4.5 KiB
4.5 KiB
| 1 | training_steps | training_tokens | training_loss | walltime | gputime | learning_rate |
|---|---|---|---|---|---|---|
| 2 | 25 | 102400000 | 1.4206320714950562 | 0.26831979325136307 | 34.34493353617447 | 2.938559919130057e-05 |
| 3 | 50 | 204800000 | 1.3607354307174682 | 0.532874067107453 | 68.20788058975398 | 2.8771199140464887e-05 |
| 4 | 75 | 307200000 | 1.344892144203186 | 0.797669098578563 | 102.10164461805607 | 2.8156800908618607e-05 |
| 5 | 100 | 409600000 | 1.3339987087249756 | 1.0622922554949321 | 135.9734087033513 | 2.7542400857782923e-05 |
| 6 | 125 | 512000000 | 1.3272197246551514 | 1.3275567747589183 | 169.92726716914154 | 2.692800080694724e-05 |
| 7 | 150 | 614400000 | 1.3201901483535767 | 1.5918107887810053 | 203.75178096396868 | 2.6313600756111555e-05 |
| 8 | 175 | 716800000 | 1.3260539388656616 | 1.856745663885765 | 237.6634449773779 | 2.569920070527587e-05 |
| 9 | 200 | 819200000 | 1.3183754396438598 | 2.1223753731163395 | 271.66404775889146 | 2.5084800654440187e-05 |
| 10 | 225 | 921600000 | 1.3132305669784545 | 2.3882311399600185 | 305.69358591488236 | 2.4470400603604503e-05 |
| 11 | 250 | 1024000000 | 1.3129970407485962 | 2.65354331628931 | 339.65354448503166 | 2.385600055276882e-05 |
| 12 | 275 | 1126400000 | 1.3064435338973999 | 2.9190579786122703 | 373.6394212623706 | 2.3241600501933135e-05 |
| 13 | 300 | 1228800000 | 1.3097565698623657 | 3.1846308088092967 | 407.63274352759 | 2.262720045109745e-05 |
| 14 | 325 | 1331200000 | 1.2990926265716554 | 3.450655307807062 | 441.6838793993039 | 2.2012800400261767e-05 |
| 15 | 350 | 1433600000 | 1.3015284061431884 | 3.7156531358282527 | 475.60360138601635 | 2.1398400349426083e-05 |
| 16 | 375 | 1536000000 | 1.300846767425537 | 3.9803074113379786 | 509.47934865126126 | 2.07840002985904e-05 |
| 17 | 400 | 1638400000 | 1.2993078660964965 | 4.245298594229775 | 543.3982200614112 | 2.0169600247754715e-05 |
| 18 | 425 | 1740800000 | 1.2959114503860474 | 4.510613332994379 | 577.3585066232805 | 1.955520019691903e-05 |
| 19 | 450 | 1843200000 | 1.2931818628311158 | 4.775614008341895 | 611.2785930677626 | 1.8940800146083347e-05 |
| 20 | 475 | 1945600000 | 1.2935280084609986 | 5.040500104048112 | 645.1840133181583 | 1.8326400095247664e-05 |
| 21 | 500 | 2048000000 | 1.297581434249878 | 5.305721228775273 | 679.1323172832349 | 1.771200004441198e-05 |
| 22 | 525 | 2150400000 | 1.2973516607284545 | 5.571934178461597 | 713.2075748430844 | 1.7097599993576296e-05 |
| 23 | 550 | 2252800000 | 1.2920558738708496 | 5.836718603762894 | 747.0999812816505 | 1.6483199942740612e-05 |
| 24 | 575 | 2355200000 | 1.2921710443496703 | 6.101621121729093 | 781.0075035813239 | 1.5868799891904928e-05 |
| 25 | 600 | 2457600000 | 1.2922473382949828 | 6.3664986443806235 | 814.9118264807198 | 1.5254399841069244e-05 |
| 26 | 625 | 2560000000 | 1.286066074371338 | 6.632426781060178 | 848.9506279757028 | 1.463999979023356e-05 |
| 27 | 650 | 2662400000 | 1.2801355123519897 | 6.897544031576831 | 882.8856360418343 | 1.4025599739397876e-05 |
| 28 | 675 | 2764800000 | 1.2844274616241456 | 7.16281749378081 | 916.8406392039436 | 1.3411199688562192e-05 |
| 29 | 700 | 2867200000 | 1.2837993860244752 | 7.427888308341158 | 950.7697034676683 | 1.2796799637726508e-05 |
| 30 | 725 | 2969600000 | 1.277207851409912 | 7.694053462864512 | 984.8388432466576 | 1.2182399586890824e-05 |
| 31 | 750 | 3072000000 | 1.2725739479064941 | 7.9594902915458245 | 1018.8147573178655 | 1.1568000445549842e-05 |
| 32 | 775 | 3174400000 | 1.279445676803589 | 8.224737335718995 | 1052.7663789720314 | 1.0953600394714158e-05 |
| 33 | 800 | 3276800000 | 1.2785338878631591 | 8.4897940390995 | 1086.693637004736 | 1.0339200343878474e-05 |
| 34 | 825 | 3379200000 | 1.2763902473449706 | 8.754925038348853 | 1120.6304049086532 | 9.72480029304279e-06 |
| 35 | 850 | 3481600000 | 1.273976821899414 | 9.020435715932496 | 1154.6157716393595 | 9.110400242207106e-06 |
| 36 | 875 | 3584000000 | 1.2713893747329712 | 9.285925992178 | 1188.598526998784 | 8.496000191371422e-06 |
| 37 | 900 | 3686400000 | 1.2784578609466553 | 9.551624662507189 | 1222.6079568009202 | 7.881600140535738e-06 |
| 38 | 925 | 3788800000 | 1.2703066444396973 | 9.81712425603072 | 1256.5919047719321 | 7.267200089700054e-06 |
| 39 | 950 | 3891200000 | 1.271108751296997 | 10.082206830408738 | 1290.5224742923185 | 6.6528000388643704e-06 |
| 40 | 975 | 3993600000 | 1.2680458974838258 | 10.347317189690123 | 1324.4566002803358 | 6.0383999880286865e-06 |
| 41 | 1000 | 4096000000 | 1.2702019023895263 | 10.612797046162356 | 1358.4380219087816 | 5.4239999371930026e-06 |
| 42 | 1025 | 4198400000 | 1.2751475191116333 | 10.87931673718002 | 1392.5525423590425 | 4.809599886357319e-06 |
| 43 | 1050 | 4300800000 | 1.266355185508728 | 11.143856210205902 | 1426.4135949063555 | 4.195199835521635e-06 |
| 44 | 1075 | 4403200000 | 1.2681057167053222 | 11.408356219250548 | 1460.2695960640701 | 3.580800012059626e-06 |
| 45 | 1100 | 4505600000 | 1.271327452659607 | 11.672805533763803 | 1494.1191083217668 | 2.9663999612239422e-06 |
| 46 | 1125 | 4608000000 | 1.2650820541381835 | 11.938276334099923 | 1528.0993707647901 | 2.3519999103882583e-06 |
| 47 | 1150 | 4710400000 | 1.270536971092224 | 12.203680372205294 | 1562.0710876422777 | 1.737599973239412e-06 |
| 48 | 1175 | 4812800000 | 1.2631586408615112 | 12.468635068036095 | 1595.9852887086201 | 1.1232000360905658e-06 |
| 49 | 1200 | 4915200000 | 1.2647824430465697 | 12.734026105942206 | 1629.9553415606024 | 5.087999852548819e-07 |
| 50 | 1220 | 4997120000 | 1.2646446466445922 | 12.946103368596539 | 1657.101231180357 | 1.727999965339677e-08 |