|
Step 1 | loss:0.010427827946841717 lr:4.000000000000001e-06 tokens_per_second_per_gpu:5008.803920961876 |
|
Step 2 | loss:0.012005687691271305 lr:8.000000000000001e-06 tokens_per_second_per_gpu:4543.881741505023 |
|
Step 3 | loss:0.009577717632055283 lr:1.2e-05 tokens_per_second_per_gpu:6734.236745220564 |
|
Step 4 | loss:0.00831858441233635 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:6769.381361399619 |
|
Step 5 | loss:0.011338017880916595 lr:2e-05 tokens_per_second_per_gpu:6808.394730665254 |
|
Step 6 | loss:0.012518859468400478 lr:2.4e-05 tokens_per_second_per_gpu:6826.8391987912155 |
|
Step 7 | loss:0.009475968778133392 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:6732.7444724965135 |
|
Step 8 | loss:0.009848631918430328 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:6760.5034121812705 |
|
Step 9 | loss:0.04560374096035957 lr:3.6e-05 tokens_per_second_per_gpu:3810.7806500671277 |
|
Step 10 | loss:0.012298542074859142 lr:4e-05 tokens_per_second_per_gpu:6847.044814584687 |
|
Step 11 | loss:0.011072923429310322 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:4733.153092515809 |
|
Step 12 | loss:0.05228746309876442 lr:4.8e-05 tokens_per_second_per_gpu:7031.137102265347 |
|
Step 13 | loss:0.00804749596863985 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:6787.49204446146 |
|
Step 14 | loss:0.01451866701245308 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:7111.1075156944025 |
|
Step 15 | loss:0.006390584632754326 lr:6e-05 tokens_per_second_per_gpu:6842.452370635766 |
|
Step 16 | loss:0.02179665118455887 lr:6.400000000000001e-05 tokens_per_second_per_gpu:6823.107724400367 |
|
Step 17 | loss:0.0033636281732469797 lr:6.800000000000001e-05 tokens_per_second_per_gpu:6808.574304054001 |
|
Step 18 | loss:0.009917511604726315 lr:7.2e-05 tokens_per_second_per_gpu:7069.924856487332 |
|
Step 19 | loss:0.004517083056271076 lr:7.6e-05 tokens_per_second_per_gpu:6764.437095893996 |
|
Step 20 | loss:0.006020938046276569 lr:8e-05 tokens_per_second_per_gpu:6923.754124218399 |
|
Step 21 | loss:0.0030509368516504765 lr:8.4e-05 tokens_per_second_per_gpu:6805.189456766779 |
|
Step 22 | loss:0.00804334506392479 lr:8.800000000000001e-05 tokens_per_second_per_gpu:7069.793757152901 |
|
Step 23 | loss:0.003392538521438837 lr:9.200000000000001e-05 tokens_per_second_per_gpu:6836.617304348815 |
|
Step 24 | loss:0.0021571789402514696 lr:9.6e-05 tokens_per_second_per_gpu:6766.132565380621 |
|
Step 25 | loss:0.0030511049553751945 lr:0.0001 tokens_per_second_per_gpu:6778.980036945585 |
|
Step 26 | loss:0.006041023414582014 lr:9.999512620046522e-05 tokens_per_second_per_gpu:6937.8041427283015 |
|
Step 27 | loss:0.0059476569294929504 lr:9.998050575201771e-05 tokens_per_second_per_gpu:6505.623481762069 |
|
Step 28 | loss:0.005402639042586088 lr:9.995614150494293e-05 tokens_per_second_per_gpu:7043.925655167204 |
|
Step 29 | loss:0.005851719994097948 lr:9.992203820909906e-05 tokens_per_second_per_gpu:3346.9873526000856 |
|
Step 30 | loss:0.0020611840300261974 lr:9.987820251299122e-05 tokens_per_second_per_gpu:6830.3186216681825 |
|
Step 31 | loss:0.0037254351191222668 lr:9.982464296247522e-05 tokens_per_second_per_gpu:6925.960355958691 |
|
Step 32 | loss:0.0023793913424015045 lr:9.976136999909156e-05 tokens_per_second_per_gpu:6839.809402276852 |
|
Step 33 | loss:0.003644440555945039 lr:9.968839595802982e-05 tokens_per_second_per_gpu:4677.784518884225 |
|
Step 34 | loss:0.0015612317947670817 lr:9.96057350657239e-05 tokens_per_second_per_gpu:6737.955977517824 |
|
Step 35 | loss:0.0035902569070458412 lr:9.951340343707852e-05 tokens_per_second_per_gpu:6856.4531858965265 |
|
Step 36 | loss:0.0032603067811578512 lr:9.941141907232765e-05 tokens_per_second_per_gpu:6810.5289537738745 |
|
Step 37 | loss:0.003907656762748957 lr:9.929980185352526e-05 tokens_per_second_per_gpu:7054.548892382373 |
|
Step 38 | loss:0.0011479186359792948 lr:9.917857354066931e-05 tokens_per_second_per_gpu:6799.882482842793 |
|
Step 39 | loss:0.005801335908472538 lr:9.904775776745958e-05 tokens_per_second_per_gpu:7075.814535317771 |
|
Step 40 | loss:0.0031425445340573788 lr:9.890738003669029e-05 tokens_per_second_per_gpu:7034.364400477758 |
|
Step 41 | loss:0.0025631876196712255 lr:9.875746771527816e-05 tokens_per_second_per_gpu:6793.955462066984 |
|
Step 42 | loss:0.001818945980630815 lr:9.859805002892732e-05 tokens_per_second_per_gpu:6905.6879619222145 |
|
Step 43 | loss:0.004916809033602476 lr:9.842915805643155e-05 tokens_per_second_per_gpu:6934.969671944544 |
|
Step 44 | loss:0.02129308320581913 lr:9.825082472361557e-05 tokens_per_second_per_gpu:6855.163517028159 |
|
Step 45 | loss:0.0223652645945549 lr:9.806308479691595e-05 tokens_per_second_per_gpu:7096.430714609596 |
|
Step 46 | loss:0.002566624665632844 lr:9.786597487660337e-05 tokens_per_second_per_gpu:6838.96004185691 |
|
Step 47 | loss:0.0028638732619583607 lr:9.765953338964735e-05 tokens_per_second_per_gpu:6808.621479851141 |
|
Step 48 | loss:0.0011649236548691988 lr:9.744380058222483e-05 tokens_per_second_per_gpu:6894.453426767675 |
|
Step 49 | loss:0.018686098977923393 lr:9.721881851187406e-05 tokens_per_second_per_gpu:7133.293399589013 |
|
Step 50 | loss:0.003414908656850457 lr:9.698463103929542e-05 tokens_per_second_per_gpu:7046.301558692089 |
|
Step 51 | loss:0.013546042144298553 lr:9.674128381980072e-05 tokens_per_second_per_gpu:7042.4875394006 |
|
Step 52 | loss:0.002427030121907592 lr:9.648882429441257e-05 tokens_per_second_per_gpu:6794.84895780147 |
|
Step 53 | loss:0.0018121228786185384 lr:9.622730168061567e-05 tokens_per_second_per_gpu:6938.909780768277 |
|
Step 54 | loss:0.0024043091107159853 lr:9.595676696276172e-05 tokens_per_second_per_gpu:7058.786650613044 |
|
Step 55 | loss:0.0004099662182852626 lr:9.567727288213005e-05 tokens_per_second_per_gpu:6782.433544703813 |
|
Step 56 | loss:0.0035382509231567383 lr:9.538887392664544e-05 tokens_per_second_per_gpu:6340.576769430522 |
|
Step 57 | loss:0.0026507212314754725 lr:9.50916263202557e-05 tokens_per_second_per_gpu:7129.957745497268 |
|
Step 58 | loss:0.0014208294451236725 lr:9.478558801197065e-05 tokens_per_second_per_gpu:6951.299428853478 |
|
Step 59 | loss:0.013981368392705917 lr:9.447081866456489e-05 tokens_per_second_per_gpu:7071.6907771911765 |
|
Step 60 | loss:0.003813214600086212 lr:9.414737964294636e-05 tokens_per_second_per_gpu:7104.69149462406 |
|
Step 61 | loss:0.0021942683961242437 lr:9.381533400219318e-05 tokens_per_second_per_gpu:6948.905083627324 |
|
Step 62 | loss:0.000814873434137553 lr:9.347474647526095e-05 tokens_per_second_per_gpu:6853.1087155786445 |
|
Step 63 | loss:0.0035422611981630325 lr:9.312568346036288e-05 tokens_per_second_per_gpu:7080.4084352494 |
|
Step 64 | loss:0.0011617210693657398 lr:9.276821300802534e-05 tokens_per_second_per_gpu:6883.420349062332 |
|
Step 65 | loss:0.0025042295455932617 lr:9.24024048078213e-05 tokens_per_second_per_gpu:7075.091915582967 |
|
Step 66 | loss:0.004087530542165041 lr:9.202833017478422e-05 tokens_per_second_per_gpu:6823.599166612906 |
|
Step 67 | loss:0.003984375856816769 lr:9.164606203550497e-05 tokens_per_second_per_gpu:6792.725634094935 |
|
Step 68 | loss:0.004546380136162043 lr:9.125567491391476e-05 tokens_per_second_per_gpu:7089.574978639151 |
|
Step 69 | loss:0.0024830603506416082 lr:9.085724491675642e-05 tokens_per_second_per_gpu:6837.292820955085 |
|
Step 70 | loss:0.0029061806853860617 lr:9.045084971874738e-05 tokens_per_second_per_gpu:6827.2410775373755 |
|
Step 71 | loss:0.0034427084028720856 lr:9.003656854743667e-05 tokens_per_second_per_gpu:6864.66198527211 |
|
Step 72 | loss:0.001464420696720481 lr:8.961448216775954e-05 tokens_per_second_per_gpu:6822.178329585212 |
|
Step 73 | loss:0.002612335840240121 lr:8.9184672866292e-05 tokens_per_second_per_gpu:6838.830248369909 |
|
Step 74 | loss:0.0045876093208789825 lr:8.874722443520899e-05 tokens_per_second_per_gpu:7056.158575948568 |
|
Step 75 | loss:0.002774039749056101 lr:8.83022221559489e-05 tokens_per_second_per_gpu:6802.963020641426 |
|
Step 76 | loss:0.002137867035344243 lr:8.784975278258783e-05 tokens_per_second_per_gpu:6817.5861010485 |
|
Step 77 | loss:0.002842382062226534 lr:8.73899045249266e-05 tokens_per_second_per_gpu:6785.7430365621685 |
|
Step 78 | loss:0.002142858225852251 lr:8.692276703129421e-05 tokens_per_second_per_gpu:6804.014333258267 |
|
Step 79 | loss:0.0015875640092417598 lr:8.644843137107059e-05 tokens_per_second_per_gpu:6724.91936376274 |
|
Step 80 | loss:0.0018124596681445837 lr:8.596699001693255e-05 tokens_per_second_per_gpu:6846.558579000179 |
|
Step 81 | loss:0.00355800474062562 lr:8.547853682682604e-05 tokens_per_second_per_gpu:7075.9772933281865 |
|
Step 82 | loss:0.0021482682786881924 lr:8.498316702566828e-05 tokens_per_second_per_gpu:6868.955295302446 |
|
Step 83 | loss:0.0021761327516287565 lr:8.44809771867835e-05 tokens_per_second_per_gpu:6751.233050487658 |
|
Step 84 | loss:0.001975941937416792 lr:8.397206521307584e-05 tokens_per_second_per_gpu:6761.111402996535 |
|
Step 85 | loss:0.0025848988443613052 lr:8.345653031794292e-05 tokens_per_second_per_gpu:6802.3682461658045 |
|
Step 86 | loss:0.004574115853756666 lr:8.293447300593402e-05 tokens_per_second_per_gpu:7113.086878800607 |
|
Step 87 | loss:0.007184212561696768 lr:8.240599505315655e-05 tokens_per_second_per_gpu:7069.960020819823 |
|
Step 88 | loss:0.002063318155705929 lr:8.18711994874345e-05 tokens_per_second_per_gpu:6721.899285472525 |
|
Step 89 | loss:0.0022942281793802977 lr:8.133019056822304e-05 tokens_per_second_per_gpu:6872.463710717629 |
|
Step 90 | loss:0.005228151101619005 lr:8.07830737662829e-05 tokens_per_second_per_gpu:7091.47543806555 |
|
Step 91 | loss:0.002778491470962763 lr:8.022995574311876e-05 tokens_per_second_per_gpu:6918.719198741909 |
|
Step 92 | loss:0.00034355948446318507 lr:7.967094433018508e-05 tokens_per_second_per_gpu:6767.886403882791 |
|
Step 93 | loss:0.0017243159236386418 lr:7.910614850786448e-05 tokens_per_second_per_gpu:6924.718945423088 |
|
Step 94 | loss:0.0015514715341851115 lr:7.85356783842216e-05 tokens_per_second_per_gpu:6741.568062307173 |
|
Step 95 | loss:0.00177426275331527 lr:7.795964517353735e-05 tokens_per_second_per_gpu:6826.294128026231 |
|
Step 96 | loss:0.0010320349829271436 lr:7.737816117462752e-05 tokens_per_second_per_gpu:6790.442234767555 |
|
Step 97 | loss:0.002792761428281665 lr:7.679133974894983e-05 tokens_per_second_per_gpu:6793.460903280145 |
|
Step 98 | loss:0.0012509945081546903 lr:7.619929529850397e-05 tokens_per_second_per_gpu:6748.048046446525 |
|
Step 99 | loss:0.0003892534878104925 lr:7.560214324352858e-05 tokens_per_second_per_gpu:6856.93868103825 |
|
Step 100 | loss:0.001663127215579152 lr:7.500000000000001e-05 tokens_per_second_per_gpu:6936.128233988353 |
|
Step 101 | loss:0.0029043490067124367 lr:7.439298295693665e-05 tokens_per_second_per_gpu:6888.205778313194 |
|
Step 102 | loss:0.0008506955346092582 lr:7.378121045351378e-05 tokens_per_second_per_gpu:6781.707978527126 |
|
Step 103 | loss:0.001238394994288683 lr:7.316480175599309e-05 tokens_per_second_per_gpu:6791.616479659178 |
|
Step 104 | loss:0.0013181371614336967 lr:7.254387703447154e-05 tokens_per_second_per_gpu:6771.346624293808 |
|
Step 105 | loss:0.0016408805968239903 lr:7.191855733945387e-05 tokens_per_second_per_gpu:6954.431686441531 |
|
Step 106 | loss:0.0009435561369173229 lr:7.128896457825364e-05 tokens_per_second_per_gpu:6755.779447471709 |
|
Step 107 | loss:0.0022064659278839827 lr:7.06552214912271e-05 tokens_per_second_per_gpu:6887.610212397179 |
|
Step 108 | loss:0.00030679383780807257 lr:7.001745162784477e-05 tokens_per_second_per_gpu:6949.994220774615 |
|
Step 109 | loss:0.0016244077123701572 lr:6.937577932260515e-05 tokens_per_second_per_gpu:6790.821867412899 |
|
Step 110 | loss:0.0016033818246796727 lr:6.873032967079561e-05 tokens_per_second_per_gpu:6756.3403573268215 |
|
Step 111 | loss:0.0005207827198319137 lr:6.808122850410461e-05 tokens_per_second_per_gpu:6799.655995077981 |
|
Step 112 | loss:0.0052481950260698795 lr:6.742860236609077e-05 tokens_per_second_per_gpu:7087.606787117775 |
|
Step 113 | loss:0.006328810937702656 lr:6.677257848751277e-05 tokens_per_second_per_gpu:6934.034005304637 |
|
Step 114 | loss:0.0011291435221210122 lr:6.611328476152557e-05 tokens_per_second_per_gpu:6871.8333951491195 |
|
Step 115 | loss:0.00048354084719903767 lr:6.545084971874738e-05 tokens_per_second_per_gpu:6780.266863755895 |
|
Step 116 | loss:0.00043865066254511476 lr:6.478540250220234e-05 tokens_per_second_per_gpu:6915.482403663006 |
|
Step 117 | loss:0.0021259665954858065 lr:6.411707284214384e-05 tokens_per_second_per_gpu:6816.025366953438 |
|
Step 118 | loss:0.008526140823960304 lr:6.344599103076329e-05 tokens_per_second_per_gpu:7075.479872722786 |
|
Step 119 | loss:0.0015032440423965454 lr:6.277228789678953e-05 tokens_per_second_per_gpu:6793.758984555935 |
|
Step 120 | loss:0.003990808967500925 lr:6.209609477998338e-05 tokens_per_second_per_gpu:7047.216593349506 |
|
Step 121 | loss:0.004816874396055937 lr:6.141754350553279e-05 tokens_per_second_per_gpu:6818.7207761915215 |
|
Step 122 | loss:0.00147228071000427 lr:6.073676635835317e-05 tokens_per_second_per_gpu:6814.826293721152 |
|
Step 123 | loss:0.0006123994244262576 lr:6.005389605729824e-05 tokens_per_second_per_gpu:6846.409181850501 |
|
Step 124 | loss:0.00288543407805264 lr:5.9369065729286245e-05 tokens_per_second_per_gpu:6908.781832888838 |
|
Step 125 | loss:0.0011689026141539216 lr:5.868240888334653e-05 tokens_per_second_per_gpu:7073.299779415434 |
|
Step 126 | loss:0.00034374496317468584 lr:5.799405938459175e-05 tokens_per_second_per_gpu:6807.663781246732 |
|
Step 127 | loss:0.00042975673568435013 lr:5.730415142812059e-05 tokens_per_second_per_gpu:6809.353222422066 |
|
Step 128 | loss:0.005754610989242792 lr:5.661281951285613e-05 tokens_per_second_per_gpu:7068.458683328511 |
|
Step 129 | loss:0.0002537728287279606 lr:5.5920198415325064e-05 tokens_per_second_per_gpu:6754.827923560454 |
|
Step 130 | loss:0.0005576722323894501 lr:5.522642316338268e-05 tokens_per_second_per_gpu:6788.842293043924 |
|
Step 131 | loss:0.004440902732312679 lr:5.453162900988902e-05 tokens_per_second_per_gpu:7048.482917691646 |
|
Step 132 | loss:0.0004139615339227021 lr:5.383595140634093e-05 tokens_per_second_per_gpu:6942.025881187428 |
|
Step 133 | loss:0.0024621011689305305 lr:5.313952597646568e-05 tokens_per_second_per_gpu:7043.749870494549 |
|
Step 134 | loss:0.0013672587228938937 lr:5.244248848978067e-05 tokens_per_second_per_gpu:6929.812635857822 |
|
Step 135 | loss:0.0027264454402029514 lr:5.174497483512506e-05 tokens_per_second_per_gpu:6835.052810061578 |
|
Step 136 | loss:0.0012849484337493777 lr:5.104712099416785e-05 tokens_per_second_per_gpu:7064.693295972902 |
|
Step 137 | loss:0.0008558609406463802 lr:5.034906301489808e-05 tokens_per_second_per_gpu:6747.508059166015 |
|
Step 138 | loss:0.00029380517662502825 lr:4.965093698510193e-05 tokens_per_second_per_gpu:6754.683125182554 |
|
Step 139 | loss:0.0007402076153084636 lr:4.895287900583216e-05 tokens_per_second_per_gpu:6845.057294076618 |
|
Step 140 | loss:0.0002960671845357865 lr:4.825502516487497e-05 tokens_per_second_per_gpu:6748.741245167262 |
|
Step 141 | loss:0.000997895491309464 lr:4.755751151021934e-05 tokens_per_second_per_gpu:6942.016348126688 |
|
Step 142 | loss:0.0009276614873670042 lr:4.6860474023534335e-05 tokens_per_second_per_gpu:6767.839635599327 |
|
Step 143 | loss:0.0004551708116196096 lr:4.616404859365907e-05 tokens_per_second_per_gpu:6888.172090585795 |
|
Step 144 | loss:0.0005538578261621296 lr:4.5468370990111006e-05 tokens_per_second_per_gpu:6768.255774804881 |
|
Step 145 | loss:0.0009637348703108728 lr:4.477357683661734e-05 tokens_per_second_per_gpu:6818.526926226486 |
|
Step 146 | loss:0.0027866477612406015 lr:4.407980158467495e-05 tokens_per_second_per_gpu:7056.942774868622 |
|
Step 147 | loss:0.002221394097432494 lr:4.3387180487143876e-05 tokens_per_second_per_gpu:6808.126183156505 |
|
Step 148 | loss:0.0017781126080080867 lr:4.269584857187943e-05 tokens_per_second_per_gpu:7079.1447666266 |
|
Step 149 | loss:0.002728288760408759 lr:4.2005940615408264e-05 tokens_per_second_per_gpu:7061.440566873951 |
|
Step 150 | loss:0.00043648516293615103 lr:4.131759111665349e-05 tokens_per_second_per_gpu:6838.369778287981 |
|
Step 151 | loss:0.005630104336887598 lr:4.063093427071376e-05 tokens_per_second_per_gpu:7121.344205876374 |
|
Step 152 | loss:0.001904865843243897 lr:3.9946103942701777e-05 tokens_per_second_per_gpu:6800.521178331733 |
|
Step 153 | loss:0.0029734631534665823 lr:3.926323364164684e-05 tokens_per_second_per_gpu:6822.838847173219 |
|
Step 154 | loss:0.0009773087222129107 lr:3.858245649446721e-05 tokens_per_second_per_gpu:6759.756627635941 |
|
Step 155 | loss:0.00153159792535007 lr:3.790390522001662e-05 tokens_per_second_per_gpu:7051.6791390615945 |
|
Step 156 | loss:0.0017198395216837525 lr:3.7227712103210486e-05 tokens_per_second_per_gpu:7066.022989144581 |
|
Step 157 | loss:0.0016727091278880835 lr:3.655400896923672e-05 tokens_per_second_per_gpu:6811.702307534606 |
|
Step 158 | loss:0.003214507596567273 lr:3.588292715785617e-05 tokens_per_second_per_gpu:6922.819964740895 |
|
Step 159 | loss:0.0010125575354322791 lr:3.5214597497797684e-05 tokens_per_second_per_gpu:7060.987353340303 |
|
Step 160 | loss:0.0010515168542042375 lr:3.4549150281252636e-05 tokens_per_second_per_gpu:6804.303949781229 |
|
Step 161 | loss:0.001024384517222643 lr:3.388671523847445e-05 tokens_per_second_per_gpu:6841.669938396447 |
|
Step 162 | loss:0.0018848608015105128 lr:3.322742151248725e-05 tokens_per_second_per_gpu:6751.846793117959 |
|
Step 163 | loss:0.0013347417116165161 lr:3.257139763390925e-05 tokens_per_second_per_gpu:7027.891719500398 |
|
Step 164 | loss:0.0006750918691977859 lr:3.1918771495895396e-05 tokens_per_second_per_gpu:6785.860509976884 |
|
Step 165 | loss:0.0011055140057578683 lr:3.12696703292044e-05 tokens_per_second_per_gpu:7077.9940436212155 |
|
Step 166 | loss:0.0007286557811312377 lr:3.062422067739485e-05 tokens_per_second_per_gpu:7043.7316350507 |
|
Step 167 | loss:0.0037401369772851467 lr:2.9982548372155263e-05 tokens_per_second_per_gpu:7083.24516489987 |
|
Step 168 | loss:0.0010677126701921225 lr:2.934477850877292e-05 tokens_per_second_per_gpu:6932.174790116868 |
|
Step 169 | loss:0.00019011566473636776 lr:2.8711035421746367e-05 tokens_per_second_per_gpu:6749.252022014583 |
|
Step 170 | loss:0.00033960933797061443 lr:2.8081442660546125e-05 tokens_per_second_per_gpu:6863.493168543277 |
|
Step 171 | loss:0.0015284103574231267 lr:2.7456122965528475e-05 tokens_per_second_per_gpu:6828.519459914139 |
|
Step 172 | loss:0.0036087161861360073 lr:2.6835198244006927e-05 tokens_per_second_per_gpu:7082.15377515148 |
|
Step 173 | loss:0.0005151398945599794 lr:2.6218789546486234e-05 tokens_per_second_per_gpu:6752.773445394205 |
|
Step 174 | loss:0.00032851702417247 lr:2.560701704306336e-05 tokens_per_second_per_gpu:6789.504094228726 |
|
Step 175 | loss:0.001663737464696169 lr:2.500000000000001e-05 tokens_per_second_per_gpu:6815.591288989559 |
|
Step 176 | loss:0.0011574072996154428 lr:2.4397856756471432e-05 tokens_per_second_per_gpu:6828.92087090997 |
|
Step 177 | loss:0.0018865606980398297 lr:2.3800704701496053e-05 tokens_per_second_per_gpu:7081.598663947833 |
|
Step 178 | loss:0.0011174243409186602 lr:2.3208660251050158e-05 tokens_per_second_per_gpu:7082.039230725635 |
|
Step 179 | loss:0.00067571533145383 lr:2.2621838825372493e-05 tokens_per_second_per_gpu:6798.832947386817 |
|
Step 180 | loss:0.00047556660138070583 lr:2.2040354826462668e-05 tokens_per_second_per_gpu:6924.668744916678 |
|
Step 181 | loss:0.00037496539880521595 lr:2.1464321615778422e-05 tokens_per_second_per_gpu:6800.830937853566 |
|
Step 182 | loss:0.0004152611654717475 lr:2.0893851492135537e-05 tokens_per_second_per_gpu:6947.978079695834 |
|
Step 183 | loss:0.0009621500503271818 lr:2.0329055669814934e-05 tokens_per_second_per_gpu:6783.273996315187 |
|
Step 184 | loss:0.0012321381364017725 lr:1.977004425688126e-05 tokens_per_second_per_gpu:6811.429980135828 |
|
Step 185 | loss:0.00025866113719530404 lr:1.9216926233717085e-05 tokens_per_second_per_gpu:6783.257337206322 |
|
Step 186 | loss:0.002340645994991064 lr:1.866980943177699e-05 tokens_per_second_per_gpu:7067.855191085557 |
|
Step 187 | loss:0.0013471072306856513 lr:1.8128800512565513e-05 tokens_per_second_per_gpu:7093.102910885423 |
|
Step 188 | loss:0.0012069465592503548 lr:1.7594004946843456e-05 tokens_per_second_per_gpu:6876.0927182988735 |
|
Step 189 | loss:0.001518066506832838 lr:1.7065526994065973e-05 tokens_per_second_per_gpu:6902.493203679121 |
|
Step 190 | loss:0.0015219164779409766 lr:1.6543469682057106e-05 tokens_per_second_per_gpu:6756.480865419263 |
|
Step 191 | loss:0.0019189255544915795 lr:1.602793478692419e-05 tokens_per_second_per_gpu:7088.821810042651 |
|
Step 192 | loss:0.0005621357704512775 lr:1.551902281321651e-05 tokens_per_second_per_gpu:6830.200919745289 |
|
Step 193 | loss:0.001488498062826693 lr:1.5016832974331724e-05 tokens_per_second_per_gpu:6753.454997326393 |
|
Step 194 | loss:0.0016284087905660272 lr:1.4521463173173965e-05 tokens_per_second_per_gpu:6869.125853864198 |
|
Step 195 | loss:0.002182665513828397 lr:1.4033009983067452e-05 tokens_per_second_per_gpu:6832.429235304975 |
|
Step 196 | loss:0.0011356642935425043 lr:1.3551568628929434e-05 tokens_per_second_per_gpu:6842.570545775131 |
|
Step 197 | loss:0.0014715568395331502 lr:1.3077232968705805e-05 tokens_per_second_per_gpu:7079.698799487813 |
|
Step 198 | loss:0.0011941406410187483 lr:1.2610095475073414e-05 tokens_per_second_per_gpu:6788.546335926008 |
|
Step 199 | loss:0.002553859492763877 lr:1.2150247217412186e-05 tokens_per_second_per_gpu:7072.1766037679445 |
|
Step 200 | loss:0.002418858464807272 lr:1.1697777844051105e-05 tokens_per_second_per_gpu:7070.26639598808 |
|
Step 201 | loss:0.00022807034838479012 lr:1.1252775564791024e-05 tokens_per_second_per_gpu:6755.340153978266 |
|
Step 202 | loss:0.0022267724853008986 lr:1.0815327133708015e-05 tokens_per_second_per_gpu:7076.30069714757 |
|
Step 203 | loss:0.0009444208699278533 lr:1.0385517832240471e-05 tokens_per_second_per_gpu:6897.970980091377 |
|
Step 204 | loss:0.0031882880721241236 lr:9.963431452563332e-06 tokens_per_second_per_gpu:7073.835945134803 |
|
Step 205 | loss:0.000676371215377003 lr:9.549150281252633e-06 tokens_per_second_per_gpu:7080.9184577339265 |
|
Step 206 | loss:0.0008925383444875479 lr:9.142755083243576e-06 tokens_per_second_per_gpu:6930.198401475367 |
|
Step 207 | loss:0.002081420738250017 lr:8.744325086085248e-06 tokens_per_second_per_gpu:6957.562423264895 |
|
Step 208 | loss:0.00026374580920673907 lr:8.353937964495029e-06 tokens_per_second_per_gpu:6745.388585455252 |
|
Step 209 | loss:0.001403855043463409 lr:7.971669825215788e-06 tokens_per_second_per_gpu:6765.415505030002 |
|
Step 210 | loss:0.0006239673239178956 lr:7.597595192178702e-06 tokens_per_second_per_gpu:6754.522948906783 |
|
Step 211 | loss:0.0012805211590602994 lr:7.2317869919746705e-06 tokens_per_second_per_gpu:6908.773129201858 |
|
Step 212 | loss:0.0016043313080444932 lr:6.874316539637127e-06 tokens_per_second_per_gpu:6819.215629540058 |
|
Step 213 | loss:0.00026408283156342804 lr:6.52525352473905e-06 tokens_per_second_per_gpu:6856.267463665356 |
|
Step 214 | loss:0.0010434025898575783 lr:6.184665997806832e-06 tokens_per_second_per_gpu:6752.933544010319 |
|
Step 215 | loss:0.0016748131019994617 lr:5.852620357053651e-06 tokens_per_second_per_gpu:7069.560336048503 |
|
Step 216 | loss:0.0002644062624312937 lr:5.529181335435124e-06 tokens_per_second_per_gpu:6783.721789910482 |
|
Step 217 | loss:0.0012606634991243482 lr:5.214411988029355e-06 tokens_per_second_per_gpu:6788.511260014302 |
|
Step 218 | loss:0.0011555441888049245 lr:4.908373679744316e-06 tokens_per_second_per_gpu:6812.071941439878 |
|
Step 219 | loss:0.0010011408012360334 lr:4.611126073354571e-06 tokens_per_second_per_gpu:6790.057154106953 |
|
Step 220 | loss:0.001161118852905929 lr:4.322727117869951e-06 tokens_per_second_per_gpu:6838.034017608517 |
|
Step 221 | loss:0.0008470311295241117 lr:4.043233037238281e-06 tokens_per_second_per_gpu:6739.783261886782 |
|
Step 222 | loss:0.0003358850080985576 lr:3.772698319384349e-06 tokens_per_second_per_gpu:6810.188296253875 |
|
Step 223 | loss:0.0017017056234180927 lr:3.511175705587433e-06 tokens_per_second_per_gpu:7134.196991419764 |
|
Step 224 | loss:0.00045213307021185756 lr:3.258716180199278e-06 tokens_per_second_per_gpu:6820.160351750362 |
|
Step 225 | loss:0.0012671389849856496 lr:3.0153689607045845e-06 tokens_per_second_per_gpu:6791.659265496022 |
|
Step 226 | loss:0.0012812168570235372 lr:2.7811814881259503e-06 tokens_per_second_per_gpu:6810.583773959078 |
|
Step 227 | loss:0.0007159471279010177 lr:2.5561994177751737e-06 tokens_per_second_per_gpu:6743.998299794295 |
|
Step 228 | loss:0.0021349831949919462 lr:2.340466610352654e-06 tokens_per_second_per_gpu:7066.600262207837 |
|
Step 229 | loss:0.00030012783827260137 lr:2.134025123396638e-06 tokens_per_second_per_gpu:6814.5203125288635 |
|
Step 230 | loss:0.00024607600062154233 lr:1.9369152030840556e-06 tokens_per_second_per_gpu:6785.876556055032 |
|
Step 231 | loss:0.0006418603588826954 lr:1.7491752763844293e-06 tokens_per_second_per_gpu:7075.07446026204 |
|
Step 232 | loss:0.00033673577127046883 lr:1.5708419435684462e-06 tokens_per_second_per_gpu:6945.267938724145 |
|
Step 233 | loss:0.00025602109963074327 lr:1.4019499710726913e-06 tokens_per_second_per_gpu:6790.554445807879 |
|
Step 234 | loss:0.00047656253445893526 lr:1.2425322847218368e-06 tokens_per_second_per_gpu:6771.395451788634 |
|
Step 235 | loss:0.00046232191380113363 lr:1.0926199633097157e-06 tokens_per_second_per_gpu:6758.807390887128 |
|
Step 236 | loss:0.0018393310019746423 lr:9.522422325404235e-07 tokens_per_second_per_gpu:6817.929599404819 |
|
Step 237 | loss:0.0011434406042099 lr:8.214264593307098e-07 tokens_per_second_per_gpu:6823.818443994626 |
|
Step 238 | loss:0.0012595762964338064 lr:7.001981464747565e-07 tokens_per_second_per_gpu:6804.744850083202 |
|
Step 239 | loss:0.0027921022847294807 lr:5.885809276723608e-07 tokens_per_second_per_gpu:7088.774800407417 |
|
Step 240 | loss:0.0010998341022059321 lr:4.865965629214819e-07 tokens_per_second_per_gpu:6783.880260917502 |
|
Step 241 | loss:0.0020137943793088198 lr:3.9426493427611177e-07 tokens_per_second_per_gpu:7076.471847159209 |
|
Step 242 | loss:0.0006402755388990045 lr:3.1160404197018154e-07 tokens_per_second_per_gpu:7070.256800749601 |
|
Step 243 | loss:0.0020476654171943665 lr:2.386300009084408e-07 tokens_per_second_per_gpu:6931.143869152546 |
|
Step 244 | loss:0.0016461233608424664 lr:1.753570375247815e-07 tokens_per_second_per_gpu:6873.38200128151 |
|
Step 245 | loss:0.0015378650277853012 lr:1.2179748700879012e-07 tokens_per_second_per_gpu:6931.3903853247375 |
|
Step 246 | loss:0.0012600197223946452 lr:7.796179090094891e-08 tokens_per_second_per_gpu:6836.136965216229 |
|
Step 247 | loss:0.0010782753815874457 lr:4.385849505708084e-08 tokens_per_second_per_gpu:6771.003891387363 |
|
Step 248 | loss:0.0006726465653628111 lr:1.949424798228239e-08 tokens_per_second_per_gpu:7068.659410114673 |
|
Step 249 | loss:0.0013102944940328598 lr:4.873799534788059e-09 tokens_per_second_per_gpu:7036.706840644525 |
|
Step 250 | loss:0.0007836272125132382 lr:0.0 tokens_per_second_per_gpu:6834.360445101376 |
|
|