ekinakyurek's picture
Upload folder using huggingface_hub
0bfc910 verified
raw
history blame
20.5 kB
Step 1 | loss:0.06137857958674431 lr:5.263157894736842e-06 tokens_per_second_per_gpu:2479.2557458453025
Step 2 | loss:0.06642866134643555 lr:1.0526315789473684e-05 tokens_per_second_per_gpu:7008.171015431836
Step 3 | loss:0.03752458468079567 lr:1.5789473684210526e-05 tokens_per_second_per_gpu:3877.6736262521918
Step 4 | loss:0.029267575591802597 lr:2.105263157894737e-05 tokens_per_second_per_gpu:7155.614108816863
Step 5 | loss:0.028851419687271118 lr:2.6315789473684212e-05 tokens_per_second_per_gpu:7148.743192805045
Step 6 | loss:0.04431711137294769 lr:3.157894736842105e-05 tokens_per_second_per_gpu:6955.270902339343
Step 7 | loss:0.0951983630657196 lr:3.6842105263157895e-05 tokens_per_second_per_gpu:1564.8232364176567
Step 8 | loss:0.037941981106996536 lr:4.210526315789474e-05 tokens_per_second_per_gpu:7004.341659352373
Step 9 | loss:0.062087491154670715 lr:4.736842105263158e-05 tokens_per_second_per_gpu:2437.2461262840743
Step 10 | loss:0.01989690586924553 lr:5.2631578947368424e-05 tokens_per_second_per_gpu:7074.205961736607
Step 11 | loss:0.07088522613048553 lr:5.789473684210527e-05 tokens_per_second_per_gpu:1513.8632441684401
Step 12 | loss:0.07305476069450378 lr:6.31578947368421e-05 tokens_per_second_per_gpu:6588.605375397182
Step 13 | loss:0.03919636458158493 lr:6.842105263157895e-05 tokens_per_second_per_gpu:3879.739349466213
Step 14 | loss:0.0720977857708931 lr:7.368421052631579e-05 tokens_per_second_per_gpu:1542.2516454819404
Step 15 | loss:0.031764183193445206 lr:7.894736842105263e-05 tokens_per_second_per_gpu:6963.814052263876
Step 16 | loss:0.06742829829454422 lr:8.421052631578948e-05 tokens_per_second_per_gpu:6607.16598212532
Step 17 | loss:0.04868115484714508 lr:8.947368421052632e-05 tokens_per_second_per_gpu:6584.838820866436
Step 18 | loss:0.017628151923418045 lr:9.473684210526316e-05 tokens_per_second_per_gpu:7177.563593212763
Step 19 | loss:0.020311690866947174 lr:0.0001 tokens_per_second_per_gpu:2590.6882749918486
Step 20 | loss:0.015545966103672981 lr:9.999175604498867e-05 tokens_per_second_per_gpu:2496.963378854733
Step 21 | loss:0.018341902643442154 lr:9.996702689846645e-05 tokens_per_second_per_gpu:7195.021016510377
Step 22 | loss:0.015196132473647594 lr:9.992582071507216e-05 tokens_per_second_per_gpu:7016.290339140367
Step 23 | loss:0.0612853467464447 lr:9.986815108288272e-05 tokens_per_second_per_gpu:6569.364232210876
Step 24 | loss:0.01929628849029541 lr:9.979403701893226e-05 tokens_per_second_per_gpu:2460.4669664872413
Step 25 | loss:0.019473399966955185 lr:9.970350296294113e-05 tokens_per_second_per_gpu:1499.8470508884607
Step 26 | loss:0.03200409188866615 lr:9.959657876925671e-05 tokens_per_second_per_gpu:7239.610178559596
Step 27 | loss:0.017302783206105232 lr:9.94732996970087e-05 tokens_per_second_per_gpu:5996.86153252467
Step 28 | loss:0.004033551551401615 lr:9.933370639848211e-05 tokens_per_second_per_gpu:7201.4367487232375
Step 29 | loss:0.01271115057170391 lr:9.917784490571187e-05 tokens_per_second_per_gpu:6855.521691211172
Step 30 | loss:0.00921716634184122 lr:9.900576661530335e-05 tokens_per_second_per_gpu:6907.611496708283
Step 31 | loss:0.007851222530007362 lr:9.88175282714839e-05 tokens_per_second_per_gpu:6982.739553363163
Step 32 | loss:0.005679881200194359 lr:9.861319194739109e-05 tokens_per_second_per_gpu:7209.017464479098
Step 33 | loss:0.0335458405315876 lr:9.83928250246034e-05 tokens_per_second_per_gpu:6536.725284462274
Step 34 | loss:0.002178790746256709 lr:9.815650017092077e-05 tokens_per_second_per_gpu:6927.960273976468
Step 35 | loss:0.005245713982731104 lr:9.790429531640161e-05 tokens_per_second_per_gpu:6872.199943870271
Step 36 | loss:0.009940961375832558 lr:9.763629362766496e-05 tokens_per_second_per_gpu:7136.483525740678
Step 37 | loss:0.01861240528523922 lr:9.735258348046536e-05 tokens_per_second_per_gpu:6547.181982388551
Step 38 | loss:0.009708410128951073 lr:9.705325843055045e-05 tokens_per_second_per_gpu:6576.529668345566
Step 39 | loss:0.0007537209312431514 lr:9.673841718280999e-05 tokens_per_second_per_gpu:7194.531527477346
Step 40 | loss:0.005907827988266945 lr:9.64081635587273e-05 tokens_per_second_per_gpu:7013.89910043468
Step 41 | loss:0.025580713525414467 lr:9.606260646214313e-05 tokens_per_second_per_gpu:6893.1454224529025
Step 42 | loss:0.009543796069920063 lr:9.570185984334383e-05 tokens_per_second_per_gpu:6837.158326101836
Step 43 | loss:0.005642628762871027 lr:9.53260426614852e-05 tokens_per_second_per_gpu:7112.090928102137
Step 44 | loss:0.01089418400079012 lr:9.493527884536486e-05 tokens_per_second_per_gpu:6898.010062084118
Step 45 | loss:0.003734344383701682 lr:9.452969725255558e-05 tokens_per_second_per_gpu:6982.935237304722
Step 46 | loss:0.00653404276818037 lr:9.410943162691359e-05 tokens_per_second_per_gpu:6999.90360278525
Step 47 | loss:0.007921351119875908 lr:9.367462055447528e-05 tokens_per_second_per_gpu:7058.223483871023
Step 48 | loss:0.0022041138727217913 lr:9.322540741775744e-05 tokens_per_second_per_gpu:7156.570505553709
Step 49 | loss:0.0019865743815898895 lr:9.276194034847566e-05 tokens_per_second_per_gpu:7191.5091405241765
Step 50 | loss:0.006164330057799816 lr:9.228437217869667e-05 tokens_per_second_per_gpu:6913.287158747746
Step 51 | loss:0.0021636197343468666 lr:9.179286039044073e-05 tokens_per_second_per_gpu:7193.336462476348
Step 52 | loss:0.0003868835046887398 lr:9.128756706375065e-05 tokens_per_second_per_gpu:7167.724296363764
Step 53 | loss:0.002843113150447607 lr:9.076865882324452e-05 tokens_per_second_per_gpu:6835.067091349924
Step 54 | loss:0.005795885343104601 lr:9.023630678316995e-05 tokens_per_second_per_gpu:1429.3565041671563
Step 55 | loss:0.002304018009454012 lr:8.969068649097766e-05 tokens_per_second_per_gpu:7148.733257444672
Step 56 | loss:0.000881826679687947 lr:8.913197786943336e-05 tokens_per_second_per_gpu:6239.948612608849
Step 57 | loss:0.008953557349741459 lr:8.856036515728666e-05 tokens_per_second_per_gpu:6568.32429598485
Step 58 | loss:0.0023659064900130033 lr:8.797603684851685e-05 tokens_per_second_per_gpu:7029.699243591673
Step 59 | loss:0.009606261737644672 lr:8.737918563017553e-05 tokens_per_second_per_gpu:875.7865507819542
Step 60 | loss:0.000325437547871843 lr:8.677000831884638e-05 tokens_per_second_per_gpu:7160.753009772704
Step 61 | loss:0.0009475620463490486 lr:8.614870579574337e-05 tokens_per_second_per_gpu:6537.545246055638
Step 62 | loss:0.0004457616596482694 lr:8.551548294046843e-05 tokens_per_second_per_gpu:7202.46535760003
Step 63 | loss:0.0017868372378870845 lr:8.487054856345081e-05 tokens_per_second_per_gpu:6978.817027795806
Step 64 | loss:0.002297638915479183 lr:8.421411533709009e-05 tokens_per_second_per_gpu:7026.679455370572
Step 65 | loss:0.005144163966178894 lr:8.35463997256257e-05 tokens_per_second_per_gpu:7159.458331842342
Step 66 | loss:0.005180073902010918 lr:8.28676219137561e-05 tokens_per_second_per_gpu:6886.117784708622
Step 67 | loss:0.017951397225260735 lr:8.217800573403105e-05 tokens_per_second_per_gpu:6998.800223677583
Step 68 | loss:0.003106670221313834 lr:8.147777859304096e-05 tokens_per_second_per_gpu:7192.151440026888
Step 69 | loss:0.0005834997864440084 lr:8.076717139642775e-05 tokens_per_second_per_gpu:7141.500819677652
Step 70 | loss:0.0006361087434925139 lr:8.004641847274181e-05 tokens_per_second_per_gpu:7123.0430533684475
Step 71 | loss:0.002692887792363763 lr:7.931575749617026e-05 tokens_per_second_per_gpu:6903.045040515296
Step 72 | loss:0.004022689536213875 lr:7.857542940816183e-05 tokens_per_second_per_gpu:7010.640730283293
Step 73 | loss:0.007148392964154482 lr:7.782567833797457e-05 tokens_per_second_per_gpu:6959.873030100997
Step 74 | loss:0.00052885920740664 lr:7.70667515221722e-05 tokens_per_second_per_gpu:2248.9850064000257
Step 75 | loss:0.006416045594960451 lr:7.629889922309577e-05 tokens_per_second_per_gpu:6551.106190335205
Step 76 | loss:0.013594008050858974 lr:7.552237464633761e-05 tokens_per_second_per_gpu:6572.749369183231
Step 77 | loss:0.0019993868190795183 lr:7.473743385724478e-05 tokens_per_second_per_gpu:7167.023410871366
Step 78 | loss:0.0037486106157302856 lr:7.394433569647934e-05 tokens_per_second_per_gpu:7208.792802301606
Step 79 | loss:0.004148067440837622 lr:7.31433416946636e-05 tokens_per_second_per_gpu:7148.342254973541
Step 80 | loss:0.002117311116307974 lr:7.233471598613815e-05 tokens_per_second_per_gpu:7188.488890880382
Step 81 | loss:0.0013821276370435953 lr:7.151872522186146e-05 tokens_per_second_per_gpu:7159.295892820142
Step 82 | loss:0.002174496417865157 lr:7.069563848147956e-05 tokens_per_second_per_gpu:7232.565560670028
Step 83 | loss:0.0018288022838532925 lr:6.986572718459479e-05 tokens_per_second_per_gpu:5941.173448989184
Step 84 | loss:4.641738996724598e-05 lr:6.902926500126292e-05 tokens_per_second_per_gpu:7109.766379234241
Step 85 | loss:0.0018767565488815308 lr:6.818652776174827e-05 tokens_per_second_per_gpu:1432.778854750476
Step 86 | loss:0.0003951110120397061 lr:6.733779336556642e-05 tokens_per_second_per_gpu:7171.230626922222
Step 87 | loss:5.442116889753379e-05 lr:6.648334168984452e-05 tokens_per_second_per_gpu:6988.30806070758
Step 88 | loss:0.0009744969429448247 lr:6.562345449702951e-05 tokens_per_second_per_gpu:6562.684053949671
Step 89 | loss:0.003042783122509718 lr:6.47584153419747e-05 tokens_per_second_per_gpu:7164.879416875312
Step 90 | loss:0.004840945824980736 lr:6.388850947843517e-05 tokens_per_second_per_gpu:6548.819781099054
Step 91 | loss:0.04257185012102127 lr:6.301402376500304e-05 tokens_per_second_per_gpu:6563.159952009452
Step 92 | loss:0.0003310129977762699 lr:6.213524657051353e-05 tokens_per_second_per_gpu:6931.409321505919
Step 93 | loss:0.0017436131602153182 lr:6.125246767895286e-05 tokens_per_second_per_gpu:7100.635671872784
Step 94 | loss:0.029420141130685806 lr:6.036597819389972e-05 tokens_per_second_per_gpu:892.7385802426592
Step 95 | loss:0.0012339272070676088 lr:5.947607044253142e-05 tokens_per_second_per_gpu:7197.489092409817
Step 96 | loss:0.0015628329711034894 lr:5.858303787922663e-05 tokens_per_second_per_gpu:7001.323551608363
Step 97 | loss:0.002540476154536009 lr:5.768717498879635e-05 tokens_per_second_per_gpu:7157.387851938877
Step 98 | loss:0.0030821363907307386 lr:5.67887771893752e-05 tokens_per_second_per_gpu:7118.1938180099
Step 99 | loss:0.003468114882707596 lr:5.5888140735004804e-05 tokens_per_second_per_gpu:6913.603699674096
Step 100 | loss:1.1724262549250852e-05 lr:5.498556261794161e-05 tokens_per_second_per_gpu:6542.027668394402
Step 101 | loss:0.00033156335121020675 lr:5.4081340470721284e-05 tokens_per_second_per_gpu:6866.491398464939
Step 102 | loss:0.00018934289983008057 lr:5.31757724680119e-05 tokens_per_second_per_gpu:6929.343445991777
Step 103 | loss:0.0050728898495435715 lr:5.22691572282884e-05 tokens_per_second_per_gpu:7002.206168044021
Step 104 | loss:6.202025542734191e-05 lr:5.136179371536076e-05 tokens_per_second_per_gpu:7162.082218210978
Step 105 | loss:0.02080409601330757 lr:5.045398113978817e-05 tokens_per_second_per_gpu:6527.827812651708
Step 106 | loss:9.652554581407458e-05 lr:4.9546018860211844e-05 tokens_per_second_per_gpu:6575.436752129983
Step 107 | loss:0.005580708384513855 lr:4.863820628463925e-05 tokens_per_second_per_gpu:7179.232413916016
Step 108 | loss:0.00015298044309020042 lr:4.773084277171161e-05 tokens_per_second_per_gpu:6510.4209945558205
Step 109 | loss:0.0007602784899063408 lr:4.682422753198812e-05 tokens_per_second_per_gpu:7145.035794055615
Step 110 | loss:0.0004423031641636044 lr:4.591865952927873e-05 tokens_per_second_per_gpu:6926.118395719402
Step 111 | loss:0.00044464613893069327 lr:4.501443738205841e-05 tokens_per_second_per_gpu:6905.97314167665
Step 112 | loss:4.120828816667199e-05 lr:4.41118592649952e-05 tokens_per_second_per_gpu:6923.159408961165
Step 113 | loss:0.002765388460829854 lr:4.321122281062481e-05 tokens_per_second_per_gpu:7037.377110385236
Step 114 | loss:0.0004615378566086292 lr:4.231282501120366e-05 tokens_per_second_per_gpu:6928.471521481375
Step 115 | loss:0.007979671470820904 lr:4.1416962120773396e-05 tokens_per_second_per_gpu:6576.7190097059365
Step 116 | loss:0.0022445840295404196 lr:4.0523929557468594e-05 tokens_per_second_per_gpu:7198.353443106417
Step 117 | loss:0.00226109498180449 lr:3.9634021806100274e-05 tokens_per_second_per_gpu:7148.581781938675
Step 118 | loss:0.004573361482471228 lr:3.874753232104714e-05 tokens_per_second_per_gpu:6509.157601250276
Step 119 | loss:0.0008165035396814346 lr:3.786475342948647e-05 tokens_per_second_per_gpu:7166.266075351035
Step 120 | loss:0.0018289797008037567 lr:3.6985976234996954e-05 tokens_per_second_per_gpu:7027.255308669309
Step 121 | loss:0.001715413061901927 lr:3.611149052156483e-05 tokens_per_second_per_gpu:6622.310977430487
Step 122 | loss:0.009811998344957829 lr:3.524158465802531e-05 tokens_per_second_per_gpu:6418.948657182144
Step 123 | loss:0.001800251891836524 lr:3.437654550297049e-05 tokens_per_second_per_gpu:6463.260229638729
Step 124 | loss:0.0005283604259602726 lr:3.351665831015549e-05 tokens_per_second_per_gpu:6875.197798193578
Step 125 | loss:0.00013838180166203529 lr:3.2662206634433576e-05 tokens_per_second_per_gpu:6896.016038671038
Step 126 | loss:0.0013230371987447143 lr:3.181347223825174e-05 tokens_per_second_per_gpu:6505.274090153978
Step 127 | loss:1.0814403140102513e-05 lr:3.0970734998737095e-05 tokens_per_second_per_gpu:7164.190992439555
Step 128 | loss:0.0017106267623603344 lr:3.013427281540523e-05 tokens_per_second_per_gpu:6889.678797777871
Step 129 | loss:9.598342330718879e-06 lr:2.9304361518520445e-05 tokens_per_second_per_gpu:7071.477213066363
Step 130 | loss:0.00014741574705112725 lr:2.8481274778138567e-05 tokens_per_second_per_gpu:7158.475132830302
Step 131 | loss:3.6312769225332886e-05 lr:2.766528401386187e-05 tokens_per_second_per_gpu:7185.121918184236
Step 132 | loss:0.0023543310817331076 lr:2.685665830533642e-05 tokens_per_second_per_gpu:6946.903022247468
Step 133 | loss:0.0006961273611523211 lr:2.6055664303520653e-05 tokens_per_second_per_gpu:6893.053448692954
Step 134 | loss:0.0023735391441732645 lr:2.526256614275524e-05 tokens_per_second_per_gpu:6938.1841245932965
Step 135 | loss:0.0016860445030033588 lr:2.4477625353662398e-05 tokens_per_second_per_gpu:6934.161705560541
Step 136 | loss:0.0019232911290600896 lr:2.370110077690425e-05 tokens_per_second_per_gpu:6563.779349624029
Step 137 | loss:1.7346914319205098e-05 lr:2.2933248477827813e-05 tokens_per_second_per_gpu:6944.653072673807
Step 138 | loss:0.00024932483211159706 lr:2.2174321662025427e-05 tokens_per_second_per_gpu:6531.996766062305
Step 139 | loss:9.376812522532418e-05 lr:2.1424570591838183e-05 tokens_per_second_per_gpu:7193.175244200958
Step 140 | loss:0.002470591804012656 lr:2.068424250382974e-05 tokens_per_second_per_gpu:4566.956254582536
Step 141 | loss:0.00022290470951702446 lr:1.9953581527258182e-05 tokens_per_second_per_gpu:6548.438839485251
Step 142 | loss:0.0026550027541816235 lr:1.9232828603572256e-05 tokens_per_second_per_gpu:7159.1613884342005
Step 143 | loss:0.002340412698686123 lr:1.852222140695906e-05 tokens_per_second_per_gpu:7041.593680058002
Step 144 | loss:3.749767711269669e-05 lr:1.7821994265968962e-05 tokens_per_second_per_gpu:6971.716090160394
Step 145 | loss:0.0007544458494521677 lr:1.7132378086243904e-05 tokens_per_second_per_gpu:6530.11202130702
Step 146 | loss:0.000901580264326185 lr:1.6453600274374298e-05 tokens_per_second_per_gpu:7140.198673024971
Step 147 | loss:0.0017697644652798772 lr:1.5785884662909916e-05 tokens_per_second_per_gpu:6994.0019214971335
Step 148 | loss:0.0029617343097925186 lr:1.5129451436549203e-05 tokens_per_second_per_gpu:6968.174861529074
Step 149 | loss:3.308681334601715e-05 lr:1.4484517059531588e-05 tokens_per_second_per_gpu:7120.27347738732
Step 150 | loss:2.3677974240854383e-05 lr:1.3851294204256638e-05 tokens_per_second_per_gpu:7131.577527538173
Step 151 | loss:0.0039107962511479855 lr:1.322999168115363e-05 tokens_per_second_per_gpu:6921.898986735984
Step 152 | loss:0.0014382178196683526 lr:1.262081436982448e-05 tokens_per_second_per_gpu:7135.462705613168
Step 153 | loss:0.00013949266576673836 lr:1.2023963151483165e-05 tokens_per_second_per_gpu:7141.568273964799
Step 154 | loss:0.00034261183463968337 lr:1.143963484271337e-05 tokens_per_second_per_gpu:7181.014148423853
Step 155 | loss:0.0001881904900074005 lr:1.0868022130566651e-05 tokens_per_second_per_gpu:6885.578218076869
Step 156 | loss:0.0011999218259006739 lr:1.0309313509022351e-05 tokens_per_second_per_gpu:6553.694028254888
Step 157 | loss:0.0017170794308185577 lr:9.763693216830055e-06 tokens_per_second_per_gpu:7003.676704997268
Step 158 | loss:0.0005050586769357324 lr:9.231341176755488e-06 tokens_per_second_per_gpu:7135.511901573634
Step 159 | loss:0.00019906694069504738 lr:8.712432936249365e-06 tokens_per_second_per_gpu:6987.864609367065
Step 160 | loss:0.0016715177334845066 lr:8.207139609559283e-06 tokens_per_second_per_gpu:7123.890621086048
Step 161 | loss:2.8178919819765724e-05 lr:7.715627821303339e-06 tokens_per_second_per_gpu:7160.330810065798
Step 162 | loss:9.990563739847858e-06 lr:7.238059651524354e-06 tokens_per_second_per_gpu:7123.779660050521
Step 163 | loss:0.0005461033433675766 lr:6.774592582242567e-06 tokens_per_second_per_gpu:7163.835117506741
Step 164 | loss:5.685839641955681e-05 lr:6.325379445524731e-06 tokens_per_second_per_gpu:7175.049677661744
Step 165 | loss:0.00015523542242590338 lr:5.890568373086425e-06 tokens_per_second_per_gpu:7177.204570064459
Step 166 | loss:0.00028514687437564135 lr:5.470302747444428e-06 tokens_per_second_per_gpu:7113.568560249128
Step 167 | loss:0.0009198871557600796 lr:5.064721154635155e-06 tokens_per_second_per_gpu:7130.146315271507
Step 168 | loss:0.0008578493143431842 lr:4.673957338514812e-06 tokens_per_second_per_gpu:6523.779006004142
Step 169 | loss:0.006529966834932566 lr:4.298140156656178e-06 tokens_per_second_per_gpu:2981.3523580671667
Step 170 | loss:0.00027952014352194965 lr:3.937393537856871e-06 tokens_per_second_per_gpu:7132.7979475840875
Step 171 | loss:0.003136750077828765 lr:3.5918364412727e-06 tokens_per_second_per_gpu:6909.186322430136
Step 172 | loss:0.002072084927931428 lr:3.261582817190023e-06 tokens_per_second_per_gpu:6996.861812707333
Step 173 | loss:3.5205408494221047e-05 lr:2.9467415694495627e-06 tokens_per_second_per_gpu:6535.438683688943
Step 174 | loss:0.00022089613776188344 lr:2.6474165195346346e-06 tokens_per_second_per_gpu:6461.535384124085
Step 175 | loss:0.00012490279914345592 lr:2.363706372335045e-06 tokens_per_second_per_gpu:6599.775211293683
Step 176 | loss:0.00010572143946774304 lr:2.095704683598376e-06 tokens_per_second_per_gpu:7191.446670700946
Step 177 | loss:0.0024727554991841316 lr:1.843499829079237e-06 tokens_per_second_per_gpu:6971.867985833486
Step 178 | loss:1.9526514734025113e-05 lr:1.6071749753965914e-06 tokens_per_second_per_gpu:6581.267215364958
Step 179 | loss:6.196992035256699e-05 lr:1.3868080526089178e-06 tokens_per_second_per_gpu:7171.080944544644
Step 180 | loss:0.001949672936461866 lr:1.1824717285160991e-06 tokens_per_second_per_gpu:7163.785784646817
Step 181 | loss:0.00016391932149417698 lr:9.942333846966746e-07 tokens_per_second_per_gpu:7180.392168680158
Step 182 | loss:0.0009728447766974568 lr:8.221550942881406e-07 tokens_per_second_per_gpu:7146.644537695887
Step 183 | loss:7.682470459258184e-05 lr:6.662936015178978e-07 tokens_per_second_per_gpu:7131.1960021686955
Step 184 | loss:0.00020370380661915988 lr:5.267003029913065e-07 tokens_per_second_per_gpu:7117.571778062538
Step 185 | loss:5.8240973885403946e-05 lr:4.03421230743295e-07 tokens_per_second_per_gpu:6396.989451228981
Step 186 | loss:0.003642873838543892 lr:2.9649703705887375e-07 tokens_per_second_per_gpu:7190.961610793101
Step 187 | loss:0.001256400253623724 lr:2.0596298106774213e-07 tokens_per_second_per_gpu:6921.300056944758
Step 188 | loss:0.0002320767962373793 lr:1.3184891711727764e-07 tokens_per_second_per_gpu:6908.784408685789
Step 189 | loss:0.002786273369565606 lr:7.417928492784443e-08 tokens_per_second_per_gpu:6621.345022044395
Step 190 | loss:0.00688420282676816 lr:3.2973101533567695e-08 tokens_per_second_per_gpu:6557.5550033739
Step 191 | loss:0.0072914292104542255 lr:8.243955011333349e-09 tokens_per_second_per_gpu:6617.923676452857
Step 192 | loss:0.0015793157508596778 lr:0.0 tokens_per_second_per_gpu:7180.119801068949