9.0 KiB
9.0 KiB
| 1 | training_steps | training_tokens | training_loss | walltime | gputime | learning_rate |
|---|---|---|---|---|---|---|
| 2 | 91 | 381681664 | 1.705876648426056 | 349.417592048645 | 178901.80712890625 | 1.0371736607339699e-05 |
| 3 | 216 | 905969664 | 1.3897495508193969 | 832.8181312084198 | 426402.88317871094 | 2.2908907340024598e-05 |
| 4 | 341 | 1430257664 | 1.3739526987075805 | 1318.5057065486908 | 675074.9217529297 | 2.2900934709468856e-05 |
| 5 | 466 | 1954545664 | 1.3832926273345947 | 1805.5603597164154 | 924446.9041748047 | 2.2880112737766467e-05 |
| 6 | 591 | 2478833664 | 1.3864504384994507 | 2294.4699738025665 | 1174768.626586914 | 2.2846465071779676e-05 |
| 7 | 716 | 3003121664 | 1.3858818292617798 | 2784.9419543743134 | 1425890.2806396484 | 2.2800028091296554e-05 |
| 8 | 841 | 3527409664 | 1.3914724779129028 | 3264.606221675873 | 1671478.3854980469 | 2.2740854547009803e-05 |
| 9 | 966 | 4051697664 | 1.3931560230255127 | 3746.0561714172363 | 1917980.759765625 | 2.2669011741527356e-05 |
| 10 | 1091 | 4575985664 | 1.3886774349212647 | 4224.053797483444 | 2162715.5443115234 | 2.2584577891393565e-05 |
| 11 | 1216 | 5100273664 | 1.382537717819214 | 4707.173058748245 | 2410072.6060791016 | 2.248765122203622e-05 |
| 12 | 1341 | 5624561664 | 1.3739740705490113 | 5187.4164662361145 | 2655957.2307128906 | 2.237833723484073e-05 |
| 13 | 1466 | 6148849664 | 1.3830442571640014 | 5670.519166946411 | 2903305.8134765625 | 2.2256761440075934e-05 |
| 14 | 1591 | 6673137664 | 1.3852701997756958 | 6152.999006271362 | 3150335.4912109375 | 2.21230584429577e-05 |
| 15 | 1716 | 7197425664 | 1.386291127204895 | 6642.058992147446 | 3400734.203979492 | 2.197737921960652e-05 |
| 16 | 1841 | 7721713664 | 1.3890380668640137 | 7120.562220573425 | 3645727.8569335938 | 2.181988747906871e-05 |
| 17 | 1966 | 8246001664 | 1.3930994033813477 | 7602.080244779587 | 3892265.0853271484 | 2.1650757844327018e-05 |
| 18 | 2091 | 8770289664 | 1.3860662460327149 | 8087.039831638336 | 4140564.393798828 | 2.1470183128258213e-05 |
| 19 | 2216 | 9294577664 | 1.3901223468780517 | 8576.771399736404 | 4391306.956665039 | 2.1278365238686092e-05 |
| 20 | 2341 | 9818865664 | 1.3740155982971192 | 9059.70199084282 | 4638567.419311523 | 2.1075518816360272e-05 |
| 21 | 2466 | 10343153664 | 1.3859577751159669 | 9559.923065662384 | 4894680.609619141 | 2.0861871234956197e-05 |
| 22 | 2591 | 10867441664 | 1.3812617683410644 | 10046.367039442062 | 5143739.924194336 | 2.063766442006454e-05 |
| 23 | 2716 | 11391729664 | 1.3804499912261963 | 10535.779034852982 | 5394318.865844727 | 2.0403147573233582e-05 |
| 24 | 2841 | 11916017664 | 1.384134612083435 | 11017.524654626846 | 5640972.623168945 | 2.015858444792684e-05 |
| 25 | 2966 | 12440305664 | 1.397765965461731 | 11485.786287546158 | 5880722.579223633 | 1.9904251530533656e-05 |
| 26 | 3091 | 12964593664 | 1.388447904586792 | 11955.793720245361 | 6121366.384765625 | 1.964043258340098e-05 |
| 27 | 3216 | 13488881664 | 1.3898451328277588 | 12451.093034505844 | 6374959.633666992 | 1.936742410180159e-05 |
| 28 | 3341 | 14013169664 | 1.3765104770660401 | 12931.488008260727 | 6620921.860229492 | 1.908553167595528e-05 |
| 29 | 3466 | 14537457664 | 1.3819945049285889 | 13421.37786245346 | 6871745.465576172 | 1.8795073629007675e-05 |
| 30 | 3591 | 15061745664 | 1.3872785711288451 | 13903.579456567764 | 7118632.681762695 | 1.8496373741072603e-05 |
| 31 | 3716 | 15586033664 | 1.3836394453048706 | 14392.38246178627 | 7368899.82043457 | 1.8189770344179124e-05 |
| 32 | 3841 | 16110321664 | 1.3756385660171508 | 14880.113869667053 | 7618618.301269531 | 1.7875605408335105e-05 |
| 33 | 3966 | 16634609664 | 1.3765320539474488 | 15363.77294754982 | 7866251.749145508 | 1.7554231817484833e-05 |
| 34 | 4091 | 17158897664 | 1.3764560317993164 | 15841.730751752853 | 8110966.144897461 | 1.7226009731530212e-05 |
| 35 | 4216 | 17683185664 | 1.382050995826721 | 16318.189003229141 | 8354912.76965332 | 1.6891310224309564e-05 |
| 36 | 4341 | 18207473664 | 1.3691874313354493 | 16799.251779079437 | 8601216.910888672 | 1.6550506188650616e-05 |
| 37 | 4466 | 18731761664 | 1.373625202178955 | 17280.20972585678 | 8847467.379638672 | 1.620398325030692e-05 |
| 38 | 4591 | 19256049664 | 1.3770133256912231 | 17751.82107067108 | 9088932.388183594 | 1.5852127035032026e-05 |
| 39 | 4716 | 19780337664 | 1.373738374710083 | 18241.69244503975 | 9339746.531860352 | 1.549533408251591e-05 |
| 40 | 4841 | 20304625664 | 1.3801136875152589 | 18729.366693258286 | 9589435.746948242 | 1.5134005479922052e-05 |
| 41 | 4966 | 20828913664 | 1.3735867881774901 | 19202.151559352875 | 9831501.598388672 | 1.4768545952392742e-05 |
| 42 | 5091 | 21353201664 | 1.3708916187286377 | 19678.468351125717 | 10075375.795776367 | 1.4399365682038479e-05 |
| 43 | 5216 | 21877489664 | 1.3585072612762452 | 20166.363731384277 | 10325178.23046875 | 1.4026880307937972e-05 |
| 44 | 5341 | 22401777664 | 1.3708581686019898 | 20646.85131764412 | 10571187.874633789 | 1.3651506378664635e-05 |
| 45 | 5466 | 22926065664 | 1.3721266412734985 | 21129.20548892021 | 10818153.210327148 | 1.3273666809254792e-05 |
| 46 | 5591 | 23450353664 | 1.3749419021606446 | 21609.75633239746 | 11064195.2421875 | 1.2893784514744766e-05 |
| 47 | 5716 | 23974641664 | 1.3759718179702758 | 22099.91101717949 | 11315154.440795898 | 1.2512286957644392e-05 |
| 48 | 5841 | 24498929664 | 1.3701322412490844 | 22587.00215792656 | 11564545.104858398 | 1.2129601600463502e-05 |
| 49 | 5966 | 25023217664 | 1.3589839601516724 | 23068.37870335579 | 11811009.896118164 | 1.1746158634196036e-05 |
| 50 | 6091 | 25547505664 | 1.3674912643432617 | 23564.337091207504 | 12064940.590698242 | 1.136238824983593e-05 |
| 51 | 6216 | 26071793664 | 1.3616641139984131 | 24060.992257356644 | 12319228.035766602 | 1.0978721547871828e-05 |
| 52 | 6341 | 26596081664 | 1.3673647165298461 | 24553.457004785538 | 12571369.986450195 | 1.0595587809802964e-05 |
| 53 | 6466 | 27120369664 | 1.3683636331558227 | 25043.20528125763 | 12822121.104003906 | 1.0213419045612682e-05 |
| 54 | 6591 | 27644657664 | 1.3685188150405885 | 25522.376963853836 | 13067457.005493164 | 9.832643627305515e-06 |
| 55 | 6716 | 28168945664 | 1.3669057893753052 | 26007.466133594513 | 13315822.66040039 | 9.453689017391298e-06 |
| 56 | 6841 | 28693233664 | 1.3573708486557008 | 26490.140152931213 | 13562951.758300781 | 9.076979949895758e-06 |
| 57 | 6966 | 29217521664 | 1.3678750085830689 | 26974.407760858536 | 13810896.77355957 | 8.702940249349922e-06 |
| 58 | 7091 | 29741809664 | 1.3570352029800414 | 27459.788273334503 | 14059411.595947266 | 8.331989192811307e-06 |
| 59 | 7216 | 30266097664 | 1.362500047683716 | 27948.002388238907 | 14309377.22277832 | 7.964544238348026e-06 |
| 60 | 7341 | 30790385664 | 1.3568921756744385 | 28434.61261844635 | 14558521.660644531 | 7.60101602281793e-06 |
| 61 | 7466 | 31314673664 | 1.3600246238708495 | 28930.43299293518 | 14812381.692382812 | 7.241814273584168e-06 |
| 62 | 7591 | 31838961664 | 1.3630630922317506 | 29420.152116775513 | 15063117.883789062 | 6.887341442052275e-06 |
| 63 | 7716 | 32363249664 | 1.3645733547210694 | 29905.080822467804 | 15311401.381103516 | 6.537995886901626e-06 |
| 64 | 7841 | 32887537664 | 1.3608429622650147 | 30395.29596066475 | 15562391.531860352 | 6.194169600348687e-06 |
| 65 | 7966 | 33411825664 | 1.3538905429840087 | 30882.7067861557 | 15811945.874511719 | 5.856248662894359e-06 |
| 66 | 8091 | 33936113664 | 1.357135763168335 | 31372.948741674423 | 16062949.755737305 | 5.524611879081931e-06 |
| 67 | 8216 | 34460401664 | 1.356378779411316 | 31884.885987997055 | 16325061.625854492 | 5.19963214173913e-06 |
| 68 | 8341 | 34984689664 | 1.357187376022339 | 32370.82417345047 | 16573861.97680664 | 4.881674612988718e-06 |
| 69 | 8466 | 35508977664 | 1.35336323261261 | 32855.67463135719 | 16822105.411254883 | 4.571094905259088e-06 |
| 70 | 8591 | 36033265664 | 1.355205135345459 | 33346.159249305725 | 17073233.53564453 | 4.268243174010422e-06 |
| 71 | 8716 | 36557553664 | 1.358914623260498 | 33827.9269824028 | 17319898.614990234 | 3.9734582060191315e-06 |
| 72 | 8841 | 37081841664 | 1.362475266456604 | 34321.028290748596 | 17572366.48486328 | 3.6870717394776875e-06 |
| 73 | 8966 | 37606129664 | 1.3590269899368286 | 34796.32628655434 | 17815719.05871582 | 3.409404826015816e-06 |
| 74 | 9091 | 38130417664 | 1.3527347040176392 | 35277.81164979935 | 18062239.564697266 | 3.14076919494255e-06 |
| 75 | 9216 | 38654705664 | 1.3541545391082763 | 35762.953654289246 | 18310632.270996094 | 2.8814667984988773e-06 |
| 76 | 9341 | 39178993664 | 1.351501841545105 | 36248.5650036335 | 18559265.28186035 | 2.631788220242015e-06 |
| 77 | 9466 | 39703281664 | 1.35175705909729 | 36739.43635678291 | 18810591.41467285 | 2.3920142666611355e-06 |
| 78 | 9591 | 40227569664 | 1.3450146627426147 | 37227.1895442009 | 19060321.04663086 | 2.1624136934406124e-06 |
| 79 | 9716 | 40751857664 | 1.34777916431427 | 37715.7041785717 | 19310440.53942871 | 1.9432443423283985e-06 |
| 80 | 9841 | 41276145664 | 1.3524326610565185 | 38211.86196422577 | 19564473.325683594 | 1.734752345328161e-06 |
| 81 | 9966 | 41800433664 | 1.345165228843689 | 38683.90825486183 | 19806161.026489258 | 1.5371716699519311e-06 |
| 82 | 10091 | 42324721664 | 1.3548077869415283 | 39168.04429388046 | 20054038.678466797 | 1.3507242329069413e-06 |
| 83 | 10216 | 42849009664 | 1.3514936256408692 | 39660.411581754684 | 20306130.7298584 | 1.1756192179745995e-06 |
| 84 | 10341 | 43373297664 | 1.3460756397247315 | 40151.08649110794 | 20557356.283447266 | 1.0120531896973262e-06 |
| 85 | 10466 | 43897585664 | 1.3461112928390504 | 40633.303092479706 | 20804251.18334961 | 8.602099228482984e-07 |
| 86 | 10591 | 44421873664 | 1.3597946453094483 | 41123.430518865585 | 21055196.42565918 | 7.202597203104233e-07 |
| 87 | 10716 | 44946161664 | 1.3555755615234375 | 41606.695585012436 | 21302628.139526367 | 5.923597541368508e-07 |
| 88 | 10841 | 45470449664 | 1.3505602884292602 | 42100.69473004341 | 21555555.701782227 | 4.7665361080362345e-07 |
| 89 | 10966 | 45994737664 | 1.3511819410324097 | 42579.13560962677 | 21800517.432128906 | 3.732711491011287e-07 |
| 90 | 11091 | 46519025664 | 1.3547854137420654 | 43062.60950422287 | 22048056.06616211 | 2.8232847171238973e-07 |
| 91 | 11216 | 47043313664 | 1.3471012353897094 | 43556.501729249954 | 22300928.885375977 | 2.0392761257426173e-07 |
| 92 | 11341 | 47567601664 | 1.3546306133270263 | 44040.74517941475 | 22548861.53186035 | 1.3815662214256008e-07 |
| 93 | 11466 | 48091889664 | 1.347469425201416 | 44528.56511092186 | 22798625.336791992 | 8.50893187021029e-08 |
| 94 | 11591 | 48616177664 | 1.351351170539856 | 45005.3742287159 | 23042751.60510254 | 4.478528481399735e-08 |
| 95 | 11716 | 49140465664 | 1.3564130067825317 | 45486.778151750565 | 23289230.41369629 | 1.7289766063299794e-08 |
| 96 | 11841 | 49664753664 | 1.3507808351516724 | 45969.55499148369 | 23536412.15563965 | 2.6336253178271818e-09 |
| 97 | 11916 | 49979326464 | 1.3504765431086223 | 46256.48653841019 | 23683321.107666016 | 1.0287991812629738e-11 |