4109 488.6556 724.4703 1055.5088 1493.9883 2160.6521 3084.1731 4766.7876 7903.5205 14117.6455 | lr 3.5e-04 | norm 4834.9722 | dt 9.879 +type train | step 2541 | loss 108.0134 208.9040 325.6293 521.2919 763.2939 1098.0884 1529.6604 2181.4790 3089.9890 4770.9424 7915.3809 14285.9775 | lr 3.5e-04 | norm 5198.7202 | dt 9.890 +type train | step 2542 | loss 103.0348 199.2788 311.2724 501.7830 739.3759 1066.9539 1494.5477 2138.9739 3039.5771 4666.7134 7705.9648 13716.3916 | lr 3.5e-04 | norm 4168.8428 | dt 9.896 +type train | step 2543 | loss 108.9795 213.6826 329.2960 529.0599 773.9930 1120.4285 1564.4105 2234.0952 3147.2595 4819.5029 7913.2905 14044.9395 | lr 3.5e-04 | norm 4487.6377 | dt 9.894 +type train | step 2544 | loss 114.3224 219.6625 330.8424 527.5178 759.0756 1104.1823 1533.2307 2184.3506 3041.1094 4632.2729 7641.6372 13694.2246 | lr 3.5e-04 | norm 5972.0063 | dt 9.877 +type train | step 2545 | loss 118.5908 230.4425 348.1826 552.5497 797.9815 1156.3616 1603.8282 2287.8401 3177.6125 4864.6587 8076.0220 14622.7217 | lr 3.5e-04 | norm 6561.6826 | dt 9.869 +type train | step 2546 | loss 111.8185 215.7456 331.7918 538.5408 780.3239 1131.7843 1575.0420 2249.7444 3124.3765 4820.6797 7997.4517 14443.9023 | lr 3.5e-04 | norm 5595.9922 | dt 9.887 +type train | step 2547 | loss 110.7993 217.6916 332.1211 528.1179 777.2495 1116.9200 1561.6361 2227.5884 3145.6951 4829.6753 7961.4258 14281.6982 | lr 3.5e-04 | norm 5262.0093 | dt 9.886 +type train | step 2548 | loss 100.9284 196.1916 303.9696 497.1248 736.1536 1069.5526 1506.1816 2174.4243 3076.8462 4772.6206 7913.6738 14312.3105 | lr 3.5e-04 | norm 5535.3403 | dt 9.897 +type train | step 2549 | loss 100.6064 197.4206 307.5508 498.9207 734.4838 1060.5126 1495.0519 2142.3970 3044.1553 4700.9585 7787.3359 13972.6777 | lr 3.5e-04 | norm 5455.1479 | dt 9.880 +type train | step 2550 | loss 101.0211 195.0608 304.5741 494.7832 734.0624 1064.1104 1498.8245 2167.5913 3090.0293 4784.8271 7898.3145 14033.8447 | lr 3.5e-04 | norm 4761.9766 | dt 9.881 +type train | step 2551 | loss 102.2081 197.8708 306.8241 498.9250 736.0909 1074.4164 1513.1023 2188.5681 3090.0818 4753.2412 7880.2749 14172.7812 | lr 3.5e-04 | norm 4845.8594 | dt 9.890 +type train | step 2552 | loss 106.2281 206.4016 317.3738 508.1979 744.3592 1074.5398 1500.0836 2152.1348 3024.7012 4654.6787 7690.3438 13716.1064 | lr 3.5e-04 | norm 4566.7866 | dt 9.880 +type train | step 2553 | loss 100.9644 196.7187 311.7085 506.9472 746.3502 1082.5632 1524.9908 2199.0095 3118.7874 4826.7637 7915.8770 14015.0879 | lr 3.5e-04 | norm 5296.0635 | dt 9.873 +type train | step 2554 | loss 102.8985 199.9134 310.3536 500.8058 735.3572 1065.8580 1487.8300 2135.6172 3011.6931 4628.2090 7638.6172 13587.9932 | lr 3.5e-04 | norm 4299.7700 | dt 9.883 +type train | step 2555 | loss 100.7289 195.9586 307.9057 501.8193 741.8745 1084.9263 1525.7358 2200.7656 3108.3833 4789.5093 7886.2627 14123.6426 | lr 3.5e-04 | norm 4273.7964 | dt 9.885 +type train | step 2556 | loss 104.2825 204.0608 314.9861 508.7620 749.1390 1091.4160 1524.6489 2186.9751 3076.7981 4731.5801 7811.9873 13906.8154 | lr 3.5e-04 | norm 3999.4358 | dt 9.898 +type train | step 2557 | loss 123.1820 242.6729 361.2339 568.3038 818.6155 1183.8423 1641.1619 2343.0256 3230.7659 4909.6426 8012.5977 14222.1006 | lr 3.5e-04 | norm 4981.0962 | dt 9.889 +type train | step 2558 | loss 101.5948 197.7364 310.3866 508.0766 744.0523 1077.3457 1507.9995 2146.3748 2991.5906 4606.3145 7637.1880 13737.7246 | lr 3.5e-04 | norm 5914.6709 | dt 9.874 +type train | step 2559 | loss 112.4252 219.3328 331.1835 527.8309 769.0565 1108.9778 1537.9928 2202.0781 3089.5684 4739.2520 7809.7368 13958.7734 | lr 3.5e-04 | norm 4659.2568 | dt 9.874 +type train | step 2560 | loss 98.3323 190.9137 299.9471 485.7363 720.0770 1045.7863 1477.1638 2133.0022 3041.7205 4720.5635 7820.3223 14075.3535 | lr 3.5e-04 | norm 5233.7471 | dt 9.886 +type train | step 2561 | loss 107.2407 207.5427 318.4274 512.3293 749.8599 1092.9033 1530.2209 2196.6147 3102.0620 4746.2695 7818.5708 13918.3203 | lr 3.5e-04 | norm 4530.6147 | dt 9.875 +type train | step 2562 | loss 98.0330 190.2535 298.6006 486.3657 723.0740 1052.6501 1486.1726 2141.0364 3047.7441 4716.8560 7811.8472 13949.9473 | lr 3.5e-04 | norm 4759.9175 | dt 9.888 +type train | step 2563 | loss 101.4665 197.5766 309.5130 499.0477 734.0225 1069.5696 1501.5139 2170.1423 3063.9111 4729.3555 7811.6255 13961.7627 | lr 3.5e-04 | norm 4456.5718 | dt 9.884 +type train | step 2564 | loss 113.1431 219.7190 339.3830 541.2119 786.0807 1130.6497 1567.4495 2241.1187 3162.6438 4901.5527 8103.9541 14546.8213 | lr 3.5e-04 | norm 4711.3696 | dt 9.885 +type train | step 2565 | loss 109.5006 211.4141 326.8478 524.6998 773.1203 1122.5747 1579.8278 2260.8694 3184.2183 4866.3921 7974.9951 14320.2725 | lr 3.5e-04 | norm 5565.6924 | dt 9.860 +type train | step 2566 | loss 101.5148 197.0993 307.9698 502.2974 741.5090 1074.1624 1508.5474 2164.5767 3070.6304 4714.1943 7741.5669 13828.6211 | lr 3.5e-04 | norm 4445.1104 | dt 9.877 +type train | step 2567 | loss 118.9907 235.3399 357.0142 559.7490 808.5624 1191.2885 1645.9924 2358.3181 3193.3408 4811.2324 7776.5586 13842.6016 | lr 3.5e-04 | norm 5834.0596 | dt 9.856 +type train | step 2568 | loss 102.8588 200.1804 312.8852 508.6031 749.7982 1089.7150 1531.3551 2202.2014 3112.5339 4828.6616 7996.2168 14262.1963 | lr 3.4e-04 | norm 4706.1997 | dt 9.904 +type train | step 2569 | loss 100.4319 199.3229 308.1298 506.3267 744.7515 1086.3446 1523.4783 2199.3733 3105.9448 4797.6484 7938.8159 14248.1484 | lr 3.4e-04 | norm 5883.1694 | dt 9.866 +type train | step 2570 | loss 99.3223 192.1974 299.2801 487.1363 722.6111 1053.6118 1479.9233 2136.0752 3010.0676 4639.4028 7668.0020 13723.2939 | lr 3.4e-04 | norm 4654.6431 | dt 9.881 +type train | step 2571 | loss 97.2099 188.0068 296.9917 487.8267 722.5801 1049.7269 1471.6150 2126.2156 3007.2139 4622.0815 7627.3306 13626.5479 | lr 3.4e-04 | norm 4988.6733 | dt 9.874 +type train | step 2572 | loss 103.5617 199.0195 306.6649 496.7993 732.8407 1071.0480 1506.7773 2172.6008 3062.9910 4737.4097 7823.0557 13916.9004 | lr 3.4e-04 | norm 4719.0532 | dt 9.880 +type train | step 2573 | loss 100.8023 196.1067 306.0545 494.7494 731.0258 1054.9438 1478.8342 2126.5928 3017.1169 4647.0488 7663.0469 13650.6152 | lr 3.4e-04 | norm 4741.8511 | dt 9.899 +type train | step 2574 | loss 110.5216 216.5237 333.8262 528.1313 769.2352 1093.8048 1514.6866 2150.2620 3035.8882 4657.4883 7632.8545 13623.8223 | lr 3.4e-04 | norm 3882.6301 | dt 9.897 +type train | step 2575 | loss 101.5908 195.9054 309.5434 507.7479 751.2033 1078.1377 1514.8662 2168.7742 3098.3552 4764.0737 7802.8818 13850.1602 | lr 3.4e-04 | norm 4844.0273 | dt 9.879 +type train | step 2576 | loss 100.6002 194.0747 299.5750 489.1296 717.6447 1059.2273 1498.9969 2179.0139 3060.9583 4750.0273 7914.2920 14413.2607 | lr 3.4e-04 | norm 7058.9380 | dt 9.869 +type train | step 2577 | loss 115.0981 224.5556 340.2944 540.0532 782.1691 1126.4623 1569.7047 2235.6384 3109.6292 4765.9023 7859.4941 14001.2129 | lr 3.4e-04 | norm 4866.6963 | dt 9.898 +type train | step 2578 | loss 105.3348 203.7904 315.5006 511.7873 746.3085 1079.5461 1506.4315 2157.9111 3017.6147 4640.3550 7706.2983 13795.0137 | lr 3.4e-04 | norm 4822.8589 | dt 9.876 +type train | step 2579 | loss 117.9517 227.5083 350.2909 559.9848 810.0073 1177.3998 1647.9677 2358.0222 3245.6250 4951.8135 8221.5234 14863.4600 | lr 3.4e-04 | norm 10348.5996 | dt 9.868 +type train | step 2580 | loss 100.5792 195.4147 302.9666 496.7060 728.4962 1063.5614 1493.4506 2160.1841 3051.7041 4708.7231 7795.3174 14027.1475 | lr 3.4e-04 | norm 5549.7114 | dt 9.874 +type train | step 2581 | loss 100.1593 195.4052 303.4568 497.9813 733.8805 1080.2515 1527.9126 2209.2024 3076.3125 4773.7334 7938.4429 14438.3594 | lr 3.4e-04 | norm 8532.5293 | dt 9.861 +type train | step 2582 | loss 102.1811 199.7199 310.5066 503.3568 740.9991 1072.7297 1496.8263 2146.2615 3033.6943 4662.0308 7700.5786 13814.7061 | lr 3.4e-04 | norm 5300.4824 | dt 9.886 +type train | step 2583 | loss 106.8616 209.4308 326.8804 533.8230 779.0763 1121.6573 1560.8356 2218.0459 3130.9189 4784.0557 7859.9878 14128.2441 | lr 3.4e-04 | norm 5184.5337 | dt 9.883 +type train | step 2584 | loss 113.1772 220.1270 336.0956 545.2789 786.3269 1140.2234 1582.2714 2252.6091 3109.1665 4732.5942 7795.1123 13974.2842 | lr 3.4e-04 | norm 5694.1421 | dt 9.861 +type train | step 2585 | loss 110.6170 216.5445 331.3875 533.8912 776.8040 1117.0487 1547.3230 2187.4578 3069.3701 4690.3164 7688.1235 13693.8379 | lr 3.4e-04 | norm 7124.7578 | dt 9.872 +type train | step 2586 | loss 105.7694 204.0935 319.2418 518.6807 760.5709 1103.7883 1543.7842 2213.3113 3126.8616 4793.8496 7897.1484 14089.0293 | lr 3.4e-04 | norm 5401.5698 | dt 9.877 +type train | step 2587 | loss 97.9983 192.6953 305.5646 500.2596 742.1877 1077.4546 1515.1582 2189.4329 3123.3374 4855.3691 7987.0698 14176.3291 | lr 3.4e-04 | norm 4612.2686 | dt 9.879 +type train | step 2588 | loss 101.5102 195.4575 303.4719 492.2086 728.0853 1054.7051 1487.8392 2144.3965 3049.6135 4693.4351 7677.2451 13590.2695 | lr 3.4e-04 | norm 5619.7017 | dt 9.899 +type train | step 2589 | loss 101.1418 197.3235 306.5580 498.0908 741.8133 1083.4496 1537.9617 2226.8335 3157.6055 4855.9868 7983.0728 14286.5420 | lr 3.4e-04 | norm 5257.1484 | dt 9.891 +type train | step 2590 | loss 105.6703 207.8078 321.8437 519.3271 762.6326 1113.0748 1556.4473 2233.9634 3140.1997 4825.4546 7965.9868 14206.0420 | lr 3.4e-04 | norm 4218.1001 | dt 9.893 +type train | step 2591 | loss 108.6704 210.8946 326.0491 526.4297 769.3156 1112.2235 1548.4442 2219.5137 3099.5715 4760.4800 7915.9336 14316.6787 | lr 3.4e-04 | norm 5041.9199 | dt 9.885 +type train | step 2592 | loss 101.0602 199.4211 315.7256 520.5955 758.9803 1109.1249 1560.0741 2244.2522 3132.9287 4856.7236 8210.7812 14945.1182 | lr 3.4e-04 | norm 8377.6611 | dt 9.881 +type train | step 2593 | loss 97.0394 187.2962 291.8215 478.9069 710.8827 1030.7794 1454.6726 2105.8738 2988.8188 4625.4751 7623.5869 13550.6709 | lr 3.4e-04 | norm 4767.1602 | dt 9.875 +type train | step 2594 | loss 94.0270 191.8380 313.0508 513.5477 771.9806 1132.4543 1604.2030 2340.4646 3320.1633 5186.3193 8625.3721 15475.9521 | lr 3.4e-04 | norm 9611.2881 | dt 9.862 +type train | step 2595 | loss 108.8008 209.9531 321.0645 519.5808 754.2391 1088.3890 1521.0909 2195.0300 3100.7478 4806.8242 8059.1636 14799.5195 | lr 3.4e-04 | norm 7629.8555 | dt 9.890 +type train | step 2596 | loss 104.4298 204.0452 316.4922 516.0316 757.8525 1097.5200 1538.6990 2217.5132 3108.1296 4801.0371 7942.9399 14186.4365 | lr 3.4e-04 | norm 5334.5967 | dt 9.882 +type train | step 2597 | loss 108.4804 210.9440 327.5378 528.0052 776.9608 1126.6543 1575.4122 2256.8933 3193.8000 4858.9956 7960.4551 14213.4014 | lr 3.4e-04 | norm 4875.1226 | dt 9.894 +type train | step 2598 | loss 105.5881 205.5976 313.4167 507.2502 742.9478 1088.1506 1527.6056 2205.2288 3101.6443 4801.0508 7935.8462 14224.7559 | lr 3.4e-04 | norm 4760.6816 | dt 9.871 +type train | step 2599 | loss 105.2936 204.8298 315.5465 508.0062 744.0163 1068.1345 1498.7354 2133.6089 3008.1562 4634.7744 7618.8364 13592.1230 | lr 3.4e-04 | norm 5337.3799 | dt 9.893 +type train | step 2600 | loss 103.5374 202.0954 315.9890 514.4603 760.9731 1103.3607 1551.7742 2226.9751 3138.0588 4813.7490 7922.0669 14042.3818 | lr 3.4e-04 | norm 4561.2837 | dt 9.892 +type train | step 2601 | loss 99.5738 191.4198 298.6062 485.7780 723.1718 1054.0029 1482.0797 2144.6924 3047.8152 4694.9819 7750.5625 13761.9248 | lr 3.4e-04 | norm 4511.3169 | dt 9.877 +type train | step 2602 | loss 101.0062 195.2981 304.0101 494.5788 728.7816 1063.6686 1492.3037 2144.1743 3027.7178 4652.1899 7636.3950 13584.3115 | lr 3.4e-04 | norm 4613.4727 | dt 9.899 +type train | step 2603 | loss 100.4320 195.3185 306.8720 500.3645 735.3762 1071.4725 1498.6533 2151.5105 3012.9429 4651.9209 7676.0933 13747.5645 | lr 3.4e-04 | norm 5664.0664 | dt 9.885 +type train | step 2604 | loss 98.1895 190.4382 302.8859 497.0778 735.4728 1071.3217 1507.1029 2166.2986 3069.7356 4740.2861 7759.8921 13815.7256 | lr 3.4e-04 | norm 4780.1045 | dt 9.886 +type train | step 2605 | loss 103.0940 201.6926 312.9463 505.4749 743.9930 1065.1746 1485.3105 2119.5876 3002.9624 4627.5898 7614.5103 13544.2012 | lr 3.4e-04 | norm 4576.5859 | dt 9.877 +type train | step 2606 | loss 107.2209 206.2934 318.4232 516.3798 752.6449 1097.0184 1532.0867 2199.9475 3068.8945 4695.2769 7768.7090 13896.0596 | lr 3.4e-04 | norm 4578.6689 | dt 9.874 +type train | step 2607 | loss 105.5016 202.9231 312.7076 508.5470 742.6337 1085.2043 1516.1877 2182.2942 3065.7009 4749.7681 7909.0762 14240.1006 | lr 3.4e-04 | norm 4980.9707 | dt 9.879 +type train | step 2608 | loss 98.3626 185.4268 294.0211 492.1204 729.2250 1054.8248 1485.5210 2152.9338 3062.1355 4823.6035 8113.6855 14861.6699 | lr 3.4e-04 | norm 7814.2280 | dt 9.860 +type train | step 2609 | loss 95.0111 183.9134 290.3453 475.9186 706.3979 1039.0051 1470.3794 2137.2378 3030.3188 4671.5518 7704.2271 13650.8164 | lr 3.4e-04 | norm 4877.6899 | dt 9.873 +type train | step 2610 | loss 100.7681 203.1882 315.0737 512.7594 762.9304 1119.3879 1590.4464 2305.3589 3288.6746 5076.6992 8389.3535 14988.4551 | lr 3.4e-04 | norm 5944.3330 | dt 9.893 +type train | step 2611 | loss 95.6503 185.1546 289.7144 475.5937 704.8516 1030.3409 1451.8464 2111.9541 2993.0828 4653.1348 7707.2314 13792.8926 | lr 3.4e-04 | norm 4803.9839 | dt 9.889 +type train | step 2612 | loss 102.5836 201.2590 313.7048 508.1599 750.2911 1095.6187 1542.3455 2224.5737 3147.5840 4876.3413 8050.7056 14423.1416 | lr 3.4e-04 | norm 4931.4917 | dt 9.889 +type train | step 2613 | loss 103.8307 201.3027 312.1529 504.6358 742.0650 1076.4580 1513.6472 2181.8831 3092.1460 4771.2373 7865.4775 14034.2588 | lr 3.4e-04 | norm 5163.3643 | dt 9.871 +type train | step 2614 | loss 93.1705 179.4011 281.7368 463.9505 693.0460 1020.9279 1453.6261 2121.5186 3027.8667 4728.0278 7859.6333 14079.3662 | lr 3.4e-04 | norm 6182.6064 | dt 9.882 +type train | step 2615 | loss 99.0377 191.0894 298.1471 485.3779 715.4865 1042.2095 1462.6736 2108.5359 2983.4534 4589.0938 7585.0918 13487.2568 | lr 3.4e-04 | norm 4388.9858 | dt 9.888 +type train | step 2616 | loss 102.1581 198.5728 308.9881 503.2592 738.7948 1075.8132 1508.1957 2177.9448 3066.8020 4711.6826 7830.4341 14094.3174 | lr 3.4e-04 | norm 5145.0063 | dt 9.879 +type train | step 2617 | loss 104.8614 206.4637 318.6175 511.1055 750.1202 1093.8647 1531.9722 2208.6616 3112.1848 4765.4648 7826.5850 13860.3252 | lr 3.4e-04 | norm 4778.4297 | dt 9.875 +type train | step 2618 | loss 96.3897 187.3434 293.8268 478.8618 712.7916 1035.1621 1459.6016 2102.1047 2985.7175 4619.1143 7636.2061 13579.5010 | lr 3.4e-04 | norm 5005.1118 | dt 9.869 +type train | step 2619 | loss 102.5743 200.3980 308.0685 496.6747 727.3566 1057.4703 1480.3654 2134.2041 3015.9138 4630.1206 7638.1265 13555.7031 | lr 3.4e-04 | norm 4143.8936 | dt 9.884 +type train | step 2620 | loss 109.4577 213.7246 323.5695 514.2140 750.5693 1075.6879 1498.5645 2138.1489 2999.2834 4621.0879 7666.2974 13699.8174 | lr 3.4e-04 | norm 4739.1646 | dt 9.884 +type train | step 2621 | loss 95.0322 187.1006 298.2419 489.3412 732.4663 1071.0431 1521.0178 2205.9492 3136.0261 4898.0200 8109.9980 14495.8115 | lr 3.4e-04 | norm 5907.3306 | dt 9.871 +type train | step 2622 | loss 112.0184 214.7780 328.1976 517.2831 753.0359 1095.7914 1533.5913 2198.5034 3052.3237 4691.7651 7793.5586 13951.2822 | lr 3.4e-04 | norm 5775.6709 | dt 9.885 +type train | step 2623 | loss 106.1943 205.1286 318.5833 511.8784 751.2994 1084.6263 1516.6055 2186.0867 3102.1956 4797.2104 7948.7090 14327.1357 | lr 3.4e-04 | norm 6208.4082 | dt 9.861 +type train | step 2624 | loss 104.4314 201.7733 312.7905 505.4553 745.9103 1083.2922 1513.3911 2179.8308 3068.3689 4723.8101 7815.3218 13919.4639 | lr 3.4e-04 | norm 4309.5806 | dt 9.887 +type train | step 2625 | loss 100.2002 194.7646 301.5797 487.6702 720.1605 1046.6697 1466.7594 2113.9651 2971.3887 4587.8579 7570.6782 13516.2236 | lr 3.4e-04 | norm 4963.0161 | dt 9.893 +type train | step 2626 | loss 107.3465 209.7507 322.2545 520.4717 759.8798 1111.9584 1556.7529 2251.0908 3124.6021 4714.5391 7679.3662 13483.4443 | lr 3.4e-04 | norm 4404.4746 | dt 9.881 +type train | step 2627 | loss 94.9704 182.7872 286.3219 467.4455 695.1915 1009.8815 1422.6968 2054.9180 2923.1697 4534.2534 7552.7510 13442.9023 | lr 3.4e-04 | norm 4355.1274 | dt 9.886 +type train | step 2628 | loss 97.5559 189.2577 297.5749 487.7480 719.0670 1050.1957 1474.5607 2123.2910 2997.0635 4649.1040 7701.4385 13715.7461 | lr 3.4e-04 | norm 3836.2017 | dt 9.876 +type train | step 2629 | loss 107.8362 209.4732 320.0309 515.2767 750.8890 1087.5687 1515.7178 2163.3848 3006.9856 4648.4014 7682.4014 13701.6367 | lr 3.4e-04 | norm 5262.7949 | dt 9.870 +type train | step 2630 | loss 95.6023 184.6834 289.8185 473.4876 700.2482 1023.8983 1445.3650 2092.3545 2976.6997 4631.4971 7677.8799 13729.8965 | lr 3.4e-04 | norm 5066.8276 | dt 9.868 +type train | step 2631 | loss 104.7006 203.1527 316.7823 509.8405 744.9609 1077.4393 1508.7266 2162.3289 3041.9053 4702.1108 7752.8359 13823.7480 | lr 3.4e-04 | norm 4482.0356 | dt 9.891 +type train | step 2632 | loss 97.7582 187.5339 292.1664 478.0792 707.4778 1035.6600 1465.0793 2125.2205 3007.3772 4654.8726 7704.1396 13814.6074 | lr 3.4e-04 | norm 4764.0093 | dt 9.876 +type train | step 2633 | loss 102.1429 199.1942 312.5096 507.2173 748.6021 1082.2273 1516.6835 2178.9143 3093.3523 4778.6157 7914.2822 14086.7275 | lr 3.4e-04 | norm 4436.2534 | dt 9.880 +type train | step 2634 | loss 102.2545 199.4681 309.1824 497.1049 730.4734 1060.4872 1486.7927 2131.9319 3015.8291 4687.1553 7765.3770 13880.0654 | lr 3.4e-04 | norm 4306.1748 | dt 9.885 +type train | step 2635 | loss 114.3298 221.9096 337.5391 527.3152 768.1866 1117.0170 1557.6621 2232.1230 3091.2024 4721.5088 7867.5962 14179.5107 | lr 3.4e-04 | norm 7344.7495 | dt 9.858 +type train | step 2636 | loss 108.9469 211.9564 326.5864 530.0100 776.0950 1124.3448 1564.1709 2242.9341 3104.2849 4760.0044 7828.7422 14136.6221 | lr 3.4e-04 | norm 6183.0952 | dt 9.869 +type train | step 2637 | loss 103.9616 200.5108 311.9303 507.9507 751.2805 1084.6107 1523.3608 2191.5759 3099.9097 4771.8921 7850.8735 13987.9580 | lr 3.4e-04 | norm 5232.1172 | dt 9.882 +type train | step 2638 | loss 102.8588 199.5668 310.4557 504.6855 740.4739 1079.2631 1511.5085 2165.6138 3044.5566 4685.9688 7757.7349 13952.7168 | lr 3.3e-04 | norm 4955.6968 | dt 9.875 +type train | step 2639 | loss 104.0008 204.4500 316.1702 509.4268 743.3716 1077.0333 1509.1229 2174.4006 3054.9883 4682.4492 7697.7476 13750.3145 | lr 3.3e-04 | norm 5121.8032 | dt 9.884 +type train | step 2640 | loss 103.9491 202.1081 311.4142 503.1707 740.5762 1067.8335 1490.9088 2140.0002 3029.1729 4663.1875 7691.8071 13753.6074 | lr 3.3e-04 | norm 4647.8208 | dt 9.879 +type train | step 2641 | loss 107.4733 209.1057 319.2792 509.7796 746.5016 1081.0876 1517.6864 2184.1672 3072.9580 4733.3496 7807.0527 13801.1621 | lr 3.3e-04 | norm 4607.8965 | dt 9.883 +type train | step 2642 | loss 105.6314 205.7097 319.2822 520.4839 769.1450 1114.4359 1567.2849 2257.6184 3199.8694 4963.5103 8244.8555 14875.9385 | lr 3.3e-04 | norm 6357.3608 | dt 9.876 +type train | step 2643 | loss 108.8045 209.2057 319.0006 514.0652 749.9919 1088.2836 1521.6785 2175.8474 3047.0127 4645.5918 7603.7222 13536.0410 | lr 3.3e-04 | norm 4965.2705 | dt 9.882 +type train | step 2644 | loss 98.9322 191.7847 301.1498 492.8303 728.4314 1063.3978 1492.4338 2149.4783 3032.0112 4696.4771 7756.4141 13843.5391 | lr 3.3e-04 | norm 4302.4268 | dt 9.876 +type train | step 2645 | loss 110.9874 217.7475 327.1394 522.9332 765.1254 1111.4242 1550.5054 2213.3511 3102.7068 4752.2944 7828.5601 14025.5859 | lr 3.3e-04 | norm 4332.2305 | dt 10.191 +type train | step 2646 | loss 105.3216 203.8266 316.1607 503.4833 739.5899 1064.0527 1487.3647 2124.1025 3001.8716 4613.0059 7600.5278 13535.9404 | lr 3.3e-04 | norm 4003.4863 | dt 9.883 +type train | step 2647 | loss 92.2178 177.8757 280.0415 459.8655 687.6385 1003.0013 1420.7399 2057.6489 2933.1604 4563.6938 7552.7705 13432.4609 | lr 3.3e-04 | norm 4559.4731 | dt 9.879 +type train | step 2648 | loss 103.6465 201.6837 311.5405 508.6745 742.1128 1074.9059 1501.7755 2156.8892 3035.7451 4683.2378 7695.2651 13744.5811 | lr 3.3e-04 | norm 4873.2822 | dt 9.874 +type train | step 2649 | loss 104.9035 205.9483 314.3827 506.3549 743.4915 1082.6188 1511.0574 2185.9790 3076.9741 4762.8579 7884.0713 14074.1201 | lr 3.3e-04 | norm 5021.2500 | dt 9.874 +type train | step 2650 | loss 103.1762 201.0149 309.4062 499.6336 733.5312 1056.6624 1475.9320 2108.8701 2968.1960 4539.9946 7458.8599 13247.3340 | lr 3.3e-04 | norm 5498.8594 | dt 9.886 +type train | step 2651 | loss 107.9850 210.6592 318.3107 515.8776 752.8636 1110.3169 1568.3085 2262.8406 3157.6624 4843.9927 8037.8887 14481.5957 | lr 3.3e-04 | norm 5642.5566 | dt 9.883 +type train | step 2652 | loss 104.3825 203.2910 311.2861 502.7151 739.0817 1082.7786 1530.3274 2212.0784 3109.0186 4782.3198 7850.2583 14043.3027 | lr 3.3e-04 | norm 5254.4902 | dt 9.875 +type train | step 2653 | loss 105.0432 206.1170 321.7481 519.7939 762.4202 1111.4235 1562.6903 2233.8010 3125.9849 4818.5420 7945.8706 14174.2471 | lr 3.3e-04 | norm 5680.3560 | dt 9.888 +type train | step 2654 | loss 101.9207 198.7870 305.4792 494.2573 730.8868 1064.3473 1494.2122 2142.7166 3029.9719 4704.6987 7836.2510 14160.3877 | lr 3.3e-04 | norm 4477.1343 | dt 9.874 +type train | step 2655 | loss 111.4992 219.7518 329.1743 534.2531 771.3151 1124.9023 1570.8381 2258.0005 3136.5808 4805.4365 7892.0420 14136.3096 | lr 3.3e-04 | norm 6344.9126 | dt 9.875 +type train | step 2656 | loss 98.2881 193.7063 300.0020 488.0781 721.6687 1052.9127 1473.2531 2125.7996 3018.2002 4670.1743 7740.8789 13826.7812 | lr 3.3e-04 | norm 4279.0942 | dt 9.891 +type train | step 2657 | loss 98.5891 190.7778 299.0487 485.7269 717.5460 1045.3883 1464.7604 2105.9753 2993.8628 4638.5889 7668.8926 13637.4199 | lr 3.3e-04 | norm 4444.9805 | dt 9.879 +type train | step 2658 | loss 97.7845 189.2354 295.9504 482.6849 715.4279 1038.7046 1465.1700 2112.9758 3012.7588 4667.3203 7730.7080 13761.7041 | lr 3.3e-04 | norm 4168.2236 | dt 9.872 +type train | step 2659 | loss 96.3048 188.8112 294.7479 479.9062 711.6076 1031.4247 1446.0352 2078.6506 2956.3438 4552.7017 7552.1162 13487.0645 | lr 3.3e-04 | norm 4356.9531 | dt 9.878 +type train | step 2660 | loss 108.5503 210.9496 323.6120 519.7372 769.2067 1120.8744 1572.6528 2261.2524 3153.4070 4825.5024 7910.5308 14044.6309 | lr 3.3e-04 | norm 5471.1011 | dt 9.885 +type train | step 2661 | loss 96.4119 187.8074 295.4027 481.9613 714.4896 1041.4592 1460.5197 2097.1897 2978.7532 4610.2461 7591.5156 13484.2832 | lr 3.3e-04 | norm 4215.2798 | dt 9.893 +type train | step 2662 | loss 107.9570 206.5707 317.6659 512.9319 750.0980 1087.1672 1519.0922 2174.7617 3069.6001 4716.7373 7824.1890 14110.3809 | lr 3.3e-04 | norm 4678.7598 | dt 9.901 +type train | step 2663 | loss 106.2510 206.4866 316.5241 503.2715 735.1859 1058.5946 1477.4485 2113.1370 2973.8525 4595.9126 7713.3965 13939.5342 | lr 3.3e-04 | norm 5556.2026 | dt 9.869 +type train | step 2664 | loss 105.2273 203.1046 308.9025 493.4239 720.4257 1041.9124 1461.4690 2096.3284 2945.3643 4533.3457 7549.5557 13445.0723 | lr 3.3e-04 | norm 4872.7578 | dt 9.883 +type train | step 2665 | loss 106.2739 206.7205 319.2023 513.0294 748.6758 1095.7288 1535.9175 2214.3242 3104.2043 4781.2168 7895.0605 14004.6133 | lr 3.3e-04 | norm 5454.7686 | dt 9.873 +type train | step 2666 | loss 105.2590 203.7104 313.2491 500.0121 731.4760 1059.4653 1479.6267 2130.0825 2999.9570 4637.5938 7656.4819 13695.0312 | lr 3.3e-04 | norm 5084.0933 | dt 9.869 +type train | step 2667 | loss 98.8546 196.7787 314.0547 514.4181 756.9203 1099.8136 1562.1687 2249.7510 3239.0547 5026.8359 8306.0078 14812.5781 | lr 3.3e-04 | norm 9982.5967 | dt 9.864 +type train | step 2668 | loss 97.7150 198.1204 320.6614 525.2907 773.7325 1136.5382 1626.1772 2355.6201 3393.6743 5272.0918 8700.0830 15426.1211 | lr 3.3e-04 | norm 13185.2471 | dt 9.866 +type train | step 2669 | loss 94.5138 190.4777 306.7135 506.4517 752.2339 1112.6624 1607.8795 2328.6733 3339.4724 5213.8784 8668.1094 15323.3574 | lr 3.3e-04 | norm 12503.9238 | dt 9.852 +type train | step 2670 | loss 102.0298 201.2933 316.8659 513.8337 757.0380 1098.3250 1555.6301 2246.2278 3216.7903 4978.7598 8220.8281 14471.8887 | lr 3.3e-04 | norm 7084.0396 | dt 9.877 +type train | step 2671 | loss 106.2048 207.2502 313.8839 504.9429 734.4705 1073.8794 1503.1450 2167.7351 3038.4937 4650.8032 7682.9775 13672.4414 | lr 3.3e-04 | norm 5977.7944 | dt 9.884 +type train | step 2672 | loss 101.1914 197.2368 305.1360 494.5718 726.5641 1064.6636 1494.6553 2160.6362 3045.5449 4718.9316 7819.1450 14022.5186 | lr 3.3e-04 | norm 6262.6294 | dt 9.890 +type train | step 2673 | loss 97.3209 190.0114 300.0616 489.7448 724.5280 1058.6331 1492.5728 2149.1069 3058.1975 4733.8726 7843.7793 14119.5684 | lr 3.3e-04 | norm 7070.7271 | dt 9.879 +type train | step 2674 | loss 108.9406 209.5305 322.0374 520.0637 760.9642 1101.9690 1542.5687 2208.5996 3113.2742 4799.0801 7945.8496 14252.9990 | lr 3.3e-04 | norm 6904.7534 | dt 9.878 +type train | step 2675 | loss 103.4305 201.5885 312.5362 502.9484 733.9340 1057.0203 1475.1885 2106.7495 2970.3965 4579.8340 7532.6582 13471.4229 | lr 3.3e-04 | norm 5834.8687 | dt 9.899 +type train | step 2676 | loss 99.2586 191.4893 300.5276 491.6492 725.5006 1049.8262 1468.6527 2106.5596 3000.1287 4637.2939 7684.2974 13653.6074 | lr 3.3e-04 | norm 5104.6543 | dt 9.887 +type train | step 2677 | loss 99.3242 189.8740 298.1027 482.2628 712.5680 1036.9325 1460.4034 2110.1880 3001.7493 4663.5771 7708.7217 13694.8145 | lr 3.3e-04 | norm 5013.1074 | dt 9.880 +type train | step 2678 | loss 105.3851 205.4375 316.2273 509.6845 747.5905 1107.7153 1566.3373 2273.8472 3179.4551 4856.8931 7952.3467 14121.3662 | lr 3.3e-04 | norm 5041.6445 | dt 9.867 +type train | step 2679 | loss 97.7760 190.5869 296.4521 481.9290 712.7191 1041.0273 1470.6836 2118.7957 2994.7583 4630.2759 7679.8618 13783.9609 | lr 3.3e-04 | norm 4891.7407 | dt 9.894 +type train | step 2680 | loss 99.0308 190.8539 298.7365 485.0463 715.9327 1044.7620 1467.2507 2114.9407 2983.5195 4614.9404 7622.5112 13576.7617 | lr 3.3e-04 | norm 4335.9141 | dt 9.877 +type train | step 2681 | loss 102.7868 199.6210 307.3419 496.2947 729.6553 1057.2394 1478.5647 2115.8333 2985.8445 4604.2139 7562.2236 13452.8271 | lr 3.3e-04 | norm 4091.8396 | dt 9.886 +type train | step 2682 | loss 114.3496 220.9965 334.8659 526.1324 767.6870 1109.6178 1557.2959 2239.2878 3155.8699 4879.8555 8107.3521 14662.4561 | lr 3.3e-04 | norm 6232.8721 | dt 9.886 +type train | step 2683 | loss 100.6581 196.0546 304.7448 495.3519 729.0832 1062.7223 1487.9498 2141.6865 3017.8918 4652.4067 7701.0005 13751.9248 | lr 3.3e-04 | norm 4588.9458 | dt 9.886 +type train | step 2684 | loss 103.9405 201.8431 309.3151 495.8614 726.6034 1050.9548 1469.5846 2100.8093 2954.6738 4529.0107 7439.2402 13138.2373 | lr 3.3e-04 | norm 4673.4146 | dt 9.883 +type train | step 2685 | loss 98.9132 188.6711 292.7213 477.7792 706.6819 1030.6843 1449.7750 2095.7529 2965.2148 4567.7520 7536.4771 13403.6924 | lr 3.3e-04 | norm 4890.0410 | dt 9.891 +type train | step 2686 | loss 99.9453 196.3515 304.9829 495.7558 728.2802 1059.5911 1485.4509 2140.4805 3024.2581 4680.8569 7764.5688 13894.3594 | lr 3.3e-04 | norm 4639.1631 | dt 9.901 +type train | step 2687 | loss 97.3981 187.8818 296.6004 484.1221 715.1427 1045.1248 1481.7361 2139.8672 3045.7744 4742.0391 7894.3867 14187.6104 | lr 3.3e-04 | norm 4941.5122 | dt 9.876 +type train | step 2688 | loss 98.5689 192.1136 302.7502 495.3703 737.0908 1079.7391 1528.3986 2218.2795 3144.3650 4873.6123 8083.7686 14413.1309 | lr 3.3e-04 | norm 5834.0308 | dt 9.894 +type train | step 2689 | loss 101.2679 196.3883 303.3104 490.4676 716.7628 1039.3171 1452.9248 2078.0103 2928.5742 4512.7988 7450.1040 13259.9209 | lr 3.3e-04 | norm 4284.6289 | dt 9.875 +type train | step 2690 | loss 108.1855 210.0155 325.7154 522.8647 765.5682 1105.4137 1550.7966 2224.2773 3123.7712 4822.0605 8065.5674 14492.7383 | lr 3.3e-04 | norm 6024.7412 | dt 9.869 +type train | step 2691 | loss 97.1425 188.2756 294.1863 481.8765 713.1346 1040.2019 1472.4453 2127.0159 3026.7764 4719.1724 7845.9839 14019.0918 | lr 3.3e-04 | norm 4984.3809 | dt 9.884 +type train | step 2692 | loss 102.9239 201.2213 312.8116 506.3231 744.4949 1081.2876 1515.0396 2172.8013 3067.6895 4710.5186 7771.0811 13864.3369 | lr 3.3e-04 | norm 5745.8462 | dt 9.903 +type train | step 2693 | loss 101.8247 198.1246 306.3049 496.0066 730.0013 1062.6271 1493.7131 2142.7371 3032.5010 4672.6494 7706.9268 13681.4316 | lr 3.3e-04 | norm 4942.2017 | dt 9.883 +type train | step 2694 | loss 93.5067 182.2603 287.1794 475.7573 709.7845 1043.5911 1481.2344 2150.5583 3040.9624 4703.9258 7794.4883 14084.8926 | lr 3.3e-04 | norm 6143.0767 | dt 9.875 +type train | step 2695 | loss 101.9085 196.8432 307.1605 503.9256 744.2927 1084.0835 1528.1863 2211.8750 3092.4202 4781.9824 7953.3682 14364.2363 | lr 3.3e-04 | norm 8005.5239 | dt 9.866 +type train | step 2696 | loss 105.8712 206.4657 317.9215 515.0609 750.7237 1088.3452 1520.8528 2187.7952 3068.6768 4707.9009 7739.0034 13799.3945 | lr 3.3e-04 | norm 4865.0366 | dt 9.907 +type train | step 2697 | loss 100.1076 195.3139 302.8066 490.7090 719.6543 1047.3282 1470.3209 2114.3591 2999.0872 4636.8486 7638.8428 13563.3516 | lr 3.3e-04 | norm 4679.4097 | dt 9.898 +type train | step 2698 | loss 102.0564 199.2677 306.5329 497.1676 728.1706 1068.5151 1486.4885 2141.4033 2985.8569 4588.2085 7538.4907 13445.2129 | lr 3.3e-04 | norm 5182.1030 | dt 9.879 +type train | step 2699 | loss 101.5938 197.5488 307.3941 497.3125 734.1060 1061.9600 1484.5244 2128.1702 3018.9221 4666.5083 7692.3584 13752.7500 | lr 3.3e-04 | norm 4820.2446 | dt 9.896 +type train | step 2700 | loss 107.1165 208.3830 325.1889 524.6292 772.8448 1105.1108 1546.3679 2197.4575 3120.2234 4755.6802 7738.7148 13662.6201 | lr 3.3e-04 | norm 6382.9058 | dt 9.895 +type train | step 2701 | loss 97.4733 188.7103 293.5789 478.4395 708.4042 1035.0066 1459.8317 2119.0107 2996.4207 4667.9072 7701.7886 13735.9238 | lr 3.3e-04 | norm 4933.6147 | dt 9.872 +type train | step 2702 | loss 97.0569 187.8556 295.4655 482.3981 714.0924 1046.9056 1474.2493 2131.6838 3033.2673 4687.7085 7721.5356 13709.5078 | lr 3.3e-04 | norm 4549.9692 | dt 9.882 +type train | step 2703 | loss 90.2941 173.5703 274.7220 454.6416 679.8876 990.5217 1399.8284 2024.7676 2893.7913 4486.9072 7403.3486 13141.5352 | lr 3.3e-04 | norm 4789.9541 | dt 9.881 +type train | step 2704 | loss 96.0767 186.0249 295.8831 490.5599 734.1981 1091.9000 1551.3459 2255.3223 3178.5693 4972.4390 8207.0645 14659.4443 | lr 3.3e-04 | norm 8297.6426 | dt 9.870 +type train | step 2705 | loss 106.2767 205.8072 317.1091 510.4008 743.6603 1081.2212 1509.5243 2151.3777 3021.6741 4615.3330 7606.4590 13548.9980 | lr 3.3e-04 | norm 4401.9136 | dt 9.878 +type train | step 2706 | loss 96.2482 185.7821 293.4463 480.5504 708.5634 1029.0425 1450.8021 2081.0295 2954.4150 4569.4497 7567.6919 13425.3262 | lr 3.2e-04 | norm 4039.4993 | dt 9.882 +type train | step 2707 | loss 100.6551 194.9337 304.4458 494.4619 730.1945 1063.7444 1491.5249 2136.9402 3030.5986 4677.4980 7710.3418 13648.4521 | lr 3.2e-04 | norm 4570.2993 | dt 9.906 +type train | step 2708 | loss 104.3227 201.2649 312.7462 508.7896 745.0357 1084.2373 1504.2184 2153.7134 3006.9968 4616.6182 7600.4365 13512.3984 | lr 3.2e-04 | norm 4395.8623 | dt 9.898 +type train | step 2709 | loss 121.9992 239.3201 364.7854 577.7307 821.8201 1162.8086 1581.1721 2206.4197 2984.1365 4489.8516 7206.9268 12814.5762 | lr 3.2e-04 | norm 6604.5791 | dt 9.882 +type train | step 2710 | loss 99.2694 192.6363 299.5068 486.3053 717.2434 1044.8423 1470.1926 2113.3323 2992.1035 4604.9307 7573.5405 13400.6904 | lr 3.2e-04 | norm 4411.8970 | dt 9.907 +type train | step 2711 | loss 104.0356 199.9971 308.2262 498.8316 731.1166 1062.5640 1491.3748 2161.2620 3046.5435 4698.3535 7780.5283 13925.7539 | lr 3.2e-04 | norm 4564.7939 | dt 9.916 +type train | step 2712 | loss 108.0073 212.3209 330.8287 535.5072 781.3387 1126.4487 1567.4202 2233.6736 3121.3120 4778.9653 7850.6387 14053.0938 | lr 3.2e-04 | norm 5324.3003 | dt 9.941 +type train | step 2713 | loss 94.1693 182.3325 289.4763 476.4652 709.0746 1037.8621 1466.4561 2117.0166 3005.1821 4636.9600 7637.3862 13544.6797 | lr 3.2e-04 | norm 4061.0269 | dt 9.920 +type train | step 2714 | loss 100.6715 197.1299 307.4933 497.5767 733.0971 1061.5939 1485.2716 2134.1118 3013.0847 4662.4165 7714.1636 13719.5742 | lr 3.2e-04 | norm 4122.8784 | dt 9.917 +type train | step 2715 | loss 95.5542 185.9021 294.7074 486.4062 718.2989 1052.1957 1486.3354 2145.7881 3037.2190 4684.4131 7719.2930 13690.4736 | lr 3.2e-04 | norm 5068.2441 | dt 9.913 +type train | step 2716 | loss 97.2706 189.3384 297.5486 485.9251 720.5291 1046.7950 1478.0498 2127.5310 3040.1838 4703.4663 7810.6826 13884.3867 | lr 3.2e-04 | norm 3795.2554 | dt 9.878 +type train | step 2717 | loss 98.0961 189.6619 296.2895 483.2297 714.1910 1047.5115 1478.4227 2131.0166 3000.8787 4628.1685 7616.5542 13445.8848 | lr 3.2e-04 | norm 3872.8127 | dt 9.889 +type train | step 2718 | loss 97.1402 188.4371 293.7520 481.8379 712.1794 1040.9692 1469.2122 2119.9541 3004.8474 4641.4302 7662.7148 13614.9346 | lr 3.2e-04 | norm 4214.4917 | dt 9.891 +type train | step 2719 | loss 95.7472 184.6695 289.7745 472.7542 704.4908 1027.9868 1452.3988 2093.4395 2972.5840 4583.2144 7526.0161 13359.2178 | lr 3.2e-04 | norm 4395.5449 | dt 9.885 +type train | step 2720 | loss 113.0110 217.7151 329.8033 525.7097 761.0146 1103.4825 1527.5211 2169.4812 2993.5027 4611.5649 7563.8452 13529.0615 | lr 3.2e-04 | norm 9076.8340 | dt 9.870 +type train | step 2721 | loss 106.0915 205.1296 316.2856 513.5242 749.0410 1085.9576 1513.3638 2155.8499 3023.6392 4622.2842 7610.7012 13541.7695 | lr 3.2e-04 | norm 4161.4761 | dt 9.877 +type train | step 2722 | loss 97.8690 189.7626 298.5909 487.4612 718.4567 1048.8711 1468.9500 2118.8767 3008.9077 4659.5249 7697.6396 13716.2275 | lr 3.2e-04 | norm 4290.8325 | dt 9.876 +type train | step 2723 | loss 97.2588 189.5504 294.2719 478.0574 706.2412 1028.2668 1443.5347 2090.6399 2979.2849 4615.1279 7633.4912 13560.0059 | lr 3.2e-04 | norm 4805.9238 | dt 9.875 +type train | step 2724 | loss 101.7865 195.6534 303.8102 493.1082 729.0547 1062.8148 1489.2913 2142.0784 3021.0793 4654.2866 7654.7715 13466.2891 | lr 3.2e-04 | norm 3887.2444 | dt 9.889 +type train | step 2725 | loss 102.7515 199.7300 310.7914 502.4271 736.1303 1064.9513 1489.6624 2134.7761 3013.6050 4654.1064 7667.1064 13617.9141 | lr 3.2e-04 | norm 4407.0464 | dt 9.882 +type train | step 2726 | loss 97.7268 189.3550 295.8431 482.2851 714.6596 1034.7900 1461.5211 2104.1091 2992.0618 4635.4824 7684.4180 13717.8555 | lr 3.2e-04 | norm 5135.6201 | dt 9.870 +type train | step 2727 | loss 99.9292 194.7705 304.3624 499.1887 734.8740 1075.0674 1511.4518 2183.8560 3078.6274 4741.4146 7805.0112 13838.1484 | lr 3.2e-04 | norm 4329.3789 | dt 9.890 +type train | step 2728 | loss 103.4370 201.7592 314.8943 509.1452 749.9938 1086.2762 1522.3708 2183.6111 3086.6953 4767.7998 7874.5439 14017.3848 | lr 3.2e-04 | norm 4397.0786 | dt 9.879 +type train | step 2729 | loss 111.0495 222.3275 337.4093 542.1852 788.2162 1134.6859 1577.5546 2253.4275 3157.0693 4851.2778 8043.0205 14531.1738 | lr 3.2e-04 | norm 6830.6738 | dt 9.875 +type train | step 2730 | loss 99.3077 191.4035 302.0870 492.4610 728.1063 1064.2854 1503.2797 2194.2000 3117.7266 4841.3066 7991.5063 14268.6465 | lr 3.2e-04 | norm 5535.2690 | dt 9.866 +type train | step 2731 | loss 106.7605 209.3711 320.2569 521.5793 762.4827 1117.2385 1562.2897 2250.7393 3159.6064 4859.4180 8023.2036 14310.4736 | lr 3.2e-04 | norm 5577.5498 | dt 9.874 +type train | step 2732 | loss 96.5015 188.3588 294.4498 477.9492 712.7091 1041.7058 1477.7013 2141.1746 3036.6973 4714.3804 7847.4409 14021.3887 | lr 3.2e-04 | norm 4943.8667 | dt 9.887 +type train | step 2733 | loss 96.8056 187.2119 290.8819 474.2047 702.2334 1028.0350 1448.0002 2088.2473 2947.6904 4571.0161 7554.3374 13560.7891 | lr 3.2e-04 | norm 4595.7461 | dt 9.865 +type train | step 2734 | loss 97.0757 189.2161 297.1910 486.1768 720.0874 1058.5790 1499.5065 2164.0032 3049.6125 4719.3735 7777.4668 13855.9170 | lr 3.2e-04 | norm 4709.4414 | dt 9.904 +type train | step 2735 | loss 102.2739 197.4449 307.1974 492.9689 725.1360 1055.7747 1481.3390 2121.0129 3002.6880 4657.4434 7688.2354 13738.6562 | lr 3.2e-04 | norm 4581.4927 | dt 9.889 +type train | step 2736 | loss 101.3154 193.4924 303.6208 492.8336 722.8032 1060.2832 1486.9004 2143.4106 2986.6499 4619.3511 7650.1118 13790.5391 | lr 3.2e-04 | norm 6504.0718 | dt 9.850 +type train | step 2737 | loss 101.2717 194.6423 302.7033 490.8287 718.1387 1041.1488 1450.0334 2069.7217 2912.2783 4478.5679 7402.8711 13149.0547 | lr 3.2e-04 | norm 4117.1465 | dt 9.890 +type train | step 2738 | loss 101.4689 196.9340 306.8230 496.6518 731.5320 1067.8872 1497.4193 2160.4358 3052.9299 4705.9658 7773.6592 13854.5557 | lr 3.2e-04 | norm 4489.7739 | dt 9.889 +type train | step 2739 | loss 101.1555 194.0021 299.2527 484.6329 713.3689 1044.3989 1463.4049 2111.7532 2969.2732 4579.4106 7529.1714 13360.3164 | lr 3.2e-04 | norm 4752.0483 | dt 9.885 +type train | step 2740 | loss 92.5745 179.2025 283.6240 468.9069 698.6500 1029.2377 1467.0598 2132.2827 3046.2993 4768.3120 7968.3442 14312.4160 | lr 3.2e-04 | norm 5220.6006 | dt 9.855 +type train | step 2741 | loss 102.3314 198.9761 309.1190 500.9566 738.7559 1069.6180 1496.0773 2145.5654 3033.3313 4708.9927 7800.2612 13980.9004 | lr 3.2e-04 | norm 4912.7148 | dt 9.875 +type train | step 2742 | loss 101.6992 198.0291 306.3135 494.9652 728.5557 1053.7522 1482.9420 2131.9189 3008.4409 4662.4136 7666.8569 13684.9355 | lr 3.2e-04 | norm 4698.1377 | dt 9.874 +type train | step 2743 | loss 96.9149 187.8993 290.6965 476.4270 706.7626 1037.0234 1458.4788 2109.9658 2986.9077 4631.5620 7668.8740 13678.9795 | lr 3.2e-04 | norm 4711.8682 | dt 9.874 +type train | step 2744 | loss 104.7525 205.1242 318.2067 510.7878 751.1371 1085.9987 1522.8844 2165.6924 3034.2139 4675.3945 7749.5400 13838.0674 | lr 3.2e-04 | norm 4856.6841 | dt 9.881 +type train | step 2745 | loss 106.7120 207.9206 320.6684 517.9842 756.5987 1099.1646 1528.4258 2171.0007 3031.4954 4647.0874 7671.5039 13691.1162 | lr 3.2e-04 | norm 4384.9478 | dt 9.886 +type train | step 2746 | loss 109.6198 215.4707 326.1183 521.6282 761.1846 1102.1595 1545.0050 2208.9756 3094.7900 4764.3057 7865.8896 14004.4375 | lr 3.2e-04 | norm 4210.4243 | dt 9.891 +type train | step 2747 | loss 96.9886 187.9352 295.7661 481.1140 712.5383 1032.5459 1448.9199 2079.6262 2947.1021 4563.6758 7516.1006 13303.4004 | lr 3.2e-04 | norm 3859.7466 | dt 9.892 +type train | step 2748 | loss 110.6644 216.0052 330.8654 527.3951 762.3785 1093.8665 1521.1039 2173.5757 3050.4341 4707.7427 7829.2666 13923.5400 | lr 3.2e-04 | norm 5852.3105 | dt 9.865 +type train | step 2749 | loss 94.4915 184.0952 290.5001 473.9994 706.5430 1032.3408 1458.4340 2107.1709 3007.0251 4666.9385 7683.3706 13580.4639 | lr 3.2e-04 | norm 4912.7524 | dt 9.876 +type train | step 2750 | loss 106.5258 206.7661 319.3402 516.1621 755.2921 1099.0405 1532.9122 2211.0144 3092.7769 4740.9219 7830.2002 14050.2305 | lr 3.2e-04 | norm 5651.7700 | dt 9.870 +type train | step 2751 | loss 103.0554 198.1997 304.0443 492.7214 721.8503 1048.2312 1466.7626 2106.8542 2972.2341 4580.7217 7584.4180 13566.8896 | lr 3.2e-04 | norm 4883.5356 | dt 9.881 +type train | step 2752 | loss 104.3441 201.0035 310.9397 500.8741 735.7719 1068.7892 1502.3080 2164.6250 3044.0322 4686.1011 7721.1660 13733.2998 | lr 3.2e-04 | norm 4793.0220 | dt 9.878 +type train | step 2753 | loss 96.5636 186.8640 290.4137 471.2918 694.8814 1002.3610 1401.1318 2005.0372 2855.5513 4401.2559 7273.0015 12925.6562 | lr 3.2e-04 | norm 3913.5037 | dt 9.878 +type train | step 2754 | loss 96.3240 186.4328 295.4947 482.0522 716.1480 1048.2296 1479.4180 2126.6953 3018.7141 4670.0913 7738.3330 13707.2168 | lr 3.2e-04 | norm 4274.0806 | dt 9.878 +type train | step 2755 | loss 109.3326 211.2545 320.3716 510.3601 741.4659 1075.7195 1495.0034 2142.8374 2990.2261 4588.1152 7616.3809 13633.2305 | lr 3.2e-04 | norm 5344.2349 | dt 9.862 +type train | step 2756 | loss 112.7466 215.2849 319.5411 516.0952 742.1470 1088.1167 1495.7102 2158.5347 2990.1831 4586.6445 7641.8940 13504.2002 | lr 3.2e-04 | norm 10032.2734 | dt 9.831 +type train | step 2757 | loss 107.3037 207.9548 320.8790 517.5930 757.9434 1108.2329 1549.3163 2241.7773 3119.9502 4782.5947 7891.9351 13950.2480 | lr 3.2e-04 | norm 4838.9722 | dt 9.861 +type train | step 2758 | loss 99.6589 190.9009 298.2197 484.7473 717.4347 1056.7517 1482.8137 2153.9858 3034.3970 4681.0889 7729.8257 13895.9102 | lr 3.2e-04 | norm 5235.6743 | dt 9.866 +type train | step 2759 | loss 104.9128 199.9916 311.5786 504.8743 741.8737 1074.0540 1494.2832 2132.7695 2987.9805 4619.6309 7635.9814 13731.7041 | lr 3.2e-04 | norm 5013.4443 | dt 9.878 +type train | step 2760 | loss 90.9838 174.3345 277.3648 457.7183 683.7590 998.7259 1408.2936 2029.1870 2904.8323 4511.7056 7450.1206 13190.6406 | lr 3.2e-04 | norm 4681.9341 | dt 9.877 +type train | step 2761 | loss 100.0216 195.3189 299.6601 484.1556 710.3057 1029.8347 1448.5419 2083.8137 2948.8662 4553.7803 7485.3179 13277.2461 | lr 3.2e-04 | norm 4748.2573 | dt 9.889 +type train | step 2762 | loss 96.2099 185.6272 290.2227 476.4896 708.6708 1030.4493 1446.4417 2078.6829 2950.6538 4564.8657 7571.5098 13493.5039 | lr 3.2e-04 | norm 4590.2451 | dt 9.866 +type train | step 2763 | loss 101.1326 195.9015 302.8449 491.8950 722.0032 1045.8541 1465.1079 2096.4348 2944.7480 4532.8032 7450.2026 13266.4238 | lr 3.2e-04 | norm 4752.1289 | dt 9.887 +type train | step 2764 | loss 111.0433 215.5958 333.2072 534.6279 773.0295 1113.8024 1533.3560 2171.7148 3021.9778 4651.7988 7623.6162 13642.0156 | lr 3.2e-04 | norm 6105.6191 | dt 9.860 +type train | step 2765 | loss 107.6072 212.1678 327.0085 521.5751 755.5891 1090.7133 1517.9647 2159.8730 3023.2300 4635.7085 7578.7754 13573.5537 | lr 3.2e-04 | norm 4352.1821 | dt 9.879 +type train | step 2766 | loss 98.9978 191.2320 295.4144 477.0511 704.0016 1020.0450 1438.2452 2073.8672 2944.5713 4559.5693 7525.7095 13434.8613 | lr 3.2e-04 | norm 4936.9507 | dt 9.859 +type train | step 2767 | loss 109.0826 215.8482 335.0222 533.9385 777.2156 1112.6416 1559.4991 2232.8689 3158.7839 4930.4790 8183.9307 14878.7939 | lr 3.2e-04 | norm 8012.2876 | dt 9.868 +type train | step 2768 | loss 102.3641 199.9923 308.5654 496.3743 731.0137 1055.8562 1480.6003 2122.6907 3002.2527 4640.2349 7620.3647 13525.9512 | lr 3.2e-04 | norm 4510.8618 | dt 9.882 +type train | step 2769 | loss 98.0636 190.9692 303.3191 496.0595 732.2565 1068.4216 1511.3073 2186.0813 3096.3877 4771.2373 7863.1709 14002.2510 | lr 3.2e-04 | norm 5121.3076 | dt 9.873 +type train | step 2770 | loss 104.1971 202.6388 316.4240 512.6574 752.0508 1092.5966 1536.6134 2211.6604 3118.3506 4847.8384 8080.0151 14450.5557 | lr 3.2e-04 | norm 5790.1812 | dt 9.872 +type train | step 2771 | loss 91.2012 174.3891 277.7285 457.5304 684.5380 1007.4808 1429.6232 2072.5496 2965.6262 4610.2510 7652.5278 13661.0547 | lr 3.2e-04 | norm 4497.5820 | dt 9.889 +type train | step 2772 | loss 96.5458 187.0697 294.1953 481.2894 710.7355 1037.3839 1461.5649 2105.7441 2982.3457 4594.9409 7530.0049 13287.3047 | lr 3.2e-04 | norm 4107.0859 | dt 9.877 +type train | step 2773 | loss 100.3742 190.8207 300.0490 488.3266 724.3101 1055.9246 1489.0103 2154.2041 3058.1233 4741.5381 7748.8076 13684.3457 | lr 3.2e-04 | norm 5638.5083 | dt 9.865 +type train | step 2774 | loss 103.0928 199.3767 308.7795 498.4745 731.7321 1058.1111 1482.0536 2124.4700 3003.5007 4616.4419 7612.0044 13534.3633 | lr 3.1e-04 | norm 4179.1572 | dt 9.896 +type train | step 2775 | loss 100.2327 194.1993 304.2793 495.6351 728.1434 1054.9248 1486.1156 2137.1211 3041.2673 4689.3584 7703.4419 13668.5430 | lr 3.1e-04 | norm 4179.2412 | dt 9.893 +type train | step 2776 | loss 104.1828 200.3500 310.9985 497.9518 730.9976 1070.8297 1504.4370 2169.1023 3041.7080 4715.2266 7779.0581 14018.1074 | lr 3.1e-04 | norm 5532.0210 | dt 9.863 +type train | step 2777 | loss 100.7637 202.9976 317.9464 515.6199 755.3933 1081.4341 1505.9640 2154.3594 3032.0852 4649.5322 7727.5508 13782.5566 | lr 3.1e-04 | norm 7209.1606 | dt 9.868 +type train | step 2778 | loss 98.1807 190.7351 295.9875 485.3074 714.5244 1051.3190 1481.2130 2140.2048 3001.0156 4618.2837 7587.2026 13494.7578 | lr 3.1e-04 | norm 5142.5425 | dt 9.880 +type train | step 2779 | loss 92.0531 178.6418 280.6894 463.4498 689.4536 1009.1342 1429.3269 2066.5581 2945.5356 4562.4209 7511.3618 13401.6836 | lr 3.1e-04 | norm 4618.9204 | dt 9.863 +type train | step 2780 | loss 102.7232 200.3641 310.5576 501.2217 735.9264 1070.2787 1495.5327 2144.7456 3012.7419 4616.2290 7580.2007 13428.2275 | lr 3.1e-04 | norm 4459.4751 | dt 9.893 +type train | step 2781 | loss 101.7514 197.4964 304.1942 496.6618 731.6678 1067.8210 1494.8761 2157.7397 3021.1282 4652.0371 7675.1714 13718.1572 | lr 3.1e-04 | norm 4800.8384 | dt 9.878 +type train | step 2782 | loss 97.9789 191.6001 296.3202 483.6606 713.5376 1046.2286 1482.0936 2145.3354 3016.9155 4681.2344 7770.5386 13892.9824 | lr 3.1e-04 | norm 4851.0449 | dt 9.888 +type train | step 2783 | loss 105.6061 205.3685 316.7207 513.7056 754.4229 1120.3044 1581.1814 2291.7361 3213.8696 4946.7544 8063.2803 14292.2939 | lr 3.1e-04 | norm 5472.1006 | dt 9.852 +type train | step 2784 | loss 98.7426 189.7327 294.1341 476.3750 706.4855 1039.0186 1467.1897 2116.8884 3016.4109 4671.4189 7676.1133 13677.1680 | lr 3.1e-04 | norm 4831.4395 | dt 9.862 +type train | step 2785 | loss 96.5547 186.5473 292.0515 474.9168 708.5388 1037.7897 1459.3040 2103.0618 2981.2068 4628.1191 7645.3545 13611.6777 | lr 3.1e-04 | norm 4790.9634 | dt 9.883 +type train | step 2786 | loss 96.1629 190.3049 299.2912 493.4092 729.5289 1070.7439 1503.7960 2168.3098 3065.3860 4774.2642 7907.5181 14113.1465 | lr 3.1e-04 | norm 5494.3887 | dt 9.859 +type train | step 2787 | loss 97.4741 188.6438 292.4894 474.8691 700.9374 1016.9232 1427.2478 2047.2808 2897.3088 4485.8579 7428.5664 13211.3027 | lr 3.1e-04 | norm 4104.6411 | dt 9.895 +type train | step 2788 | loss 89.7260 172.6735 274.1346 452.8781 677.3586 989.7229 1404.8105 2036.3745 2905.2695 4536.6919 7506.8340 13355.4609 | lr 3.1e-04 | norm 4585.9043 | dt 9.871 +type train | step 2789 | loss 97.2229 189.0761 294.7625 477.1177 707.1765 1030.4757 1445.2598 2080.3862 2959.8271 4547.3838 7435.5234 13187.7607 | lr 3.1e-04 | norm 5322.4678 | dt 9.860 +type train | step 2790 | loss 99.2653 191.1758 297.3989 482.6202 707.5029 1031.8143 1449.1793 2079.7249 2903.4771 4475.6982 7353.7471 13202.9463 | lr 3.1e-04 | norm 5561.8110 | dt 9.872 +type train | step 2791 | loss 110.4915 214.2340 327.0548 525.7557 766.2855 1113.6476 1554.5601 2235.9043 3136.1589 4836.0698 7904.3901 14172.1436 | lr 3.1e-04 | norm 5394.8574 | dt 9.866 +type train | step 2792 | loss 92.7976 181.1268 283.8136 467.8114 699.7126 1025.5101 1452.8027 2107.3662 2996.4585 4640.6914 7655.3242 13558.2285 | lr 3.1e-04 | norm 4498.9429 | dt 9.869 +type train | step 2793 | loss 97.3706 186.9461 291.8572 476.3229 705.4197 1027.6021 1448.7170 2078.0708 2937.8037 4537.9888 7475.9263 13236.2861 | lr 3.1e-04 | norm 4487.5332 | dt 9.882 +type train | step 2794 | loss 102.5033 199.3093 311.1251 505.2627 742.1240 1084.0565 1519.2985 2194.0757 3109.5596 4783.8525 7875.8330 14005.7793 | lr 3.1e-04 | norm 4970.4185 | dt 9.876 +type train | step 2795 | loss 103.4611 197.0878 307.3469 497.2126 734.0601 1065.3556 1496.4203 2150.5889 3054.7522 4696.1387 7726.0132 13719.5078 | lr 3.1e-04 | norm 4649.3081 | dt 9.883 +type train | step 2796 | loss 99.3443 194.2331 299.4445 487.6331 719.9958 1049.0879 1473.0187 2123.1582 3011.8774 4660.1152 7706.8408 13696.7129 | lr 3.1e-04 | norm 4258.9077 | dt 9.876 +type train | step 2797 | loss 103.9115 200.3996 309.0587 495.5356 733.9592 1072.5571 1513.3538 2164.0007 3040.3418 4661.8193 7644.6997 13450.2334 | lr 3.1e-04 | norm 4700.3096 | dt 9.893 +type train | step 2798 | loss 101.2305 194.1550 301.8465 494.4818 731.7500 1098.2610 1554.4594 2284.7454 3165.0774 4831.7344 7914.1172 14101.4180 | lr 3.1e-04 | norm 6397.1626 | dt 9.859 +type train | step 2799 | loss 107.7638 209.8745 323.6775 516.7626 755.1567 1105.8945 1557.4893 2246.5330 3115.9758 4749.6064 7778.7676 13890.8945 | lr 3.1e-04 | norm 5091.9434 | dt 9.863 +type train | step 2800 | loss 103.2953 200.8999 308.9942 496.8968 728.8728 1065.4839 1499.5186 2169.8167 3042.4817 4708.7227 7807.7524 13940.3457 | lr 3.1e-04 | norm 5066.1670 | dt 9.880 +type train | step 2801 | loss 92.9771 177.8348 278.6429 458.3017 683.8811 1002.8116 1420.8220 2066.3647 2943.9319 4579.5752 7604.3604 13666.0107 | lr 3.1e-04 | norm 5004.0625 | dt 9.878 +type train | step 2802 | loss 98.4235 191.4679 298.1648 484.9684 716.3984 1039.7222 1452.0762 2084.3179 2958.9495 4574.9092 7547.9937 13393.0439 | lr 3.1e-04 | norm 4849.5356 | dt 9.896 +type train | step 2803 | loss 104.7895 200.5641 311.0623 500.1997 731.8818 1067.9712 1491.8870 2135.8552 2994.4524 4616.4771 7599.4248 13510.8418 | lr 3.1e-04 | norm 5037.0029 | dt 9.862 +type train | step 2804 | loss 106.2030 206.4238 317.5763 513.1940 749.2688 1092.3807 1528.5250 2202.8750 3069.7886 4717.1328 7768.2974 13908.4814 | lr 3.1e-04 | norm 5415.3003 | dt 9.879 +type train | step 2805 | loss 100.6997 193.6877 304.7182 493.1904 729.4377 1064.8057 1497.1893 2157.2610 3044.3750 4692.1934 7704.4941 13749.8057 | lr 3.1e-04 | norm 4642.8174 | dt 9.888 +type train | step 2806 | loss 94.0776 181.9160 286.7037 469.3084 696.7693 1012.2142 1428.7025 2060.0808 2936.5635 4561.7314 7555.1631 13412.2021 | lr 3.1e-04 | norm 5328.2271 | dt 9.877 +type train | step 2807 | loss 141.7249 286.2444 414.1870 624.4587 911.1370 1315.7585 1833.6370 2604.7771 3560.6750 5237.2007 8266.5732 14354.0645 | lr 3.1e-04 | norm 5419.3052 | dt 9.869 +type train | step 2808 | loss 102.3808 198.9151 309.0181 495.5298 728.4709 1053.8380 1476.3655 2118.2864 3008.6492 4657.4038 7663.7700 13659.1758 | lr 3.1e-04 | norm 4692.3687 | dt 9.885 +type train | step 2809 | loss 101.1319 195.0181 303.4414 489.4862 721.0386 1050.0381 1469.3413 2113.4895 2994.9800 4629.0464 7630.7910 13618.4863 | lr 3.1e-04 | norm 4399.8105 | dt 9.894 +type train | step 2810 | loss 100.2815 190.9407 293.4935 475.7484 701.8690 1024.8000 1443.7168 2092.8994 2962.2568 4606.9688 7636.4253 13675.2061 | lr 3.1e-04 | norm 4512.9751 | dt 9.875 +type train | step 2811 | loss 118.0311 230.1733 345.8445 546.6450 781.1913 1120.2355 1545.6138 2184.9106 2989.7896 4593.3804 7500.3940 13415.1377 | lr 3.1e-04 | norm 6376.0049 | dt 9.843 +type train | step 2812 | loss 102.2273 196.1922 304.2198 495.1128 731.1964 1064.5127 1500.9220 2159.3657 3013.1523 4652.3296 7594.3999 13489.8135 | lr 3.1e-04 | norm 4575.9409 | dt 9.868 +type train | step 2813 | loss 102.8881 197.9323 304.6127 495.0074 728.3035 1061.3282 1490.0798 2153.1565 3031.1665 4663.0015 7655.6982 13648.9648 | lr 3.1e-04 | norm 4627.8193 | dt 9.882 +type train | step 2814 | loss 103.6839 200.1163 313.2305 510.3458 753.5483 1108.3051 1562.7781 2253.4607 3153.6907 4824.6079 7918.4604 14069.6299 | lr 3.1e-04 | norm 5126.6587 | dt 9.882 +type train | step 2815 | loss 97.5597 189.1975 296.3748 479.7731 711.8391 1034.3490 1457.1697 2106.7288 2987.3042 4641.6733 7677.6431 13667.7646 | lr 3.1e-04 | norm 4402.2681 | dt 9.884 +type train | step 2816 | loss 97.8971 189.3689 294.0611 476.0326 701.2201 1023.6796 1440.1976 2076.2317 2943.0747 4577.3193 7613.2827 13696.8701 | lr 3.1e-04 | norm 5046.3818 | dt 9.870 +type train | step 2817 | loss 103.7783 201.8900 313.1219 505.6133 741.1580 1083.9471 1526.9871 2197.6631 3096.1467 4760.7363 7840.1084 13974.2461 | lr 3.1e-04 | norm 4977.3706 | dt 9.870 +type train | step 2818 | loss 94.7176 183.6201 288.7351 474.6296 700.9231 1023.0971 1442.4832 2084.6272 2961.7410 4584.3857 7604.8198 13519.3486 | lr 3.1e-04 | norm 4155.0996 | dt 9.882 +type train | step 2819 | loss 95.2908 184.4906 286.4331 469.0112 692.1075 1012.6383 1417.8578 2049.9863 2906.6765 4494.9111 7417.0059 13147.0732 | lr 3.1e-04 | norm 4060.8220 | dt 9.888 +type train | step 2820 | loss 98.4558 189.9576 292.3912 477.6126 708.3339 1042.6135 1469.5455 2127.1226 3015.3264 4659.1172 7641.6021 13502.0703 | lr 3.1e-04 | norm 4200.5044 | dt 9.873 +type train | step 2821 | loss 95.7708 186.7757 291.9514 478.1032 710.4141 1040.4546 1474.1414 2129.7563 3024.0852 4691.4404 7688.0801 13544.8525 | lr 3.1e-04 | norm 4224.6167 | dt 9.883 +type train | step 2822 | loss 98.3951 191.4755 300.5617 489.3835 722.0266 1069.6045 1516.8062 2200.4392 3114.6553 4803.3447 7943.9038 14145.0527 | lr 3.1e-04 | norm 5336.4214 | dt 9.882 +type train | step 2823 | loss 103.8951 203.4150 315.7580 506.9354 741.9455 1074.3164 1494.9742 2143.4138 2994.2971 4621.3545 7645.0176 13700.3037 | lr 3.1e-04 | norm 4916.0562 | dt 9.863 +type train | step 2824 | loss 98.8523 191.2631 301.3517 491.5858 723.4526 1057.0432 1484.8164 2139.9314 3006.0171 4665.3154 7760.8999 13856.1152 | lr 3.1e-04 | norm 4265.0835 | dt 9.867 +type train | step 2825 | loss 109.0823 213.9911 327.1655 525.7131 768.8427 1123.1281 1574.9208 2252.9434 3120.5044 4695.5806 7594.7754 13388.1084 | lr 3.1e-04 | norm 4703.0229 | dt 9.873 +type train | step 2826 | loss 98.0123 190.7941 300.1009 490.4827 718.5233 1041.2056 1459.5483 2097.8945 2975.7058 4621.3789 7643.7788 13699.7822 | lr 3.1e-04 | norm 4449.9673 | dt 9.876 +type train | step 2827 | loss 100.2460 195.4804 308.0135 503.1937 738.6429 1082.1520 1520.3599 2189.4761 3064.1211 4759.8882 7940.5938 14435.3076 | lr 3.1e-04 | norm 5324.5718 | dt 9.869 +type train | step 2828 | loss 99.6832 195.8699 301.9012 489.9791 724.0084 1050.8599 1480.5684 2119.5642 2984.1243 4599.1553 7600.2104 13510.6582 | lr 3.1e-04 | norm 4352.9780 | dt 9.892 +type train | step 2829 | loss 99.0815 191.3374 297.2527 484.6567 710.7938 1031.9946 1448.9186 2082.5457 2941.8647 4555.1851 7541.0049 13465.9072 | lr 3.1e-04 | norm 4177.6992 | dt 9.877 +type train | step 2830 | loss 95.1949 183.1467 288.3160 473.4939 704.4290 1031.5140 1460.0973 2114.1494 2980.1121 4609.5835 7613.9678 13515.8789 | lr 3.1e-04 | norm 4685.6221 | dt 9.862 +type train | step 2831 | loss 104.1407 202.8502 312.5462 507.8292 744.7745 1083.0938 1509.1967 2159.2861 3017.0183 4627.6201 7616.8052 13636.0312 | lr 3.1e-04 | norm 5163.3193 | dt 9.877 +type train | step 2832 | loss 107.4070 208.0353 318.2573 507.9003 741.5312 1063.7029 1485.0337 2107.4502 2959.3591 4550.0513 7446.2100 13316.8086 | lr 3.1e-04 | norm 5442.1528 | dt 9.872 +type train | step 2833 | loss 107.3177 210.1947 321.8518 512.5833 751.6863 1094.6713 1536.3047 2199.2246 3099.0972 4733.6919 7720.3394 13606.7510 | lr 3.1e-04 | norm 4337.7012 | dt 9.880 +type train | step 2834 | loss 99.3840 194.8591 304.8250 492.2671 728.7318 1064.7930 1503.2859 2178.8037 3071.1077 4780.1006 7881.5918 13929.9941 | lr 3.1e-04 | norm 4884.3677 | dt 9.882 +type train | step 2835 | loss 96.6244 188.1880 297.6622 485.0106 718.4243 1049.5150 1484.1472 2134.3796 3019.4680 4641.5430 7644.9365 13581.9717 | lr 3.1e-04 | norm 4516.2441 | dt 9.862 +type train | step 2836 | loss 108.3084 209.2230 322.0236 511.7952 753.3906 1101.6316 1535.5449 2199.9185 3069.5295 4674.6445 7662.5566 13579.7451 | lr 3.1e-04 | norm 4229.5610 | dt 9.884 +type train | step 2837 | loss 95.1518 183.9986 285.4516 462.8657 689.5837 1004.1758 1415.4398 2040.2603 2890.8059 4464.8145 7374.4316 13087.9912 | lr 3.1e-04 | norm 4039.1548 | dt 9.898 +type train | step 2838 | loss 96.0508 186.9800 291.8828 471.5518 697.0137 1008.4270 1420.3790 2043.9464 2897.5532 4454.1670 7325.1665 12899.3203 | lr 3.1e-04 | norm 4041.7058 | dt 9.889 +type train | step 2839 | loss 105.5274 206.7422 316.6200 510.4520 752.3651 1096.4960 1533.8160 2221.3293 3126.8206 4801.7891 7870.9438 13794.0596 | lr 3.1e-04 | norm 5018.6362 | dt 9.883 +type train | step 2840 | loss 103.0376 202.3311 313.1349 504.5865 738.0930 1070.6562 1489.3867 2139.0881 3015.3477 4641.5747 7611.5317 13465.2090 | lr 3.1e-04 | norm 4119.1797 | dt 9.886 +type train | step 2841 | loss 104.1970 202.1852 314.0502 509.3321 746.8754 1089.7802 1531.8414 2209.0713 3110.0181 4777.1406 7845.5991 13885.8555 | lr 3.1e-04 | norm 4449.1968 | dt 9.892 +type train | step 2842 | loss 108.9862 214.8253 339.7206 545.2083 798.8659 1185.7299 1674.1766 2424.0667 3357.0540 5107.2832 8437.3789 15015.5381 | lr 3.0e-04 | norm 8603.4395 | dt 9.882 +type train | step 2843 | loss 103.7052 205.2150 316.3579 513.7271 751.2973 1087.0227 1520.2615 2188.6792 3091.4768 4787.2529 7867.0425 13946.8125 | lr 3.0e-04 | norm 5897.4375 | dt 9.855 +type train | step 2844 | loss 107.9620 215.6102 331.0217 536.3113 778.0736 1128.5991 1571.1516 2242.5618 3115.1135 4771.8745 7811.3662 13738.4424 | lr 3.0e-04 | norm 7862.1655 | dt 9.862 +type train | step 2845 | loss 104.6371 203.5949 310.3231 502.1399 736.7247 1086.4305 1537.6627 2230.1545 3121.9478 4794.1777 7855.0073 13895.5508 | lr 3.0e-04 | norm 5071.0020 | dt 9.871 +type train | step 2846 | loss 110.1191 216.4979 332.7798 536.4014 775.0656 1107.6223 1530.1682 2167.3682 3023.4773 4615.4272 7596.7949 13610.0693 | lr 3.0e-04 | norm 5750.9751 | dt 9.879 +type train | step 2847 | loss 89.1087 170.0848 275.4742 461.8774 694.8198 1026.8374 1468.1501 2145.6934 3071.3264 4759.9697 7784.3691 13844.4199 | lr 3.0e-04 | norm 7950.2021 | dt 9.867 +type train | step 2848 | loss 106.6055 208.7346 321.7919 514.5443 750.5430 1094.4231 1535.6921 2219.7803 3095.2542 4738.2393 7758.8828 13740.9688 | lr 3.0e-04 | norm 5852.9419 | dt 9.879 +type train | step 2849 | loss 98.3139 191.8593 297.3174 485.6093 716.2864 1048.5972 1475.7543 2137.0967 3019.9817 4671.3511 7644.0029 13513.0068 | lr 3.0e-04 | norm 5049.1470 | dt 9.868 +type train | step 2850 | loss 97.0017 188.6766 295.5402 481.3228 710.0154 1038.7579 1455.7844 2095.3564 2960.2881 4567.8403 7524.1450 13305.6865 | lr 3.0e-04 | norm 4741.9111 | dt 9.886 +type train | step 2851 | loss 99.6914 195.5306 301.2811 488.5819 718.6507 1052.7531 1478.4572 2136.1360 2999.9973 4631.4331 7656.2881 13658.5908 | lr 3.0e-04 | norm 4710.9258 | dt 9.884 +type train | step 2852 | loss 91.1355 177.2311 282.3917 471.5851 705.3033 1038.9204 1483.5146 2176.8789 3083.5120 4787.5576 7945.9351 14181.7822 | lr 3.0e-04 | norm 6630.6284 | dt 9.867 +type train | step 2853 | loss 111.3647 217.8091 329.5132 525.1047 759.7739 1105.5668 1539.3003 2199.5964 3056.0332 4692.8599 7721.4487 13685.2129 | lr 3.0e-04 | norm 5072.7700 | dt 9.874 +type train | step 2854 | loss 101.8132 196.8578 304.5082 497.3389 730.1883 1072.0696 1507.4004 2176.6079 3054.8105 4699.1333 7756.3369 13878.2129 | lr 3.0e-04 | norm 4703.5830 | dt 9.870 +type train | step 2855 | loss 95.5829 184.4081 286.6522 466.6434 693.1971 1009.6403 1424.6525 2047.1499 2914.0847 4521.1221 7459.7412 13292.6836 | lr 3.0e-04 | norm 4322.9214 | dt 9.878 +type train | step 2856 | loss 107.3983 209.0341 320.1093 509.8153 743.6744 1070.8109 1469.0940 2081.3237 2902.5869 4436.7363 7236.1357 12870.8164 | lr 3.0e-04 | norm 4988.0547 | dt 9.867 +type train | step 2857 | loss 92.8988 178.7628 280.5024 462.0707 689.0618 1016.4900 1443.3167 2101.5129 2977.5728 4636.0947 7647.8706 13531.5674 | lr 3.0e-04 | norm 4690.6348 | dt 9.881 +type train | step 2858 | loss 97.9488 192.8573 303.7221 491.3831 723.3171 1052.7859 1481.7498 2140.8667 3027.5603 4706.0059 7771.1318 13797.3398 | lr 3.0e-04 | norm 5331.4595 | dt 9.872 +type train | step 2859 | loss 88.9598 171.2885 274.1380 450.8469 676.9439 990.9866 1411.4028 2049.6421 2933.2068 4575.4468 7548.4775 13456.1660 | lr 3.0e-04 | norm 4454.7729 | dt 9.877 +type train | step 2860 | loss 104.3162 200.1443 304.7299 490.1340 721.6711 1064.3787 1500.5015 2181.5286 3099.0991 4771.2446 7863.7280 13977.0547 | lr 3.0e-04 | norm 4625.8467 | dt 9.866 +type train | step 2861 | loss 99.1283 192.0817 299.6255 484.9223 715.4677 1044.8999 1470.1051 2113.6108 2985.8120 4631.4204 7674.1826 13703.9766 | lr 3.0e-04 | norm 4673.9995 | dt 9.892 +type train | step 2862 | loss 94.5452 183.3729 286.8321 470.8531 696.9943 1018.6732 1434.9084 2070.5867 2930.9854 4522.2588 7439.0640 13173.2764 | lr 3.0e-04 | norm 4344.2817 | dt 9.880 +type train | step 2863 | loss 96.2377 185.4346 289.8943 473.9213 703.3761 1038.7207 1468.0575 2129.4458 3014.7292 4641.1499 7641.7783 13556.8213 | lr 3.0e-04 | norm 4768.3452 | dt 9.869 +type train | step 2864 | loss 99.1518 188.4532 294.7778 479.6113 704.1671 1034.6670 1458.3978 2109.5215 2980.4751 4632.3535 7652.7583 13717.4727 | lr 3.0e-04 | norm 5354.3823 | dt 9.867 +type train | step 2865 | loss 96.5517 188.5947 297.2399 485.6963 715.9226 1044.6251 1463.9324 2105.4038 2977.5059 4607.7402 7593.0898 13495.5518 | lr 3.0e-04 | norm 3899.1121 | dt 9.879 +type train | step 2866 | loss 96.3257 189.5901 298.5156 488.7353 721.5594 1056.7839 1490.6589 2164.3672 3047.2871 4718.1147 7847.2485 14007.3965 | lr 3.0e-04 | norm 4511.1499 | dt 9.864 +type train | step 2867 | loss 100.0518 193.6583 298.6635 483.0700 712.3727 1035.8033 1453.2578 2095.1545 2948.8037 4536.3442 7443.7349 13190.7402 | lr 3.0e-04 | norm 4264.1934 | dt 9.890 +type train | step 2868 | loss 107.8879 212.1433 323.7674 524.8221 768.1260 1108.8402 1560.8025 2238.0120 3150.3884 4882.9614 8109.1479 14494.9951 | lr 3.0e-04 | norm 6326.0117 | dt 9.871 +type train | step 2869 | loss 86.3691 170.4860 276.7236 464.9156 704.3067 1047.1478 1490.8810 2168.9375 3094.5635 4815.9526 7959.5620 14042.4600 | lr 3.0e-04 | norm 6496.1289 | dt 9.857 +type train | step 2870 | loss 105.8712 209.0401 316.3434 501.3975 734.2748 1065.4141 1490.9279 2145.5845 3030.9045 4653.5020 7626.0117 13540.8896 | lr 3.0e-04 | norm 4787.9819 | dt 9.873 +type train | step 2871 | loss 96.2747 187.0445 293.9982 479.9290 708.2143 1031.0221 1447.8435 2080.9919 2943.2505 4559.8203 7565.0063 13508.6826 | lr 3.0e-04 | norm 4147.9609 | dt 9.887 +type train | step 2872 | loss 92.0194 178.2229 281.4772 465.9620 695.8178 1024.0066 1455.7356 2109.9919 2992.0339 4661.2822 7751.5205 14064.3438 | lr 3.0e-04 | norm 5983.1602 | dt 9.879 +type train | step 2873 | loss 94.5726 183.4289 288.6810 477.2108 705.7340 1038.4509 1463.4485 2117.3108 2991.8379 4619.7954 7657.6831 13624.1699 | lr 3.0e-04 | norm 5424.2681 | dt 9.876 +type train | step 2874 | loss 98.9512 191.5223 296.1747 481.9196 708.2690 1024.8959 1435.7073 2045.8672 2891.2478 4449.9541 7356.9849 13071.0283 | lr 3.0e-04 | norm 4163.8125 | dt 9.881 +type train | step 2875 | loss 98.7576 191.6008 296.2256 482.9444 711.5342 1045.2444 1472.2800 2126.0771 2994.4766 4623.4497 7625.6377 13602.6338 | lr 3.0e-04 | norm 5047.7183 | dt 9.866 +type train | step 2876 | loss 103.5944 202.6289 314.4692 506.3248 738.7990 1065.8381 1480.2722 2110.2256 2961.8230 4560.0483 7574.0967 13553.9053 | lr 3.0e-04 | norm 5123.0977 | dt 9.885 +type train | step 2877 | loss 95.4268 199.1973 330.7478 545.0968 807.7512 1192.4708 1679.2379 2432.9905 3457.9739 5375.6011 9000.9492 16413.5742 | lr 3.0e-04 | norm 7574.8428 | dt 9.867 +type train | step 2878 | loss 108.8409 213.1355 326.4532 520.3140 760.8169 1118.0431 1568.5017 2268.6177 3126.4209 4786.9272 7846.3438 13974.2041 | lr 3.0e-04 | norm 4800.4883 | dt 9.882 +type train | step 2879 | loss 97.6543 189.4599 291.3698 475.1789 702.5685 1018.1392 1434.3152 2070.5825 2938.4177 4536.9453 7464.2607 13245.7012 | lr 3.0e-04 | norm 4097.9238 | dt 9.875 +type train | step 2880 | loss 96.2981 185.1857 288.7579 471.7832 698.4132 1020.8246 1438.5741 2077.4585 2965.7837 4567.9219 7500.8779 13193.4961 | lr 3.0e-04 | norm 4198.4790 | dt 9.863 +type train | step 2881 | loss 99.3773 194.9761 305.0697 496.3972 734.1635 1067.3998 1501.0486 2151.1477 3046.3547 4709.8750 7772.4385 13722.5371 | lr 3.0e-04 | norm 3870.9292 | dt 9.874 +type train | step 2882 | loss 103.8252 203.3199 315.4556 512.2030 752.0170 1096.8141 1534.9286 2208.0862 3089.3682 4759.9727 7855.0371 13912.3535 | lr 3.0e-04 | norm 4589.7407 | dt 9.876 +type train | step 2883 | loss 98.2852 188.8275 292.7773 472.4695 698.6052 1016.3902 1430.3701 2065.5835 2926.2988 4533.6763 7463.3955 13234.1445 | lr 3.0e-04 | norm 4424.9082 | dt 9.869 +type train | step 2884 | loss 93.3318 178.9922 281.2184 458.5521 685.2075 997.9147 1409.3698 2047.0970 2926.6018 4564.9302 7535.1221 13404.1250 | lr 3.0e-04 | norm 4481.4531 | dt 9.885 +type train | step 2885 | loss 96.3035 190.8731 301.1330 494.4745 727.1827 1064.0162 1486.1581 2154.3098 3044.2083 4737.9175 7867.1299 14042.6650 | lr 3.0e-04 | norm 5202.4385 | dt 9.868 +type train | step 2886 | loss 94.1876 180.0939 279.9334 457.0195 683.0032 997.2077 1410.9580 2035.1138 2899.3921 4524.5137 7549.4180 13427.9570 | lr 3.0e-04 | norm 4857.0991 | dt 9.863 +type train | step 2887 | loss 91.3787 174.7395 274.0456 450.0344 671.9559 986.8319 1397.2322 2018.3816 2864.3335 4433.7007 7340.6108 13090.1641 | lr 3.0e-04 | norm 4655.9995 | dt 9.865 +type train | step 2888 | loss 101.9206 198.5334 308.4986 500.1716 736.2285 1076.6334 1507.2308 2165.9580 3040.8972 4714.3472 7786.5166 13908.0986 | lr 3.0e-04 | norm 4712.7407 | dt 9.883 +type train | step 2889 | loss 103.9959 203.3138 313.5547 508.7558 747.3357 1074.9960 1508.1127 2154.5154 3039.9158 4674.9795 7682.6250 13694.6006 | lr 3.0e-04 | norm 3942.3735 | dt 9.887 +type train | step 2890 | loss 97.6369 189.6960 295.7418 482.7134 714.8429 1039.4753 1452.6276 2070.4561 2925.4148 4527.0913 7487.4849 13271.0029 | lr 3.0e-04 | norm 4199.9102 | dt 9.881 +type train | step 2891 | loss 97.0396 188.1767 290.3422 471.8982 694.9681 1013.1502 1428.2925 2059.0461 2891.7275 4489.6421 7462.2954 13314.3457 | lr 3.0e-04 | norm 4416.7544 | dt 9.884 +type train | step 2892 | loss 94.0701 180.7290 286.7704 469.6111 699.8438 1025.4392 1451.2720 2098.6743 2962.3867 4613.9448 7667.2451 13744.1924 | lr 3.0e-04 | norm 4687.1411 | dt 9.881 +type train | step 2893 | loss 97.3930 190.4122 298.1409 486.9618 717.6450 1051.1099 1483.9124 2143.1243 3024.0374 4668.1562 7723.0479 13851.9561 | lr 3.0e-04 | norm 4811.0073 | dt 9.885 +type train | step 2894 | loss 108.8675 220.5633 342.6006 563.0262 823.3831 1212.0337 1684.7795 2412.2581 3347.9758 5108.6963 8379.7041 14865.7334 | lr 3.0e-04 | norm 5372.6294 | dt 9.866 +type train | step 2895 | loss 99.8071 193.7759 303.7443 496.1104 734.5065 1063.3992 1492.4166 2142.7432 3027.8289 4661.3154 7697.9912 13625.0430 | lr 3.0e-04 | norm 4526.7300 | dt 9.889 +type train | step 2896 | loss 96.5937 187.5980 298.6400 490.4997 726.0532 1066.4924 1504.8046 2175.7693 3079.2285 4791.1250 7991.1831 14254.9375 | lr 3.0e-04 | norm 5534.0630 | dt 9.866 +type train | step 2897 | loss 100.6225 194.8027 305.5304 496.0986 733.7086 1070.8489 1506.8047 2172.2893 3059.7649 4722.6572 7793.2959 13912.9795 | lr 3.0e-04 | norm 4620.0142 | dt 9.879 +type train | step 2898 | loss 101.7910 199.3660 306.2787 496.4800 732.3129 1067.6794 1497.5093 2150.2107 3048.0723 4677.5630 7642.0298 13438.6738 | lr 3.0e-04 | norm 4136.0532 | dt 9.873 +type train | step 2899 | loss 97.7220 190.3709 299.2258 487.4861 723.0345 1059.1765 1489.1223 2148.7085 3021.4009 4692.8057 7739.6094 13830.0713 | lr 3.0e-04 | norm 4875.7627 | dt 9.864 +type train | step 2900 | loss 100.1683 194.9859 303.2823 487.2120 715.7228 1035.2736 1445.5436 2068.0200 2918.2129 4473.8848 7355.7422 13052.7061 | lr 3.0e-04 | norm 4597.8101 | dt 9.865 +type train | step 2901 | loss 98.0842 191.2446 297.5557 482.3747 711.8029 1043.5607 1467.3743 2117.8079 2987.5078 4616.0454 7609.5454 13444.3516 | lr 3.0e-04 | norm 4250.8496 | dt 9.872 +type train | step 2902 | loss 99.1065 194.2465 303.6688 493.9199 728.7855 1057.1732 1481.9297 2123.5410 2994.3967 4611.2290 7589.9014 13507.3389 | lr 3.0e-04 | norm 4173.4976 | dt 9.890 +type train | step 2903 | loss 96.5779 187.1926 296.0497 487.4328 724.3268 1051.7732 1486.5919 2149.6169 3039.4919 4691.3569 7716.1514 13694.2832 | lr 3.0e-04 | norm 5276.9375 | dt 9.861 +type train | step 2904 | loss 101.7530 197.5704 308.0361 493.7852 731.4056 1059.5731 1490.7700 2146.1335 3044.8352 4737.4375 7826.2266 14004.6523 | lr 3.0e-04 | norm 4788.4922 | dt 9.871 +type train | step 2905 | loss 102.8478 201.3936 311.0214 497.8132 733.9611 1061.4833 1491.8230 2139.6577 3021.9204 4664.7822 7690.8052 13605.5059 | lr 3.0e-04 | norm 4224.3633 | dt 9.892 +type train | step 2906 | loss 98.6087 190.4914 295.3488 476.0572 705.9236 1034.3745 1456.4050 2100.7312 2971.1418 4591.2935 7558.0225 13369.4922 | lr 3.0e-04 | norm 3992.7241 | dt 9.895 +type train | step 2907 | loss 105.3659 205.3524 318.3271 513.3488 748.2335 1097.8721 1536.3337 2209.6431 3043.4866 4666.4800 7732.8320 13878.9854 | lr 3.0e-04 | norm 5572.3491 | dt 9.858 +type train | step 2908 | loss 97.2419 191.3240 302.9807 496.4053 734.2833 1064.5731 1486.8099 2136.6909 3027.3770 4680.5132 7754.7407 13764.4766 | lr 3.0e-04 | norm 4722.0581 | dt 9.881 +type train | step 2909 | loss 100.4613 198.5232 310.2630 503.5079 734.2054 1058.7300 1479.7341 2108.1821 2955.5884 4547.0078 7464.3701 13403.6514 | lr 2.9e-04 | norm 5064.7349 | dt 9.872 +type train | step 2910 | loss 98.7584 191.5513 298.9455 482.8501 710.3809 1033.6084 1450.8074 2087.4336 2937.8413 4535.1431 7474.6069 13339.2266 | lr 2.9e-04 | norm 4305.5801 | dt 9.878 +type train | step 2911 | loss 100.2389 192.9224 300.9028 489.0039 720.9034 1037.3815 1451.0156 2073.4158 2946.3242 4536.4771 7389.1172 13027.8779 | lr 2.9e-04 | norm 3887.4309 | dt 9.876 +type train | step 2912 | loss 100.2976 194.4497 302.6533 493.2672 728.0458 1067.3324 1498.6484 2145.4500 3018.5642 4659.7646 7615.7314 13422.8887 | lr 2.9e-04 | norm 4287.4302 | dt 9.869 +type train | step 2913 | loss 108.3469 210.6979 323.2014 524.5941 763.4137 1115.7819 1553.0807 2242.6738 3109.8789 4758.7490 7827.7285 13964.2441 | lr 2.9e-04 | norm 4639.4136 | dt 9.867 +type train | step 2914 | loss 96.9489 187.6621 290.9327 470.9783 698.9650 1013.7830 1424.6641 2050.6643 2926.1646 4536.8042 7460.2241 13241.2002 | lr 2.9e-04 | norm 4236.0869 | dt 9.893 +type train | step 2915 | loss 94.4444 183.4210 286.4529 464.5881 691.9612 1022.8898 1453.0441 2108.7302 2991.1328 4632.5425 7639.2163 13498.3223 | lr 2.9e-04 | norm 4948.2744 | dt 9.872 +type train | step 2916 | loss 97.8674 186.9351 290.7216 471.8900 698.6581 1015.2183 1426.9377 2054.9146 2917.2209 4512.3867 7437.6514 13213.8164 | lr 2.9e-04 | norm 5015.3262 | dt 9.872 +type train | step 2917 | loss 96.5257 187.6445 292.3022 474.2310 701.9944 1041.1904 1470.2312 2134.2354 2989.5974 4598.1133 7545.8926 13384.3496 | lr 2.9e-04 | norm 4410.8433 | dt 9.863 +type train | step 2918 | loss 108.6221 213.4803 325.8419 519.8838 757.6654 1098.7703 1530.0582 2191.9272 3073.5894 4699.6016 7706.1191 13703.2129 | lr 2.9e-04 | norm 4775.3418 | dt 9.877 +type train | step 2919 | loss 94.6645 186.9949 294.4907 487.7123 723.0203 1062.2687 1503.0675 2177.8616 3084.9272 4816.5176 7990.7939 14379.2568 | lr 2.9e-04 | norm 6598.6196 | dt 9.863 +type train | step 2920 | loss 93.9628 185.8770 293.5622 482.1025 721.7722 1057.4478 1493.5625 2160.5981 3075.1460 4739.6377 7736.1592 13689.0664 | lr 2.9e-04 | norm 6223.8208 | dt 9.860 +type train | step 2921 | loss 96.0002 187.0533 296.1191 483.8209 715.8901 1052.2335 1486.7401 2160.3521 3044.6995 4752.5190 7870.4712 14014.5215 | lr 2.9e-04 | norm 5261.8994 | dt 9.868 +type train | step 2922 | loss 93.0995 180.6930 286.2282 472.3199 705.1815 1037.7155 1472.2084 2142.7715 3034.3154 4695.8774 7749.7905 13784.4512 | lr 2.9e-04 | norm 4771.4399 | dt 9.865 +type train | step 2923 | loss 103.1998 200.2324 309.9965 500.2670 732.0831 1053.5350 1472.4497 2106.2932 2958.0283 4529.1592 7391.7798 13061.0723 | lr 2.9e-04 | norm 4615.0532 | dt 9.885 +type train | step 2924 | loss 97.0602 188.5496 294.7603 485.1969 714.6732 1047.9425 1477.0100 2130.9346 2980.6909 4592.9771 7565.4814 13401.3184 | lr 2.9e-04 | norm 4656.7227 | dt 9.889 +type train | step 2925 | loss 96.9961 187.9742 292.6480 477.6176 702.8453 1026.3896 1445.3983 2078.6963 2937.7107 4553.8716 7535.8613 13492.0146 | lr 2.9e-04 | norm 4096.8691 | dt 9.884 +type train | step 2926 | loss 96.5281 183.9586 289.6558 472.2566 696.4989 1017.5278 1433.8357 2074.8601 2925.9521 4536.3027 7477.5210 13276.6914 | lr 2.9e-04 | norm 4477.4355 | dt 9.872 +type train | step 2927 | loss 105.3371 207.5052 319.0766 511.3693 752.0715 1091.7411 1531.9025 2195.0645 3080.3926 4720.5796 7684.9375 13518.0107 | lr 2.9e-04 | norm 4064.7312 | dt 9.872 +type train | step 2928 | loss 108.2934 211.0455 326.4247 526.8425 774.1619 1134.6708 1599.7251 2307.6846 3234.9907 5002.7246 8321.7090 15064.8340 | lr 2.9e-04 | norm 5292.5327 | dt 9.857 +type train | step 2929 | loss 102.3278 199.4730 309.3651 500.4270 732.5361 1064.5593 1490.8931 2144.6650 3014.3413 4658.5269 7659.9609 13631.3525 | lr 2.9e-04 | norm 4483.9180 | dt 9.883 +type train | step 2930 | loss 89.2220 172.2496 274.9444 452.9443 679.1960 990.2563 1404.1335 2022.9526 2863.4343 4456.5010 7349.9897 13179.0537 | lr 2.9e-04 | norm 5499.0317 | dt 9.879 +type train | step 2931 | loss 93.4835 179.7036 282.0766 464.4382 694.4233 1018.0060 1443.1473 2096.5110 2984.9785 4651.7324 7712.0688 13828.4326 | lr 2.9e-04 | norm 4903.3223 | dt 9.879 +type train | step 2932 | loss 100.2881 194.0685 303.2769 493.1247 725.1769 1056.3773 1476.9351 2117.8174 2970.8452 4582.2607 7538.9658 13413.2617 | lr 2.9e-04 | norm 4663.2979 | dt 9.880 +type train | step 2933 | loss 121.9216 240.0484 359.8800 556.3560 793.7563 1123.4468 1550.6320 2196.0127 3002.8044 4566.0884 7394.8589 13167.6689 | lr 2.9e-04 | norm 5299.1313 | dt 9.848 +type train | step 2934 | loss 94.0019 182.8801 283.7266 463.9997 688.6819 1004.3136 1411.1638 2032.5297 2878.6609 4474.6318 7417.5972 13182.0732 | lr 2.9e-04 | norm 4364.1938 | dt 9.860 +type train | step 2935 | loss 92.7746 179.5914 282.8144 466.5171 697.3439 1025.6434 1456.4744 2120.9526 3019.1541 4699.1260 7731.7598 13743.7119 | lr 2.9e-04 | norm 5081.3833 | dt 9.867 +type train | step 2936 | loss 92.9965 179.9463 285.4398 469.4508 699.8837 1018.3727 1433.4745 2063.0095 2930.3230 4528.4551 7458.7749 13191.6934 | lr 2.9e-04 | norm 4339.1592 | dt 9.880 +type train | step 2937 | loss 95.8603 186.5944 292.3304 478.1360 707.0507 1028.8907 1444.0592 2077.8760 2938.1941 4564.5000 7569.4775 13423.1572 | lr 2.9e-04 | norm 4073.9028 | dt 9.884 +type train | step 2938 | loss 105.4460 205.2838 315.9544 509.6510 748.1431 1088.4293 1518.9150 2177.7673 3038.5249 4673.5859 7654.6997 13551.3145 | lr 2.9e-04 | norm 4174.6558 | dt 9.880 +type train | step 2939 | loss 99.6499 195.0055 302.2440 488.7858 720.3153 1056.1700 1487.2720 2145.9443 3031.6636 4680.8970 7689.5078 13644.1104 | lr 2.9e-04 | norm 3896.0305 | dt 9.870 +type train | step 2940 | loss 100.8616 196.3990 307.1843 494.3764 724.7115 1042.5920 1454.9861 2076.6045 2927.7495 4510.9009 7412.6948 13138.0781 | lr 2.9e-04 | norm 4028.3660 | dt 9.876 +type train | step 2941 | loss 91.5807 177.2074 281.5640 470.6222 701.4494 1032.5376 1468.1715 2140.1816 3021.3132 4731.8149 7839.9170 14010.5420 | lr 2.9e-04 | norm 5793.5718 | dt 9.859 +type train | step 2942 | loss 105.1815 204.4055 317.5414 515.9385 756.4593 1100.3448 1539.8461 2220.8335 3118.5015 4843.0498 8015.0771 14301.3252 | lr 2.9e-04 | norm 5240.1050 | dt 9.875 +type train | step 2943 | loss 101.1794 197.1814 306.1168 493.8662 723.9215 1053.3004 1476.4775 2118.6917 2984.6753 4611.0249 7581.2153 13458.6426 | lr 2.9e-04 | norm 3918.8992 | dt 9.886 +type train | step 2944 | loss 97.7658 191.0884 297.3374 482.3241 711.2324 1035.2449 1456.1041 2090.7424 2962.9282 4592.6675 7568.7021 13415.9727 | lr 2.9e-04 | norm 4146.6035 | dt 9.882 +type train | step 2945 | loss 104.8927 203.0991 324.8593 530.2117 794.8956 1169.7489 1646.8900 2407.8623 3407.7146 5173.1357 8335.8887 14867.6152 | lr 2.9e-04 | norm 5437.8560 | dt 9.856 +type train | step 2946 | loss 110.2324 218.9721 336.8053 545.4595 791.2053 1137.7415 1580.1920 2245.0510 3096.5996 4682.7036 7584.3101 13425.2627 | lr 2.9e-04 | norm 5878.7354 | dt 9.880 +type train | step 2947 | loss 97.5297 188.2534 293.7949 477.2479 705.3131 1025.4176 1444.7979 2083.4131 2945.1306 4557.4297 7528.4209 13427.9287 | lr 2.9e-04 | norm 4371.9385 | dt 9.885 +type train | step 2948 | loss 100.5499 194.3443 297.9711 481.5613 711.2676 1041.8064 1474.3309 2141.3403 3015.9646 4700.7612 7815.1953 13996.4609 | lr 2.9e-04 | norm 4561.4214 | dt 9.888 +type train | step 2949 | loss 100.0466 194.2946 301.9095 489.2702 719.5596 1045.0934 1463.8516 2103.5107 2969.9006 4585.0425 7595.0703 13483.0781 | lr 2.9e-04 | norm 4437.8906 | dt 9.882 +type train | step 2950 | loss 95.9383 186.2550 293.2303 481.8784 713.0131 1046.2280 1469.9260 2120.7432 2978.9780 4586.0303 7600.6357 13621.0225 | lr 2.9e-04 | norm 5026.6514 | dt 9.882 +type train | step 2951 | loss 94.1608 182.9196 289.7930 475.9431 704.2128 1036.0767 1466.9567 2131.6265 2994.5320 4647.5044 7676.0728 13717.8574 | lr 2.9e-04 | norm 5099.4336 | dt 9.877 +type train | step 2952 | loss 96.4600 189.1674 295.5808 481.1309 715.9968 1058.1658 1503.6102 2186.2239 3119.7290 4817.0732 7849.0366 13893.9834 | lr 2.9e-04 | norm 5223.7666 | dt 9.860 +type train | step 2953 | loss 99.8445 194.1442 300.5285 486.7232 719.6630 1048.4708 1473.6342 2127.7358 3019.6406 4639.7861 7624.5698 13383.4355 | lr 2.9e-04 | norm 4838.7695 | dt 9.875 +type train | step 2954 | loss 102.0423 200.8334 311.4807 504.4435 741.2914 1079.6061 1516.8055 2184.9182 3073.2703 4714.1094 7735.5742 13666.5723 | lr 2.9e-04 | norm 4405.7915 | dt 9.891 +type train | step 2955 | loss 98.9824 194.7983 299.5953 485.0685 714.2008 1038.2963 1454.8987 2095.8818 2963.8926 4590.8965 7594.4141 13555.7607 | lr 2.9e-04 | norm 4884.9062 | dt 9.879 +type train | step 2956 | loss 99.2809 196.8010 302.9713 499.2889 733.1640 1069.9631 1503.7120 2169.2273 3033.9297 4664.0254 7695.7153 13724.6426 | lr 2.9e-04 | norm 4849.5156 | dt 9.880 +type train | step 2957 | loss 97.9258 190.8701 296.1661 481.3755 715.8264 1043.5208 1469.6394 2119.0767 3002.2478 4674.8008 7756.7280 13857.8438 | lr 2.9e-04 | norm 4536.2476 | dt 9.870 +type train | step 2958 | loss 106.8255 208.5116 319.5942 520.6104 758.9435 1117.1405 1573.7346 2275.9019 3180.7556 4916.8047 8154.2017 14691.8096 | lr 2.9e-04 | norm 5732.1157 | dt 9.863 +type train | step 2959 | loss 99.8724 194.5749 304.5305 494.3858 732.2517 1064.8708 1493.7321 2144.5994 3010.5288 4616.2271 7597.7412 13472.7422 | lr 2.9e-04 | norm 4144.6528 | dt 9.876 +type train | step 2960 | loss 99.3725 193.1016 299.5943 488.3413 722.2568 1053.4353 1478.2906 2124.8994 2992.5706 4620.4111 7611.1870 13535.7031 | lr 2.9e-04 | norm 3996.1809 | dt 9.883 +type train | step 2961 | loss 94.3754 189.7059 304.6898 499.9039 741.4112 1081.1143 1515.8959 2203.6006 3126.6670 4844.8965 8041.3867 14483.3574 | lr 2.9e-04 | norm 7672.2041 | dt 9.882 +type train | step 2962 | loss 96.9194 192.1258 306.9722 507.7069 749.3663 1088.5551 1531.7255 2222.3345 3136.6306 4899.1294 8172.5176 14844.3672 | lr 2.9e-04 | norm 6787.2163 | dt 9.866 +type train | step 2963 | loss 99.8178 193.8788 303.2560 493.3789 727.0909 1049.5962 1467.2273 2094.5806 2929.8511 4486.5698 7305.1675 12945.7012 | lr 2.9e-04 | norm 4733.5972 | dt 9.874 +type train | step 2964 | loss 96.6469 187.0218 295.6907 483.1203 714.0898 1037.7448 1459.1965 2098.0295 2982.7634 4609.7334 7608.8975 13546.3096 | lr 2.9e-04 | norm 4796.3970 | dt 9.887 +type train | step 2965 | loss 98.1527 192.0210 300.1341 490.6048 727.1196 1056.1821 1480.9547 2136.3115 3015.2520 4619.1431 7566.8091 13330.2471 | lr 2.9e-04 | norm 4636.6357 | dt 9.880 +type train | step 2966 | loss 103.8805 206.7499 322.8231 524.3565 774.0568 1113.2925 1559.3484 2228.3494 3156.8938 4872.2852 8035.4062 14286.3711 | lr 2.9e-04 | norm 4618.1074 | dt 9.880 +type train | step 2967 | loss 98.8544 195.0113 304.5344 493.3309 729.1150 1056.1742 1479.6775 2123.3818 3013.1416 4661.3486 7665.8042 13540.7090 | lr 2.9e-04 | norm 4465.9800 | dt 9.876 +type train | step 2968 | loss 100.5140 194.7880 302.4625 490.0768 719.1187 1038.4580 1456.5828 2092.0430 2914.0977 4477.7378 7345.3623 13372.9287 | lr 2.9e-04 | norm 8310.3350 | dt 9.857 +type train | step 2969 | loss 107.2045 209.1760 323.3026 523.4385 763.7149 1107.6450 1548.0828 2219.7329 3114.2500 4773.9043 7858.4932 14104.0186 | lr 2.9e-04 | norm 5526.4604 | dt 9.865 +type train | step 2970 | loss 111.7117 221.1925 338.8962 540.0348 786.4462 1127.5443 1561.5663 2210.3174 3081.8586 4688.2764 7663.0947 13563.3926 | lr 2.9e-04 | norm 4677.8823 | dt 9.888 +type train | step 2971 | loss 96.0204 186.2255 299.8988 498.1504 739.0446 1076.1465 1514.9709 2182.2153 3098.0464 4798.2534 7943.0894 14160.6865 | lr 2.9e-04 | norm 4748.6543 | dt 9.875 +type train | step 2972 | loss 100.8490 196.5915 306.7536 500.0560 739.5603 1077.1465 1512.6066 2162.7642 3047.3555 4666.0693 7668.2158 13638.6426 | lr 2.9e-04 | norm 4713.3887 | dt 9.870 +type train | step 2973 | loss 107.9990 211.6236 329.8028 524.0801 770.0453 1115.4211 1556.7581 2216.7761 3101.2656 4760.8018 7887.2578 14119.5967 | lr 2.9e-04 | norm 5744.7314 | dt 9.880 +type train | step 2974 | loss 105.1653 210.9064 328.8481 531.0265 779.9398 1131.6887 1570.7957 2219.8899 3105.4844 4745.5156 7730.9102 13709.7363 | lr 2.9e-04 | norm 5283.3252 | dt 9.855 +type train | step 2975 | loss 101.0986 199.6103 313.8861 512.9781 750.6785 1093.1536 1524.2117 2205.1121 3082.6389 4770.6138 7947.7134 14213.4961 | lr 2.9e-04 | norm 6022.8394 | dt 9.862 +type train | step 2976 | loss 104.9858 209.7392 321.6693 515.5002 759.6291 1120.0096 1559.7845 2264.8242 3133.1165 4725.7456 7651.9116 13510.9609 | lr 2.9e-04 | norm 5227.3701 | dt 9.869 +type train | step 2977 | loss 102.7914 201.3124 310.7705 502.6725 740.6702 1077.3481 1505.6168 2156.0459 3044.8108 4679.2661 7663.0913 13561.5820 | lr 2.8e-04 | norm 4442.7217 | dt 9.899 +type train | step 2978 | loss 103.1284 201.1446 311.3310 501.9398 738.7795 1071.8174 1498.2368 2139.9180 3033.0913 4664.1660 7690.1519 13708.3604 | lr 2.8e-04 | norm 4451.5718 | dt 9.889 +type train | step 2979 | loss 103.5487 203.4097 319.9799 520.5010 759.5766 1094.3149 1521.1976 2170.2756 3022.5886 4670.0986 7749.1973 13926.9385 | lr 2.8e-04 | norm 5329.5078 | dt 9.875 +type train | step 2980 | loss 100.5655 197.9194 308.9047 500.1857 741.0735 1075.4680 1512.7843 2170.3066 3067.7949 4697.6455 7684.7080 13579.4053 | lr 2.8e-04 | norm 3736.6721 | dt 9.897 +type train | step 2981 | loss 98.4765 192.2626 301.5832 490.3277 725.6683 1054.9521 1486.6765 2149.1682 3036.1472 4689.2324 7736.2700 13721.4648 | lr 2.8e-04 | norm 4465.2617 | dt 9.878 +type train | step 2982 | loss 98.5792 192.2491 299.2871 484.8531 715.5157 1032.7958 1446.7180 2079.4417 2929.3218 4499.4214 7430.4512 13242.5586 | lr 2.8e-04 | norm 5230.9585 | dt 9.877 +type train | step 2983 | loss 107.6961 215.4268 331.2090 537.6680 777.4710 1124.2003 1554.7916 2218.3298 3110.3013 4771.9102 7890.2144 14083.8662 | lr 2.8e-04 | norm 5760.2554 | dt 9.862 +type train | step 2984 | loss 96.0219 188.8595 299.9054 491.6766 727.5597 1054.3053 1487.5471 2140.9727 3032.4492 4684.5435 7758.4243 13860.3242 | lr 2.8e-04 | norm 4494.6680 | dt 9.879 +type train | step 2985 | loss 106.0486 208.3603 325.7431 528.6038 773.9910 1129.0656 1565.6876 2255.1736 3155.6021 4862.8843 8061.0161 14418.0361 | lr 2.8e-04 | norm 4833.2021 | dt 9.876 +type train | step 2986 | loss 102.2145 201.3445 314.1750 508.7585 749.7822 1081.8478 1515.1979 2161.9658 3050.7883 4677.2197 7688.7715 13769.2070 | lr 2.8e-04 | norm 5148.5693 | dt 9.890 +type train | step 2987 | loss 104.5072 205.3599 318.9032 515.4205 754.2280 1085.1935 1511.8770 2150.8499 3028.6895 4626.4321 7599.2554 13447.9922 | lr 2.8e-04 | norm 4177.8701 | dt 9.869 +type train | step 2988 | loss 95.3910 185.2302 293.2946 480.0006 713.7875 1036.5225 1455.6744 2081.0972 2940.1689 4508.3428 7423.5361 13162.3008 | lr 2.8e-04 | norm 3920.5537 | dt 9.889 +type train | step 2989 | loss 101.1976 198.9242 312.6705 508.2010 746.5288 1084.2723 1514.3860 2167.0398 3045.4214 4715.3140 7831.9810 14011.7852 | lr 2.8e-04 | norm 4664.3286 | dt 9.881 +type train | step 2990 | loss 105.5106 213.9289 333.9068 534.4957 779.8707 1111.6418 1546.6398 2195.6470 3125.6179 4769.7451 7819.7329 13860.1426 | lr 2.8e-04 | norm 6414.8066 | dt 9.866 +type train | step 2991 | loss 95.9904 186.0316 296.5032 485.1867 721.3305 1049.6570 1481.5571 2126.3179 3030.9275 4666.0205 7682.7935 13644.1865 | lr 2.8e-04 | norm 4531.5303 | dt 9.873 +type train | step 2992 | loss 99.2476 192.9834 299.9812 486.9036 721.5267 1047.0454 1467.5874 2107.7754 2981.2607 4613.5938 7612.6704 13524.7588 | lr 2.8e-04 | norm 4081.2837 | dt 9.885 +type train | step 2993 | loss 98.5259 192.3558 301.2931 491.7054 729.3298 1054.0334 1473.4879 2102.2175 2983.4785 4608.7876 7597.4058 13493.6396 | lr 2.8e-04 | norm 3930.9622 | dt 9.893 +type train | step 2994 | loss 93.8697 183.2387 290.1567 479.6872 713.3453 1030.8120 1446.0034 2073.4453 2958.2544 4583.2114 7558.8643 13435.5117 | lr 2.8e-04 | norm 3831.3655 | dt 9.874 +type train | step 2995 | loss 101.8459 198.7713 310.0048 501.5036 739.7312 1073.2462 1504.3782 2142.6389 3019.5786 4651.3564 7687.0840 13664.9844 | lr 2.8e-04 | norm 3839.1897 | dt 9.898 +type train | step 2996 | loss 108.1964 210.1318 324.5820 521.7530 765.0981 1118.8995 1566.6195 2254.8616 3152.1304 4850.3613 7981.7900 14212.0420 | lr 2.8e-04 | norm 5010.1626 | dt 9.863 +type train | step 2997 | loss 117.3397 224.6875 345.6201 551.8260 789.8713 1152.4417 1601.4189 2292.2363 3112.6174 4753.1748 7770.1338 13886.8232 | lr 2.8e-04 | norm 6996.2837 | dt 9.852 +type train | step 2998 | loss 108.0726 213.3298 330.5424 532.3386 782.2117 1129.9182 1572.7672 2241.2966 3151.1672 4825.1304 7901.1064 14032.2461 | lr 2.8e-04 | norm 4662.5835 | dt 9.893 +type train | step 2999 | loss 103.9324 204.4487 312.3955 501.5704 737.9047 1067.8656 1494.7633 2132.3083 2990.6343 4572.5039 7538.6479 13475.9814 | lr 2.8e-04 | norm 4601.2974 | dt 9.883 +type train | step 3000 | loss 104.9075 205.8460 321.7504 521.9754 766.7302 1112.4391 1550.8333 2216.5225 3090.5496 4721.3286 7744.7285 13633.0312 | lr 2.8e-04 | norm 4395.2056 | dt 9.883 +type train | step 3001 | loss 107.3598 216.0452 339.8487 557.7007 817.7247 1178.2837 1643.7157 2375.0405 3317.5276 5129.3071 8583.8945 15507.0137 | lr 2.8e-04 | norm 8281.0684 | dt 9.859 +type train | step 3002 | loss 98.7097 194.4946 307.7027 505.4983 748.3998 1086.3485 1523.4430 2184.5544 3069.7393 4723.9727 7791.7822 13900.5625 | lr 2.8e-04 | norm 5282.3467 | dt 9.862 +type train | step 3003 | loss 99.3236 193.9471 302.9138 493.5727 731.5901 1060.6666 1484.6575 2131.6326 3023.5830 4658.1460 7662.4297 13553.1133 | lr 2.8e-04 | norm 4921.9097 | dt 9.878 +type train | step 3004 | loss 107.1321 209.4297 321.9931 519.2308 763.3620 1105.9906 1541.2322 2198.8262 3085.3970 4746.0239 7836.6670 14049.4551 | lr 2.8e-04 | norm 4625.5874 | dt 9.864 +type train | step 3005 | loss 103.4459 201.8715 313.2418 503.9705 743.6351 1077.4369 1506.7432 2167.2979 3052.2593 4668.4424 7639.2334 13486.7979 | lr 2.8e-04 | norm 4492.1475 | dt 9.866 +type train | step 3006 | loss 100.4554 197.0007 306.5650 502.1812 743.2969 1105.9421 1581.2961 2290.7456 3228.6287 5002.2773 8206.0068 14523.3848 | lr 2.8e-04 | norm 6695.7437 | dt 9.857 +type train | step 3007 | loss 99.7857 197.4953 309.6682 503.9630 744.4678 1083.9860 1524.0524 2188.1970 3090.4229 4747.5840 7774.2490 13768.3359 | lr 2.8e-04 | norm 4348.1943 | dt 9.885 +type train | step 3008 | loss 102.5709 203.1659 320.1625 521.1146 761.0737 1105.4191 1544.8474 2218.4146 3111.4233 4784.8398 7942.5820 14175.3848 | lr 2.8e-04 | norm 5431.7153 | dt 9.885 +type train | step 3009 | loss 96.3753 189.1138 295.8648 483.8777 717.0156 1037.7004 1459.2505 2093.2126 2970.4275 4547.6714 7467.4062 13217.3477 | lr 2.8e-04 | norm 5104.3394 | dt 9.863 +type train | step 3010 | loss 103.0636 203.8583 313.3611 510.1208 748.9304 1084.6130 1519.1262 2183.8335 3048.8586 4707.7920 7718.9351 13711.5352 | lr 2.8e-04 | norm 4878.4546 | dt 9.862 +type train | step 3011 | loss 103.4845 202.7888 314.5637 510.1574 753.4576 1088.3616 1521.4403 2176.1631 3070.0012 4749.0679 7816.7974 13887.3535 | lr 2.8e-04 | norm 4185.8442 | dt 9.908 +type train | step 3012 | loss 108.2951 210.9632 324.4944 525.4305 765.2216 1129.2146 1583.5404 2292.0796 3166.8408 4819.5415 7847.7568 13846.4873 | lr 2.8e-04 | norm 4595.8115 | dt 9.860 +type train | step 3013 | loss 104.1760 207.8207 324.1015 524.2954 771.9288 1109.7976 1551.5187 2210.9424 3108.5647 4748.3730 7771.9478 13771.4434 | lr 2.8e-04 | norm 4235.1396 | dt 9.885 +type train | step 3014 | loss 99.5841 194.8191 304.6669 497.8379 738.7043 1065.4685 1502.1779 2143.9954 3036.0774 4692.5635 7707.9155 13703.9629 | lr 2.8e-04 | norm 4456.1587 | dt 9.874 +type train | step 3015 | loss 98.8437 193.5187 300.4332 488.0240 718.3226 1042.1847 1452.3242 2074.9961 2937.9067 4521.1123 7480.2695 13276.3926 | lr 2.8e-04 | norm 4088.5015 | dt 9.874 +type train | step 3016 | loss 101.6066 198.0293 310.0200 506.9855 750.8367 1086.9882 1518.8391 2162.5967 3054.6218 4691.0332 7730.5596 13789.0098 | lr 2.8e-04 | norm 4429.5146 | dt 9.873 +type train | step 3017 | loss 103.5746 200.7992 311.4727 503.5546 738.5945 1071.2074 1493.3765 2135.7100 3000.6370 4601.2314 7558.6440 13373.1543 | lr 2.8e-04 | norm 4377.5596 | dt 9.882 +type train | step 3018 | loss 91.5611 179.6800 283.2127 469.2496 699.5099 1031.6115 1458.4396 2113.7341 3006.1177 4674.0278 7717.5547 13745.0088 | lr 2.8e-04 | norm 5142.3169 | dt 9.862 +type train | step 3019 | loss 100.9956 197.9122 309.5222 506.1409 745.9802 1089.5282 1538.2249 2219.3652 3116.5291 4797.7095 7919.5835 14216.7666 | lr 2.8e-04 | norm 4926.8838 | dt 9.881 +type train | step 3020 | loss 103.7816 202.6026 313.8505 509.9349 753.0081 1091.7432 1529.9731 2199.1980 3088.0364 4736.0356 7778.5073 13835.3760 | lr 2.8e-04 | norm 4601.2573 | dt 9.863 +type train | step 3021 | loss 103.4330 205.5538 320.3006 519.1548 763.4756 1104.6431 1551.6008 2226.3782 3146.6226 4862.4678 8049.3784 14384.0186 | lr 2.8e-04 | norm 5060.4365 | dt 9.861 +type train | step 3022 | loss 105.9118 208.7204 325.4601 534.4287 783.4297 1146.8217 1609.0234 2315.2336 3249.7012 4976.4819 8293.9932 14873.1123 | lr 2.8e-04 | norm 6877.3667 | dt 9.858 +type train | step 3023 | loss 106.0248 208.6233 323.3833 525.8448 770.0100 1117.3992 1560.3547 2225.8618 3148.1714 4802.1533 7897.6187 14012.6074 | lr 2.8e-04 | norm 5034.7783 | dt 9.868 +type train | step 3024 | loss 105.4136 206.7613 321.1226 517.0485 756.6870 1086.4756 1516.6780 2159.0593 3040.7268 4668.6782 7691.9048 13671.5957 | lr 2.8e-04 | norm 4686.2866 | dt 9.876 +type train | step 3025 | loss 101.7094 198.6490 308.5541 502.3210 740.7042 1073.8907 1503.1786 2158.8254 3044.2791 4699.3687 7775.2324 13867.5029 | lr 2.8e-04 | norm 4449.4658 | dt 9.879 +type train | step 3026 | loss 100.4891 196.8090 307.9277 497.5158 735.0187 1071.9470 1505.6724 2163.5178 3061.4050 4712.5029 7784.6240 13855.9170 | lr 2.8e-04 | norm 4796.2778 | dt 9.865 +type train | step 3027 | loss 100.5082 194.8911 304.9142 500.0902 735.4114 1075.4312 1500.8477 2143.6528 3014.9277 4625.2666 7594.2534 13388.9102 | lr 2.8e-04 | norm 4597.6523 | dt 9.870 +type train | step 3028 | loss 96.9890 191.4073 299.1454 485.6470 722.1121 1044.4630 1461.1749 2085.8711 2944.4138 4522.5347 7418.7842 13184.0938 | lr 2.8e-04 | norm 3794.4792 | dt 9.875 +type train | step 3029 | loss 100.0353 196.4256 304.9142 496.8907 736.6431 1081.6133 1530.4958 2196.6145 3082.5813 4739.1597 7797.5776 13891.9883 | lr 2.8e-04 | norm 4645.9302 | dt 9.882 +type train | step 3030 | loss 103.8160 205.0001 316.5052 510.5724 747.4412 1088.6560 1527.5387 2195.7722 3084.8438 4755.9072 7823.8545 14019.5078 | lr 2.8e-04 | norm 4983.4741 | dt 9.889 +type train | step 3031 | loss 99.8234 197.2959 309.3147 503.6360 741.2523 1077.4340 1511.7515 2172.7236 3053.1633 4695.2466 7716.9189 13719.6201 | lr 2.8e-04 | norm 4537.1440 | dt 9.881 +type train | step 3032 | loss 106.3216 209.5702 323.6532 522.0093 764.3126 1101.7059 1531.8180 2181.3804 3072.8528 4698.3984 7693.5610 13590.9248 | lr 2.8e-04 | norm 4247.3760 | dt 9.868 +type train | step 3033 | loss 107.4286 212.5148 325.4599 522.1605 765.0963 1108.9972 1550.6399 2227.1426 3128.3223 4812.6938 7867.3970 13898.4980 | lr 2.8e-04 | norm 4003.4534 | dt 9.879 +type train | step 3034 | loss 97.8874 192.4398 303.2166 494.7238 734.2581 1059.1864 1492.1013 2133.1460 3032.4482 4665.8091 7665.5059 13528.6289 | lr 2.8e-04 | norm 3890.6868 | dt 9.888 +type train | step 3035 | loss 94.0628 181.1656 287.9011 472.6839 709.6935 1037.1733 1481.3657 2140.4158 3076.5122 4691.5972 7637.5596 13408.6758 | lr 2.8e-04 | norm 5848.6465 | dt 9.863 +type train | step 3036 | loss 98.9740 199.8152 315.2078 514.4394 757.2225 1097.5115 1540.0515 2213.0681 3149.7859 4856.9512 8024.0889 14263.3643 | lr 2.8e-04 | norm 5676.8325 | dt 9.863 +type train | step 3037 | loss 102.5508 202.4642 312.2905 505.1316 743.7224 1085.5417 1525.4207 2201.0813 3091.9644 4748.3618 7823.1914 13910.4258 | lr 2.8e-04 | norm 4189.9111 | dt 9.873 +type train | step 3038 | loss 105.0921 205.2481 317.7947 512.1832 750.5317 1078.9263 1502.7056 2136.6667 2997.3347 4601.5210 7597.3755 13505.1182 | lr 2.8e-04 | norm 3869.4319 | dt 9.885 +type train | step 3039 | loss 101.2376 201.2017 317.7218 516.7000 762.9263 1108.0908 1553.9528 2225.9202 3149.9248 4854.7681 8013.0596 14183.1533 | lr 2.8e-04 | norm 5033.8164 | dt 9.869 +type train | step 3040 | loss 103.8283 203.6978 318.2682 512.4556 756.6548 1093.4661 1539.1162 2207.2454 3111.9668 4801.4180 7923.6377 14091.9609 | lr 2.8e-04 | norm 5723.4673 | dt 9.880 +type train | step 3041 | loss 97.5925 193.1669 304.7286 497.8613 737.6713 1074.4784 1516.3215 2185.7527 3082.9934 4794.6694 7986.2314 14361.2275 | lr 2.8e-04 | norm 5040.4668 | dt 9.879 +type train | step 3042 | loss 99.8243 196.9072 311.8255 511.0975 758.6061 1091.8767 1525.5492 2177.6377 3080.3652 4693.4033 7710.5166 13560.5146 | lr 2.8e-04 | norm 4648.6729 | dt 9.890 +type train | step 3043 | loss 114.4064 223.1843 339.0214 534.3679 768.1219 1113.8370 1541.3867 2197.7593 3067.1338 4670.2617 7757.5498 13854.2520 | lr 2.8e-04 | norm 6040.3975 | dt 9.889 +type train | step 3044 | loss 96.6644 193.2987 307.6332 507.6987 748.3502 1110.3595 1570.7373 2283.4915 3236.6616 5077.2056 8552.9512 15555.3799 | lr 2.8e-04 | norm 8265.1758 | dt 9.848 +type train | step 3045 | loss 105.0045 208.4352 327.4471 535.6042 794.1348 1156.1313 1617.3105 2316.7517 3269.6650 5052.0425 8321.3711 14784.4219 | lr 2.7e-04 | norm 6326.8105 | dt 9.855 +type train | step 3046 | loss 102.4982 204.2518 324.3587 527.1968 773.9686 1105.1680 1544.0941 2195.0557 3106.6831 4796.1216 7923.3340 14136.1562 | lr 2.7e-04 | norm 5567.5698 | dt 9.877 +type train | step 3047 | loss 106.6845 210.9208 325.1092 520.7287 761.2474 1102.8434 1542.4860 2204.9126 3090.7402 4720.0869 7725.4727 13755.3828 | lr 2.7e-04 | norm 5494.8594 | dt 9.891 +type train | step 3048 | loss 104.5136 204.7764 317.2509 514.4031 753.2520 1086.8390 1509.9286 2149.9792 3021.9312 4630.0488 7604.9229 13502.8770 | lr 2.7e-04 | norm 4452.0640 | dt 9.875 +type train | step 3049 | loss 113.0280 223.3831 339.7283 546.9160 796.9498 1144.2719 1580.8030 2253.1997 3151.0229 4807.3267 7910.8193 14031.9150 | lr 2.7e-04 | norm 6041.4946 | dt 9.872 +type train | step 3050 | loss 105.2549 205.2363 314.2879 504.3509 743.5174 1078.8940 1510.6121 2164.7661 3037.1045 4657.8052 7636.0332 13597.3252 | lr 2.7e-04 | norm 4660.4912 | dt 9.876 +type train | step 3051 | loss 97.1043 189.4315 299.3677 491.1176 728.4582 1046.5087 1471.2347 2107.7598 3006.3884 4640.8608 7621.5449 13501.8496 | lr 2.7e-04 | norm 4027.3193 | dt 9.885 +type train | step 3052 | loss 102.2391 200.8867 316.9115 511.0395 750.8995 1083.2214 1516.7322 2172.6250 3065.2979 4726.7100 7790.8662 13871.1924 | lr 2.7e-04 | norm 4156.8984 | dt 9.958 +type train | step 3053 | loss 107.7711 211.1342 324.0848 520.0066 757.9547 1085.7153 1511.1106 2152.5566 3021.8386 4634.2905 7665.3018 13780.2402 | lr 2.7e-04 | norm 4444.0264 | dt 9.868 +type train | step 3054 | loss 114.2391 226.9151 348.0894 558.5705 809.1713 1166.2867 1621.5980 2302.0857 3181.4324 4833.0483 7900.8066 13985.6201 | lr 2.7e-04 | norm 5829.7139 | dt 9.878 +type train | step 3055 | loss 97.4479 197.2570 312.6949 516.4208 765.6222 1109.7388 1557.5962 2247.0225 3179.8232 4901.2993 8083.6372 14413.8037 | lr 2.7e-04 | norm 5233.9028 | dt 9.873 +type train | step 3056 | loss 96.1021 190.1996 305.5536 502.3611 747.1058 1085.8508 1522.8184 2188.7515 3102.8945 4771.4688 7807.1270 13846.8096 | lr 2.7e-04 | norm 4580.5371 | dt 9.876 +type train | step 3057 | loss 109.5762 213.1770 324.6217 525.5732 767.9343 1122.6355 1563.3051 2238.7646 3071.8755 4677.4482 7622.9326 13490.6475 | lr 2.7e-04 | norm 5247.0107 | dt 9.854 +type train | step 3058 | loss 97.7247 194.1525 306.0031 500.9954 741.4337 1086.0532 1525.9980 2206.3013 3111.4336 4794.7871 7944.9136 14257.1582 | lr 2.7e-04 | norm 5540.5215 | dt 9.870 +type train | step 3059 | loss 101.5929 203.8963 318.7713 518.0366 757.2311 1091.6279 1518.1628 2166.8833 3045.2041 4691.3022 7767.7759 13832.7070 | lr 2.7e-04 | norm 5198.6045 | dt 9.880 +type train | step 3060 | loss 96.6647 189.2887 296.4801 484.6124 717.3599 1039.8969 1458.9602 2104.3179 2972.9316 4604.8818 7637.1431 13601.0879 | lr 2.7e-04 | norm 4480.4600 | dt 9.888 +type train | step 3061 | loss 98.5939 191.2856 299.1201 484.9255 717.8015 1043.4358 1462.5433 2098.8420 2960.8228 4573.9912 7548.4863 13509.2842 | lr 2.7e-04 | norm 4630.0063 | dt 9.871 +type train | step 3062 | loss 104.9557 212.9129 343.5288 568.1400 845.4940 1226.2771 1712.5500 2477.7119 3513.7483 5441.1128 9077.4365 16140.8535 | lr 2.7e-04 | norm 8121.1069 | dt 9.855 +type train | step 3063 | loss 104.9871 206.4781 327.4529 532.8644 790.1489 1151.6011 1607.7600 2322.7280 3271.2209 5043.1284 8336.1299 14846.6436 | lr 2.7e-04 | norm 4715.7583 | dt 9.858 +type train | step 3064 | loss 102.9925 202.3698 314.1678 508.6416 745.1198 1091.4982 1523.1035 2178.5293 3046.7993 4634.5161 7662.1270 13611.9238 | lr 2.7e-04 | norm 4457.6963 | dt 9.861 +type train | step 3065 | loss 95.7181 189.2798 298.3498 489.0829 728.3625 1065.3451 1507.0605 2185.2749 3099.1372 4813.8418 7970.3740 14129.5693 | lr 2.7e-04 | norm 5742.0186 | dt 9.860 +type train | step 3066 | loss 96.6861 189.0219 297.2756 489.4153 727.7916 1051.3184 1476.5912 2114.6750 2992.3311 4621.0762 7642.1133 13573.3564 | lr 2.7e-04 | norm 4469.7910 | dt 9.880 +type train | step 3067 | loss 102.8104 203.5364 315.5495 509.0949 750.0034 1084.7689 1520.8734 2169.0627 3069.3103 4699.3110 7696.0044 13620.3232 | lr 2.7e-04 | norm 4716.5669 | dt 9.874 +type train | step 3068 | loss 98.8065 193.4719 302.9736 492.0440 728.2692 1057.4591 1487.3811 2128.3682 3012.3701 4638.5967 7663.0776 13616.2461 | lr 2.7e-04 | norm 4578.1919 | dt 9.883 +type train | step 3069 | loss 97.9368 192.5984 304.0903 493.0331 731.4459 1057.9598 1484.2499 2121.6504 3018.8027 4673.0645 7733.6519 13811.9014 | lr 2.7e-04 | norm 5151.5596 | dt 9.882 +type train | step 3070 | loss 103.7564 205.2785 327.0481 537.2306 792.8395 1155.0858 1623.4773 2336.2390 3264.3840 5020.7559 8272.0752 14800.6016 | lr 2.7e-04 | norm 5383.3521 | dt 9.867 +type train | step 3071 | loss 100.4015 196.2761 312.1316 505.9794 746.7342 1088.2931 1526.0066 2195.2642 3099.3989 4775.8374 7878.6001 14013.5547 | lr 2.7e-04 | norm 4859.6045 | dt 9.887 +type train | step 3072 | loss 100.1009 197.5890 309.5166 501.8762 741.0775 1068.9554 1495.9956 2151.4641 3044.0305 4673.5220 7713.9766 13732.3135 | lr 2.7e-04 | norm 4477.0396 | dt 9.874 +type train | step 3073 | loss 103.3422 203.4400 319.8028 516.3735 761.2776 1101.9700 1548.2374 2213.7920 3099.9475 4756.4097 7797.3862 13934.4844 | lr 2.7e-04 | norm 4309.7441 | dt 9.883 +type train | step 3074 | loss 99.3886 198.8265 315.7061 519.5317 764.8214 1105.9814 1541.6696 2211.1567 3132.2231 4865.1240 8223.5059 14904.1455 | lr 2.7e-04 | norm 7277.0142 | dt 9.871 +type train | step 3075 | loss 104.5984 205.2684 317.0027 514.1434 752.2690 1095.3894 1525.0101 2179.2114 3059.9336 4718.4565 7761.1577 13938.9121 | lr 2.7e-04 | norm 4521.9536 | dt 9.880 +type train | step 3076 | loss 117.9598 231.5342 351.4193 557.9438 808.0328 1169.3380 1630.1394 2336.4221 3226.0168 4899.6914 7999.2285 14130.3633 | lr 2.7e-04 | norm 5030.4639 | dt 9.861 +type train | step 3077 | loss 95.9316 186.6867 297.0339 484.9423 722.4308 1048.5286 1482.3784 2138.6028 3040.6909 4683.2520 7719.1274 13671.4600 | lr 2.7e-04 | norm 5441.6899 | dt 9.871 +type train | step 3078 | loss 96.7669 187.7311 296.1626 482.1043 712.6610 1033.3386 1449.7522 2070.3689 2929.9326 4514.0796 7426.1084 13130.1973 | lr 2.7e-04 | norm 4007.8337 | dt 9.897 +type train | step 3079 | loss 99.0660 198.5357 310.5666 511.3624 749.4160 1078.3264 1514.0422 2170.4446 3057.0259 4675.4980 7706.9873 13591.8408 | lr 2.7e-04 | norm 6651.0635 | dt 9.873 +type train | step 3080 | loss 98.1435 192.1934 301.5420 492.5529 726.8281 1049.2375 1470.4308 2103.0930 2976.3208 4593.4971 7593.0068 13576.8564 | lr 2.7e-04 | norm 4405.7188 | dt 9.894 +type train | step 3081 | loss 98.1025 194.7336 304.7110 493.3264 733.1833 1057.9460 1481.0037 2134.0022 3007.7024 4609.9229 7596.9814 13437.1699 | lr 2.7e-04 | norm 4652.2056 | dt 9.871 +type train | step 3082 | loss 95.2866 188.4566 297.5951 483.5670 719.6334 1047.1243 1476.3696 2128.3264 3016.8096 4647.5684 7645.2466 13517.1826 | lr 2.7e-04 | norm 4145.2241 | dt 9.881 +type train | step 3083 | loss 100.9952 197.1613 304.8915 496.4243 733.5264 1057.0507 1483.3608 2127.0896 2998.0334 4617.2925 7597.5747 13419.7129 | lr 2.7e-04 | norm 4254.4175 | dt 9.890 +type train | step 3084 | loss 107.0193 210.5534 325.6985 522.4199 765.5354 1095.0192 1524.4944 2172.4705 3054.5920 4687.2329 7698.4590 13703.1367 | lr 2.7e-04 | norm 4544.7500 | dt 9.901 +type train | step 3085 | loss 101.6767 198.8196 312.3553 508.8005 743.5354 1073.8607 1496.5292 2138.2551 3017.0410 4651.5225 7705.8867 13794.1553 | lr 2.7e-04 | norm 4470.6831 | dt 9.869 +type train | step 3086 | loss 84.4774 169.5320 290.0003 488.3830 738.8586 1084.5309 1566.1620 2263.3533 3259.2515 5127.4668 8618.4912 15743.6230 | lr 2.7e-04 | norm 12792.8115 | dt 9.849 +type train | step 3087 | loss 107.7266 214.0223 329.7958 527.8113 770.2859 1107.1929 1543.4268 2191.9509 3086.7837 4704.1045 7719.6040 13681.8330 | lr 2.7e-04 | norm 4318.2246 | dt 9.863 +type train | step 3088 | loss 95.0621 185.9236 296.3126 487.8115 723.4662 1056.3165 1487.6124 2148.1707 3016.2739 4668.8047 7749.5918 13813.7295 | lr 2.7e-04 | norm 4650.5767 | dt 9.864 +type train | step 3089 | loss 96.6665 188.2954 298.4331 490.9558 727.3281 1054.9436 1481.9557 2128.7500 3019.4954 4657.6865 7697.2769 13835.2383 | lr 2.7e-04 | norm 4684.1030 | dt 9.880 +type train | step 3090 | loss 94.5838 184.5941 292.7766 480.1143 716.3011 1032.6769 1451.3503 2083.3508 2972.5015 4580.2627 7530.1655 13284.9512 | lr 2.7e-04 | norm 3674.9053 | dt 9.882 +type train | step 3091 | loss 107.1596 208.1368 331.4430 539.3817 790.7852 1156.5093 1629.7609 2344.1001 3282.2634 5041.9141 8263.1270 14690.5078 | lr 2.7e-04 | norm 6271.9609 | dt 9.865 +type train | step 3092 | loss 98.7591 193.5043 305.8301 501.1710 743.8198 1083.3693 1513.4094 2175.0405 3075.4751 4752.4766 7833.4883 13850.7324 | lr 2.7e-04 | norm 5350.0259 | dt 9.864 +type train | step 3093 | loss 99.2365 194.3396 303.4048 492.5335 725.8574 1048.9641 1463.3652 2094.9868 2964.0400 4544.8906 7490.1367 13303.3828 | lr 2.7e-04 | norm 4181.1855 | dt 9.886 +type train | step 3094 | loss 106.0725 207.4005 319.6788 511.1396 746.6502 1076.0217 1502.4845 2155.7839 3024.3364 4652.2876 7684.4932 13800.7031 | lr 2.7e-04 | norm 4855.0967 | dt 9.877 +type train | step 3095 | loss 109.8578 217.2310 335.2529 535.6676 774.8008 1105.7211 1524.7107 2159.3076 2984.5376 4560.4087 7457.4238 13253.5078 | lr 2.7e-04 | norm 5295.4790 | dt 9.875 +type train | step 3096 | loss 101.1320 197.0045 307.3883 499.1348 733.5070 1060.4602 1480.6464 2113.1548 2978.9792 4594.5850 7612.2529 13675.3096 | lr 2.7e-04 | norm 4178.1094 | dt 9.884 +type train | step 3097 | loss 104.4461 206.8521 315.6151 504.0927 728.7565 1035.0190 1430.8013 1987.8074 2725.1643 4115.7183 6609.4331 11873.6338 | lr 2.7e-04 | norm 5646.7954 | dt 9.829 +type train | step 3098 | loss 99.6994 196.7620 308.3235 500.5884 738.0677 1070.7863 1498.5181 2151.7605 3031.8237 4651.2451 7581.8491 13427.2217 | lr 2.7e-04 | norm 5036.3101 | dt 9.860 +type train | step 3099 | loss 101.1719 198.1597 313.4088 512.7936 760.4081 1116.9794 1565.5638 2255.7375 3163.5681 4848.3301 7969.0601 14144.7969 | lr 2.7e-04 | norm 5158.6675 | dt 9.865 +type train | step 3100 | loss 104.1663 202.6574 318.1307 517.0682 757.7790 1105.1913 1547.1357 2221.8333 3130.7000 4854.1982 8011.9570 14176.8105 | lr 2.7e-04 | norm 4888.5605 | dt 9.873 +type train | step 3101 | loss 100.2249 195.5872 304.8875 499.0675 742.5182 1095.3212 1541.2013 2233.1362 3122.3936 4758.2202 7803.1865 13803.9355 | lr 2.7e-04 | norm 5507.9331 | dt 9.857 +type train | step 3102 | loss 110.1101 216.3538 335.3408 534.0707 777.2614 1119.7573 1554.5149 2206.5071 3082.4648 4724.7402 7792.8945 13850.5947 | lr 2.7e-04 | norm 4199.6855 | dt 9.886 +type train | step 3103 | loss 104.9447 206.6500 319.7553 515.6859 755.0422 1088.0625 1513.6161 2165.1746 3043.6179 4685.4424 7751.9238 13793.2461 | lr 2.7e-04 | norm 4073.9299 | dt 9.871 +type train | step 3104 | loss 102.6244 199.6120 310.6032 503.2412 742.8836 1078.5361 1510.6460 2168.8850 3043.8203 4618.6240 7530.0820 13257.8076 | lr 2.7e-04 | norm 5229.9771 | dt 9.883 +type train | step 3105 | loss 100.8969 197.2604 302.9473 494.7724 727.7635 1055.7042 1482.5513 2115.4138 2954.4414 4552.8120 7476.8823 13241.6338 | lr 2.7e-04 | norm 4671.6455 | dt 9.869 +type train | step 3106 | loss 90.5684 179.3810 290.5590 481.9045 720.6334 1044.6232 1474.0710 2134.3706 3055.7542 4760.5664 7856.8755 13922.7285 | lr 2.7e-04 | norm 7251.1060 | dt 9.855 +type train | step 3107 | loss 98.5418 191.9408 297.4451 481.3501 711.1063 1036.3151 1459.1864 2098.3174 2969.1348 4609.9341 7624.7051 13654.7832 | lr 2.7e-04 | norm 5111.9634 | dt 9.863 +type train | step 3108 | loss 90.5602 176.4896 277.6881 458.2552 683.8087 1000.1910 1411.1332 2052.3286 2890.6765 4497.9434 7440.4761 13397.4062 | lr 2.7e-04 | norm 7941.2705 | dt 9.853 +type train | step 3109 | loss 96.1302 189.6237 299.4181 487.2202 722.2291 1045.6384 1472.2585 2114.2646 3009.2129 4664.6699 7729.3916 13825.7383 | lr 2.7e-04 | norm 4328.1382 | dt 9.877 +type train | step 3110 | loss 94.8758 186.4898 295.2383 481.0630 721.3452 1061.4786 1504.8829 2174.2695 3071.4968 4766.4004 7882.9727 14136.0029 | lr 2.7e-04 | norm 6078.2979 | dt 9.869 +type train | step 3111 | loss 101.9394 198.0390 307.1354 492.2275 725.8010 1050.7570 1479.4041 2116.4951 2981.9163 4573.7822 7484.1943 13268.8740 | lr 2.7e-04 | norm 4584.0200 | dt 9.858 +type train | step 3112 | loss 105.7525 208.1006 321.5835 519.4871 760.6145 1104.4446 1535.1311 2198.3127 3092.0962 4762.9883 7858.4404 13948.9717 | lr 2.7e-04 | norm 4707.0376 | dt 9.873 +type train | step 3113 | loss 97.6138 188.7236 298.5742 490.7551 725.2731 1058.0166 1480.7290 2134.8950 2988.0901 4584.1167 7458.6948 13146.2842 | lr 2.6e-04 | norm 4994.7988 | dt 9.864 +type train | step 3114 | loss 95.4405 187.4476 299.2508 489.4544 728.3522 1057.8198 1488.2316 2139.5850 3052.6135 4715.9629 7733.4160 13638.4102 | lr 2.6e-04 | norm 3974.0469 | dt 9.877 +type train | step 3115 | loss 93.9179 186.3113 294.8285 484.8322 730.0024 1079.8721 1524.7489 2224.9829 3140.2800 4857.0483 7999.7676 14243.5283 | lr 2.6e-04 | norm 6357.3984 | dt 9.886 +type train | step 3116 | loss 105.6590 208.5947 322.8202 516.1497 750.9567 1083.8550 1505.6493 2150.9167 3019.6550 4658.9639 7676.8071 13734.6670 | lr 2.6e-04 | norm 4602.5898 | dt 9.872 +type train | step 3117 | loss 95.7087 184.7653 289.9498 479.2767 715.6136 1043.9146 1472.8229 2129.0957 3011.7678 4648.7563 7620.4663 13443.3975 | lr 2.6e-04 | norm 6407.5791 | dt 9.868 +type train | step 3118 | loss 95.9077 186.9467 292.1971 474.1734 704.7567 1017.9451 1427.7350 2057.1260 2920.3105 4493.9966 7381.4937 13042.6494 | lr 2.6e-04 | norm 3917.8374 | dt 9.902 +type train | step 3119 | loss 97.6647 192.7307 301.6446 491.3934 725.4157 1052.8909 1478.8821 2128.9395 3015.8022 4651.0469 7677.9736 13636.8320 | lr 2.6e-04 | norm 4441.0308 | dt 9.877 +type train | step 3120 | loss 106.2663 210.1729 332.2222 545.7179 798.2975 1149.5450 1597.6608 2270.6318 3153.5952 4808.0342 7930.2852 14159.7988 | lr 2.6e-04 | norm 6582.4751 | dt 9.874 +type train | step 3121 | loss 84.4836 169.0251 273.9218 464.2592 694.5217 1027.4688 1463.4763 2136.1636 3047.1685 4793.6108 8143.6909 14992.7383 | lr 2.6e-04 | norm 9271.2676 | dt 9.842 +type train | step 3122 | loss 97.3864 189.1554 297.2593 486.5951 721.5880 1056.8883 1499.8202 2160.2080 3060.3254 4725.8574 7787.0054 13788.0078 | lr 2.6e-04 | norm 5770.1206 | dt 9.873 +type train | step 3123 | loss 101.1198 200.0659 311.9220 505.4330 739.0696 1065.8799 1490.9050 2143.4844 3028.9326 4710.0083 7906.2437 14189.3125 | lr 2.6e-04 | norm 5366.2676 | dt 9.870 +type train | step 3124 | loss 103.1014 203.9225 316.0526 512.6868 752.2963 1100.1401 1537.5111 2210.8660 3041.4861 4636.5537 7660.4214 13677.5947 | lr 2.6e-04 | norm 5165.5249 | dt 9.879 +type train | step 3125 | loss 100.0929 195.2780 304.0988 494.2159 731.2490 1058.9965 1484.1711 2123.0918 2992.7446 4604.1855 7609.7085 13574.8281 | lr 2.6e-04 | norm 5023.0557 | dt 9.883 +type train | step 3126 | loss 91.0023 178.0578 284.5549 469.7164 702.4778 1027.6616 1459.3158 2096.5908 2983.0735 4588.7192 7546.9688 13330.5830 | lr 2.6e-04 | norm 4356.8818 | dt 9.878 +type train | step 3127 | loss 96.9208 189.5341 298.1281 485.9062 720.6447 1053.7129 1490.4583 2157.2869 3055.2595 4745.1431 7870.5996 14131.2686 | lr 2.6e-04 | norm 4675.2490 | dt 9.871 +type train | step 3128 | loss 95.1806 186.4782 293.7710 480.7169 713.2875 1037.6650 1455.7488 2092.1401 2971.0842 4591.9492 7537.4058 13306.9463 | lr 2.6e-04 | norm 4140.8857 | dt 9.873 +type train | step 3129 | loss 92.6052 186.3665 298.0032 492.2189 729.8640 1052.7086 1475.9006 2123.8218 3029.5637 4729.3633 7851.1216 14087.0332 | lr 2.6e-04 | norm 6747.8770 | dt 9.869 +type train | step 3130 | loss 100.2709 197.5311 309.7263 507.6084 747.9666 1080.4354 1519.3597 2188.6572 3073.8494 4743.9404 7863.4160 13955.9424 | lr 2.6e-04 | norm 5160.0645 | dt 9.868 +type train | step 3131 | loss 106.0868 213.5858 334.5292 540.4406 790.4873 1126.3448 1567.3500 2219.7690 3129.6208 4779.9028 7948.8765 14110.7139 | lr 2.6e-04 | norm 7296.7964 | dt 9.876 +type train | step 3132 | loss 99.1084 194.4544 302.7129 492.0999 724.5076 1050.4933 1467.4114 2088.4033 2937.9590 4477.8989 7333.3945 13009.2666 | lr 2.6e-04 | norm 4556.4365 | dt 9.906 +type train | step 3133 | loss 101.0886 199.3261 312.2953 504.4910 746.1647 1074.0852 1520.0310 2182.9617 3078.2773 4752.3325 7779.2808 13736.4219 | lr 2.6e-04 | norm 6201.8599 | dt 9.868 +type train | step 3134 | loss 97.6255 191.5779 297.5286 480.6691 712.8219 1034.9185 1449.7400 2094.3425 2968.3442 4586.3081 7585.6079 13485.4834 | lr 2.6e-04 | norm 4339.4307 | dt 9.882 +type train | step 3135 | loss 98.7470 193.9572 304.3071 502.7607 743.4321 1097.1940 1543.9244 2248.4143 3158.7974 4876.3555 8111.8701 14473.0547 | lr 2.6e-04 | norm 5634.1328 | dt 9.871 +type train | step 3136 | loss 95.9413 189.6560 299.5733 492.0494 732.7101 1062.2366 1490.0363 2141.0002 3022.9397 4649.1323 7633.3901 13464.3232 | lr 2.6e-04 | norm 4554.3052 | dt 9.882 +type train | step 3137 | loss 100.4456 197.3963 305.4486 498.3143 735.2334 1072.5419 1503.9462 2167.4211 3006.1199 4614.9570 7668.1196 13748.9316 | lr 2.6e-04 | norm 6095.9438 | dt 9.857 +type train | step 3138 | loss 99.0146 193.1458 299.3167 487.3528 717.5267 1038.8091 1460.1201 2090.1631 2958.1055 4570.2168 7561.7695 13475.0654 | lr 2.6e-04 | norm 4367.6685 | dt 9.887 +type train | step 3139 | loss 97.3059 190.0632 299.3472 488.3030 720.5667 1045.0430 1467.3143 2101.5862 2972.6885 4601.1421 7623.2363 13583.3232 | lr 2.6e-04 | norm 4231.9048 | dt 9.876 +type train | step 3140 | loss 95.6731 188.9206 296.7030 486.3857 723.1212 1058.1384 1486.8086 2144.5774 3024.7866 4641.3428 7656.2129 13576.7871 | lr 2.6e-04 | norm 4581.0742 | dt 9.873 +type train | step 3141 | loss 96.2050 189.1145 296.6968 483.7365 719.1885 1039.7692 1463.6782 2105.6892 2997.5613 4636.0273 7628.4229 13408.2559 | lr 2.6e-04 | norm 3861.2380 | dt 9.888 +type train | step 3142 | loss 96.9004 187.9659 297.4917 488.5132 721.4778 1058.3768 1495.0507 2155.0576 3014.3823 4650.6460 7679.9233 13622.7461 | lr 2.6e-04 | norm 4359.9937 | dt 9.874 +type train | step 3143 | loss 99.5684 193.5418 299.8508 485.3526 716.4313 1039.0981 1456.2010 2095.4128 2942.3257 4525.6729 7401.2061 13033.8242 | lr 2.6e-04 | norm 4050.2698 | dt 9.881 +type train | step 3144 | loss 101.6050 198.9137 311.2075 498.9692 735.9005 1054.2375 1480.6892 2121.4470 2989.9268 4614.7212 7544.8237 13471.4160 | lr 2.6e-04 | norm 5726.9629 | dt 9.880 +type train | step 3145 | loss 98.8455 192.2556 301.2634 489.1423 725.1183 1059.6577 1498.7117 2155.2222 3046.6804 4697.2271 7684.1724 13460.0801 | lr 2.6e-04 | norm 4245.3145 | dt 9.894 +type train | step 3146 | loss 91.8960 179.9566 285.6259 468.0528 699.3548 1022.0139 1452.0153 2099.4316 2979.7781 4615.2773 7601.3105 13468.9541 | lr 2.6e-04 | norm 3838.1208 | dt 9.884 +type train | step 3147 | loss 101.8448 200.7889 309.6251 500.7869 735.3500 1068.1635 1495.3641 2143.6226 3007.3047 4604.7432 7577.9375 13309.3867 | lr 2.6e-04 | norm 4077.2166 | dt 9.887 +type train | step 3148 | loss 96.2865 188.7268 297.7245 486.6974 718.8286 1045.5072 1463.7793 2108.9082 2974.0942 4574.2007 7530.1123 13289.3828 | lr 2.6e-04 | norm 3740.5994 | dt 9.882 +type train | step 3149 | loss 97.7941 191.3635 298.0117 486.0834 718.9802 1048.6696 1473.7334 2128.1238 3019.8135 4671.7979 7701.0381 13619.3223 | lr 2.6e-04 | norm 4391.0229 | dt 9.873 +type train | step 3150 | loss 101.2525 197.2870 305.4842 495.7365 725.6776 1044.8727 1459.4932 2083.0630 2936.9971 4519.1719 7422.6606 13092.8281 | lr 2.6e-04 | norm 4020.9092 | dt 9.879 +type train | step 3151 | loss 94.5407 183.6484 285.9456 465.4422 693.1509 1009.5244 1425.5442 2063.8208 2938.1775 4546.3223 7513.0239 13418.6035 | lr 2.6e-04 | norm 4951.9336 | dt 9.872 +type train | step 3152 | loss 103.0689 201.5817 313.9055 510.7015 750.7667 1092.1292 1526.5870 2191.3591 3077.8098 4744.9136 7759.8638 13670.0645 | lr 2.6e-04 | norm 4332.5991 | dt 9.872 +type train | step 3153 | loss 96.3506 190.2368 302.0927 496.4084 737.0625 1067.8114 1495.8674 2144.2852 3036.9255 4675.7256 7685.0596 13538.7930 | lr 2.6e-04 | norm 5022.6479 | dt 9.875 +type train | step 3154 | loss 99.2481 198.2666 310.1532 504.5441 741.6537 1076.1294 1506.2358 2149.3083 3012.1025 4642.1860 7669.6284 13727.7520 | lr 2.6e-04 | norm 4616.4590 | dt 9.867 +type train | step 3155 | loss 99.7282 194.4352 302.9456 491.9596 725.9999 1055.5212 1482.6024 2125.5996 2999.7717 4628.9658 7654.9390 13580.1758 | lr 2.6e-04 | norm 4521.8828 | dt 9.891 +type train | step 3156 | loss 101.9920 199.6292 312.9808 510.3464 754.4208 1092.1119 1522.6649 2187.6272 3081.9409 4725.5190 7772.5967 13748.6738 | lr 2.6e-04 | norm 4733.8423 | dt 9.891 +type train | step 3157 | loss 99.2810 193.9093 305.8454 497.4169 737.3646 1076.6154 1511.9982 2168.5642 3055.8867 4737.8911 7862.2861 13926.4521 | lr 2.6e-04 | norm 4529.8521 | dt 9.873 +type train | step 3158 | loss 97.4944 190.6957 298.6771 485.1506 715.8182 1038.1498 1457.2283 2094.2449 2973.6643 4592.8335 7568.8662 13399.3711 | lr 2.6e-04 | norm 3693.1301 | dt 9.883 +type train | step 3159 | loss 95.1788 185.1694 293.0020 478.9674 712.8018 1025.9272 1444.5369 2071.9248 2954.3110 4570.9561 7540.1284 13328.0107 | lr 2.6e-04 | norm 4012.6184 | dt 9.886 +type train | step 3160 | loss 97.2491 191.0403 297.9995 488.7445 718.5822 1051.4159 1476.8066 2132.2556 3010.5737 4664.8389 7794.6836 14125.7314 | lr 2.6e-04 | norm 6864.7065 | dt 9.849 +type train | step 3161 | loss 90.8902 177.4306 282.6918 467.1120 696.0509 1016.7184 1432.5603 2070.6941 2920.8079 4512.1182 7454.4761 13281.7754 | lr 2.6e-04 | norm 4485.8530 | dt 9.876 +type train | step 3162 | loss 101.7908 200.1340 312.0319 509.0984 749.6615 1090.8302 1530.1575 2212.6553 3098.9126 4769.2578 7846.9204 13943.0273 | lr 2.6e-04 | norm 4374.0747 | dt 9.867 +type train | step 3163 | loss 96.6238 188.8311 296.1156 480.8346 713.4595 1031.7583 1449.0375 2088.8918 2954.7979 4566.3726 7528.5132 13457.3242 | lr 2.6e-04 | norm 4321.2109 | dt 9.887 +type train | step 3164 | loss 98.0906 190.9618 299.2329 495.0598 727.3696 1054.1768 1476.3165 2111.5261 2952.4187 4548.7061 7476.1943 13226.0010 | lr 2.6e-04 | norm 4890.5215 | dt 9.867 +type train | step 3165 | loss 104.7219 206.1595 323.4487 525.8852 767.5452 1112.1963 1552.7996 2221.1221 3128.3574 4847.3677 8012.1025 14222.2783 | lr 2.6e-04 | norm 4953.7319 | dt 9.879 +type train | step 3166 | loss 101.1574 200.1694 310.9989 504.8352 749.9429 1097.9163 1545.7034 2223.1367 3123.3811 4785.5034 7838.2021 13807.9375 | lr 2.6e-04 | norm 4444.0293 | dt 9.870 +type train | step 3167 | loss 109.2713 217.4878 331.3725 524.5778 762.9780 1110.7529 1547.8833 2225.2808 3095.3091 4742.0693 7757.2715 13804.7793 | lr 2.6e-04 | norm 6561.4536 | dt 9.868 +type train | step 3168 | loss 98.9072 193.3670 300.0144 486.2427 719.4316 1043.9211 1466.3942 2098.9500 2967.7522 4574.6885 7501.0420 13381.2568 | lr 2.6e-04 | norm 4783.5361 | dt 9.874 +type train | step 3169 | loss 99.5444 194.8141 303.3636 495.0856 730.2249 1054.9775 1480.8910 2128.1890 2996.1057 4633.8916 7644.4780 13671.4717 | lr 2.6e-04 | norm 4555.8252 | dt 9.878 +type train | step 3170 | loss 109.7087 214.5509 328.1006 525.3356 772.3239 1114.9551 1553.4993 2229.6477 3119.9314 4763.9756 7880.3398 13949.3506 | lr 2.6e-04 | norm 5426.9028 | dt 9.857 +type train | step 3171 | loss 103.8972 202.0488 312.4947 503.2455 735.6757 1065.1812 1477.2043 2101.0959 2932.1147 4490.0547 7377.8232 13212.7998 | lr 2.6e-04 | norm 5124.7319 | dt 9.875 +type train | step 3172 | loss 93.0387 181.6896 290.1127 478.8941 714.7404 1038.9187 1468.0155 2121.3503 3020.6453 4685.7212 7684.1479 13576.5283 | lr 2.6e-04 | norm 5112.2241 | dt 9.880 +type train | step 3173 | loss 99.9447 195.3846 305.0225 500.2323 735.6358 1061.9965 1488.4242 2128.4216 2988.1497 4596.1992 7556.2041 13419.8691 | lr 2.6e-04 | norm 4380.2148 | dt 9.881 +type train | step 3174 | loss 104.3639 205.7866 315.2055 505.1157 739.3914 1071.9476 1500.8495 2154.1301 3011.5884 4643.5073 7635.0791 13560.2080 | lr 2.6e-04 | norm 4356.6523 | dt 9.877 +type train | step 3175 | loss 101.6860 199.9056 309.8076 500.2366 733.9041 1057.5376 1480.4778 2115.7048 2995.4243 4591.6245 7484.9448 13218.3066 | lr 2.6e-04 | norm 3762.4133 | dt 9.888 +type train | step 3176 | loss 98.3961 194.2698 303.3666 496.3495 734.6119 1068.3750 1497.9648 2152.4451 3048.6943 4728.7402 7788.4351 13802.5420 | lr 2.6e-04 | norm 4496.1333 | dt 9.872 +type train | step 3177 | loss 106.5888 209.6313 322.3481 512.6086 750.0637 1076.7036 1500.2061 2140.1345 2978.1670 4578.6284 7489.6997 13515.2598 | lr 2.6e-04 | norm 5743.6152 | dt 9.849 +type train | step 3178 | loss 107.2738 209.8021 326.3168 529.7449 769.0416 1105.9336 1536.9297 2180.2446 3036.5068 4639.1260 7554.9395 13318.4121 | lr 2.6e-04 | norm 4082.3369 | dt 9.873 +type train | step 3179 | loss 97.1016 189.6420 297.8108 485.1274 716.0914 1041.4539 1461.5487 2094.6018 2948.3835 4533.3501 7455.7134 13210.3477 | lr 2.6e-04 | norm 3796.0986 | dt 9.884 +type train | step 3180 | loss 118.2133 236.0899 357.2531 564.0143 810.5372 1165.3928 1612.2678 2282.0107 3165.9060 4769.2417 7788.5977 13729.9316 | lr 2.6e-04 | norm 7306.1807 | dt 9.858 +type train | step 3181 | loss 101.6928 200.7279 311.0706 502.2146 739.3029 1072.3286 1496.1282 2141.3633 3005.3835 4619.2256 7615.8154 13513.9756 | lr 2.6e-04 | norm 3611.6243 | dt 9.879 +type train | step 3182 | loss 89.4307 177.4041 283.9071 467.9680 701.4759 1017.6772 1440.9030 2071.1738 2963.7129 4587.7417 7568.3496 13442.7598 | lr 2.6e-04 | norm 4715.2534 | dt 9.862 +type train | step 3183 | loss 95.3238 186.2854 294.1835 488.5632 720.9449 1066.7183 1509.2228 2190.9370 3092.8394 4787.0156 7892.7529 13954.5352 | lr 2.5e-04 | norm 5131.7837 | dt 9.869 +type train | step 3184 | loss 97.5067 189.3324 299.6955 490.6708 725.8388 1061.3232 1487.4454 2134.7917 2990.2314 4603.7744 7539.9507 13413.0010 | lr 2.5e-04 | norm 5571.2334 | dt 9.864 +type train | step 3185 | loss 93.6292 181.9956 288.7600 475.1668 706.8445 1031.4863 1457.4585 2097.9849 2953.5996 4550.1602 7450.4722 13205.9912 | lr 2.5e-04 | norm 4183.5039 | dt 9.890 +type train | step 3186 | loss 101.2146 199.9641 311.0665 512.4166 749.2537 1084.1641 1501.9678 2136.1777 2959.3757 4486.1265 7306.8462 12900.3877 | lr 2.5e-04 | norm 4828.3047 | dt 9.864 +type train | step 3187 | loss 95.9745 186.5272 293.7442 481.9447 713.5115 1030.6941 1441.2333 2064.1096 2918.5566 4489.3311 7372.6641 12971.5986 | lr 2.5e-04 | norm 3634.2664 | dt 9.866 +type train | step 3188 | loss 97.3352 190.2926 296.1060 482.1655 711.4382 1039.6945 1460.8293 2103.0598 2951.0635 4582.6738 7516.5244 13328.7295 | lr 2.5e-04 | norm 5540.5146 | dt 9.862 +type train | step 3189 | loss 91.7314 178.7065 284.1902 465.7979 695.2244 1013.0447 1434.0432 2071.1082 2939.1812 4544.9082 7469.2793 13187.0166 | lr 2.5e-04 | norm 4004.4902 | dt 9.875 +type train | step 3190 | loss 101.6844 199.8376 312.8427 504.4749 740.4641 1071.9786 1503.5338 2156.7227 3021.8110 4651.5620 7655.7017 13574.0312 | lr 2.5e-04 | norm 3985.1465 | dt 9.899 +type train | step 3191 | loss 107.4657 209.5346 322.7536 519.8592 759.2250 1080.1309 1503.2095 2142.0623 2999.5259 4573.7090 7467.8892 13205.4912 | lr 2.5e-04 | norm 5091.2466 | dt 9.860 +type train | step 3192 | loss 103.4219 204.3107 316.6933 511.2031 740.2936 1074.2676 1498.5063 2139.7988 2984.2983 4583.6333 7582.0806 13518.9688 | lr 2.5e-04 | norm 5461.0562 | dt 9.875 +type train | step 3193 | loss 97.1015 191.9890 303.2556 500.0669 747.1831 1105.4160 1557.4182 2265.2952 3182.7144 4917.1812 8086.3735 14437.8730 | lr 2.5e-04 | norm 5397.0356 | dt 9.862 +type train | step 3194 | loss 109.2167 212.6969 330.3165 533.0163 774.1736 1121.6946 1554.6866 2210.9761 3026.5840 4598.6929 7507.6450 13235.2930 | lr 2.5e-04 | norm 4748.6948 | dt 9.868 +type train | step 3195 | loss 95.8297 190.3543 299.6461 483.5593 717.7078 1048.3617 1474.7450 2123.1472 2978.8467 4601.1411 7513.5508 13306.7275 | lr 2.5e-04 | norm 5607.8120 | dt 9.884 +type train | step 3196 | loss 101.3638 197.8347 306.8152 494.3646 728.7367 1054.5298 1476.4391 2118.3276 2990.9524 4619.4053 7623.5977 13649.7441 | lr 2.5e-04 | norm 4378.3218 | dt 9.897 +type train | step 3197 | loss 100.8572 198.1723 308.5826 497.6504 729.4663 1057.0557 1476.4226 2114.3318 2965.3667 4590.2334 7626.8550 13675.1416 | lr 2.5e-04 | norm 5319.8779 | dt 9.862 +type train | step 3198 | loss 101.7772 201.4882 313.0233 508.3235 756.7241 1111.8558 1566.9688 2275.6770 3183.4766 4894.0688 7994.5410 14046.1816 | lr 2.5e-04 | norm 5232.7422 | dt 9.866 +type train | step 3199 | loss 98.4751 191.4694 300.1906 483.9645 714.6118 1023.2621 1429.0923 2040.1251 2886.7480 4434.9346 7273.7729 12796.2930 | lr 2.5e-04 | norm 4023.4609 | dt 9.885 +type train | step 3200 | loss 98.3859 191.3970 299.0198 489.0995 722.5353 1043.2112 1458.9028 2109.9370 2982.9121 4626.0820 7694.1670 13774.3096 | lr 2.5e-04 | norm 5611.1069 | dt 9.870 +type train | step 3201 | loss 91.4763 177.0670 284.1524 474.0678 705.8191 1033.1824 1462.3074 2114.3896 3008.9478 4669.2285 7740.8750 13765.3789 | lr 2.5e-04 | norm 4384.3232 | dt 9.871 +type train | step 3202 | loss 98.7920 195.1098 306.5126 497.3006 732.2640 1060.2814 1481.9261 2122.5901 2992.0442 4630.5845 7668.6406 13685.3701 | lr 2.5e-04 | norm 4530.3662 | dt 9.882 +type train | step 3203 | loss 98.1679 193.2934 299.9045 484.0298 714.8408 1034.1521 1447.9041 2068.7041 2919.9128 4509.7476 7445.6216 13182.8555 | lr 2.5e-04 | norm 4310.1206 | dt 9.887 +type train | step 3204 | loss 96.9898 188.6904 298.4618 490.2239 725.7245 1055.9451 1486.1833 2139.6331 3011.5474 4637.4575 7653.8145 13609.7881 | lr 2.5e-04 | norm 4592.6289 | dt 9.869 +type train | step 3205 | loss 94.0040 184.0317 290.2076 477.1916 715.3533 1053.8210 1495.0054 2170.0898 3072.8005 4724.0850 7740.2227 13570.9961 | lr 2.5e-04 | norm 4545.3027 | dt 9.879 +type train | step 3206 | loss 94.9035 185.8470 293.2235 480.9492 713.3127 1049.4272 1486.8807 2150.1965 3049.2539 4711.3667 7768.4277 13693.2148 | lr 2.5e-04 | norm 4211.9766 | dt 9.877 +type train | step 3207 | loss 104.0744 204.1246 317.2671 512.8425 752.7284 1084.3035 1511.1697 2146.5669 3010.8787 4608.9849 7567.0942 13374.2959 | lr 2.5e-04 | norm 4210.5815 | dt 9.881 +type train | step 3208 | loss 96.6980 188.9615 300.6237 494.5079 730.5839 1072.9801 1510.0593 2182.3225 3063.1855 4741.6880 7811.1436 13813.9277 | lr 2.5e-04 | norm 5187.1470 | dt 9.895 +type train | step 3209 | loss 106.7380 208.6919 322.5948 530.3823 769.0186 1111.7450 1540.9968 2193.7947 3019.3687 4625.5005 7612.9429 13527.2090 | lr 2.5e-04 | norm 4509.3940 | dt 9.872 +type train | step 3210 | loss 100.3168 193.6044 303.6323 494.7572 727.9092 1059.0182 1490.9241 2142.9314 3002.0850 4599.5010 7529.9897 13324.3848 | lr 2.5e-04 | norm 4723.2075 | dt 9.876 +type train | step 3211 | loss 95.6380 187.5744 292.2456 478.7455 707.2301 1021.2427 1435.1055 2058.3643 2915.5229 4517.1353 7416.5132 13056.1807 | lr 2.5e-04 | norm 3848.6055 | dt 9.889 +type train | step 3212 | loss 96.9726 190.1929 296.0584 486.8413 724.8756 1065.5347 1511.1687 2180.4993 3071.1431 4736.0112 7849.3335 14059.2207 | lr 2.5e-04 | norm 4732.0093 | dt 9.854 +type train | step 3213 | loss 100.4559 198.0798 310.2744 501.7513 742.7299 1079.0698 1513.9762 2179.2183 3057.9756 4708.5049 7807.6353 13806.1543 | lr 2.5e-04 | norm 5079.8608 | dt 9.857 +type train | step 3214 | loss 105.0306 206.0179 318.7860 514.2614 753.6147 1092.6660 1518.4716 2173.6372 3033.3303 4647.8076 7657.5684 13578.0732 | lr 2.5e-04 | norm 4269.2910 | dt 9.864 +type train | step 3215 | loss 98.5518 192.0664 301.3247 489.1110 729.7838 1057.5602 1485.9126 2132.6670 3013.9106 4630.6943 7609.2686 13405.9463 | lr 2.5e-04 | norm 3885.5171 | dt 9.872 +type train | step 3216 | loss 104.2669 205.6158 319.5221 512.1764 748.7159 1072.4719 1488.2527 2122.5203 2976.5886 4579.4971 7547.2344 13478.9248 | lr 2.5e-04 | norm 4562.8760 | dt 9.888 +type train | step 3217 | loss 97.2186 192.0288 299.5697 491.1530 724.9314 1051.7739 1471.7269 2119.6428 3000.2292 4642.9219 7689.3345 13651.3242 | lr 2.5e-04 | norm 4560.4971 | dt 9.882 +type train | step 3218 | loss 98.2675 193.7322 304.8500 498.3971 736.0153 1074.5704 1511.7906 2175.9607 3056.7021 4732.2217 7837.3125 14020.4648 | lr 2.5e-04 | norm 4095.4297 | dt 9.869 +type train | step 3219 | loss 92.3539 179.1232 288.2807 478.4329 712.0424 1044.9810 1483.5751 2134.7979 3029.0889 4689.2236 7779.7324 13821.3428 | lr 2.5e-04 | norm 4580.9551 | dt 9.876 +type train | step 3220 | loss 97.4756 191.9930 300.5242 493.4790 732.0679 1060.1830 1489.3811 2140.1775 3000.6123 4639.5801 7615.8330 13560.2881 | lr 2.5e-04 | norm 5727.1597 | dt 9.864 +type train | step 3221 | loss 97.6390 193.6399 300.8017 487.7110 721.5488 1038.7174 1455.5103 2083.5208 2958.8418 4567.1055 7499.0825 13313.6543 | lr 2.5e-04 | norm 3978.9636 | dt 9.873 +type train | step 3222 | loss 105.5604 204.2763 312.4395 509.0156 740.2768 1072.8674 1488.5894 2129.0291 2960.9412 4576.0737 7664.1387 13820.5303 | lr 2.5e-04 | norm 7457.0474 | dt 9.852 +type train | step 3223 | loss 104.2746 205.1402 314.4597 501.8480 737.9135 1058.4575 1484.1764 2120.9028 3001.6523 4623.8569 7565.3955 13338.1016 | lr 2.5e-04 | norm 4656.4282 | dt 9.867 +type train | step 3224 | loss 97.2719 190.2577 296.5168 483.3323 708.9397 1037.4192 1471.5991 2122.6213 2971.4822 4578.4229 7565.4355 13522.8828 | lr 2.5e-04 | norm 5854.6206 | dt 9.876 +type train | step 3225 | loss 99.7833 195.8255 313.0406 514.3591 761.2091 1101.8486 1547.6901 2221.7612 3155.9937 4891.6138 8072.1196 14383.9629 | lr 2.5e-04 | norm 4967.7788 | dt 9.874 +type train | step 3226 | loss 90.2221 177.8425 284.8898 473.2038 710.5337 1034.9467 1469.6550 2135.1963 3055.7891 4716.1318 7690.0703 13504.5664 | lr 2.5e-04 | norm 5017.9336 | dt 9.853 +type train | step 3227 | loss 100.1253 193.7076 302.1425 488.1941 726.0282 1034.7238 1460.5697 2091.2625 2986.7834 4607.9375 7585.9248 13433.1377 | lr 2.5e-04 | norm 8400.1992 | dt 9.876 +type train | step 3228 | loss 93.7719 182.3790 289.0020 476.3726 710.6410 1035.4266 1462.6556 2109.1265 2995.6367 4674.7549 7759.9229 13816.6641 | lr 2.5e-04 | norm 4803.8638 | dt 9.872 +type train | step 3229 | loss 94.3948 185.8033 294.0661 480.2724 711.7336 1034.5446 1453.2180 2091.1428 2973.0776 4591.4512 7582.2930 13391.9648 | lr 2.5e-04 | norm 3874.4160 | dt 9.895 +type train | step 3230 | loss 95.1075 185.1822 290.1828 475.7527 707.6392 1024.8887 1442.6130 2070.9341 2952.1917 4587.1680 7561.2891 13374.9697 | lr 2.5e-04 | norm 4072.9607 | dt 9.882 +type train | step 3231 | loss 102.0422 197.1958 309.0347 505.9146 739.5497 1066.0490 1485.3818 2118.0303 2962.9966 4572.9004 7539.7607 13461.3008 | lr 2.5e-04 | norm 4655.4131 | dt 9.866 +type train | step 3232 | loss 95.1015 185.5590 289.7773 474.2301 703.6063 1036.9955 1472.2598 2113.7256 2976.0193 4573.1338 7548.1289 13525.4961 | lr 2.5e-04 | norm 4904.3652 | dt 9.861 +type train | step 3233 | loss 97.6835 193.5342 302.5548 492.6784 733.6543 1057.2355 1484.5262 2123.4397 2994.0747 4603.5190 7560.6958 13385.8291 | lr 2.5e-04 | norm 6285.0386 | dt 9.865 +type train | step 3234 | loss 98.0494 190.9244 296.9489 481.9352 712.3352 1030.5999 1458.8220 2106.0427 2974.3296 4607.4072 7633.4961 13620.4727 | lr 2.5e-04 | norm 5280.3252 | dt 9.868 +type train | step 3235 | loss 97.9190 193.2904 303.5910 495.7548 735.7268 1065.6068 1485.9061 2130.0952 2989.0449 4608.1050 7598.5073 13641.1631 | lr 2.5e-04 | norm 5133.0728 | dt 9.871 +type train | step 3236 | loss 92.1065 182.9179 291.6518 482.9210 719.8269 1046.7662 1476.2561 2135.1858 3023.0945 4691.2964 7816.1494 13939.7539 | lr 2.5e-04 | norm 5313.4746 | dt 9.881 +type train | step 3237 | loss 95.8355 187.2575 294.6006 481.7536 712.4095 1030.9707 1449.0018 2085.2136 2944.3823 4561.3589 7532.0293 13360.0518 | lr 2.5e-04 | norm 4222.9565 | dt 9.878 +type train | step 3238 | loss 94.6512 185.8342 290.7756 481.8718 712.8677 1046.2217 1474.3533 2132.0386 3007.2769 4628.1812 7671.3472 13624.6426 | lr 2.5e-04 | norm 4744.2988 | dt 9.877 +type train | step 3239 | loss 105.4501 209.2157 322.2574 513.7684 755.2592 1079.4485 1510.1387 2148.0540 3027.0115 4682.5117 7718.6382 13693.7090 | lr 2.5e-04 | norm 4910.1548 | dt 9.881 +type train | step 3240 | loss 93.1128 183.5931 293.5686 481.8391 719.5989 1042.2596 1472.6202 2110.9404 3018.3489 4693.4570 7767.6943 13829.9150 | lr 2.5e-04 | norm 4512.3931 | dt 9.908 +type train | step 3241 | loss 106.6555 211.6877 324.3406 519.9098 762.6051 1095.6698 1532.7261 2186.7283 3068.4197 4689.3994 7698.0425 13592.5664 | lr 2.5e-04 | norm 4198.5132 | dt 9.880 +type train | step 3242 | loss 91.6461 178.6707 283.8270 467.1267 701.8954 1018.5924 1437.3263 2073.3325 2955.5586 4565.3174 7468.2153 13069.6465 | lr 2.5e-04 | norm 3524.9463 | dt 9.875 +type train | step 3243 | loss 103.3738 204.8981 316.9151 513.8412 753.9855 1088.9731 1527.0237 2179.6338 3068.7871 4719.8018 7762.0439 13866.1963 | lr 2.5e-04 | norm 4036.0835 | dt 9.891 +type train | step 3244 | loss 100.8192 196.4629 308.6325 508.3378 741.2218 1080.6116 1506.6604 2157.7319 3008.6602 4624.2778 7623.6318 13490.5918 | lr 2.5e-04 | norm 4125.1060 | dt 9.882 +type train | step 3245 | loss 103.0724 201.7002 314.3833 517.0004 750.5037 1084.2579 1506.7845 2141.1697 2974.7468 4545.5718 7443.9355 13214.0039 | lr 2.5e-04 | norm 4489.0811 | dt 9.861 +type train | step 3246 | loss 96.9338 190.3132 297.3524 484.3046 719.6718 1035.4508 1454.6202 2099.3787 2982.2959 4606.0234 7580.0210 13480.7031 | lr 2.5e-04 | norm 5076.2593 | dt 9.859 +type train | step 3247 | loss 98.9010 191.3156 300.7433 485.2100 717.4835 1043.2947 1470.7305 2124.7114 2978.8020 4607.0449 7624.4365 13519.4375 | lr 2.5e-04 | norm 5422.7568 | dt 9.874 +type train | step 3248 | loss 95.6559 187.3896 295.1982 483.4253 715.3188 1040.4980 1463.6156 2106.7085 2975.8079 4608.8062 7580.9521 13404.8486 | lr 2.5e-04 | norm 3856.0164 | dt 9.885 +type train | step 3249 | loss 93.1170 179.0677 281.9407 462.1978 688.2338 999.2156 1407.0394 2035.0042 2886.3118 4467.4136 7372.3682 13097.1670 | lr 2.5e-04 | norm 5083.6133 | dt 9.862 +type train | step 3250 | loss 91.8144 180.6091 287.2906 474.1842 709.1438 1020.8616 1436.9088 2056.3066 2932.3789 4534.7163 7472.6812 13182.0908 | lr 2.5e-04 | norm 4177.1724 | dt 9.874 +type train | step 3251 | loss 88.1970 177.9538 294.8119 500.6942 752.4824 1094.8414 1558.3368 2238.5852 3216.2722 5026.9839 8429.4258 15018.9629 | lr 2.5e-04 | norm 9092.9141 | dt 9.858 +type train | step 3252 | loss 102.0010 199.8842 313.4519 508.6442 750.2635 1089.7916 1520.5701 2173.4404 3025.4722 4632.4336 7636.5371 13582.9131 | lr 2.4e-04 | norm 4330.7593 | dt 9.879 +type train | step 3253 | loss 114.5634 227.2036 335.9565 532.6222 779.1921 1151.2449 1615.5562 2298.3474 3178.2583 4893.5557 7997.5322 14303.0303 | lr 2.4e-04 | norm 7885.3101 | dt 9.858 +type train | step 3254 | loss 96.5242 188.6049 294.8672 481.6902 714.0204 1040.5626 1458.2941 2094.3801 2968.0779 4622.2324 7671.2441 13593.0430 | lr 2.4e-04 | norm 4371.1074 | dt 9.861 +type train | step 3255 | loss 96.1681 186.0541 292.2267 479.4210 710.9556 1035.0420 1452.1969 2082.5845 2928.5269 4504.2397 7436.2422 13216.7881 | lr 2.4e-04 | norm 4393.6904 | dt 9.875 +type train | step 3256 | loss 107.1742 210.1237 327.3966 531.2435 767.9174 1100.0160 1521.8048 2150.1938 2949.4116 4490.8062 7343.5977 13046.9785 | lr 2.4e-04 | norm 4968.6235 | dt 9.891 +type train | step 3257 | loss 98.6599 192.9318 301.0203 492.5075 722.6062 1049.6648 1470.2853 2113.6946 2969.0569 4590.7119 7620.7563 13622.7637 | lr 2.4e-04 | norm 4633.3809 | dt 9.873 +type train | step 3258 | loss 100.1954 196.7679 307.4779 504.6003 740.2182 1086.6887 1529.8845 2215.9578 3086.3940 4738.7075 7874.0176 14101.0234 | lr 2.4e-04 | norm 5111.8188 | dt 9.867 +type train | step 3259 | loss 107.4168 210.9619 330.1391 543.7266 792.6797 1146.2639 1605.9521 2319.4922 3235.6248 4955.3716 8051.8086 14173.5322 | lr 2.4e-04 | norm 4863.8154 | dt 9.866 +type train | step 3260 | loss 97.7027 191.4959 297.5057 486.2329 714.1526 1045.4829 1461.4741 2105.9644 2958.2131 4566.7749 7546.6899 13407.0908 | lr 2.4e-04 | norm 4427.2900 | dt 9.863 +type train | step 3261 | loss 98.2997 191.4651 298.7245 490.1366 720.3973 1043.2788 1454.3821 2074.5234 2917.0759 4509.7949 7449.3525 13245.3760 | lr 2.4e-04 | norm 3984.9807 | dt 9.859 +type train | step 3262 | loss 97.0389 188.6122 298.4139 486.7979 720.8208 1056.0691 1488.5641 2146.0271 3011.1733 4671.4873 7687.3076 13590.7178 | lr 2.4e-04 | norm 7298.3765 | dt 9.877 +type train | step 3263 | loss 95.6719 189.2849 297.4054 489.8352 722.8588 1079.1514 1532.7206 2236.9106 3134.2556 4847.0020 8020.9023 14233.2988 | lr 2.4e-04 | norm 5500.3291 | dt 9.857 +type train | step 3264 | loss 96.2444 187.5728 297.1168 485.2021 717.9805 1047.1449 1474.8307 2124.9338 2988.5986 4618.2935 7650.5327 13627.1797 | lr 2.4e-04 | norm 4556.0591 | dt 9.874 +type train | step 3265 | loss 98.4158 193.1658 305.0007 499.9414 742.4064 1084.7501 1523.1394 2198.5085 3094.6990 4788.6440 7850.0762 13945.2891 | lr 2.4e-04 | norm 6643.8325 | dt 9.857 +type train | step 3266 | loss 102.8752 199.5809 307.2085 497.4596 727.5615 1054.2374 1466.7600 2095.2468 2926.0659 4500.6934 7417.8184 13163.8145 | lr 2.4e-04 | norm 4271.4395 | dt 9.883 +type train | step 3267 | loss 104.9768 211.2190 324.6633 523.2188 764.1130 1115.9111 1556.0570 2246.7610 3137.8357 4833.0327 7923.6646 13974.8877 | lr 2.4e-04 | norm 5196.3335 | dt 9.895 +type train | step 3268 | loss 91.1321 180.7169 290.4595 483.0744 723.5970 1057.9480 1491.7098 2157.0811 3065.0967 4729.6016 7763.4648 13657.0410 | lr 2.4e-04 | norm 4413.8120 | dt 9.879 +type train | step 3269 | loss 98.8286 192.1289 297.6524 486.9497 708.4898 1025.8247 1436.9485 2045.8723 2876.4792 4454.3867 7423.0547 13615.3721 | lr 2.4e-04 | norm 8130.4126 | dt 9.861 +type train | step 3270 | loss 96.4515 187.4078 292.5824 476.2806 705.1010 1020.7998 1439.9351 2073.2559 2938.3201 4570.0425 7531.7422 13341.3174 | lr 2.4e-04 | norm 4858.8940 | dt 9.865 +type train | step 3271 | loss 93.5184 183.9882 290.6897 475.6637 705.2777 1024.8660 1446.4840 2080.2998 2943.1907 4542.2871 7496.5068 13228.0352 | lr 2.4e-04 | norm 4203.3188 | dt 9.868 +type train | step 3272 | loss 91.3100 179.2377 284.5314 469.9463 699.6840 1022.6606 1443.0795 2084.7495 2953.6426 4574.4375 7551.5859 13420.1436 | lr 2.4e-04 | norm 4947.4282 | dt 9.869 +type train | step 3273 | loss 95.3842 187.5580 295.7056 486.9376 721.4675 1053.5977 1491.2897 2149.5469 3031.4587 4698.0864 7782.8179 13943.6660 | lr 2.4e-04 | norm 5570.8872 | dt 9.857 +type train | step 3274 | loss 98.5885 194.1669 302.9625 490.5587 727.4683 1055.7000 1489.8333 2137.3147 2994.0566 4613.0249 7531.9785 13269.7324 | lr 2.4e-04 | norm 4458.7144 | dt 9.869 +type train | step 3275 | loss 91.0859 177.6958 279.8690 462.9922 690.4689 1003.0728 1413.7010 2036.4642 2888.7861 4480.3022 7365.6958 12972.1455 | lr 2.4e-04 | norm 4008.7048 | dt 9.882 +type train | step 3276 | loss 96.1237 191.0825 302.4589 497.9686 741.4465 1075.4913 1515.1836 2188.3809 3078.4780 4773.5547 7884.3208 13933.1738 | lr 2.4e-04 | norm 4543.3745 | dt 9.867 +type train | step 3277 | loss 104.2469 204.3899 317.7651 509.6996 744.7461 1084.1096 1515.7371 2166.3855 3012.2786 4606.5391 7548.5947 13325.1152 | lr 2.4e-04 | norm 6414.9175 | dt 9.876 +type train | step 3278 | loss 106.0341 204.3736 319.0480 512.6874 744.1492 1091.4323 1526.1604 2178.9102 2979.0405 4563.2412 7471.6094 13265.3643 | lr 2.4e-04 | norm 7630.2817 | dt 9.862 +type train | step 3279 | loss 90.5011 177.8066 280.6446 460.0199 688.5181 998.8511 1409.3054 2034.9220 2918.3130 4519.5752 7424.4897 13268.0088 | lr 2.4e-04 | norm 5811.9653 | dt 9.868 +type train | step 3280 | loss 96.5124 189.3367 296.5592 485.0020 721.9506 1052.3759 1488.9569 2143.1616 3026.8000 4677.7192 7689.8677 13621.4922 | lr 2.4e-04 | norm 4868.5215 | dt 9.874 +type train | step 3281 | loss 99.4533 195.5070 301.6824 491.1299 722.5461 1042.8459 1464.5833 2093.5913 2960.2893 4565.0371 7475.8652 13220.9707 | lr 2.4e-04 | norm 4482.9707 | dt 9.871 +type train | step 3282 | loss 92.4331 180.7362 286.5485 470.4146 699.3309 1009.0731 1420.0853 2042.7979 2902.9016 4496.2236 7399.8643 13125.3184 | lr 2.4e-04 | norm 4369.0098 | dt 9.886 +type train | step 3283 | loss 104.6126 203.0760 317.4114 515.6021 757.3478 1091.6698 1518.9849 2161.5967 3009.5688 4592.8833 7532.9858 13344.3691 | lr 2.4e-04 | norm 5274.2114 | dt 9.883 +type train | step 3284 | loss 112.9108 218.2287 336.6240 547.6240 790.8035 1157.7554 1619.1879 2346.6870 3216.2954 4971.7261 8219.6182 14718.5283 | lr 2.4e-04 | norm 9306.3770 | dt 9.855 +type train | step 3285 | loss 120.6859 238.6771 361.5682 580.7786 839.2938 1264.8019 1834.5157 2779.7671 3789.3379 5801.1865 9251.0107 15613.6895 | lr 2.4e-04 | norm 5696.1523 | dt 9.843 +type train | step 3286 | loss 93.7872 184.1548 288.1868 468.9081 695.8308 1006.0997 1412.7689 2034.9971 2885.7585 4485.5684 7438.3481 13350.1621 | lr 2.4e-04 | norm 6483.3540 | dt 9.874 +type train | step 3287 | loss 93.5811 183.8589 290.4024 475.6534 710.1301 1030.9916 1457.2174 2103.3267 2993.4612 4646.2168 7636.8564 13445.5020 | lr 2.4e-04 | norm 4012.0632 | dt 9.868 +type train | step 3288 | loss 92.2873 180.0926 282.9105 468.2635 698.3485 1029.1274 1455.1013 2113.7537 2986.2546 4652.6841 7690.7661 13598.6172 | lr 2.4e-04 | norm 4939.6460 | dt 9.876 +type train | step 3289 | loss 92.5469 181.2597 285.5898 469.1258 697.2034 1010.8794 1427.9641 2050.7300 2909.4744 4504.0986 7437.6289 13172.3906 | lr 2.4e-04 | norm 4169.4390 | dt 9.864 +type train | step 3290 | loss 97.2008 190.4106 299.1148 491.3865 724.4064 1049.6807 1479.2024 2116.7451 2985.4419 4607.1592 7621.3008 13549.6729 | lr 2.4e-04 | norm 4357.8711 | dt 9.882 +type train | step 3291 | loss 167.7797 338.9153 484.1738 706.2883 1006.8005 1506.4955 2052.7651 2866.8000 3805.8066 5568.5757 8689.3125 14680.8330 | lr 2.4e-04 | norm 7547.6494 | dt 9.835 +type train | step 3292 | loss 96.2050 187.5777 292.8559 474.2373 705.3256 1021.9053 1445.5570 2081.1948 2950.7471 4556.6855 7504.1255 13369.0459 | lr 2.4e-04 | norm 5583.9341 | dt 9.865 +type train | step 3293 | loss 97.1764 188.8452 296.3741 483.6300 715.7853 1036.2859 1454.3501 2082.8916 2938.7288 4524.4209 7471.9526 13338.3018 | lr 2.4e-04 | norm 6380.9429 | dt 9.865 +type train | step 3294 | loss 95.2094 187.8756 296.0779 487.0044 723.7742 1052.9923 1480.9138 2134.1113 3028.0913 4699.6353 7751.3325 13721.2773 | lr 2.4e-04 | norm 4268.0215 | dt 9.868 +type train | step 3295 | loss 105.2146 204.8620 318.5765 517.1824 749.2369 1073.3610 1484.9954 2107.2822 2907.8232 4463.2407 7353.2812 13234.5391 | lr 2.4e-04 | norm 6188.4658 | dt 9.854 +type train | step 3296 | loss 89.3809 183.4642 298.3601 502.1067 750.1154 1086.4783 1512.7499 2174.0425 3051.9031 4735.0952 7798.1816 13900.8906 | lr 2.4e-04 | norm 9483.3320 | dt 9.845 +type train | step 3297 | loss 90.7133 180.4173 290.8208 486.7292 729.1489 1063.2031 1500.4043 2167.3174 3073.4558 4748.7578 7858.9238 13804.4941 | lr 2.4e-04 | norm 5503.7339 | dt 9.856 +type train | step 3298 | loss 106.6103 211.4957 321.9246 516.4413 757.0767 1089.6010 1527.8348 2182.9663 3061.5671 4717.1118 7815.0537 13926.5498 | lr 2.4e-04 | norm 5347.5547 | dt 9.874 +type train | step 3299 | loss 101.2287 196.0652 306.8720 500.9939 742.5366 1083.7344 1526.5704 2183.8179 3061.0139 4718.0151 7839.7383 14027.1523 | lr 2.4e-04 | norm 5654.7227 | dt 9.865 +type train | step 3300 | loss 132.7474 256.9777 381.6610 584.3501 839.8098 1244.4243 1733.7745 2428.7070 3326.1719 4947.5776 7902.6084 13858.4062 | lr 2.4e-04 | norm 6704.5737 | dt 9.845 +type train | step 3301 | loss 99.7061 194.5516 308.0244 504.9128 749.4958 1082.9073 1523.0024 2190.7305 3077.2788 4711.4248 7706.3760 13631.5947 | lr 2.4e-04 | norm 5584.4209 | dt 9.862 +type train | step 3302 | loss 95.5006 187.6645 294.5685 480.6962 711.0584 1023.0834 1438.4559 2063.7163 2923.3711 4534.7305 7484.9707 13329.4883 | lr 2.4e-04 | norm 4109.9844 | dt 9.863 +type train | step 3303 | loss 99.9002 197.3331 306.9670 500.8648 741.7678 1070.8635 1503.7439 2159.0178 3064.5898 4727.2754 7755.2393 13662.9941 | lr 2.4e-04 | norm 4094.5105 | dt 9.881 +type train | step 3304 | loss 103.7032 204.8736 315.7967 509.2254 747.0854 1079.8539 1510.6676 2167.3865 3046.5986 4675.2129 7671.0957 13466.1240 | lr 2.4e-04 | norm 3810.9617 | dt 9.875 +type train | step 3305 | loss 98.1212 192.4388 301.4522 489.6616 724.2529 1045.6904 1463.7916 2097.8450 2968.7053 4581.7715 7529.3174 13343.2285 | lr 2.4e-04 | norm 3598.1179 | dt 9.889 +type train | step 3306 | loss 96.2847 191.2930 305.8911 505.0635 747.5982 1092.7278 1532.9241 2211.1760 3111.0615 4775.3677 7854.1226 13915.3389 | lr 2.4e-04 | norm 5853.5894 | dt 9.867 +type train | step 3307 | loss 95.6712 186.7368 293.3832 478.7520 707.7575 1031.2664 1455.1964 2095.6472 2964.9810 4618.1865 7648.9580 13678.6201 | lr 2.4e-04 | norm 4183.1812 | dt 9.865 +type train | step 3308 | loss 92.8477 181.7608 286.1623 471.5156 704.2773 1029.5261 1463.9335 2121.5408 3010.2163 4662.4331 7641.2393 13457.8184 | lr 2.4e-04 | norm 3933.4224 | dt 9.863 +type train | step 3309 | loss 104.3547 203.5479 315.4593 515.0457 752.9370 1084.4604 1506.5679 2154.7222 3003.0610 4647.7642 7594.2041 13427.0879 | lr 2.4e-04 | norm 5119.8516 | dt 9.866 +type train | step 3310 | loss 95.5713 187.5942 292.2852 478.1230 709.7469 1023.9775 1440.3477 2063.4446 2913.3296 4486.5435 7476.4165 13309.8721 | lr 2.4e-04 | norm 5601.2979 | dt 9.866 +type train | step 3311 | loss 114.7861 226.4591 344.0862 543.8546 800.1640 1164.0048 1607.7574 2297.4319 3160.6292 4753.4351 7729.3613 13591.0391 | lr 2.4e-04 | norm 8239.9209 | dt 9.843 +type train | step 3312 | loss 97.7488 191.7594 298.3352 486.7944 723.8996 1072.7070 1514.7947 2206.4229 3080.6953 4729.9180 7730.8618 13560.9258 | lr 2.4e-04 | norm 4947.3701 | dt 9.871 +type train | step 3313 | loss 98.7520 193.4986 304.2828 493.9547 724.3025 1043.6508 1462.7783 2087.2612 2949.9561 4546.3979 7462.7271 13247.7461 | lr 2.4e-04 | norm 4322.7661 | dt 9.883 +type train | step 3314 | loss 98.8945 197.0376 312.3300 513.2533 759.9163 1107.4845 1557.2004 2245.4312 3167.7568 4889.7842 8083.2285 14406.1855 | lr 2.4e-04 | norm 7146.4985 | dt 9.887 +type train | step 3315 | loss 100.9194 196.8300 309.8069 502.2148 741.2402 1063.7018 1487.4076 2128.6089 3016.7344 4652.6934 7640.5571 13529.1191 | lr 2.4e-04 | norm 7245.3389 | dt 9.871 +type train | step 3316 | loss 96.5074 188.9873 296.2254 480.2040 708.8435 1026.5447 1440.8568 2069.3228 2923.3589 4520.7407 7486.9429 13333.4014 | lr 2.4e-04 | norm 5270.7500 | dt 9.869 +type train | step 3317 | loss 95.3439 183.6310 286.3195 471.1686 701.7968 1023.5786 1449.3733 2100.1855 2968.0979 4601.3403 7568.4551 13399.5791 | lr 2.4e-04 | norm 4399.3857 | dt 9.861 +type train | step 3318 | loss 96.1960 187.5286 294.5904 481.5765 710.6494 1029.9580 1446.1908 2078.3926 2937.4443 4551.0635 7507.0469 13285.4336 | lr 2.4e-04 | norm 4463.4624 | dt 9.877 +type train | step 3319 | loss 107.4164 210.0094 325.8035 521.0217 762.1751 1104.2278 1547.9745 2212.5403 3059.7778 4707.5996 7756.6738 13812.9141 | lr 2.4e-04 | norm 5850.1089 | dt 9.871 +type train | step 3320 | loss 103.0198 203.2650 314.4894 510.6538 749.9070 1071.5844 1492.6829 2126.9836 2987.9353 4568.4395 7501.4019 13259.5420 | lr 2.4e-04 | norm 4602.5513 | dt 9.881 +type train | step 3321 | loss 91.0103 179.5807 287.4500 477.1406 712.8457 1031.6564 1461.5771 2119.3398 3019.3027 4690.3066 7743.0156 13742.5215 | lr 2.4e-04 | norm 4953.6895 | dt 9.882 +type train | step 3322 | loss 97.4182 190.7719 300.6326 492.7569 729.4740 1068.6803 1509.1659 2188.2251 3089.4263 4762.8896 7868.0918 14018.9463 | lr 2.4e-04 | norm 4514.8281 | dt 9.869 +type train | step 3323 | loss 101.3865 197.8063 307.5263 497.1321 731.1819 1047.9507 1458.8059 2080.2629 2916.8369 4494.5859 7470.0708 13322.9844 | lr 2.3e-04 | norm 5510.0259 | dt 9.889 +type train | step 3324 | loss 101.8378 201.6344 311.9424 502.3251 731.6413 1058.1244 1474.6729 2101.1499 2921.3816 4468.4790 7322.2988 13011.1777 | lr 2.3e-04 | norm 4760.9067 | dt 9.880 +type train | step 3325 | loss 97.4364 192.2566 302.0880 493.2985 731.6641 1057.4822 1487.4364 2139.5183 3036.0374 4719.5244 7814.5469 13913.1250 | lr 2.3e-04 | norm 4769.7119 | dt 9.882 +type train | step 3326 | loss 101.6346 198.8167 311.1210 512.0815 749.3502 1089.0901 1517.2170 2154.9236 2975.6033 4578.9629 7505.3198 13359.5342 | lr 2.3e-04 | norm 4421.2065 | dt 9.867 +type train | step 3327 | loss 108.5406 213.3433 328.4687 534.5413 770.5964 1114.7975 1545.7507 2186.5354 2996.3862 4580.9556 7551.7686 13503.8818 | lr 2.3e-04 | norm 4887.7017 | dt 9.855 +type train | step 3328 | loss 93.2057 183.9683 290.3693 481.2595 718.5314 1048.1638 1475.7281 2128.0293 3002.5859 4657.9990 7644.1899 13512.2002 | lr 2.3e-04 | norm 4499.8657 | dt 9.862 +type train | step 3329 | loss 100.1195 197.1538 304.9840 496.0504 733.4352 1061.7325 1485.0479 2125.5889 2991.7744 4583.6553 7555.3311 13498.2607 | lr 2.3e-04 | norm 4469.8228 | dt 9.877 +type train | step 3330 | loss 103.2222 201.0291 312.6046 508.9661 740.7072 1073.2736 1499.0122 2144.5273 2985.1218 4573.3906 7534.7480 13409.2041 | lr 2.3e-04 | norm 4691.5200 | dt 9.876 +type train | step 3331 | loss 101.9897 201.2728 312.4718 506.5369 741.6778 1074.7233 1504.1394 2153.7705 3006.4854 4619.3052 7606.1255 13478.3682 | lr 2.3e-04 | norm 4404.6035 | dt 9.882 +type train | step 3332 | loss 96.6017 188.6898 294.4626 480.7712 710.6135 1027.4070 1444.5159 2074.3489 2929.0737 4509.1201 7434.9321 13048.6699 | lr 2.3e-04 | norm 4035.4075 | dt 9.868 +type train | step 3333 | loss 93.8001 184.8497 291.5793 478.9017 708.5068 1024.4811 1436.9971 2049.8442 2880.5862 4444.4321 7338.4580 13078.3301 | lr 2.3e-04 | norm 4145.7681 | dt 9.867 +type train | step 3334 | loss 92.8910 184.2612 291.6044 481.9478 714.5223 1053.1781 1491.3623 2160.9978 3044.8486 4701.8027 7769.8730 13864.4766 | lr 2.3e-04 | norm 6266.0723 | dt 9.865 +type train | step 3335 | loss 97.5193 190.3572 296.2252 483.5925 712.2238 1031.5627 1445.6829 2071.9487 2918.7205 4490.3394 7403.8535 13095.5352 | lr 2.3e-04 | norm 3662.2109 | dt 9.871 +type train | step 3336 | loss 96.2984 187.4507 294.2892 478.7343 710.4619 1039.5717 1467.5352 2110.5647 2960.0796 4549.9985 7472.5518 13200.8916 | lr 2.3e-04 | norm 4234.1719 | dt 9.857 +type train | step 3337 | loss 96.7563 192.6079 300.3586 492.6267 726.3878 1077.7437 1529.2566 2230.1938 3098.6206 4825.0308 8078.7549 14615.0020 | lr 2.3e-04 | norm 8657.1299 | dt 9.850 +type train | step 3338 | loss 99.4408 194.7695 304.1032 491.6871 723.3317 1037.6350 1451.6478 2076.5903 2917.4229 4502.9180 7463.3521 13270.5840 | lr 2.3e-04 | norm 3926.1985 | dt 9.877 +type train | step 3339 | loss 94.7452 186.3947 295.4869 484.5142 715.2407 1040.9663 1468.8859 2106.9727 2968.4058 4597.9097 7573.3550 13441.1846 | lr 2.3e-04 | norm 3879.4448 | dt 9.877 +type train | step 3340 | loss 98.3671 191.9510 301.0347 489.0749 725.2404 1043.3004 1468.5181 2099.9734 2959.8621 4529.0342 7404.8926 13014.8369 | lr 2.3e-04 | norm 4250.7231 | dt 9.867 +type train | step 3341 | loss 103.4664 204.0883 317.5152 511.8741 747.0857 1081.5381 1514.3136 2186.1846 3056.1389 4706.9287 7785.4697 13764.0068 | lr 2.3e-04 | norm 5520.0068 | dt 9.876 +type train | step 3342 | loss 90.4634 177.5033 283.7101 467.7050 697.4742 1016.7234 1433.0071 2073.7842 2944.9434 4560.2793 7530.7510 13310.1055 | lr 2.3e-04 | norm 3709.1113 | dt 9.880 +type train | step 3343 | loss 90.0908 175.8148 277.9254 457.9996 683.9439 995.6415 1401.5007 2014.6348 2850.0649 4397.6543 7245.0732 12668.6475 | lr 2.3e-04 | norm 3631.5608 | dt 9.891 +type train | step 3344 | loss 93.1470 182.0895 287.3392 472.4588 703.1363 1022.0825 1444.4412 2081.4099 2955.3733 4555.3164 7495.3730 13243.4746 | lr 2.3e-04 | norm 4139.8960 | dt 9.869 +type train | step 3345 | loss 94.7773 185.5005 291.8307 476.1537 704.1786 1014.9407 1422.8722 2043.4417 2889.3569 4468.8364 7325.7920 12878.5771 | lr 2.3e-04 | norm 3712.9397 | dt 9.895 +type train | step 3346 | loss 92.8401 181.7009 284.2698 466.9189 693.7313 1002.5881 1411.2035 2030.9126 2875.6514 4451.5835 7346.6475 12959.0850 | lr 2.3e-04 | norm 3801.7563 | dt 9.864 +type train | step 3347 | loss 101.9194 200.2957 313.9225 509.3081 749.4119 1084.1953 1513.9086 2167.5496 3041.5950 4704.1313 7714.2466 13627.5039 | lr 2.3e-04 | norm 4279.5562 | dt 9.870 +type train | step 3348 | loss 90.0250 176.7050 281.5500 470.3550 703.9333 1038.8309 1478.7931 2152.3638 3040.3711 4730.2461 7856.7441 13959.2021 | lr 2.3e-04 | norm 4629.2178 | dt 9.875 +type train | step 3349 | loss 94.0823 182.3275 285.8849 468.0271 693.8296 1000.4338 1400.0356 2010.7886 2852.4849 4390.0425 7216.5957 12711.0186 | lr 2.3e-04 | norm 4117.1191 | dt 9.874 +type train | step 3350 | loss 95.6541 184.9858 287.8994 472.0626 695.6558 1015.6592 1432.1882 2059.4487 2885.6458 4431.6558 7312.5010 12887.6426 | lr 2.3e-04 | norm 4229.6694 | dt 9.875 +type train | step 3351 | loss 110.4590 216.8130 328.9805 523.3282 764.9311 1102.3608 1535.4474 2195.8755 3044.0708 4632.1260 7518.2017 13198.6836 | lr 2.3e-04 | norm 4761.1094 | dt 9.862 +type train | step 3352 | loss 94.8826 186.1577 293.5012 483.1303 713.6878 1033.4177 1452.0314 2088.7368 2941.1152 4556.9033 7552.2437 13423.5264 | lr 2.3e-04 | norm 4236.9502 | dt 9.867 +type train | step 3353 | loss 95.0587 185.1674 293.7128 482.5175 715.3407 1038.3103 1461.6637 2103.2451 2978.8760 4617.8638 7613.6548 13482.0449 | lr 2.3e-04 | norm 3813.2529 | dt 9.878 +type train | step 3354 | loss 93.0338 182.5458 286.9692 467.8852 696.4727 1008.2884 1417.1378 2037.1307 2885.0601 4473.6846 7385.7539 13072.3936 | lr 2.3e-04 | norm 3787.3840 | dt 9.872 +type train | step 3355 | loss 98.4493 193.6070 302.0543 490.4920 721.8924 1044.3339 1468.7041 2104.4653 2956.8384 4520.3276 7386.8643 13009.9102 | lr 2.3e-04 | norm 3774.3804 | dt 9.884 +type train | step 3356 | loss 92.8635 180.6117 283.0331 464.7748 692.7422 1002.7407 1415.6116 2043.7012 2880.5479 4472.6309 7393.8828 13156.2529 | lr 2.3e-04 | norm 4397.8438 | dt 9.881 +type train | step 3357 | loss 91.2881 176.0709 278.3248 460.1647 687.5356 1000.5073 1410.3553 2036.9546 2878.2720 4471.7710 7377.0288 13038.8438 | lr 2.3e-04 | norm 3707.5745 | dt 10.194 +type train | step 3358 | loss 89.0772 174.7251 275.9684 456.0792 685.8126 1007.8795 1438.9407 2090.0449 2967.2185 4688.4429 7737.4683 13791.7520 | lr 2.3e-04 | norm 9254.0059 | dt 9.853 +type train | step 3359 | loss 90.6742 178.2912 280.5930 461.5602 695.3984 1018.2938 1460.5692 2122.1963 3019.7056 4716.2690 7748.4131 13585.4824 | lr 2.3e-04 | norm 7865.2432 | dt 9.871 +type train | step 3360 | loss 101.3064 204.0531 323.1422 526.4734 776.4481 1119.9496 1587.1813 2284.6777 3206.1113 4971.1094 8283.6562 14785.8252 | lr 2.3e-04 | norm 8871.5117 | dt 9.861 +type train | step 3361 | loss 97.8804 194.0208 303.0864 491.6235 727.2735 1055.5386 1481.1168 2127.3181 2992.0669 4613.4443 7580.6025 13409.1943 | lr 2.3e-04 | norm 4783.0835 | dt 9.887 +type train | step 3362 | loss 93.4154 183.5268 288.7372 469.3215 698.7844 1007.8939 1425.0292 2051.8862 2904.1021 4517.1743 7436.9043 13163.9277 | lr 2.3e-04 | norm 5783.3125 | dt 9.863 +type train | step 3363 | loss 102.4197 204.4846 314.0085 506.8042 740.9573 1064.6302 1486.8864 2126.5984 2959.5059 4537.8262 7471.7490 13247.6572 | lr 2.3e-04 | norm 4778.1304 | dt 9.867 +type train | step 3364 | loss 95.7754 187.0105 289.8138 472.5928 701.2826 1023.4699 1445.7865 2090.0847 2948.7554 4558.6167 7466.7676 13151.1113 | lr 2.3e-04 | norm 4238.2290 | dt 9.877 +type train | step 3365 | loss 90.6780 176.8756 282.1167 466.2597 697.0033 1015.0024 1438.1624 2077.3411 2941.5425 4555.9087 7480.6680 13278.0830 | lr 2.3e-04 | norm 4747.3091 | dt 9.876 +type train | step 3366 | loss 89.3023 173.7509 275.8923 455.5626 680.5977 991.1484 1406.2358 2036.6354 2900.3140 4514.4097 7430.4404 13131.2617 | lr 2.3e-04 | norm 4327.0820 | dt 9.871 +type train | step 3367 | loss 88.2508 174.1071 281.4240 463.3413 695.4703 1011.0012 1431.0804 2073.3237 2940.3901 4566.6670 7556.4858 13479.3232 | lr 2.3e-04 | norm 4459.7554 | dt 9.859 +type train | step 3368 | loss 91.6298 178.9194 284.4140 468.1150 698.6237 1018.4602 1437.3418 2068.3672 2932.6980 4554.7490 7514.3721 13359.6924 | lr 2.3e-04 | norm 3916.5044 | dt 9.876 +type train | step 3369 | loss 93.2593 180.1366 286.4884 469.3552 700.1848 1014.0920 1431.8801 2070.1196 2936.7280 4567.1826 7562.4385 13342.6367 | lr 2.3e-04 | norm 4008.8069 | dt 9.876 +type train | step 3370 | loss 94.8501 185.5158 289.1133 471.4073 696.6320 1011.6852 1424.5099 2050.1426 2904.9492 4491.9028 7407.4209 13140.7061 | lr 2.3e-04 | norm 4580.0381 | dt 9.870 +type train | step 3371 | loss 101.7010 194.6916 306.8875 498.6759 736.4510 1061.5914 1490.4594 2140.7173 3042.8484 4714.5923 7787.5811 13870.3721 | lr 2.3e-04 | norm 6304.1880 | dt 9.850 +type train | step 3372 | loss 97.4026 190.8201 297.6285 484.7176 718.0350 1036.8285 1455.2349 2075.7871 2927.6501 4512.2710 7410.6777 13116.5225 | lr 2.3e-04 | norm 3872.1409 | dt 9.889 +type train | step 3373 | loss 97.1857 191.5873 303.4417 497.8958 735.5541 1067.1047 1494.7238 2143.6814 2985.9426 4617.9058 7584.6191 13474.0508 | lr 2.3e-04 | norm 7251.4595 | dt 9.862 +type train | step 3374 | loss 99.2717 199.9201 313.2622 514.0871 755.8765 1094.9005 1537.5889 2185.0994 3051.2402 4668.7163 7620.4487 13359.4941 | lr 2.3e-04 | norm 4218.3252 | dt 9.875 +type train | step 3375 | loss 92.5716 181.0159 284.7866 467.3466 693.2501 1005.6435 1417.5798 2042.6997 2890.8389 4461.7402 7339.5264 12951.8799 | lr 2.3e-04 | norm 4135.7441 | dt 9.882 +type train | step 3376 | loss 112.4152 223.9259 344.6612 543.7531 785.3506 1119.3463 1566.1619 2212.6838 3112.5085 4800.6670 7861.3970 14098.1797 | lr 2.3e-04 | norm 7283.7363 | dt 9.875 +type train | step 3377 | loss 101.6093 200.7948 315.1343 520.7961 761.0338 1120.4148 1573.3378 2272.9470 3130.3584 4803.9199 7888.3281 14001.9824 | lr 2.3e-04 | norm 5307.4292 | dt 9.860 +type train | step 3378 | loss 93.3034 181.9379 288.1069 475.9163 707.1277 1039.0668 1468.3971 2134.9084 2991.9634 4635.2661 7641.9868 13595.2686 | lr 2.3e-04 | norm 4737.2388 | dt 9.874 +type train | step 3379 | loss 91.6427 179.0356 286.2904 473.2904 711.8552 1036.5404 1468.2421 2119.8958 3015.4399 4669.5962 7702.2114 13658.7070 | lr 2.3e-04 | norm 5046.1265 | dt 9.867 +type train | step 3380 | loss 98.0620 191.0690 301.9024 489.7658 726.6729 1055.2623 1483.1917 2137.9639 3017.0444 4668.6802 7658.7979 13510.1738 | lr 2.3e-04 | norm 3945.3665 | dt 9.884 +type train | step 3381 | loss 92.9470 181.8246 287.7405 472.4848 702.5928 1029.2729 1457.4122 2114.5342 2977.2266 4604.3789 7613.5356 13507.6514 | lr 2.3e-04 | norm 4000.6189 | dt 9.873 +type train | step 3382 | loss 89.5831 174.8814 275.8745 457.6753 686.0286 1007.2892 1432.8346 2089.8538 2961.6570 4612.8438 7644.1377 13607.6748 | lr 2.3e-04 | norm 4330.9194 | dt 9.865 +type train | step 3383 | loss 107.0849 216.1558 358.8788 591.8632 864.1223 1293.5764 1854.6580 2701.0698 3696.0706 5744.6196 9462.3750 17131.1934 | lr 2.3e-04 | norm 11395.0039 | dt 9.838 +type train | step 3384 | loss 94.8082 185.2480 296.2257 484.7971 717.3008 1032.6001 1442.0051 2054.7742 2906.5779 4483.8345 7356.6191 13128.6992 | lr 2.3e-04 | norm 4868.5142 | dt 9.863 +type train | step 3385 | loss 90.8113 177.9630 284.5230 469.0532 701.4080 1019.9889 1448.0800 2094.7883 2973.7927 4595.5479 7539.2861 13268.6592 | lr 2.3e-04 | norm 3763.6978 | dt 9.868 +type train | step 3386 | loss 97.2941 191.4603 298.4603 483.0860 713.2706 1032.9945 1455.6562 2091.8113 2964.2393 4601.4521 7564.3843 13512.5371 | lr 2.3e-04 | norm 4994.0767 | dt 9.874 +type train | step 3387 | loss 99.2278 193.4270 301.5671 492.4492 723.6547 1041.4598 1461.8538 2098.2266 2946.2224 4536.1079 7499.9800 13326.6172 | lr 2.3e-04 | norm 4687.6050 | dt 9.875 +type train | step 3388 | loss 94.6869 181.7541 285.2183 468.7939 696.9084 1013.0547 1433.7778 2068.2961 2933.5107 4533.1982 7473.6826 13205.8936 | lr 2.3e-04 | norm 4284.8364 | dt 9.868 +type train | step 3389 | loss 121.5511 238.7761 361.6370 572.0583 823.5295 1170.0144 1621.7427 2316.7642 3227.4541 4936.5737 8133.8701 14728.2559 | lr 2.3e-04 | norm 7905.2290 | dt 9.866 +type train | step 3390 | loss 97.1692 190.4856 295.2110 479.3015 704.3353 1022.4173 1440.3705 2070.5156 2917.7913 4526.2388 7482.1201 13279.6260 | lr 2.3e-04 | norm 4278.2920 | dt 9.871 +type train | step 3391 | loss 97.7316 192.6316 301.3478 488.5665 723.0618 1050.8604 1483.1128 2141.8303 3007.2534 4656.4160 7704.4160 13559.9580 | lr 2.3e-04 | norm 4018.6375 | dt 9.865 +type train | step 3392 | loss 96.9819 188.1502 290.6046 474.8314 700.6448 1026.6515 1446.3545 2094.8098 2939.5723 4556.7832 7514.6665 13319.4863 | lr 2.3e-04 | norm 4248.6523 | dt 9.852 +type train | step 3393 | loss 87.6053 171.5128 271.6058 447.3152 669.9399 968.2932 1371.4808 1988.2688 2837.7180 4425.2915 7331.2183 12982.4951 | lr 2.3e-04 | norm 3739.2581 | dt 9.869 +type train | step 3394 | loss 96.7725 188.4096 294.8365 482.1295 710.7327 1030.2126 1448.6310 2075.2737 2914.2954 4471.7998 7311.9844 12831.1680 | lr 2.3e-04 | norm 3662.6721 | dt 9.874 +type train | step 3395 | loss 97.0757 188.8999 294.0245 483.0967 711.4561 1047.1174 1472.4187 2122.7866 2952.9319 4541.0938 7537.0322 13536.9717 | lr 2.3e-04 | norm 5880.2612 | dt 9.846 +type train | step 3396 | loss 112.2658 221.8587 337.8352 538.7308 778.7676 1129.9086 1571.6384 2243.5122 3095.3181 4699.0732 7622.3662 13399.8887 | lr 2.2e-04 | norm 3876.5833 | dt 9.863 +type train | step 3397 | loss 93.0281 180.0731 284.5308 466.0208 690.7815 1006.4589 1421.8030 2052.3320 2878.0862 4431.9302 7286.6465 12838.8311 | lr 2.2e-04 | norm 4414.4478 | dt 9.867 +type train | step 3398 | loss 101.1114 200.0260 311.6157 504.4805 741.3870 1080.2378 1511.6648 2172.7373 3064.9155 4684.2905 7698.5366 13568.3066 | lr 2.2e-04 | norm 3993.6904 | dt 9.889 +type train | step 3399 | loss 95.2937 187.9843 294.5201 480.8903 712.1993 1026.3269 1444.0248 2073.7732 2938.2847 4530.7100 7425.2480 13128.3330 | lr 2.2e-04 | norm 4555.8071 | dt 9.881 +type train | step 3400 | loss 92.8755 179.4811 281.4542 461.4985 688.1752 997.3370 1409.3112 2034.1940 2890.0195 4475.7969 7332.5029 12927.5479 | lr 2.2e-04 | norm 6233.6328 | dt 9.864 +type train | step 3401 | loss 93.8989 182.3503 287.2636 475.6837 708.0774 1046.6838 1478.0820 2154.8848 3040.3513 4745.4595 7877.9238 14056.8525 | lr 2.2e-04 | norm 4848.3218 | dt 9.857 +type train | step 3402 | loss 100.3302 195.4578 307.5753 501.0880 737.2876 1079.0118 1504.3577 2150.3992 2997.1521 4626.4277 7599.2046 13574.5488 | lr 2.2e-04 | norm 5121.3979 | dt 9.855 +type train | step 3403 | loss 91.4314 179.4123 282.3640 464.0781 690.9520 1010.8915 1431.8186 2072.3228 2937.1855 4559.4751 7498.4912 13195.1787 | lr 2.2e-04 | norm 4293.7397 | dt 9.877 +type train | step 3404 | loss 94.1322 185.1030 291.2997 481.8429 712.8513 1033.5260 1452.2827 2080.6387 2949.3008 4568.3330 7526.9507 13314.6631 | lr 2.2e-04 | norm 4583.2744 | dt 9.877 +type train | step 3405 | loss 102.1330 199.3112 312.9890 513.9799 749.5135 1081.6327 1500.3097 2138.7029 2968.0630 4528.7744 7378.0996 13030.0664 | lr 2.2e-04 | norm 4922.0874 | dt 9.870 +type train | step 3406 | loss 98.5918 193.6096 304.2759 495.9639 728.8394 1058.7792 1481.6403 2127.9209 2972.9280 4576.0347 7543.7114 13360.9268 | lr 2.2e-04 | norm 3742.4436 | dt 9.875 +type train | step 3407 | loss 105.2894 208.5386 330.1244 534.5171 788.7452 1132.8754 1586.3916 2254.0344 3164.3403 4868.6699 8041.1514 14059.4346 | lr 2.2e-04 | norm 8136.9756 | dt 9.863 +type train | step 3408 | loss 107.9041 214.1998 345.7366 566.2883 833.4817 1205.1791 1687.7365 2394.2244 3341.6470 5119.1050 8529.8604 14814.7803 | lr 2.2e-04 | norm 11646.9844 | dt 9.866 +type train | step 3409 | loss 101.3324 199.1222 311.7377 501.7038 743.6755 1095.6023 1550.6770 2252.8359 3109.1951 4738.2822 7743.4580 13654.7803 | lr 2.2e-04 | norm 4741.1929 | dt 9.873 +type train | step 3410 | loss 99.0529 192.4786 299.3513 485.7913 719.1007 1044.7025 1471.0505 2115.1965 2981.2065 4603.1548 7515.4526 13234.1504 | lr 2.2e-04 | norm 4203.5537 | dt 9.893 +type train | step 3411 | loss 97.0677 189.1719 296.2612 480.9358 712.7670 1030.0563 1444.0841 2074.6926 2925.7397 4526.7783 7471.8643 13207.4619 | lr 2.2e-04 | norm 4745.2954 | dt 9.876 +type train | step 3412 | loss 106.3895 208.6485 321.6209 515.7857 753.0253 1102.4491 1541.4971 2209.9719 3059.3870 4685.3657 7683.4893 13609.1475 | lr 2.2e-04 | norm 4643.4092 | dt 9.873 +type train | step 3413 | loss 97.5380 190.4916 297.4550 483.0303 709.4218 1024.0376 1439.8870 2063.2197 2912.0576 4512.2617 7492.5322 13389.4727 | lr 2.2e-04 | norm 4339.4331 | dt 9.887 +type train | step 3414 | loss 94.6619 188.0274 294.9426 481.1589 713.4426 1040.2859 1465.5084 2102.5994 2986.9407 4625.0005 7647.5859 13520.7510 | lr 2.2e-04 | norm 4145.4199 | dt 9.881 +type train | step 3415 | loss 91.8767 181.4927 290.9609 480.1212 715.2237 1039.1356 1468.0076 2119.5811 3019.0166 4666.3252 7704.2524 13772.3496 | lr 2.2e-04 | norm 5373.2544 | dt 9.869 +type train | step 3416 | loss 99.7656 197.3441 302.9505 489.4847 721.5810 1047.2893 1474.1809 2126.8621 2984.4587 4627.6953 7621.8428 13528.9531 | lr 2.2e-04 | norm 4459.0527 | dt 9.888 +type train | step 3417 | loss 99.9145 196.6291 304.0453 495.2210 729.9276 1050.1453 1471.3525 2102.4639 2944.9636 4538.6270 7517.9492 13435.7627 | lr 2.2e-04 | norm 4500.3096 | dt 9.879 +type train | step 3418 | loss 93.3582 183.3947 288.3194 470.8958 697.7115 1011.3286 1422.4525 2044.5236 2891.1492 4489.5664 7399.6445 13104.3301 | lr 2.2e-04 | norm 3826.0850 | dt 9.876 +type train | step 3419 | loss 104.9814 205.5013 319.0238 515.5760 752.9115 1084.4716 1510.8263 2150.6230 2979.6958 4588.6787 7532.3662 13440.7002 | lr 2.2e-04 | norm 4819.2998 | dt 9.873 +type train | step 3420 | loss 98.8956 196.6921 307.2401 503.5736 739.6605 1070.8009 1495.6191 2134.6936 2978.8201 4568.8740 7490.8843 13237.6680 | lr 2.2e-04 | norm 4524.4536 | dt 9.867 +type train | step 3421 | loss 102.4931 202.4100 313.3763 503.1879 737.7007 1071.7942 1504.8328 2156.6355 3038.7302 4669.2070 7653.1733 13467.9824 | lr 2.2e-04 | norm 3833.3875 | dt 9.881 +type train | step 3422 | loss 97.5429 190.2872 299.2517 486.8858 718.5891 1034.9777 1447.9391 2060.1104 2889.3779 4445.1777 7284.2852 12804.5850 | lr 2.2e-04 | norm 4266.7207 | dt 9.880 +type train | step 3423 | loss 92.9813 180.7037 286.2060 469.1723 698.5674 1023.1857 1444.1549 2086.7974 2940.1626 4545.7886 7470.2354 13239.4121 | lr 2.2e-04 | norm 4069.0264 | dt 9.878 +type train | step 3424 | loss 111.2587 218.5514 337.3714 538.9760 789.4630 1123.9370 1564.2948 2221.1943 3110.7144 4810.9854 7906.0703 13967.9043 | lr 2.2e-04 | norm 6251.1626 | dt 9.878 +type train | step 3425 | loss 92.6728 180.0153 283.7722 465.6071 692.9622 1004.0727 1421.2964 2052.2908 2916.2812 4514.2354 7408.2397 13015.2471 | lr 2.2e-04 | norm 3811.8223 | dt 9.866 +type train | step 3426 | loss 96.0809 190.9759 298.7514 489.2941 727.5351 1063.3589 1508.0887 2182.5481 3069.2017 4746.3887 7876.3608 14042.7148 | lr 2.2e-04 | norm 6148.5376 | dt 9.862 +type train | step 3427 | loss 97.6288 188.5334 291.2953 473.2834 697.3696 1013.3802 1418.9967 2047.6289 2888.0273 4473.4307 7419.0522 13202.8740 | lr 2.2e-04 | norm 4177.9067 | dt 9.853 +type train | step 3428 | loss 103.5941 200.4849 310.5622 503.1656 738.5602 1066.3271 1493.8586 2139.6196 2996.2686 4592.8203 7499.7812 13288.5039 | lr 2.2e-04 | norm 4647.8179 | dt 9.874 +type train | step 3429 | loss 96.2373 187.3048 292.8129 476.5710 706.6802 1017.6793 1426.7397 2045.4314 2881.0798 4456.0186 7352.4644 12944.9189 | lr 2.2e-04 | norm 3620.9475 | dt 9.878 +type train | step 3430 | loss 91.0002 178.3497 278.7554 457.3942 681.9578 988.0853 1394.7673 2008.4591 2859.3142 4447.3989 7376.7109 13020.7324 | lr 2.2e-04 | norm 3917.3276 | dt 9.874 +type train | step 3431 | loss 96.7718 188.8060 301.4688 491.7114 727.0909 1057.6252 1484.2213 2130.5452 3008.6064 4678.1699 7757.4160 13736.3398 | lr 2.2e-04 | norm 4133.5449 | dt 9.871 +type train | step 3432 | loss 103.0258 199.4063 311.1648 506.1860 731.7326 1062.8719 1469.8320 2086.4524 2865.9282 4412.7861 7244.0996 12954.4639 | lr 2.2e-04 | norm 5218.3345 | dt 9.854 +type train | step 3433 | loss 100.4451 200.1920 311.8122 501.4378 737.6842 1078.9286 1516.0518 2178.8730 3037.1250 4673.1934 7643.4365 13509.6758 | lr 2.2e-04 | norm 4688.3247 | dt 9.865 +type train | step 3434 | loss 97.5820 190.9408 299.2840 486.1277 714.0804 1030.0660 1442.7075 2059.5942 2889.3101 4458.2173 7364.8223 13116.6367 | lr 2.2e-04 | norm 4088.0583 | dt 9.872 +type train | step 3435 | loss 94.2189 184.2563 291.6649 477.7848 709.4675 1027.3845 1451.7538 2097.4282 2976.6545 4613.2012 7597.6387 13440.6367 | lr 2.2e-04 | norm 3857.0288 | dt 9.874 +type train | step 3436 | loss 107.1087 210.0033 323.5875 521.9622 757.1144 1087.2694 1512.0062 2154.8689 3013.8127 4648.5288 7711.0508 13715.8096 | lr 2.2e-04 | norm 5528.9165 | dt 9.857 +type train | step 3437 | loss 98.0170 192.5491 300.2214 489.3901 721.5208 1043.2621 1467.5789 2112.2996 2983.5349 4613.5469 7634.2842 13493.9043 | lr 2.2e-04 | norm 3850.1587 | dt 9.869 +type train | step 3438 | loss 95.6208 188.0226 297.1150 489.2525 718.4783 1045.8488 1468.7153 2113.3054 2963.5393 4580.1011 7521.1172 13322.3086 | lr 2.2e-04 | norm 4508.4121 | dt 9.875 +type train | step 3439 | loss 97.7737 191.5411 307.5532 505.8053 742.5006 1073.8253 1499.7588 2153.0354 3010.1211 4613.8584 7581.1665 13347.2344 | lr 2.2e-04 | norm 6625.4502 | dt 9.877 +type train | step 3440 | loss 92.2477 178.3632 279.8982 463.0350 691.1456 1019.1415 1447.0015 2110.8223 2987.5371 4674.9458 7786.6938 13866.2412 | lr 2.2e-04 | norm 5131.0059 | dt 9.854 +type train | step 3441 | loss 101.4059 199.4023 306.5471 492.8751 722.7596 1047.4717 1477.5663 2133.3191 2988.0444 4586.2515 7558.6812 13370.8877 | lr 2.2e-04 | norm 4893.6392 | dt 9.881 +type train | step 3442 | loss 97.2748 190.3999 299.1474 487.3002 718.8193 1043.6531 1469.8660 2112.1172 2951.8477 4556.1543 7503.3491 13306.3125 | lr 2.2e-04 | norm 4424.6914 | dt 9.876 +type train | step 3443 | loss 96.8025 189.4198 296.5731 485.4125 713.4092 1036.3291 1455.7385 2092.6431 2947.3293 4541.2334 7492.0376 13416.0869 | lr 2.2e-04 | norm 4478.8135 | dt 9.873 +type train | step 3444 | loss 99.4817 195.6571 300.2933 490.2490 724.3267 1067.9805 1513.7839 2184.7090 3046.7273 4698.5405 7745.2207 13697.9258 | lr 2.2e-04 | norm 4556.4277 | dt 9.874 +type train | step 3445 | loss 92.5053 180.3219 283.8720 466.2606 696.3276 1011.8135 1430.9089 2065.4990 2905.3679 4487.5684 7350.8906 12956.8008 | lr 2.2e-04 | norm 4696.5859 | dt 9.879 +type train | step 3446 | loss 104.2456 203.7109 313.4771 502.4241 736.6190 1063.4392 1488.6857 2130.5354 2970.9768 4549.9746 7448.8052 13218.1543 | lr 2.2e-04 | norm 4504.3906 | dt 9.885 +type train | step 3447 | loss 103.2124 202.7253 311.5598 506.7921 738.9389 1062.7179 1489.4645 2124.5676 2972.4570 4566.7251 7600.6455 13665.1309 | lr 2.2e-04 | norm 4941.8101 | dt 9.871 +type train | step 3448 | loss 89.8080 177.0156 281.3148 464.5671 692.0685 1010.3590 1430.4402 2070.3132 2956.4688 4586.2158 7551.6899 13341.4121 | lr 2.2e-04 | norm 3772.6462 | dt 9.883 +type train | step 3449 | loss 102.0808 199.9649 310.2487 498.6309 730.5434 1064.4178 1496.5643 2154.0776 3021.2812 4675.2432 7722.7876 13682.4619 | lr 2.2e-04 | norm 3829.0366 | dt 9.869 +type train | step 3450 | loss 112.2273 223.4780 343.3298 559.0172 810.9465 1177.7958 1631.9365 2333.9341 3210.1416 4877.0522 8011.0449 14201.9746 | lr 2.2e-04 | norm 5277.4048 | dt 9.856 +type train | step 3451 | loss 99.3168 195.5536 303.2698 499.0543 736.4985 1062.7509 1481.9072 2111.0940 2951.4050 4524.9766 7456.7549 13226.5635 | lr 2.2e-04 | norm 4126.2793 | dt 9.881 +type train | step 3452 | loss 96.8675 191.6190 297.0885 483.2366 712.8727 1028.3406 1440.7467 2074.9475 2918.9062 4526.3296 7445.0698 13194.1426 | lr 2.2e-04 | norm 4592.7158 | dt 9.875 +type train | step 3453 | loss 127.2035 249.2646 369.2087 571.5648 812.0168 1180.8253 1647.8777 2360.6782 3198.5510 4891.3604 8015.8389 14199.7090 | lr 2.2e-04 | norm 6575.0938 | dt 9.872 +type train | step 3454 | loss 90.8371 177.7405 283.1571 464.2996 694.1597 1007.4308 1418.5731 2037.2784 2893.4473 4449.2573 7314.2871 12901.2637 | lr 2.2e-04 | norm 4012.4968 | dt 9.882 +type train | step 3455 | loss 89.1571 172.9258 273.8220 453.0009 678.6348 983.6934 1385.5931 1994.9673 2844.5305 4390.5186 7208.7402 12655.5195 | lr 2.2e-04 | norm 3546.2834 | dt 9.875 +type train | step 3456 | loss 93.9818 182.8775 286.9675 468.6773 695.2795 1007.9234 1416.9783 2037.2341 2874.0728 4434.2100 7331.0845 12883.8486 | lr 2.2e-04 | norm 3761.0154 | dt 9.881 +type train | step 3457 | loss 95.9771 185.9150 293.4341 480.6339 710.1274 1030.6094 1448.2834 2082.8247 2924.5747 4511.2837 7473.3267 13326.9873 | lr 2.2e-04 | norm 4155.4399 | dt 9.868 +type train | step 3458 | loss 93.8165 185.8717 293.6828 480.2209 714.1547 1037.6248 1466.7346 2120.1423 3011.0200 4646.5684 7666.6641 13582.6211 | lr 2.2e-04 | norm 4245.5098 | dt 9.876 +type train | step 3459 | loss 101.4265 200.6082 311.7147 501.3256 738.8260 1069.1344 1496.6176 2146.3689 3005.6633 4627.2842 7601.2085 13365.0771 | lr 2.2e-04 | norm 3700.2400 | dt 9.887 +type train | step 3460 | loss 98.9675 194.5465 301.2556 489.6593 713.9409 1033.0145 1439.7889 2053.6057 2867.5334 4393.2344 7197.4351 12696.1582 | lr 2.2e-04 | norm 4173.7202 | dt 9.863 +type train | step 3461 | loss 96.1891 188.7146 297.7137 487.2556 719.8853 1051.9454 1483.2666 2142.9053 3022.7559 4715.7085 7814.4932 13856.8115 | lr 2.2e-04 | norm 4051.1584 | dt 9.865 +type train | step 3462 | loss 97.5459 189.9614 297.1497 487.1498 718.6790 1048.7690 1475.2288 2127.3750 2998.1685 4636.6816 7624.6436 13466.0352 | lr 2.2e-04 | norm 3885.9629 | dt 9.871 +type train | step 3463 | loss 92.2330 180.3413 287.5398 469.8696 701.0837 1015.7653 1432.9620 2067.1631 2930.1560 4559.4365 7531.4185 13368.4551 | lr 2.2e-04 | norm 3845.1997 | dt 9.865 +type train | step 3464 | loss 94.9961 186.3890 294.8499 486.6710 725.6908 1048.7668 1470.8549 2111.8813 2985.7380 4613.7119 7564.3389 13249.1338 | lr 2.2e-04 | norm 3974.6687 | dt 9.879 +type train | step 3465 | loss 86.6209 167.4805 265.6105 442.5157 666.1883 979.0419 1394.6547 2030.3853 2889.3447 4483.2476 7374.3164 12900.4912 | lr 2.2e-04 | norm 4114.9243 | dt 9.877 +type train | step 3466 | loss 94.0786 183.6524 289.0952 476.5156 711.1122 1024.7717 1443.9292 2087.5076 2963.4355 4629.5366 7707.6611 13806.7246 | lr 2.2e-04 | norm 7024.2373 | dt 9.867 +type train | step 3467 | loss 90.0399 174.5001 277.3607 459.0881 687.1198 1007.4703 1427.5057 2071.0732 2930.0637 4557.9194 7493.2769 13195.2842 | lr 2.2e-04 | norm 3947.7329 | dt 9.871 +type train | step 3468 | loss 100.7485 197.6772 303.3695 487.3188 720.4534 1045.9828 1473.0668 2112.6731 2984.6816 4620.3491 7643.8350 13560.5107 | lr 2.2e-04 | norm 5711.1006 | dt 9.855 +type train | step 3469 | loss 95.4646 186.2105 290.7555 472.8058 701.3094 1021.1121 1441.2808 2086.5317 2941.9797 4545.7471 7460.9077 13099.8740 | lr 2.1e-04 | norm 4057.1384 | dt 9.869 +type train | step 3470 | loss 101.5991 199.5321 312.5382 508.8764 744.3098 1069.6680 1491.7852 2126.9773 2975.5364 4576.4907 7521.6816 13380.4990 | lr 2.1e-04 | norm 5317.9692 | dt 9.878 +type train | step 3471 | loss 97.6251 191.0576 298.2793 484.6439 713.8794 1022.5378 1433.6970 2047.5413 2878.4685 4430.7456 7289.2446 12908.6436 | lr 2.1e-04 | norm 3929.6709 | dt 9.885 +type train | step 3472 | loss 99.7404 194.8460 301.3751 486.1871 715.6884 1032.6692 1459.4763 2099.5828 2948.2197 4531.7002 7436.3296 13158.1113 | lr 2.1e-04 | norm 4395.5088 | dt 9.871 +type train | step 3473 | loss 102.6931 203.9430 312.4043 504.7955 741.3660 1081.0977 1516.5087 2178.8728 3050.1565 4715.1445 7794.4175 13743.3457 | lr 2.1e-04 | norm 4406.1294 | dt 9.862 +type train | step 3474 | loss 92.1425 179.3803 282.6447 466.6129 693.4400 1013.9393 1434.6484 2068.2212 2918.2651 4521.3428 7472.7993 13208.5479 | lr 2.1e-04 | norm 5223.2729 | dt 9.873 +type train | step 3475 | loss 91.8468 178.3459 281.3465 462.6787 694.2966 1002.8816 1417.1683 2046.6462 2912.8860 4524.4365 7452.1841 13151.9922 | lr 2.1e-04 | norm 3529.1775 | dt 9.877 +type train | step 3476 | loss 90.6876 175.7077 275.6288 454.3267 679.1562 985.9604 1394.9696 2011.1437 2864.7615 4455.8374 7369.7764 13036.4355 | lr 2.1e-04 | norm 4079.5344 | dt 9.875 +type train | step 3477 | loss 106.9124 210.9208 320.3899 512.3314 752.2351 1103.6666 1547.8195 2240.7131 3084.2839 4725.6440 7676.9468 13547.5352 | lr 2.1e-04 | norm 5861.4927 | dt 9.869 +type train | step 3478 | loss 91.5094 178.4047 282.5457 465.2947 692.8043 1003.4072 1417.1456 2042.3127 2898.4404 4487.8950 7452.3057 13155.4385 | lr 2.1e-04 | norm 3543.1719 | dt 9.883 +type train | step 3479 | loss 95.1542 184.3763 290.8898 473.1149 704.4033 1014.0916 1429.3690 2050.6121 2908.8604 4495.4448 7373.1221 13018.3408 | lr 2.1e-04 | norm 4232.0610 | dt 9.868 +type train | step 3480 | loss 91.4394 177.4159 281.5240 463.1144 689.6060 1002.9102 1418.3724 2037.4993 2889.6262 4458.9199 7379.9185 13000.9258 | lr 2.1e-04 | norm 3494.5544 | dt 9.875 +type train | step 3481 | loss 96.3967 190.0027 296.7121 478.8713 706.2268 1019.4179 1434.2710 2051.7168 2894.6130 4489.4424 7439.6401 13165.5674 | lr 2.1e-04 | norm 4129.1753 | dt 9.864 +type train | step 3482 | loss 92.0698 185.3290 300.7653 494.7565 743.7991 1080.6195 1529.1433 2229.7581 3158.8369 4957.2808 8219.3828 14436.4639 | lr 2.1e-04 | norm 6461.0820 | dt 9.861 +type train | step 3483 | loss 92.9136 183.1521 291.4934 478.7762 716.1988 1046.4149 1481.6847 2149.0283 3034.8477 4696.1948 7745.6978 13667.8994 | lr 2.1e-04 | norm 4711.7144 | dt 9.875 +type train | step 3484 | loss 99.6122 194.2750 305.6446 495.9203 729.7996 1052.2692 1480.9149 2113.8577 2984.9177 4629.5835 7618.0645 13431.8584 | lr 2.1e-04 | norm 4117.3359 | dt 9.859 +type train | step 3485 | loss 96.9136 191.0564 301.9588 496.1495 738.1279 1075.3177 1514.9052 2174.8386 3060.8264 4711.4927 7723.1396 13690.0605 | lr 2.1e-04 | norm 4196.0430 | dt 9.875 +type train | step 3486 | loss 105.3008 205.7840 315.4651 509.5079 744.5931 1079.8773 1520.2781 2174.4211 3026.1929 4643.5684 7647.7041 13595.8203 | lr 2.1e-04 | norm 4214.9580 | dt 9.885 +type train | step 3487 | loss 90.2151 177.5848 284.5158 470.2011 700.3290 1015.7703 1435.2677 2068.3486 2930.7217 4535.6279 7515.1938 13281.9219 | lr 2.1e-04 | norm 3918.7737 | dt 9.878 +type train | step 3488 | loss 93.7339 183.9966 291.5185 477.2399 708.0456 1018.4252 1427.6821 2049.3035 2906.1694 4491.0718 7382.9224 13035.5156 | lr 2.1e-04 | norm 3770.3525 | dt 9.887 +type train | step 3489 | loss 90.4271 178.5502 281.9314 460.3043 688.7534 996.1074 1407.7219 2033.8854 2901.6438 4489.5908 7386.2817 12967.4883 | lr 2.1e-04 | norm 5125.6733 | dt 9.884 +type train | step 3490 | loss 96.3082 188.3525 293.8744 480.5430 715.7375 1034.8070 1459.7771 2096.3477 2953.1665 4560.8887 7456.7036 13148.3750 | lr 2.1e-04 | norm 4393.4224 | dt 9.873 +type train | step 3491 | loss 97.0654 187.9051 289.2515 469.3610 694.7770 1004.0620 1415.4396 2033.1802 2875.1238 4449.2969 7359.4722 13094.1709 | lr 2.1e-04 | norm 4136.8926 | dt 9.871 +type train | step 3492 | loss 100.9447 198.3219 308.4944 498.5969 736.0640 1066.4745 1498.9806 2153.1934 3024.6045 4661.4922 7672.1899 13592.2539 | lr 2.1e-04 | norm 4209.6113 | dt 9.883 +type train | step 3493 | loss 85.1060 166.4163 269.2916 450.9390 677.6883 993.7802 1418.0043 2063.1348 2951.6216 4612.8364 7610.3521 13485.8125 | lr 2.1e-04 | norm 5215.5918 | dt 9.850 +type train | step 3494 | loss 102.4246 200.4956 312.1323 505.2215 740.6881 1069.3795 1496.5775 2152.8167 3031.3774 4618.2212 7573.9556 13408.4102 | lr 2.1e-04 | norm 4333.2144 | dt 9.869 +type train | step 3495 | loss 107.5255 212.7517 326.4143 524.3382 767.1085 1108.9128 1540.7216 2187.8955 3049.9866 4686.9438 7699.2930 13551.9453 | lr 2.1e-04 | norm 4662.1851 | dt 9.884 +type train | step 3496 | loss 107.4938 213.6859 325.0770 515.4529 747.8237 1050.1891 1466.8533 2078.7156 2921.5117 4467.9189 7301.8560 12922.3379 | lr 2.1e-04 | norm 7739.1465 | dt 9.853 +type train | step 3497 | loss 95.4160 185.1002 289.7354 469.1530 695.8850 1003.1553 1412.2771 2027.2301 2863.6360 4417.9961 7282.7114 12842.7490 | lr 2.1e-04 | norm 4404.9399 | dt 9.868 +type train | step 3498 | loss 91.5234 178.8215 283.3734 467.5513 693.7320 998.8197 1411.1586 2039.2765 2881.3357 4485.6235 7444.0913 13349.4697 | lr 2.1e-04 | norm 4571.7812 | dt 9.886 +type train | step 3499 | loss 96.5763 190.2418 297.5330 482.2812 716.4456 1031.8055 1450.1960 2075.5005 2942.4180 4562.7822 7540.6846 13346.3906 | lr 2.1e-04 | norm 4972.3193 | dt 9.872 +type train | step 3500 | loss 93.9831 183.4293 286.3121 468.8459 695.6965 1012.8224 1422.5732 2041.7666 2882.7581 4447.6069 7409.4521 13224.5215 | lr 2.1e-04 | norm 4205.6826 | dt 9.859 +type train | step 3501 | loss 92.4097 178.9657 281.1310 463.4859 686.4573 992.2366 1394.5944 2004.7776 2834.4055 4390.1841 7209.2471 12685.9014 | lr 2.1e-04 | norm 3749.1191 | dt 9.867 +type train | step 3502 | loss 105.2060 205.5261 314.0437 501.0157 735.5005 1064.5917 1483.7091 2130.3613 2970.3508 4579.1431 7593.2241 13532.9619 | lr 2.1e-04 | norm 4365.3208 | dt 9.867 +type train | step 3503 | loss 96.7772 192.6244 301.9308 489.8568 728.9818 1063.9966 1506.4617 2192.4253 3120.3879 4840.2417 7992.6304 14135.6836 | lr 2.1e-04 | norm 6344.2153 | dt 9.856 +type train | step 3504 | loss 93.7195 184.8628 287.9640 473.7037 705.1387 1024.7729 1445.0529 2083.9756 2964.1189 4602.9165 7601.8843 13372.7871 | lr 2.1e-04 | norm 4514.8579 | dt 9.861 +type train | step 3505 | loss 91.6527 180.4132 285.0289 467.8163 696.2791 1015.5217 1435.2856 2074.2556 2933.6470 4541.4951 7533.2783 13362.5352 | lr 2.1e-04 | norm 4188.7349 | dt 9.868 +type train | step 3506 | loss 99.9152 195.9989 302.1395 489.4776 719.7231 1036.7205 1456.8549 2081.6614 2934.0652 4548.3853 7498.0474 13260.1523 | lr 2.1e-04 | norm 3988.0398 | dt 9.880 +type train | step 3507 | loss 101.1479 200.4036 309.4083 497.6442 724.5627 1046.4434 1463.0844 2096.0688 2933.6489 4521.1006 7475.9717 13263.8838 | lr 2.1e-04 | norm 3973.7073 | dt 9.880 +type train | step 3508 | loss 93.2617 182.6924 288.5879 473.6702 701.8965 1022.0857 1443.5900 2068.9207 2933.3074 4573.7002 7543.8525 13397.5469 | lr 2.1e-04 | norm 4387.0825 | dt 9.878 +type train | step 3509 | loss 102.3773 203.7918 316.8455 520.5355 757.3347 1099.0288 1527.4087 2182.5166 3033.9629 4681.4058 7719.1035 13739.6064 | lr 2.1e-04 | norm 5272.1909 | dt 9.868 +type train | step 3510 | loss 92.9143 181.8374 284.0847 466.8344 693.5417 1005.3745 1407.4583 2028.6941 2879.4773 4462.7139 7347.4956 12933.8604 | lr 2.1e-04 | norm 4125.1865 | dt 9.875 +type train | step 3511 | loss 91.5876 179.5567 286.5772 471.6859 701.6603 1027.0342 1454.2633 2105.4197 2979.5955 4630.0879 7608.9907 13406.5059 | lr 2.1e-04 | norm 4053.0854 | dt 9.866 +type train | step 3512 | loss 104.7561 211.2281 326.3495 530.7717 775.5551 1131.2148 1577.1848 2263.5571 3188.5906 4888.3057 7985.6553 13976.6748 | lr 2.1e-04 | norm 7161.5493 | dt 9.856 +type train | step 3513 | loss 88.6753 172.1089 274.6158 459.8359 688.8981 1010.1295 1439.1202 2085.5840 2944.1243 4575.5962 7632.2817 13620.0303 | lr 2.1e-04 | norm 6057.8008 | dt 9.871 +type train | step 3514 | loss 94.0626 183.5827 290.2315 475.0573 703.8439 1019.9910 1436.1011 2067.2852 2917.3586 4517.0762 7468.5234 13185.6631 | lr 2.1e-04 | norm 3940.3906 | dt 9.893 +type train | step 3515 | loss 97.7332 192.7051 303.3284 493.6714 728.5170 1058.7498 1492.2991 2152.2341 3030.7759 4686.5498 7711.9917 13626.5625 | lr 2.1e-04 | norm 3868.2004 | dt 9.870 +type train | step 3516 | loss 94.8662 183.6559 289.5081 475.9185 704.7607 1026.5436 1457.0032 2096.6260 2953.5298 4617.9624 7631.6279 13640.0234 | lr 2.1e-04 | norm 4954.6265 | dt 9.867 +type train | step 3517 | loss 101.5475 200.4000 309.2941 499.9409 735.6055 1071.5765 1502.8981 2158.0681 3009.9783 4613.1865 7618.2563 13473.6621 | lr 2.1e-04 | norm 4523.4414 | dt 9.875 +type train | step 3518 | loss 85.3975 169.2907 273.2860 456.3878 689.2588 1005.4033 1435.3079 2080.1555 2986.1448 4631.8628 7581.6118 13276.1191 | lr 2.1e-04 | norm 4748.9429 | dt 9.874 +type train | step 3519 | loss 104.3723 203.9184 312.6507 505.7220 744.7831 1088.2000 1526.4385 2199.0696 3069.4412 4704.2598 7708.8887 13596.1504 | lr 2.1e-04 | norm 4048.9707 | dt 9.890 +type train | step 3520 | loss 88.9254 175.7243 280.9594 468.4617 701.4543 1024.4380 1458.7290 2110.6868 2995.1140 4635.9707 7618.1914 13426.4395 | lr 2.1e-04 | norm 4590.0630 | dt 9.878 +type train | step 3521 | loss 116.5287 230.4232 352.2566 560.4371 815.4410 1196.7009 1664.5034 2413.5359 3297.6860 5018.0269 8195.8838 14401.2910 | lr 2.1e-04 | norm 7566.2285 | dt 9.859 +type train | step 3522 | loss 92.7802 181.1293 289.2568 474.5236 704.9346 1016.3661 1429.8900 2053.0156 2901.4907 4478.6997 7410.8521 13109.3545 | lr 2.1e-04 | norm 3710.6841 | dt 9.887 +type train | step 3523 | loss 94.6858 186.5604 297.1111 487.5099 722.0470 1051.4240 1482.2156 2128.8552 3007.0247 4681.5317 7729.3145 13662.4111 | lr 2.1e-04 | norm 4153.2275 | dt 9.870 +type train | step 3524 | loss 92.7155 179.9428 283.5205 463.6818 689.4408 1004.4023 1423.8446 2052.6890 2908.4951 4506.7485 7468.7148 13249.3662 | lr 2.1e-04 | norm 4112.8379 | dt 9.909 +type train | step 3525 | loss 97.6226 193.4725 299.0496 489.8931 721.6941 1067.1066 1510.8270 2203.7170 3074.4167 4738.9712 7785.0444 13665.1816 | lr 2.1e-04 | norm 3988.5876 | dt 9.881 +type train | step 3526 | loss 95.2223 186.2233 291.1158 474.3890 701.9191 1012.3842 1417.0820 2031.0547 2851.1299 4412.3208 7343.0205 13057.8682 | lr 2.1e-04 | norm 4591.5962 | dt 9.889 +type train | step 3527 | loss 95.4418 186.2384 292.1447 476.6567 706.3274 1031.6244 1448.8582 2105.0303 2935.1138 4533.0859 7424.7422 13116.7559 | lr 2.1e-04 | norm 4686.4116 | dt 9.878 +type train | step 3528 | loss 91.3023 177.2219 279.5230 455.9030 678.9886 990.9077 1397.8673 2011.5140 2830.6372 4408.5278 7299.9131 12870.3848 | lr 2.1e-04 | norm 3782.3860 | dt 9.887 +type train | step 3529 | loss 94.0753 185.7649 294.4663 481.6263 713.4828 1034.5636 1460.1663 2095.2900 2950.1548 4569.2007 7521.5093 13320.4805 | lr 2.1e-04 | norm 4467.1157 | dt 9.870 +type train | step 3530 | loss 89.4270 173.9229 274.9712 453.5585 674.6761 982.2162 1385.4327 2001.1727 2835.1196 4421.0508 7288.5830 12850.9053 | lr 2.1e-04 | norm 3659.6475 | dt 9.874 +type train | step 3531 | loss 103.0636 201.7938 312.0020 501.7746 738.2693 1063.6296 1487.7008 2124.9219 2976.2620 4608.8604 7577.1001 13351.6523 | lr 2.1e-04 | norm 5801.0078 | dt 9.857 +type train | step 3532 | loss 91.7277 179.1584 282.5222 462.1197 686.4821 1004.2385 1418.5466 2059.5923 2900.4492 4502.4902 7436.9390 13187.8398 | lr 2.1e-04 | norm 3843.3875 | dt 9.874 +type train | step 3533 | loss 94.5732 188.1610 294.8207 483.5602 714.6871 1036.6204 1450.5300 2096.0889 2903.9041 4508.7412 7438.6587 13436.6201 | lr 2.1e-04 | norm 5122.5044 | dt 9.876 +type train | step 3534 | loss 90.3926 175.2197 275.9317 452.1519 675.4754 980.0237 1386.7131 1997.3536 2837.6953 4396.5562 7248.5986 12729.5166 | lr 2.1e-04 | norm 4265.5425 | dt 9.890 +type train | step 3535 | loss 89.2751 173.9049 276.0029 455.1171 676.4749 992.4762 1402.6914 2035.0575 2884.2791 4490.9707 7451.2769 13258.2402 | lr 2.1e-04 | norm 3742.5857 | dt 9.872 +type train | step 3536 | loss 92.4873 180.6671 281.9932 467.2323 694.4831 1015.3125 1433.9803 2066.3779 2918.7268 4516.6206 7478.8130 13232.9707 | lr 2.1e-04 | norm 3812.6377 | dt 9.879 +type train | step 3537 | loss 93.6560 183.4626 288.6596 473.5804 703.3027 1024.8832 1442.5450 2089.7432 2962.4929 4600.6250 7590.3691 13413.3926 | lr 2.1e-04 | norm 3736.8652 | dt 9.866 +type train | step 3538 | loss 94.4546 183.9582 287.4156 470.3910 696.1789 1013.5325 1431.3801 2046.6763 2888.5657 4492.3892 7426.4429 13072.6533 | lr 2.1e-04 | norm 3919.9258 | dt 9.877 +type train | step 3539 | loss 96.0862 187.9936 292.3916 477.0187 705.3976 1018.1176 1433.1271 2061.7766 2922.2935 4572.7690 7566.4180 13388.9678 | lr 2.1e-04 | norm 3950.7144 | dt 9.880 +type train | step 3540 | loss 91.2982 179.4627 281.4784 460.3197 685.9550 1005.0879 1425.8969 2060.7451 2921.4597 4567.2969 7566.2139 13374.2236 | lr 2.1e-04 | norm 3860.7539 | dt 9.870 +type train | step 3541 | loss 100.0435 194.3942 303.8059 491.7800 726.8764 1051.4377 1472.7285 2114.6938 2960.2661 4625.9717 7535.9316 13312.7812 | lr 2.1e-04 | norm 5293.4111 | dt 9.890 +type train | step 3542 | loss 92.9935 180.6248 285.0609 471.4874 698.3223 1018.5022 1437.8662 2063.3171 2898.5942 4493.5703 7419.8853 13147.6582 | lr 2.1e-04 | norm 4100.9116 | dt 9.872 +type train | step 3543 | loss 93.2292 185.0406 290.6333 480.3719 719.4738 1056.1202 1497.0127 2182.1758 3099.5896 4846.7764 7965.0757 14099.3672 | lr 2.1e-04 | norm 4525.2847 | dt 9.859 +type train | step 3544 | loss 89.2718 172.7860 272.5717 452.5626 677.3601 996.9587 1418.8385 2055.8801 2912.3591 4540.1416 7541.2178 13343.3125 | lr 2.1e-04 | norm 4055.6458 | dt 9.867 +type train | step 3545 | loss 92.4369 181.1213 285.1903 467.1041 697.4399 1018.7112 1438.2024 2084.4832 2943.7166 4576.0850 7567.6221 13468.4111 | lr 2.0e-04 | norm 4740.8657 | dt 9.858 +type train | step 3546 | loss 93.8731 184.2310 289.1560 471.8746 698.5251 1009.5356 1424.0435 2041.3296 2880.4990 4443.7925 7292.4697 12934.7725 | lr 2.0e-04 | norm 4039.8413 | dt 9.880 +type train | step 3547 | loss 95.0875 184.9946 286.8375 470.9261 702.6508 1027.0828 1452.8929 2096.1880 2958.2458 4577.4058 7548.4863 13306.8525 | lr 2.0e-04 | norm 4043.4680 | dt 9.871 +type train | step 3548 | loss 102.2520 201.9726 312.7732 506.8505 748.1025 1076.3237 1503.8512 2157.7402 2988.0391 4595.6377 7540.8389 13355.0586 | lr 2.0e-04 | norm 6551.9043 | dt 9.875 +type train | step 3549 | loss 96.3194 186.9988 296.3075 482.5240 716.4830 1033.8580 1455.2081 2089.3154 2966.2500 4587.8809 7544.1895 13199.4551 | lr 2.0e-04 | norm 4168.1235 | dt 9.881 +type train | step 3550 | loss 95.8994 185.7328 289.2296 470.9532 698.6495 1018.4259 1429.3323 2070.8862 2900.7788 4479.1123 7444.5747 13194.6738 | lr 2.0e-04 | norm 4709.0610 | dt 9.876 +type train | step 3551 | loss 92.2884 180.8046 284.1911 469.9824 696.0670 1011.6646 1425.5437 2055.7312 2913.2100 4503.3950 7425.4761 13030.7119 | lr 2.0e-04 | norm 3779.6191 | dt 9.877 +type train | step 3552 | loss 91.2530 178.5459 283.9910 466.3527 697.9882 1016.0948 1441.8827 2087.9224 2956.0500 4589.9380 7609.5098 13577.5391 | lr 2.0e-04 | norm 5627.9199 | dt 9.860 +type train | step 3553 | loss 95.8177 187.1070 292.1808 476.0097 705.4323 1017.5158 1427.4948 2045.9692 2902.1313 4510.2461 7474.2686 13362.3906 | lr 2.0e-04 | norm 3916.2561 | dt 9.885 +type train | step 3554 | loss 92.4016 179.0843 282.9693 463.1052 688.1676 997.8407 1409.6323 2029.4338 2875.6230 4477.4736 7397.8696 13024.4492 | lr 2.0e-04 | norm 3679.3894 | dt 9.873 +type train | step 3555 | loss 95.7922 186.0396 293.3728 480.1681 711.2521 1038.0391 1457.0018 2092.7207 2942.5867 4579.4048 7582.1543 13554.6543 | lr 2.0e-04 | norm 4623.9888 | dt 9.856 +type train | step 3556 | loss 96.2603 188.0805 291.3569 473.8135 700.0104 1007.1777 1411.5658 2029.7035 2868.6685 4440.8345 7316.0093 12948.2158 | lr 2.0e-04 | norm 4108.2759 | dt 9.877 +type train | step 3557 | loss 89.6872 172.0009 274.3002 452.1740 675.7510 988.6171 1399.6224 2021.4353 2864.8452 4452.6455 7353.6826 13077.4795 | lr 2.0e-04 | norm 4222.3496 | dt 9.873 +type train | step 3558 | loss 92.0395 177.4600 281.5374 465.0598 696.7856 1038.8561 1478.3098 2145.0764 3033.3433 4676.0938 7733.5801 13701.0547 | lr 2.0e-04 | norm 4122.0010 | dt 9.880 +type train | step 3559 | loss 98.7536 193.4344 297.7890 480.7070 714.8228 1039.0930 1464.6305 2106.2849 2967.8057 4571.8711 7507.3950 13221.1689 | lr 2.0e-04 | norm 3989.5349 | dt 9.891 +type train | step 3560 | loss 102.2896 203.3346 314.9562 506.8445 739.9221 1065.5392 1487.6112 2126.9221 2989.5015 4700.6187 7755.0195 13822.4189 | lr 2.0e-04 | norm 7134.2896 | dt 9.881 +type train | step 3561 | loss 92.9656 181.8000 285.3397 464.7774 691.1064 1001.1755 1407.0851 2019.7095 2840.7698 4404.3262 7267.8599 12871.9150 | lr 2.0e-04 | norm 4154.1460 | dt 9.867 +type train | step 3562 | loss 100.0127 194.2826 303.3240 495.2968 729.1127 1050.4551 1476.2787 2094.6934 2934.2925 4530.8604 7499.0327 13273.4971 | lr 2.0e-04 | norm 4483.2461 | dt 9.888 +type train | step 3563 | loss 97.0227 189.2632 297.2645 484.1834 718.3357 1055.3903 1484.3602 2147.0693 2999.9651 4612.3042 7617.2441 13521.7910 | lr 2.0e-04 | norm 4264.3447 | dt 9.866 +type train | step 3564 | loss 102.6373 199.9850 315.1785 512.9487 756.7472 1109.4312 1550.4413 2236.4077 3084.3862 4720.1919 7708.9111 13668.7891 | lr 2.0e-04 | norm 6129.2095 | dt 9.869 +type train | step 3565 | loss 95.6734 187.0332 294.4058 479.4312 708.7763 1032.4493 1454.7489 2100.4390 2952.2078 4573.7271 7536.9062 13288.9180 | lr 2.0e-04 | norm 3616.7791 | dt 9.883 +type train | step 3566 | loss 96.2591 187.7910 294.3763 480.9296 713.7458 1041.4186 1472.4187 2125.4084 2988.3577 4668.3306 7792.4463 13996.6016 | lr 2.0e-04 | norm 4597.7510 | dt 9.872 +type train | step 3567 | loss 92.7002 180.1290 279.8074 456.3731 680.1464 992.9919 1406.9908 2035.7910 2883.1428 4490.8599 7461.0605 13248.4600 | lr 2.0e-04 | norm 4241.6113 | dt 9.860 +type train | step 3568 | loss 99.8705 193.1806 303.3344 494.5020 722.7186 1039.0698 1439.2003 2042.2535 2836.5413 4375.2769 7212.8232 12864.1865 | lr 2.0e-04 | norm 5481.8960 | dt 9.882 +type train | step 3569 | loss 89.6079 172.8347 275.0990 452.5439 676.9971 981.3724 1380.8621 1990.3069 2808.3245 4363.2939 7208.7642 12777.4678 | lr 2.0e-04 | norm 4013.2400 | dt 9.887 +type train | step 3570 | loss 92.9170 184.1248 288.2760 473.9420 703.6501 1027.3313 1444.0884 2076.4688 2910.1882 4487.1680 7364.3589 13041.7734 | lr 2.0e-04 | norm 4301.7036 | dt 9.873 +type train | step 3571 | loss 90.9363 177.0704 284.7823 467.6578 695.6762 1012.8877 1429.8540 2059.2766 2905.0779 4499.6265 7379.5874 13052.3320 | lr 2.0e-04 | norm 3780.2065 | dt 9.872 +type train | step 3572 | loss 93.1844 180.9740 287.5429 471.5396 700.9075 1029.5564 1460.0447 2115.9495 2998.9517 4677.1938 7741.6440 13713.2959 | lr 2.0e-04 | norm 4712.4780 | dt 9.887 +type train | step 3573 | loss 85.9022 167.3016 266.7683 441.3850 664.7218 971.0879 1388.7181 2013.4899 2869.3711 4461.4819 7329.8672 12888.6699 | lr 2.0e-04 | norm 3795.9927 | dt 9.871 +type train | step 3574 | loss 97.2001 188.2055 291.4195 471.1537 697.5866 1013.1022 1428.2535 2065.0596 2911.4001 4478.8936 7358.0386 13063.8965 | lr 2.0e-04 | norm 4100.4849 | dt 9.869 +type train | step 3575 | loss 89.1684 177.7883 282.7964 467.8517 703.7285 1022.7787 1448.4259 2096.8528 2973.3311 4660.4814 7619.6982 13453.8799 | lr 2.0e-04 | norm 6017.4922 | dt 9.883 +type train | step 3576 | loss 89.8007 177.1264 280.3713 466.2249 696.8369 1023.2444 1462.2067 2128.0093 2985.1577 4645.2368 7638.3174 13457.7500 | lr 2.0e-04 | norm 6709.0127 | dt 9.883 +type train | step 3577 | loss 99.0494 193.2731 298.8763 487.5218 720.5635 1059.9204 1502.0955 2169.6287 2983.3804 4585.4302 7532.8838 13355.0459 | lr 2.0e-04 | norm 7131.3369 | dt 9.870 +type train | step 3578 | loss 89.3553 174.2002 274.5031 450.4622 678.0816 988.5782 1403.3073 2037.3680 2901.9333 4500.3530 7346.4375 12869.4385 | lr 2.0e-04 | norm 4048.8889 | dt 9.871 +type train | step 3579 | loss 99.7628 195.4189 303.4210 496.0168 731.7329 1061.6899 1502.1185 2168.2175 3065.3796 4782.9175 7933.6680 14168.4629 | lr 2.0e-04 | norm 4372.5522 | dt 9.861 +type train | step 3580 | loss 96.3056 187.0937 290.6460 474.4991 704.0031 1029.4910 1446.6299 2103.2903 2942.6255 4524.5254 7371.4277 12976.0518 | lr 2.0e-04 | norm 5065.5806 | dt 9.861 +type train | step 3581 | loss 96.7782 190.3401 294.8110 475.9482 703.5654 1030.1764 1454.8832 2102.0891 2958.9106 4573.6660 7486.1606 13180.6748 | lr 2.0e-04 | norm 4269.9990 | dt 9.872 +type train | step 3582 | loss 98.4418 193.8221 299.3001 488.3926 719.2876 1045.7377 1473.4825 2110.7759 2936.5208 4485.0474 7340.1333 12987.8809 | lr 2.0e-04 | norm 4389.6021 | dt 9.875 +type train | step 3583 | loss 95.3543 186.3512 293.3956 482.5292 712.1946 1042.2705 1475.4811 2123.2705 2967.9504 4585.8511 7574.0864 13369.7578 | lr 2.0e-04 | norm 4266.5601 | dt 9.878 +type train | step 3584 | loss 96.9202 187.5132 291.1558 480.2572 707.9533 1040.9707 1472.1364 2127.4548 2969.1733 4554.6206 7497.0190 13145.3447 | lr 2.0e-04 | norm 4267.6182 | dt 9.881 +type train | step 3585 | loss 82.8110 160.7512 262.1740 445.5671 670.3007 988.0664 1406.7867 2053.9600 2924.2915 4559.4873 7577.5640 13583.8037 | lr 2.0e-04 | norm 5615.3652 | dt 9.863 +type train | step 3586 | loss 90.7648 176.2308 278.3311 462.3964 692.8274 1019.5369 1447.3041 2100.0020 2968.8533 4635.2896 7617.3511 13453.9863 | lr 2.0e-04 | norm 4179.5615 | dt 9.854 +type train | step 3587 | loss 94.9914 187.4312 294.0634 482.2076 715.7247 1033.2256 1451.9188 2076.1538 2929.6343 4526.0864 7457.4961 13220.7139 | lr 2.0e-04 | norm 4180.4229 | dt 9.871 +type train | step 3588 | loss 91.5258 176.1428 280.7849 460.6959 689.0204 1010.4107 1431.5371 2081.8721 2929.6426 4552.3716 7515.6040 13250.0967 | lr 2.0e-04 | norm 4378.2886 | dt 9.884 +type train | step 3589 | loss 99.3965 195.5105 309.4807 506.5660 746.8859 1081.2151 1513.0255 2161.5720 3014.5913 4628.6084 7542.1309 13470.0742 | lr 2.0e-04 | norm 5757.7769 | dt 9.883 +type train | step 3590 | loss 87.9599 169.6474 272.8324 452.0967 683.8069 1007.7598 1440.5853 2114.9917 3008.9182 4708.9785 7781.3408 13687.0322 | lr 2.0e-04 | norm 6096.1416 | dt 9.886 +type train | step 3591 | loss 94.6751 182.7449 287.7283 472.7515 701.0683 1019.2949 1440.5262 2079.1904 2917.6016 4528.6802 7533.3418 13418.2129 | lr 2.0e-04 | norm 4837.9946 | dt 9.900 +type train | step 3592 | loss 90.4891 176.2815 278.0462 460.8516 688.9919 1011.9984 1435.6350 2098.5005 2963.5552 4611.8560 7637.1299 13467.0840 | lr 2.0e-04 | norm 4415.6621 | dt 9.872 +type train | step 3593 | loss 93.9278 184.4984 288.0626 469.2549 703.1832 1019.8421 1433.7601 2068.4268 2931.2744 4535.9229 7447.9995 13045.5059 | lr 2.0e-04 | norm 4589.4663 | dt 9.898 +type train | step 3594 | loss 89.0201 173.3408 276.6920 455.8065 680.6263 991.4808 1401.2358 2035.2346 2883.7175 4477.8940 7358.8848 12980.0625 | lr 2.0e-04 | norm 3707.4041 | dt 9.890 +type train | step 3595 | loss 100.7142 199.3035 306.5412 496.4902 726.0317 1064.4591 1511.5403 2191.4312 3054.3230 4695.2896 7787.6255 13874.8887 | lr 2.0e-04 | norm 7884.3564 | dt 9.853 +type train | step 3596 | loss 104.0312 205.6005 318.3566 509.9118 749.2990 1082.5109 1524.3972 2178.3735 3035.9409 4677.5825 7650.6738 13528.1592 | lr 2.0e-04 | norm 5382.5156 | dt 9.869 +type train | step 3597 | loss 94.8843 183.9198 289.8128 475.2946 706.1658 1023.9579 1439.3546 2071.4219 2923.1467 4553.0005 7526.0923 13304.4922 | lr 2.0e-04 | norm 3934.5352 | dt 9.886 +type train | step 3598 | loss 99.4206 196.7851 302.4408 491.3405 728.2459 1055.3779 1479.4001 2113.0049 2968.0640 4598.4551 7624.2734 13540.9141 | lr 2.0e-04 | norm 3885.8574 | dt 9.878 +type train | step 3599 | loss 84.4290 166.1535 266.0785 446.7347 675.4886 989.0785 1416.1121 2056.8445 2912.8872 4571.3018 7604.4624 13659.7295 | lr 2.0e-04 | norm 6360.3018 | dt 9.872 +type train | step 3600 | loss 96.9707 191.7064 302.4345 495.4277 726.6991 1050.0253 1475.5614 2122.1465 2972.5349 4605.2729 7594.8354 13459.8574 | lr 2.0e-04 | norm 4794.8589 | dt 9.853 +type train | step 3601 | loss 95.1016 186.6050 295.7485 487.3799 725.4596 1055.7393 1488.8499 2155.9827 3038.4788 4697.9966 7699.7026 13564.1270 | lr 2.0e-04 | norm 4655.4756 | dt 9.871 +type train | step 3602 | loss 110.0882 216.1846 330.5587 528.3231 767.6270 1103.8616 1543.7756 2202.2783 3096.7979 4823.4053 7983.4775 14294.9014 | lr 2.0e-04 | norm 6196.2549 | dt 9.874 +type train | step 3603 | loss 94.6997 185.7089 291.8288 478.7183 709.7510 1034.5482 1456.0801 2088.7161 2938.9934 4508.1167 7415.9214 13103.1680 | lr 2.0e-04 | norm 3876.7881 | dt 9.906 +type train | step 3604 | loss 91.0874 178.3924 281.5444 462.1527 689.1145 1016.5575 1433.4443 2093.7939 2941.2080 4560.7339 7542.6201 13302.8564 | lr 2.0e-04 | norm 4534.4014 | dt 9.893 +type train | step 3605 | loss 90.9995 181.9942 286.3700 474.4197 710.2431 1021.3163 1446.1362 2075.7803 2951.3757 4580.7900 7528.9312 13327.3057 | lr 2.0e-04 | norm 6380.2222 | dt 9.880 +type train | step 3606 | loss 90.8459 178.1112 283.6832 469.5930 703.2908 1024.7220 1450.4166 2097.3799 2967.7676 4624.2358 7642.8447 13553.9229 | lr 2.0e-04 | norm 5012.7046 | dt 9.864 +type train | step 3607 | loss 90.4044 176.0352 279.5147 457.6216 681.5682 987.5313 1397.6456 2014.6790 2868.0732 4478.4170 7419.5986 13134.5850 | lr 2.0e-04 | norm 4468.5737 | dt 9.883 +type train | step 3608 | loss 96.2384 189.7530 295.8995 484.8007 716.6398 1047.0095 1457.2684 2114.5283 2952.9819 4594.2383 7665.2637 13647.3799 | lr 2.0e-04 | norm 7378.6606 | dt 9.859 +type train | step 3609 | loss 91.9024 179.9461 282.0188 462.4069 688.7277 1008.1801 1425.5693 2061.7058 2905.6921 4504.6650 7425.6714 13134.4814 | lr 2.0e-04 | norm 4109.1812 | dt 9.875 +type train | step 3610 | loss 91.2756 177.1029 276.3401 455.8586 679.1091 992.0363 1404.0911 2032.7557 2875.5818 4509.3975 7499.4414 13293.0088 | lr 2.0e-04 | norm 4905.0303 | dt 9.869 +type train | step 3611 | loss 95.3349 187.9080 297.5622 485.9240 720.1682 1048.4547 1482.8884 2139.3826 3030.0557 4742.5830 7865.2500 14058.8984 | lr 2.0e-04 | norm 5732.3550 | dt 9.863 +type train | step 3612 | loss 94.4052 187.0969 293.3927 477.9665 710.6406 1030.8124 1454.5784 2097.4548 2971.6912 4612.3032 7589.6309 13522.0449 | lr 2.0e-04 | norm 4977.2314 | dt 9.885 +type train | step 3613 | loss 91.4539 178.1410 285.8272 470.9083 702.2135 1026.0020 1451.8561 2097.4736 2975.3210 4588.1787 7587.7817 13528.0527 | lr 2.0e-04 | norm 4648.0122 | dt 9.864 +type train | step 3614 | loss 95.7098 186.1578 291.1462 474.3983 706.3798 1020.5258 1442.0692 2072.0474 2928.0217 4535.2539 7449.1943 13126.6113 | lr 2.0e-04 | norm 4223.4375 | dt 9.875 +type train | step 3615 | loss 93.4286 182.7174 287.8920 469.9862 696.5009 1014.2795 1431.1436 2061.8745 2906.4675 4509.5483 7447.1885 13147.5420 | lr 2.0e-04 | norm 3767.2280 | dt 9.874 +type train | step 3616 | loss 91.7381 181.2941 288.7442 478.6397 713.9481 1037.2076 1461.6444 2117.9714 2998.4019 4649.6665 7652.6816 13403.0225 | lr 2.0e-04 | norm 4090.7534 | dt 9.875 +type train | step 3617 | loss 89.9150 175.2301 276.4836 456.5949 683.9451 998.2956 1417.1127 2060.7461 2928.6667 4580.2412 7579.6362 13378.2715 | lr 2.0e-04 | norm 4317.4697 | dt 9.857 +type train | step 3618 | loss 108.3307 209.2455 317.6479 513.1941 745.8727 1089.3722 1532.4708 2199.8962 3034.7651 4667.5283 7676.5840 13521.1309 | lr 2.0e-04 | norm 4147.6167 | dt 9.868 +type train | step 3619 | loss 89.1215 173.9888 276.2651 455.4646 682.4110 998.9093 1418.7708 2058.6799 2928.4001 4566.9795 7587.2769 13458.9160 | lr 2.0e-04 | norm 3755.7275 | dt 9.883 +type train | step 3620 | loss 87.0182 168.3453 269.5985 449.1349 678.0573 991.2874 1413.5385 2046.6992 2909.0691 4524.9121 7441.4126 13171.0703 | lr 2.0e-04 | norm 5768.8477 | dt 9.879 +type train | step 3621 | loss 95.9344 188.7218 297.2957 487.8583 718.8641 1044.5729 1464.8445 2103.7922 2917.8904 4538.8594 7523.9336 13467.1172 | lr 2.0e-04 | norm 5454.7524 | dt 9.850 +type train | step 3622 | loss 92.2222 177.6191 279.5323 457.5757 682.5463 990.4607 1400.6400 2017.8657 2840.4482 4395.6562 7225.7256 12737.0996 | lr 2.0e-04 | norm 3957.5901 | dt 9.861 +type train | step 3623 | loss 94.0374 184.9285 286.2638 465.9585 690.7932 998.4302 1405.9138 2018.8494 2848.4019 4416.6455 7243.0991 12824.6133 | lr 1.9e-04 | norm 3987.8057 | dt 9.871 +type train | step 3624 | loss 103.3375 202.0054 310.0211 509.5707 740.4012 1065.7040 1483.6587 2115.4441 2931.6987 4514.4277 7465.7192 13385.3662 | lr 1.9e-04 | norm 5440.6621 | dt 9.862 +type train | step 3625 | loss 98.3415 192.4553 301.0597 487.8338 717.6580 1040.6169 1464.9246 2100.2393 2948.5515 4591.3794 7598.3599 13586.7852 | lr 1.9e-04 | norm 4157.3945 | dt 9.876 +type train | step 3626 | loss 87.4978 169.8197 273.4636 454.2026 682.2859 1000.8883 1421.4401 2069.6296 2932.6562 4541.2378 7479.0698 13172.2861 | lr 1.9e-04 | norm 4779.1787 | dt 9.870 +type train | step 3627 | loss 89.8156 174.4586 278.4250 459.7805 686.8865 1002.1386 1422.3073 2052.2874 2906.2998 4509.2705 7455.0732 13159.7480 | lr 1.9e-04 | norm 4426.7686 | dt 9.869 +type train | step 3628 | loss 92.1999 182.5378 291.4046 482.4015 720.2072 1039.7585 1461.7231 2092.3777 2956.7849 4565.3442 7547.3481 13350.5264 | lr 1.9e-04 | norm 4212.5737 | dt 9.866 +type train | step 3629 | loss 81.3005 156.3833 251.2572 420.5949 641.8118 957.2862 1389.3220 2067.8589 2977.6506 4642.8779 7568.4668 13280.0752 | lr 1.9e-04 | norm 5511.4639 | dt 9.840 +type train | step 3630 | loss 88.9748 170.9150 270.1983 447.0809 670.5279 980.2593 1393.9817 2018.0676 2877.1667 4486.5610 7452.9482 13226.8535 | lr 1.9e-04 | norm 5256.0327 | dt 9.858 +type train | step 3631 | loss 91.4021 177.7990 279.4489 460.4799 685.5142 999.9288 1413.9011 2046.7539 2894.2717 4484.9360 7400.2510 13009.8389 | lr 1.9e-04 | norm 4552.4878 | dt 9.888 +type train | step 3632 | loss 95.6452 185.1157 287.9650 469.9470 694.1429 1010.6851 1419.9635 2048.9915 2887.5430 4476.0723 7350.8423 12933.6465 | lr 1.9e-04 | norm 4138.9658 | dt 9.889 +type train | step 3633 | loss 92.7140 179.3514 283.3583 464.4715 690.5475 1001.2805 1414.0785 2046.5852 2894.5850 4500.7822 7428.1729 13160.2168 | lr 1.9e-04 | norm 3924.5203 | dt 9.876 +type train | step 3634 | loss 91.7669 180.3924 285.4343 476.6898 708.0333 1032.1239 1454.7091 2110.7083 2974.0144 4618.4629 7654.5127 13690.4824 | lr 1.9e-04 | norm 5271.1694 | dt 9.878 +type train | step 3635 | loss 95.9114 187.6183 296.0129 482.6892 711.8509 1032.0786 1452.8188 2084.4619 2936.1841 4560.3066 7503.2637 13239.0557 | lr 1.9e-04 | norm 3697.8872 | dt 9.883 +type train | step 3636 | loss 91.6430 179.0527 281.9606 463.9249 689.0638 996.6818 1409.2968 2030.5782 2879.2720 4475.8594 7415.6943 13155.2402 | lr 1.9e-04 | norm 4146.8228 | dt 9.888 +type train | step 3637 | loss 97.6856 189.8104 289.1774 472.4504 697.2062 1026.6316 1447.1373 2103.0320 2947.4692 4521.7607 7419.8706 13057.3965 | lr 1.9e-04 | norm 4461.6313 | dt 9.863 +type train | step 3638 | loss 107.6758 213.3490 328.7308 526.4733 760.2392 1109.4988 1555.1874 2226.0703 3040.7607 4642.7993 7660.9487 13600.2666 | lr 1.9e-04 | norm 11065.2021 | dt 9.894 +type train | step 3639 | loss 111.9972 218.9335 334.5558 531.5121 768.1691 1107.1680 1548.4250 2207.5576 3027.5693 4616.6665 7560.2314 13275.2256 | lr 1.9e-04 | norm 8358.3457 | dt 9.890 +type train | step 3640 | loss 95.0497 184.9680 292.5305 482.1902 715.1610 1047.7183 1479.5409 2133.9463 2988.7493 4623.5596 7631.8574 13485.7002 | lr 1.9e-04 | norm 4759.5371 | dt 9.888 +type train | step 3641 | loss 94.3196 185.5381 288.0935 470.0723 697.7318 1022.0801 1442.2544 2086.9297 2920.7869 4543.3628 7563.7725 13422.7617 | lr 1.9e-04 | norm 4745.1094 | dt 9.877 +type train | step 3642 | loss 90.6563 176.7525 280.1827 461.3520 686.2881 998.1196 1414.7510 2035.4922 2882.5908 4465.8013 7373.0063 13018.2051 | lr 1.9e-04 | norm 4005.5164 | dt 9.893 +type train | step 3643 | loss 96.9810 190.0309 296.9553 481.1248 707.5128 1017.3324 1425.1816 2037.2483 2855.5037 4404.7983 7260.0776 12843.5176 | lr 1.9e-04 | norm 4300.1787 | dt 9.897 +type train | step 3644 | loss 91.0721 177.2145 281.1674 463.2165 689.9991 1005.0929 1422.2748 2055.5632 2926.6196 4554.3154 7562.8154 13444.6455 | lr 1.9e-04 | norm 4014.5930 | dt 9.911 +type train | step 3645 | loss 92.6750 179.3410 281.6400 462.6796 687.2565 1003.1799 1416.0604 2042.1570 2891.9377 4516.3066 7525.5342 13413.2109 | lr 1.9e-04 | norm 3990.4731 | dt 9.891 +type train | step 3646 | loss 94.9772 185.9649 292.1366 478.9463 710.0036 1036.2406 1452.8883 2082.2615 2938.8057 4512.9360 7399.8721 12938.8369 | lr 1.9e-04 | norm 3483.0730 | dt 9.911 +type train | step 3647 | loss 107.6342 212.1821 329.1092 535.7409 787.1232 1125.9468 1556.7516 2209.5854 3015.3867 4634.4023 7618.9248 13593.1699 | lr 1.9e-04 | norm 9233.2383 | dt 9.853 +type train | step 3648 | loss 94.1651 185.3085 292.1326 476.3880 705.2908 1020.7898 1437.8630 2061.8201 2917.1533 4529.9531 7468.3691 13212.4688 | lr 1.9e-04 | norm 3941.3206 | dt 9.890 +type train | step 3649 | loss 90.8632 175.2485 276.6439 454.4763 682.2137 998.9075 1418.3468 2061.5044 2906.2908 4530.0718 7485.4150 13224.2373 | lr 1.9e-04 | norm 4701.3784 | dt 9.872 +type train | step 3650 | loss 91.5251 176.8361 278.8835 461.5988 692.5215 1019.5331 1447.7485 2101.2112 2966.2939 4609.9292 7587.4180 13424.2578 | lr 1.9e-04 | norm 4283.5161 | dt 9.879 +type train | step 3651 | loss 88.8967 173.3894 274.6634 452.5867 677.8967 987.3229 1401.2551 2022.3033 2879.1680 4475.2910 7405.0786 13055.6797 | lr 1.9e-04 | norm 3698.5713 | dt 9.880 +type train | step 3652 | loss 111.5838 229.9032 359.5464 594.0706 870.8408 1306.7781 1834.3138 2730.2087 3709.8481 5635.6245 9018.3633 15733.9355 | lr 1.9e-04 | norm 10875.1650 | dt 9.834 +type train | step 3653 | loss 94.3120 183.1738 292.9170 481.2354 707.3824 1022.1723 1442.7621 2078.3235 2901.1245 4488.9937 7411.6528 13119.4404 | lr 1.9e-04 | norm 5830.5557 | dt 9.869 +type train | step 3654 | loss 94.2835 184.5970 286.5808 466.9681 693.5709 1030.6769 1467.5928 2144.7288 3013.0059 4683.6753 7776.7124 13782.0264 | lr 1.9e-04 | norm 5505.4673 | dt 9.860 +type train | step 3655 | loss 85.6067 167.4804 263.8015 441.3311 661.1151 971.1829 1377.3300 1998.9735 2821.9768 4429.7681 7382.6416 13174.4873 | lr 1.9e-04 | norm 6507.5542 | dt 9.859 +type train | step 3656 | loss 98.3171 188.4752 284.9405 465.7391 688.1849 1011.9975 1422.6946 2054.1250 2851.0046 4374.3833 7121.7495 12499.6152 | lr 1.9e-04 | norm 5199.3828 | dt 9.849 +type train | step 3657 | loss 96.4844 187.9126 296.9775 485.5858 718.9888 1045.0529 1467.4271 2108.6001 2948.8108 4570.0166 7592.6099 13584.4258 | lr 1.9e-04 | norm 7436.1079 | dt 9.859 +type train | step 3658 | loss 96.3738 188.2294 293.0349 476.7316 706.9733 1026.0676 1443.8015 2070.0471 2925.6321 4533.8154 7494.5903 13213.2305 | lr 1.9e-04 | norm 4319.0269 | dt 9.864 +type train | step 3659 | loss 90.3584 176.6182 279.0896 459.5549 683.5416 993.0420 1408.7864 2038.9907 2874.6169 4493.2646 7472.1460 13206.5801 | lr 1.9e-04 | norm 4230.1187 | dt 9.860 +type train | step 3660 | loss 97.9387 191.0441 295.5606 483.2275 711.7991 1030.7567 1446.3374 2077.2571 2912.6780 4537.9580 7491.5059 13328.0146 | lr 1.9e-04 | norm 3954.5969 | dt 9.863 +type train | step 3661 | loss 92.1354 178.2797 280.9426 464.3242 689.7911 1018.7104 1445.0444 2106.3340 2969.9182 4582.5625 7553.5278 13443.9570 | lr 1.9e-04 | norm 4808.5210 | dt 9.869 +type train | step 3662 | loss 99.2698 196.9891 306.7682 499.6339 737.0903 1058.8770 1476.3943 2106.6021 2942.9192 4494.8081 7365.8335 12955.3994 | lr 1.9e-04 | norm 5935.6187 | dt 9.889 +type train | step 3663 | loss 95.8988 187.2757 291.8863 476.7047 706.2316 1021.4896 1430.7009 2055.1614 2883.8708 4439.2295 7289.3423 12896.5625 | lr 1.9e-04 | norm 3873.9072 | dt 9.876 +type train | step 3664 | loss 87.1998 170.0020 269.4485 446.4573 670.5544 984.4434 1403.1915 2040.1761 2908.5273 4527.8691 7530.5869 13408.1992 | lr 1.9e-04 | norm 4212.3516 | dt 9.868 +type train | step 3665 | loss 95.5853 183.3597 284.5684 466.3470 693.2747 1012.4322 1433.7614 2074.6375 2913.9824 4509.8979 7423.0312 13140.7598 | lr 1.9e-04 | norm 4327.4185 | dt 9.860 +type train | step 3666 | loss 87.6511 169.8036 268.8679 445.5289 667.3891 975.4501 1384.0735 2002.9333 2844.5720 4439.5405 7360.0366 13075.9912 | lr 1.9e-04 | norm 3770.6094 | dt 9.871 +type train | step 3667 | loss 94.8609 186.6246 291.8625 476.7839 703.8983 1026.1801 1451.8567 2093.0146 2960.4233 4606.9258 7662.0303 13637.9961 | lr 1.9e-04 | norm 4186.5327 | dt 9.881 +type train | step 3668 | loss 90.8279 176.9351 276.5656 454.6884 679.3691 986.1504 1396.6580 2023.9517 2865.6858 4449.1948 7336.6729 12925.3447 | lr 1.9e-04 | norm 4268.8174 | dt 9.879 +type train | step 3669 | loss 90.3060 173.4181 276.5759 456.2045 683.3804 1001.5071 1414.7710 2047.2852 2884.7048 4488.2515 7411.1172 13057.8545 | lr 1.9e-04 | norm 4448.8535 | dt 9.864 +type train | step 3670 | loss 93.6863 181.3798 285.1480 463.7561 690.3528 1002.8192 1409.7426 2029.2074 2864.7563 4427.2656 7256.1587 12660.4414 | lr 1.9e-04 | norm 3913.5962 | dt 9.889 +type train | step 3671 | loss 94.4146 183.5921 290.1528 473.1145 698.8904 1013.8787 1422.3258 2032.8129 2852.0386 4406.2529 7299.8564 12951.3008 | lr 1.9e-04 | norm 4181.5742 | dt 9.871 +type train | step 3672 | loss 92.7799 182.0020 285.5305 467.1467 696.2864 1013.1064 1431.1843 2059.6147 2914.9429 4526.6470 7444.0986 13098.6182 | lr 1.9e-04 | norm 3552.3303 | dt 9.885 +type train | step 3673 | loss 92.9544 182.4463 288.5979 474.2667 704.1373 1020.4890 1439.0183 2070.2539 2925.8030 4526.8647 7452.8003 13047.5283 | lr 1.9e-04 | norm 4109.1919 | dt 9.861 +type train | step 3674 | loss 97.5806 189.4266 295.8058 486.1684 714.7177 1040.4218 1457.8773 2093.0027 2906.5391 4445.9727 7336.0054 12961.2969 | lr 1.9e-04 | norm 4505.5635 | dt 9.863 +type train | step 3675 | loss 93.9525 180.2018 288.9018 472.2228 698.1953 1009.3752 1413.4237 2026.7009 2839.3330 4390.6797 7273.9170 13028.0244 | lr 1.9e-04 | norm 4806.4565 | dt 9.862 +type train | step 3676 | loss 93.8547 183.7513 287.4197 473.4581 697.2861 1014.5051 1429.2557 2059.9517 2885.6572 4484.6689 7438.9536 13150.5332 | lr 1.9e-04 | norm 3711.5195 | dt 9.885 +type train | step 3677 | loss 96.5926 188.1116 292.3194 477.7231 704.9852 1030.5377 1447.4253 2092.4255 2925.0447 4522.8892 7517.4141 13270.9883 | lr 1.9e-04 | norm 3794.9268 | dt 9.861 +type train | step 3678 | loss 94.3265 184.9655 288.0038 471.1037 695.7862 1013.9730 1421.4585 2045.9354 2875.7751 4483.7876 7423.2188 13212.4150 | lr 1.9e-04 | norm 4555.2251 | dt 9.861 +type train | step 3679 | loss 92.0322 179.3641 284.0107 464.7158 694.6274 1021.6389 1454.0593 2109.6428 2970.7344 4617.2930 7613.0132 13580.2549 | lr 1.9e-04 | norm 5491.8296 | dt 9.861 +type train | step 3680 | loss 94.4676 182.6370 287.6474 474.3659 706.1547 1026.5895 1447.6282 2080.8462 2941.1194 4569.9019 7536.2324 13353.6465 | lr 1.9e-04 | norm 3814.2332 | dt 9.872 +type train | step 3681 | loss 95.5839 185.6459 295.5701 480.8959 713.1223 1027.4841 1444.9349 2063.4692 2887.7778 4442.5234 7317.4268 12984.0098 | lr 1.9e-04 | norm 5282.5303 | dt 9.910 +type train | step 3682 | loss 93.9960 184.3887 291.4195 476.5308 706.5634 1024.5177 1441.6145 2066.5659 2915.0962 4501.2612 7414.9746 13010.9814 | lr 1.9e-04 | norm 3837.7080 | dt 9.915 +type train | step 3683 | loss 93.4800 182.1606 285.9584 471.7906 697.8049 1014.9252 1423.6279 2051.0474 2873.1069 4437.5781 7303.6997 12859.9590 | lr 1.9e-04 | norm 4081.5095 | dt 9.878 +type train | step 3684 | loss 89.6135 174.4027 277.1964 456.8452 682.0251 988.1144 1396.0096 2012.5254 2847.5718 4401.9966 7264.2671 12771.8721 | lr 1.9e-04 | norm 4019.2451 | dt 9.882 +type train | step 3685 | loss 91.0560 179.0632 281.7461 462.0650 687.9239 1002.2665 1416.7761 2041.4846 2883.4993 4478.3018 7381.8589 13098.8740 | lr 1.9e-04 | norm 3827.3547 | dt 9.892 +type train | step 3686 | loss 89.5090 173.5654 272.6892 450.1884 669.7903 981.8982 1387.6648 2010.1597 2845.6511 4449.6606 7339.1323 13033.4785 | lr 1.9e-04 | norm 4154.8877 | dt 9.898 +type train | step 3687 | loss 98.1875 191.4319 294.8338 477.6659 705.3259 1031.7502 1456.4355 2102.7859 2942.4321 4585.2085 7591.0376 13430.3594 | lr 1.9e-04 | norm 4692.4424 | dt 9.878 +type train | step 3688 | loss 92.0104 178.6086 281.1476 462.1247 685.6919 997.3387 1410.0355 2024.2883 2846.0869 4403.0728 7279.1494 12788.1719 | lr 1.9e-04 | norm 3939.9431 | dt 9.884 +type train | step 3689 | loss 95.4762 189.6745 300.6760 492.9373 728.2101 1046.8616 1465.5647 2090.9583 2940.9138 4513.4487 7350.8350 12943.2891 | lr 1.9e-04 | norm 3857.5469 | dt 9.879 +type train | step 3690 | loss 101.6103 198.4382 307.7722 503.4451 737.2077 1069.3118 1496.9092 2147.4858 2960.8169 4560.9824 7507.4336 13383.4297 | lr 1.9e-04 | norm 4609.8330 | dt 9.875 +type train | step 3691 | loss 94.2479 182.3261 283.5173 465.9791 692.3729 1012.3753 1427.8330 2052.4075 2873.7952 4431.8877 7332.3271 12999.1328 | lr 1.9e-04 | norm 4247.4985 | dt 9.886 +type train | step 3692 | loss 90.1191 175.4000 279.7630 461.2270 688.0970 1000.5176 1415.9214 2051.3445 2898.1196 4487.9150 7421.2109 13065.6904 | lr 1.9e-04 | norm 3617.1387 | dt 9.894 +type train | step 3693 | loss 90.1259 175.9152 282.9536 472.2720 707.1429 1041.1870 1480.7040 2160.9998 3052.2195 4747.5024 7855.0298 13823.3281 | lr 1.9e-04 | norm 4420.8335 | dt 9.884 +type train | step 3694 | loss 89.1991 171.7507 275.6798 458.4008 683.3770 1003.5319 1426.7035 2068.6453 2913.6870 4539.8047 7534.5996 13334.6475 | lr 1.9e-04 | norm 4349.6284 | dt 9.864 +type train | step 3695 | loss 91.6645 179.2841 284.5074 471.1519 701.7715 1021.5458 1445.4923 2080.0327 2935.6091 4537.2339 7516.8008 13326.6836 | lr 1.9e-04 | norm 3796.1174 | dt 9.894 +type train | step 3696 | loss 95.4513 186.8083 292.0710 476.3459 700.3787 1011.0263 1422.2946 2041.0784 2859.5303 4399.0781 7227.2637 12689.5312 | lr 1.9e-04 | norm 3812.8000 | dt 9.881 +type train | step 3697 | loss 87.0705 167.0516 265.9314 441.7966 666.8951 974.4276 1388.3179 2011.8636 2857.4736 4452.4980 7374.8335 13015.3467 | lr 1.9e-04 | norm 4067.7126 | dt 9.861 +type train | step 3698 | loss 88.6108 172.9816 272.8550 450.3253 673.7642 979.7409 1384.3376 2000.0236 2833.4236 4426.0425 7309.8457 12878.7539 | lr 1.9e-04 | norm 3496.3210 | dt 9.873 +type train | step 3699 | loss 93.6772 182.4967 289.7297 479.2092 714.4178 1048.2343 1478.6721 2139.6008 3020.0676 4672.4453 7641.0845 13383.8262 | lr 1.9e-04 | norm 3614.6702 | dt 9.877 +type train | step 3700 | loss 92.9343 179.5253 283.5756 466.6384 690.2702 1001.9044 1408.5713 2027.7687 2845.9922 4432.5815 7414.0771 13249.2275 | lr 1.9e-04 | norm 4189.9731 | dt 9.869 +type train | step 3701 | loss 94.6821 184.0369 288.7318 470.9055 694.1617 1012.8654 1431.2213 2071.8687 2906.0139 4503.9424 7429.2319 13133.4648 | lr 1.9e-04 | norm 3892.4675 | dt 9.875 +type train | step 3702 | loss 97.9118 190.2544 299.4541 493.2137 732.5812 1063.6906 1498.8232 2153.7292 3046.9404 4728.8623 7793.9453 13724.5479 | lr 1.9e-04 | norm 4059.9585 | dt 9.874 +type train | step 3703 | loss 98.1233 193.2935 296.3202 481.5042 713.6062 1049.7797 1481.6366 2153.8047 3002.0159 4643.8096 7630.2505 13461.6035 | lr 1.9e-04 | norm 4214.0474 | dt 9.894 +type train | step 3704 | loss 91.4299 177.5274 279.5280 459.5562 684.4575 1000.9280 1415.0533 2046.6373 2889.6384 4494.8037 7445.9189 13204.7568 | lr 1.8e-04 | norm 3769.3232 | dt 9.882 +type train | step 3705 | loss 95.7978 186.8624 289.2826 472.2982 697.4077 1015.0433 1429.7943 2068.7751 2897.8960 4501.2998 7476.4180 13295.0820 | lr 1.8e-04 | norm 3729.1282 | dt 9.882 +type train | step 3706 | loss 90.4638 177.1208 278.2242 456.9508 681.6856 994.6302 1409.7036 2048.3638 2896.5005 4525.5010 7445.0610 13004.2783 | lr 1.8e-04 | norm 3595.7007 | dt 9.871 +type train | step 3707 | loss 95.1527 185.5638 292.0960 477.8017 709.6071 1032.1245 1460.6387 2111.6348 2973.9353 4604.4795 7565.3213 13317.7871 | lr 1.8e-04 | norm 4432.2461 | dt 9.876 +type train | step 3708 | loss 92.9221 186.6166 303.2399 505.8594 744.3804 1070.9517 1484.8962 2107.0107 2963.0391 4558.1514 7528.7402 13274.6914 | lr 1.8e-04 | norm 6264.5322 | dt 9.868 +type train | step 3709 | loss 88.2544 172.9619 274.1015 453.5428 681.9885 1003.3179 1424.8198 2070.5452 2928.9102 4561.3535 7542.8438 13273.9355 | lr 1.8e-04 | norm 3875.6479 | dt 9.857 +type train | step 3710 | loss 100.4297 195.7136 307.6044 500.3130 736.6174 1086.0673 1531.2280 2202.0552 3079.2480 4750.9609 7699.1260 13369.7725 | lr 1.8e-04 | norm 6340.7817 | dt 9.877 +type train | step 3711 | loss 87.7818 173.0829 277.8391 460.8704 693.1346 1008.5933 1430.7316 2071.4910 2937.6042 4556.0059 7446.0298 13056.8740 | lr 1.8e-04 | norm 5225.5112 | dt 9.860 +type train | step 3712 | loss 97.5543 189.9186 301.7646 491.5206 722.5129 1043.3781 1464.6694 2095.6072 2959.9255 4560.8047 7525.4673 13281.2178 | lr 1.8e-04 | norm 4759.8369 | dt 9.877 +type train | step 3713 | loss 91.5852 177.9069 285.6227 474.7590 703.0948 1017.8170 1437.2540 2070.6892 2914.9006 4534.7905 7517.9526 13521.0635 | lr 1.8e-04 | norm 5420.5215 | dt 9.857 +type train | step 3714 | loss 98.7466 194.3139 304.4008 497.6369 737.3603 1060.4917 1488.9204 2137.0269 3030.1355 4737.5195 7860.5347 13956.2178 | lr 1.8e-04 | norm 5286.8281 | dt 9.880 +type train | step 3715 | loss 96.3165 188.3465 295.5766 483.9162 718.1441 1037.5717 1452.9830 2077.3655 2932.7178 4505.0820 7410.7759 13043.3057 | lr 1.8e-04 | norm 3805.2471 | dt 9.892 +type train | step 3716 | loss 98.4642 194.8102 304.7255 501.6052 741.2839 1075.2701 1507.4741 2169.6157 3050.0493 4691.4590 7713.8994 13562.5020 | lr 1.8e-04 | norm 4277.9194 | dt 9.876 +type train | step 3717 | loss 98.5440 195.3383 307.6830 505.1001 748.0220 1075.3392 1508.0085 2159.6995 3035.0527 4690.2432 7795.8872 13808.5947 | lr 1.8e-04 | norm 4913.4048 | dt 9.876 +type train | step 3718 | loss 109.9897 219.0363 333.1212 528.7264 777.3286 1123.5431 1578.1926 2236.8352 3134.5525 4786.9351 7760.1812 13547.2256 | lr 1.8e-04 | norm 4414.3975 | dt 9.866 +type train | step 3719 | loss 100.6130 200.3853 316.1571 515.9441 757.9332 1094.2494 1527.9438 2170.5061 3023.9561 4662.7695 7627.0098 13572.3213 | lr 1.8e-04 | norm 4427.7266 | dt 9.878 +type train | step 3720 | loss 97.5028 191.4850 300.8084 490.2383 725.3848 1050.2743 1478.2677 2112.7212 2979.0750 4603.4424 7603.3325 13495.2197 | lr 1.8e-04 | norm 3560.1990 | dt 9.878 +type train | step 3721 | loss 94.4693 193.6331 314.7913 523.2960 773.0082 1110.0708 1563.2843 2242.5820 3192.3433 4945.3452 8183.5879 14462.8838 | lr 1.8e-04 | norm 8486.1084 | dt 9.856 +type train | step 3722 | loss 99.5416 197.9411 309.9631 500.7923 738.4855 1054.2769 1470.7405 2091.9797 2946.6499 4529.4253 7413.7510 13021.4111 | lr 1.8e-04 | norm 3983.9773 | dt 9.889 +type train | step 3723 | loss 93.6446 184.5311 290.9485 476.7821 707.0458 1028.3511 1447.7798 2077.1887 2924.0547 4526.8809 7493.3101 13263.7939 | lr 1.8e-04 | norm 4192.5620 | dt 10.180 +type train | step 3724 | loss 97.7969 196.9255 320.1495 527.9930 776.5555 1119.4467 1566.1017 2236.1204 3143.4290 4846.5771 7997.0176 14309.5244 | lr 1.8e-04 | norm 5507.2061 | dt 9.881 +type train | step 3725 | loss 95.9479 188.2818 302.1335 498.1435 742.1279 1065.4768 1493.9592 2133.1023 3007.4443 4634.0400 7680.9580 13715.3516 | lr 1.8e-04 | norm 3956.9336 | dt 9.894 +type train | step 3726 | loss 95.8186 190.3896 301.6552 490.7776 729.7099 1055.5914 1488.7799 2136.4790 3015.5149 4677.6562 7777.3804 13837.0010 | lr 1.8e-04 | norm 4830.2686 | dt 9.890 +type train | step 3727 | loss 110.2270 212.3319 325.8084 523.1346 761.5891 1084.4685 1508.4376 2133.2615 2973.7729 4607.4082 7707.9219 13909.9736 | lr 1.8e-04 | norm 8321.7832 | dt 9.867 +type train | step 3728 | loss 103.4176 204.7861 317.6454 518.5585 749.0159 1075.2611 1487.9254 2104.5745 2896.1594 4446.9443 7304.0283 12970.7051 | lr 1.8e-04 | norm 4773.2593 | dt 9.868 +type train | step 3729 | loss 106.3758 212.0748 328.1848 529.4116 774.5595 1125.6042 1576.3195 2258.4224 3142.9583 4810.5327 7914.8086 13927.3984 | lr 1.8e-04 | norm 5304.0947 | dt 9.870 +type train | step 3730 | loss 100.7138 196.8591 306.3386 496.8683 729.2030 1051.5786 1462.7747 2081.4753 2906.0884 4459.2617 7309.0312 12906.3525 | lr 1.8e-04 | norm 3839.8167 | dt 9.879 +type train | step 3731 | loss 98.5048 192.1543 301.9336 493.7112 730.5314 1048.3571 1472.0210 2100.9653 2948.0544 4542.0527 7455.0913 13204.2305 | lr 1.8e-04 | norm 4680.0571 | dt 9.880 +type train | step 3732 | loss 93.5842 185.4093 299.2864 497.8845 741.3696 1076.3396 1512.4907 2166.9436 3051.7424 4697.6206 7734.2109 13672.9580 | lr 1.8e-04 | norm 5099.0386 | dt 9.866 +type train | step 3733 | loss 100.2781 198.3153 311.8584 506.0933 743.1451 1065.4744 1488.0088 2123.3328 2981.8948 4615.6006 7652.9033 13689.1875 | lr 1.8e-04 | norm 4649.3901 | dt 9.877 +type train | step 3734 | loss 97.1234 193.5849 304.8671 499.2126 741.5156 1067.1560 1499.4615 2164.5105 3052.1926 4713.5815 7738.3550 13630.7070 | lr 1.8e-04 | norm 3829.8105 | dt 9.875 +type train | step 3735 | loss 100.1135 200.2887 316.4457 519.0716 764.8138 1110.4423 1553.5424 2227.5774 3110.4238 4764.2036 7844.2344 13915.0488 | lr 1.8e-04 | norm 4812.8955 | dt 9.882 +type train | step 3736 | loss 100.4474 199.0495 309.9656 504.6245 740.7123 1077.7803 1524.3621 2200.9431 3079.8176 4769.1929 7928.8843 14099.2432 | lr 1.8e-04 | norm 4416.0347 | dt 9.873 +type train | step 3737 | loss 96.4251 188.9659 297.6924 485.3717 714.0927 1031.8044 1446.6604 2069.9648 2923.2832 4504.5996 7430.1636 13088.1387 | lr 1.8e-04 | norm 3707.0701 | dt 9.886 +type train | step 3738 | loss 96.0487 186.6523 294.2206 479.2573 709.4451 1025.9215 1443.4108 2074.3457 2921.8047 4512.1851 7450.4580 13213.2764 | lr 1.8e-04 | norm 4401.1880 | dt 9.878 +type train | step 3739 | loss 100.6017 199.3776 313.1212 504.0357 741.6098 1070.4419 1493.7778 2132.5159 2989.9839 4614.0283 7553.9580 13299.6201 | lr 1.8e-04 | norm 3981.2053 | dt 9.885 +type train | step 3740 | loss 99.0406 194.4049 301.7565 489.8813 723.2103 1044.7139 1462.1124 2104.5842 2958.7930 4557.9653 7536.7256 13366.4844 | lr 1.8e-04 | norm 4523.1650 | dt 9.878 +type train | step 3741 | loss 102.7710 203.4021 315.5631 511.0113 750.4232 1092.6285 1533.9604 2200.5762 3065.9282 4720.3081 7784.9116 13883.1855 | lr 1.8e-04 | norm 4056.0784 | dt 9.862 +type train | step 3742 | loss 90.8203 178.4282 281.8858 466.3329 695.0857 1002.8002 1412.1880 2037.3987 2889.1753 4459.2480 7355.9053 12966.4131 | lr 1.8e-04 | norm 3986.0962 | dt 9.876 +type train | step 3743 | loss 100.1288 199.6715 310.7513 501.7752 738.6315 1059.4675 1482.3605 2108.0366 2959.5642 4534.7715 7464.5576 13122.5049 | lr 1.8e-04 | norm 4164.7778 | dt 9.876 +type train | step 3744 | loss 102.7865 202.3922 314.6055 509.8257 742.9407 1064.8777 1475.6240 2101.2126 2940.2385 4532.7969 7458.6758 13226.0254 | lr 1.8e-04 | norm 3483.4709 | dt 9.873 +type train | step 3745 | loss 95.8099 190.2961 301.3266 493.0992 729.7472 1054.0702 1485.9717 2127.9619 2998.9412 4638.0200 7638.3706 13415.5283 | lr 1.8e-04 | norm 4095.3821 | dt 9.880 +type train | step 3746 | loss 103.6560 203.3380 316.0191 508.8208 745.1915 1069.6348 1488.9866 2120.9109 2961.4985 4553.5781 7471.1660 13131.3633 | lr 1.8e-04 | norm 4677.4878 | dt 9.872 +type train | step 3747 | loss 92.8921 182.7629 286.1328 475.7012 711.6565 1035.3496 1459.6652 2115.2893 2988.5981 4598.5918 7573.5029 13261.3984 | lr 1.8e-04 | norm 5702.9644 | dt 9.865 +type train | step 3748 | loss 107.9151 211.5737 327.7685 524.9976 762.8606 1089.3123 1514.9806 2148.2593 2967.2063 4518.1621 7399.2529 13025.2441 | lr 1.8e-04 | norm 4815.9888 | dt 9.881 +type train | step 3749 | loss 98.9226 200.4350 313.4858 514.9679 761.9103 1094.9711 1536.4235 2192.8489 3098.5244 4782.4331 7831.6958 13738.7998 | lr 1.8e-04 | norm 4560.1724 | dt 9.859 +type train | step 3750 | loss 102.1135 202.2637 314.9273 509.2123 746.4340 1075.3384 1503.4495 2152.4321 3019.4958 4670.5166 7707.1592 13787.4893 | lr 1.8e-04 | norm 4161.1777 | dt 9.876 +type train | step 3751 | loss 103.1741 202.8118 319.0063 513.6084 750.7701 1079.5533 1513.1321 2180.3606 3058.8159 4755.0801 7857.7793 13969.3740 | lr 1.8e-04 | norm 6204.0601 | dt 9.860 +type train | step 3752 | loss 94.5503 183.2723 289.9664 477.0096 709.8826 1030.9208 1450.3226 2091.4031 2936.8801 4540.8457 7540.7842 13451.0957 | lr 1.8e-04 | norm 4698.4956 | dt 9.871 +type train | step 3753 | loss 94.9035 187.2221 294.1366 481.4828 713.0558 1037.9662 1460.8804 2099.8799 2951.6846 4531.9316 7418.3052 12989.3779 | lr 1.8e-04 | norm 3818.1738 | dt 9.866 +type train | step 3754 | loss 98.9859 193.6919 308.9240 507.9342 749.7490 1080.4094 1518.6216 2183.6296 3094.1182 4785.3218 7956.7676 14220.0889 | lr 1.8e-04 | norm 5244.1484 | dt 9.875 +type train | step 3755 | loss 96.1370 189.1003 297.6422 484.7853 717.4409 1043.8203 1466.7571 2103.0859 2953.2661 4574.7305 7529.3042 13292.0176 | lr 1.8e-04 | norm 3748.5400 | dt 9.886 +type train | step 3756 | loss 96.2757 189.8781 299.5898 487.7990 718.7375 1039.2087 1457.3589 2089.8250 2924.2058 4535.7471 7503.7251 13285.9365 | lr 1.8e-04 | norm 4329.9004 | dt 9.871 +type train | step 3757 | loss 102.7276 201.6357 311.9818 504.1732 738.1720 1063.8627 1489.8118 2119.3821 2947.9966 4532.4292 7487.5103 13275.1504 | lr 1.8e-04 | norm 4016.2000 | dt 9.869 +type train | step 3758 | loss 98.6128 195.5599 311.0410 513.6543 759.5560 1097.4292 1551.2124 2227.8606 3136.4519 4863.8130 8080.3472 14389.9043 | lr 1.8e-04 | norm 4514.9277 | dt 9.868 +type train | step 3759 | loss 100.0030 200.8655 318.2169 520.5780 765.5220 1109.2130 1554.7495 2241.6641 3153.4753 4894.2666 8137.5298 14332.5762 | lr 1.8e-04 | norm 5541.1021 | dt 9.861 +type train | step 3760 | loss 98.8947 194.7734 308.0209 505.4507 741.7089 1082.4752 1523.7216 2201.2754 3090.2041 4798.3979 7955.2627 14081.8320 | lr 1.8e-04 | norm 5180.6821 | dt 9.867 +type train | step 3761 | loss 95.8165 189.8447 301.7091 495.7048 736.8477 1072.2938 1511.5367 2177.3750 3069.7537 4759.1299 7865.4980 13953.7168 | lr 1.8e-04 | norm 4583.9678 | dt 9.869 +type train | step 3762 | loss 100.0738 198.6078 312.8020 514.5234 757.2405 1101.1948 1548.4352 2228.6543 3108.7932 4816.6177 7977.3428 14193.1406 | lr 1.8e-04 | norm 3851.7759 | dt 9.885 +type train | step 3763 | loss 95.5248 187.6361 294.4825 482.9932 717.0370 1034.4014 1456.2115 2090.1611 2947.6094 4571.2959 7559.4546 13355.0410 | lr 1.8e-04 | norm 3636.5034 | dt 9.876 +type train | step 3764 | loss 107.2110 211.1456 323.7429 516.6287 754.3908 1077.6146 1500.6990 2136.6079 2970.9065 4605.3926 7631.9785 13541.4141 | lr 1.8e-04 | norm 4956.8545 | dt 9.878 +type train | step 3765 | loss 87.4900 174.0377 280.6716 465.6500 705.0318 1037.7771 1484.3911 2168.9585 3084.6750 4804.0371 7902.7388 13908.3984 | lr 1.8e-04 | norm 5100.6768 | dt 9.870 +type train | step 3766 | loss 112.7935 231.9164 352.2990 561.7708 817.3658 1161.9243 1620.6168 2316.7527 3189.1106 4949.4873 8220.2441 14528.3447 | lr 1.8e-04 | norm 7442.2246 | dt 9.874 +type train | step 3767 | loss 96.5600 190.1211 297.0154 484.0979 716.9299 1035.3230 1457.2251 2086.3733 2944.5442 4535.4766 7473.3203 13241.3242 | lr 1.8e-04 | norm 3474.9851 | dt 9.891 +type train | step 3768 | loss 96.8252 191.3777 301.4552 489.8397 722.1094 1042.2880 1460.1843 2090.0894 2943.1953 4538.5347 7482.8823 13259.3320 | lr 1.8e-04 | norm 4179.2114 | dt 9.897 +type train | step 3769 | loss 102.0799 204.6823 316.2016 507.4898 743.1395 1063.7607 1480.3218 2122.1726 2981.2354 4592.7017 7566.7842 13367.5576 | lr 1.8e-04 | norm 5230.0278 | dt 9.874 +type train | step 3770 | loss 98.1651 194.1806 300.7469 491.1738 727.0380 1046.4532 1472.6140 2106.1707 2959.5718 4580.6860 7533.9058 13330.8701 | lr 1.8e-04 | norm 5227.2554 | dt 9.896 +type train | step 3771 | loss 94.6219 188.6896 294.0750 474.1486 700.3805 1016.9652 1433.3330 2056.8413 2906.3630 4530.0742 7515.4014 13383.5762 | lr 1.8e-04 | norm 5763.2764 | dt 9.881 +type train | step 3772 | loss 94.2211 185.0513 295.6666 485.2927 723.4103 1046.2695 1478.0173 2131.7832 3002.4482 4640.7891 7654.0522 13572.8896 | lr 1.8e-04 | norm 4941.9097 | dt 9.878 +type train | step 3773 | loss 99.6996 196.3653 307.7909 496.0193 729.0062 1055.8864 1464.0171 2081.3472 2892.1252 4433.5923 7292.9312 12917.0273 | lr 1.8e-04 | norm 4758.2100 | dt 9.879 +type train | step 3774 | loss 94.7493 187.8244 296.6104 487.5205 720.0862 1040.2910 1457.1554 2081.3538 2944.0137 4536.8730 7484.9399 13196.9619 | lr 1.8e-04 | norm 3532.6648 | dt 9.878 +type train | step 3775 | loss 95.0934 186.7536 293.9327 480.8162 712.1205 1033.1202 1451.9236 2084.4634 2939.1394 4506.9604 7426.6919 13105.4004 | lr 1.8e-04 | norm 3555.2112 | dt 9.870 +type train | step 3776 | loss 96.9053 192.0625 303.9015 496.3627 733.1729 1055.3687 1477.2108 2108.4521 2973.6416 4585.0273 7537.6792 13256.9658 | lr 1.8e-04 | norm 3664.4822 | dt 9.893 +type train | step 3777 | loss 96.2584 190.6300 303.3107 499.4712 731.0219 1053.0681 1473.4695 2103.7410 2951.8120 4529.1187 7473.3345 13221.5186 | lr 1.8e-04 | norm 4294.8257 | dt 9.874 +type train | step 3778 | loss 96.1390 187.5834 294.9044 481.7324 714.6594 1029.5984 1450.2247 2082.6726 2925.7886 4544.3838 7557.3623 13495.5508 | lr 1.8e-04 | norm 4524.5439 | dt 9.876 +type train | step 3779 | loss 91.4407 181.4097 287.4056 477.0974 709.3252 1031.1462 1448.9623 2088.3193 2961.3611 4596.3135 7601.0190 13405.0059 | lr 1.8e-04 | norm 3924.7031 | dt 9.876 +type train | step 3780 | loss 102.1744 203.7723 313.8057 508.5571 745.0079 1071.0826 1497.8143 2135.0168 2995.0806 4585.9072 7526.6221 13230.6133 | lr 1.8e-04 | norm 4101.7686 | dt 9.879 +type train | step 3781 | loss 105.1675 205.9971 328.4622 539.9449 783.1107 1136.0522 1585.9578 2245.8083 3035.3787 4628.8613 7620.5889 13609.1572 | lr 1.8e-04 | norm 7989.2031 | dt 9.851 +type train | step 3782 | loss 96.4668 189.7331 300.9225 492.8095 728.0201 1054.3278 1476.7368 2113.8357 2975.7197 4598.8032 7599.3638 13411.0703 | lr 1.8e-04 | norm 3396.4819 | dt 9.886 +type train | step 3783 | loss 103.5091 206.9650 319.3788 518.9227 755.6396 1099.8134 1545.4156 2224.0039 3097.9231 4772.9800 7884.9072 14094.5439 | lr 1.8e-04 | norm 6281.1650 | dt 9.864 +type train | step 3784 | loss 110.0008 216.7473 327.1464 524.8965 764.6224 1115.9326 1557.9060 2229.7615 3045.2832 4652.8018 7615.4292 13442.4199 | lr 1.8e-04 | norm 4938.2319 | dt 9.867 +type train | step 3785 | loss 109.1014 217.4770 332.2654 528.9047 771.4104 1124.5875 1571.2421 2237.5193 3089.8406 4696.4194 7649.7559 13372.8818 | lr 1.8e-04 | norm 4575.6084 | dt 9.877 +type train | step 3786 | loss 98.2948 195.7258 306.4394 499.0919 733.6743 1057.3345 1476.8744 2111.0679 2943.3867 4504.3760 7392.9771 13051.9570 | lr 1.8e-04 | norm 4357.4717 | dt 9.882 +type train | step 3787 | loss 95.4346 186.5640 292.6331 475.8952 704.4752 1018.8806 1436.0502 2055.4194 2896.5415 4465.1567 7329.3066 12988.2051 | lr 1.8e-04 | norm 3980.4424 | dt 9.885 +type train | step 3788 | loss 94.7804 186.5131 292.9642 480.8901 713.0432 1043.1489 1473.4297 2128.9053 3019.6135 4669.5806 7661.0352 13499.1553 | lr 1.8e-04 | norm 4377.2617 | dt 9.879 +type train | step 3789 | loss 98.3840 192.9949 301.4314 494.0537 727.0043 1050.0094 1470.5808 2110.4714 2962.0193 4586.2915 7587.8379 13421.9238 | lr 1.7e-04 | norm 3841.8550 | dt 9.886 +type train | step 3790 | loss 100.1093 196.6457 309.6959 502.4062 738.0893 1073.0549 1482.5811 2121.6387 2936.7271 4521.9907 7414.8335 13144.4678 | lr 1.7e-04 | norm 5308.9722 | dt 9.879 +type train | step 3791 | loss 98.3247 194.1549 307.4835 508.7353 752.2714 1083.9655 1529.6895 2196.7397 3107.2532 4792.4292 7915.2661 14045.0371 | lr 1.7e-04 | norm 4249.1860 | dt 9.879 +type train | step 3792 | loss 97.9173 194.4706 306.5091 497.9212 729.8796 1038.4375 1456.0339 2068.1160 2873.0215 4403.3647 7280.1670 12927.6270 | lr 1.7e-04 | norm 7564.5449 | dt 9.872 +type train | step 3793 | loss 100.0988 199.6732 313.5383 513.1538 751.9025 1083.0579 1511.6460 2167.4824 3024.0732 4668.2573 7798.0737 13999.6309 | lr 1.7e-04 | norm 6745.4614 | dt 9.873 +type train | step 3794 | loss 90.1195 178.2359 284.6627 473.5732 705.0367 1017.3487 1430.4476 2048.2791 2894.7366 4486.1519 7387.5542 13007.6357 | lr 1.7e-04 | norm 4198.0112 | dt 9.877 +type train | step 3795 | loss 100.6122 199.0778 311.2323 503.5826 738.0039 1059.9591 1477.6761 2103.1265 2958.2869 4547.3330 7455.0200 13206.8682 | lr 1.7e-04 | norm 3729.2000 | dt 9.893 +type train | step 3796 | loss 100.3177 205.0534 336.8890 550.7315 794.8493 1155.7690 1606.0176 2296.0823 3144.0935 4848.2891 8094.4238 14599.0000 | lr 1.7e-04 | norm 9969.3262 | dt 9.856 +type train | step 3797 | loss 93.6843 181.6308 286.7043 472.2627 697.1973 1016.2412 1432.4590 2061.1670 2906.7651 4547.6089 7567.6943 13467.2178 | lr 1.7e-04 | norm 4786.0098 | dt 9.874 +type train | step 3798 | loss 99.9990 197.8747 306.9207 496.5918 732.1844 1057.2096 1482.1423 2126.9407 2991.4497 4593.5308 7525.2544 13259.2197 | lr 1.7e-04 | norm 4223.7026 | dt 9.881 +type train | step 3799 | loss 101.4987 201.3910 316.5881 518.7538 763.9178 1106.5267 1543.0793 2204.3979 3051.0444 4641.3613 7586.7017 13370.9814 | lr 1.7e-04 | norm 4685.9492 | dt 9.876 +type train | step 3800 | loss 100.3167 198.0473 308.6850 503.1427 743.2750 1080.5444 1512.0216 2163.9993 3007.6235 4622.1152 7667.7212 13822.0146 | lr 1.7e-04 | norm 5282.7524 | dt 9.880 +type train | step 3801 | loss 99.6593 198.1876 310.8734 505.0755 744.7637 1079.2633 1515.1337 2170.3574 3036.3967 4706.7383 7759.3096 13676.1338 | lr 1.7e-04 | norm 4114.1792 | dt 9.890 +type train | step 3802 | loss 98.6601 195.0037 306.7240 501.1475 738.0352 1067.4438 1496.4290 2138.4397 3004.6121 4617.6206 7617.7324 13505.9697 | lr 1.7e-04 | norm 3952.2798 | dt 9.883 +type train | step 3803 | loss 96.2116 191.7260 301.5876 492.6278 727.4493 1042.7192 1459.4414 2087.4614 2944.8660 4540.1162 7492.6543 13282.7129 | lr 1.7e-04 | norm 3834.8718 | dt 9.892 +type train | step 3804 | loss 95.5624 189.2220 297.0322 487.3642 720.0739 1042.2483 1465.8086 2106.1099 2965.4883 4614.0801 7647.6816 13529.6875 | lr 1.7e-04 | norm 3673.8689 | dt 9.878 +type train | step 3805 | loss 103.9179 206.5407 316.5679 508.0403 739.0873 1060.5461 1473.5372 2103.6682 2919.2869 4466.4736 7343.0840 12951.1475 | lr 1.7e-04 | norm 3855.9329 | dt 9.882 +type train | step 3806 | loss 102.8935 203.8661 313.5264 510.2525 745.6738 1071.6045 1502.0826 2142.9255 3011.8096 4647.7075 7676.5361 13606.5791 | lr 1.7e-04 | norm 3608.4075 | dt 9.880 +type train | step 3807 | loss 104.3182 205.2283 315.5219 506.0311 736.3578 1058.6261 1480.4698 2111.0618 2934.4568 4569.3950 7555.8364 13491.1670 | lr 1.7e-04 | norm 5056.4409 | dt 9.865 +type train | step 3808 | loss 101.6001 201.3880 313.6552 510.1417 752.0915 1101.4027 1546.4888 2214.8813 3073.5181 4717.9233 7842.9590 13976.2822 | lr 1.7e-04 | norm 4834.4385 | dt 9.866 +type train | step 3809 | loss 98.6633 197.5930 309.8604 501.1254 739.2648 1063.6097 1486.3073 2115.4451 2943.7561 4489.1777 7336.7490 12978.7666 | lr 1.7e-04 | norm 3736.2305 | dt 9.874 +type train | step 3810 | loss 100.2647 198.2342 311.2696 506.0351 741.8878 1077.3873 1504.6018 2146.5820 2995.1833 4601.2749 7538.3281 13303.8838 | lr 1.7e-04 | norm 4143.7412 | dt 9.870 +type train | step 3811 | loss 104.5163 207.7680 325.9563 530.0961 776.8099 1123.6837 1577.3030 2243.0566 3150.3250 4831.1172 7934.3965 14063.3887 | lr 1.7e-04 | norm 4068.6594 | dt 9.869 +type train | step 3812 | loss 98.1599 196.6223 310.6281 507.0223 746.8168 1073.7810 1505.3854 2157.6267 3056.7532 4750.4033 7867.7554 13985.2637 | lr 1.7e-04 | norm 4509.5371 | dt 9.878 +type train | step 3813 | loss 96.3252 194.0179 307.6913 506.9193 750.5687 1077.1702 1507.2346 2143.5664 3021.2837 4629.0352 7618.6567 13425.1982 | lr 1.7e-04 | norm 4813.0942 | dt 9.883 +type train | step 3814 | loss 96.9323 191.1084 301.8326 491.3150 723.8237 1045.6040 1468.7473 2090.2358 2934.8704 4530.9590 7505.3965 13302.5039 | lr 1.7e-04 | norm 3915.4243 | dt 9.884 +type train | step 3815 | loss 95.9287 191.0325 302.5274 491.8421 728.7908 1049.7240 1470.2795 2098.7261 2963.9663 4575.6904 7533.9570 13274.7812 | lr 1.7e-04 | norm 3616.9653 | dt 9.885 +type train | step 3816 | loss 98.7589 196.8474 310.9727 509.1240 752.1748 1091.6343 1528.7727 2190.5278 3062.2063 4711.7002 7796.1982 13981.2021 | lr 1.7e-04 | norm 5484.4746 | dt 9.865 +type train | step 3817 | loss 94.1116 182.8495 288.5247 474.8334 703.4197 1013.8008 1424.6354 2047.5658 2885.4351 4453.3960 7347.9414 13117.5234 | lr 1.7e-04 | norm 4501.2515 | dt 9.874 +type train | step 3818 | loss 92.2612 183.0711 290.5519 475.4578 708.0095 1022.8434 1436.2362 2056.3171 2909.9712 4533.7593 7554.7500 13378.6123 | lr 1.7e-04 | norm 5608.4980 | dt 9.872 +type train | step 3819 | loss 93.4695 185.0195 294.3494 480.9701 713.0231 1029.9874 1444.5300 2060.2729 2920.0132 4514.2231 7497.1909 13332.8359 | lr 1.7e-04 | norm 5203.6611 | dt 9.871 +type train | step 3820 | loss 95.7889 187.8786 296.0490 484.5692 717.4495 1038.8096 1461.7205 2089.2449 2930.5054 4541.4048 7511.3384 13376.4844 | lr 1.7e-04 | norm 3786.1282 | dt 9.873 +type train | step 3821 | loss 94.5772 187.0697 296.4942 489.2164 731.0531 1059.8994 1496.5751 2154.7168 3034.8865 4683.0391 7697.4653 13518.8369 | lr 1.7e-04 | norm 4851.1826 | dt 9.881 +type train | step 3822 | loss 99.7852 196.9434 307.3105 501.7376 734.5972 1064.8435 1491.3988 2131.3318 2973.7571 4567.6055 7543.6338 13364.0361 | lr 1.7e-04 | norm 4409.8154 | dt 9.882 +type train | step 3823 | loss 94.8681 187.6689 296.8733 484.4736 721.5063 1051.8579 1484.1298 2138.2029 3014.1287 4645.7822 7694.3140 13633.6211 | lr 1.7e-04 | norm 4112.4126 | dt 9.897 +type train | step 3824 | loss 93.8333 182.0954 287.5147 474.5858 702.4202 1016.5746 1426.1680 2045.2466 2857.3477 4386.1543 7252.1655 12948.2852 | lr 1.7e-04 | norm 5906.2876 | dt 9.854 +type train | step 3825 | loss 88.5572 173.8762 278.9031 460.5746 690.1915 999.6730 1417.9828 2046.5115 2926.9797 4550.6587 7528.5674 13362.6260 | lr 1.7e-04 | norm 4270.9600 | dt 9.882 +type train | step 3826 | loss 92.8182 180.8814 285.0013 468.7111 695.9290 1011.4456 1419.6216 2040.7235 2889.7217 4449.7183 7355.7544 12968.2021 | lr 1.7e-04 | norm 3837.0063 | dt 9.876 +type train | step 3827 | loss 96.6790 190.4771 297.4295 489.7491 725.8151 1047.4535 1472.4377 2112.7229 2967.5034 4593.9946 7598.6323 13450.8604 | lr 1.7e-04 | norm 4748.6021 | dt 9.874 +type train | step 3828 | loss 101.1962 199.9710 309.6791 502.0721 736.9197 1046.7360 1465.9849 2093.4543 2936.5215 4541.0508 7527.4731 13385.9971 | lr 1.7e-04 | norm 7107.2739 | dt 9.886 +type train | step 3829 | loss 96.2606 190.3292 299.4671 489.7606 725.7410 1052.1694 1478.2998 2139.6799 3009.7893 4621.8091 7569.0459 13252.8760 | lr 1.7e-04 | norm 3585.4146 | dt 9.875 +type train | step 3830 | loss 103.5192 203.5103 318.3272 515.3078 755.5734 1082.8655 1518.6969 2165.4802 3007.5652 4625.9033 7674.1260 13778.4463 | lr 1.7e-04 | norm 4437.6836 | dt 9.875 +type train | step 3831 | loss 95.3639 191.0672 304.1428 501.1981 739.8997 1069.7322 1495.7233 2141.9404 3008.3335 4667.5869 7726.8384 13599.7188 | lr 1.7e-04 | norm 4321.0303 | dt 9.880 +type train | step 3832 | loss 93.4636 184.1881 292.1429 480.8713 720.6587 1039.3445 1467.7120 2111.1606 2998.1494 4615.1758 7562.1235 13242.2646 | lr 1.7e-04 | norm 3863.8721 | dt 9.883 +type train | step 3833 | loss 99.7435 196.3304 306.4498 497.4986 731.8056 1055.8186 1484.3810 2115.8491 2957.8635 4576.8984 7618.1758 13596.8467 | lr 1.7e-04 | norm 4212.8589 | dt 9.882 +type train | step 3834 | loss 102.7380 201.1718 316.1412 516.1483 755.8276 1088.7478 1520.6538 2164.3586 3019.1860 4667.1943 7721.1401 13769.1758 | lr 1.7e-04 | norm 5622.6465 | dt 9.855 +type train | step 3835 | loss 94.6271 187.6463 299.2237 494.1449 732.8766 1066.5708 1509.0607 2177.8745 3073.5742 4762.4473 7821.8838 13789.8701 | lr 1.7e-04 | norm 4508.3574 | dt 9.878 +type train | step 3836 | loss 95.5282 189.3767 297.1976 490.1422 726.0926 1055.3699 1477.9606 2115.4080 2967.9807 4567.3389 7512.6377 13189.2168 | lr 1.7e-04 | norm 3614.8547 | dt 9.885 +type train | step 3837 | loss 93.6991 186.1799 294.3880 482.3777 715.3528 1036.7550 1460.5731 2109.8938 2954.7124 4570.5205 7508.7939 13200.1689 | lr 1.7e-04 | norm 3814.4583 | dt 9.883 +type train | step 3838 | loss 95.0964 187.9182 297.0928 487.2699 723.7728 1045.0530 1467.4460 2106.0435 2943.7207 4524.7739 7440.9209 13044.9414 | lr 1.7e-04 | norm 3710.7788 | dt 9.875 +type train | step 3839 | loss 96.3261 189.2072 298.5506 488.7580 724.3496 1045.6482 1477.4597 2120.2922 2987.5942 4608.1792 7582.5620 13434.0430 | lr 1.7e-04 | norm 3954.2180 | dt 9.875 +type train | step 3840 | loss 97.8722 190.1631 305.1736 505.3889 745.0587 1081.9365 1525.3669 2198.8940 3095.4199 4763.2598 7860.5063 13867.2031 | lr 1.7e-04 | norm 4987.9697 | dt 9.856 +type train | step 3841 | loss 104.0063 205.0198 322.3457 518.0961 768.3738 1129.3835 1583.6049 2285.8513 3169.0977 4866.1387 7885.3906 13944.4482 | lr 1.7e-04 | norm 6715.9395 | dt 9.862 +type train | step 3842 | loss 98.5536 191.8138 299.7044 490.9586 724.5956 1047.0897 1472.7135 2112.3013 2968.8447 4545.5762 7479.2563 13180.1924 | lr 1.7e-04 | norm 3806.7434 | dt 9.867 +type train | step 3843 | loss 95.0931 190.1406 297.3524 488.4416 722.2854 1038.3645 1452.1495 2076.1677 2925.7397 4512.4497 7387.2085 13005.1855 | lr 1.7e-04 | norm 3782.2576 | dt 9.885 +type train | step 3844 | loss 98.5552 194.6732 307.6665 503.0290 745.0318 1069.2362 1514.4902 2174.7493 3070.1946 4726.6479 7700.9717 13489.6631 | lr 1.7e-04 | norm 5356.0830 | dt 9.872 +type train | step 3845 | loss 94.6362 187.3392 295.6134 482.5550 713.4214 1030.5315 1444.0171 2063.4478 2905.6873 4452.5342 7312.2339 12882.6162 | lr 1.7e-04 | norm 3464.9465 | dt 9.881 +type train | step 3846 | loss 97.6526 192.5297 303.0037 495.0145 727.7531 1057.2163 1488.8767 2130.0105 2980.0903 4592.3418 7574.9160 13376.3584 | lr 1.7e-04 | norm 3907.7336 | dt 9.883 +type train | step 3847 | loss 101.2439 200.6659 313.3450 505.7940 742.1478 1069.5347 1503.5863 2146.7844 3015.8047 4657.8472 7696.1465 13708.2246 | lr 1.7e-04 | norm 4347.6411 | dt 9.871 +type train | step 3848 | loss 93.0580 182.1891 287.0713 470.1308 699.8259 1018.5146 1434.6786 2066.4961 2917.0264 4490.9912 7355.4287 12891.6729 | lr 1.7e-04 | norm 3523.6135 | dt 9.873 +type train | step 3849 | loss 89.5901 176.1990 281.8306 466.9780 701.1987 1017.4863 1438.0869 2075.5522 2944.4844 4593.5312 7660.8130 13611.9844 | lr 1.7e-04 | norm 3945.7495 | dt 9.893 +type train | step 3850 | loss 90.5069 175.8059 281.0292 471.2258 713.3329 1037.3311 1478.3691 2127.4854 3011.5859 4712.7129 7975.5063 14386.6709 | lr 1.7e-04 | norm 9662.4141 | dt 9.868 +type train | step 3851 | loss 99.3590 195.3679 307.2990 497.3152 733.2781 1054.4819 1479.0671 2109.2280 2957.7175 4556.9414 7492.1392 13214.6221 | lr 1.7e-04 | norm 3394.3701 | dt 9.880 +type train | step 3852 | loss 101.6768 202.0772 313.9782 512.0847 748.7792 1076.5566 1502.4053 2143.4236 2985.5930 4577.2524 7486.2368 13353.2168 | lr 1.7e-04 | norm 5483.8135 | dt 9.870 +type train | step 3853 | loss 104.1468 208.1805 327.6355 533.4700 778.6116 1108.2258 1533.6326 2186.0225 3052.6001 4661.8740 7689.7129 13547.8604 | lr 1.7e-04 | norm 6245.3076 | dt 9.873 +type train | step 3854 | loss 95.7763 187.7898 296.7569 485.1416 715.8788 1032.2479 1444.5217 2059.7214 2888.6421 4433.6987 7278.8447 12777.0977 | lr 1.7e-04 | norm 3518.8374 | dt 9.910 +type train | step 3855 | loss 102.1184 202.4798 315.0060 509.7166 751.5338 1080.7651 1522.0670 2193.3557 3067.5840 4731.6880 7771.9043 13841.3125 | lr 1.7e-04 | norm 7107.1147 | dt 9.863 +type train | step 3856 | loss 100.3812 195.4908 303.1408 491.3450 725.8954 1052.7921 1479.9265 2127.7437 2974.8569 4595.6724 7572.3926 13534.6162 | lr 1.7e-04 | norm 4776.7314 | dt 9.877 +type train | step 3857 | loss 92.5901 183.0354 288.2394 474.3256 703.7374 1029.3556 1466.5070 2124.9138 2994.0806 4654.8521 7755.4058 13905.4053 | lr 1.7e-04 | norm 5272.2080 | dt 9.891 +type train | step 3858 | loss 97.6957 191.1833 300.8938 489.7108 723.1389 1042.6412 1461.3586 2095.2415 2949.2402 4569.0801 7585.1738 13480.4873 | lr 1.7e-04 | norm 4412.1567 | dt 9.867 +type train | step 3859 | loss 98.6872 195.4206 308.7758 504.7239 744.0145 1080.9901 1518.1184 2175.3979 3036.9961 4670.1045 7694.8569 13589.3125 | lr 1.7e-04 | norm 3845.3882 | dt 9.870 +type train | step 3860 | loss 103.8867 205.0722 319.5181 518.7081 758.1792 1083.7657 1510.3619 2143.8906 2984.1226 4609.2344 7588.3979 13468.7949 | lr 1.7e-04 | norm 4787.8662 | dt 9.886 +type train | step 3861 | loss 99.7440 198.2640 310.1275 499.1740 738.9314 1083.3152 1523.3615 2191.7229 3065.1116 4696.1387 7682.7837 13455.7539 | lr 1.7e-04 | norm 4071.9570 | dt 9.884 +type train | step 3862 | loss 92.7386 184.3106 290.8509 477.5489 714.0865 1041.7563 1472.6232 2123.8879 3008.5176 4679.4092 7731.5405 13733.5420 | lr 1.7e-04 | norm 5070.3013 | dt 9.873 +type train | step 3863 | loss 101.2236 203.6797 318.7275 517.8555 769.0099 1113.9380 1566.3619 2246.0225 3151.4617 4844.5889 7981.6152 14050.6279 | lr 1.7e-04 | norm 5042.0483 | dt 9.872 +type train | step 3864 | loss 96.1882 188.0650 295.3834 484.2455 719.0702 1035.2555 1459.5475 2076.1228 2920.2300 4489.0151 7435.5127 13160.3633 | lr 1.7e-04 | norm 4847.9976 | dt 9.877 +type train | step 3865 | loss 97.5556 192.2402 302.8953 491.4255 725.3346 1046.5457 1468.8418 2105.4727 2949.8936 4537.9404 7475.4263 13221.1191 | lr 1.7e-04 | norm 3749.9756 | dt 9.889 +type train | step 3866 | loss 91.7066 181.5051 289.0649 477.5027 712.8749 1027.5951 1443.6449 2067.7449 2925.9375 4514.6841 7439.7520 13074.1084 | lr 1.7e-04 | norm 4268.8320 | dt 9.882 +type train | step 3867 | loss 89.6598 175.0477 279.6384 468.2341 698.6835 1017.4127 1436.1969 2073.0466 2911.2334 4510.5957 7479.3789 13319.5127 | lr 1.7e-04 | norm 5221.3555 | dt 9.865 +type train | step 3868 | loss 98.8427 193.0182 300.3979 494.9137 727.3302 1045.9352 1461.8888 2089.8650 2896.6318 4482.6055 7352.9604 12975.3789 | lr 1.7e-04 | norm 6974.4409 | dt 9.859 +type train | step 3869 | loss 94.3704 184.5606 292.4146 480.0719 710.1750 1029.4514 1450.4642 2079.6562 2951.0618 4513.4312 7355.2310 12828.1650 | lr 1.7e-04 | norm 5228.1001 | dt 9.857 +type train | step 3870 | loss 98.4941 193.9160 301.0470 492.5331 729.6219 1067.2783 1503.3484 2171.1377 3041.3833 4686.1152 7763.1787 13751.4229 | lr 1.7e-04 | norm 5575.2983 | dt 9.873 +type train | step 3871 | loss 103.4989 199.4830 308.8407 507.3070 749.3171 1097.1594 1537.8300 2231.4062 3032.0012 4568.1123 7585.1445 13487.9824 | lr 1.7e-04 | norm 9235.0293 | dt 9.819 +type train | step 3872 | loss 108.9412 217.0881 328.2283 535.1590 781.2653 1152.6759 1608.9257 2317.0950 3151.1514 4746.6797 7817.0576 13829.1689 | lr 1.7e-04 | norm 6586.3755 | dt 9.840 +type train | step 3873 | loss 97.0003 190.7174 301.3428 488.8494 724.8443 1046.8846 1473.6085 2115.4893 2989.0352 4596.3696 7563.6714 13307.2275 | lr 1.7e-04 | norm 4430.5977 | dt 9.885 +type train | step 3874 | loss 99.9136 197.5267 305.2509 496.7083 734.0635 1060.1755 1485.5120 2135.7925 2984.1401 4575.1885 7565.1055 13460.4062 | lr 1.7e-04 | norm 5355.6396 | dt 9.878 +type train | step 3875 | loss 95.3418 189.1784 298.4385 488.1163 718.1088 1036.6829 1452.8806 2070.5740 2901.9553 4467.6035 7345.5762 13036.0508 | lr 1.7e-04 | norm 4198.5361 | dt 9.890 +type train | step 3876 | loss 96.7287 197.4087 314.0488 513.3065 757.5688 1078.9227 1509.1096 2153.2266 3088.5630 4817.6753 8110.5762 14494.7598 | lr 1.7e-04 | norm 8566.0195 | dt 9.883 +type train | step 3877 | loss 99.8713 207.0246 320.7761 518.5081 763.1806 1105.9391 1547.1438 2214.5537 3107.5122 4768.8901 7879.1367 14003.9688 | lr 1.7e-04 | norm 7781.0894 | dt 9.838 +type train | step 3878 | loss 100.0144 193.9991 313.1881 513.6472 756.2406 1086.4447 1534.8824 2203.1819 3110.1372 4833.4629 7964.4473 14173.5830 | lr 1.6e-04 | norm 5161.7095 | dt 9.862 +type train | step 3879 | loss 100.9842 200.0256 315.7295 514.5598 761.7566 1088.4581 1525.1940 2180.6958 3063.0762 4766.4980 7851.8408 13997.8330 | lr 1.6e-04 | norm 6248.1006 | dt 9.860 +type train | step 3880 | loss 95.7376 193.0655 307.3315 504.5345 744.7844 1073.0061 1508.6299 2170.0959 3047.4856 4717.9956 7755.9868 13729.0078 | lr 1.6e-04 | norm 5045.3599 | dt 9.862 +type train | step 3881 | loss 97.4689 191.4010 301.7085 493.3660 726.4356 1052.2332 1479.3024 2124.8843 2982.2017 4615.9746 7650.2324 13639.4668 | lr 1.6e-04 | norm 4649.9893 | dt 9.887 +type train | step 3882 | loss 98.4454 194.3061 304.5811 495.2613 732.0544 1057.2247 1477.4438 2113.1248 2957.6880 4544.1646 7495.3438 13232.4229 | lr 1.6e-04 | norm 3701.2764 | dt 9.893 +type train | step 3883 | loss 96.4375 190.8838 300.1303 488.5898 730.0900 1049.5769 1479.3744 2123.3298 3013.3984 4652.3916 7636.1479 13503.5732 | lr 1.6e-04 | norm 4818.7759 | dt 9.871 +type train | step 3884 | loss 91.0367 179.1648 286.3867 470.8415 700.9661 1014.4417 1426.9890 2050.0054 2900.4739 4491.8618 7430.1616 13119.5020 | lr 1.6e-04 | norm 3893.1924 | dt 9.892 +type train | step 3885 | loss 97.7111 199.7257 323.0330 534.7193 783.6962 1141.9955 1620.8800 2359.2310 3350.2136 5266.5615 8716.4609 15480.3652 | lr 1.6e-04 | norm 10066.2939 | dt 9.856 +type train | step 3886 | loss 100.8777 198.2739 314.2207 513.0385 750.7192 1095.2133 1537.3555 2226.2727 3111.0942 4841.7266 7991.7871 14127.4648 | lr 1.6e-04 | norm 6340.4907 | dt 9.873 +type train | step 3887 | loss 93.8636 185.2802 289.8256 475.7695 706.7692 1017.6847 1426.1738 2038.7655 2889.6594 4459.8438 7342.8472 12908.1084 | lr 1.6e-04 | norm 3588.5120 | dt 9.887 +type train | step 3888 | loss 96.8600 191.5958 300.7591 487.9989 717.1376 1030.5288 1445.6284 2060.3965 2887.8813 4467.8813 7398.3242 13171.9160 | lr 1.6e-04 | norm 3618.2273 | dt 9.874 +type train | step 3889 | loss 100.7008 197.7991 307.4386 496.7611 733.4884 1056.8719 1476.2906 2111.8582 2955.8469 4560.9775 7548.6357 13401.9160 | lr 1.6e-04 | norm 4313.0591 | dt 9.880 +type train | step 3890 | loss 95.5903 188.7952 297.7213 488.1315 724.6906 1049.1110 1474.0107 2113.0854 3003.9277 4627.5679 7572.0972 13232.0518 | lr 1.6e-04 | norm 4335.1724 | dt 9.892 +type train | step 3891 | loss 93.9180 187.3807 303.1017 501.2604 742.0576 1069.0710 1504.6886 2154.5410 3047.2065 4765.4712 7905.1367 13997.4961 | lr 1.6e-04 | norm 5482.1865 | dt 9.883 +type train | step 3892 | loss 102.0422 205.0146 317.4729 520.6719 758.3226 1105.6323 1554.5726 2221.4902 3021.8745 4587.9019 7536.7881 13379.5547 | lr 1.6e-04 | norm 8239.6084 | dt 9.857 +type train | step 3893 | loss 97.9003 194.4139 306.2684 500.0689 738.6338 1066.1599 1496.5265 2134.6980 3019.9128 4678.9526 7715.8389 13678.6191 | lr 1.6e-04 | norm 3878.3271 | dt 9.877 +type train | step 3894 | loss 95.7266 191.4438 302.4691 494.9836 732.0912 1053.6276 1482.5096 2120.9707 2994.4480 4632.8115 7586.9688 13377.7266 | lr 1.6e-04 | norm 3855.2622 | dt 9.880 +type train | step 3895 | loss 103.4980 212.5896 338.6756 540.8414 811.8990 1175.3759 1641.5356 2350.6748 3275.8303 5056.1196 8384.3574 14701.2217 | lr 1.6e-04 | norm 6942.2422 | dt 9.865 +type train | step 3896 | loss 94.0867 186.8875 296.7266 481.4901 713.4968 1027.2965 1445.0035 2070.0181 2921.3933 4533.9785 7468.2412 13221.2266 | lr 1.6e-04 | norm 3872.3313 | dt 9.891 +type train | step 3897 | loss 97.5120 193.9753 304.0341 493.6453 728.9294 1049.9789 1469.7859 2097.9619 2960.0229 4576.3271 7518.1245 13185.8584 | lr 1.6e-04 | norm 3381.2319 | dt 9.875 +type train | step 3898 | loss 88.3914 174.7766 279.5033 462.0329 692.9264 1005.2712 1427.4597 2056.5071 2923.9604 4511.4883 7399.2920 12986.1201 | lr 1.6e-04 | norm 3716.6951 | dt 9.887 +type train | step 3899 | loss 115.9618 226.7009 341.7589 540.9890 784.8639 1131.5374 1582.7386 2263.9531 3137.4636 4789.2227 7781.7690 13533.2402 | lr 1.6e-04 | norm 3757.9009 | dt 9.881 +type train | step 3900 | loss 104.2873 205.0217 316.8802 509.3677 748.8722 1074.4872 1508.8986 2148.7136 3020.2517 4629.6064 7556.8032 13273.0967 | lr 1.6e-04 | norm 5300.3462 | dt 9.881 +type train | step 3901 | loss 102.6355 204.0912 314.6233 510.3783 744.1103 1080.9205 1508.0271 2155.1785 3009.7009 4676.3340 7831.5439 14116.3203 | lr 1.6e-04 | norm 6081.2246 | dt 9.877 +type train | step 3902 | loss 91.2985 179.6561 284.1902 467.3040 694.2034 1004.6791 1415.9773 2036.8259 2885.1497 4474.8638 7395.1714 12950.9102 | lr 1.6e-04 | norm 3220.9915 | dt 9.885 +type train | step 3903 | loss 100.8638 196.7564 312.1953 510.5128 748.1833 1084.8502 1515.6432 2162.4536 3008.2324 4645.0718 7629.4360 13472.0205 | lr 1.6e-04 | norm 3966.0054 | dt 9.881 +type train | step 3904 | loss 94.5048 187.7858 296.5630 495.4932 736.3477 1075.4219 1514.2157 2194.3965 3101.5278 4853.9253 8055.4883 14453.4023 | lr 1.6e-04 | norm 8121.6768 | dt 9.858 +type train | step 3905 | loss 94.8817 187.1434 293.2556 479.0466 711.9341 1028.1864 1445.0072 2070.9385 2934.4175 4539.0674 7463.4438 13061.5332 | lr 1.6e-04 | norm 3833.6870 | dt 9.887 +type train | step 3906 | loss 101.2366 198.7848 305.7538 499.4826 732.5301 1058.3550 1485.8965 2134.4485 2983.3430 4626.3867 7653.3638 13572.4014 | lr 1.6e-04 | norm 4559.8325 | dt 9.878 +type train | step 3907 | loss 89.1588 177.9640 288.1009 480.0583 717.1862 1045.4785 1480.7034 2143.9861 3049.1179 4721.0996 7766.7720 13714.7764 | lr 1.6e-04 | norm 5197.5957 | dt 9.873 +type train | step 3908 | loss 99.1078 196.9408 305.7314 497.8068 732.3846 1064.8384 1495.0004 2139.6455 2981.6799 4608.9204 7539.0044 13290.4365 | lr 1.6e-04 | norm 3683.9910 | dt 9.883 +type train | step 3909 | loss 92.0936 184.0474 297.8935 495.4489 732.5367 1053.8463 1483.1201 2133.5195 3029.6309 4722.2432 7874.3721 13950.4199 | lr 1.6e-04 | norm 4801.4409 | dt 9.865 +type train | step 3910 | loss 93.2588 186.9477 293.5472 481.9610 716.4874 1043.9960 1476.7695 2129.2505 2990.8328 4624.3701 7593.5854 13360.7793 | lr 1.6e-04 | norm 3633.0125 | dt 9.902 +type train | step 3911 | loss 91.3238 177.4885 282.6002 466.4559 695.3195 1008.9116 1427.4028 2059.9192 2925.5352 4553.0317 7522.6987 13252.9922 | lr 1.6e-04 | norm 3777.3240 | dt 9.922 +type train | step 3912 | loss 104.7964 208.9102 319.7825 509.0158 741.5271 1060.2196 1473.6843 2099.3213 2920.4998 4458.2109 7283.2432 12705.9756 | lr 1.6e-04 | norm 4608.2026 | dt 9.892 +type train | step 3913 | loss 96.3225 189.9748 301.6726 492.1995 728.0966 1052.2441 1476.0414 2115.1079 2966.9504 4573.3145 7502.2383 13241.6826 | lr 1.6e-04 | norm 3663.9224 | dt 9.856 +type train | step 3914 | loss 94.8534 188.7715 303.2014 502.5080 745.6138 1091.7189 1546.2949 2226.8032 3130.0044 4825.7695 7942.6880 14132.9502 | lr 1.6e-04 | norm 4311.5645 | dt 9.888 +type train | step 3915 | loss 95.2273 187.5651 296.5210 483.5442 717.6735 1044.9065 1469.4670 2116.9602 2977.8352 4606.1250 7562.3018 13381.8086 | lr 1.6e-04 | norm 4012.9917 | dt 9.877 +type train | step 3916 | loss 95.4658 189.8633 298.8897 485.6346 720.0623 1033.7931 1455.5844 2085.3689 2943.9243 4548.0425 7475.3701 13137.6016 | lr 1.6e-04 | norm 3675.2014 | dt 9.874 +type train | step 3917 | loss 92.7642 182.3815 288.1253 471.8394 699.6044 1012.4336 1426.1417 2041.0670 2877.9563 4439.7832 7289.7954 12739.4521 | lr 1.6e-04 | norm 3276.7822 | dt 9.889 +type train | step 3918 | loss 96.3274 188.8335 295.7393 483.9565 716.6812 1032.2407 1449.6431 2071.8254 2893.7532 4461.9102 7376.3521 13103.1338 | lr 1.6e-04 | norm 3720.1848 | dt 9.876 +type train | step 3919 | loss 88.8565 174.6565 280.4270 469.2801 702.1661 1023.4248 1452.2545 2086.7039 2933.1287 4568.7661 7562.0962 13427.7090 | lr 1.6e-04 | norm 4755.6592 | dt 9.872 +type train | step 3920 | loss 93.7182 183.3720 289.0804 474.2044 704.2175 1024.1949 1446.4065 2084.5132 2947.4543 4551.4009 7502.7715 13202.0889 | lr 1.6e-04 | norm 3775.8237 | dt 9.885 +type train | step 3921 | loss 90.2960 178.1146 284.8076 472.8279 701.1474 1016.8743 1435.7145 2068.1592 2915.5720 4497.2109 7430.7041 13163.7021 | lr 1.6e-04 | norm 3812.7085 | dt 9.879 +type train | step 3922 | loss 88.6264 171.8951 276.0410 459.9833 689.7319 1003.8990 1426.0551 2068.1484 2942.1787 4607.2393 7632.5479 13567.2041 | lr 1.6e-04 | norm 4287.4907 | dt 9.863 +type train | step 3923 | loss 90.0979 178.3369 286.1816 476.9684 710.6596 1028.3394 1453.2783 2095.2642 2957.2737 4581.3911 7528.7388 13213.0322 | lr 1.6e-04 | norm 4184.7842 | dt 9.867 +type train | step 3924 | loss 90.3830 177.2472 279.8733 459.9438 684.6049 991.9485 1399.6493 2010.2246 2842.4082 4413.7070 7289.2075 12984.5781 | lr 1.6e-04 | norm 4215.8940 | dt 9.878 +type train | step 3925 | loss 96.8358 192.4301 301.9049 489.9816 725.9955 1052.6787 1483.4019 2130.6394 2998.5376 4637.1367 7661.5371 13569.2607 | lr 1.6e-04 | norm 3951.6289 | dt 9.865 +type train | step 3926 | loss 108.4112 215.0467 332.5491 528.9824 772.6204 1135.2048 1600.6411 2303.8154 3164.3369 4801.4946 7879.2520 13900.7402 | lr 1.6e-04 | norm 5519.9521 | dt 9.855 +type train | step 3927 | loss 89.4364 173.6186 279.2903 463.6169 694.4907 1009.2264 1440.1848 2086.4766 2973.5215 4638.6562 7665.8496 13458.0840 | lr 1.6e-04 | norm 4618.2378 | dt 9.862 +type train | step 3928 | loss 78.2891 153.0499 255.9251 436.9297 672.8014 1000.3676 1454.3937 2139.7742 3061.5190 4882.3076 8018.1440 14088.2520 | lr 1.6e-04 | norm 7817.4644 | dt 9.844 +type train | step 3929 | loss 95.8276 187.9517 295.4742 484.9449 714.3592 1038.2373 1460.6968 2092.4541 2928.6936 4489.7969 7370.2163 12972.6992 | lr 1.6e-04 | norm 3711.0786 | dt 9.879 +type train | step 3930 | loss 89.6834 176.3459 280.4847 461.0030 687.5557 994.7389 1403.2111 2024.6636 2864.2117 4429.4111 7271.9404 12755.5977 | lr 1.6e-04 | norm 3696.2449 | dt 9.880 +type train | step 3931 | loss 87.4557 171.7219 275.6325 460.2437 691.7171 1007.5127 1433.8236 2076.4404 2957.9666 4591.3071 7541.3828 13232.9316 | lr 1.6e-04 | norm 3651.3643 | dt 9.882 +type train | step 3932 | loss 99.4240 196.3364 306.5374 495.7096 731.3281 1056.8099 1477.6870 2113.9956 2959.9949 4557.8467 7483.3350 13166.4902 | lr 1.6e-04 | norm 3334.8442 | dt 9.871 +type train | step 3933 | loss 106.2807 211.4784 327.1060 527.2335 771.4022 1128.2034 1584.3301 2279.8015 3171.6443 4798.1270 7840.1235 13725.0713 | lr 1.6e-04 | norm 6201.6445 | dt 9.857 +type train | step 3934 | loss 101.0040 201.0831 315.3810 514.8242 762.6401 1106.8975 1541.7617 2193.3132 3104.8101 4741.1089 7717.0410 13483.7061 | lr 1.6e-04 | norm 6519.1870 | dt 9.860 +type train | step 3935 | loss 97.3752 194.8151 302.9761 495.0727 731.6760 1059.3256 1485.6086 2130.1521 3008.5610 4635.8179 7580.5410 13315.8594 | lr 1.6e-04 | norm 3809.3872 | dt 9.890 +type train | step 3936 | loss 94.6238 185.3660 293.3148 487.5973 725.7748 1070.0969 1517.5106 2188.6980 3053.2483 4705.8335 7739.2739 13768.2334 | lr 1.6e-04 | norm 5278.5942 | dt 9.852 +type train | step 3937 | loss 100.6538 198.2327 308.9460 503.5017 737.6948 1064.8212 1487.8923 2121.0898 2956.8674 4546.2686 7462.9316 13161.0039 | lr 1.6e-04 | norm 4405.6992 | dt 9.879 +type train | step 3938 | loss 95.7952 186.5851 294.3777 479.7184 710.0663 1029.6172 1443.1044 2066.6443 2903.8225 4477.5752 7362.4839 12988.7793 | lr 1.6e-04 | norm 3527.3137 | dt 9.881 +type train | step 3939 | loss 87.6451 174.0845 274.5766 455.0630 684.7050 1003.5066 1438.0154 2082.4517 2972.5125 4664.9111 7749.0776 13848.9619 | lr 1.6e-04 | norm 4809.8174 | dt 9.867 +type train | step 3940 | loss 92.7004 181.4997 289.1634 476.9250 710.1505 1037.0210 1471.6630 2124.6448 3011.7527 4675.5894 7720.4082 13724.2539 | lr 1.6e-04 | norm 4727.1860 | dt 9.873 +type train | step 3941 | loss 89.1592 177.2316 285.8215 475.6830 719.1787 1054.2953 1499.2458 2174.1311 3065.8003 4769.7969 7811.0493 13658.6328 | lr 1.6e-04 | norm 4677.6924 | dt 9.881 +type train | step 3942 | loss 103.3750 201.6517 314.5398 511.4709 747.4462 1086.5015 1521.7222 2194.9219 3021.7598 4675.7573 7708.3584 13761.1543 | lr 1.6e-04 | norm 5480.0562 | dt 9.860 +type train | step 3943 | loss 87.0780 175.4551 282.6415 470.5936 702.9766 1020.0546 1442.9150 2080.4634 2969.4822 4638.3198 7689.5845 13609.1270 | lr 1.6e-04 | norm 4669.8945 | dt 9.878 +type train | step 3944 | loss 97.2110 190.6666 297.4206 487.5255 718.0444 1049.7990 1480.4579 2128.5676 2971.5635 4575.2852 7496.0459 13165.6875 | lr 1.6e-04 | norm 3954.6250 | dt 9.873 +type train | step 3945 | loss 91.8599 180.5546 283.8525 467.8900 698.4421 1015.0995 1442.4177 2079.4473 2945.8374 4577.2324 7562.5229 13420.6191 | lr 1.6e-04 | norm 5142.5698 | dt 9.870 +type train | step 3946 | loss 96.9915 192.1492 302.5508 497.5379 730.6157 1059.5466 1485.5895 2127.8030 2968.8579 4585.0361 7575.8203 13448.2666 | lr 1.6e-04 | norm 4058.9905 | dt 9.862 +type train | step 3947 | loss 114.0244 232.2242 360.3629 582.1837 838.1523 1204.5276 1649.4912 2346.7612 3210.1353 4890.7988 7993.4258 14221.8672 | lr 1.6e-04 | norm 5281.2397 | dt 9.833 +type train | step 3948 | loss 95.4766 189.2978 301.3975 494.2212 734.0254 1065.5642 1497.9940 2149.3062 3020.6062 4667.4639 7690.0527 13519.3701 | lr 1.6e-04 | norm 4172.0396 | dt 9.875 +type train | step 3949 | loss 100.9508 196.9047 305.2739 494.9639 731.5580 1060.2715 1492.6294 2137.6348 2991.7031 4644.5220 7653.5811 13490.0000 | lr 1.6e-04 | norm 4765.4302 | dt 9.871 +type train | step 3950 | loss 91.4976 181.4938 285.6231 470.4706 698.7385 1005.8969 1416.2009 2032.1013 2859.5112 4413.4707 7240.8750 12755.8203 | lr 1.6e-04 | norm 4199.0972 | dt 9.884 +type train | step 3951 | loss 90.9298 178.0351 281.3486 463.2488 691.0642 1000.5239 1414.5876 2038.8304 2888.0349 4478.0669 7371.8892 12980.0176 | lr 1.6e-04 | norm 3486.9236 | dt 9.885 +type train | step 3952 | loss 97.3714 192.4423 301.4385 491.2804 718.2191 1045.0854 1468.9072 2105.6631 2947.8704 4554.5225 7492.0479 13232.5596 | lr 1.6e-04 | norm 3579.4048 | dt 9.881 +type train | step 3953 | loss 96.6677 191.3191 299.0437 486.4146 715.3190 1032.3267 1452.7013 2088.7388 2930.7942 4573.2681 7588.8535 13480.4297 | lr 1.6e-04 | norm 4309.7788 | dt 9.865 +type train | step 3954 | loss 99.3650 196.9700 306.8843 500.1079 738.2945 1069.4398 1504.2186 2156.9775 3026.9314 4628.9346 7563.8965 13289.7051 | lr 1.6e-04 | norm 4225.2822 | dt 9.870 +type train | step 3955 | loss 96.0743 192.0030 304.3138 502.5528 736.2205 1066.3394 1498.4512 2136.8545 3008.4888 4662.7886 7727.6304 13735.9434 | lr 1.6e-04 | norm 4477.8130 | dt 9.877 +type train | step 3956 | loss 96.8877 191.4295 301.0615 494.4622 731.4946 1052.1292 1480.0940 2106.9883 2968.2524 4585.8467 7637.9160 13533.8838 | lr 1.6e-04 | norm 4100.2632 | dt 9.884 +type train | step 3957 | loss 99.8007 198.6980 310.3652 502.5801 738.2264 1066.0037 1495.6241 2139.8735 2992.8108 4606.6333 7576.8149 13410.9023 | lr 1.6e-04 | norm 3603.5862 | dt 9.888 +type train | step 3958 | loss 104.3358 204.5505 315.4121 513.2933 745.6931 1070.7220 1492.2225 2120.4329 2935.4114 4493.3140 7388.4072 12971.8506 | lr 1.6e-04 | norm 3890.4644 | dt 9.860 +type train | step 3959 | loss 105.2833 206.4046 317.0067 518.9455 757.4817 1101.2928 1531.1740 2191.3508 3018.8857 4610.2935 7567.1514 13363.0342 | lr 1.6e-04 | norm 5266.2246 | dt 9.868 +type train | step 3960 | loss 95.3135 188.3111 295.3673 483.6768 715.2169 1036.1052 1456.3689 2088.4312 2956.3137 4586.0347 7567.7329 13325.8877 | lr 1.6e-04 | norm 3477.0132 | dt 9.868 +type train | step 3961 | loss 90.6198 179.2526 287.7125 478.4138 706.6260 1022.6746 1442.2131 2082.0095 2916.6787 4479.0420 7504.0444 13420.3369 | lr 1.6e-04 | norm 7724.4849 | dt 9.854 +type train | step 3962 | loss 98.3038 194.0357 302.3768 490.6509 720.9554 1040.8616 1457.3243 2071.1997 2908.8457 4500.5068 7403.9561 13020.2324 | lr 1.6e-04 | norm 3526.2502 | dt 9.871 +type train | step 3963 | loss 94.4848 185.2713 291.8184 476.7013 705.0765 1019.0394 1437.8368 2070.8291 2914.1133 4518.3408 7445.5835 13141.8311 | lr 1.6e-04 | norm 4134.4390 | dt 9.889 +type train | step 3964 | loss 95.2830 189.1609 297.5303 485.3963 721.5659 1044.4353 1473.2239 2119.0408 2996.4431 4651.3589 7728.0967 13611.0215 | lr 1.6e-04 | norm 6027.6509 | dt 9.878 +type train | step 3965 | loss 98.6826 195.4094 304.1804 491.9944 725.1793 1042.3325 1464.0859 2082.4941 2940.5730 4563.9082 7502.3306 13208.7051 | lr 1.6e-04 | norm 3726.8589 | dt 9.878 +type train | step 3966 | loss 91.6358 180.7757 286.1833 469.7978 696.5741 1008.4742 1429.2006 2051.1062 2896.6255 4478.2773 7341.7910 12922.2061 | lr 1.6e-04 | norm 3552.3057 | dt 9.873 +type train | step 3967 | loss 101.7336 199.2605 307.8465 492.0057 727.5864 1046.4175 1468.3658 2089.7632 2929.0381 4507.1934 7406.9028 13037.4883 | lr 1.6e-04 | norm 5425.9536 | dt 9.864 +type train | step 3968 | loss 95.7724 187.8521 293.0931 483.6931 710.7255 1026.2911 1444.1764 2066.6882 2872.5049 4432.8320 7323.8145 12959.3721 | lr 1.6e-04 | norm 3681.3660 | dt 9.889 +type train | step 3969 | loss 94.8652 189.9896 296.4312 484.6050 712.5111 1027.0051 1437.8733 2053.1836 2900.4351 4456.3628 7310.4805 12757.3965 | lr 1.6e-04 | norm 3155.2627 | dt 9.883 +type train | step 3970 | loss 97.3894 193.6546 304.6472 493.5793 729.8433 1057.4415 1490.3918 2135.3218 3024.6855 4712.7812 7824.3765 13870.9307 | lr 1.6e-04 | norm 4386.7783 | dt 9.871 +type train | step 3971 | loss 98.5979 194.1234 304.5562 496.3537 736.1953 1063.3243 1492.7826 2142.3945 3013.0896 4655.6567 7666.1543 13507.1855 | lr 1.6e-04 | norm 3927.8904 | dt 9.888 +type train | step 3972 | loss 98.3187 194.4931 307.6890 507.6713 737.0309 1079.6901 1506.6587 2150.1292 2959.5122 4528.2241 7376.2876 12968.4453 | lr 1.6e-04 | norm 5218.9180 | dt 9.850 +type train | step 3973 | loss 93.3988 187.2677 295.5488 486.1069 726.0209 1072.4346 1518.6733 2195.1077 3079.8115 4749.1680 7747.5977 13593.4775 | lr 1.5e-04 | norm 4763.8647 | dt 9.881 +type train | step 3974 | loss 97.7701 193.3454 299.4411 490.7139 717.9553 1037.9193 1453.9689 2071.6990 2877.4482 4413.2881 7248.8564 12755.6943 | lr 1.5e-04 | norm 3277.0532 | dt 9.874 +type train | step 3975 | loss 96.2311 191.7811 298.5023 481.9265 712.0803 1022.6318 1436.6851 2053.8188 2895.7942 4503.8120 7473.6475 13188.0664 | lr 1.5e-04 | norm 3261.5886 | dt 9.881 +type train | step 3976 | loss 94.9321 186.5964 292.9399 480.2425 711.1570 1027.5312 1441.1960 2066.5798 2917.0217 4521.7212 7447.7363 13084.3213 | lr 1.5e-04 | norm 3356.9221 | dt 9.885 +type train | step 3977 | loss 101.9880 203.7421 318.3719 517.1063 750.9207 1088.6119 1514.5682 2151.9697 2977.0869 4550.8291 7467.4004 13145.1367 | lr 1.5e-04 | norm 4194.9658 | dt 9.874 +type train | step 3978 | loss 94.9986 186.2217 293.1179 478.3953 707.1428 1033.7556 1465.2156 2115.0527 2955.4685 4525.9248 7354.5127 12880.8857 | lr 1.5e-04 | norm 3760.1716 | dt 9.863 +type train | step 3979 | loss 95.1114 187.6902 293.4993 484.1581 714.2191 1031.0187 1450.5909 2070.4460 2891.0649 4487.3574 7385.7812 13033.1777 | lr 1.5e-04 | norm 4390.0820 | dt 9.873 +type train | step 3980 | loss 102.5133 200.2495 313.5761 508.7096 747.9328 1076.0594 1502.8813 2147.2212 2996.0664 4628.1270 7625.8379 13497.8271 | lr 1.5e-04 | norm 4055.0186 | dt 9.872 +type train | step 3981 | loss 93.7850 183.9383 294.3154 487.5310 723.0532 1048.6121 1485.1736 2141.4243 3012.5649 4651.5259 7643.3306 13512.6318 | lr 1.5e-04 | norm 3948.3940 | dt 9.870 +type train | step 3982 | loss 99.7753 196.6366 305.0258 498.4262 730.6597 1056.4055 1484.4298 2125.2686 2954.5896 4531.1636 7440.8447 13138.9912 | lr 1.5e-04 | norm 3905.1497 | dt 9.872 +type train | step 3983 | loss 96.6241 190.8677 299.7646 492.0169 731.6433 1063.1803 1498.4601 2146.0991 3023.8748 4652.6616 7594.5195 13371.3418 | lr 1.5e-04 | norm 3771.1965 | dt 9.872 +type train | step 3984 | loss 90.0829 177.7851 285.9449 471.3820 702.2953 1022.5524 1452.6754 2096.9453 2973.5615 4618.6826 7612.7197 13423.6768 | lr 1.5e-04 | norm 3672.8494 | dt 9.871 +type train | step 3985 | loss 96.2247 190.3772 295.1996 484.2164 717.1849 1049.1503 1479.5361 2146.8784 2989.9624 4614.8643 7589.6738 13243.8613 | lr 1.5e-04 | norm 3726.6196 | dt 9.871 +type train | step 3986 | loss 102.0045 199.5401 308.7541 499.4463 733.6905 1059.6204 1483.1837 2115.9001 2949.9819 4535.1299 7494.1226 13334.4287 | lr 1.5e-04 | norm 4017.2397 | dt 9.890 +type train | step 3987 | loss 84.1594 160.1738 251.2596 416.2890 625.4491 938.2565 1334.9427 1943.0607 2750.1038 4213.8599 6828.6450 11852.4648 | lr 1.5e-04 | norm 9728.1924 | dt 9.837 +type train | step 3988 | loss 91.1437 178.7814 284.3475 469.7180 700.2606 1024.4656 1448.0002 2085.1001 2936.6838 4524.3716 7439.4067 13030.5938 | lr 1.5e-04 | norm 3404.3484 | dt 9.882 +type train | step 3989 | loss 90.1611 179.4398 286.7287 474.8564 706.4918 1026.9026 1448.1250 2074.0540 2925.7693 4523.2935 7484.9692 13153.2275 | lr 1.5e-04 | norm 3466.2688 | dt 9.876 +type train | step 3990 | loss 93.4046 184.7280 290.9053 481.7632 715.6579 1049.5099 1486.6837 2154.0608 3030.3105 4699.6626 7719.0688 13647.8633 | lr 1.5e-04 | norm 4157.5918 | dt 9.873 +type train | step 3991 | loss 92.5300 183.9624 292.9925 481.4257 714.2313 1036.4336 1459.8975 2092.5371 2948.7312 4591.3340 7610.6973 13431.2490 | lr 1.5e-04 | norm 3513.8535 | dt 9.887 +type train | step 3992 | loss 93.1754 183.2896 288.2167 473.1033 700.9328 1010.0351 1419.2947 2040.6697 2888.6096 4481.1343 7408.7549 13173.2100 | lr 1.5e-04 | norm 3969.8494 | dt 9.871 +type train | step 3993 | loss 92.5693 183.1768 289.9700 474.3160 704.3890 1020.6155 1439.4741 2067.7693 2939.6809 4551.7690 7499.7393 13093.8516 | lr 1.5e-04 | norm 3427.8689 | dt 9.870 +type train | step 3994 | loss 97.8195 192.9470 301.2763 492.3423 722.7338 1048.1803 1480.5042 2128.1746 2966.6753 4596.0654 7605.3931 13498.5498 | lr 1.5e-04 | norm 4151.5430 | dt 9.883 +type train | step 3995 | loss 108.7114 215.8092 335.1467 540.0712 784.9714 1128.8608 1576.7549 2239.9629 3083.8320 4726.7617 7791.5693 13811.7637 | lr 1.5e-04 | norm 6639.0923 | dt 9.866 +type train | step 3996 | loss 100.2142 197.6692 304.7675 494.6594 730.2936 1051.3682 1482.6880 2109.5918 2965.0986 4545.0972 7490.8726 13137.0361 | lr 1.5e-04 | norm 3619.6785 | dt 9.868 +type train | step 3997 | loss 97.3060 190.4475 298.9516 488.9265 722.3792 1042.3472 1469.0092 2097.4797 2944.7847 4551.2715 7545.6519 13365.2910 | lr 1.5e-04 | norm 4042.5405 | dt 9.875 +type train | step 3998 | loss 91.7363 181.0044 289.3654 476.3247 709.3705 1026.2716 1446.4762 2082.1458 2954.1758 4587.8911 7584.6138 13369.5430 | lr 1.5e-04 | norm 3329.5771 | dt 9.873 +type train | step 3999 | loss 84.2903 166.0237 267.6438 447.1051 676.2364 995.3682 1418.9441 2066.3901 2946.9534 4578.3872 7503.9014 13174.0166 | lr 1.5e-04 | norm 4465.8188 | dt 9.861 +type train | step 4000 | loss 94.4072 186.0570 294.1524 485.0604 718.8694 1037.4620 1455.6012 2081.6895 2932.4924 4533.8657 7460.4053 13149.6465 | lr 1.5e-04 | norm 3298.2944 | dt 9.878 +type train | step 4001 | loss 103.2519 202.2429 313.9288 512.6964 752.9249 1087.1591 1515.3663 2166.0442 2994.2388 4583.5439 7542.4922 13375.3867 | lr 1.5e-04 | norm 4519.4390 | dt 9.862 +type train | step 4002 | loss 100.2014 198.1062 303.4931 487.1366 715.6500 1036.9291 1453.6029 2087.1741 2924.7810 4486.2080 7341.9980 12862.1396 | lr 1.5e-04 | norm 3910.6487 | dt 9.874 +type train | step 4003 | loss 100.7633 198.9971 309.3102 499.6619 730.6425 1058.9353 1483.5596 2104.0393 2935.4170 4506.5752 7358.3511 12891.2012 | lr 1.5e-04 | norm 4330.1016 | dt 9.858 +type train | step 4004 | loss 100.2248 199.1108 308.2749 503.3511 737.0925 1070.1757 1500.5034 2140.0210 2975.4421 4563.3154 7540.1577 13295.6221 | lr 1.5e-04 | norm 3595.5791 | dt 9.874 +type train | step 4005 | loss 93.7108 187.4165 300.5223 495.6193 735.5940 1053.0812 1475.1632 2098.5037 2988.0347 4615.7754 7627.7012 13336.4824 | lr 1.5e-04 | norm 4423.3560 | dt 9.868 +type train | step 4006 | loss 92.6509 186.3449 299.9050 496.8015 737.7203 1082.1489 1526.7964 2196.8174 3087.5164 4754.5005 7854.9395 13929.3506 | lr 1.5e-04 | norm 4921.9551 | dt 9.886 +type train | step 4007 | loss 98.0449 195.3046 304.0555 496.4961 729.1837 1046.5414 1469.5143 2091.4170 2944.1479 4547.5498 7510.0806 13284.4951 | lr 1.5e-04 | norm 3418.1802 | dt 9.877 +type train | step 4008 | loss 100.1623 196.7421 305.6123 496.5752 727.4584 1049.5999 1467.2333 2100.7568 2917.5010 4508.7607 7398.1401 13071.4473 | lr 1.5e-04 | norm 3456.2644 | dt 9.883 +type train | step 4009 | loss 93.1690 184.1830 289.4041 474.5831 701.9037 1015.0338 1434.1920 2055.6028 2897.9285 4467.8545 7317.0645 12774.9922 | lr 1.5e-04 | norm 3235.9485 | dt 9.894 +type train | step 4010 | loss 96.9613 193.1330 297.9081 482.1013 706.9103 1027.2310 1441.0978 2067.4543 2898.6567 4507.0527 7482.8154 13284.6738 | lr 1.5e-04 | norm 4067.0298 | dt 9.889 +type train | step 4011 | loss 97.3391 195.0197 310.7513 503.6577 742.4191 1060.3940 1486.6364 2117.4663 2977.5149 4555.4980 7362.4336 12836.9404 | lr 1.5e-04 | norm 4735.0376 | dt 9.862 +type train | step 4012 | loss 83.1129 167.4821 274.0234 451.9959 685.0352 999.0168 1441.9601 2113.0007 3069.6243 4845.3184 7964.8418 14109.3096 | lr 1.5e-04 | norm 10000.4121 | dt 9.845 +type train | step 4013 | loss 91.1010 178.9937 283.4164 469.0739 699.2562 1013.0955 1427.3060 2052.0022 2893.9778 4477.5640 7404.6211 13087.5918 | lr 1.5e-04 | norm 3609.3718 | dt 9.884 +type train | step 4014 | loss 97.8560 192.4816 302.4413 496.5695 733.2335 1065.3600 1497.1267 2149.5957 3020.5371 4665.5854 7691.1099 13581.8672 | lr 1.5e-04 | norm 3347.9221 | dt 9.868 +type train | step 4015 | loss 90.2772 177.7240 285.7613 472.4941 704.3503 1027.2361 1444.9746 2078.2227 2919.5791 4509.8691 7480.1880 13157.9619 | lr 1.5e-04 | norm 4268.1138 | dt 9.867 +type train | step 4016 | loss 106.0596 209.2000 322.5781 517.0573 747.8829 1078.4487 1512.1675 2145.0049 2985.7917 4608.6982 7610.9722 13512.5703 | lr 1.5e-04 | norm 4186.6870 | dt 9.886 +type train | step 4017 | loss 97.9339 192.5412 301.5498 487.1539 717.2451 1032.4210 1448.1400 2074.1968 2918.9412 4491.7627 7356.8413 12894.3574 | lr 1.5e-04 | norm 3511.3252 | dt 9.886 +type train | step 4018 | loss 85.2849 166.9181 267.6475 443.5608 667.3930 968.1099 1373.3547 1983.0684 2823.1780 4384.8975 7233.1621 12813.9902 | lr 1.5e-04 | norm 4184.8091 | dt 9.865 +type train | step 4019 | loss 92.9832 184.9288 291.0480 478.6479 708.5996 1025.9901 1445.2040 2084.7327 2933.8230 4542.9756 7500.8379 13303.3613 | lr 1.5e-04 | norm 3427.7493 | dt 9.888 +type train | step 4020 | loss 89.9528 176.9926 282.6364 465.0815 699.2104 1010.4341 1428.8824 2054.3010 2910.5779 4505.6938 7422.2588 13077.5605 | lr 1.5e-04 | norm 3884.6423 | dt 9.867 +type train | step 4021 | loss 105.1825 209.7254 328.0789 527.0450 770.5753 1111.1119 1557.0688 2229.1638 3120.6553 4800.7051 7837.5640 13698.2773 | lr 1.5e-04 | norm 4734.8936 | dt 9.871 +type train | step 4022 | loss 95.1411 189.3582 298.7924 489.2330 723.3544 1046.1346 1474.3776 2121.9822 3011.0203 4645.1807 7590.7598 13222.0254 | lr 1.5e-04 | norm 4035.3064 | dt 9.866 +type train | step 4023 | loss 92.5889 190.5815 300.8712 504.1655 738.7143 1081.5232 1541.0537 2259.1973 3129.9324 4914.9404 8177.5645 14529.1777 | lr 1.5e-04 | norm 9442.9082 | dt 9.839 +type train | step 4024 | loss 98.5506 193.4636 305.0968 496.4564 727.8004 1048.0984 1467.8884 2094.5598 2927.4646 4535.9644 7550.1807 13481.2969 | lr 1.5e-04 | norm 4448.7686 | dt 9.883 +type train | step 4025 | loss 91.2158 181.5146 288.6972 473.8506 706.1152 1026.9969 1455.3962 2088.5586 2978.5364 4630.7056 7620.1924 13359.3330 | lr 1.5e-04 | norm 3862.2891 | dt 9.877 +type train | step 4026 | loss 98.7890 196.5669 303.7141 492.2362 723.3682 1044.4934 1466.6700 2109.4517 2964.1550 4646.1758 7719.3735 13749.6621 | lr 1.5e-04 | norm 5593.3398 | dt 9.860 +type train | step 4027 | loss 103.8708 206.1869 314.3087 504.8037 735.9860 1058.3097 1477.1292 2106.6213 2933.3152 4525.6924 7437.7358 13120.3447 | lr 1.5e-04 | norm 4328.0337 | dt 9.885 +type train | step 4028 | loss 97.6376 192.9112 302.6040 494.1732 731.0282 1062.4644 1493.9666 2151.0337 2997.5688 4610.3721 7607.3096 13410.9727 | lr 1.5e-04 | norm 3859.7805 | dt 9.883 +type train | step 4029 | loss 91.6401 179.4249 284.7996 471.3662 703.5491 1034.9537 1463.2239 2115.5806 2958.8906 4567.1006 7552.2812 13388.3164 | lr 1.5e-04 | norm 4367.0444 | dt 9.866 +type train | step 4030 | loss 87.0760 172.0123 274.8281 455.2825 683.5893 997.1676 1418.4487 2049.3674 2911.4597 4514.1948 7422.5942 13055.3477 | lr 1.5e-04 | norm 4009.9338 | dt 9.903 +type train | step 4031 | loss 92.2056 183.2887 290.5409 477.0366 711.6517 1022.6945 1447.2317 2086.7629 2989.6646 4613.3574 7519.0342 13054.6055 | lr 1.5e-04 | norm 4620.9775 | dt 9.863 +type train | step 4032 | loss 95.1738 187.2451 296.1810 489.5851 727.0255 1061.9653 1500.7942 2157.2271 3019.4272 4658.2178 7664.8818 13585.0811 | lr 1.5e-04 | norm 4353.3862 | dt 9.870 +type train | step 4033 | loss 94.5485 187.2795 295.5841 485.1451 718.5837 1037.5559 1461.2648 2092.0410 2927.3579 4489.6265 7394.5469 13017.0791 | lr 1.5e-04 | norm 3881.7935 | dt 9.874 +type train | step 4034 | loss 96.6231 192.3353 299.4959 488.8423 723.9044 1041.0930 1464.2266 2093.7295 2956.7886 4589.9785 7564.9380 13328.1182 | lr 1.5e-04 | norm 3811.3738 | dt 9.880 +type train | step 4035 | loss 95.8171 192.1042 298.8101 484.6393 716.5573 1042.5364 1473.4156 2115.5005 2955.1299 4531.2227 7437.3071 13045.4961 | lr 1.5e-04 | norm 3839.5308 | dt 9.865 +type train | step 4036 | loss 97.6410 192.8175 303.6072 495.1594 733.7966 1057.5344 1487.8107 2118.8823 2991.5667 4591.4893 7505.2686 13114.0371 | lr 1.5e-04 | norm 3470.0183 | dt 9.889 +type train | step 4037 | loss 92.2117 179.9676 283.6454 466.7889 696.6627 1013.4833 1433.9562 2064.5867 2921.1570 4515.5332 7439.5479 13132.7021 | lr 1.5e-04 | norm 3678.7629 | dt 9.863 +type train | step 4038 | loss 93.0880 184.9877 290.4449 480.5914 712.7391 1034.4603 1461.7931 2102.3853 2960.8860 4590.5591 7582.6489 13411.5752 | lr 1.5e-04 | norm 4173.5840 | dt 9.869 +type train | step 4039 | loss 119.4220 243.0079 364.8143 571.9119 845.2869 1227.3322 1726.0028 2454.2078 3331.4885 4948.2554 7881.7183 13661.1641 | lr 1.5e-04 | norm 5824.9038 | dt 9.860 +type train | step 4040 | loss 115.6605 228.3144 343.8723 540.6398 782.6516 1108.0138 1535.9944 2150.8616 2969.2012 4542.2109 7399.0239 13063.2070 | lr 1.5e-04 | norm 5421.8550 | dt 9.861 +type train | step 4041 | loss 91.3192 180.2967 283.5409 468.8456 697.5848 1013.2883 1434.3328 2072.4365 2932.5156 4554.2739 7470.7856 13111.2549 | lr 1.5e-04 | norm 3634.9399 | dt 9.871 +type train | step 4042 | loss 101.5818 200.3776 308.3659 500.8029 735.1301 1067.1367 1500.7704 2161.5649 3011.5549 4648.1533 7619.5098 13472.3096 | lr 1.5e-04 | norm 4133.4883 | dt 9.870 +type train | step 4043 | loss 100.4342 199.0523 310.0506 504.3032 740.5673 1065.5652 1490.2585 2128.9519 2975.1824 4593.2764 7587.4595 13400.3623 | lr 1.5e-04 | norm 3884.8428 | dt 9.881 +type train | step 4044 | loss 100.2950 196.9092 307.7944 505.2074 743.1271 1079.5981 1513.1796 2171.7944 3004.6218 4643.6152 7650.4653 13534.2549 | lr 1.5e-04 | norm 4579.5947 | dt 9.877 +type train | step 4045 | loss 91.3789 180.1782 285.5233 472.2805 702.4034 1022.7627 1445.9806 2075.4568 2926.4417 4481.2661 7368.0171 12924.5850 | lr 1.5e-04 | norm 4082.2603 | dt 9.871 +type train | step 4046 | loss 89.2043 176.4291 281.8664 464.6319 693.7986 1002.5614 1417.2955 2036.9717 2877.3398 4478.2026 7395.4316 13000.8467 | lr 1.5e-04 | norm 3775.5518 | dt 9.875 +type train | step 4047 | loss 97.4142 190.2568 299.2876 489.9429 720.8175 1043.4493 1470.9902 2112.3838 2965.3372 4566.9351 7494.2715 13241.3125 | lr 1.5e-04 | norm 4377.3110 | dt 9.879 +type train | step 4048 | loss 95.0099 188.2708 295.0021 482.5797 717.2337 1033.7357 1458.5696 2090.4873 2944.9487 4546.6060 7456.9395 13148.3604 | lr 1.5e-04 | norm 3912.4670 | dt 9.873 +type train | step 4049 | loss 98.5705 196.5522 309.7539 508.6483 753.3197 1120.5649 1597.6533 2342.2822 3244.8130 4981.6367 8059.4692 13924.3027 | lr 1.5e-04 | norm 4623.2437 | dt 9.858 +type train | step 4050 | loss 101.8031 200.2684 310.6039 508.1801 739.8000 1061.8514 1480.0249 2101.4678 2921.5518 4492.3887 7412.5010 13119.9424 | lr 1.5e-04 | norm 4126.7651 | dt 9.864 +type train | step 4051 | loss 99.0829 198.0087 308.1537 500.2895 735.1838 1057.1091 1482.7570 2118.6992 2989.5718 4609.3389 7544.9380 13270.8193 | lr 1.5e-04 | norm 4188.6987 | dt 9.885 +type train | step 4052 | loss 92.6848 181.6660 287.0515 474.1585 703.1948 1034.8505 1465.3174 2128.6409 2973.6895 4619.8369 7636.1909 13442.5469 | lr 1.5e-04 | norm 4187.4238 | dt 9.878 +type train | step 4053 | loss 96.2290 190.3277 295.4571 481.6831 713.1108 1051.8809 1488.7871 2166.2109 3030.9666 4690.5967 7762.0879 13784.9854 | lr 1.5e-04 | norm 5489.1914 | dt 9.866 +type train | step 4054 | loss 92.6731 181.8943 288.7910 475.1852 702.3519 1021.9400 1442.5784 2073.0767 2911.6035 4498.8022 7416.0640 13047.3203 | lr 1.5e-04 | norm 3647.6663 | dt 9.874 +type train | step 4055 | loss 97.8021 193.9544 304.8387 493.4406 730.1360 1061.4187 1494.3325 2141.8323 3019.5627 4688.9946 7744.6582 13752.6973 | lr 1.5e-04 | norm 4204.6611 | dt 9.881 +type train | step 4056 | loss 91.9563 181.6281 291.0844 478.0028 711.8432 1039.4216 1468.4956 2114.7759 2990.8569 4600.2563 7529.3721 13139.3008 | lr 1.5e-04 | norm 3046.9807 | dt 9.873 +type train | step 4057 | loss 94.5132 187.5576 294.0020 478.1604 708.7886 1038.5404 1475.3660 2131.6284 3001.7146 4664.5107 7665.7666 13470.7305 | lr 1.5e-04 | norm 4989.8779 | dt 9.877 +type train | step 4058 | loss 93.6408 184.1404 291.9131 481.4116 713.4189 1040.7759 1471.3783 2115.6531 2965.0681 4557.3018 7519.4180 13294.9160 | lr 1.5e-04 | norm 3774.2056 | dt 9.879 +type train | step 4059 | loss 93.1256 184.4420 293.2074 481.9775 718.5069 1041.2961 1471.0417 2115.1785 2993.2476 4625.2026 7577.8447 13322.4316 | lr 1.5e-04 | norm 3528.0354 | dt 9.891 +type train | step 4060 | loss 86.7774 178.8544 289.0128 486.0620 741.4554 1094.6310 1556.6187 2271.4561 3227.6709 5103.0488 8519.0059 14882.6357 | lr 1.5e-04 | norm 9039.1680 | dt 9.837 +type train | step 4061 | loss 96.6571 193.8363 300.9948 491.1154 723.7983 1044.1128 1466.0685 2097.9839 2955.5427 4605.5361 7606.3506 13431.3984 | lr 1.5e-04 | norm 3557.4819 | dt 9.895 +type train | step 4062 | loss 96.4854 190.5473 297.3060 480.1334 712.1554 1027.7703 1451.4850 2087.8767 2952.6702 4597.6553 7625.7407 13518.3730 | lr 1.5e-04 | norm 4176.6172 | dt 9.876 +type train | step 4063 | loss 93.5423 183.1952 292.2776 480.7073 715.3743 1049.6216 1491.6254 2166.3188 3050.5366 4739.9697 7884.1357 13990.3438 | lr 1.5e-04 | norm 5695.8032 | dt 9.856 +type train | step 4064 | loss 102.4276 201.5397 312.0058 502.0598 734.0889 1074.5509 1512.2823 2162.1526 3019.4995 4647.7148 7599.4189 13360.5723 | lr 1.5e-04 | norm 4326.8491 | dt 9.859 +type train | step 4065 | loss 95.9642 191.2476 297.1584 486.4228 718.2004 1042.9371 1471.0762 2110.8545 2961.8799 4563.3418 7537.4800 13331.6045 | lr 1.5e-04 | norm 4250.8267 | dt 9.877 +type train | step 4066 | loss 95.7962 188.1550 294.5109 480.3000 714.0647 1024.1649 1437.6328 2061.9807 2924.3142 4556.9248 7554.5801 13374.1074 | lr 1.5e-04 | norm 5191.7412 | dt 9.866 +type train | step 4067 | loss 101.7468 199.7544 310.4177 505.9650 743.3260 1072.1849 1504.9341 2160.1335 3029.1143 4708.9160 7818.6797 13925.4717 | lr 1.5e-04 | norm 6030.3696 | dt 9.857 +type train | step 4068 | loss 95.8340 188.6841 299.4125 490.2262 720.1700 1042.7446 1478.4042 2132.3643 3023.2649 4705.6274 7751.4307 13853.7383 | lr 1.5e-04 | norm 5053.2324 | dt 9.874 +type train | step 4069 | loss 89.9081 180.3855 288.8386 480.5686 715.7258 1035.5172 1465.5079 2110.8713 3003.3596 4689.4531 7744.2090 13779.8643 | lr 1.5e-04 | norm 4779.3916 | dt 9.857 +type train | step 4070 | loss 89.1459 176.5688 282.6947 467.5553 694.2092 1004.8905 1416.8536 2031.2478 2879.3833 4463.3501 7383.2202 13016.0742 | lr 1.5e-04 | norm 3296.1641 | dt 9.878 +type train | step 4071 | loss 90.9128 178.8805 285.3159 470.9152 699.9725 1018.5636 1446.1262 2091.7017 2961.8613 4587.0439 7545.4712 13197.4229 | lr 1.5e-04 | norm 3370.0378 | dt 9.872 +type train | step 4072 | loss 95.3512 191.5525 298.1712 488.9392 722.4259 1046.0446 1475.9276 2117.3284 2973.1475 4576.0845 7533.9619 13240.7988 | lr 1.5e-04 | norm 3410.1650 | dt 9.877 +type train | step 4073 | loss 98.6512 195.7683 304.4457 492.6035 727.3253 1055.0997 1479.1202 2106.5518 2942.5312 4540.2080 7445.6094 13053.2070 | lr 1.5e-04 | norm 3784.9824 | dt 9.871 +type train | step 4074 | loss 101.7760 201.5251 313.0934 506.3514 739.3731 1065.5486 1493.1984 2124.9319 2969.4907 4584.0137 7588.3652 13470.4629 | lr 1.5e-04 | norm 4070.2366 | dt 9.878 +type train | step 4075 | loss 103.5768 207.3515 323.1414 519.3536 756.6053 1084.8124 1513.2682 2158.2263 3007.2927 4657.8984 7693.2012 13595.5869 | lr 1.4e-04 | norm 5376.9902 | dt 9.880 +type train | step 4076 | loss 96.3214 190.3872 300.9527 492.3593 723.6542 1037.8845 1452.2003 2073.5952 2906.8223 4485.3931 7431.4316 13128.5654 | lr 1.4e-04 | norm 3642.8645 | dt 9.877 +type train | step 4077 | loss 91.9599 181.3572 285.3066 465.8369 692.3868 1011.1659 1430.1067 2057.0173 2904.2996 4502.7090 7427.0723 13110.2207 | lr 1.4e-04 | norm 3892.3931 | dt 10.190 +type train | step 4078 | loss 93.4968 185.4939 292.3069 478.0256 706.7631 1024.2043 1436.1053 2067.5684 2916.8855 4492.2568 7439.1094 13131.8682 | lr 1.4e-04 | norm 4882.6089 | dt 9.875 +type train | step 4079 | loss 99.0692 194.9052 305.4988 498.5429 728.9800 1047.1924 1463.9022 2086.1907 2914.3870 4478.2017 7360.2627 13007.7900 | lr 1.4e-04 | norm 3685.7971 | dt 9.866 +type train | step 4080 | loss 103.4343 203.6609 316.0685 512.9079 747.4802 1086.3699 1519.2935 2174.3457 3019.0686 4662.2090 7733.6968 13849.4150 | lr 1.4e-04 | norm 4207.7397 | dt 9.881 +type train | step 4081 | loss 98.1246 191.8707 304.0579 498.7910 732.3088 1071.9446 1513.7302 2165.0781 2988.8232 4588.2842 7526.2017 13359.9941 | lr 1.4e-04 | norm 4906.0508 | dt 9.862 +type train | step 4082 | loss 87.7110 172.4680 274.4593 455.5705 680.9880 986.4608 1399.1007 2018.2737 2852.0039 4431.1230 7336.7754 12944.2568 | lr 1.4e-04 | norm 3794.9504 | dt 9.867 +type train | step 4083 | loss 90.9768 180.2981 285.1115 467.3458 695.0674 1010.6891 1433.2482 2064.0339 2923.8872 4525.1660 7472.5415 13106.7500 | lr 1.4e-04 | norm 3534.6870 | dt 9.876 +type train | step 4084 | loss 97.7824 192.5706 304.5396 497.7805 734.9709 1057.3533 1484.8884 2114.5156 2980.9758 4588.8428 7526.5923 13161.0566 | lr 1.4e-04 | norm 3315.0610 | dt 9.883 +type train | step 4085 | loss 92.0937 181.5048 288.5696 477.8760 706.4084 1020.4380 1437.0181 2059.6565 2910.8630 4499.5933 7463.8276 13227.4648 | lr 1.4e-04 | norm 3633.0007 | dt 9.877 +type train | step 4086 | loss 89.0818 175.2443 278.1848 459.3225 682.3342 993.3777 1413.5715 2038.7234 2885.4141 4476.4165 7357.5376 12891.3613 | lr 1.4e-04 | norm 3387.3289 | dt 9.891 +type train | step 4087 | loss 95.7551 187.9449 294.7692 478.6350 710.3856 1021.0183 1436.2568 2049.4841 2896.0840 4512.5542 7485.1870 13213.6709 | lr 1.4e-04 | norm 4419.8198 | dt 9.873 +type train | step 4088 | loss 106.9295 211.8009 322.5993 510.8453 740.9418 1070.5320 1484.8636 2102.7576 2878.3882 4421.6680 7287.4561 13089.8252 | lr 1.4e-04 | norm 6702.8252 | dt 9.850 +type train | step 4089 | loss 92.9093 181.6906 283.3552 465.8980 690.6957 994.4415 1400.0469 2003.1000 2822.6497 4398.2920 7276.6719 12857.7266 | lr 1.4e-04 | norm 4398.2749 | dt 9.871 +type train | step 4090 | loss 97.1234 190.1540 298.0341 489.9949 721.0130 1038.0978 1456.6628 2092.8140 2946.1606 4569.2212 7542.0400 13382.2637 | lr 1.4e-04 | norm 3964.8176 | dt 9.866 +type train | step 4091 | loss 92.0639 181.0074 284.9197 465.5266 689.6889 997.1665 1405.9905 2025.0815 2872.8838 4482.1196 7420.8750 13000.0020 | lr 1.4e-04 | norm 3368.5405 | dt 9.875 +type train | step 4092 | loss 87.4308 171.9415 274.1378 454.7411 680.9437 985.8122 1393.1610 2002.8555 2844.5974 4424.6250 7251.6924 12734.3203 | lr 1.4e-04 | norm 3191.0942 | dt 9.877 +type train | step 4093 | loss 97.8868 191.3564 298.2693 484.6083 717.5662 1047.6178 1470.1530 2116.0352 2965.3840 4582.4771 7555.2173 13335.2119 | lr 1.4e-04 | norm 4026.2197 | dt 9.866 +type train | step 4094 | loss 86.7464 170.1055 273.5402 454.1223 679.9287 997.8659 1421.2429 2063.1973 2919.9697 4566.2651 7568.2246 13374.4971 | lr 1.4e-04 | norm 4184.8340 | dt 9.874 +type train | step 4095 | loss 96.9654 191.6000 301.6042 493.1477 724.3421 1049.1041 1471.1033 2104.0669 2951.6362 4598.3193 7622.5649 13508.9990 | lr 1.4e-04 | norm 3767.0815 | dt 9.876 +type train | step 4096 | loss 93.8672 184.7890 291.7744 476.0561 706.1065 1019.5381 1429.2388 2044.9990 2885.0171 4473.1021 7394.1206 12991.8525 | lr 1.4e-04 | norm 3161.2656 | dt 9.884 +type train | step 4097 | loss 87.6712 171.8865 273.7729 454.2452 678.5325 989.4683 1397.5986 2013.8801 2840.6406 4403.4526 7245.3330 12724.0557 | lr 1.4e-04 | norm 3420.5308 | dt 9.868 +type train | step 4098 | loss 92.8313 181.1470 284.3117 466.2200 689.8097 1006.4729 1428.8511 2056.6624 2901.1301 4523.0811 7527.1538 13301.8535 | lr 1.4e-04 | norm 3691.8623 | dt 9.865 +type train | step 4099 | loss 88.9164 175.3056 276.3612 453.5022 677.5461 984.2297 1390.6022 1996.0247 2839.4780 4405.1899 7268.1255 12730.5947 | lr 1.4e-04 | norm 3039.2495 | dt 9.879 +type train | step 4100 | loss 92.3238 182.2417 289.4897 471.0269 699.7114 1016.9388 1437.3041 2067.0017 2908.6509 4511.6494 7440.0957 13157.2959 | lr 1.4e-04 | norm 4059.2278 | dt 9.866 +type train | step 4101 | loss 93.8493 185.2984 292.6136 481.1151 713.6184 1039.0789 1462.1842 2098.2375 2945.5698 4539.9199 7494.3701 13207.8711 | lr 1.4e-04 | norm 3342.8052 | dt 9.868 +type train | step 4102 | loss 84.1628 163.5268 263.2062 438.9814 661.0424 959.5328 1361.6343 1968.3503 2826.7344 4430.8418 7372.7036 13035.0771 | lr 1.4e-04 | norm 3604.3115 | dt 9.871 +type train | step 4103 | loss 89.7791 173.2417 273.1055 447.1907 666.1147 973.0206 1381.1886 2005.6360 2847.4814 4437.9185 7333.5923 12967.3789 | lr 1.4e-04 | norm 4254.3882 | dt 9.864 +type train | step 4104 | loss 105.1829 205.1566 314.8538 505.0284 735.5878 1050.7709 1473.8241 2094.9451 2943.6765 4553.5205 7520.3208 13338.6660 | lr 1.4e-04 | norm 6537.0361 | dt 9.859 +type train | step 4105 | loss 102.6477 206.4859 314.2457 502.5955 737.6395 1072.7689 1511.7595 2170.9255 3010.8855 4650.2266 7638.3066 13574.9404 | lr 1.4e-04 | norm 6164.1782 | dt 9.847 +type train | step 4106 | loss 98.1498 193.6714 300.7042 485.7037 712.8739 1039.1139 1456.8176 2097.6694 2912.8813 4471.8789 7276.1875 12698.7051 | lr 1.4e-04 | norm 3340.1619 | dt 9.883 +type train | step 4107 | loss 102.5105 201.4259 315.4942 518.7044 757.6181 1104.2139 1547.5470 2241.8164 3130.4688 4874.9219 8113.3896 14517.7139 | lr 1.4e-04 | norm 6181.5029 | dt 9.850 +type train | step 4108 | loss 105.4253 206.0992 313.7808 503.2425 734.3011 1061.0050 1482.7831 2120.2422 2957.5945 4585.4810 7569.2627 13338.3145 | lr 1.4e-04 | norm 4725.1777 | dt 9.868 +type train | step 4109 | loss 94.6380 186.7481 292.4786 474.0900 701.4109 1015.4814 1430.7314 2062.4465 2886.4226 4433.1543 7243.7661 12719.9717 | lr 1.4e-04 | norm 4109.0752 | dt 9.865 +type train | step 4110 | loss 119.4020 234.9509 357.0840 551.9413 784.6506 1117.3904 1552.8376 2197.6108 2988.9482 4619.3174 7778.7505 13781.2754 | lr 1.4e-04 | norm 9266.1514 | dt 9.842 +type train | step 4111 | loss 96.9396 189.4888 296.5484 480.3575 701.7980 1013.6077 1421.1018 2032.8507 2835.4204 4381.3584 7248.5269 12819.4580 | lr 1.4e-04 | norm 3985.0071 | dt 9.853 +type train | step 4112 | loss 91.8800 181.4346 282.7099 460.9692 683.9769 991.2357 1408.3666 2027.3665 2862.9646 4460.7158 7350.0361 12923.2607 | lr 1.4e-04 | norm 5087.5220 | dt 9.876 +type train | step 4113 | loss 96.2047 188.5963 294.3943 483.0451 712.4333 1022.5270 1437.4475 2056.7158 2902.3997 4479.4097 7402.7812 13047.0010 | lr 1.4e-04 | norm 3546.6709 | dt 9.883 +type train | step 4114 | loss 94.0668 187.2722 292.0455 481.9608 712.0317 1028.4761 1444.1804 2080.5374 2919.1492 4547.3066 7506.0767 13271.9863 | lr 1.4e-04 | norm 4077.0452 | dt 9.852 +type train | step 4115 | loss 86.0165 170.4335 273.1158 453.7169 677.6343 988.8305 1408.6215 2039.5011 2898.9956 4519.2856 7452.7158 13059.9775 | lr 1.4e-04 | norm 3880.5681 | dt 9.876 +type train | step 4116 | loss 95.8323 189.7592 297.4014 479.8107 711.5429 1013.2021 1423.4172 2032.5608 2869.6865 4441.9263 7279.8696 12764.4932 | lr 1.4e-04 | norm 3922.0859 | dt 9.876 +type train | step 4117 | loss 93.3009 184.8678 289.4987 478.3791 702.8453 1024.6792 1441.2950 2078.6426 2929.6819 4544.9365 7483.2104 13165.3350 | lr 1.4e-04 | norm 3731.5967 | dt 9.871 +type train | step 4118 | loss 91.7259 182.2198 289.2014 475.7700 705.2026 1028.5928 1453.0198 2098.2285 2959.0303 4605.5352 7599.5669 13406.1172 | lr 1.4e-04 | norm 3637.5020 | dt 9.867 +type train | step 4119 | loss 98.8260 195.7559 304.9609 496.5269 723.6505 1046.6525 1474.4575 2113.8372 2940.0610 4584.5835 7576.4600 13459.0879 | lr 1.4e-04 | norm 6719.8188 | dt 9.852 +type train | step 4120 | loss 90.3297 174.8018 277.3035 457.7571 683.7504 1002.6517 1420.4630 2060.0088 2890.4570 4498.4697 7402.6802 13099.0586 | lr 1.4e-04 | norm 5900.4136 | dt 9.854 +type train | step 4121 | loss 88.4380 174.6907 275.8356 454.3517 678.2806 1004.5579 1428.4041 2075.2959 2921.4011 4521.7988 7408.4751 13015.3203 | lr 1.4e-04 | norm 4283.6353 | dt 9.850 +type train | step 4122 | loss 101.7123 198.2069 310.5446 500.5581 735.3071 1070.6718 1501.2141 2145.9221 2998.9854 4580.2485 7427.8457 12895.4326 | lr 1.4e-04 | norm 3280.3826 | dt 9.884 +type train | step 4123 | loss 102.6988 204.8128 313.9066 506.8097 738.0877 1071.0258 1485.5491 2116.6228 2873.6619 4361.3477 7127.0752 12657.4971 | lr 1.4e-04 | norm 7394.3237 | dt 9.850 +type train | step 4124 | loss 96.2733 189.3118 296.3743 479.9854 708.6305 1028.5280 1445.9480 2073.6487 2895.0007 4479.4946 7392.1875 13076.0869 | lr 1.4e-04 | norm 4287.9517 | dt 9.860 +type train | step 4125 | loss 95.4994 188.0113 293.2389 480.1639 705.8175 1021.4000 1431.5674 2046.8757 2875.2769 4433.4790 7340.1211 12957.2051 | lr 1.4e-04 | norm 3593.5640 | dt 9.866 +type train | step 4126 | loss 93.3513 184.8496 291.7740 478.1326 710.6623 1027.6432 1442.2778 2061.9822 2915.5320 4511.1172 7446.6807 13114.9258 | lr 1.4e-04 | norm 3483.1589 | dt 9.875 +type train | step 4127 | loss 97.0771 194.2415 306.7084 501.4990 739.8260 1073.8778 1510.1251 2168.5071 3053.4365 4700.0815 7692.2368 13442.0303 | lr 1.4e-04 | norm 3859.0005 | dt 9.864 +type train | step 4128 | loss 100.7403 200.5898 313.9733 506.8250 741.1996 1060.5181 1478.4889 2096.3928 2915.0024 4470.0933 7316.1333 12860.7939 | lr 1.4e-04 | norm 3505.7390 | dt 9.872 +type train | step 4129 | loss 88.8646 175.5628 279.7627 462.4560 690.4270 1003.3164 1419.8707 2051.2063 2916.0691 4525.8701 7467.1099 13113.5020 | lr 1.4e-04 | norm 3476.2322 | dt 9.868 +type train | step 4130 | loss 88.7926 173.6917 276.4656 456.6589 682.2036 991.9346 1407.9419 2038.2650 2879.2209 4474.2695 7332.7661 12833.3701 | lr 1.4e-04 | norm 3319.5881 | dt 9.871 +type train | step 4131 | loss 95.6590 189.3912 295.6533 483.3632 713.7554 1038.2126 1457.3433 2096.3291 2941.7158 4550.1113 7502.0605 13260.7598 | lr 1.4e-04 | norm 3624.6472 | dt 9.864 +type train | step 4132 | loss 98.8087 196.1190 305.4362 500.9260 739.1766 1061.2720 1487.9535 2148.7834 3011.9485 4683.7861 7742.5361 13851.4336 | lr 1.4e-04 | norm 5673.9131 | dt 9.870 +type train | step 4133 | loss 93.3057 183.6060 290.0092 475.7793 708.4924 1024.0555 1447.7637 2077.6206 2931.5110 4551.8252 7535.6963 13278.0615 | lr 1.4e-04 | norm 3765.1987 | dt 9.883 +type train | step 4134 | loss 92.0205 185.7884 300.1032 497.3047 734.3655 1084.3978 1543.2510 2243.7397 3146.4153 4936.3901 8102.2368 14357.0586 | lr 1.4e-04 | norm 6829.9326 | dt 9.860 +type train | step 4135 | loss 91.6316 179.9706 286.1737 472.8575 703.8379 1014.4879 1427.7000 2052.6162 2896.9551 4492.3188 7399.0171 13022.4658 | lr 1.4e-04 | norm 3381.8665 | dt 9.877 +type train | step 4136 | loss 90.6059 180.2938 285.8914 469.9075 699.3202 1017.5518 1438.6017 2071.5356 2934.6724 4516.3867 7394.7329 12884.3242 | lr 1.4e-04 | norm 3692.0652 | dt 9.888 +type train | step 4137 | loss 99.0110 195.9366 305.4530 491.3603 724.1512 1045.6180 1466.9238 2102.8372 2929.7251 4534.9404 7493.9902 13235.4805 | lr 1.4e-04 | norm 3688.3938 | dt 9.880 +type train | step 4138 | loss 87.7705 178.8190 296.4584 497.5685 743.8929 1078.9275 1527.2820 2201.8750 3112.9751 4867.9258 8061.9497 14259.0400 | lr 1.4e-04 | norm 7044.0610 | dt 9.854 +type train | step 4139 | loss 90.2284 180.8055 290.9103 484.2487 721.5100 1051.6014 1485.5188 2148.7930 3020.2000 4749.7676 7918.7388 13982.3164 | lr 1.4e-04 | norm 5062.5654 | dt 9.856 +type train | step 4140 | loss 100.4806 199.6927 313.2076 519.8409 752.1728 1099.5848 1536.3329 2208.2563 3046.6628 4711.2920 7781.7476 13972.6631 | lr 1.4e-04 | norm 6156.6426 | dt 9.857 +type train | step 4141 | loss 89.3192 175.3998 278.4170 457.0801 682.0779 986.1721 1392.6129 2000.3054 2817.5762 4369.3745 7216.8120 12745.1289 | lr 1.4e-04 | norm 3976.5952 | dt 9.866 +type train | step 4142 | loss 92.9784 179.9523 286.8632 470.7242 699.9162 1016.0463 1433.7377 2062.4873 2909.5830 4528.0234 7500.5625 13254.0371 | lr 1.4e-04 | norm 3782.8943 | dt 9.876 +type train | step 4143 | loss 97.0271 191.1098 302.3034 492.0249 727.9138 1057.6509 1488.5933 2141.0886 3009.0703 4669.6562 7810.7231 13873.3291 | lr 1.4e-04 | norm 5313.2939 | dt 9.853 +type train | step 4144 | loss 92.6672 182.3188 285.6661 468.4373 692.6536 1004.2501 1416.1899 2032.9838 2861.4429 4437.6074 7343.2368 12962.0762 | lr 1.4e-04 | norm 3472.7153 | dt 9.866 +type train | step 4145 | loss 96.4746 189.4233 298.7162 489.3646 720.1381 1047.9513 1472.6249 2110.6113 2937.4724 4555.9253 7535.9351 13427.4785 | lr 1.4e-04 | norm 3985.5793 | dt 9.865 +type train | step 4146 | loss 93.5035 184.6960 289.4122 470.6508 695.8699 1008.8450 1422.1865 2043.7933 2886.9956 4479.1909 7398.3311 13084.4355 | lr 1.4e-04 | norm 3361.5776 | dt 9.874 +type train | step 4147 | loss 91.1995 179.6356 286.9258 475.2899 706.8917 1023.6758 1444.7134 2080.3279 2920.3833 4542.9453 7484.5132 13258.6582 | lr 1.4e-04 | norm 4328.0229 | dt 9.864 +type train | step 4148 | loss 102.2370 202.2493 313.9369 506.2585 733.7473 1052.4852 1459.2360 2068.6572 2863.6687 4392.7476 7219.8071 12833.3447 | lr 1.4e-04 | norm 4715.0723 | dt 9.847 +type train | step 4149 | loss 94.0033 183.8632 290.1758 474.5052 702.6807 1020.0412 1436.5524 2057.2444 2899.3787 4502.6641 7461.5654 13168.3818 | lr 1.4e-04 | norm 3618.1753 | dt 9.870 +type train | step 4150 | loss 97.6050 196.0159 306.8381 496.7136 729.6054 1048.2823 1474.3452 2114.7554 2973.0889 4597.2017 7600.6924 13454.5293 | lr 1.4e-04 | norm 5564.6533 | dt 9.871 +type train | step 4151 | loss 99.5804 192.9546 298.3972 485.0501 717.0443 1045.3671 1461.7139 2089.8218 2926.7571 4492.0762 7293.5054 12762.9766 | lr 1.4e-04 | norm 5606.0146 | dt 9.847 +type train | step 4152 | loss 88.2569 173.8848 275.3371 453.6680 675.6619 974.8031 1379.0908 1989.5522 2815.9539 4395.4976 7286.4419 12841.4082 | lr 1.4e-04 | norm 5269.5190 | dt 9.863 +type train | step 4153 | loss 91.2052 179.7292 284.2243 467.9175 691.2510 999.8848 1406.7593 2011.4647 2827.0874 4356.5273 7147.8110 12506.9092 | lr 1.4e-04 | norm 3497.1541 | dt 9.868 +type train | step 4154 | loss 92.8752 182.7471 287.8648 471.3848 698.0846 1011.6155 1429.8499 2055.9849 2883.4529 4457.6616 7357.6523 12923.7275 | lr 1.4e-04 | norm 4181.9985 | dt 9.876 +type train | step 4155 | loss 93.8818 183.3889 287.7630 470.4840 697.6012 1013.6660 1427.0999 2040.6337 2851.2617 4379.9395 7182.0317 12668.5723 | lr 1.4e-04 | norm 3867.6658 | dt 9.866 +type train | step 4156 | loss 91.7314 179.4982 285.0989 467.9834 697.7039 1007.7822 1424.3746 2043.5029 2899.2566 4477.1050 7351.7080 12866.9150 | lr 1.4e-04 | norm 4292.5547 | dt 9.881 +type train | step 4157 | loss 90.6235 177.9867 285.0798 473.1139 705.6461 1028.4943 1454.7861 2099.0674 2970.9124 4613.3223 7574.6660 13303.9844 | lr 1.4e-04 | norm 3751.5681 | dt 9.875 +type train | step 4158 | loss 94.3227 184.3726 289.0197 471.5858 697.2087 1010.9122 1420.5466 2047.1160 2882.5925 4460.4922 7410.6699 13110.9346 | lr 1.4e-04 | norm 4024.4324 | dt 9.866 +type train | step 4159 | loss 90.2377 178.3379 287.6487 478.1520 712.1899 1037.6111 1469.8022 2126.0664 2997.0803 4647.6270 7690.6865 13633.9854 | lr 1.4e-04 | norm 4446.1704 | dt 9.872 +type train | step 4160 | loss 94.4449 185.4859 290.3750 477.5434 706.2430 1020.0995 1437.3776 2061.5457 2903.6904 4519.3613 7484.7256 13292.0635 | lr 1.4e-04 | norm 3690.5188 | dt 9.867 +type train | step 4161 | loss 95.8649 188.9153 298.9580 487.0821 720.1125 1046.9259 1478.2596 2125.7585 3005.1670 4662.8232 7729.1377 13570.1016 | lr 1.4e-04 | norm 3292.9512 | dt 9.878 +type train | step 4162 | loss 84.5112 165.0522 266.5193 442.8713 669.7054 971.9224 1383.4303 1995.4738 2841.5269 4413.5586 7298.2705 12867.6016 | lr 1.4e-04 | norm 4221.7817 | dt 9.875 +type train | step 4163 | loss 74.1176 141.3486 231.6577 389.6691 598.9155 898.7388 1312.0540 1938.1140 2795.7283 4484.9102 7597.6567 13775.8301 | lr 1.4e-04 | norm 12137.8047 | dt 9.846 +type train | step 4164 | loss 74.4945 144.2124 234.0972 396.5746 607.9770 906.9028 1320.4149 1945.6337 2803.7058 4486.5610 7536.4907 13658.2285 | lr 1.4e-04 | norm 10979.5322 | dt 9.848 +type train | step 4165 | loss 84.3526 165.0568 266.9445 446.5723 670.7220 981.4850 1397.8468 2016.7892 2875.6306 4487.9189 7434.9399 13071.5244 | lr 1.4e-04 | norm 3584.0591 | dt 9.878 +type train | step 4166 | loss 88.7097 174.9538 279.3719 461.8904 688.5694 996.6423 1419.6854 2054.2686 2906.5884 4519.5459 7496.8442 13247.0898 | lr 1.4e-04 | norm 5323.4810 | dt 9.866 +type train | step 4167 | loss 92.7812 188.8781 302.8284 502.7630 744.9709 1093.4155 1528.8081 2217.4961 3117.3267 4838.2012 8105.0967 14675.8945 | lr 1.4e-04 | norm 8815.7158 | dt 9.853 +type train | step 4168 | loss 101.2596 201.3694 311.0319 498.7179 730.2073 1041.4784 1456.7806 2075.2544 2922.5454 4513.6689 7427.3477 13127.3311 | lr 1.4e-04 | norm 4199.7251 | dt 9.872 +type train | step 4169 | loss 94.1123 183.3740 285.3452 467.0581 690.9949 995.1761 1396.3816 2001.3784 2806.1558 4332.2490 7163.0171 12625.8789 | lr 1.4e-04 | norm 4024.7539 | dt 9.868 +type train | step 4170 | loss 92.2717 182.5105 285.9482 470.3685 694.2913 1004.3650 1420.3959 2040.5286 2883.0859 4480.7573 7441.3101 13145.2637 | lr 1.4e-04 | norm 3464.8611 | dt 9.881 +type train | step 4171 | loss 87.1281 172.7697 276.1754 460.2862 686.8793 994.5313 1405.8629 2022.3306 2884.6179 4504.2046 7488.2319 13163.1562 | lr 1.4e-04 | norm 3870.0471 | dt 9.864 +type train | step 4172 | loss 87.4456 173.4061 278.6706 460.9135 683.3224 995.3405 1401.6357 2014.6305 2833.4053 4393.5317 7272.4561 12796.3105 | lr 1.4e-04 | norm 3910.5881 | dt 9.864 +type train | step 4173 | loss 94.4139 185.4750 290.3227 470.6160 696.6282 1004.2592 1412.0973 2023.4298 2848.9658 4415.2939 7256.3208 12706.7510 | lr 1.4e-04 | norm 3347.9863 | dt 9.874 +type train | step 4174 | loss 97.1807 194.5198 305.2020 503.3820 741.2340 1078.0247 1507.4983 2164.3406 3024.6069 4652.7388 7711.1294 13791.4551 | lr 1.4e-04 | norm 5468.1924 | dt 9.851 +type train | step 4175 | loss 89.9650 175.9839 279.9861 466.2474 692.5280 1004.4839 1417.6460 2048.4993 2902.7344 4527.0723 7474.6450 13267.6738 | lr 1.4e-04 | norm 4071.2722 | dt 9.869 +type train | step 4176 | loss 94.4453 185.6862 292.3378 478.8925 712.5767 1030.4535 1455.8550 2079.6389 2914.5884 4501.0645 7410.1904 13033.8008 | lr 1.4e-04 | norm 4456.4956 | dt 9.888 +type train | step 4177 | loss 96.3057 189.6647 295.3064 483.3787 715.4077 1033.3290 1452.2283 2074.3787 2912.7703 4513.3247 7471.2124 13182.4902 | lr 1.4e-04 | norm 3791.0674 | dt 9.855 +type train | step 4178 | loss 96.3857 188.5244 295.0329 481.2440 708.7316 1033.0046 1453.8066 2088.0474 2921.4749 4488.4658 7383.2500 13020.7061 | lr 1.4e-04 | norm 3548.4126 | dt 9.863 +type train | step 4179 | loss 89.2724 174.1126 270.8428 455.3504 680.3470 994.8704 1398.8975 2029.5173 2843.7664 4411.8921 7327.8975 12885.1572 | lr 1.4e-04 | norm 6321.2012 | dt 9.854 +type train | step 4180 | loss 99.2199 199.7074 313.6506 512.8295 757.2102 1092.4360 1522.6079 2179.6580 3095.2439 4705.4932 7560.7891 13110.1025 | lr 1.4e-04 | norm 4610.3511 | dt 9.865 +type train | step 4181 | loss 99.0509 194.4183 300.7120 484.4719 711.8854 1033.3438 1461.8092 2097.1436 2941.5461 4567.1348 7548.7900 13292.2324 | lr 1.4e-04 | norm 4365.1616 | dt 9.857 +type train | step 4182 | loss 95.5116 188.7866 295.5717 484.7493 714.9585 1049.4038 1479.1367 2133.4507 2976.1809 4591.2983 7600.2295 13436.6973 | lr 1.4e-04 | norm 3880.0393 | dt 9.868 +type train | step 4183 | loss 91.0478 179.7729 284.2110 464.2462 688.5245 993.7619 1403.8506 2018.9111 2861.0647 4474.9824 7496.8989 13499.1582 | lr 1.4e-04 | norm 5645.2925 | dt 9.852 +type train | step 4184 | loss 97.2479 191.0399 302.9096 492.9160 725.5914 1043.9436 1467.9351 2102.4048 2949.8374 4589.7725 7626.9688 13569.5820 | lr 1.4e-04 | norm 5218.5347 | dt 9.866 +type train | step 4185 | loss 90.9715 178.6420 282.7236 464.0367 691.4607 998.6807 1408.6522 2019.1486 2851.5171 4392.8623 7211.4556 12670.5811 | lr 1.4e-04 | norm 3750.8574 | dt 9.870 +type train | step 4186 | loss 94.5467 187.4175 293.5002 477.8608 706.2943 1020.8771 1436.0990 2055.9895 2884.8950 4470.1104 7408.1035 13111.9551 | lr 1.4e-04 | norm 4332.6328 | dt 9.871 +type train | step 4187 | loss 96.8138 192.4244 303.2221 494.0245 728.2678 1046.0753 1469.7085 2099.6650 2943.2493 4554.4336 7488.4727 13134.1855 | lr 1.4e-04 | norm 3578.1816 | dt 9.882 +type train | step 4188 | loss 88.6720 175.0280 279.9528 461.8977 690.4615 1004.9954 1430.6390 2054.7822 2906.3389 4501.3335 7431.5771 13160.7734 | lr 1.3e-04 | norm 4181.0483 | dt 9.858 +type train | step 4189 | loss 90.3233 180.7812 284.0378 469.9627 699.5023 1031.0693 1465.9780 2118.8772 2941.2939 4540.6768 7459.6519 13173.9648 | lr 1.3e-04 | norm 4659.9912 | dt 9.865 +type train | step 4190 | loss 94.1783 184.1209 293.0817 479.9962 711.1242 1026.8641 1445.9556 2073.7563 2924.8550 4527.5361 7432.1323 13069.9375 | lr 1.3e-04 | norm 3646.9846 | dt 9.865 +type train | step 4191 | loss 95.4092 186.6752 291.1759 479.7599 708.6781 1055.5457 1500.4587 2196.6182 3070.5986 4827.3413 8105.4233 14429.9365 | lr 1.3e-04 | norm 6849.3286 | dt 9.841 +type train | step 4192 | loss 91.6667 181.9924 290.5493 478.7990 711.4856 1034.8264 1465.9844 2107.8105 2976.7993 4634.0684 7601.5728 13377.8564 | lr 1.3e-04 | norm 3866.4429 | dt 9.864 +type train | step 4193 | loss 95.2965 192.6269 307.3917 500.5181 739.9353 1085.2834 1530.9498 2220.2446 3107.4812 4827.6006 7961.7822 13974.1523 | lr 1.3e-04 | norm 6728.1807 | dt 9.864 +type train | step 4194 | loss 92.4573 183.7701 288.3456 478.1345 711.6016 1044.2634 1474.2201 2131.7976 2977.1902 4584.8999 7538.1338 13270.7256 | lr 1.3e-04 | norm 3751.9448 | dt 9.869 +type train | step 4195 | loss 94.0837 184.1158 290.6390 479.4904 709.9564 1032.3140 1452.3015 2089.8237 2933.1042 4516.0088 7438.0171 13101.4775 | lr 1.3e-04 | norm 3902.5476 | dt 9.874 +type train | step 4196 | loss 92.0107 179.7411 283.8854 467.9108 693.7360 1004.2435 1418.1375 2032.4094 2867.7913 4441.9424 7291.2422 12821.9160 | lr 1.3e-04 | norm 4157.5640 | dt 9.867 +type train | step 4197 | loss 90.6121 176.9579 276.8039 452.0913 674.2097 986.8796 1399.7566 2031.4976 2861.7861 4466.7812 7409.9077 13194.9053 | lr 1.3e-04 | norm 4182.4346 | dt 9.853 +type train | step 4198 | loss 95.7449 190.6646 300.4002 487.3928 714.6504 1033.8022 1445.8431 2055.0012 2866.3870 4433.8433 7294.3237 12941.9590 | lr 1.3e-04 | norm 3998.2361 | dt 9.862 +type train | step 4199 | loss 89.7933 175.8133 279.5132 458.3438 685.4507 993.7176 1404.7177 2017.7413 2848.2859 4406.3823 7228.7920 12664.8086 | lr 1.3e-04 | norm 3574.5361 | dt 9.875 +type train | step 4200 | loss 89.0021 173.7492 277.0085 459.6719 686.0852 1005.9518 1432.1711 2075.7793 2935.7554 4550.7832 7531.3818 13254.9932 | lr 1.3e-04 | norm 3790.0510 | dt 9.867 +type train | step 4201 | loss 91.8509 179.9861 283.6172 465.7612 692.3350 1006.7310 1421.3257 2041.0895 2880.2866 4455.2515 7357.9170 13061.3643 | lr 1.3e-04 | norm 3492.5986 | dt 9.870 +type train | step 4202 | loss 91.1496 177.0091 278.8391 457.8110 680.6185 993.7422 1406.4520 2040.4614 2865.8601 4487.2417 7467.5811 13286.4121 | lr 1.3e-04 | norm 5103.1919 | dt 9.871 +type train | step 4203 | loss 95.9358 192.3752 298.4224 484.7737 723.5004 1038.5614 1467.3636 2101.9927 2977.0710 4645.9360 7701.8057 13639.8857 | lr 1.3e-04 | norm 5275.6548 | dt 9.858 +type train | step 4204 | loss 89.0355 175.9062 280.1001 463.6674 689.2661 997.7942 1409.2406 2028.4734 2863.1245 4466.0352 7366.8091 12996.0918 | lr 1.3e-04 | norm 3539.8677 | dt 9.880 +type train | step 4205 | loss 99.1474 196.0775 302.8679 491.6497 722.0652 1043.3651 1465.2310 2107.6665 2941.5652 4553.4746 7501.1597 13213.6445 | lr 1.3e-04 | norm 3647.2371 | dt 9.875 +type train | step 4206 | loss 90.2429 176.0889 279.4307 458.5572 681.5185 985.4874 1386.2562 1982.4442 2808.5298 4349.0166 7176.8916 12642.3711 | lr 1.3e-04 | norm 3479.1963 | dt 9.878 +type train | step 4207 | loss 89.3443 176.8350 282.6802 469.7935 702.3511 1037.5135 1481.6094 2159.0898 3057.7197 4819.6206 8044.0889 14512.7275 | lr 1.3e-04 | norm 6974.7295 | dt 9.850 +type train | step 4208 | loss 88.8803 174.7943 274.6624 451.6266 673.9542 976.9869 1385.8546 1994.2161 2819.8745 4401.5537 7264.7119 12729.7480 | lr 1.3e-04 | norm 3255.1055 | dt 9.865 +type train | step 4209 | loss 91.5901 183.5083 295.0509 489.1108 730.2218 1068.8103 1520.1534 2216.0032 3140.3562 4914.1016 8129.9395 14349.1680 | lr 1.3e-04 | norm 4889.2295 | dt 9.857 +type train | step 4210 | loss 87.1506 173.7022 276.3005 454.3008 678.4644 983.5023 1394.4417 2007.6797 2852.3120 4459.4106 7410.6802 13129.4600 | lr 1.3e-04 | norm 3600.8906 | dt 9.867 +type train | step 4211 | loss 92.0740 180.4178 285.7197 468.6037 695.9453 1008.1066 1420.8557 2042.9531 2884.4607 4461.6084 7344.0923 12877.0869 | lr 1.3e-04 | norm 3932.4092 | dt 9.883 +type train | step 4212 | loss 90.7521 182.3459 286.0968 471.4609 701.2726 1025.5918 1461.7150 2125.1445 2986.1980 4643.3008 7667.7158 13471.7705 | lr 1.3e-04 | norm 4175.5664 | dt 9.875 +type train | step 4213 | loss 97.5970 191.4379 296.3302 480.5670 706.9034 1020.9015 1437.1422 2048.3188 2865.4426 4440.1416 7335.0967 12984.7480 | lr 1.3e-04 | norm 3962.9661 | dt 9.880 +type train | step 4214 | loss 85.5582 168.5554 270.3300 450.9429 676.0771 987.8021 1405.6775 2037.0292 2901.8850 4532.1670 7516.9863 13251.8975 | lr 1.3e-04 | norm 3592.1953 | dt 9.864 +type train | step 4215 | loss 92.1064 182.0756 284.1092 466.3699 693.6852 1006.9554 1420.2272 2044.9359 2883.6462 4468.7598 7367.5273 13039.8359 | lr 1.3e-04 | norm 3664.4375 | dt 9.868 +type train | step 4216 | loss 92.9589 183.0548 285.6746 469.6599 691.8043 1002.1672 1414.7065 2029.1642 2838.6716 4399.8896 7262.4966 12821.9492 | lr 1.3e-04 | norm 3963.3892 | dt 9.869 +type train | step 4217 | loss 97.8006 195.2592 303.9933 488.9461 717.9380 1036.0964 1457.7998 2087.2004 2924.5710 4538.3032 7554.5361 13453.1045 | lr 1.3e-04 | norm 4446.3394 | dt 9.866 +type train | step 4218 | loss 91.6861 179.4527 284.8665 469.2939 699.7118 1028.2244 1459.8608 2113.1350 2983.3430 4635.1274 7642.0996 13366.7588 | lr 1.3e-04 | norm 4442.6123 | dt 9.865 +type train | step 4219 | loss 96.4356 191.5499 303.0852 492.0288 725.1180 1041.9928 1465.6161 2094.1633 2964.0327 4588.4507 7561.7021 13245.6826 | lr 1.3e-04 | norm 3349.6672 | dt 9.861 +type train | step 4220 | loss 90.3120 176.7557 281.3569 464.6108 687.5527 996.0673 1403.9567 2018.4962 2843.2598 4388.4238 7214.2588 12654.2969 | lr 1.3e-04 | norm 3158.2727 | dt 9.873 +type train | step 4221 | loss 88.2502 172.0084 271.0287 446.9273 667.4716 967.9411 1369.3540 1975.7238 2792.7998 4339.0405 7152.2173 12470.9150 | lr 1.3e-04 | norm 3460.2573 | dt 9.856 +type train | step 4222 | loss 93.8128 185.6057 290.7466 479.9451 706.8117 1034.4047 1470.7957 2127.4268 2967.0369 4621.4541 7623.6113 13437.1953 | lr 1.3e-04 | norm 3921.0190 | dt 9.845 +type train | step 4223 | loss 90.9839 179.4058 286.2735 474.5416 704.9304 1018.5000 1434.2844 2061.0894 2911.1370 4525.4844 7497.7212 13245.0303 | lr 1.3e-04 | norm 3970.2881 | dt 9.869 +type train | step 4224 | loss 94.9659 186.2902 287.9430 467.4247 689.3038 998.1298 1406.9825 2025.2944 2841.2063 4440.0938 7395.9795 13048.9932 | lr 1.3e-04 | norm 3997.8933 | dt 9.877 +type train | step 4225 | loss 90.9587 178.3075 284.9853 471.2271 702.4854 1024.5820 1453.0189 2091.4038 2952.8889 4603.1650 7646.2637 13542.4707 | lr 1.3e-04 | norm 4333.1313 | dt 9.885 +type train | step 4226 | loss 95.4315 190.0432 297.0226 479.9851 702.3220 1009.8013 1419.5024 2032.2021 2858.7722 4424.6138 7323.6831 12914.4141 | lr 1.3e-04 | norm 5872.8491 | dt 9.873 +type train | step 4227 | loss 88.8613 173.3888 276.2245 454.6525 678.2205 984.4315 1393.1029 2005.5143 2835.2502 4394.6851 7297.2192 12995.0742 | lr 1.3e-04 | norm 3705.6587 | dt 9.875 +type train | step 4228 | loss 90.7591 177.6897 283.7388 467.7697 695.1798 1006.2368 1421.2931 2038.1213 2884.6262 4473.4556 7426.6499 13150.0566 | lr 1.3e-04 | norm 3632.8684 | dt 9.868 +type train | step 4229 | loss 94.7726 186.3324 297.7100 490.2742 727.5036 1071.0808 1522.1521 2205.8818 3080.0530 4736.6934 7836.6494 13800.7041 | lr 1.3e-04 | norm 4604.3857 | dt 9.887 +type train | step 4230 | loss 96.2220 190.5453 299.9183 493.7432 732.6290 1063.4185 1500.5591 2156.3708 2996.9688 4638.3833 7584.2852 13402.1133 | lr 1.3e-04 | norm 5535.4883 | dt 9.863 +type train | step 4231 | loss 90.3426 178.5921 282.7147 466.4814 694.3833 1011.4347 1430.0162 2066.9800 2904.2258 4506.8506 7434.5952 13141.4414 | lr 1.3e-04 | norm 4646.8496 | dt 9.875 +type train | step 4232 | loss 91.0786 178.1725 281.6676 464.3251 692.9855 1006.0494 1426.3038 2059.7607 2923.3899 4553.1519 7459.6162 13051.7617 | lr 1.3e-04 | norm 3598.1785 | dt 9.875 +type train | step 4233 | loss 92.8104 181.4318 282.0102 464.3117 686.2822 994.0698 1400.1093 2019.8060 2860.9890 4456.6333 7439.8062 13228.8906 | lr 1.3e-04 | norm 5118.3608 | dt 9.864 +type train | step 4234 | loss 97.1918 192.4796 300.8974 486.1705 716.4021 1034.1573 1457.5321 2083.6660 2927.1829 4513.9927 7442.1206 13142.4395 | lr 1.3e-04 | norm 4274.8726 | dt 9.863 +type train | step 4235 | loss 93.9204 183.6638 292.0604 484.6312 714.7369 1043.7369 1471.1284 2112.7261 2953.1641 4557.5991 7514.6460 13299.9248 | lr 1.3e-04 | norm 4073.3208 | dt 9.863 +type train | step 4236 | loss 88.9662 175.7163 281.4965 467.7635 700.3588 1011.8985 1433.2183 2054.9785 2932.0139 4549.8291 7493.0020 13246.5430 | lr 1.3e-04 | norm 3652.0479 | dt 9.875 +type train | step 4237 | loss 98.6116 194.6534 304.6945 489.8304 722.5458 1041.4878 1469.9968 2103.7334 2945.3792 4520.5791 7427.7021 13106.1768 | lr 1.3e-04 | norm 4649.3730 | dt 9.884 +type train | step 4238 | loss 92.0336 183.2176 289.7657 473.8040 714.4918 1054.5845 1504.2367 2203.2793 3107.5642 4832.4922 7933.8354 13937.8799 | lr 1.3e-04 | norm 5936.9155 | dt 9.869 +type train | step 4239 | loss 91.7488 180.0035 282.8599 465.0837 688.8428 1001.6347 1422.2845 2045.0742 2878.8879 4474.6357 7364.8618 12972.1094 | lr 1.3e-04 | norm 3827.4102 | dt 9.866 +type train | step 4240 | loss 93.2930 183.6631 289.8652 474.6862 705.6447 1016.1937 1432.8988 2058.0752 2912.0427 4509.1797 7430.0542 13078.2510 | lr 1.3e-04 | norm 3963.5068 | dt 9.874 +type train | step 4241 | loss 88.8125 177.2014 289.9974 479.3377 716.8040 1035.6089 1465.7139 2114.6880 2992.5066 4708.3052 7826.3311 13670.8076 | lr 1.3e-04 | norm 5062.4541 | dt 9.859 +type train | step 4242 | loss 98.2254 194.7223 304.4389 495.0776 730.7618 1055.5547 1480.9655 2113.7864 2951.9009 4552.3955 7526.3843 13181.9932 | lr 1.3e-04 | norm 4137.5635 | dt 9.880 +type train | step 4243 | loss 90.1091 178.2527 282.7813 465.8254 691.4598 1005.6663 1426.1178 2052.7661 2910.4321 4549.6655 7558.8975 13325.6641 | lr 1.3e-04 | norm 3842.1492 | dt 9.866 +type train | step 4244 | loss 94.6531 185.4385 290.6350 474.7913 698.4151 1013.0436 1429.0066 2056.1575 2900.1870 4493.7617 7442.1641 13084.5840 | lr 1.3e-04 | norm 3457.9148 | dt 9.875 +type train | step 4245 | loss 95.7149 188.0525 295.3824 483.3100 709.9342 1028.0564 1441.5612 2064.7073 2889.1589 4471.3110 7410.4370 13072.2656 | lr 1.3e-04 | norm 3979.0837 | dt 9.871 +type train | step 4246 | loss 97.7396 195.1371 309.7541 510.7479 756.9551 1101.5237 1549.0167 2216.6394 3109.0830 4806.2822 7961.7988 14155.6113 | lr 1.3e-04 | norm 4422.0923 | dt 9.872 +type train | step 4247 | loss 94.7608 185.2832 287.9591 469.6297 694.8826 1015.1546 1422.0413 2047.7188 2849.3223 4401.7397 7274.6338 12748.6973 | lr 1.3e-04 | norm 3911.5935 | dt 9.847 +type train | step 4248 | loss 88.7210 174.8392 278.9021 459.7437 685.3755 996.7764 1410.4651 2034.6620 2886.3105 4480.9121 7394.3340 13012.8496 | lr 1.3e-04 | norm 3664.7722 | dt 9.882 +type train | step 4249 | loss 90.1500 175.9337 280.3258 460.3514 689.6630 1006.2864 1426.2543 2053.1926 2902.0967 4498.1406 7418.1807 12988.3086 | lr 1.3e-04 | norm 3485.4370 | dt 9.880 +type train | step 4250 | loss 94.3216 187.7347 295.0129 485.1482 708.5104 1021.7976 1436.5079 2051.1162 2881.4917 4472.1460 7408.7964 13136.8174 | lr 1.3e-04 | norm 4582.1943 | dt 9.858 +type train | step 4251 | loss 91.7971 179.7912 285.6252 466.1409 693.5074 1005.1963 1422.2076 2051.0991 2906.5703 4506.3408 7427.0762 13044.1953 | lr 1.3e-04 | norm 3455.1357 | dt 9.854 +type train | step 4252 | loss 93.2166 182.7282 286.1903 467.0201 691.0081 999.7776 1417.8875 2033.9938 2874.2693 4451.9282 7368.9106 12986.6270 | lr 1.3e-04 | norm 3411.4749 | dt 9.852 +type train | step 4253 | loss 117.9960 235.5557 351.8915 553.8276 807.2070 1179.3654 1649.0084 2365.9802 3266.9792 4953.4980 7935.1011 13662.5996 | lr 1.3e-04 | norm 4576.5503 | dt 9.852 +type train | step 4254 | loss 95.0857 187.7901 293.5622 479.5542 710.2084 1034.9725 1452.5651 2081.2866 2921.0935 4522.3457 7483.3442 13264.7764 | lr 1.3e-04 | norm 3658.1406 | dt 9.871 +type train | step 4255 | loss 94.8594 189.5291 296.7230 482.0913 708.5895 1013.1345 1417.4967 2014.6152 2823.1936 4370.4263 7207.2476 12808.8506 | lr 1.3e-04 | norm 4024.6204 | dt 9.860 +type train | step 4256 | loss 87.4702 172.8834 273.8542 453.3358 677.5400 992.6198 1408.7493 2040.3772 2885.6479 4473.2598 7376.0195 12965.7861 | lr 1.3e-04 | norm 4268.3218 | dt 9.873 +type train | step 4257 | loss 96.0101 188.5637 296.0234 482.8839 718.9656 1054.9679 1492.7256 2161.8489 3037.4895 4701.7319 7747.0645 13639.5879 | lr 1.3e-04 | norm 3848.1475 | dt 9.865 +type train | step 4258 | loss 91.5764 181.5255 286.4921 472.8352 698.6457 1011.4174 1427.2400 2042.7258 2884.2271 4441.5029 7371.1421 12958.5127 | lr 1.3e-04 | norm 3350.3655 | dt 9.871 +type train | step 4259 | loss 96.1108 190.7628 299.2544 487.4668 719.5878 1040.6127 1468.7426 2111.1462 2958.4607 4579.2588 7560.2822 13376.4541 | lr 1.3e-04 | norm 4429.3110 | dt 9.873 +type train | step 4260 | loss 93.2754 183.7748 291.6415 479.6707 712.6044 1035.0884 1459.8390 2100.9844 2946.0605 4577.1987 7555.3262 13222.3096 | lr 1.3e-04 | norm 4292.7124 | dt 9.867 +type train | step 4261 | loss 95.6479 190.9710 301.2450 488.3231 723.8522 1045.0720 1472.2057 2103.4929 2963.9888 4586.6851 7517.0425 13149.1338 | lr 1.3e-04 | norm 3809.3518 | dt 9.893 +type train | step 4262 | loss 91.1505 178.4800 278.6448 455.9175 677.3892 978.7174 1378.0338 1976.1345 2778.1438 4305.8105 7104.5664 12527.8994 | lr 1.3e-04 | norm 3430.3479 | dt 9.883 +type train | step 4263 | loss 99.6951 195.5933 307.8319 502.5633 738.9826 1070.4336 1509.3389 2168.5530 3029.2764 4688.2754 7765.6597 13859.0166 | lr 1.3e-04 | norm 5259.6313 | dt 9.876 +type train | step 4264 | loss 87.9656 174.2302 275.6990 455.3833 683.1708 988.0217 1398.5149 2012.5597 2858.0750 4379.8716 7119.6143 12397.5703 | lr 1.3e-04 | norm 5737.7090 | dt 9.869 +type train | step 4265 | loss 103.7743 206.2410 319.5438 510.0801 746.5939 1073.0481 1500.8422 2134.8809 2928.2175 4431.1675 7215.4097 12658.0391 | lr 1.3e-04 | norm 4000.5688 | dt 9.871 +type train | step 4266 | loss 92.7029 182.7232 285.9360 467.8808 693.0767 1008.9452 1423.6833 2048.0090 2897.2253 4485.3262 7373.0020 12943.1582 | lr 1.3e-04 | norm 3827.4548 | dt 9.877 +type train | step 4267 | loss 85.9577 167.6885 266.9400 441.5140 664.3936 970.1990 1386.7761 2011.1372 2867.6775 4480.6836 7447.7617 13213.7891 | lr 1.3e-04 | norm 3859.6665 | dt 9.875 +type train | step 4268 | loss 104.0877 204.2193 314.4672 504.6433 739.1478 1082.3983 1522.5800 2197.0647 3061.1682 4740.3706 7810.3130 13764.5664 | lr 1.3e-04 | norm 3980.2456 | dt 9.857 +type train | step 4269 | loss 89.3591 174.4932 278.3971 455.8875 677.1504 978.7756 1384.9116 1996.7740 2829.6948 4397.3931 7288.7505 12887.2607 | lr 1.3e-04 | norm 3623.7676 | dt 9.859 +type train | step 4270 | loss 87.3051 171.1207 274.3019 455.0099 679.0745 985.9561 1397.4956 2010.2852 2840.7485 4398.0161 7228.8604 12697.9395 | lr 1.3e-04 | norm 3457.2671 | dt 9.865 +type train | step 4271 | loss 108.2812 218.7899 338.6477 540.9882 781.1545 1113.8263 1517.3040 2108.5859 2848.9407 4293.6992 6933.9917 12341.0996 | lr 1.3e-04 | norm 5174.4453 | dt 9.849 +type train | step 4272 | loss 94.8834 186.4212 293.3302 476.1813 703.8058 1031.3521 1451.2996 2093.2732 2938.8809 4535.8018 7499.5811 13211.0059 | lr 1.3e-04 | norm 3681.2263 | dt 9.872 +type train | step 4273 | loss 93.7764 184.4853 286.8077 470.3897 696.5275 1015.3436 1429.8586 2049.7598 2898.9441 4530.2690 7512.1265 13192.3145 | lr 1.3e-04 | norm 3622.0037 | dt 9.885 +type train | step 4274 | loss 111.5487 219.5946 336.7339 537.2652 781.1055 1118.1494 1564.2666 2216.5002 3060.8850 4731.5361 7820.6787 13873.2734 | lr 1.3e-04 | norm 6460.0869 | dt 9.876 +type train | step 4275 | loss 86.4260 170.2030 272.4110 456.5061 687.9792 1013.4496 1451.1490 2121.1084 3007.2095 4695.5610 7834.4819 13869.2812 | lr 1.3e-04 | norm 4424.8599 | dt 9.849 +type train | step 4276 | loss 87.0006 170.4358 273.7484 457.0547 686.6931 999.0903 1419.7159 2056.9424 2918.3296 4554.2178 7518.1226 13204.5869 | lr 1.3e-04 | norm 3817.9424 | dt 9.869 +type train | step 4277 | loss 92.6983 180.3866 283.6252 468.5809 693.3447 1010.5085 1424.6722 2052.8384 2880.8096 4494.0244 7507.8965 13463.5449 | lr 1.3e-04 | norm 4988.6460 | dt 9.862 +type train | step 4278 | loss 90.3806 179.3789 282.3876 462.9259 690.4783 1008.8427 1442.1360 2095.1533 2961.1333 4609.6211 7557.5972 13170.4922 | lr 1.3e-04 | norm 4679.9048 | dt 9.870 +type train | step 4279 | loss 94.2366 182.3054 287.2475 472.0327 698.8659 1017.9626 1438.9294 2081.4045 2907.5076 4542.7505 7578.1411 13519.4512 | lr 1.3e-04 | norm 4635.6523 | dt 9.861 +type train | step 4280 | loss 90.3704 175.0108 276.5464 452.7647 675.2573 981.7022 1385.9402 1999.4697 2826.0176 4400.6792 7287.6621 12821.9033 | lr 1.3e-04 | norm 3851.8489 | dt 9.855 +type train | step 4281 | loss 89.2669 176.4107 284.0783 468.1656 698.9901 1026.5000 1450.4368 2092.1340 2931.9622 4538.0659 7516.7173 13282.5039 | lr 1.3e-04 | norm 3894.2451 | dt 9.860 +type train | step 4282 | loss 88.9789 176.5260 282.4070 472.8587 711.8073 1043.8066 1483.6342 2154.6436 3033.2561 4649.9478 7588.8926 13183.9658 | lr 1.3e-04 | norm 3518.1248 | dt 9.871 +type train | step 4283 | loss 91.1279 177.9504 280.7736 460.7860 685.8313 992.5706 1402.9913 2016.7135 2847.1711 4441.7661 7340.7148 12937.5430 | lr 1.3e-04 | norm 4676.3755 | dt 9.852 +type train | step 4284 | loss 96.4445 189.4411 296.5632 486.6743 714.5369 1043.3806 1474.6604 2125.7830 2941.5396 4549.9175 7492.1450 13166.5977 | lr 1.3e-04 | norm 4696.2739 | dt 9.864 +type train | step 4285 | loss 95.1404 189.8378 297.0204 480.9746 710.7737 1036.3966 1464.0410 2104.9246 2956.0459 4576.8647 7522.4282 13216.1836 | lr 1.3e-04 | norm 3844.6704 | dt 9.867 +type train | step 4286 | loss 91.0400 180.3417 281.1717 461.7080 685.2648 1006.1428 1421.2843 2049.3625 2889.0947 4487.0918 7391.5220 12910.3584 | lr 1.3e-04 | norm 4170.8091 | dt 9.860 +type train | step 4287 | loss 90.0829 176.2776 276.3602 454.3192 674.4577 983.7075 1389.4431 2007.0438 2835.6758 4430.4897 7329.4561 13037.6367 | lr 1.3e-04 | norm 3668.5659 | dt 9.870 +type train | step 4288 | loss 86.5917 168.8182 272.0862 450.3772 674.5752 979.5875 1392.4059 2016.4221 2871.0811 4476.3545 7466.9863 13297.2773 | lr 1.3e-04 | norm 4947.9365 | dt 9.862 +type train | step 4289 | loss 88.8804 176.0219 279.3074 459.3898 686.6776 1004.9380 1430.0420 2070.4346 2937.0854 4560.9814 7528.9990 13198.3516 | lr 1.3e-04 | norm 3524.4956 | dt 9.871 +type train | step 4290 | loss 103.1007 201.3621 316.1324 520.9754 759.0604 1091.3781 1516.7166 2162.3259 3000.1086 4624.7891 7619.4590 13549.4736 | lr 1.3e-04 | norm 5841.0371 | dt 9.852 +type train | step 4291 | loss 89.7714 174.5789 275.9034 456.3732 682.8204 1000.4746 1419.1013 2052.3076 2901.8069 4525.3413 7524.9126 13384.3965 | lr 1.3e-04 | norm 4233.8623 | dt 9.854 +type train | step 4292 | loss 99.5462 194.5690 299.8497 482.7361 708.2027 1024.6494 1441.2722 2081.1560 2938.7969 4577.2568 7547.2480 13314.0674 | lr 1.3e-04 | norm 4113.0298 | dt 9.864 +type train | step 4293 | loss 94.2959 184.8023 291.1992 478.5808 710.6598 1032.6138 1459.7880 2108.9678 2978.0183 4631.2227 7674.6890 13514.4395 | lr 1.3e-04 | norm 3928.0796 | dt 9.864 +type train | step 4294 | loss 93.1105 183.7975 286.3957 471.0836 697.9379 1013.7204 1431.0723 2053.3394 2900.6824 4520.3999 7453.7578 13058.2012 | lr 1.3e-04 | norm 3466.4443 | dt 9.865 +type train | step 4295 | loss 94.6126 183.2190 285.5430 467.8829 690.6761 1010.2888 1429.0145 2059.1760 2888.2532 4507.5620 7543.6504 13481.0059 | lr 1.3e-04 | norm 4293.4258 | dt 9.867 +type train | step 4296 | loss 89.7186 175.2297 276.1678 454.9578 680.4506 996.9747 1419.5123 2049.6755 2915.4104 4572.3999 7592.1411 13377.2373 | lr 1.3e-04 | norm 3457.3081 | dt 9.866 +type train | step 4297 | loss 91.7537 180.0802 284.5634 466.4839 693.2335 1000.8929 1408.5646 2020.8501 2845.9587 4431.7373 7348.3262 12985.9482 | lr 1.3e-04 | norm 3605.6238 | dt 9.868 +type train | step 4298 | loss 90.1285 174.2343 272.7411 451.9772 675.1262 991.5862 1408.3590 2042.2239 2871.5876 4488.1621 7484.3164 13233.0479 | lr 1.3e-04 | norm 3634.0491 | dt 9.865 +type train | step 4299 | loss 95.1195 187.2898 297.0405 490.5454 724.8663 1064.4047 1504.0626 2184.7610 3066.1873 4715.1851 7731.6309 13584.6914 | lr 1.3e-04 | norm 4112.5898 | dt 9.862 +type train | step 4300 | loss 91.8209 177.7657 281.2711 467.9022 699.6517 1034.7216 1478.4281 2145.1973 3010.5317 4645.8193 7671.2197 13512.2061 | lr 1.3e-04 | norm 6361.1592 | dt 9.845 +type train | step 4301 | loss 92.4864 182.2872 286.3491 467.5918 693.3605 998.9540 1411.6674 2027.6797 2852.3145 4394.2559 7195.9507 12625.0771 | lr 1.3e-04 | norm 3927.4756 | dt 9.874 +type train | step 4302 | loss 93.3982 181.3404 283.1439 464.5057 685.9413 992.8986 1402.6382 2013.5034 2834.7979 4402.0688 7314.4243 12940.1328 | lr 1.3e-04 | norm 4036.2424 | dt 9.861 +type train | step 4303 | loss 92.4437 182.4509 287.4424 474.5632 704.4074 1033.5438 1465.3595 2111.3469 2956.0679 4573.9429 7514.8071 13220.2441 | lr 1.3e-04 | norm 4657.5342 | dt 9.872 +type train | step 4304 | loss 92.5598 180.5776 284.9938 469.4957 695.9155 1009.7032 1427.0415 2056.7786 2902.9565 4512.7988 7440.8506 13118.9785 | lr 1.3e-04 | norm 3559.0139 | dt 9.862 +type train | step 4305 | loss 97.4857 190.4765 300.3960 490.3802 718.8973 1042.3867 1455.8235 2063.6096 2855.1067 4377.3867 7214.3369 12708.0166 | lr 1.3e-04 | norm 5276.3237 | dt 9.880 +type train | step 4306 | loss 89.4677 177.0213 279.9727 463.3336 691.0760 1009.4808 1431.5726 2072.1450 2931.0435 4556.2300 7545.7285 13314.1006 | lr 1.3e-04 | norm 4101.7339 | dt 9.880 +type train | step 4307 | loss 94.8710 189.4774 295.1758 480.8362 706.8519 1024.4133 1445.9425 2077.0254 2919.4690 4535.2339 7471.5039 13154.6250 | lr 1.3e-04 | norm 4300.0547 | dt 9.866 +type train | step 4308 | loss 94.6156 184.2444 288.3996 469.6984 694.3647 1008.1251 1422.3413 2039.6017 2871.9812 4464.8687 7402.9595 13148.7979 | lr 1.3e-04 | norm 3669.3987 | dt 9.873 +type train | step 4309 | loss 88.5556 173.8270 273.8576 454.2459 675.8870 980.1675 1390.0186 1994.9801 2837.1057 4413.3213 7317.2402 12975.5791 | lr 1.3e-04 | norm 3703.7639 | dt 9.858 +type train | step 4310 | loss 91.1474 175.6169 275.0031 451.8607 675.9749 981.7935 1387.6084 1993.9075 2816.9424 4395.6211 7314.4058 12913.1992 | lr 1.3e-04 | norm 3698.6338 | dt 9.869 +type train | step 4311 | loss 93.9670 183.6530 291.6732 485.1312 720.0619 1044.4235 1473.6007 2114.0447 3002.4768 4708.4287 7777.3115 13787.6562 | lr 1.3e-04 | norm 4816.0518 | dt 9.870 +type train | step 4312 | loss 89.2377 175.2108 273.3497 447.7956 666.4969 971.2109 1370.7872 1971.0917 2788.6423 4323.2510 7157.9951 12498.3516 | lr 1.3e-04 | norm 3720.5818 | dt 9.860 +type train | step 4313 | loss 115.6133 225.7403 345.3174 550.3721 800.9674 1161.8378 1655.8550 2346.4397 3099.1414 4609.3047 7526.9570 14036.9199 | lr 1.3e-04 | norm 15262.8301 | dt 9.833 +type train | step 4314 | loss 122.9155 240.1445 364.6329 575.8370 831.7772 1198.1270 1698.4578 2394.7041 3164.5786 4690.1533 7640.5010 14088.0801 | lr 1.3e-04 | norm 14463.4932 | dt 9.818 +type train | step 4315 | loss 84.3792 165.1545 261.8302 438.8055 659.6174 967.8123 1379.1304 2014.0789 2856.9912 4454.0024 7332.5010 12808.6875 | lr 1.3e-04 | norm 3853.1360 | dt 9.863 +type train | step 4316 | loss 90.0359 175.2710 277.9029 457.0349 678.2695 982.1595 1387.5001 1992.3740 2819.3093 4393.3418 7241.9287 12748.0635 | lr 1.3e-04 | norm 3897.0193 | dt 9.857 +type train | step 4317 | loss 86.0048 169.6664 269.7520 449.0061 671.3594 973.9938 1382.6158 1993.6738 2840.5579 4417.7026 7279.9951 12803.5137 | lr 1.2e-04 | norm 3318.3965 | dt 9.884 +type train | step 4318 | loss 93.7882 182.2800 284.6487 468.3689 696.4126 1017.0789 1443.6687 2088.7659 2930.1958 4545.4824 7525.6914 13302.9355 | lr 1.2e-04 | norm 3855.4346 | dt 9.874 +type train | step 4319 | loss 86.6242 169.2675 268.6164 445.6158 667.9060 974.9282 1389.8190 2012.5247 2852.6797 4472.3950 7388.2241 13103.2852 | lr 1.2e-04 | norm 4039.3967 | dt 9.869 +type train | step 4320 | loss 97.1488 194.2375 301.0139 486.4173 710.5288 1025.5712 1439.2570 2043.6387 2823.0789 4350.6455 7110.1235 12452.5244 | lr 1.2e-04 | norm 4699.7207 | dt 9.854 +type train | step 4321 | loss 92.2854 182.3633 285.1388 464.1397 687.7179 995.5511 1404.0320 2008.1842 2826.0413 4378.9287 7206.2222 12663.0400 | lr 1.2e-04 | norm 3600.4885 | dt 9.880 +type train | step 4322 | loss 95.4859 185.6922 292.1014 476.2018 702.6609 1026.1349 1448.7271 2089.6753 2939.0122 4571.9277 7552.2881 13265.1582 | lr 1.2e-04 | norm 3568.8635 | dt 9.869 +type train | step 4323 | loss 92.5578 182.1730 286.3896 468.1338 695.0775 1012.1743 1429.7701 2046.4062 2891.5884 4445.0063 7263.6704 12604.7041 | lr 1.2e-04 | norm 3718.3630 | dt 9.874 +type train | step 4324 | loss 93.9228 188.7917 301.0518 492.3849 735.1451 1069.0372 1505.6185 2172.8755 3073.2703 4753.8071 7840.6968 13909.8662 | lr 1.2e-04 | norm 4507.8262 | dt 9.865 +type train | step 4325 | loss 87.3341 172.1241 272.2963 451.1895 672.6960 975.8618 1379.9894 1987.8962 2818.4990 4413.5649 7322.3838 12831.3477 | lr 1.2e-04 | norm 3337.9685 | dt 9.870 +type train | step 4326 | loss 108.6473 219.1451 340.0184 558.7981 797.9623 1148.9976 1586.6973 2256.6045 3069.9041 4694.3345 7716.7920 13712.8340 | lr 1.2e-04 | norm 6855.6719 | dt 9.852 +type train | step 4327 | loss 88.9652 174.8584 275.1324 449.9149 675.9133 985.4421 1401.6875 2027.8066 2885.8435 4494.3535 7416.7700 13060.9785 | lr 1.2e-04 | norm 4079.9822 | dt 9.863 +type train | step 4328 | loss 86.4023 175.1582 279.6011 464.1050 699.4959 1023.8962 1465.8839 2122.1628 3032.1577 4754.6636 7971.7681 14280.8223 | lr 1.2e-04 | norm 6935.3726 | dt 9.856 +type train | step 4329 | loss 110.7832 221.1576 342.2460 547.8715 803.9457 1158.2288 1627.0403 2311.0752 3186.8806 4840.7266 7932.6533 13983.7139 | lr 1.2e-04 | norm 7442.8374 | dt 9.867 +type train | step 4330 | loss 109.9291 218.6032 338.4876 540.9033 790.7684 1126.7842 1575.3134 2230.8950 3088.9045 4718.2451 7739.5044 13592.0527 | lr 1.2e-04 | norm 7118.4087 | dt 9.854 +type train | step 4331 | loss 87.6316 170.2087 272.3923 452.2192 674.3591 983.3510 1391.9713 2011.5693 2845.1082 4426.5039 7361.7207 13017.1338 | lr 1.2e-04 | norm 3398.7734 | dt 9.859 +type train | step 4332 | loss 89.9807 177.7489 278.8768 458.7250 685.4811 1003.9706 1431.5726 2081.9282 2953.2869 4609.2168 7572.2949 13284.9873 | lr 1.2e-04 | norm 3686.2788 | dt 9.865 +type train | step 4333 | loss 84.7635 166.1830 265.1833 438.0770 658.9898 963.2916 1368.2817 1983.5095 2812.4070 4405.1626 7282.9395 12664.2998 | lr 1.2e-04 | norm 3646.4924 | dt 9.877 +type train | step 4334 | loss 94.5777 186.9744 292.3220 477.3621 709.4579 1038.0280 1472.9783 2124.9868 2984.8423 4613.2402 7590.3774 13366.3340 | lr 1.2e-04 | norm 4231.3101 | dt 9.871 +type train | step 4335 | loss 90.8638 179.0170 280.5780 458.5157 681.8651 987.6598 1397.1440 2001.9867 2824.2153 4375.2476 7224.0190 12717.2207 | lr 1.2e-04 | norm 3991.2222 | dt 9.879 +type train | step 4336 | loss 96.5148 191.5799 297.8761 484.2167 712.7579 1026.9761 1439.7257 2063.9976 2916.5129 4509.4819 7443.9644 13102.6699 | lr 1.2e-04 | norm 3316.7192 | dt 9.871 +type train | step 4337 | loss 84.8411 165.9301 263.2265 439.2928 661.7092 972.6923 1391.1222 2032.0167 2895.7830 4501.9248 7431.0376 13013.8496 | lr 1.2e-04 | norm 3823.4883 | dt 9.870 +type train | step 4338 | loss 91.3663 179.0989 280.1927 458.5429 681.6188 990.3591 1402.0146 2015.0007 2838.3279 4413.6455 7291.4058 12888.4980 | lr 1.2e-04 | norm 4307.6309 | dt 9.855 +type train | step 4339 | loss 95.9034 189.2877 294.5799 479.2006 710.9628 1032.0726 1455.1533 2091.0537 2963.8706 4612.1738 7613.7666 13365.1250 | lr 1.2e-04 | norm 3634.2603 | dt 9.870 +type train | step 4340 | loss 92.6001 182.0940 289.6472 477.3231 706.6184 1033.8336 1454.6514 2095.7527 2919.2568 4493.2549 7389.0337 12998.4287 | lr 1.2e-04 | norm 4333.7246 | dt 9.871 +type train | step 4341 | loss 115.3676 226.7027 353.2654 582.4100 828.8381 1230.8051 1687.2408 2388.1191 3103.4155 4678.9604 7735.4819 13895.4600 | lr 1.2e-04 | norm 10482.8672 | dt 9.824 +type train | step 4342 | loss 104.9856 213.3888 330.9174 532.5085 761.6859 1094.8668 1491.9211 2082.5012 2803.9219 4183.5171 6712.7480 11810.3779 | lr 1.2e-04 | norm 5243.2842 | dt 9.837 +type train | step 4343 | loss 104.0662 208.9281 322.0021 514.7377 748.3011 1072.5275 1486.2026 2085.1040 2885.4229 4404.6553 7177.5439 12679.8369 | lr 1.2e-04 | norm 4340.6738 | dt 9.843 +type train | step 4344 | loss 93.8274 182.6329 287.7494 468.1841 692.5000 1011.9365 1422.8525 2041.8000 2861.0269 4434.9429 7314.4595 12961.8379 | lr 1.2e-04 | norm 3833.6934 | dt 9.867 +type train | step 4345 | loss 88.0438 172.6566 274.5400 453.6140 674.8611 984.6276 1401.6991 2027.4387 2860.9919 4469.0474 7416.6294 13118.0859 | lr 1.2e-04 | norm 3733.0913 | dt 9.864 +type train | step 4346 | loss 91.5068 179.4016 283.6863 468.7183 696.8091 1018.8878 1441.9316 2075.7720 2940.8540 4578.0659 7575.8252 13468.0098 | lr 1.2e-04 | norm 4128.0483 | dt 9.863 +type train | step 4347 | loss 89.3123 175.3745 276.0431 454.4870 676.4055 985.8618 1397.7163 2012.3577 2849.9360 4424.7710 7283.7437 12843.2217 | lr 1.2e-04 | norm 3864.6575 | dt 9.867 +type train | step 4348 | loss 93.4702 185.4466 290.5682 473.4051 700.0379 1014.2464 1425.5808 2055.5063 2866.2944 4444.8125 7327.1152 12935.8145 | lr 1.2e-04 | norm 4734.7222 | dt 9.870 +type train | step 4349 | loss 91.8350 181.8955 287.6310 478.6793 710.1282 1047.9714 1476.5010 2132.6284 2967.7515 4560.8223 7500.1562 13156.3730 | lr 1.2e-04 | norm 4012.2639 | dt 9.866 +type train | step 4350 | loss 88.6822 173.6245 279.0548 462.0225 693.6299 1009.2955 1436.2698 2080.0264 2946.2144 4572.5127 7578.0337 13400.5049 | lr 1.2e-04 | norm 4296.2349 | dt 9.868 +type train | step 4351 | loss 83.3705 164.7322 264.4185 453.8141 683.5176 1000.2803 1426.4390 2087.6492 2942.2041 4737.0264 7936.0459 14157.1641 | lr 1.2e-04 | norm 9423.4639 | dt 9.843 +type train | step 4352 | loss 93.8694 186.7822 292.4173 477.5716 704.9239 1022.9651 1436.7720 2061.4688 2870.2556 4425.1538 7285.5635 12917.2559 | lr 1.2e-04 | norm 3791.1973 | dt 9.874 +type train | step 4353 | loss 89.8130 176.9408 279.2738 459.9130 688.2653 1002.9639 1418.0474 2037.7717 2880.2219 4468.5674 7447.4561 13147.9268 | lr 1.2e-04 | norm 3753.1880 | dt 9.872 +type train | step 4354 | loss 96.0998 186.3194 292.2157 481.9501 713.1528 1034.9069 1457.6925 2099.6663 2934.2913 4548.1206 7472.4419 13154.6533 | lr 1.2e-04 | norm 3740.9448 | dt 9.869 +type train | step 4355 | loss 95.0147 188.0236 298.6404 482.2037 711.1278 1023.3868 1436.7972 2047.9302 2873.5659 4441.3804 7339.9814 12887.8828 | lr 1.2e-04 | norm 3332.1213 | dt 9.884 +type train | step 4356 | loss 90.3301 177.8617 280.9823 461.1385 685.5588 1005.6730 1433.6311 2073.6663 2931.1409 4524.2681 7481.1270 13092.2236 | lr 1.2e-04 | norm 3773.3745 | dt 9.862 +type train | step 4357 | loss 86.9984 170.5553 272.1430 447.9048 672.7213 983.3736 1395.5300 2016.8755 2869.6860 4448.7998 7326.0737 12777.7344 | lr 1.2e-04 | norm 3323.2119 | dt 9.879 +type train | step 4358 | loss 91.6547 177.6887 281.6046 465.7378 690.9543 1009.8959 1420.0928 2036.1372 2845.0427 4387.8252 7214.9082 12740.3486 | lr 1.2e-04 | norm 3592.5500 | dt 9.859 +type train | step 4359 | loss 92.9445 185.0885 288.6646 475.1241 703.8307 1034.3308 1467.7623 2114.7004 2980.6040 4636.9014 7692.2656 13683.3359 | lr 1.2e-04 | norm 4429.1348 | dt 9.866 +type train | step 4360 | loss 92.3914 181.3352 289.2074 477.2359 705.8619 1028.8800 1445.3116 2080.4893 2909.4001 4502.3716 7416.7417 13040.6836 | lr 1.2e-04 | norm 3482.1567 | dt 9.858 +type train | step 4361 | loss 91.5004 179.1762 286.4505 471.6230 702.5269 1022.4586 1440.9899 2072.4478 2923.0112 4512.5552 7407.5938 12954.5293 | lr 1.2e-04 | norm 3027.9978 | dt 9.891 +type train | step 4362 | loss 90.6993 176.7716 284.1253 467.1803 692.5252 1008.8269 1418.6462 2041.8086 2866.6399 4455.5073 7368.0898 13095.0010 | lr 1.2e-04 | norm 4985.9531 | dt 9.852 +type train | step 4363 | loss 88.5881 170.9499 272.1893 451.5756 672.5479 989.1332 1405.2927 2032.0829 2869.1084 4450.1216 7348.8408 12912.6934 | lr 1.2e-04 | norm 3751.4612 | dt 9.848 +type train | step 4364 | loss 88.1941 172.5391 269.9487 448.3008 668.3417 979.0422 1390.4615 2009.4662 2844.7280 4444.8291 7399.6968 13045.5254 | lr 1.2e-04 | norm 3938.1812 | dt 9.859 +type train | step 4365 | loss 89.8129 174.6382 277.1777 456.2789 678.4717 989.8214 1404.6681 2027.1721 2862.6111 4428.4937 7259.4482 12757.5781 | lr 1.2e-04 | norm 3562.6628 | dt 9.874 +type train | step 4366 | loss 102.8966 200.4919 313.2493 511.0237 751.5701 1080.1217 1517.1477 2170.1521 3033.5049 4662.4458 7651.8662 13511.5342 | lr 1.2e-04 | norm 5452.4473 | dt 9.854 +type train | step 4367 | loss 88.2403 173.4238 280.0194 459.3342 687.3156 1014.9290 1442.1998 2084.9255 2948.2981 4594.4609 7611.0850 13469.5820 | lr 1.2e-04 | norm 4474.0356 | dt 9.869 +type train | step 4368 | loss 83.4238 162.2506 259.4297 430.7154 647.9370 937.5864 1332.0507 1921.8268 2739.5332 4281.8535 7121.0713 12543.0762 | lr 1.2e-04 | norm 3685.3003 | dt 9.884 +type train | step 4369 | loss 94.6957 184.4171 293.7616 478.7420 707.8933 1033.5837 1451.1658 2087.5149 2903.2891 4498.3574 7449.4917 13224.1914 | lr 1.2e-04 | norm 4628.3569 | dt 9.870 +type train | step 4370 | loss 93.7841 184.9929 292.2470 477.2218 703.2420 1025.1237 1450.1971 2089.7874 2927.9177 4525.7803 7455.6152 13019.7441 | lr 1.2e-04 | norm 3805.3113 | dt 9.871 +type train | step 4371 | loss 93.7261 184.1136 287.0067 469.4162 695.7055 1009.6697 1418.5317 2038.9717 2862.1001 4448.4233 7471.0239 13366.8350 | lr 1.2e-04 | norm 5555.2935 | dt 9.855 +type train | step 4372 | loss 102.4316 206.0768 318.5033 512.3158 751.3037 1098.7616 1533.7544 2176.1541 2956.1597 4491.0479 7335.7793 12938.0020 | lr 1.2e-04 | norm 5818.6978 | dt 9.852 +type train | step 4373 | loss 91.1600 183.1983 289.4303 477.6897 707.5000 1028.7578 1455.3153 2090.5737 2954.8215 4571.7778 7539.5322 13258.2510 | lr 1.2e-04 | norm 4438.3462 | dt 9.867 +type train | step 4374 | loss 88.6782 174.8487 274.9539 452.5293 671.4410 978.6334 1388.6147 2002.5492 2829.2556 4412.9746 7321.6709 12971.8652 | lr 1.2e-04 | norm 4077.3003 | dt 9.873 +type train | step 4375 | loss 89.4729 176.4020 282.6077 466.2054 693.4391 1027.8416 1464.6910 2121.7668 2997.4966 4661.5586 7744.2412 13765.3330 | lr 1.2e-04 | norm 4548.1606 | dt 9.860 +type train | step 4376 | loss 87.7074 173.8424 277.8134 462.5871 695.9504 1012.0567 1436.1281 2079.2800 2953.5679 4595.8682 7533.0435 13104.6465 | lr 1.2e-04 | norm 3917.2910 | dt 9.860 +type train | step 4377 | loss 86.2843 168.6748 265.7848 441.0021 662.3226 976.9546 1384.6804 2015.7667 2832.4443 4379.5073 7222.1177 12702.6836 | lr 1.2e-04 | norm 3724.9578 | dt 9.859 +type train | step 4378 | loss 94.3602 182.9097 287.0645 469.9528 691.9256 1004.0098 1411.6731 2021.2283 2843.0500 4405.0635 7278.3638 12785.5645 | lr 1.2e-04 | norm 4121.7661 | dt 9.891 +type train | step 4379 | loss 87.9423 174.2375 277.9435 462.5872 689.4408 1006.9708 1433.4645 2075.4866 2948.9705 4592.8359 7561.5337 13232.9180 | lr 1.2e-04 | norm 3463.4385 | dt 9.878 +type train | step 4380 | loss 93.1767 183.6917 288.7925 472.3908 696.4784 1002.8212 1406.9288 2015.0057 2831.9148 4359.2969 7144.8066 12627.8467 | lr 1.2e-04 | norm 4835.4717 | dt 9.862 +type train | step 4381 | loss 91.9007 179.0544 283.6800 464.7594 691.5850 1012.3060 1427.8757 2064.9846 2915.6965 4527.9170 7483.7104 13152.8252 | lr 1.2e-04 | norm 3799.1890 | dt 9.861 +type train | step 4382 | loss 91.7476 180.3184 287.3080 473.1455 701.8474 1015.7137 1429.4015 2047.1259 2885.6655 4484.0879 7391.6675 12936.0850 | lr 1.2e-04 | norm 3615.6926 | dt 9.868 +type train | step 4383 | loss 90.9134 177.1162 279.4303 462.0887 686.9872 1004.0490 1419.8240 2040.0603 2879.3567 4474.4995 7406.0059 12997.6650 | lr 1.2e-04 | norm 3782.7590 | dt 9.879 +type train | step 4384 | loss 80.2266 155.8288 249.9747 418.5469 632.0555 925.2211 1320.4980 1919.9634 2742.8682 4294.9165 7134.4326 12607.7705 | lr 1.2e-04 | norm 4152.0640 | dt 9.854 +type train | step 4385 | loss 89.4095 173.7072 274.1700 455.3204 678.0671 991.1533 1408.0352 2037.0168 2877.0713 4483.8604 7424.9546 13069.3789 | lr 1.2e-04 | norm 3707.4045 | dt 9.876 +type train | step 4386 | loss 94.0997 184.0531 291.9772 480.9994 711.7785 1028.8739 1444.7845 2068.9812 2906.8735 4505.8823 7440.9409 13181.4316 | lr 1.2e-04 | norm 3409.7698 | dt 9.867 +type train | step 4387 | loss 89.5711 177.4638 281.8169 459.7067 683.5046 986.0289 1395.7501 2011.8949 2854.2456 4426.7832 7311.5884 12904.8818 | lr 1.2e-04 | norm 3375.9265 | dt 9.876 +type train | step 4388 | loss 90.6086 178.3544 281.8568 464.3472 692.6606 1013.0527 1435.3512 2089.2798 2934.7007 4573.4624 7582.8540 13409.6865 | lr 1.2e-04 | norm 4345.9863 | dt 9.872 +type train | step 4389 | loss 97.9722 192.1188 295.9872 476.8190 700.2943 1015.3280 1419.7170 2026.3453 2812.0105 4317.9189 7012.0010 12323.2129 | lr 1.2e-04 | norm 3604.2336 | dt 9.858 +type train | step 4390 | loss 87.3203 170.1763 272.6474 451.0130 671.8429 977.9447 1383.6824 2006.2505 2841.8318 4460.9336 7460.8799 13212.4668 | lr 1.2e-04 | norm 4123.5635 | dt 9.882 +type train | step 4391 | loss 93.1951 183.7672 294.1752 480.7617 711.6902 1037.5746 1469.2921 2116.0034 2954.8098 4561.4907 7488.6953 13271.5469 | lr 1.2e-04 | norm 4690.8999 | dt 9.880 +type train | step 4392 | loss 86.0279 171.3042 272.9456 450.7840 674.1692 985.4810 1403.4768 2035.1831 2882.8203 4468.6875 7373.8804 12866.0791 | lr 1.2e-04 | norm 3628.5500 | dt 9.865 +type train | step 4393 | loss 84.9219 166.5568 264.6483 438.9526 658.6893 960.7863 1371.6880 1985.1211 2825.5815 4412.1357 7308.0527 12822.7705 | lr 1.2e-04 | norm 3834.9727 | dt 9.888 +type train | step 4394 | loss 86.7580 170.6128 268.2298 445.0638 663.4899 966.5182 1372.8922 1983.8699 2813.3123 4387.7393 7269.6289 12779.4355 | lr 1.2e-04 | norm 3722.0847 | dt 9.863 +type train | step 4395 | loss 93.3655 184.7816 291.2038 480.4791 712.7762 1032.6801 1457.3450 2088.0771 2928.9517 4560.6577 7570.9844 13477.1348 | lr 1.2e-04 | norm 4337.3379 | dt 9.900 +type train | step 4396 | loss 92.0443 181.0700 286.7383 473.3698 702.9307 1019.1401 1431.0865 2060.0203 2899.2104 4491.8682 7449.4219 13111.7422 | lr 1.2e-04 | norm 3567.4919 | dt 9.867 +type train | step 4397 | loss 89.6165 174.3739 276.0410 453.6122 676.1512 983.7976 1392.2372 1995.1523 2817.3687 4345.4414 7172.6636 12567.5830 | lr 1.2e-04 | norm 3407.4441 | dt 9.879 +type train | step 4398 | loss 97.8833 191.9756 298.0107 488.1876 721.3246 1049.4753 1478.5576 2121.7698 2980.1045 4600.7139 7540.5137 13186.6484 | lr 1.2e-04 | norm 4080.8542 | dt 9.886 +type train | step 4399 | loss 91.8758 179.9167 285.0961 465.1057 689.5683 1000.6819 1415.7478 2031.0402 2855.6924 4416.5557 7281.3608 12842.3145 | lr 1.2e-04 | norm 3192.0784 | dt 9.878 +type train | step 4400 | loss 85.1853 167.3432 271.1676 454.5061 684.1628 1005.9090 1428.5996 2064.2700 2910.8782 4506.1416 7418.7871 13014.6318 | lr 1.2e-04 | norm 4402.3936 | dt 9.869 +type train | step 4401 | loss 92.1659 183.2236 285.8663 467.7024 695.4253 1017.6525 1446.5186 2088.8569 2944.3496 4583.1016 7580.4170 13316.5254 | lr 1.2e-04 | norm 3772.0947 | dt 9.866 +type train | step 4402 | loss 91.9695 180.4271 284.1198 471.0616 701.4798 1016.7187 1430.3420 2076.3098 2913.5779 4573.2632 7602.1855 13362.0879 | lr 1.2e-04 | norm 6012.6558 | dt 9.873 +type train | step 4403 | loss 89.4483 173.6773 274.8931 452.6666 677.0715 987.1091 1391.6470 2000.7722 2830.9202 4398.5928 7261.0146 12735.3789 | lr 1.2e-04 | norm 3198.9800 | dt 9.875 +type train | step 4404 | loss 91.7868 180.2739 285.2068 467.6090 695.7092 1009.2294 1423.8616 2045.5618 2894.5464 4497.8657 7443.3848 13019.5391 | lr 1.2e-04 | norm 4052.3230 | dt 9.882 +type train | step 4405 | loss 102.2317 198.3013 304.0940 493.0629 726.7618 1084.4199 1526.1281 2222.8560 3069.5659 4682.7505 7711.9580 13449.7334 | lr 1.2e-04 | norm 7556.8467 | dt 9.843 +type train | step 4406 | loss 87.3216 170.6725 273.4257 453.2482 675.7468 987.4100 1403.3770 2021.4941 2859.4072 4449.5752 7338.1270 12914.4785 | lr 1.2e-04 | norm 3808.8796 | dt 9.885 +type train | step 4407 | loss 94.7919 187.1174 295.8246 481.8284 708.4252 1012.9838 1423.7134 2032.2562 2868.8923 4438.4219 7288.7549 12830.2930 | lr 1.2e-04 | norm 4274.3145 | dt 9.876 +type train | step 4408 | loss 91.8669 181.8089 288.0010 473.8344 701.6538 1008.0167 1425.6537 2046.7189 2896.2144 4512.0352 7486.1499 13244.4434 | lr 1.2e-04 | norm 3792.7844 | dt 9.872 +type train | step 4409 | loss 92.3551 180.8454 287.1487 472.3763 697.8103 1015.0205 1429.9238 2064.9231 2913.4797 4536.4360 7504.2480 13284.3105 | lr 1.2e-04 | norm 3609.2544 | dt 9.873 +type train | step 4410 | loss 90.7098 177.9648 281.5130 462.3017 686.3477 997.9322 1406.9603 2026.1133 2873.3845 4463.1733 7372.5659 13005.7100 | lr 1.2e-04 | norm 3549.2910 | dt 9.876 +type train | step 4411 | loss 91.8424 181.1746 286.7943 472.1615 699.6407 1022.2968 1440.8306 2075.3486 2903.8311 4484.3345 7450.8828 13169.3389 | lr 1.2e-04 | norm 4024.4390 | dt 9.864 +type train | step 4412 | loss 91.1303 179.4854 284.9029 468.8778 694.3740 999.1975 1405.9430 2017.9735 2847.1228 4384.6270 7208.4829 12641.0908 | lr 1.2e-04 | norm 3413.7781 | dt 9.873 +type train | step 4413 | loss 89.5382 174.8700 274.4295 451.7517 674.3930 987.5043 1392.8003 2007.6063 2854.1716 4417.1777 7287.9014 12711.3047 | lr 1.2e-04 | norm 3376.2546 | dt 9.861 +type train | step 4414 | loss 98.6633 194.8162 304.2046 492.7545 724.7671 1037.1687 1460.7711 2102.7056 2976.9065 4613.2168 7663.9692 13551.3145 | lr 1.2e-04 | norm 6400.6733 | dt 9.859 +type train | step 4415 | loss 100.4245 199.6574 306.2811 496.5300 726.4448 1059.1075 1496.8969 2158.0950 3021.3472 4689.5542 7791.2715 13818.6934 | lr 1.2e-04 | norm 4403.3560 | dt 9.872 +type train | step 4416 | loss 94.0945 185.3963 293.7307 479.7175 708.5641 1027.8331 1455.3101 2088.3311 2933.7561 4519.1787 7443.2104 13065.7666 | lr 1.2e-04 | norm 3438.4861 | dt 9.874 +type train | step 4417 | loss 91.0143 180.6287 285.5195 467.4633 696.1874 1023.5146 1459.7529 2114.0198 2985.0959 4634.9976 7665.1050 13546.5625 | lr 1.2e-04 | norm 3426.9258 | dt 9.866 +type train | step 4418 | loss 161.3110 319.1220 439.1132 680.1591 951.3862 1413.1998 1968.3928 2787.8274 3627.3152 5395.9604 8718.6963 14955.8213 | lr 1.2e-04 | norm 9955.1318 | dt 9.826 +type train | step 4419 | loss 88.9136 174.7764 276.0751 459.1594 682.9363 995.3471 1406.9412 2025.1356 2838.3303 4379.1313 7229.3467 12685.3428 | lr 1.2e-04 | norm 4091.3013 | dt 9.857 +type train | step 4420 | loss 89.6556 175.5024 276.9995 456.3587 677.5100 989.1305 1399.2240 2021.8341 2857.5378 4456.1851 7433.3447 13069.5723 | lr 1.2e-04 | norm 3614.6721 | dt 9.866 +type train | step 4421 | loss 97.2600 193.8600 300.4297 489.9131 720.7352 1044.1948 1466.7979 2092.5369 2951.9226 4543.8711 7441.2271 12955.0469 | lr 1.2e-04 | norm 3783.3464 | dt 9.878 +type train | step 4422 | loss 96.3361 188.7728 288.9231 467.1814 686.4901 993.4872 1392.0846 1990.5630 2798.6135 4323.6133 7135.0708 12469.5020 | lr 1.2e-04 | norm 3926.9880 | dt 9.869 +type train | step 4423 | loss 96.0441 189.6142 297.8831 482.4237 709.0617 1018.9271 1432.0276 2047.8542 2878.9302 4471.9980 7429.7690 13105.7197 | lr 1.2e-04 | norm 3938.8586 | dt 9.883 +type train | step 4424 | loss 92.7115 182.1004 285.1893 467.9857 695.6932 1015.4501 1434.8772 2076.3787 2938.6653 4540.1436 7463.5518 13105.4082 | lr 1.2e-04 | norm 3639.7410 | dt 9.874 +type train | step 4425 | loss 92.9287 182.5873 288.2888 477.6356 714.7153 1042.1240 1470.2207 2115.0479 3004.9578 4647.8086 7672.3721 13476.1572 | lr 1.2e-04 | norm 6481.9155 | dt 9.858 +type train | step 4426 | loss 90.1990 180.2489 288.6383 479.1066 708.0580 1029.1016 1450.8171 2080.3850 2941.7373 4568.2690 7625.3623 13471.1807 | lr 1.2e-04 | norm 5523.9604 | dt 9.872 +type train | step 4427 | loss 91.6502 179.6886 282.2839 463.5367 684.5692 995.4087 1404.7832 2011.6581 2841.7705 4418.1987 7288.5854 12802.8291 | lr 1.2e-04 | norm 3660.6162 | dt 9.877 +type train | step 4428 | loss 86.6316 169.6697 268.3004 447.9178 674.7170 999.2842 1430.1001 2082.9272 2942.5354 4599.1611 7605.4575 13358.3252 | lr 1.2e-04 | norm 4663.5464 | dt 9.859 +type train | step 4429 | loss 86.8772 169.3070 268.9451 447.5016 668.7709 976.1824 1384.8239 1994.0641 2817.1182 4362.2412 7174.5527 12589.5137 | lr 1.2e-04 | norm 3980.6990 | dt 9.864 +type train | step 4430 | loss 106.7746 210.5819 320.2952 529.1979 765.1739 1113.7961 1562.4034 2261.5669 3158.4958 4894.0884 8066.2427 13919.4053 | lr 1.2e-04 | norm 6494.2056 | dt 9.843 +type train | step 4431 | loss 91.9579 179.1354 286.0484 469.9803 697.5869 1008.7316 1422.9724 2043.7317 2871.5586 4456.2568 7372.2925 12999.9932 | lr 1.2e-04 | norm 3896.5266 | dt 9.869 +type train | step 4432 | loss 112.0150 223.5571 347.0247 555.2819 798.9594 1152.3057 1590.4767 2228.0564 2997.0286 4557.2827 7361.7261 12878.2607 | lr 1.2e-04 | norm 5299.8657 | dt 9.865 +type train | step 4433 | loss 97.9676 198.2837 312.4500 504.9021 746.8900 1080.9939 1514.0834 2168.6885 3037.9128 4716.2012 7722.9224 13477.2393 | lr 1.2e-04 | norm 5064.3726 | dt 9.859 +type train | step 4434 | loss 88.1832 173.0362 274.7966 456.9402 684.1966 998.2456 1414.3776 2039.5178 2905.2944 4523.7427 7477.4268 13147.5039 | lr 1.2e-04 | norm 3311.4404 | dt 9.875 +type train | step 4435 | loss 95.0690 187.8526 293.0630 474.3975 702.0980 1015.1604 1429.6871 2041.6178 2868.4678 4451.9917 7382.1484 13064.0830 | lr 1.2e-04 | norm 3978.0071 | dt 9.871 +type train | step 4436 | loss 87.2546 170.1090 271.0577 450.7760 673.5106 975.5204 1383.2101 1984.9562 2823.6013 4379.4424 7252.5679 12836.6484 | lr 1.2e-04 | norm 3793.8652 | dt 9.871 +type train | step 4437 | loss 92.0314 181.7673 285.6740 468.8598 695.1790 1012.5988 1431.0399 2069.7539 2909.5640 4504.0337 7401.9980 12918.8574 | lr 1.2e-04 | norm 3576.6326 | dt 9.887 +type train | step 4438 | loss 95.9211 186.9194 295.3940 483.0666 716.0079 1035.7627 1460.8156 2092.4978 2947.4312 4593.8359 7596.1328 13433.8555 | lr 1.2e-04 | norm 3650.2097 | dt 9.877 +type train | step 4439 | loss 85.6308 166.4052 266.4635 440.1447 657.5902 955.6700 1357.0148 1959.4564 2782.9031 4336.6396 7187.2632 12662.9590 | lr 1.2e-04 | norm 3399.6716 | dt 9.876 +type train | step 4440 | loss 91.4937 181.0767 285.5246 467.9329 691.7982 1012.5688 1437.9987 2072.5273 2924.9756 4544.7422 7523.2627 13370.8613 | lr 1.2e-04 | norm 3728.2390 | dt 9.872 +type train | step 4441 | loss 93.0008 183.4366 288.5332 471.4149 698.7803 1021.1722 1443.1865 2077.6956 2934.9390 4569.2461 7583.9580 13471.3896 | lr 1.2e-04 | norm 4084.6455 | dt 9.881 +type train | step 4442 | loss 88.9451 175.4772 274.9103 452.4749 671.9052 978.8696 1386.9705 1995.7175 2823.9324 4397.4014 7340.3955 12996.7764 | lr 1.2e-04 | norm 3561.6533 | dt 9.873 +type train | step 4443 | loss 91.3700 179.3791 283.1017 463.2094 688.1678 1000.6387 1415.9193 2030.9352 2868.0740 4471.0864 7415.8550 13109.2334 | lr 1.2e-04 | norm 4100.5610 | dt 9.881 +type train | step 4444 | loss 91.6569 176.2338 275.1777 453.4732 677.2469 988.8405 1399.3101 2008.8477 2824.5557 4382.5444 7247.5127 12787.8008 | lr 1.2e-04 | norm 4057.3594 | dt 10.172 +type train | step 4445 | loss 93.1857 183.2769 284.7455 463.8638 688.0833 996.2933 1401.4438 2011.7401 2852.2388 4448.4136 7350.2554 12961.8223 | lr 1.2e-04 | norm 3638.4690 | dt 9.863 +type train | step 4446 | loss 99.1597 194.6260 300.5463 487.3062 712.4637 1041.0773 1462.5245 2106.9595 2926.2170 4544.0229 7551.9819 13467.8809 | lr 1.2e-04 | norm 4300.4072 | dt 9.851 +type train | step 4447 | loss 89.9696 177.5337 283.4899 466.0446 692.8906 1007.6823 1426.1162 2051.7686 2899.6792 4502.0469 7412.6787 12948.7314 | lr 1.2e-04 | norm 3486.2839 | dt 9.871 +type train | step 4448 | loss 86.3326 175.4551 286.3891 484.2788 715.1599 1035.1218 1475.5281 2124.3997 2961.1235 4629.6997 7745.5557 13946.2715 | lr 1.2e-04 | norm 8545.9629 | dt 9.839 +type train | step 4449 | loss 93.0303 182.1356 285.4365 467.6844 691.1039 999.8555 1409.1582 2018.6808 2845.5798 4400.8564 7263.6030 12737.7295 | lr 1.2e-04 | norm 3426.5872 | dt 9.879 +type train | step 4450 | loss 102.4917 202.8101 314.7858 517.0387 761.6667 1120.3909 1580.9861 2294.4922 3186.7954 4911.0161 8075.1245 14178.4580 | lr 1.2e-04 | norm 5432.7163 | dt 9.868 +type train | step 4451 | loss 92.5470 186.0159 295.4955 483.3256 715.4198 1030.5579 1448.0654 2079.0488 2932.5620 4550.0039 7513.3618 13224.1191 | lr 1.2e-04 | norm 3512.2415 | dt 9.871 +type train | step 4452 | loss 90.7545 178.8789 281.6299 466.5760 702.0129 1030.9146 1456.1599 2102.5857 2936.7947 4512.7856 7474.5732 13383.5625 | lr 1.2e-04 | norm 6103.0273 | dt 9.844 +type train | step 4453 | loss 93.5996 185.9676 294.3954 482.6443 712.6476 1024.3701 1441.2715 2059.3057 2901.1724 4469.1558 7344.4536 12861.4131 | lr 1.2e-04 | norm 3576.6145 | dt 9.892 +type train | step 4454 | loss 91.9579 185.1320 298.9433 499.6639 737.9530 1065.5227 1496.0983 2144.2708 3018.7378 4677.2637 7766.2505 13645.2891 | lr 1.2e-04 | norm 4571.6489 | dt 9.874 +type train | step 4455 | loss 97.1068 192.7858 306.9134 509.8557 756.0080 1106.1086 1564.6433 2253.8804 3153.5215 4865.2393 8066.4346 14233.5889 | lr 1.2e-04 | norm 5166.3755 | dt 9.865 +type train | step 4456 | loss 98.6662 194.9631 303.6385 492.7724 727.8066 1047.4175 1469.2762 2107.0105 2962.8330 4590.7832 7552.1621 13238.7354 | lr 1.2e-04 | norm 3668.0017 | dt 9.894 +type train | step 4457 | loss 88.8066 175.5208 280.7910 464.1291 692.8031 1006.3776 1421.6443 2047.2209 2897.6470 4493.3062 7455.6401 13137.8936 | lr 1.2e-04 | norm 3612.6609 | dt 9.893 +type train | step 4458 | loss 99.8910 214.0059 370.6262 650.9603 953.6436 1350.8770 1890.3879 2679.5535 3722.7961 5634.8359 9495.7305 17087.7832 | lr 1.2e-04 | norm 19380.9727 | dt 9.828 +type train | step 4459 | loss 94.8441 195.2978 317.4856 530.7216 782.0643 1123.0469 1575.4276 2248.4333 3164.7881 4871.8701 8079.2168 14310.7559 | lr 1.2e-04 | norm 6690.7583 | dt 9.880 +type train | step 4460 | loss 94.7331 186.5983 295.3384 480.1692 711.2321 1026.3878 1441.9395 2063.3931 2918.1755 4517.4609 7479.8936 13162.9268 | lr 1.2e-04 | norm 4350.8843 | dt 9.887 +type train | step 4461 | loss 92.3750 183.8792 289.1248 473.8739 700.7242 1020.5287 1446.0295 2080.1631 2918.1711 4518.7964 7504.2671 13366.4160 | lr 1.2e-04 | norm 4121.9331 | dt 9.866 +type train | step 4462 | loss 94.9158 185.9552 292.8438 481.9349 711.9712 1034.2640 1454.4335 2095.6667 2921.6799 4493.4072 7413.2646 13072.2803 | lr 1.2e-04 | norm 4942.4473 | dt 9.870 +type train | step 4463 | loss 101.2803 201.9420 316.0882 510.7097 748.3874 1072.2081 1507.3563 2154.5015 2998.4761 4625.5337 7670.0137 13548.1191 | lr 1.2e-04 | norm 4442.6304 | dt 9.875 +type train | step 4464 | loss 94.0649 188.1183 300.9251 492.1692 726.0683 1050.7355 1476.9603 2107.2434 2960.7554 4585.7383 7600.8784 13394.3994 | lr 1.2e-04 | norm 3573.0466 | dt 9.877 +type train | step 4465 | loss 93.7718 186.1412 296.0454 488.6042 725.2534 1056.9380 1499.0717 2149.8171 3018.3743 4702.4487 7874.0215 14063.2080 | lr 1.2e-04 | norm 5995.7720 | dt 9.867 +type train | step 4466 | loss 93.8892 185.9231 293.8777 478.5147 708.5388 1031.6202 1446.5660 2081.0127 2931.9229 4520.2095 7416.4893 12999.9316 | lr 1.2e-04 | norm 3393.3738 | dt 9.902 +type train | step 4467 | loss 88.6593 174.9155 278.3609 457.7523 684.6117 997.8654 1415.4391 2038.0487 2909.4312 4520.7632 7465.4668 13111.5537 | lr 1.2e-04 | norm 3867.7625 | dt 9.880 +type train | step 4468 | loss 92.8636 182.8441 291.0561 484.9587 722.2980 1043.0835 1467.2688 2099.1252 2944.4634 4514.0830 7428.4863 13031.6924 | lr 1.2e-04 | norm 3752.9473 | dt 9.890 +type train | step 4469 | loss 95.8123 190.3370 301.5657 492.8252 728.4238 1045.5813 1468.8865 2107.8833 2976.0994 4583.0142 7555.0425 13237.2998 | lr 1.2e-04 | norm 3367.7979 | dt 9.890 +type train | step 4470 | loss 93.9994 186.7659 298.9368 490.8712 728.2479 1054.1609 1491.0857 2146.3455 3034.9324 4711.7051 7781.4038 13748.4766 | lr 1.2e-04 | norm 4125.9004 | dt 9.874 +type train | step 4471 | loss 92.8029 181.2726 283.7902 465.8733 691.7804 997.7731 1403.9885 2013.6295 2851.6963 4417.3896 7356.3828 13023.4316 | lr 1.2e-04 | norm 4588.9341 | dt 9.851 +type train | step 4472 | loss 86.1577 170.1010 274.2985 459.8953 686.0452 995.8342 1405.2496 2023.0621 2851.4329 4440.0298 7381.7700 13154.7949 | lr 1.2e-04 | norm 4339.8198 | dt 9.874 +type train | step 4473 | loss 96.2676 192.6600 300.3501 488.4639 720.6765 1036.5261 1450.7200 2073.6924 2933.2134 4538.3740 7536.4512 13398.2158 | lr 1.1e-04 | norm 4570.6880 | dt 9.873 +type train | step 4474 | loss 100.0238 205.0075 320.8975 526.0954 777.1957 1125.5006 1577.3004 2245.6760 3163.9272 4846.1978 7969.9077 13965.8594 | lr 1.1e-04 | norm 5096.8330 | dt 9.884 +type train | step 4475 | loss 91.7259 181.9371 289.5226 477.6923 707.5313 1029.1417 1448.2657 2079.9111 2924.6179 4515.9321 7435.8203 13110.0137 | lr 1.1e-04 | norm 3326.5891 | dt 9.884 +type train | step 4476 | loss 102.3943 204.3329 315.8743 513.0017 751.3994 1081.7761 1537.8282 2208.6111 3123.9351 4862.0908 8087.1582 14331.5693 | lr 1.1e-04 | norm 6839.3511 | dt 9.860 +type train | step 4477 | loss 95.6516 190.4568 301.0777 493.2749 726.4549 1045.9016 1469.2587 2099.6182 2970.1528 4611.3838 7669.8945 13656.8682 | lr 1.1e-04 | norm 4167.1973 | dt 9.866 +type train | step 4478 | loss 93.3848 185.8934 294.5290 479.1858 711.0648 1026.7112 1448.8643 2073.5710 2933.7354 4551.4526 7547.6206 13322.1504 | lr 1.1e-04 | norm 3276.2700 | dt 9.885 +type train | step 4479 | loss 92.6042 184.6036 294.7043 486.9339 724.1821 1042.1562 1467.3601 2101.7083 2978.5410 4634.3232 7633.4077 13355.7139 | lr 1.1e-04 | norm 4043.4402 | dt 9.884 +type train | step 4480 | loss 90.7848 180.3742 287.2766 473.9897 708.7782 1027.7380 1453.9297 2082.0752 2947.3999 4611.2480 7733.0620 13737.9287 | lr 1.1e-04 | norm 4534.6826 | dt 9.859 +type train | step 4481 | loss 98.6391 193.6459 302.3502 491.2530 718.2473 1032.0361 1442.9941 2045.3635 2851.5247 4357.9404 7190.3579 12741.1455 | lr 1.1e-04 | norm 3568.2976 | dt 9.881 +type train | step 4482 | loss 96.2836 190.0003 294.0539 476.7115 708.7202 1030.7493 1458.3630 2089.3494 2922.0518 4510.3008 7429.9565 12985.4316 | lr 1.1e-04 | norm 5135.1982 | dt 9.872 +type train | step 4483 | loss 97.8294 191.0925 299.4848 491.2525 724.2745 1042.4012 1466.5812 2087.3040 2936.9580 4561.1660 7548.0454 13399.1572 | lr 1.1e-04 | norm 4286.4961 | dt 9.875 +type train | step 4484 | loss 84.8092 168.8903 271.8223 455.0482 684.7758 1009.3950 1442.4476 2087.6716 2976.4614 4629.3418 7637.7432 13422.1865 | lr 1.1e-04 | norm 4304.7803 | dt 9.888 +type train | step 4485 | loss 95.6323 189.5482 299.7178 490.3007 728.2653 1058.1588 1491.2047 2139.9004 3015.7461 4679.1938 7730.6011 13631.1709 | lr 1.1e-04 | norm 3773.5146 | dt 9.873 +type train | step 4486 | loss 97.4576 194.5722 313.3714 512.2715 751.7835 1076.6768 1500.4141 2132.0122 2991.1008 4617.8467 7616.1602 13395.6270 | lr 1.1e-04 | norm 3572.0625 | dt 9.874 +type train | step 4487 | loss 99.7666 199.9856 313.1577 513.0795 758.6816 1096.0044 1534.6093 2183.5977 3066.3291 4739.5991 7798.3843 13638.8604 | lr 1.1e-04 | norm 3994.4976 | dt 9.896 +type train | step 4488 | loss 105.4120 212.1030 336.1382 554.8568 810.0427 1172.5513 1625.8145 2314.1562 3191.6079 4875.4312 7998.3979 14189.9102 | lr 1.1e-04 | norm 4705.6094 | dt 9.867 +type train | step 4489 | loss 89.4983 177.3462 282.7891 470.1686 706.3641 1033.0311 1471.2621 2127.8945 3030.5208 4679.1387 7636.3462 13264.6973 | lr 1.1e-04 | norm 3935.7366 | dt 9.865 +type train | step 4490 | loss 99.7052 200.6929 315.7571 508.8511 749.9947 1092.4819 1531.1011 2205.4482 3066.0725 4693.3032 7737.1699 13674.0371 | lr 1.1e-04 | norm 4430.9277 | dt 9.875 +type train | step 4491 | loss 92.0654 181.7746 288.6258 474.1704 705.8673 1016.4318 1428.9092 2051.0029 2897.6323 4477.4585 7414.1934 13007.5801 | lr 1.1e-04 | norm 3188.3352 | dt 9.882 +type train | step 4492 | loss 103.0182 203.2956 317.1359 516.7125 753.1840 1098.8145 1533.4484 2183.8491 2989.2292 4584.1812 7528.0156 13201.2461 | lr 1.1e-04 | norm 4885.3755 | dt 9.881 +type train | step 4493 | loss 88.4222 180.9906 294.0753 489.2054 733.0541 1044.5721 1479.6093 2101.0417 3027.5334 4706.7334 7867.2822 14045.6777 | lr 1.1e-04 | norm 7885.4985 | dt 9.878 +type train | step 4494 | loss 99.0965 196.6265 311.3387 501.4293 738.8464 1059.4138 1481.2933 2107.4956 2944.4441 4524.5747 7432.5518 13091.3428 | lr 1.1e-04 | norm 3401.9346 | dt 9.902 +type train | step 4495 | loss 96.6928 190.6729 294.2309 480.1925 708.4061 1028.9973 1454.4242 2103.7405 2946.7893 4562.3286 7568.2168 13621.2773 | lr 1.1e-04 | norm 7545.3335 | dt 9.860 +type train | step 4496 | loss 89.8333 177.8068 287.4140 480.6393 713.6866 1037.4998 1465.5651 2107.2173 2977.6299 4590.6753 7605.9902 13441.3105 | lr 1.1e-04 | norm 3764.7607 | dt 9.866 +type train | step 4497 | loss 94.5995 193.8171 308.1410 501.8529 737.9470 1058.3525 1480.2754 2114.0723 2982.9568 4644.8999 7797.2256 13920.7998 | lr 1.1e-04 | norm 6054.7236 | dt 9.877 +type train | step 4498 | loss 96.1757 192.3941 301.3698 495.0387 730.7797 1059.7367 1490.4796 2142.3486 2995.9424 4607.7051 7549.7559 13224.7227 | lr 1.1e-04 | norm 3572.2617 | dt 9.871 +type train | step 4499 | loss 90.1968 178.6353 284.7465 471.1254 700.6577 1008.2549 1418.1407 2033.1282 2872.8994 4446.5952 7387.7437 13011.2930 | lr 1.1e-04 | norm 3709.4514 | dt 9.884 +type train | step 4500 | loss 91.4088 180.3498 286.2400 476.0499 704.6451 1032.6982 1468.3121 2120.0974 2978.0659 4586.2378 7553.5024 13236.7588 | lr 1.1e-04 | norm 4803.1079 | dt 9.855 +type train | step 4501 | loss 100.7270 202.0367 313.8957 504.3329 746.0161 1081.2932 1533.9419 2202.1863 3065.4338 4703.9072 7666.7422 13420.6533 | lr 1.1e-04 | norm 4952.9551 | dt 9.869 +type train | step 4502 | loss 94.4802 185.2718 293.8776 481.4679 720.1771 1050.5894 1482.0068 2125.7891 2996.6052 4604.8350 7556.7510 13250.8838 | lr 1.1e-04 | norm 3504.4387 | dt 9.864 +type train | step 4503 | loss 95.3411 190.6082 302.0862 494.0897 726.3650 1053.2125 1481.2216 2115.7930 2958.6262 4568.3960 7542.0752 13289.8477 | lr 1.1e-04 | norm 3462.9146 | dt 9.878 +type train | step 4504 | loss 98.1039 197.2602 309.6180 505.6177 745.5095 1077.6564 1513.7079 2152.7366 3021.0574 4649.2974 7673.3379 13474.4521 | lr 1.1e-04 | norm 3689.3882 | dt 9.891 +type train | step 4505 | loss 92.6224 183.9648 290.7560 478.7243 716.1251 1041.6445 1474.5468 2108.7996 2971.6479 4614.3252 7752.2285 13923.1289 | lr 1.1e-04 | norm 4748.5693 | dt 9.858 +type train | step 4506 | loss 94.7650 187.6832 295.0825 482.5023 716.0063 1029.7303 1448.5859 2079.3750 2942.5823 4551.3408 7464.0425 13062.0566 | lr 1.1e-04 | norm 3433.5105 | dt 9.869 +type train | step 4507 | loss 92.7056 186.7673 295.7415 486.9031 720.4066 1039.4105 1466.2466 2100.2668 2949.6350 4553.8276 7531.5029 13359.0303 | lr 1.1e-04 | norm 5750.1899 | dt 9.881 +type train | step 4508 | loss 95.0998 188.0430 293.4409 478.5920 710.2628 1025.4847 1450.5016 2083.7974 2966.6714 4663.9668 7768.7334 13687.4336 | lr 1.1e-04 | norm 5776.4077 | dt 9.850 +type train | step 4509 | loss 95.2423 190.0478 305.6346 507.7851 754.3077 1098.9293 1552.8004 2234.2468 3158.7178 4913.2148 8140.5186 14427.5312 | lr 1.1e-04 | norm 6884.1001 | dt 9.845 +type train | step 4510 | loss 92.7709 185.9029 297.3777 486.4160 722.3954 1038.5742 1453.3625 2070.0989 2925.4766 4492.4194 7336.1621 12802.1748 | lr 1.1e-04 | norm 3519.7039 | dt 9.891 +type train | step 4511 | loss 98.7919 196.5582 307.6212 506.0090 741.7321 1073.0220 1508.4957 2162.8940 3012.7974 4667.5625 7721.8223 13711.9746 | lr 1.1e-04 | norm 4073.2466 | dt 9.869 +type train | step 4512 | loss 93.6813 189.9016 297.9079 494.3813 731.6420 1055.6868 1483.8835 2123.5554 2988.6313 4630.9355 7645.4878 13456.5205 | lr 1.1e-04 | norm 4695.3496 | dt 9.865 +type train | step 4513 | loss 104.1487 206.9008 319.5042 511.4493 750.3573 1093.0017 1535.6823 2197.3901 3007.0159 4566.4810 7477.4380 13182.6074 | lr 1.1e-04 | norm 5163.3765 | dt 9.862 +type train | step 4514 | loss 92.3519 183.2430 289.1494 474.7542 706.7949 1025.5344 1446.7690 2071.2632 2911.9087 4508.0698 7448.4062 13139.4961 | lr 1.1e-04 | norm 3647.6211 | dt 9.866 +type train | step 4515 | loss 93.1095 184.7597 293.2420 486.6181 720.4314 1039.7595 1467.3779 2100.9307 2948.9771 4528.1660 7521.6846 13331.6963 | lr 1.1e-04 | norm 4879.4541 | dt 9.883 +type train | step 4516 | loss 89.8431 178.5309 285.1262 469.7658 699.7336 1015.9722 1433.4309 2060.0000 2919.2349 4520.3989 7456.3267 13052.1680 | lr 1.1e-04 | norm 3411.4973 | dt 9.881 +type train | step 4517 | loss 93.7540 187.1583 296.8445 485.6940 720.2556 1047.8601 1472.7213 2106.6279 2975.9685 4587.3550 7584.2148 13347.8125 | lr 1.1e-04 | norm 3353.2512 | dt 9.901 +type train | step 4518 | loss 94.4192 186.7977 294.3430 481.3763 711.9233 1021.2964 1434.0835 2051.6797 2888.5046 4466.3467 7377.5786 12956.2354 | lr 1.1e-04 | norm 3218.6702 | dt 9.881 +type train | step 4519 | loss 101.7954 201.3421 313.0459 504.7024 736.8207 1066.9252 1505.3929 2158.2244 2995.2256 4564.8965 7493.3579 13249.0391 | lr 1.1e-04 | norm 4842.8467 | dt 9.885 +type train | step 4520 | loss 91.1577 181.7750 287.8075 472.3715 703.1567 1015.2770 1431.6823 2057.7810 2929.0164 4549.8110 7487.6055 13131.8262 | lr 1.1e-04 | norm 3457.7578 | dt 9.879 +type train | step 4521 | loss 95.4360 194.0007 307.7948 504.2014 745.4038 1082.5779 1516.6980 2182.0735 3055.0056 4720.5244 7805.0542 13689.4541 | lr 1.1e-04 | norm 4400.7974 | dt 9.886 +type train | step 4522 | loss 96.4277 193.4431 309.1743 507.8208 748.3795 1071.2112 1495.6764 2133.7844 3006.4553 4615.0825 7570.6021 13266.8037 | lr 1.1e-04 | norm 3629.5137 | dt 9.873 +type train | step 4523 | loss 91.9123 183.1295 294.3628 490.4534 729.0642 1062.2452 1495.1202 2149.9163 3033.5466 4685.3574 7774.3984 13747.1260 | lr 1.1e-04 | norm 4546.4370 | dt 9.858 +type train | step 4524 | loss 92.4405 181.4781 286.4091 472.4232 707.7278 1024.1707 1444.3741 2073.5403 2929.9741 4540.5459 7447.2886 13070.3018 | lr 1.1e-04 | norm 3614.2485 | dt 9.862 +type train | step 4525 | loss 93.6731 186.5001 292.8369 479.5768 710.1496 1025.6736 1443.7505 2064.1443 2910.5325 4508.7656 7494.9907 13259.3896 | lr 1.1e-04 | norm 3860.2908 | dt 9.896 +type train | step 4526 | loss 99.7017 199.9041 312.1208 505.1573 740.9758 1071.4877 1498.5812 2125.6509 2947.0847 4514.2417 7461.2705 13101.1494 | lr 1.1e-04 | norm 3475.8201 | dt 9.886 +type train | step 4527 | loss 92.1428 185.3922 294.2559 486.9873 730.1066 1071.2715 1510.5547 2176.0374 3048.9309 4699.0205 7747.1133 13645.6729 | lr 1.1e-04 | norm 4932.3110 | dt 9.867 +type train | step 4528 | loss 98.1517 195.7211 304.8240 497.8206 732.4752 1058.3914 1496.8179 2147.6116 3005.6179 4625.7520 7607.5894 13409.5342 | lr 1.1e-04 | norm 4164.2676 | dt 9.881 +type train | step 4529 | loss 94.3640 185.5826 294.1597 478.8363 707.3702 1025.8555 1445.6772 2066.5269 2913.2131 4499.3027 7448.5684 13082.9873 | lr 1.1e-04 | norm 3849.3232 | dt 9.885 +type train | step 4530 | loss 94.8017 188.6194 301.1034 492.0958 728.1596 1046.1603 1472.3638 2105.2644 2970.8728 4580.0713 7547.0537 13274.0615 | lr 1.1e-04 | norm 3523.2876 | dt 9.888 +type train | step 4531 | loss 94.0651 185.6375 291.6080 476.3040 702.8398 1009.7379 1414.1073 2018.4530 2840.1655 4404.2007 7283.7695 12775.2432 | lr 1.1e-04 | norm 3798.5752 | dt 9.872 +type train | step 4532 | loss 96.8528 192.8363 304.4905 495.8496 737.5424 1081.7645 1518.7681 2177.4451 3038.9683 4668.1782 7722.3579 13561.9385 | lr 1.1e-04 | norm 5474.8545 | dt 9.870 +type train | step 4533 | loss 98.0235 195.2401 308.0204 505.8748 748.0424 1090.7661 1536.6129 2204.1975 3083.8667 4747.6045 7852.6797 13874.0918 | lr 1.1e-04 | norm 3665.2400 | dt 9.889 +type train | step 4534 | loss 97.8124 193.4912 304.6096 493.0650 730.1957 1057.5743 1490.4019 2141.2708 3013.8630 4641.1694 7617.4951 13348.8594 | lr 1.1e-04 | norm 3331.2271 | dt 9.880 +type train | step 4535 | loss 103.5032 206.7983 320.7220 513.6224 754.7662 1078.1669 1507.1232 2136.2351 2987.8567 4583.0869 7501.9580 13082.1035 | lr 1.1e-04 | norm 3969.5530 | dt 9.885 +type train | step 4536 | loss 90.9424 179.2056 285.6601 473.6558 703.4905 1021.4653 1439.5356 2075.8875 2930.0415 4533.9238 7499.3066 13284.5996 | lr 1.1e-04 | norm 4511.7935 | dt 9.870 +type train | step 4537 | loss 93.1581 182.2853 287.8621 478.5007 708.6895 1049.9297 1493.8127 2153.3501 3010.7576 4638.7710 7655.7344 13611.2715 | lr 1.1e-04 | norm 4028.6284 | dt 9.878 +type train | step 4538 | loss 90.2005 178.6039 283.5927 467.0364 693.7668 1008.6333 1421.2903 2041.9155 2888.5977 4482.9868 7415.8667 12989.7334 | lr 1.1e-04 | norm 3362.8899 | dt 9.895 +type train | step 4539 | loss 89.8553 177.1597 282.2878 469.6090 701.1150 1021.9761 1449.9344 2090.0947 2966.4983 4594.9087 7582.2495 13272.0869 | lr 1.1e-04 | norm 3756.6226 | dt 9.876 +type train | step 4540 | loss 102.9355 206.9777 323.9859 519.2825 752.8258 1078.2004 1506.9801 2145.6743 2961.2046 4529.2725 7493.1685 13264.1592 | lr 1.1e-04 | norm 5156.2271 | dt 9.874 +type train | step 4541 | loss 89.6295 177.6530 282.8563 467.4913 702.1458 1012.7430 1430.8387 2053.4963 2919.8037 4528.0327 7465.2173 13093.0557 | lr 1.1e-04 | norm 3436.6501 | dt 9.878 +type train | step 4542 | loss 91.5431 183.9804 289.1577 482.2364 716.2803 1032.9282 1453.6072 2078.0103 2932.9844 4564.5093 7516.6328 13150.0840 | lr 1.1e-04 | norm 6218.2324 | dt 9.854 +type train | step 4543 | loss 94.8089 188.2725 297.3583 487.2191 720.6234 1041.1476 1470.2306 2108.7375 2973.3950 4580.7969 7600.0732 13472.0234 | lr 1.1e-04 | norm 4147.5874 | dt 9.861 +type train | step 4544 | loss 95.9417 192.8792 300.2740 494.8641 728.1692 1050.1803 1483.9347 2131.4761 2967.0435 4601.5708 7636.0571 13566.8467 | lr 1.1e-04 | norm 5324.9863 | dt 9.858 +type train | step 4545 | loss 93.4273 186.7415 291.1566 475.2874 704.6234 1019.1757 1432.2114 2056.1467 2899.5759 4478.1304 7396.3096 12978.0098 | lr 1.1e-04 | norm 3766.9778 | dt 9.864 +type train | step 4546 | loss 96.8497 192.3841 302.1825 489.9362 720.9802 1041.0327 1455.4347 2071.3672 2889.4341 4453.5200 7395.4805 13065.7061 | lr 1.1e-04 | norm 3749.6296 | dt 9.892 +type train | step 4547 | loss 95.4396 191.7612 298.9907 486.2734 721.2480 1042.5339 1467.9441 2097.2004 2948.4829 4591.2197 7613.1475 13522.3076 | lr 1.1e-04 | norm 4875.7969 | dt 9.878 +type train | step 4548 | loss 94.1736 183.4528 289.4833 481.8986 715.5633 1052.7920 1488.9603 2159.2834 3034.5305 4690.9253 7779.3218 13842.9531 | lr 1.1e-04 | norm 5430.5029 | dt 9.865 +type train | step 4549 | loss 103.5120 205.4096 324.3224 532.0063 773.9355 1112.1504 1552.6179 2202.1431 3085.8896 4749.3501 7839.9077 13858.9336 | lr 1.1e-04 | norm 3823.2078 | dt 9.879 +type train | step 4550 | loss 93.6087 185.4000 293.2334 478.4633 708.2286 1025.4529 1439.4335 2052.9829 2870.2961 4418.1582 7267.9453 12701.5039 | lr 1.1e-04 | norm 3648.5637 | dt 9.885 +type train | step 4551 | loss 87.9216 173.7292 281.6397 468.6030 701.7960 1019.7263 1444.5459 2076.0083 2929.0554 4503.5000 7420.4678 12927.6270 | lr 1.1e-04 | norm 6762.7397 | dt 9.889 +type train | step 4552 | loss 90.6461 177.4077 282.1817 467.4987 694.7792 1005.6374 1406.3770 2010.9756 2825.3633 4376.4429 7225.7266 12751.9414 | lr 1.1e-04 | norm 4312.3696 | dt 9.882 +type train | step 4553 | loss 111.0650 221.4213 337.9992 530.5118 773.0574 1088.3541 1517.7043 2141.5354 3024.5117 4709.5371 7687.0933 13552.3086 | lr 1.1e-04 | norm 6729.4146 | dt 9.856 +type train | step 4554 | loss 97.5908 193.0246 301.8427 494.6208 730.5405 1047.7233 1469.8583 2103.4014 2973.3750 4586.8218 7569.3525 13328.6211 | lr 1.1e-04 | norm 3675.9919 | dt 9.879 +type train | step 4555 | loss 99.7874 196.2505 305.3795 495.0789 725.9016 1049.8447 1472.5549 2104.9299 2966.8845 4555.9756 7542.5498 13340.2803 | lr 1.1e-04 | norm 3955.6182 | dt 9.859 +type train | step 4556 | loss 101.6774 203.5517 321.6729 521.8711 757.9706 1111.4348 1563.2600 2242.3975 3090.3745 4782.6152 7976.9204 14237.0391 | lr 1.1e-04 | norm 6689.7339 | dt 9.851 +type train | step 4557 | loss 93.9036 187.0215 292.4169 479.1021 707.0067 1026.8135 1443.1799 2070.0315 2907.1003 4490.4722 7394.6060 12980.2744 | lr 1.1e-04 | norm 3203.7380 | dt 9.875 +type train | step 4558 | loss 104.0592 210.0974 321.7651 517.9432 758.0673 1095.5275 1537.0754 2191.0305 3060.2185 4690.3242 7710.4233 13463.4785 | lr 1.1e-04 | norm 3646.9204 | dt 9.881 +type train | step 4559 | loss 96.0441 189.5776 301.9160 496.2319 737.1252 1074.4904 1506.0234 2150.7654 2969.3721 4539.7905 7479.1904 13200.4619 | lr 1.1e-04 | norm 4116.5698 | dt 9.869 +type train | step 4560 | loss 94.4672 187.0704 294.4288 481.9744 711.8434 1031.7894 1443.4097 2053.1301 2871.0071 4430.8984 7307.9209 12863.3916 | lr 1.1e-04 | norm 4466.4453 | dt 9.883 +type train | step 4561 | loss 97.0807 192.1155 302.9128 497.6065 733.9839 1059.9919 1484.8002 2124.8445 2986.6997 4628.7012 7671.1255 13653.0078 | lr 1.1e-04 | norm 3820.1443 | dt 9.883 +type train | step 4562 | loss 97.5629 194.5999 303.1051 491.3024 719.7214 1061.5023 1481.7057 2104.5581 2876.4551 4385.7812 7220.1709 12823.2969 | lr 1.1e-04 | norm 4877.7197 | dt 9.856 +type train | step 4563 | loss 98.0365 197.8539 304.2988 493.9695 723.7609 1051.6023 1477.1113 2128.6355 2963.8162 4584.4258 7581.1260 13386.9746 | lr 1.1e-04 | norm 4037.4041 | dt 9.871 +type train | step 4564 | loss 95.5248 190.6292 299.4616 489.2277 720.7851 1034.3784 1454.1097 2076.6592 2907.5552 4486.1465 7381.6079 13025.4062 | lr 1.1e-04 | norm 3797.0015 | dt 9.877 +type train | step 4565 | loss 96.0656 193.3542 302.8622 499.1086 736.7427 1082.5566 1523.1272 2202.7947 3072.1433 4745.6934 7881.1333 14010.6396 | lr 1.1e-04 | norm 4561.9019 | dt 9.866 +type train | step 4566 | loss 93.4451 183.1799 290.3121 478.6389 708.5120 1033.1666 1453.4241 2085.5664 2915.2622 4514.9619 7435.5444 13038.7236 | lr 1.1e-04 | norm 3468.1636 | dt 9.898 +type train | step 4567 | loss 89.7692 179.5636 285.4243 466.5640 694.7123 1003.1694 1417.2527 2032.2761 2882.6094 4477.0244 7400.5444 12975.8818 | lr 1.1e-04 | norm 3026.9858 | dt 9.876 +type train | step 4568 | loss 91.7015 181.8884 286.7102 470.4671 700.1684 1015.3478 1433.4221 2064.4302 2929.0972 4530.1499 7448.6250 12990.6475 | lr 1.1e-04 | norm 3438.0645 | dt 9.870 +type train | step 4569 | loss 88.7337 176.7806 282.8011 464.4210 691.1637 1002.6158 1423.6051 2053.7944 2922.5225 4598.0669 7687.4902 13687.2705 | lr 1.1e-04 | norm 5988.4565 | dt 9.858 +type train | step 4570 | loss 96.7891 190.8194 299.5406 489.8526 720.9472 1055.5249 1484.6322 2142.6184 2990.8462 4613.0391 7623.5918 13533.1416 | lr 1.1e-04 | norm 4056.0366 | dt 9.872 +type train | step 4571 | loss 92.1622 182.9561 291.9509 480.0331 711.8313 1042.4141 1475.1986 2126.3833 2985.7952 4637.1025 7689.2886 13525.6699 | lr 1.1e-04 | norm 3618.7646 | dt 9.870 +type train | step 4572 | loss 95.6169 189.5226 298.9529 492.1385 727.8896 1047.1008 1466.0078 2090.3218 2929.0935 4513.6084 7426.2944 13092.7529 | lr 1.1e-04 | norm 4079.8760 | dt 9.867 +type train | step 4573 | loss 92.9560 183.7761 295.5171 489.4375 731.2470 1065.7317 1510.5474 2179.9458 3088.7288 4780.9722 7893.1187 13843.8877 | lr 1.1e-04 | norm 5316.5073 | dt 9.863 +type train | step 4574 | loss 109.1573 225.9443 344.7987 558.6912 818.7924 1188.1241 1654.2474 2358.8257 3275.0708 4993.8872 8323.2344 14814.9805 | lr 1.1e-04 | norm 11149.0732 | dt 9.851 +type train | step 4575 | loss 108.2126 222.0416 337.5373 552.9612 812.4104 1198.5190 1670.1304 2396.5330 3316.9758 5048.9062 8342.2646 14770.9121 | lr 1.1e-04 | norm 11143.1279 | dt 9.835 +type train | step 4576 | loss 108.7290 221.3215 332.7318 533.7361 781.9666 1175.4987 1609.2819 2271.5122 3082.3660 4584.7837 7373.6777 12694.2461 | lr 1.1e-04 | norm 8914.2002 | dt 9.819 +type train | step 4577 | loss 92.8516 184.6489 291.1272 479.2789 711.1274 1035.8896 1463.3605 2102.8042 2951.4951 4563.2183 7543.1523 13286.3252 | lr 1.1e-04 | norm 3843.6211 | dt 9.875 +type train | step 4578 | loss 89.0666 175.5380 276.5133 452.8707 676.6300 977.4382 1386.9030 1992.5234 2821.5654 4377.3447 7381.3530 13211.7979 | lr 1.1e-04 | norm 6687.7759 | dt 9.864 +type train | step 4579 | loss 96.1689 190.9291 301.2132 492.2026 725.6253 1051.6118 1483.1494 2122.7710 2995.9543 4662.2705 7757.6006 13824.3926 | lr 1.1e-04 | norm 4950.3188 | dt 9.876 +type train | step 4580 | loss 95.8583 191.1441 299.8382 489.0219 720.7740 1040.1122 1466.2419 2097.4175 2940.5771 4569.6562 7571.2075 13363.8672 | lr 1.1e-04 | norm 3948.9373 | dt 9.880 +type train | step 4581 | loss 109.1921 223.5925 344.0391 544.0443 786.3288 1130.4323 1564.9324 2197.4995 2992.0354 4505.7490 7329.9858 12921.6240 | lr 1.1e-04 | norm 5678.9912 | dt 9.868 +type train | step 4582 | loss 100.6047 201.3282 313.3610 505.3989 734.7032 1060.1438 1485.9135 2122.9033 2969.5317 4582.6963 7613.7402 13540.2305 | lr 1.1e-04 | norm 5321.0039 | dt 9.879 +type train | step 4583 | loss 92.0951 181.9314 287.7509 473.9676 703.9698 1026.1233 1455.5719 2097.7112 2972.1218 4623.0596 7707.3613 13687.4785 | lr 1.1e-04 | norm 4877.7876 | dt 9.864 +type train | step 4584 | loss 96.8298 192.8427 304.6381 496.9982 731.5890 1049.6320 1466.6108 2079.4604 2915.6978 4477.0605 7373.1396 13002.9287 | lr 1.1e-04 | norm 3553.8938 | dt 9.884 +type train | step 4585 | loss 108.4816 217.9585 330.5082 522.9457 759.8889 1102.5610 1544.3468 2211.4380 3033.1877 4641.2881 7572.5479 13140.7070 | lr 1.1e-04 | norm 3692.3064 | dt 9.878 +type train | step 4586 | loss 90.1559 179.1455 283.2569 466.2811 691.0230 1016.3517 1434.2354 2061.7842 2904.8867 4504.3110 7461.1797 13146.5332 | lr 1.1e-04 | norm 3999.1487 | dt 9.880 +type train | step 4587 | loss 100.3286 199.4493 309.6509 501.4710 736.8981 1067.1202 1500.0989 2133.9600 2969.8806 4550.2681 7459.0913 13090.2910 | lr 1.1e-04 | norm 4005.8794 | dt 9.876 +type train | step 4588 | loss 95.0988 189.8019 299.8474 489.3789 724.0266 1038.8384 1455.3497 2071.1980 2902.5269 4479.2490 7377.0151 12925.8994 | lr 1.1e-04 | norm 3014.8799 | dt 9.895 +type train | step 4589 | loss 91.2502 179.8528 286.5519 469.8991 698.6289 1011.4321 1426.9763 2041.8281 2852.6094 4421.4014 7272.3745 12854.7168 | lr 1.1e-04 | norm 4717.6572 | dt 9.859 +type train | step 4590 | loss 93.1918 184.2033 290.5305 475.4268 704.2264 1018.1456 1430.8518 2048.4797 2895.3589 4492.0098 7429.4878 13101.8633 | lr 1.1e-04 | norm 3585.6804 | dt 9.889 +type train | step 4591 | loss 97.3808 194.0087 302.6353 496.6552 729.1622 1056.6232 1478.3799 2110.5471 2943.0618 4527.5381 7436.7114 13078.0234 | lr 1.1e-04 | norm 3962.4932 | dt 9.878 +type train | step 4592 | loss 101.5621 205.8483 320.9416 536.2380 779.3310 1140.5507 1604.8185 2302.5552 3199.3740 4943.7642 8256.2910 14865.5879 | lr 1.1e-04 | norm 8989.4668 | dt 9.833 +type train | step 4593 | loss 94.9644 191.5450 301.9721 498.8381 737.1245 1062.2064 1495.1193 2131.3027 2981.9592 4594.2251 7569.9951 13259.7441 | lr 1.1e-04 | norm 4724.3257 | dt 9.874 +type train | step 4594 | loss 89.4018 176.5421 278.6482 460.3662 686.0399 995.4734 1409.3271 2018.5908 2852.4697 4413.4097 7317.3804 12983.2549 | lr 1.1e-04 | norm 4486.1885 | dt 9.860 +type train | step 4595 | loss 96.2484 193.4213 301.5776 493.0354 726.2394 1047.3911 1471.9941 2104.6558 2956.2222 4543.1089 7511.3672 13247.0625 | lr 1.1e-04 | norm 3882.8594 | dt 9.884 +type train | step 4596 | loss 89.8204 175.7906 279.9063 461.5663 687.3723 996.7661 1407.7739 2016.4531 2858.2546 4425.9795 7331.7554 12902.2695 | lr 1.1e-04 | norm 3460.6562 | dt 9.872 +type train | step 4597 | loss 94.6220 187.7679 300.7668 492.8944 734.4604 1064.8721 1512.0295 2165.4155 3095.4961 4783.7910 7864.4863 13839.6650 | lr 1.1e-04 | norm 3880.7661 | dt 9.867 +type train | step 4598 | loss 92.6782 185.2457 293.2155 479.5000 710.2048 1022.3193 1444.4200 2075.6196 2947.2913 4579.4541 7556.8564 13294.9961 | lr 1.1e-04 | norm 3732.2329 | dt 9.881 +type train | step 4599 | loss 88.2446 175.4059 280.2828 468.0881 701.6506 1015.8721 1442.6747 2084.5430 2956.0359 4593.2314 7552.2065 13216.5459 | lr 1.1e-04 | norm 4069.9976 | dt 9.883 +type train | step 4600 | loss 100.8723 199.6628 316.0846 514.3229 753.1345 1082.7930 1515.7710 2143.7705 3018.1736 4687.1611 7807.5620 13856.6299 | lr 1.1e-04 | norm 5356.9829 | dt 9.874 +type train | step 4601 | loss 87.9509 175.9410 283.3358 468.5507 698.7269 1015.9344 1434.7346 2065.7493 2929.0884 4548.5093 7523.6436 13229.9707 | lr 1.1e-04 | norm 3891.5830 | dt 9.871 +type train | step 4602 | loss 92.0917 182.6632 288.9841 475.5976 707.3342 1021.5046 1430.6483 2044.8931 2893.9692 4458.7812 7323.8452 12835.5977 | lr 1.1e-04 | norm 3352.7493 | dt 9.880 +type train | step 4603 | loss 93.6739 185.8093 295.6850 484.1601 717.3495 1035.6532 1463.1654 2092.4829 2953.1162 4566.5942 7530.9199 13267.1211 | lr 1.1e-04 | norm 4798.0317 | dt 9.877 +type train | step 4604 | loss 100.5492 198.8329 309.8280 499.8387 732.7977 1065.9152 1492.9020 2128.0205 2932.3237 4472.4058 7342.6416 12884.5371 | lr 1.1e-04 | norm 5013.8564 | dt 9.865 +type train | step 4605 | loss 94.3900 187.4029 291.6326 477.2214 704.9874 1021.5657 1428.7115 2045.1234 2859.3000 4405.8545 7286.2896 12783.7744 | lr 1.1e-04 | norm 3450.4399 | dt 9.885 +type train | step 4606 | loss 92.7084 183.3326 294.5750 483.8203 718.0023 1040.8822 1457.7736 2088.9783 2942.9766 4569.9692 7562.4390 13271.1299 | lr 1.1e-04 | norm 3394.8240 | dt 9.890 +type train | step 4607 | loss 97.9547 195.9190 311.0435 518.1671 759.0988 1128.5746 1609.4023 2328.5630 3232.2261 5033.5493 8414.2129 15067.6875 | lr 1.1e-04 | norm 7656.4150 | dt 9.845 +type train | step 4608 | loss 99.5060 198.9544 314.7428 513.1779 754.4562 1106.6484 1554.7582 2237.6636 3118.3501 4834.7090 7973.2383 14131.7529 | lr 1.1e-04 | norm 5148.1221 | dt 9.850 +type train | step 4609 | loss 95.2568 192.7959 307.1606 501.8676 739.8732 1064.1044 1485.9282 2121.2048 2991.4055 4619.1455 7622.3037 13336.5674 | lr 1.1e-04 | norm 3760.5618 | dt 9.881 +type train | step 4610 | loss 93.4011 183.2998 288.1546 472.3886 700.9209 1013.5743 1431.5470 2050.3250 2901.6184 4502.4136 7409.3301 13013.7471 | lr 1.1e-04 | norm 3753.5200 | dt 9.868 +type train | step 4611 | loss 97.0018 194.3868 302.9920 493.6612 726.2291 1056.1445 1484.4237 2122.4634 2956.5022 4536.7788 7488.5820 13139.2412 | lr 1.1e-04 | norm 3985.3901 | dt 9.884 +type train | step 4612 | loss 99.9337 198.3229 308.8178 508.8319 742.9716 1093.9255 1533.9603 2212.3369 3056.2605 4746.4360 7905.6929 14126.7539 | lr 1.1e-04 | norm 5985.8706 | dt 9.850 +type train | step 4613 | loss 95.0382 187.7459 293.5636 485.4908 718.9732 1055.5819 1483.6616 2139.9500 2980.8003 4546.8008 7373.3247 12815.3945 | lr 1.1e-04 | norm 4451.4126 | dt 9.870 +type train | step 4614 | loss 94.6972 187.8169 293.8574 482.6519 713.5344 1046.9391 1467.1812 2109.0342 2961.5166 4587.7466 7595.8442 13399.7803 | lr 1.1e-04 | norm 4018.4248 | dt 9.865 +type train | step 4615 | loss 97.5801 192.5448 302.1738 496.7915 732.0945 1056.3691 1492.9540 2148.6890 3042.5344 4710.3096 7780.3481 13789.5898 | lr 1.1e-04 | norm 5012.1938 | dt 9.852 +type train | step 4616 | loss 97.2014 193.1699 301.5420 491.3492 726.3288 1043.9169 1466.1174 2098.2180 2951.9075 4555.2598 7567.7363 13388.1074 | lr 1.1e-04 | norm 3254.2437 | dt 9.883 +type train | step 4617 | loss 93.1965 186.4515 295.0150 485.7010 720.9537 1031.0341 1446.8805 2066.7996 2908.7012 4503.1499 7479.7300 13243.8340 | lr 1.1e-04 | norm 5131.3335 | dt 9.879 +type train | step 4618 | loss 90.4451 177.7691 284.8074 469.5096 697.4456 1016.6538 1435.7437 2063.5400 2889.4839 4457.9795 7331.3794 12890.6133 | lr 1.1e-04 | norm 3992.1230 | dt 9.881 +type train | step 4619 | loss 89.0757 187.1969 303.3031 502.4831 750.1078 1080.1000 1536.5948 2252.9773 3123.3647 4845.1880 8170.4043 14336.7324 | lr 1.1e-04 | norm 9114.7510 | dt 9.826 +type train | step 4620 | loss 99.4803 197.2245 308.9215 500.3919 735.4948 1065.5677 1493.6624 2129.5662 2963.2180 4560.2871 7571.0894 13391.1660 | lr 1.1e-04 | norm 3915.3186 | dt 9.869 +type train | step 4621 | loss 88.7580 182.6580 299.4958 499.4883 738.0131 1048.5022 1454.8125 2087.8101 2983.8210 4632.2754 7773.2095 13727.8096 | lr 1.1e-04 | norm 8519.6914 | dt 9.870 +type train | step 4622 | loss 94.8773 189.1535 300.9962 489.3278 717.8787 1038.1315 1452.6509 2076.6509 2912.8879 4505.2505 7483.2285 13233.0342 | lr 1.1e-04 | norm 3436.2415 | dt 9.895 +type train | step 4623 | loss 86.1234 169.4906 272.1134 453.0959 673.3937 982.4261 1391.6016 1995.3419 2827.3716 4384.0918 7238.7397 12745.1396 | lr 1.1e-04 | norm 4424.9653 | dt 9.879 +type train | step 4624 | loss 91.1413 181.9084 287.7388 472.8856 703.6338 1021.2557 1439.5287 2067.2021 2917.9753 4521.8755 7485.0195 13175.0527 | lr 1.1e-04 | norm 3778.0776 | dt 9.892 +type train | step 4625 | loss 103.0006 205.2359 315.6592 509.9790 746.7360 1083.9270 1519.9285 2184.5781 3037.5759 4630.2612 7583.8906 13166.5469 | lr 1.1e-04 | norm 4028.3472 | dt 9.904 +type train | step 4626 | loss 94.2318 184.6523 293.2360 480.9650 714.4947 1042.4751 1466.2993 2103.2234 2955.5063 4554.1963 7499.6528 13172.1484 | lr 1.1e-04 | norm 3375.5032 | dt 9.912 +type train | step 4627 | loss 97.4145 194.3996 301.2131 497.6302 727.4243 1045.7719 1460.2335 2084.2388 2894.4661 4426.2905 7271.7520 12731.8174 | lr 1.1e-04 | norm 3896.9602 | dt 9.875 +type train | step 4628 | loss 93.6630 186.2561 295.3414 484.2664 718.2346 1044.4434 1468.6298 2099.2615 2941.4656 4539.5884 7462.0615 13093.2012 | lr 1.1e-04 | norm 3260.1313 | dt 9.892 +type train | step 4629 | loss 95.9378 190.7630 298.0690 488.7431 721.5467 1043.7859 1463.5002 2100.5884 2954.0933 4578.9712 7623.0410 13540.4609 | lr 1.1e-04 | norm 4982.7656 | dt 9.876 +type train | step 4630 | loss 91.6869 180.1751 287.9249 475.2413 705.6018 1024.6287 1443.0781 2069.3767 2924.1353 4527.3193 7439.9033 12951.9492 | lr 1.1e-04 | norm 3175.5784 | dt 9.873 +type train | step 4631 | loss 94.0724 185.9418 293.9185 487.8806 720.6660 1055.8445 1483.8008 2133.8977 2955.5474 4535.3223 7461.8672 13042.1406 | lr 1.1e-04 | norm 4071.9463 | dt 9.872 +type train | step 4632 | loss 90.2067 179.4718 286.9824 475.6263 707.4633 1026.3651 1450.5917 2088.4961 2932.2793 4528.6689 7474.9263 13204.0137 | lr 1.1e-04 | norm 4208.8022 | dt 9.858 +type train | step 4633 | loss 99.3829 199.2241 307.6598 495.3754 726.9133 1043.4316 1458.9579 2077.3862 2900.0498 4468.4438 7352.3774 12842.2559 | lr 1.1e-04 | norm 3398.1536 | dt 9.909 +type train | step 4634 | loss 94.8137 186.9100 294.9345 485.1952 715.3113 1039.8108 1460.6914 2095.7222 2915.7583 4507.2417 7437.1104 13151.9453 | lr 1.1e-04 | norm 4434.8418 | dt 9.893 +type train | step 4635 | loss 88.8894 176.7699 281.3094 467.0931 695.2798 1020.3611 1449.8276 2093.5703 2948.2439 4584.7231 7615.9438 13456.2627 | lr 1.1e-04 | norm 3865.8896 | dt 9.885 +type train | step 4636 | loss 93.8142 185.7921 295.3131 483.2379 715.3472 1033.4858 1458.9425 2091.4233 2955.3279 4589.0459 7557.0845 13276.4648 | lr 1.1e-04 | norm 3325.2100 | dt 9.880 +type train | step 4637 | loss 96.7817 193.3032 311.0559 511.6367 751.9570 1078.6064 1506.8163 2148.0552 3025.1655 4648.9375 7592.3452 13198.3652 | lr 1.1e-04 | norm 4880.4531 | dt 9.878 +type train | step 4638 | loss 110.7298 223.8304 345.2791 548.2682 779.1615 1088.4197 1469.8518 2015.8009 2753.3625 4133.9248 6621.4619 11784.1191 | lr 1.1e-04 | norm 5018.9365 | dt 9.843 +type train | step 4639 | loss 94.3253 189.0971 299.3227 481.8371 708.1478 1037.7981 1474.1353 2120.3140 2939.7329 4619.1191 7713.4702 13723.7451 | lr 1.1e-04 | norm 7766.3047 | dt 9.856 +type train | step 4640 | loss 95.7766 191.5554 299.8491 488.2274 718.5449 1039.0792 1463.4150 2095.8037 2951.2058 4567.2168 7562.6064 13357.1113 | lr 1.1e-04 | norm 3861.1111 | dt 9.882 +type train | step 4641 | loss 91.7985 181.3473 286.2919 465.3346 691.0961 995.6404 1403.8623 2017.5779 2862.5544 4435.5444 7342.1362 12879.1094 | lr 1.1e-04 | norm 3217.4536 | dt 9.884 +type train | step 4642 | loss 99.0315 198.2426 309.4488 495.6790 731.0651 1045.1495 1465.8982 2094.1226 2965.8625 4624.4590 7698.7822 13697.1543 | lr 1.1e-04 | norm 6296.0947 | dt 9.874 +type train | step 4643 | loss 94.3298 188.1875 297.7298 487.5167 720.4697 1056.0020 1491.2290 2147.9080 3008.5361 4650.4229 7689.0645 13570.7354 | lr 1.1e-04 | norm 3597.4133 | dt 9.868 +type train | step 4644 | loss 98.7778 197.4788 308.2355 493.9959 723.8491 1041.8242 1463.8254 2102.6621 2915.0454 4468.5146 7314.0811 12906.5225 | lr 1.1e-04 | norm 4910.4961 | dt 9.859 +type train | step 4645 | loss 92.5004 183.7560 291.2889 477.5910 705.3223 1027.3674 1448.9789 2081.3557 2919.8625 4508.1665 7449.4326 13086.3760 | lr 1.1e-04 | norm 3572.9849 | dt 9.895 +type train | step 4646 | loss 99.2207 198.5027 309.7259 502.2961 735.0710 1069.8281 1495.4102 2146.5046 2954.5330 4538.3667 7495.0693 13287.9297 | lr 1.1e-04 | norm 4801.0913 | dt 9.872 +type train | step 4647 | loss 90.0748 178.3783 283.4488 470.4678 700.5496 1019.3536 1443.0137 2079.8760 2923.6060 4538.8887 7526.8086 13219.1504 | lr 1.1e-04 | norm 6410.9663 | dt 9.873 +type train | step 4648 | loss 86.6734 173.7835 280.5147 467.0216 695.1807 1004.6624 1419.2374 2047.1078 2891.8440 4515.1782 7458.5986 13103.5107 | lr 1.1e-04 | norm 4308.5166 | dt 9.862 +type train | step 4649 | loss 89.0085 176.6031 279.9635 460.3596 686.3489 1002.2015 1419.3580 2046.4553 2907.9495 4533.6758 7484.1924 13086.7432 | lr 1.1e-04 | norm 3308.9277 | dt 9.881 +type train | step 4650 | loss 90.3906 179.6027 286.2005 469.3323 699.2209 1015.4372 1436.5161 2053.0984 2897.7339 4488.6816 7356.2437 12872.7197 | lr 1.1e-04 | norm 3688.4424 | dt 9.878 +type train | step 4651 | loss 85.7499 170.0035 271.4858 450.5716 676.6368 985.0148 1404.7261 2031.9570 2887.6211 4523.2041 7537.2642 13353.7979 | lr 1.1e-04 | norm 3761.9631 | dt 9.875 +type train | step 4652 | loss 93.1489 184.9633 291.3388 479.6131 706.0782 1024.4962 1444.2621 2062.6418 2899.8101 4511.1274 7493.3740 13278.0078 | lr 1.1e-04 | norm 3803.5789 | dt 9.873 +type train | step 4653 | loss 97.3226 192.4508 303.3723 501.1721 736.8837 1063.5707 1483.5477 2122.5586 2954.5876 4540.9678 7472.2178 13097.6348 | lr 1.1e-04 | norm 4335.3647 | dt 9.858 +type train | step 4654 | loss 97.1185 191.4338 303.5672 496.7650 734.7864 1062.6740 1500.1494 2141.8801 3021.5825 4658.8174 7691.9995 13566.9248 | lr 1.1e-04 | norm 4443.7578 | dt 9.877 +type train | step 4655 | loss 91.9314 182.5619 288.2603 473.6492 705.2771 1015.1570 1430.0491 2051.1123 2904.4690 4515.7100 7469.4688 13117.5898 | lr 1.1e-04 | norm 3539.6299 | dt 9.868 +type train | step 4656 | loss 96.6170 190.6138 296.9050 486.4258 722.5040 1047.1782 1475.7708 2116.3618 2984.7869 4620.3691 7603.3862 13241.3740 | lr 1.1e-04 | norm 3690.0037 | dt 9.880 +type train | step 4657 | loss 86.1748 179.4997 295.5779 503.4619 750.3987 1092.7993 1568.0730 2280.7520 3234.1255 5110.5312 8714.5137 15839.1494 | lr 1.1e-04 | norm 9626.5059 | dt 9.838 +type train | step 4658 | loss 94.0276 187.6826 292.1564 485.0550 715.7201 1049.8434 1482.2648 2140.9978 2994.3069 4632.1797 7645.2183 13482.0703 | lr 1.1e-04 | norm 4080.3984 | dt 9.874 +type train | step 4659 | loss 92.6873 180.8574 288.4720 475.0844 702.0566 1019.9470 1434.6652 2062.0312 2886.6965 4493.3477 7489.0605 13346.8281 | lr 1.1e-04 | norm 4409.1577 | dt 9.873 +type train | step 4660 | loss 93.7222 185.5098 292.8524 475.2424 700.3793 1025.5453 1448.5441 2088.1294 2903.9917 4478.7095 7401.6987 12976.6641 | lr 1.1e-04 | norm 3717.4585 | dt 9.886 +type train | step 4661 | loss 105.5753 213.9999 331.3170 536.7502 778.2923 1131.4611 1585.6471 2286.0798 3144.4360 4787.9355 7848.2817 13731.5322 | lr 1.1e-04 | norm 4972.6523 | dt 9.850 +type train | step 4662 | loss 92.4793 185.3463 295.4240 486.2557 718.9736 1042.2598 1468.2671 2099.1450 2965.2544 4568.3794 7515.0493 13214.4785 | lr 1.1e-04 | norm 3605.1746 | dt 9.885 +type train | step 4663 | loss 101.0252 200.5929 311.5248 508.3279 741.7630 1065.4741 1492.1407 2113.7927 2930.2834 4464.4214 7304.9233 12717.2744 | lr 1.1e-04 | norm 3509.2842 | dt 9.892 +type train | step 4664 | loss 93.3617 184.1374 293.3596 482.7083 711.6561 1033.2992 1457.2395 2091.3562 2920.4392 4542.7808 7548.0376 13370.7500 | lr 1.1e-04 | norm 4267.9707 | dt 9.858 +type train | step 4665 | loss 96.0951 190.0877 295.8326 486.9412 714.8354 1031.6899 1445.0629 2059.2190 2872.8086 4426.3721 7322.5034 12934.2002 | lr 1.1e-04 | norm 3383.8801 | dt 9.870 +type train | step 4666 | loss 90.6373 179.4578 286.6842 472.4529 699.5453 1013.9774 1436.9907 2063.3601 2919.9495 4537.9932 7506.2388 13216.6182 | lr 1.1e-04 | norm 3689.1990 | dt 9.865 +type train | step 4667 | loss 91.6709 184.8510 290.7702 476.8222 708.8967 1031.1781 1457.4133 2089.4341 2946.6555 4553.4619 7525.4951 13237.2061 | lr 1.1e-04 | norm 3555.3137 | dt 9.885 +type train | step 4668 | loss 101.4111 201.6263 312.3160 498.6595 731.5220 1054.5536 1477.4873 2111.1936 2943.6379 4544.4121 7465.2744 13177.5449 | lr 1.1e-04 | norm 6591.0645 | dt 9.857 +type train | step 4669 | loss 97.6530 194.9143 305.6349 498.2853 733.1788 1058.8052 1489.6681 2146.0972 3014.1353 4674.1470 7687.7114 13509.3770 | lr 1.1e-04 | norm 4592.0635 | dt 9.863 +type train | step 4670 | loss 96.4826 190.8274 301.9152 493.9867 727.5997 1054.3635 1478.4716 2113.2656 2947.7542 4551.6855 7511.3833 13227.3438 | lr 1.1e-04 | norm 3860.1455 | dt 9.872 +type train | step 4671 | loss 86.6954 171.2374 274.4939 454.4644 677.8819 985.7905 1398.8708 2023.9803 2894.1743 4512.5518 7491.2749 13240.1572 | lr 1.1e-04 | norm 3464.7407 | dt 9.886 +type train | step 4672 | loss 88.8137 176.2471 281.9146 469.1260 699.9417 1018.7878 1439.4556 2071.2471 2911.5356 4507.6382 7473.3926 13240.2021 | lr 1.1e-04 | norm 3549.7214 | dt 9.885 +type train | step 4673 | loss 94.3121 187.1723 294.2880 481.4695 712.5005 1032.6051 1450.5537 2077.8938 2933.8528 4518.4204 7424.3774 12968.7510 | lr 1.1e-04 | norm 3674.3264 | dt 9.883 +type train | step 4674 | loss 86.6644 175.1752 284.4186 475.6921 716.0726 1044.9883 1488.5680 2156.7947 3074.7136 4797.5454 7927.7114 13828.0557 | lr 1.1e-04 | norm 4000.6584 | dt 9.872 +type train | step 4675 | loss 87.0711 171.5636 272.7218 452.9111 679.5698 1009.1450 1446.8893 2117.7842 3004.6921 4680.1045 7776.8677 13720.9443 | lr 1.1e-04 | norm 4020.8855 | dt 9.878 +type train | step 4676 | loss 95.4991 189.9221 296.5270 482.2361 710.7664 1024.9288 1449.4755 2074.4475 2912.8540 4481.1621 7390.0674 12893.9395 | lr 1.1e-04 | norm 3901.2896 | dt 9.863 +type train | step 4677 | loss 91.3666 179.4370 283.7498 471.4721 697.5979 1012.7322 1433.1450 2055.8171 2917.0527 4548.0029 7531.5503 13270.4561 | lr 1.1e-04 | norm 3421.3906 | dt 9.868 +type train | step 4678 | loss 94.9052 186.3293 294.9333 486.4688 717.1182 1039.9092 1460.3848 2085.7607 2909.8149 4490.7554 7413.4575 13002.5098 | lr 1.1e-04 | norm 3837.2979 | dt 9.877 +type train | step 4679 | loss 91.0691 182.0045 287.5465 471.0989 700.2556 1020.4630 1436.5300 2060.5540 2878.1233 4470.8550 7385.2495 13088.4102 | lr 1.1e-04 | norm 3812.4316 | dt 9.884 +type train | step 4680 | loss 107.6609 213.5726 321.4439 516.0168 749.0536 1079.7850 1508.8954 2136.0405 2950.8303 4537.1821 7476.3828 13160.0205 | lr 1.1e-04 | norm 5643.4360 | dt 9.860 +type train | step 4681 | loss 83.6195 165.8603 272.0604 457.7308 692.4723 1019.5555 1451.2466 2115.5022 3008.6746 4684.5049 7729.3604 13494.5283 | lr 1.1e-04 | norm 3417.4790 | dt 9.873 +type train | step 4682 | loss 88.5648 176.0408 281.2150 465.1152 696.6259 1014.0467 1431.5701 2049.3474 2906.8020 4490.3833 7400.1406 12933.7939 | lr 1.1e-04 | norm 3009.0854 | dt 9.881 +type train | step 4683 | loss 93.9183 186.6579 294.4550 483.2461 716.6061 1033.5988 1457.0389 2096.0066 2950.8152 4560.5786 7564.0234 13286.8770 | lr 1.1e-04 | norm 3431.3992 | dt 9.891 +type train | step 4684 | loss 85.3924 168.1427 266.4616 445.0929 673.2377 999.1492 1420.5693 2072.9141 2919.2976 4567.6455 7593.9907 13395.0898 | lr 1.1e-04 | norm 5490.1963 | dt 9.861 +type train | step 4685 | loss 87.0510 180.3838 302.2834 516.3326 763.9925 1101.4530 1551.3599 2226.4487 3156.5098 4980.1895 8362.9775 14887.5430 | lr 1.1e-04 | norm 8110.3125 | dt 9.852 +type train | step 4686 | loss 90.4307 186.8270 307.4599 516.2576 761.2079 1089.8909 1534.4561 2192.6323 3122.8052 4899.0845 8164.7671 14398.6211 | lr 1.1e-04 | norm 6403.1685 | dt 9.871 +type train | step 4687 | loss 86.2451 170.3703 273.6435 455.8458 682.9467 995.4863 1414.5400 2042.3625 2900.4546 4506.2178 7450.0000 13029.5967 | lr 1.1e-04 | norm 3376.0776 | dt 9.873 +type train | step 4688 | loss 85.8247 171.2349 274.5758 456.3011 683.6618 995.2742 1411.8514 2039.7742 2912.9280 4539.5771 7549.1138 13278.9570 | lr 1.1e-04 | norm 4320.2461 | dt 9.883 +type train | step 4689 | loss 99.3929 194.9445 303.4449 494.5539 723.1827 1045.3142 1470.2623 2091.2114 2903.8569 4460.9136 7332.6665 12861.3652 | lr 1.1e-04 | norm 3529.7927 | dt 9.874 +type train | step 4690 | loss 90.3430 178.4321 283.2549 469.6382 696.4059 1008.8248 1423.4905 2040.3362 2869.6240 4426.4897 7333.6343 12866.4824 | lr 1.1e-04 | norm 4158.4673 | dt 9.867 +type train | step 4691 | loss 90.0558 179.3933 285.2286 471.2263 701.3365 1017.2618 1442.0771 2068.2820 2926.9673 4536.1851 7506.8799 13245.4082 | lr 1.1e-04 | norm 4155.2856 | dt 9.869 +type train | step 4692 | loss 102.2496 201.8875 312.1880 504.4794 740.9783 1066.2642 1495.3594 2118.4634 2961.9646 4568.8916 7488.3457 13161.2217 | lr 1.1e-04 | norm 3979.2820 | dt 9.873 +type train | step 4693 | loss 91.2295 182.7361 288.7961 478.3860 710.8629 1045.1716 1481.4711 2132.3506 3015.9736 4700.8184 7783.0884 13672.4971 | lr 1.1e-04 | norm 4093.1372 | dt 9.862 +type train | step 4694 | loss 92.1043 184.1049 290.4460 477.7439 708.0403 1029.0557 1454.7244 2084.4170 2944.1868 4560.5713 7485.4995 13099.5127 | lr 1.1e-04 | norm 3653.5496 | dt 9.872 +type train | step 4695 | loss 89.6057 177.2195 280.4491 457.6911 681.3837 991.0890 1406.2222 2030.0671 2882.4653 4464.0103 7353.3647 12835.0566 | lr 1.1e-04 | norm 3264.5098 | dt 9.875 +type train | step 4696 | loss 92.7444 183.7324 289.5212 484.0208 718.4537 1064.3223 1501.3123 2183.6074 3061.8706 4720.4707 7789.0171 13844.9248 | lr 1.1e-04 | norm 5247.3130 | dt 9.849 +type train | step 4697 | loss 84.5633 167.8408 269.3757 452.8064 679.6873 1002.8958 1435.0432 2088.7852 2969.2676 4650.0806 7692.0137 13515.9639 | lr 1.0e-04 | norm 4432.4570 | dt 9.865 +type train | step 4698 | loss 94.0343 189.9620 303.2064 493.0535 732.8986 1059.8027 1498.6899 2151.0090 3062.5991 4767.7783 7871.2480 13968.0879 | lr 1.0e-04 | norm 4460.6289 | dt 9.885 +type train | step 4699 | loss 90.0325 178.2142 282.0622 470.3362 700.5292 1022.3025 1450.2783 2083.2170 2936.1819 4550.7104 7532.3315 13206.5312 | lr 1.0e-04 | norm 3337.2139 | dt 9.873 +type train | step 4700 | loss 86.2492 169.6107 274.2233 456.1679 684.1034 990.8232 1396.9471 2006.0144 2859.5410 4423.4673 7314.7422 12812.5469 | lr 1.0e-04 | norm 3606.6650 | dt 9.866 +type train | step 4701 | loss 96.7458 191.5568 299.3729 490.5106 720.0429 1031.5405 1436.0919 2035.0667 2834.9875 4374.4697 7184.1387 12736.3418 | lr 1.0e-04 | norm 4627.5820 | dt 9.859 +type train | step 4702 | loss 97.2456 195.4190 306.9581 503.2504 747.9973 1082.6348 1519.8762 2176.6802 3027.5464 4616.4663 7556.6948 13165.7773 | lr 1.0e-04 | norm 3549.5906 | dt 9.900 +type train | step 4703 | loss 92.0863 183.1895 287.5531 469.3072 693.4215 993.9250 1392.7258 1979.8965 2801.5920 4316.3325 7073.3584 12374.7529 | lr 1.0e-04 | norm 3280.4478 | dt 9.880 +type train | step 4704 | loss 85.6560 169.9241 271.0719 455.3977 680.1041 995.8608 1415.0347 2044.8854 2897.3481 4494.9458 7451.8750 13042.1748 | lr 1.0e-04 | norm 4952.2085 | dt 9.861 +type train | step 4705 | loss 95.5453 188.6002 295.5959 481.7853 713.6658 1044.1326 1477.7803 2127.5400 2979.5039 4620.1279 7640.2524 13448.4580 | lr 1.0e-04 | norm 3946.1382 | dt 9.870 +type train | step 4706 | loss 89.2000 176.5494 281.2667 464.6025 687.7622 997.8383 1406.5680 2022.5361 2851.5525 4403.7822 7278.1152 12771.2637 | lr 1.0e-04 | norm 3107.2878 | dt 9.875 +type train | step 4707 | loss 91.2660 180.7744 283.5967 464.3163 691.6468 1015.1089 1440.7531 2076.0945 2936.8823 4530.2852 7494.1772 13141.7930 | lr 1.0e-04 | norm 3329.5007 | dt 9.869 +type train | step 4708 | loss 112.0819 231.9389 361.4459 588.0750 844.5383 1209.0630 1662.7201 2309.5569 3123.1653 4630.5303 7402.7710 13163.5498 | lr 1.0e-04 | norm 6488.1504 | dt 9.831 +type train | step 4709 | loss 89.0072 176.4255 279.8539 466.4297 695.8818 1029.2892 1460.5422 2125.9785 2978.0801 4583.5312 7577.4092 13446.2676 | lr 1.0e-04 | norm 4237.9619 | dt 9.874 +type train | step 4710 | loss 104.0845 205.0976 328.3396 541.0036 785.7856 1132.6869 1574.6880 2238.9216 3120.5767 4834.1348 7956.3794 14059.8750 | lr 1.0e-04 | norm 4690.5420 | dt 9.875 +type train | step 4711 | loss 93.8997 187.7943 294.4386 480.6459 707.9890 1031.2740 1453.6702 2098.5796 2942.0183 4548.7617 7522.5693 13213.5361 | lr 1.0e-04 | norm 3941.5906 | dt 9.867 +type train | step 4712 | loss 98.6457 196.3589 309.4870 499.8067 731.9806 1054.3174 1476.5504 2101.2900 2913.0132 4480.9717 7387.7817 12997.2949 | lr 1.0e-04 | norm 4097.7847 | dt 9.866 +type train | step 4713 | loss 100.9763 200.7573 310.6434 501.4423 732.0532 1060.1305 1482.3956 2106.7197 2911.9692 4479.5815 7451.0771 13290.0352 | lr 1.0e-04 | norm 5597.9453 | dt 9.852 +type train | step 4714 | loss 92.2834 181.7001 288.9873 476.7766 710.3188 1044.2340 1478.0511 2130.5039 2984.6946 4617.2632 7655.0713 13561.3340 | lr 1.0e-04 | norm 4439.1416 | dt 9.867 +type train | step 4715 | loss 100.5678 200.2188 311.5408 504.0220 744.0243 1069.7323 1509.8926 2180.7393 3065.5146 4728.3584 7733.1167 13554.8281 | lr 1.0e-04 | norm 6951.1880 | dt 9.887 +type train | step 4716 | loss 94.7925 186.3763 295.7075 481.1932 710.8733 1030.1910 1451.2002 2085.0398 2928.0134 4532.9434 7476.5723 13059.8223 | lr 1.0e-04 | norm 4000.0898 | dt 9.864 +type train | step 4717 | loss 103.5780 205.9153 325.2555 528.5996 778.3871 1146.2125 1606.2866 2311.4275 3198.1147 4950.4922 8181.2466 14387.7354 | lr 1.0e-04 | norm 7448.3838 | dt 9.851 +type train | step 4718 | loss 91.9318 184.0069 292.3838 482.4091 713.0179 1033.6324 1458.3171 2089.1479 2957.0918 4539.0796 7480.8921 13121.3096 | lr 1.0e-04 | norm 3407.8235 | dt 9.877 +type train | step 4719 | loss 90.7364 185.1414 293.6344 483.6803 719.9146 1042.5334 1469.4043 2111.7305 2989.5525 4625.9194 7632.5508 13401.5762 | lr 1.0e-04 | norm 4209.6768 | dt 9.880 +type train | step 4720 | loss 101.2137 200.1065 312.8465 510.3389 744.2683 1071.6855 1494.1259 2114.7744 2908.6067 4448.9395 7313.4463 12886.4756 | lr 1.0e-04 | norm 3680.8420 | dt 9.867 +type train | step 4721 | loss 92.1866 180.8088 286.3231 471.4626 697.7388 1018.4153 1439.8086 2062.7661 2904.3101 4500.1562 7446.6650 13048.8438 | lr 1.0e-04 | norm 3566.6328 | dt 9.883 +type train | step 4722 | loss 97.8542 196.1329 303.8689 491.9240 724.1030 1033.0906 1446.1036 2068.0212 2924.1367 4525.1094 7450.5581 13067.6758 | lr 1.0e-04 | norm 4111.3154 | dt 9.882 +type train | step 4723 | loss 91.1463 180.3716 286.2057 479.8154 716.4370 1068.3110 1519.6578 2226.1584 3124.4692 4825.6670 7956.2939 13921.3379 | lr 1.0e-04 | norm 5154.3062 | dt 9.852 +type train | step 4724 | loss 97.6506 196.5357 307.3991 499.4029 733.2872 1064.1337 1488.1439 2137.3186 2979.7842 4606.8569 7611.2656 13306.9980 | lr 1.0e-04 | norm 3903.0732 | dt 9.874 +type train | step 4725 | loss 85.5930 169.5237 273.9654 459.4248 686.5188 1008.9403 1438.0120 2084.1782 2946.3450 4581.5303 7553.3794 13248.2188 | lr 1.0e-04 | norm 3814.0334 | dt 9.880 +type train | step 4726 | loss 94.8385 187.9164 293.2877 481.4497 712.6413 1034.5920 1457.1295 2092.5078 2942.2905 4526.5293 7436.1299 13004.6504 | lr 1.0e-04 | norm 3309.4846 | dt 9.886 +type train | step 4727 | loss 95.6548 190.4161 298.9046 487.5692 719.1718 1042.6750 1471.8727 2110.4153 2980.1362 4626.6953 7655.1870 13495.8145 | lr 1.0e-04 | norm 3322.6372 | dt 9.880 +type train | step 4728 | loss 94.7077 188.8691 297.4464 490.4113 727.9245 1070.9072 1516.3914 2197.3667 3079.2520 4771.5156 7841.6318 13861.8770 | lr 1.0e-04 | norm 5407.7490 | dt 9.872 +type train | step 4729 | loss 111.0728 223.1617 342.7651 550.6955 780.5586 1122.9749 1528.0209 2161.5273 2841.9517 4294.4199 7027.0337 12750.7637 | lr 1.0e-04 | norm 9566.0098 | dt 9.830 +type train | step 4730 | loss 97.0025 190.8911 298.2374 486.2415 719.4973 1046.6655 1474.4341 2120.3591 2972.8508 4568.3418 7557.7046 13337.6621 | lr 1.0e-04 | norm 3685.5928 | dt 9.870 +type train | step 4731 | loss 95.1940 188.8381 297.0002 484.9519 714.3140 1028.0984 1437.6232 2052.3411 2883.4666 4448.9297 7385.1616 13099.8945 | lr 1.0e-04 | norm 3954.5408 | dt 9.895 +type train | step 4732 | loss 92.1104 182.8088 289.4973 475.4295 705.2493 1025.6084 1446.0190 2080.0361 2931.6567 4537.2676 7482.4683 13165.8223 | lr 1.0e-04 | norm 3529.1240 | dt 9.876 +type train | step 4733 | loss 90.6747 179.5273 282.8424 464.2525 689.4349 998.7467 1407.1569 2024.2250 2851.7131 4407.2866 7250.4141 12572.7051 | lr 1.0e-04 | norm 3124.0537 | dt 9.888 +type train | step 4734 | loss 87.3610 170.2168 272.0601 454.1552 682.8401 1001.7762 1428.6508 2075.3904 2940.2134 4586.8174 7582.9834 13302.1543 | lr 1.0e-04 | norm 5782.1025 | dt 9.842 +type train | step 4735 | loss 95.6302 189.5550 303.8904 497.6879 737.0016 1065.2438 1499.1675 2148.9290 3025.4031 4675.4717 7724.7656 13534.0361 | lr 1.0e-04 | norm 3820.6252 | dt 9.893 +type train | step 4736 | loss 96.9994 190.8103 302.5484 497.3911 730.3729 1060.1169 1484.2543 2120.0940 2949.3030 4551.9961 7532.8936 13333.0430 | lr 1.0e-04 | norm 3840.7803 | dt 9.873 +type train | step 4737 | loss 88.9776 177.8999 284.4268 469.9836 700.6307 1016.2776 1447.4720 2086.5415 2968.1172 4625.9058 7688.8218 13640.4131 | lr 1.0e-04 | norm 4489.7891 | dt 9.868 +type train | step 4738 | loss 95.2865 192.1030 299.4760 485.7190 715.7260 1032.5566 1449.2819 2067.0964 2914.9734 4497.9272 7393.1387 12932.7051 | lr 1.0e-04 | norm 3256.8787 | dt 9.870 +type train | step 4739 | loss 98.3391 197.4575 309.6017 503.6989 736.8313 1054.7363 1478.6055 2102.8367 2939.4075 4539.2871 7561.6309 13398.4971 | lr 1.0e-04 | norm 4438.7637 | dt 9.872 +type train | step 4740 | loss 87.7631 173.1775 276.2533 457.4157 682.8045 995.1682 1412.4304 2037.5345 2891.3669 4490.1621 7462.2949 13089.2500 | lr 1.0e-04 | norm 3412.4751 | dt 9.877 +type train | step 4741 | loss 97.4081 191.6558 303.7798 493.4089 720.5326 1036.9525 1459.0145 2091.2390 2904.8157 4452.6416 7343.9546 13007.2451 | lr 1.0e-04 | norm 3851.5503 | dt 9.866 +type train | step 4742 | loss 96.6320 191.2042 300.2215 487.0448 713.7047 1033.8750 1454.8314 2089.0601 2918.4944 4503.2334 7408.8735 13088.8105 | lr 1.0e-04 | norm 3970.1172 | dt 9.878 +type train | step 4743 | loss 99.4556 205.2583 321.5045 523.3094 773.2518 1113.5923 1562.0533 2237.0608 3138.3318 4824.9663 7945.2104 13953.3145 | lr 1.0e-04 | norm 4703.0957 | dt 9.866 +type train | step 4744 | loss 92.8734 186.0670 290.0045 474.1004 701.5347 1012.7982 1422.3602 2024.4180 2857.7883 4402.5127 7251.4150 12740.9814 | lr 1.0e-04 | norm 3740.1118 | dt 9.877 +type train | step 4745 | loss 98.5046 196.6346 307.6369 498.1647 730.7040 1049.2196 1472.4824 2098.1440 2948.9836 4532.0112 7396.2344 12884.9609 | lr 1.0e-04 | norm 4711.2339 | dt 9.879 +type train | step 4746 | loss 85.9517 170.4190 269.9021 448.8593 672.6072 980.0208 1393.4542 2016.5100 2853.0452 4437.3594 7337.0737 12962.4688 | lr 1.0e-04 | norm 4674.5908 | dt 9.873 +type train | step 4747 | loss 98.5999 195.4014 307.3675 498.9285 731.5941 1062.1237 1491.0682 2124.0154 2943.8696 4521.3794 7440.4824 13107.4736 | lr 1.0e-04 | norm 3739.1150 | dt 9.895 +type train | step 4748 | loss 92.6360 182.8728 291.1181 478.1119 708.0529 1024.4746 1440.2633 2056.6562 2902.0193 4516.8325 7461.8960 13106.9453 | lr 1.0e-04 | norm 3211.9080 | dt 9.885 +type train | step 4749 | loss 90.4245 179.5380 285.8179 471.7493 701.2774 1017.7573 1437.0814 2058.7666 2925.7456 4527.1499 7495.8740 13117.0840 | lr 1.0e-04 | norm 3306.6545 | dt 9.880 +type train | step 4750 | loss 98.7580 196.3730 305.3771 495.7102 729.9911 1059.9916 1493.5140 2120.0730 2950.8040 4531.9717 7428.5625 13010.1670 | lr 1.0e-04 | norm 3893.9260 | dt 9.875 +type train | step 4751 | loss 95.2536 189.5924 300.2083 490.4814 723.0487 1042.4795 1462.0082 2073.1470 2921.2939 4534.8828 7501.6260 13201.6230 | lr 1.0e-04 | norm 3423.2878 | dt 9.880 +type train | step 4752 | loss 94.6567 188.3265 295.4973 484.5389 720.0906 1049.8845 1482.9094 2134.5315 2989.0225 4592.7266 7567.7109 13279.6270 | lr 1.0e-04 | norm 3370.9258 | dt 9.871 +type train | step 4753 | loss 87.2597 171.5830 274.4474 454.9741 681.8643 996.8661 1420.3777 2053.1284 2913.3589 4505.7432 7369.6680 12888.3203 | lr 1.0e-04 | norm 3400.6531 | dt 9.882 +type train | step 4754 | loss 90.1416 179.4623 287.3089 473.0484 702.2719 1018.0054 1426.1115 2046.8448 2892.9810 4486.5659 7431.2217 12996.7627 | lr 1.0e-04 | norm 3074.7505 | dt 9.876 +type train | step 4755 | loss 88.9454 177.0035 280.9839 460.3401 681.9032 989.7347 1394.9596 1996.6782 2831.2729 4388.9331 7285.6812 12758.5908 | lr 1.0e-04 | norm 3080.7854 | dt 9.872 +type train | step 4756 | loss 88.8751 176.4364 280.8264 464.8211 692.7169 1005.2857 1420.2605 2037.1921 2884.6965 4449.5234 7359.2202 12895.4844 | lr 1.0e-04 | norm 3134.7800 | dt 9.873 +type train | step 4757 | loss 95.7167 189.5096 299.0863 498.1494 736.4767 1076.2042 1516.0442 2184.3015 3061.5610 4700.2095 7724.4863 13462.1143 | lr 1.0e-04 | norm 4152.7246 | dt 9.858 +type train | step 4758 | loss 95.1345 190.9102 299.9486 490.6127 721.4088 1038.5499 1448.6663 2072.8069 2900.7439 4466.9321 7358.7598 12913.9805 | lr 1.0e-04 | norm 3359.7593 | dt 9.881 +type train | step 4759 | loss 95.3778 189.2345 294.4675 480.0953 701.8768 1030.8879 1444.0371 2079.4666 2867.2078 4441.5474 7364.9429 13059.8721 | lr 1.0e-04 | norm 6078.0845 | dt 9.843 +type train | step 4760 | loss 88.5906 175.1238 281.3920 465.1896 692.4541 1018.9597 1454.4929 2109.6836 2980.6628 4650.4531 7688.0088 13485.0713 | lr 1.0e-04 | norm 5470.6572 | dt 9.852 +type train | step 4761 | loss 92.3377 180.0443 284.2429 468.9175 695.0644 1011.5698 1427.3845 2042.4845 2880.9795 4465.1016 7361.5840 12897.3584 | lr 1.0e-04 | norm 3558.9558 | dt 9.869 +type train | step 4762 | loss 101.8251 204.2771 316.8804 509.7888 742.3330 1067.9929 1482.3151 2103.3862 2911.6990 4459.4565 7300.6758 12794.4727 | lr 1.0e-04 | norm 3198.7983 | dt 9.867 +type train | step 4763 | loss 106.6557 215.3583 342.5098 536.5128 767.0744 1086.8779 1489.5620 2083.9375 2758.0894 4144.3672 6701.4111 11907.1934 | lr 1.0e-04 | norm 8491.4258 | dt 9.820 +type train | step 4764 | loss 97.2881 192.7091 305.4980 496.0924 727.9652 1055.2158 1485.1720 2118.8401 2972.4609 4591.7744 7595.4395 13367.3750 | lr 1.0e-04 | norm 3906.1580 | dt 9.872 +type train | step 4765 | loss 95.8331 187.8325 298.8566 487.9372 716.8931 1047.0620 1478.3663 2125.4207 2999.3599 4652.2153 7763.5405 13968.2041 | lr 1.0e-04 | norm 5328.9868 | dt 9.855 +type train | step 4766 | loss 94.0591 189.8806 297.5995 484.4423 716.2438 1043.1270 1476.2532 2122.2012 2999.3293 4639.7104 7697.2529 13724.2314 | lr 1.0e-04 | norm 3867.4146 | dt 9.885 +type train | step 4767 | loss 109.5347 218.1312 335.6072 531.7275 778.2877 1110.2892 1542.8190 2170.3088 3016.6069 4631.6670 7613.2222 13327.8740 | lr 1.0e-04 | norm 4354.4233 | dt 9.870 +type train | step 4768 | loss 101.1300 201.1892 312.4081 505.8780 739.9460 1075.4250 1514.7477 2176.7129 3064.2520 4762.8799 7827.9160 13823.5908 | lr 1.0e-04 | norm 5521.5288 | dt 9.872 +type train | step 4769 | loss 91.2030 183.9217 289.5557 473.1138 701.1573 1011.8766 1428.2286 2045.6263 2894.3271 4495.4023 7416.0010 12980.3496 | lr 1.0e-04 | norm 3149.0620 | dt 9.880 +type train | step 4770 | loss 93.1553 187.0714 295.8169 482.1975 715.2690 1035.4501 1456.6196 2088.5862 2950.7412 4582.4722 7584.9551 13314.1748 | lr 1.0e-04 | norm 3882.3806 | dt 9.881 +type train | step 4771 | loss 91.0179 180.0741 284.9897 467.5899 693.9478 1001.2883 1405.6909 2013.7822 2852.2280 4413.2773 7284.2441 12767.6797 | lr 1.0e-04 | norm 2989.7427 | dt 9.878 +type train | step 4772 | loss 92.3003 187.4999 299.9849 490.7935 726.7454 1041.0918 1463.6136 2088.6978 2950.0728 4534.3223 7471.1270 12995.8828 | lr 1.0e-04 | norm 3578.8811 | dt 9.876 +type train | step 4773 | loss 91.3975 181.6863 287.9608 476.9891 707.4567 1039.4988 1474.0114 2126.7112 2989.1082 4632.8252 7668.1772 13519.9678 | lr 1.0e-04 | norm 3690.4614 | dt 9.875 +type train | step 4774 | loss 95.5500 191.3504 300.6187 488.0961 719.6100 1040.2491 1460.1936 2093.8350 2952.7651 4552.1548 7548.5996 13286.1895 | lr 1.0e-04 | norm 3754.7854 | dt 9.886 +type train | step 4775 | loss 92.8666 184.7141 291.7229 477.7102 711.8864 1032.6938 1457.1941 2100.5964 2976.6919 4578.1436 7523.5991 13201.4873 | lr 1.0e-04 | norm 3688.9700 | dt 9.877 +type train | step 4776 | loss 90.9884 181.8845 290.2915 478.8758 708.5768 1044.2395 1471.0297 2120.5742 2977.7375 4606.1729 7622.2729 13458.4902 | lr 1.0e-04 | norm 3793.0530 | dt 9.864 +type train | step 4777 | loss 91.6568 183.8613 290.6606 473.2025 702.3331 1015.1252 1433.6528 2065.5203 2909.1885 4514.2646 7432.6211 13034.2178 | lr 1.0e-04 | norm 3534.3948 | dt 9.867 +type train | step 4778 | loss 100.3602 199.8697 312.8235 504.9266 735.0696 1062.2468 1478.2050 2103.3970 2926.8247 4486.8291 7381.1958 12863.8984 | lr 1.0e-04 | norm 4182.9390 | dt 9.878 +type train | step 4779 | loss 102.5843 203.3105 319.8378 527.2016 765.5852 1136.2660 1584.0074 2289.8625 3121.2588 4794.5400 7924.0527 14209.3965 | lr 1.0e-04 | norm 7845.8667 | dt 9.871 +type train | step 4780 | loss 90.0820 176.3170 283.4564 471.2352 702.2794 1037.9670 1472.2843 2132.2446 2976.7346 4605.9019 7614.6089 13303.8760 | lr 1.0e-04 | norm 4369.4463 | dt 9.851 +type train | step 4781 | loss 86.4901 174.3178 277.6805 461.8661 691.4746 1012.7581 1439.2024 2093.9509 2962.7617 4598.6641 7661.6333 13526.9512 | lr 1.0e-04 | norm 4746.4102 | dt 9.859 +type train | step 4782 | loss 87.3097 172.3994 273.3128 451.7488 676.0601 984.8567 1399.1573 2024.8340 2876.6680 4501.2524 7463.4731 13061.3379 | lr 1.0e-04 | norm 4208.7383 | dt 9.872 +type train | step 4783 | loss 107.2190 208.2059 317.3362 505.3745 743.6981 1114.2812 1596.1915 2316.5000 3173.4375 4916.5820 8118.7559 14110.9824 | lr 1.0e-04 | norm 6621.6245 | dt 9.865 +type train | step 4784 | loss 83.9340 166.3848 268.4913 446.9553 676.4679 990.9749 1415.9921 2054.5251 2925.0920 4579.0991 7543.6055 13190.3408 | lr 1.0e-04 | norm 4258.1133 | dt 9.866 +type train | step 4785 | loss 92.8121 182.9656 287.7279 470.1097 697.8730 1010.2902 1427.0510 2039.3096 2872.4902 4455.0522 7393.6367 13032.2471 | lr 1.0e-04 | norm 3932.2119 | dt 9.888 +type train | step 4786 | loss 96.4652 192.2336 302.0812 490.7791 723.0114 1046.2886 1464.2034 2094.0007 2938.5066 4515.2207 7434.6543 13084.8535 | lr 1.0e-04 | norm 3811.8706 | dt 9.865 +type train | step 4787 | loss 88.4239 177.5363 282.5131 466.7403 693.9477 1005.4220 1413.7988 2017.1323 2851.6321 4413.2354 7285.5820 12756.6572 | lr 1.0e-04 | norm 3396.1714 | dt 9.875 +type train | step 4788 | loss 103.1569 203.8568 316.0444 521.2921 752.5963 1089.4441 1517.2351 2150.0374 2927.2471 4460.0825 7342.9746 12879.0439 | lr 1.0e-04 | norm 4539.5269 | dt 9.869 +type train | step 4789 | loss 97.1287 194.2042 303.3520 497.3058 730.2827 1069.8690 1504.3834 2149.0728 2984.2407 4572.2979 7545.4243 13255.7793 | lr 1.0e-04 | norm 5566.9663 | dt 9.879 +type train | step 4790 | loss 88.8265 175.5610 280.4417 464.2861 691.5912 1009.4889 1425.1942 2051.5288 2899.3376 4490.7710 7444.3140 13082.0137 | lr 1.0e-04 | norm 3252.0234 | dt 9.884 +type train | step 4791 | loss 97.1995 192.5499 299.5113 488.1380 714.2830 1038.9741 1454.1665 2078.8137 2872.4797 4431.4702 7314.6191 13015.2607 | lr 1.0e-04 | norm 4780.6665 | dt 9.864 +type train | step 4792 | loss 98.1343 197.2126 308.5672 504.4130 738.1389 1055.4395 1474.3978 2089.2241 2910.2119 4468.7646 7387.0493 13005.6934 | lr 1.0e-04 | norm 3534.9524 | dt 9.868 +type train | step 4793 | loss 96.8969 192.2310 303.3022 493.6009 725.6028 1055.5421 1488.0299 2134.4143 2984.3022 4626.2236 7669.0312 13440.0859 | lr 1.0e-04 | norm 3832.3167 | dt 9.867 +type train | step 4794 | loss 91.7092 181.8075 289.0949 477.3304 703.9852 1027.4025 1450.4236 2086.0491 2925.1147 4528.4639 7500.2358 13214.2002 | lr 1.0e-04 | norm 3862.1477 | dt 9.874 +type train | step 4795 | loss 94.4095 184.7025 290.4249 475.9745 704.2202 1016.3848 1434.5120 2056.1982 2916.2798 4520.1602 7506.7979 13198.7383 | lr 1.0e-04 | norm 3501.4773 | dt 10.175 +type train | step 4796 | loss 90.1185 179.4479 285.9109 470.8177 702.0035 1029.8613 1467.4210 2122.6057 3013.5708 4655.1475 7666.5034 13455.8545 | lr 1.0e-04 | norm 3877.5146 | dt 9.878 +type train | step 4797 | loss 84.2953 165.3019 265.1710 443.5524 668.4141 973.5833 1387.8617 2012.0846 2869.7256 4463.3633 7370.5801 12904.1777 | lr 1.0e-04 | norm 4140.7773 | dt 9.851 +type train | step 4798 | loss 99.3162 196.3727 306.8828 500.7910 727.1954 1050.0917 1471.0291 2097.6814 2925.1865 4529.4946 7480.7310 13199.2979 | lr 1.0e-04 | norm 3842.1150 | dt 9.876 +type train | step 4799 | loss 94.8875 188.0230 296.0537 486.3846 718.4898 1037.0240 1459.3644 2090.1216 2927.0566 4513.2168 7440.8076 13031.8711 | lr 1.0e-04 | norm 3469.4038 | dt 9.873 +type train | step 4800 | loss 108.4557 214.5985 324.5474 510.2591 739.2418 1041.6309 1441.3318 2020.5656 2805.5452 4314.5581 7095.9346 12700.0254 | lr 1.0e-04 | norm 7119.5762 | dt 9.868 +type train | step 4801 | loss 99.3322 196.5999 307.2807 502.2921 739.8159 1079.1372 1520.3287 2187.0454 3052.9766 4709.9873 7792.3350 13612.3643 | lr 1.0e-04 | norm 4308.7368 | dt 9.878 +type train | step 4802 | loss 96.6918 190.0184 298.3959 489.2723 715.6089 1033.7786 1445.2018 2055.0325 2839.4539 4357.4014 7196.0825 12687.6416 | lr 1.0e-04 | norm 3833.2488 | dt 9.869 +type train | step 4803 | loss 89.7728 178.3574 281.7146 462.1151 685.0916 989.6364 1391.1694 1982.3295 2805.5027 4330.9092 7134.3091 12478.8760 | lr 1.0e-04 | norm 2957.8401 | dt 9.899 +type train | step 4804 | loss 86.6525 170.8828 271.3562 447.5188 665.7900 968.6743 1370.5471 1972.1431 2802.4133 4346.8970 7157.1011 12485.7539 | lr 1.0e-04 | norm 3211.1438 | dt 9.874 +type train | step 4805 | loss 89.8398 175.1877 275.2118 449.7776 673.0613 974.5817 1386.4369 1993.4789 2846.9089 4355.4995 7080.9399 12196.7939 | lr 1.0e-04 | norm 5395.6519 | dt 9.869 +type train | step 4806 | loss 90.1125 181.2545 292.8958 482.8632 717.4738 1042.6813 1474.9761 2120.7612 2995.8052 4635.6968 7667.6006 13476.9043 | lr 1.0e-04 | norm 3444.9446 | dt 9.876 +type train | step 4807 | loss 104.5083 206.4311 318.0724 514.9040 736.1434 1066.2744 1478.1520 2093.9551 2871.5127 4396.1221 7162.3511 12743.9463 | lr 1.0e-04 | norm 5506.2090 | dt 9.845 +type train | step 4808 | loss 90.1153 179.7144 286.5138 470.3024 697.7776 1014.6426 1432.2593 2066.6416 2917.8613 4516.2036 7481.8013 13139.8789 | lr 1.0e-04 | norm 3677.7056 | dt 9.879 +type train | step 4809 | loss 91.2736 179.8342 285.8320 467.9740 694.5264 1003.8128 1418.8151 2037.7812 2891.4265 4464.6016 7350.3560 12904.0312 | lr 1.0e-04 | norm 3165.1411 | dt 9.871 +type train | step 4810 | loss 103.2420 206.4919 322.1215 524.9466 762.5305 1094.7329 1526.6008 2159.8855 2977.3857 4564.8486 7551.9526 13305.4102 | lr 1.0e-04 | norm 5364.3525 | dt 9.869 +type train | step 4811 | loss 96.8497 191.8058 299.5220 491.3119 719.8344 1042.0472 1458.1842 2074.0686 2877.0867 4409.4165 7239.2900 12646.7344 | lr 1.0e-04 | norm 3631.0833 | dt 9.873 +type train | step 4812 | loss 95.5102 192.6948 304.8554 498.6662 733.6152 1052.9154 1476.0966 2101.2896 2948.7471 4538.6206 7516.6611 13195.3047 | lr 1.0e-04 | norm 4010.8018 | dt 9.875 +type train | step 4813 | loss 87.4724 174.5762 279.3317 465.0425 695.9255 1012.6137 1434.4711 2065.9702 2941.6765 4566.2578 7574.8755 13391.8135 | lr 1.0e-04 | norm 4655.1201 | dt 9.866 +type train | step 4814 | loss 93.2127 189.2796 301.1154 501.3493 740.4761 1068.0973 1497.8575 2138.6516 3017.8965 4662.8569 7724.0479 13673.4404 | lr 1.0e-04 | norm 4141.2275 | dt 9.877 +type train | step 4815 | loss 97.2400 194.8872 312.7776 515.9508 757.5087 1094.6294 1551.4993 2242.2358 3084.8857 4793.0977 8068.1553 14567.1016 | lr 1.0e-04 | norm 9374.2002 | dt 9.841 +type train | step 4816 | loss 127.3390 250.9031 375.8793 594.6125 850.7062 1225.9630 1743.1108 2479.3394 3304.1465 5084.4854 8563.8643 15881.4971 | lr 1.0e-04 | norm 17906.6797 | dt 9.836 +type train | step 4817 | loss 93.5918 183.1087 290.9260 480.7709 708.7111 1027.5966 1445.0096 2070.8330 2903.5811 4515.2793 7444.3569 13080.7568 | lr 1.0e-04 | norm 3862.8835 | dt 9.884 +type train | step 4818 | loss 98.4645 194.6927 302.6215 490.2350 714.9762 1024.2354 1420.3627 2020.2815 2819.2249 4342.3223 7115.6802 12592.0928 | lr 1.0e-04 | norm 5069.4214 | dt 9.858 +type train | step 4819 | loss 89.2841 178.8346 282.3222 465.1793 692.8226 998.6683 1402.7140 2015.7241 2846.3826 4421.8779 7286.3955 12705.1572 | lr 1.0e-04 | norm 4312.8379 | dt 9.889 +type train | step 4820 | loss 91.4948 181.2237 287.2564 470.4094 699.5180 1008.3400 1422.0667 2037.6708 2885.8706 4471.1479 7418.5874 13013.7441 | lr 1.0e-04 | norm 3724.0945 | dt 9.869 +type train | step 4821 | loss 93.2612 183.1589 288.6986 472.3758 701.5515 1017.5923 1432.1177 2059.3904 2873.2639 4476.0474 7415.7227 13234.8262 | lr 1.0e-04 | norm 5495.5757 | dt 9.860 +type train | step 4822 | loss 82.2007 161.5649 260.7296 435.3220 655.0788 960.8007 1367.7798 1982.0922 2795.1536 4365.2251 7214.8896 12853.4922 | lr 1.0e-04 | norm 6079.6870 | dt 9.848 +type train | step 4823 | loss 92.1441 183.6037 286.9567 468.3672 694.3594 1019.1799 1444.1235 2089.1846 2929.2593 4581.5186 7652.7046 13550.9629 | lr 1.0e-04 | norm 4496.3706 | dt 9.843 +type train | step 4824 | loss 96.1535 191.8638 304.2603 495.4545 726.0226 1044.1984 1460.9993 2082.1956 2891.5730 4460.1699 7398.0156 13075.0410 | lr 1.0e-04 | norm 4565.4761 | dt 9.868 +type train | step 4825 | loss 90.4808 177.9319 282.1019 463.5554 689.1153 1004.5356 1420.1147 2042.4506 2881.7441 4453.7969 7398.3896 12997.2197 | lr 1.0e-04 | norm 3743.4077 | dt 9.881 +type train | step 4826 | loss 92.4416 181.9783 286.0610 475.0943 706.3801 1042.9484 1483.8580 2161.8628 3008.6758 4675.9692 7761.6045 13791.8516 | lr 1.0e-04 | norm 4784.5928 | dt 9.871 +type train | step 4827 | loss 89.7050 179.4265 281.2536 465.6055 691.7577 1012.2259 1439.6318 2089.7930 2941.0652 4562.7070 7518.7466 13138.2998 | lr 1.0e-04 | norm 3907.1035 | dt 9.869 +type train | step 4828 | loss 84.2433 165.7522 267.6151 448.0845 671.6938 982.9678 1398.1877 2025.0686 2843.1580 4435.3115 7374.9741 13049.5312 | lr 1.0e-04 | norm 5271.1733 | dt 9.860 +type train | step 4829 | loss 92.2373 184.0775 290.4003 477.2813 700.6484 1014.8790 1425.5901 2035.2986 2864.0605 4425.3213 7301.2090 12835.5508 | lr 1.0e-04 | norm 3846.2666 | dt 9.868 +type train | step 4830 | loss 92.8788 185.2239 292.2245 479.3200 703.8335 1028.3455 1449.4142 2078.8442 2924.9160 4531.0044 7499.4238 13275.4219 | lr 1.0e-04 | norm 4282.2935 | dt 9.867 +type train | step 4831 | loss 90.0939 178.4584 282.6725 463.6650 689.3104 1004.8419 1422.0515 2049.8403 2887.5964 4461.7725 7333.6582 12815.2314 | lr 1.0e-04 | norm 3100.9756 | dt 9.876 +type train | step 4832 | loss 96.9939 190.6464 298.5087 488.5756 718.7621 1049.6371 1477.1969 2127.9521 2972.4487 4575.1895 7515.9751 13198.4092 | lr 1.0e-04 | norm 4359.4023 | dt 9.871 +type train | step 4833 | loss 92.4060 181.2695 286.6158 473.2754 701.6009 1022.4826 1444.4580 2075.4841 2928.4600 4525.1924 7467.6606 13126.5801 | lr 1.0e-04 | norm 3466.6970 | dt 9.866 +type train | step 4834 | loss 90.2768 176.5155 282.7887 465.4566 693.1227 1007.3338 1421.3403 2039.2593 2870.3730 4435.3662 7331.3643 12808.9238 | lr 1.0e-04 | norm 3089.3518 | dt 9.877 +type train | step 4835 | loss 87.9408 175.7255 281.7250 464.9722 692.5920 1009.3649 1428.8018 2061.8701 2918.5630 4545.3457 7550.0830 13272.6680 | lr 1.0e-04 | norm 3545.9023 | dt 9.871 +type train | step 4836 | loss 88.7552 173.7000 275.8226 458.9786 684.4321 1008.2452 1429.7628 2068.1738 2923.8345 4549.3921 7581.9077 13324.7090 | lr 1.0e-04 | norm 3760.3071 | dt 9.874 +type train | step 4837 | loss 97.4563 193.5833 301.7269 487.5790 716.7683 1035.0765 1458.2559 2085.1943 2904.7520 4470.1562 7388.5918 13070.7900 | lr 1.0e-04 | norm 3855.7283 | dt 9.874 +type train | step 4838 | loss 93.0264 184.3517 289.0151 474.5157 703.6769 1032.7642 1458.7922 2106.0002 2943.0488 4505.0728 7381.1919 12851.5811 | lr 1.0e-04 | norm 4233.1206 | dt 9.877 +type train | step 4839 | loss 89.3274 176.0975 278.5198 455.2935 672.3381 984.3600 1406.2384 2038.8391 2879.5645 4490.3218 7379.9536 12989.6113 | lr 1.0e-04 | norm 8354.8389 | dt 9.859 +type train | step 4840 | loss 92.8779 184.4747 291.2307 476.3545 701.8582 1021.8760 1444.1997 2076.4133 2922.6387 4521.6309 7450.0005 13121.3936 | lr 1.0e-04 | norm 4499.9209 | dt 9.870 +type train | step 4841 | loss 86.5685 170.1831 271.9233 455.6466 683.7771 1001.9922 1423.3811 2061.9626 2912.8340 4504.6011 7449.2197 12997.2393 | lr 1.0e-04 | norm 4072.1716 | dt 9.871 +type train | step 4842 | loss 91.3796 181.7504 284.2624 464.2114 688.0758 1004.5652 1416.0107 2039.2505 2863.8469 4406.6235 7250.1768 12684.7246 | lr 1.0e-04 | norm 3448.7126 | dt 9.885 +type train | step 4843 | loss 100.1910 199.9846 305.2631 491.9725 732.5707 1088.3430 1542.0968 2260.9246 3127.6404 4773.8774 7750.9736 13491.4238 | lr 1.0e-04 | norm 4959.2983 | dt 9.842 +type train | step 4844 | loss 97.6156 191.9728 297.8506 481.2997 706.5523 1036.6436 1452.0884 2074.6536 2861.0093 4360.7344 7142.7725 12570.3506 | lr 1.0e-04 | norm 4350.6499 | dt 9.863 +type train | step 4845 | loss 96.3264 191.4469 299.7539 482.8450 712.1765 1031.0024 1457.5746 2088.7305 2931.4546 4527.1846 7471.4595 13216.5879 | lr 1.0e-04 | norm 5038.5718 | dt 9.860 +type train | step 4846 | loss 100.8761 198.5051 306.6680 494.3448 720.6465 1044.7750 1459.3210 2070.6143 2845.4949 4354.2896 7156.5107 12610.7383 | lr 1.0e-04 | norm 4589.8276 | dt 9.871 +type train | step 4847 | loss 92.5474 183.3955 288.3297 471.8413 697.9330 1012.3415 1429.3969 2057.9358 2912.7559 4518.0386 7480.6104 13095.2578 | lr 1.0e-04 | norm 3435.4451 | dt 9.876 +type train | step 4848 | loss 92.9357 183.6011 290.0997 474.9950 700.6976 1010.0302 1425.9886 2053.7832 2911.0586 4508.4233 7488.4194 13114.2188 | lr 1.0e-04 | norm 3474.7441 | dt 9.866 +type train | step 4849 | loss 101.7263 203.1037 314.2997 510.8685 753.1728 1088.4902 1530.3220 2194.6326 3064.9644 4727.3091 7739.7334 13691.2344 | lr 1.0e-04 | norm 3938.1196 | dt 9.881 +type train | step 4850 | loss 92.7313 184.6971 291.3972 475.3372 707.6465 1025.6255 1458.8331 2088.9465 2950.1506 4552.0713 7494.5220 13223.8535 | lr 1.0e-04 | norm 5551.9541 | dt 9.878 +type train | step 4851 | loss 96.3349 190.8923 296.4839 479.7649 703.4409 1016.0946 1425.5424 2040.1204 2853.5762 4390.4282 7260.9746 12788.7148 | lr 1.0e-04 | norm 3457.6421 | dt 9.869 +type train | step 4852 | loss 97.2045 192.5752 301.4557 493.4012 720.7384 1046.7307 1475.2249 2109.9463 2957.7173 4572.6660 7532.8613 13235.8174 | lr 1.0e-04 | norm 4394.6611 | dt 9.864 +type train | step 4853 | loss 88.4139 177.2324 284.6429 468.2443 699.0297 1017.1450 1437.4286 2068.3838 2915.7559 4533.4668 7500.4551 13177.8574 | lr 1.0e-04 | norm 3885.5835 | dt 9.878 +type train | step 4854 | loss 91.2407 181.8935 282.4704 459.2452 683.1765 1001.4010 1402.8777 2015.2061 2838.1084 4390.9580 7264.7808 12840.8438 | lr 1.0e-04 | norm 5001.3276 | dt 9.850 +type train | step 4855 | loss 91.1731 178.7777 283.8173 469.8693 696.0973 1008.3547 1422.8589 2039.8011 2864.6860 4413.4595 7312.9863 12852.6143 | lr 1.0e-04 | norm 3354.4756 | dt 9.877 +type train | step 4856 | loss 88.8075 173.7891 274.9407 454.0061 678.6832 986.0597 1394.2457 2005.2045 2844.5798 4435.9736 7395.2056 13071.4668 | lr 1.0e-04 | norm 3763.7202 | dt 9.857 +type train | step 4857 | loss 94.5249 189.9171 300.5183 492.4114 722.4036 1044.7369 1464.6868 2086.1951 2928.3027 4519.6514 7468.5752 13202.0586 | lr 1.0e-04 | norm 3466.5908 | dt 9.888 +type train | step 4858 | loss 90.8724 178.2182 282.9300 467.4051 694.1175 1010.6563 1423.4615 2042.3086 2881.2537 4435.4526 7323.6875 12849.0244 | lr 1.0e-04 | norm 3148.4878 | dt 9.868 +type train | step 4859 | loss 91.0393 179.5121 282.8638 463.8586 689.5623 996.9073 1410.7188 2029.2966 2875.6328 4483.1909 7401.9766 12989.1221 | lr 1.0e-04 | norm 3678.6531 | dt 9.872 +type train | step 4860 | loss 87.8192 172.5471 274.1443 454.0631 677.9866 993.3021 1413.0436 2039.4590 2882.8940 4504.2026 7523.6816 13441.3086 | lr 1.0e-04 | norm 4117.4448 | dt 9.871 +type train | step 4861 | loss 95.5020 189.2265 296.6021 481.5142 710.1252 1034.1942 1454.8208 2082.9302 2902.9639 4483.2827 7452.4976 13167.3369 | lr 1.0e-04 | norm 3792.0583 | dt 9.876 +type train | step 4862 | loss 88.3272 176.4793 279.0428 458.3385 680.1877 988.7981 1398.1600 2011.6415 2833.0620 4371.6104 7234.9697 12626.8838 | lr 1.0e-04 | norm 3353.6421 | dt 9.878 +type train | step 4863 | loss 94.8391 188.7216 296.6824 483.7217 713.8513 1034.2172 1456.8912 2076.4155 2909.9656 4462.3408 7383.8105 12982.4551 | lr 1.0e-04 | norm 4533.2080 | dt 9.888 +type train | step 4864 | loss 91.9010 184.0870 289.6949 473.4153 697.4606 1009.1173 1418.4279 2035.7422 2876.9065 4437.3354 7306.8745 12825.6992 | lr 1.0e-04 | norm 3430.9124 | dt 9.871 +type train | step 4865 | loss 83.4869 163.8633 261.6391 435.5245 657.9645 960.6249 1365.8970 1973.2996 2809.0439 4370.4038 7239.0513 12648.2119 | lr 1.0e-04 | norm 3234.5100 | dt 9.866 +type train | step 4866 | loss 88.8710 174.7040 277.5500 458.7909 684.1620 1001.4406 1414.1346 2035.3662 2863.8013 4413.4302 7269.0908 12715.5967 | lr 1.0e-04 | norm 3401.0056 | dt 9.877 +type train | step 4867 | loss 101.5882 203.5488 316.9105 513.5394 749.9338 1086.5938 1517.0990 2162.2754 2994.0229 4597.0879 7577.6655 13324.9082 | lr 1.0e-04 | norm 3845.5022 | dt 9.891 +type train | step 4868 | loss 94.1032 186.2168 293.1465 478.6871 702.8199 1018.9661 1430.2540 2029.9989 2845.3596 4371.8120 7213.2207 12720.7266 | lr 1.0e-04 | norm 4642.2134 | dt 9.869 +type train | step 4869 | loss 88.5387 177.7902 284.3716 467.0392 696.6077 1012.3521 1429.7993 2058.2185 2916.2822 4516.5479 7469.5679 13096.3359 | lr 1.0e-04 | norm 3456.8164 | dt 9.886 +type train | step 4870 | loss 97.6364 194.4954 302.3709 491.2087 721.3519 1049.0250 1472.9268 2113.2146 2929.5493 4522.6626 7450.4258 13109.1475 | lr 1.0e-04 | norm 4081.5005 | dt 9.880 +type train | step 4871 | loss 90.4688 180.8764 284.5765 469.9985 697.8383 1020.6567 1448.4246 2093.7593 2950.6470 4551.1016 7562.9800 13302.4180 | lr 1.0e-04 | norm 3825.3289 | dt 9.865 +type train | step 4872 | loss 91.3397 181.5781 289.6273 483.6528 723.7833 1052.5906 1486.9572 2158.2805 3020.4141 4627.8027 7659.8848 13587.8301 | lr 1.0e-04 | norm 7669.9370 | dt 9.861 +type train | step 4873 | loss 89.4857 178.2809 280.3271 458.0997 681.2171 987.0220 1399.3777 2013.6062 2840.4309 4431.3481 7337.7476 12955.6436 | lr 1.0e-04 | norm 4003.2031 | dt 9.864 +type train | step 4874 | loss 154.2843 325.2441 455.5087 667.5146 995.8970 1453.1084 2060.5129 2913.6338 3859.4512 5480.0400 8408.6475 14328.5938 | lr 1.0e-04 | norm 7149.0952 | dt 9.838 +type train | step 4875 | loss 89.2661 177.9923 282.0087 460.4456 684.6374 989.6703 1390.9509 1992.8065 2819.6147 4364.3682 7219.1626 12651.6797 | lr 1.0e-04 | norm 3165.5413 | dt 9.875 +type train | step 4876 | loss 87.8551 175.0047 282.8528 466.7588 695.1198 1011.0726 1430.2932 2056.5759 2917.2661 4567.9517 7599.6514 13343.1885 | lr 1.0e-04 | norm 3323.0085 | dt 9.872 +type train | step 4877 | loss 88.1734 173.8701 276.8870 454.5677 675.5327 987.0125 1397.9963 2007.6021 2844.1035 4407.1362 7321.2979 12812.0176 | lr 1.0e-04 | norm 3240.3242 | dt 9.873 +type train | step 4878 | loss 86.8461 170.7056 272.9468 453.7965 677.4954 984.1534 1392.4329 1993.7229 2821.1091 4360.8096 7204.5981 12548.2383 | lr 1.0e-04 | norm 3262.6929 | dt 9.882 +type train | step 4879 | loss 91.5540 178.5719 280.8533 464.4530 690.6111 1010.3035 1430.6853 2049.5728 2889.8630 4488.6348 7416.0342 12996.1416 | lr 1.0e-04 | norm 3360.6758 | dt 9.864 +type train | step 4880 | loss 89.7557 176.4143 280.7260 461.1510 684.3309 991.4199 1397.4795 2009.5680 2837.6755 4399.6704 7284.9502 12752.5586 | lr 1.0e-04 | norm 3014.7949 | dt 9.882 +type train | step 4881 | loss 87.2807 170.9713 272.5761 448.5034 667.5375 972.6400 1372.0394 1969.8518 2771.3982 4298.3418 7132.9209 12502.4219 | lr 1.0e-04 | norm 3515.9087 | dt 9.881 +type train | step 4882 | loss 85.4790 169.5545 270.0625 445.9801 668.4132 974.3528 1393.3569 2016.8730 2875.2224 4461.1318 7331.9673 12808.4902 | lr 1.0e-04 | norm 4271.3955 | dt 9.869 +type train | step 4883 | loss 89.8689 176.8177 281.1768 460.9911 686.0984 1002.1403 1417.4771 2038.2848 2896.9585 4501.4473 7454.7285 12970.8770 | lr 1.0e-04 | norm 3301.0481 | dt 9.869 +type train | step 4884 | loss 100.0087 197.2388 308.7037 504.7764 742.0725 1080.9502 1522.5133 2176.3857 3005.0947 4620.5088 7677.3433 13593.4424 | lr 1.0e-04 | norm 5344.7163 | dt 9.860 +type train | step 4885 | loss 90.7611 179.8961 284.8456 470.0330 701.3273 1026.9631 1457.6135 2097.8984 2975.4077 4609.0811 7621.9995 13473.1436 | lr 1.0e-04 | norm 3938.4158 | dt 9.873 +type train | step 4886 | loss 86.9658 170.4731 272.4732 450.6074 673.4811 979.9898 1385.4351 1991.0352 2816.6885 4376.0879 7237.5835 12788.8320 | lr 1.0e-04 | norm 3509.3481 | dt 9.878 +type train | step 4887 | loss 92.8674 183.0830 288.9467 474.6382 707.3773 1031.1118 1459.0641 2111.0288 2959.9543 4544.3857 7423.2988 13049.9004 | lr 1.0e-04 | norm 6007.9648 | dt 9.855 +type train | step 4888 | loss 85.4432 168.6345 270.3448 451.1564 675.8933 988.5862 1402.6189 2026.5393 2863.8250 4434.9805 7329.9746 12770.8906 | lr 1.0e-04 | norm 3240.0615 | dt 9.889 +type train | step 4889 | loss 90.5096 177.6422 281.8264 465.1393 693.9490 1007.3221 1426.9189 2055.3828 2894.7256 4537.2583 7545.2832 13227.8535 | lr 1.0e-04 | norm 3655.0286 | dt 9.883 +type train | step 4890 | loss 87.3956 170.7575 270.8431 445.6796 667.9183 972.0181 1379.3662 2006.2667 2858.7266 4459.0029 7365.0044 12855.7021 | lr 1.0e-04 | norm 3768.6135 | dt 9.868 +type train | step 4891 | loss 93.6475 186.8226 293.2521 477.7115 704.1339 1019.3707 1432.8229 2044.6093 2868.7920 4421.5508 7318.0186 12895.8262 | lr 1.0e-04 | norm 3382.4690 | dt 9.873 +type train | step 4892 | loss 103.6714 205.9986 315.9789 507.9997 741.8196 1064.4478 1487.2324 2105.1575 2924.3054 4493.9097 7367.2690 12775.5771 | lr 1.0e-04 | norm 3357.1514 | dt 9.862 +type train | step 4893 | loss 94.1870 184.1641 291.3276 476.8447 705.2562 1024.6497 1439.1307 2057.2920 2872.2769 4432.1489 7280.3071 12765.6533 | lr 1.0e-04 | norm 3835.8479 | dt 9.859 +type train | step 4894 | loss 93.5375 187.0578 294.5634 477.9393 712.4172 1024.7544 1451.5593 2083.7173 2943.1177 4572.6367 7493.6880 13047.8438 | lr 1.0e-04 | norm 5877.5356 | dt 9.865 +type train | step 4895 | loss 95.2537 189.5142 297.6500 477.8907 701.6820 1006.4846 1403.1536 2002.9224 2755.3564 4223.7295 6912.1655 12271.7988 | lr 1.0e-04 | norm 7423.9136 | dt 9.840 +type train | step 4896 | loss 96.0394 194.0617 308.2061 506.2503 748.7526 1083.7714 1522.1206 2178.6646 3011.4165 4577.4946 7543.2354 13196.8613 | lr 1.0e-04 | norm 5954.8457 | dt 9.847 +type train | step 4897 | loss 89.9143 177.2447 279.5844 457.8163 678.9174 980.9188 1385.1072 1990.9684 2807.7344 4338.5625 7138.5879 12458.9316 | lr 1.0e-04 | norm 3227.1963 | dt 9.876 +type train | step 4898 | loss 86.9278 171.2787 272.7733 452.4059 680.6666 993.5569 1413.2167 2045.0116 2894.2480 4482.2612 7433.2119 13040.8057 | lr 1.0e-04 | norm 3542.2051 | dt 9.882 +type train | step 4899 | loss 87.7859 173.4484 274.8326 454.4380 680.3543 996.0507 1410.0378 2040.8535 2872.6377 4452.6641 7358.5332 12969.9102 | lr 1.0e-04 | norm 4159.2842 | dt 9.862 +type train | step 4900 | loss 90.1567 178.3268 281.0259 468.8207 698.3721 1021.4936 1443.4830 2084.4968 2919.0728 4502.9170 7430.0688 13052.1572 | lr 1.0e-04 | norm 4179.3096 | dt 9.851 +type train | step 4901 | loss 92.5483 184.7241 292.0524 482.4712 713.0147 1039.9120 1470.9158 2125.7883 3003.0107 4659.6787 7767.7559 13770.8672 | lr 1.0e-04 | norm 4507.3037 | dt 9.868 +type train | step 4902 | loss 99.2634 202.0805 311.8748 502.9363 743.4913 1095.3783 1543.3700 2228.9817 3059.5139 4668.1289 7663.9429 13300.6611 | lr 1.0e-04 | norm 4279.5674 | dt 9.856 +type train | step 4903 | loss 92.0405 184.6773 291.3426 477.4877 708.0168 1049.6553 1473.5032 2107.7656 2899.6133 4393.2998 7184.1538 12645.1113 | lr 1.0e-04 | norm 4804.0410 | dt 9.838 +type train | step 4904 | loss 87.4089 172.4875 287.1422 484.9681 720.3567 1047.3927 1473.1570 2124.3945 3002.1509 4664.8457 7740.9150 13568.8711 | lr 1.0e-04 | norm 6599.3604 | dt 9.854 +type train | step 4905 | loss 93.0025 185.2878 290.9592 473.9262 699.6549 1011.0519 1417.0682 2030.5192 2854.9990 4422.5947 7343.8760 12934.8193 | lr 1.0e-04 | norm 3718.8279 | dt 9.874 +type train | step 4906 | loss 91.5318 180.3486 285.9675 466.6777 686.9413 995.7207 1407.2930 2028.6713 2853.8701 4428.9053 7343.3213 12994.6260 | lr 1.0e-04 | norm 3995.3633 | dt 9.864 +type train | step 4907 | loss 96.5217 192.4497 296.1523 480.4433 702.8259 1020.1844 1434.2051 2052.8955 2887.0471 4477.3779 7477.9204 13163.5645 | lr 1.0e-04 | norm 4228.2666 | dt 9.876 +type train | step 4908 | loss 92.5394 182.8863 291.2271 479.3518 713.1931 1032.2603 1457.8011 2090.4348 2986.0181 4627.5981 7624.8301 13365.6709 | lr 1.0e-04 | norm 3835.4822 | dt 9.862 +type train | step 4909 | loss 97.1582 192.2815 299.8817 487.9922 711.3619 1031.3447 1446.6147 2066.8088 2895.7039 4497.1147 7484.3384 13202.3613 | lr 1.0e-04 | norm 4249.8042 | dt 9.867 +type train | step 4910 | loss 92.3810 184.5175 288.4828 472.8571 701.2661 1020.9587 1450.9666 2097.3442 2929.8950 4544.5991 7561.1978 13379.5332 | lr 1.0e-04 | norm 4611.4956 | dt 9.864 +type train | step 4911 | loss 94.4795 187.4378 293.0200 479.9337 710.0316 1024.7216 1441.9673 2066.9453 2909.3484 4491.4956 7385.8149 12875.6787 | lr 1.0e-04 | norm 3665.1748 | dt 9.874 +type train | step 4912 | loss 89.2550 175.5105 280.3387 465.6487 694.7671 1007.2234 1427.5504 2058.4043 2938.8582 4544.3779 7461.7031 13052.9238 | lr 1.0e-04 | norm 3572.0945 | dt 9.857 +type train | step 4913 | loss 96.0507 191.7469 298.5682 481.6419 711.6022 1022.7563 1442.8390 2061.8462 2908.1763 4485.2622 7390.2363 12969.1963 | lr 1.0e-04 | norm 3882.1414 | dt 9.867 +type train | step 4914 | loss 88.5912 173.9088 276.1534 456.7673 679.6122 994.1277 1404.1732 2027.1472 2857.9294 4431.3315 7319.7144 12749.3037 | lr 1.0e-04 | norm 3277.0681 | dt 9.883 +type train | step 4915 | loss 89.7697 177.8875 280.8227 460.9141 683.0588 993.6832 1406.7903 2015.4393 2850.0469 4428.8804 7353.2129 12942.7607 | lr 1.0e-04 | norm 3458.0283 | dt 9.875 +type train | step 4916 | loss 91.8016 181.6034 287.8211 468.9986 698.2724 1015.0081 1424.4529 2034.1592 2861.8152 4405.7832 7251.3384 12670.9863 | lr 1.0e-04 | norm 3403.6665 | dt 9.876 +type train | step 4917 | loss 94.5843 187.8738 295.7961 485.0333 712.8151 1041.8887 1476.1891 2120.2029 2955.8750 4570.2466 7555.3145 13419.9336 | lr 1.0e-04 | norm 4106.9844 | dt 9.880 +type train | step 4918 | loss 95.1624 189.5983 293.0300 476.1342 706.0080 1025.8340 1449.8796 2087.5132 2953.0354 4555.2812 7472.6362 12998.2686 | lr 1.0e-04 | norm 3653.0540 | dt 9.877 +type train | step 4919 | loss 91.3655 181.7836 285.9279 468.5856 692.7720 1007.3562 1430.4113 2061.9146 2902.7349 4519.7563 7513.9985 13273.3105 | lr 1.0e-04 | norm 4445.9263 | dt 9.857 +type train | step 4920 | loss 91.0772 178.2106 280.0342 456.9684 680.4689 993.9352 1414.7513 2040.8069 2876.7864 4427.9590 7268.0273 12673.5645 | lr 1.0e-04 | norm 4441.6406 | dt 9.852 +type train | step 4921 | loss 92.1737 182.3615 288.5478 471.4626 697.7145 1017.2717 1440.0883 2072.7393 2918.4114 4506.7920 7473.6880 13147.4766 | lr 1.0e-04 | norm 3720.8699 | dt 9.869 +type train | step 4922 | loss 92.2363 182.3848 288.8410 472.0304 699.7011 1012.0020 1426.0276 2044.2556 2876.6597 4434.7891 7333.6445 12880.8535 | lr 1.0e-04 | norm 3063.6370 | dt 9.866 +type train | step 4923 | loss 87.0718 169.8306 271.9234 449.6329 673.0162 977.5118 1385.0715 1994.7986 2821.2017 4383.9546 7247.3730 12695.9219 | lr 1.0e-04 | norm 3620.9456 | dt 9.873 +type train | step 4924 | loss 89.5614 179.4736 282.9245 466.2829 693.3091 1011.7438 1438.4812 2079.1953 2941.1711 4592.1250 7608.5273 13381.9893 | lr 1.0e-04 | norm 3567.7798 | dt 9.871 +type train | step 4925 | loss 93.9556 186.6861 289.9546 474.5672 700.8752 1019.3494 1434.4270 2057.7241 2859.6887 4432.4521 7343.0146 13117.6221 | lr 1.0e-04 | norm 5289.0918 | dt 9.858 +type train | step 4926 | loss 92.6328 182.6731 288.8601 478.1020 708.9755 1035.6079 1467.7605 2106.8337 2952.1077 4533.9741 7536.7222 13213.9678 | lr 1.0e-04 | norm 4321.2256 | dt 9.854 +type train | step 4927 | loss 97.5506 193.7432 298.5568 485.9408 714.4443 1033.5056 1450.0338 2076.3943 2930.8579 4551.8525 7575.0000 13374.6807 | lr 1.0e-04 | norm 4101.4077 | dt 9.864 +type train | step 4928 | loss 88.5002 176.5112 281.1510 464.6673 692.0897 1001.3781 1414.0006 2032.0315 2880.5366 4458.9688 7366.3911 12935.5674 | lr 1.0e-04 | norm 3058.3689 | dt 9.880 +type train | step 4929 | loss 87.6995 173.4872 275.2292 454.0582 674.4023 978.0093 1381.0599 1987.9946 2820.7290 4377.7285 7270.2090 12607.6680 | lr 1.0e-04 | norm 3027.5103 | dt 9.865 +type train | step 4930 | loss 94.1309 187.2971 293.0570 477.8947 701.4632 1018.8369 1431.1071 2045.8303 2850.1729 4378.2759 7252.5615 12736.9941 | lr 1.0e-04 | norm 4038.5876 | dt 9.863 +type train | step 4931 | loss 85.7792 167.3071 267.7322 444.4838 667.6362 972.1611 1379.1797 1984.7065 2822.6929 4375.5117 7270.8032 12715.2354 | lr 1.0e-04 | norm 3016.2151 | dt 9.873 +type train | step 4932 | loss 89.3333 178.0652 280.8560 459.6594 683.0803 1004.4744 1428.9723 2061.5007 2911.6270 4512.0869 7465.0664 13056.8184 | lr 1.0e-04 | norm 3696.2144 | dt 9.858 +type train | step 4933 | loss 91.7237 182.8226 288.8987 471.8263 702.0656 1011.0852 1419.1003 2027.1444 2851.0491 4404.5405 7300.1587 12862.0117 | lr 1.0e-04 | norm 4012.4185 | dt 9.872 +type train | step 4934 | loss 91.0757 179.7450 284.5836 468.8872 694.7128 1005.5884 1418.8645 2028.0067 2850.5505 4394.4209 7249.9995 12791.0215 | lr 1.0e-04 | norm 6045.9829 | dt 9.871 +type train | step 4935 | loss 87.4497 173.1115 273.3475 450.7321 674.7640 982.9661 1403.5145 2030.5664 2886.7207 4502.2461 7466.3296 13190.6748 | lr 1.0e-04 | norm 4167.6982 | dt 9.857 +type train | step 4936 | loss 89.5040 175.9527 282.7010 467.9705 696.6274 1003.4432 1418.7758 2039.2446 2907.3577 4502.9463 7449.7793 13018.7979 | lr 1.0e-04 | norm 3869.5852 | dt 9.880 +type train | step 4937 | loss 86.3681 168.8570 267.7538 444.4180 666.3678 967.7190 1370.5679 1971.2644 2792.5964 4338.3730 7203.5762 12685.4912 | lr 1.0e-04 | norm 3428.9976 | dt 9.864 +type train | step 4938 | loss 93.9658 184.9096 292.8441 469.3801 697.4750 1008.5973 1437.8521 2068.8401 2913.1426 4541.4663 7449.2397 13057.9834 | lr 1.0e-04 | norm 6311.3804 | dt 9.856 +type train | step 4939 | loss 91.0141 177.5032 282.2137 463.5578 690.5784 1004.1449 1418.6425 2032.9620 2875.5911 4457.6270 7354.6792 12933.6504 | lr 1.0e-04 | norm 3758.4797 | dt 9.866 +type train | step 4940 | loss 95.3990 189.8095 298.1438 485.7178 717.4809 1039.9240 1461.1855 2091.0208 2942.0938 4547.8311 7493.7852 13144.4688 | lr 1.0e-04 | norm 3950.7441 | dt 9.864 +type train | step 4941 | loss 101.8085 207.1039 322.6984 518.3317 756.4203 1105.3909 1543.9521 2209.4082 3036.2102 4661.8120 7664.0894 13435.8457 | lr 1.0e-04 | norm 5327.4316 | dt 9.865 +type train | step 4942 | loss 94.0579 187.9955 296.5259 483.5410 709.9113 1026.1899 1436.2007 2046.8248 2864.1790 4417.4097 7243.6831 12644.0215 | lr 1.0e-04 | norm 3008.5667 | dt 9.875 +type train | step 4943 | loss 91.7337 181.0277 284.0003 466.8512 693.2427 1020.0084 1451.9615 2100.5691 2952.6797 4560.7202 7508.2993 13093.6270 | lr 1.0e-04 | norm 3400.4771 | dt 9.871 +type train | step 4944 | loss 85.6022 168.4625 267.9144 443.6585 667.5794 979.0444 1395.2227 2014.3354 2835.1370 4416.8096 7282.1436 12782.2070 | lr 1.0e-04 | norm 6066.7910 | dt 9.858 +type train | step 4945 | loss 99.5273 199.5210 308.1554 503.6623 737.1896 1069.6328 1496.5695 2148.6482 2972.7251 4547.6660 7427.8389 13027.9297 | lr 1.0e-04 | norm 4246.9580 | dt 9.869 +type train | step 4946 | loss 90.1399 177.9887 281.2434 465.6779 691.0568 1008.1958 1420.0349 2036.0292 2865.8926 4418.7285 7289.9248 12780.6963 | lr 1.0e-04 | norm 3059.0342 | dt 9.879 +type train | step 4947 | loss 97.3877 192.0633 300.8942 490.1524 722.9758 1040.5079 1459.9869 2087.0854 2927.0745 4538.4731 7501.1777 13182.1660 | lr 1.0e-04 | norm 4421.3115 | dt 9.882 +type train | step 4948 | loss 95.5777 192.2987 296.6606 482.3247 704.7158 1020.8100 1421.4377 2012.8965 2755.6494 4196.6323 6838.2368 12093.5645 | lr 1.0e-04 | norm 6024.9590 | dt 9.847 +type train | step 4949 | loss 89.9240 175.8591 278.3269 456.4665 675.6299 977.8480 1369.8104 1963.0054 2743.4185 4229.7310 6963.0469 12286.8564 | lr 1.0e-04 | norm 3389.1411 | dt 9.881 +type train | step 4950 | loss 96.7613 188.7358 294.7616 477.0732 701.3425 1007.1920 1413.2664 2004.3652 2763.2920 4231.2051 6986.9482 12317.1084 | lr 1.0e-04 | norm 3771.9250 | dt 9.851 +type train | step 4951 | loss 92.2507 180.4675 286.3095 471.4911 701.6420 1035.2048 1464.8002 2103.9490 2936.7158 4546.0952 7499.8081 13157.4609 | lr 1.0e-04 | norm 3906.1350 | dt 9.865 +type train | step 4952 | loss 94.1593 184.7723 290.3670 471.9677 697.8665 1003.0276 1415.1365 2015.5793 2824.6099 4339.0391 7157.3286 12524.1387 | lr 1.0e-04 | norm 3892.7175 | dt 9.870 +type train | step 4953 | loss 88.1653 176.1277 280.6553 462.3109 688.8096 1004.5309 1422.5381 2054.3110 2890.2292 4491.2930 7466.8516 13133.5615 | lr 1.0e-04 | norm 3617.4629 | dt 9.860 +type train | step 4954 | loss 90.3852 178.4228 279.3963 455.8220 670.8477 978.5984 1386.5356 1999.9417 2828.2175 4403.8242 7360.7905 13055.5977 | lr 1.0e-04 | norm 4164.1841 | dt 9.871 +type train | step 4955 | loss 94.4906 188.0172 287.6027 473.8969 698.8145 1026.2069 1450.7466 2094.6765 2925.1538 4531.6860 7528.7466 13227.5488 | lr 1.0e-04 | norm 4615.5151 | dt 9.865 +type train | step 4956 | loss 89.0161 176.8667 277.8048 453.8998 674.4692 984.2677 1396.6387 2017.7886 2858.7544 4424.1646 7238.0908 12575.8623 | lr 1.0e-04 | norm 3504.6995 | dt 9.859 +type train | step 4957 | loss 96.7412 192.6569 298.9265 484.1991 709.7855 1037.7684 1448.5314 2082.4954 2897.9832 4435.8530 7307.7983 12863.5957 | lr 1.0e-04 | norm 4230.0879 | dt 9.846 +type train | step 4958 | loss 91.4020 184.7369 290.6271 469.6587 695.5029 1006.2644 1411.2295 2014.6168 2830.8035 4374.1494 7189.5527 12554.4131 | lr 1.0e-04 | norm 3025.4741 | dt 9.864 +type train | step 4959 | loss 86.1282 169.5171 270.4560 447.0471 671.6547 982.6926 1401.3799 2024.1954 2880.2888 4470.9971 7451.7495 13162.8574 | lr 1.0e-04 | norm 3597.6433 | dt 9.875 +type train | step 4960 | loss 90.1165 178.2329 282.5391 462.2132 682.8359 991.6291 1401.7332 2006.6223 2830.1812 4376.1440 7284.4771 12782.5166 | lr 1.0e-04 | norm 3207.7610 | dt 9.890 +type train | step 4961 | loss 85.6532 167.4283 270.3187 451.2606 673.9426 985.2577 1396.8861 2014.3101 2855.8010 4418.3457 7315.7070 12773.0850 | lr 1.0e-04 | norm 3124.3105 | dt 9.872 +type train | step 4962 | loss 87.2036 171.7750 272.1096 454.0161 676.9207 993.1609 1422.0447 2058.9800 2926.9009 4528.1548 7487.9873 13069.6953 | lr 1.0e-04 | norm 3624.4087 | dt 9.872 +type train | step 4963 | loss 93.3156 183.9450 289.8408 476.0574 707.4236 1036.1841 1464.4453 2113.2178 2960.9963 4543.4658 7443.6724 12940.0391 | lr 1.0e-04 | norm 3405.2378 | dt 9.869 +type train | step 4964 | loss 95.1304 189.6774 292.8314 478.1705 704.2271 1025.9086 1437.2924 2065.6758 2894.6387 4505.0356 7415.2466 13131.3125 | lr 1.0e-04 | norm 5177.0898 | dt 9.860 +type train | step 4965 | loss 86.8789 171.5213 272.2916 449.3120 671.7754 975.3683 1383.4878 1989.9050 2831.9038 4396.6094 7292.7822 12900.6797 | lr 1.0e-04 | norm 3190.6370 | dt 9.878 +type train | step 4966 | loss 89.4441 177.1003 280.8644 458.6880 680.4109 989.6864 1394.9457 2004.0162 2816.1428 4372.7319 7216.2017 12620.9746 | lr 1.0e-04 | norm 2959.4692 | dt 9.874 +type train | step 4967 | loss 90.2667 177.3765 279.4711 462.1339 687.0620 992.3393 1409.2410 2034.8326 2882.0308 4497.6406 7493.3823 13268.2920 | lr 1.0e-04 | norm 4624.8477 | dt 9.859 +type train | step 4968 | loss 90.0857 179.8554 282.2084 461.5165 684.7354 991.5783 1394.9409 2009.0326 2843.5474 4397.3667 7270.9912 12781.7949 | lr 1.0e-04 | norm 3496.4558 | dt 9.877 +type train | step 4969 | loss 90.9691 181.3521 289.0902 473.4449 702.6252 1018.1892 1434.2798 2051.3445 2887.7029 4495.0981 7465.9717 13198.6318 | lr 1.0e-04 | norm 3823.4915 | dt 9.872 +type train | step 4970 | loss 86.1366 171.0459 272.7071 452.6566 675.9207 987.4701 1399.9359 2017.2946 2864.1636 4458.4873 7405.8945 13017.5596 | lr 1.0e-04 | norm 3624.8022 | dt 9.870 +type train | step 4971 | loss 93.5279 183.5230 291.2411 478.4961 701.3871 1021.5377 1441.3055 2065.2825 2881.7827 4463.8330 7414.6084 13253.1367 | lr 1.0e-04 | norm 5292.2686 | dt 9.865 +type train | step 4972 | loss 88.7150 174.0082 277.3449 455.3762 678.3511 985.1987 1391.6842 2005.5070 2835.9941 4414.9253 7310.6226 12841.2930 | lr 1.0e-04 | norm 3400.8408 | dt 9.856 +type train | step 4973 | loss 97.7132 196.4793 308.1401 497.8037 720.0090 1029.1620 1438.4445 2034.2527 2830.3823 4343.6704 7175.9009 12588.2910 | lr 1.0e-04 | norm 5333.9448 | dt 9.864 +type train | step 4974 | loss 88.7483 176.5858 279.5264 457.6542 679.3914 984.9612 1391.1519 1990.0095 2808.0220 4330.2388 7178.7998 12581.6045 | lr 1.0e-04 | norm 3773.0278 | dt 9.859 +type train | step 4975 | loss 89.2030 176.7251 280.0173 461.7521 685.6848 1001.3383 1413.1772 2035.6349 2857.8445 4414.2227 7305.3755 12838.1191 | lr 1.0e-04 | norm 3233.6052 | dt 9.892 +type train | step 4976 | loss 89.7832 178.9927 286.4543 473.2787 702.7219 1022.5704 1447.8622 2084.5654 2947.1006 4546.4160 7511.0801 13168.1074 | lr 1.0e-04 | norm 3644.0767 | dt 9.875 +type train | step 4977 | loss 90.8336 178.9049 283.5560 465.5517 690.0693 999.4291 1411.3591 2021.6667 2863.5459 4428.1069 7355.9971 12898.2607 | lr 1.0e-04 | norm 3388.5203 | dt 9.883 +type train | step 4978 | loss 95.9428 186.3408 292.5137 477.6167 700.1362 1019.5295 1431.8123 2040.5356 2852.8176 4395.1396 7319.8057 12949.6436 | lr 1.0e-04 | norm 3487.9707 | dt 9.868 +type train | step 4979 | loss 90.6304 185.1875 293.2721 485.7801 720.9583 1056.1843 1494.7535 2151.0513 3038.9680 4738.6133 7875.2764 13789.9297 | lr 1.0e-04 | norm 4636.1577 | dt 9.871 +type train | step 4980 | loss 91.7075 180.8785 286.4047 469.0231 695.1089 1007.3068 1419.0648 2036.2465 2872.8530 4465.6733 7409.4897 13039.6494 | lr 1.0e-04 | norm 3331.9358 | dt 9.866 +type train | step 4981 | loss 95.7047 190.4698 298.7034 494.3792 729.0016 1061.3757 1496.4648 2153.0757 3035.5732 4684.5176 7726.8340 13531.7480 | lr 1.0e-04 | norm 3396.3123 | dt 9.872 +type train | step 4982 | loss 83.6976 163.6717 265.8147 442.0489 661.7512 968.0255 1374.4462 1984.9226 2809.4160 4335.7021 7130.1001 12487.0010 | lr 1.0e-04 | norm 3568.8232 | dt 9.861 +type train | step 4983 | loss 89.6418 178.6706 285.1992 469.1436 694.9966 1007.1695 1422.8224 2047.1460 2906.6318 4537.6289 7584.2051 13419.0400 | lr 1.0e-04 | norm 3719.1123 | dt 9.873 +type train | step 4984 | loss 86.9747 173.6120 277.4371 461.6669 688.1045 1013.2270 1442.2009 2094.7227 2961.9160 4576.5405 7538.3223 13171.0732 | lr 1.0e-04 | norm 3617.1526 | dt 9.864 +type train | step 4985 | loss 95.2841 188.1492 296.9114 483.3698 714.3992 1034.3652 1457.9060 2093.7129 2944.3267 4565.6250 7570.6899 13351.2441 | lr 1.0e-04 | norm 4673.2163 | dt 9.856 +type train | step 4986 | loss 88.3818 174.9382 276.0716 459.9950 682.9158 999.4738 1415.8557 2041.7351 2887.3052 4492.2988 7422.5176 13005.6602 | lr 1.0e-04 | norm 3589.5637 | dt 9.870 +type train | step 4987 | loss 89.0094 175.3131 276.1880 456.1675 680.3538 995.8259 1407.2958 2020.0012 2846.0779 4407.8145 7298.6030 12758.2549 | lr 1.0e-04 | norm 3402.0225 | dt 9.867 +type train | step 4988 | loss 86.7073 171.1033 275.3291 458.0186 683.0803 999.6226 1418.2377 2056.0913 2921.5061 4548.8896 7532.6685 13103.5986 | lr 1.0e-04 | norm 3579.6560 | dt 9.870 +type train | step 4989 | loss 88.3851 173.5383 276.5687 461.1876 692.7396 1032.6266 1467.5496 2142.3643 2999.0544 4639.3218 7682.3687 13496.1855 | lr 1.0e-04 | norm 4747.8057 | dt 9.846 +type train | step 4990 | loss 86.8990 170.9819 272.6740 451.1049 673.3347 981.2201 1393.1486 2016.0608 2855.1731 4444.3247 7353.8047 12800.8633 | lr 1.0e-04 | norm 3193.2761 | dt 9.854 +type train | step 4991 | loss 85.4168 166.6118 268.9653 447.4295 669.9596 984.5557 1401.4395 2025.6381 2864.9348 4432.1172 7317.1553 12875.5615 | lr 1.0e-04 | norm 4035.2837 | dt 9.860 +type train | step 4992 | loss 88.4674 174.3813 276.7946 457.5873 683.8060 987.1779 1392.3259 1993.6173 2830.7656 4378.5103 7235.1040 12662.3652 | lr 1.0e-04 | norm 3459.0698 | dt 9.884 +type train | step 4993 | loss 87.9846 171.9942 273.5126 453.6505 677.6570 989.9994 1399.6461 2011.1643 2845.2224 4387.9707 7270.3291 12672.9395 | lr 1.0e-04 | norm 2960.7720 | dt 9.877 +type train | step 4994 | loss 100.8270 203.8629 321.8195 513.1857 748.4965 1078.3518 1507.3217 2143.5176 3016.9019 4733.4297 7928.8760 14146.5146 | lr 1.0e-04 | norm 6421.7256 | dt 9.879 +type train | step 4995 | loss 88.0491 174.5203 281.0049 465.6494 691.5866 1006.4325 1423.4202 2042.4060 2903.2329 4480.5054 7425.2070 12927.4238 | lr 1.0e-04 | norm 3335.8887 | dt 9.873 +type train | step 4996 | loss 88.3182 174.3675 275.3348 454.2760 676.7683 987.2328 1404.8110 2026.0575 2851.0483 4426.4893 7391.1875 13077.8369 | lr 1.0e-04 | norm 3482.0674 | dt 9.864 +type train | step 4997 | loss 86.4332 171.6218 272.0147 449.1794 671.5948 982.5928 1399.5083 2015.5341 2876.5227 4463.6152 7401.1001 12983.0078 | lr 1.0e-04 | norm 3361.5515 | dt 9.862 +type train | step 4998 | loss 86.1058 169.8019 272.6418 452.0096 675.8631 982.7814 1390.4011 2001.5396 2837.8035 4390.8496 7270.8706 12760.9521 | lr 1.0e-04 | norm 3692.3618 | dt 9.881 +type train | step 4999 | loss 84.3015 163.8566 262.5379 438.6393 657.1750 958.9478 1363.6007 1969.0254 2797.0664 4342.0039 7219.2236 12660.7314 | lr 1.0e-04 | norm 3219.1091 | dt 9.862 +type train | step 5000 | loss 88.9280 172.2697 272.7276 450.2390 670.8633 975.6124 1384.2075 1994.2362 2812.6565 4361.5278 7253.1226 12823.5303 | lr 1.0e-04 | norm 3784.1658 | dt 9.873