4.7 KiB
4.7 KiB
| 1 | step | train/loss | train/grad_norm | train/learning_rate | train/epoch | train/train_runtime | train/train_samples_per_second | train/train_steps_per_second | train/total_flos | train/train_loss |
|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 2 | 1.1491999626159668 | 0.6218180060386658 | 1.9999999949504854e-06 | 0.0004617871018126607 | |||||
| 3 | 4 | 1.0981999635696411 | 0.6825665235519409 | 3.999999989900971e-06 | 0.0009235742036253214 | |||||
| 4 | 6 | 1.1269999742507935 | 0.7838642001152039 | 6.000000212225132e-06 | 0.001385361305437982 | |||||
| 5 | 8 | 1.0542000532150269 | 0.8744276762008667 | 7.999999979801942e-06 | 0.0018471484072506428 | |||||
| 6 | 10 | 1.2441999912261963 | 0.7064258456230164 | 9.999999747378752e-06 | 0.0023089356254786253 | |||||
| 7 | 12 | 1.2927000522613525 | 0.6829814910888672 | 1.2000000424450263e-05 | 0.002770722610875964 | |||||
| 8 | 14 | 1.0844999551773071 | 0.5265647172927856 | 1.4000000192027073e-05 | 0.0032325098291039467 | |||||
| 9 | 16 | 1.0963000059127808 | 0.4373657703399658 | 1.5999999959603883e-05 | 0.0036942968145012856 | |||||
| 10 | 18 | 1.0615999698638916 | 0.46220508217811584 | 1.8000000636675395e-05 | 0.004156084265559912 | |||||
| 11 | 20 | 1.3325999975204468 | 0.7157824039459229 | 1.9999999494757503e-05 | 0.004617871250957251 | |||||
| 12 | 22 | 1.2070000171661377 | 0.5933427214622498 | 1.996917308133561e-05 | 0.0050796582363545895 | |||||
| 13 | 24 | 1.2044999599456787 | 0.5816172957420349 | 1.9876883015967906e-05 | 0.005541445221751928 | |||||
| 14 | 26 | 1.0740000009536743 | 0.4489712119102478 | 1.9723698642337695e-05 | 0.0060032326728105545 | |||||
| 15 | 28 | 1.1164000034332275 | 0.3696516752243042 | 1.9510565834934823e-05 | 0.006465019658207893 | |||||
| 16 | 30 | 1.045199990272522 | 0.4376335144042969 | 1.9238796085119247e-05 | 0.006926806643605232 | |||||
| 17 | 32 | 1.1247999668121338 | 0.4589230716228485 | 1.8910064682131633e-05 | 0.007388593629002571 | |||||
| 18 | 34 | 1.0688999891281128 | 0.3879022002220154 | 1.8526401618146338e-05 | 0.00785038061439991 | |||||
| 19 | 36 | 1.0292999744415283 | 0.4027869403362274 | 1.8090169760398567e-05 | 0.008312168531119823 | |||||
| 20 | 38 | 1.1052000522613525 | 0.37394437193870544 | 1.7604059394216165e-05 | 0.008773955516517162 | |||||
| 21 | 40 | 1.1557999849319458 | 0.3808683753013611 | 1.7071068214136176e-05 | 0.009235742501914501 | |||||
| 22 | 42 | 1.0232000350952148 | 0.4252733886241913 | 1.6494481315021403e-05 | 0.00969752948731184 | |||||
| 23 | 44 | 1.0364999771118164 | 0.48068660497665405 | 1.5877853002166376e-05 | 0.010159316472709179 | |||||
| 24 | 46 | 1.1340999603271484 | 0.37313926219940186 | 1.5224985872919206e-05 | 0.010621103458106518 | |||||
| 25 | 48 | 1.0866999626159668 | 0.4175492823123932 | 1.453990535082994e-05 | 0.011082890443503857 | |||||
| 26 | 50 | 1.1039999723434448 | 0.35443660616874695 | 1.3826834219798911e-05 | 0.01154467836022377 | |||||
| 27 | 52 | 1.1480000019073486 | 0.39232146739959717 | 1.3090169886709191e-05 | 0.012006465345621109 | |||||
| 28 | 54 | 1.1861000061035156 | 0.396918922662735 | 1.2334453458606731e-05 | 0.012468252331018448 | |||||
| 29 | 56 | 1.0096999406814575 | 0.3885609209537506 | 1.1564344276848715e-05 | 0.012930039316415787 | |||||
| 30 | 58 | 1.114799976348877 | 0.4421806335449219 | 1.0784590813273098e-05 | 0.013391826301813126 | |||||
| 31 | 60 | 1.0795999765396118 | 0.36081990599632263 | 9.999999747378752e-06 | 0.013853613287210464 | |||||
| 32 | 62 | 1.1764999628067017 | 0.4062329828739166 | 9.215408681484405e-06 | 0.014315400272607803 | |||||
| 33 | 64 | 1.107200026512146 | 0.39982733130455017 | 8.435655217908788e-06 | 0.014777187258005142 | |||||
| 34 | 66 | 1.1868000030517578 | 0.4688170254230499 | 7.665546036150772e-06 | 0.015238975174725056 | |||||
| 35 | 68 | 1.0312999486923218 | 0.3301626741886139 | 6.909830062795663e-06 | 0.01570076122879982 | |||||
| 36 | 70 | 1.1089999675750732 | 0.3377252221107483 | 6.173165729705943e-06 | 0.01616254821419716 | |||||
| 37 | 72 | 1.0716999769210815 | 0.39666977524757385 | 5.460095053422265e-06 | 0.016624337062239647 | |||||
| 38 | 74 | 1.1461999416351318 | 0.4125552177429199 | 4.7750145313329995e-06 | 0.017086124047636986 | |||||
| 39 | 76 | 1.042199969291687 | 0.3825180232524872 | 4.1221474020858295e-06 | 0.017547911033034325 | |||||
| 40 | 78 | 0.9157000184059143 | 0.4063441753387451 | 3.505519543978153e-06 | 0.018009698018431664 | |||||
| 41 | 80 | 1.1110999584197998 | 0.35289037227630615 | 2.9289321901160292e-06 | 0.018471485003829002 | |||||
| 42 | 82 | 1.167199969291687 | 0.33720290660858154 | 2.3959403279150138e-06 | 0.01893327198922634 | |||||
| 43 | 84 | 1.2375999689102173 | 0.38099613785743713 | 1.909829961732612e-06 | 0.01939505897462368 | |||||
| 44 | 86 | 1.2151999473571777 | 0.3848689794540405 | 1.4735983313585166e-06 | 0.01985684596002102 | |||||
| 45 | 88 | 1.1628999710083008 | 0.40408074855804443 | 1.0899348126258701e-06 | 0.020318632945418358 | |||||
| 46 | 90 | 1.1884000301361084 | 0.4015007019042969 | 7.612046601934708e-07 | 0.020780419930815697 | |||||
| 47 | 92 | 1.152500033378601 | 0.38306349515914917 | 4.894348535344761e-07 | 0.021242206916213036 | |||||
| 48 | 94 | 1.154099941253662 | 0.45273807644844055 | 2.7630079557638965e-07 | 0.021703993901610374 | |||||
| 49 | 96 | 1.0618000030517578 | 0.35036078095436096 | 1.2311659247643547e-07 | 0.022165780887007713 | |||||
| 50 | 98 | 1.0270999670028687 | 0.40208569169044495 | 3.0826662111849146e-08 | 0.022627567872405052 | |||||
| 51 | 100 | 1.0285999774932861 | 0.38247284293174744 | 0.0 | 0.02308935672044754 | 728.7083129882812 | 2.196000099182129 | 0.13699999451637268 | 1862467846144.0 | 1.117748498916626 |