Apollo-M / logs /train_log.jsonl
viknesh100's picture
last 2026-10-26 05:26:41
15a28f8 verified
Raw History Blame Contribute Delete
8.68 kB
{"step": 50, "loss": 0.9119796007871628, "lr": 5.1000000000000006e-05, "tok_s": 13345.737501110538}
{"step": 100, "loss": 0.8990946114063263, "lr": 0.00010100000000000002, "tok_s": 13282.472648956169}
{"step": 150, "loss": 0.9099994003772736, "lr": 0.000151, "tok_s": 13168.522430877054}
{"step": 200, "loss": 0.8980084508657455, "lr": 0.0002, "tok_s": 12599.29566210887}
{"step": 250, "loss": 0.9082906544208527, "lr": 0.0001999231182548571, "tok_s": 12690.907697347435}
{"step": 250, "val": 0.9263836084121999}
{"step": 300, "loss": 0.8549878299236298, "lr": 0.0001996926043706003, "tok_s": 11156.676711446875}
{"step": 350, "loss": 0.8912842571735382, "lr": 0.00019930885217633404, "tok_s": 12920.032781275779}
{"step": 400, "loss": 0.9073851257562637, "lr": 0.00019877251730624501, "tok_s": 12856.826402223356}
{"step": 450, "loss": 0.8948135226964951, "lr": 0.00019808451607946192, "tok_s": 12831.9842593104}
{"step": 500, "loss": 0.891650453209877, "lr": 0.00019724602393453975, "tok_s": 13008.296985759818}
{"step": 500, "val": 0.9250536154539175}
{"step": 550, "loss": 0.9301333129405975, "lr": 0.00019625847342124276, "tok_s": 10309.497593935435}
{"step": 600, "loss": 0.9261624217033386, "lr": 0.00019512355175305712, "tok_s": 12113.645730013894}
{"step": 650, "loss": 0.9682804495096207, "lr": 0.0001938431979246151, "tok_s": 12668.859050869152}
{"step": 700, "loss": 0.9527132958173752, "lr": 0.00019241959939895518, "tok_s": 12524.27354274689}
{"step": 750, "loss": 0.8508577793836594, "lr": 0.00019085518837027812, "tok_s": 12614.18723463337}
{"step": 750, "val": 0.9229827747323358}
{"step": 800, "loss": 0.8926655650138855, "lr": 0.000189152637608584, "tok_s": 10338.987602506822}
{"step": 850, "loss": 0.8990962505340576, "lr": 0.00018731485589328968, "tok_s": 12282.875157898436}
{"step": 900, "loss": 1.011114776134491, "lr": 0.00018534498304362759, "tok_s": 12923.515512748567}
{"step": 950, "loss": 0.8808367103338242, "lr": 0.00018324638455431756, "tok_s": 12634.401240367935}
{"step": 1000, "loss": 0.9524503499269485, "lr": 0.00018102264584567545, "tok_s": 12543.21470648191}
{"step": 1000, "val": 0.922659059107295}
{"step": 1050, "loss": 0.8739219456911087, "lr": 0.0001786775661379826, "tok_s": 10377.375157935554}
{"step": 1100, "loss": 0.9231078624725342, "lr": 0.00017621515196058186, "tok_s": 12446.257261721274}
{"step": 1150, "loss": 0.9487660825252533, "lr": 0.00017363961030678927, "tok_s": 12739.831781641597}
{"step": 1200, "loss": 0.9254888594150543, "lr": 0.00017095534144631673, "tok_s": 11473.308966912637}
{"step": 1250, "loss": 0.9310972988605499, "lr": 0.00016816693140748467, "tok_s": 12577.751999878736}
{"step": 1250, "val": 0.9210733401546363}
{"step": 1300, "loss": 0.8653187304735184, "lr": 0.00016527914414207013, "tok_s": 11284.037147817386}
{"step": 1350, "loss": 0.875058576464653, "lr": 0.00016229691338617445, "tok_s": 13086.806931577596}
{"step": 1400, "loss": 0.9580196440219879, "lr": 0.00015922533423101844, "tok_s": 12859.674411952936}
{"step": 1450, "loss": 0.8628480732440948, "lr": 0.0001560696544180641, "tok_s": 12601.750255798916}
{"step": 1500, "loss": 0.9511719644069672, "lr": 0.00015283526537333665, "tok_s": 12430.632830505027}
{"step": 1500, "val": 0.9186573113952553}
{"step": 1550, "loss": 0.934482753276825, "lr": 0.00014952769299626334, "tok_s": 10073.13633354152}
{"step": 1600, "loss": 0.958391547203064, "lr": 0.00014615258821876727, "tok_s": 12730.449882366673}
{"step": 1650, "loss": 0.9036903530359268, "lr": 0.0001427157173507447, "tok_s": 12581.582716001394}
{"step": 1700, "loss": 0.8833057880401611, "lr": 0.00013922295222842154, "tok_s": 12402.647912565104}
{"step": 1750, "loss": 0.8902811706066132, "lr": 0.0001356802601824195, "tok_s": 12507.538377892315}
{"step": 1750, "val": 0.9175305264582957}
{"step": 1800, "loss": 0.7865059971809387, "lr": 0.00013209369384267194, "tok_s": 10555.245308831361}
{"step": 1850, "loss": 0.8891026079654694, "lr": 0.0001284693807976071, "tok_s": 12961.75313356928}
{"step": 1900, "loss": 0.872664138674736, "lr": 0.00012481351312526606, "tok_s": 12441.517379559607}
{"step": 1950, "loss": 0.8614092469215393, "lr": 0.00012113233681424131, "tok_s": 12457.177008945715}
{"step": 2000, "loss": 0.951303243637085, "lr": 0.00011743214109250993, "tok_s": 13127.079772197721}
{"step": 2000, "val": 0.91477290856758}
{"step": 2050, "loss": 0.9295798391103745, "lr": 0.00011371924768239318, "tok_s": 10412.662935948929}
{"step": 2100, "loss": 0.9062058478593826, "lr": 0.00011, "tok_s": 12373.786485106477}
{"step": 2150, "loss": 0.8629401624202728, "lr": 0.0001062807523176068, "tok_s": 12735.462624419339}
{"step": 2200, "loss": 0.9598381668329239, "lr": 0.0001025678589074901, "tok_s": 12569.673240732529}
{"step": 2250, "loss": 0.8634618520736694, "lr": 9.886766318575871e-05, "tok_s": 13198.951203106682}
{"step": 2250, "val": 0.9149101198460234}
{"step": 2300, "loss": 0.8738665729761124, "lr": 9.518648687473394e-05, "tok_s": 11933.825697165994}
{"step": 2350, "loss": 0.9263006299734116, "lr": 9.153061920239292e-05, "tok_s": 13880.495173433594}
{"step": 2400, "loss": 0.8680133074522018, "lr": 8.790630615732808e-05, "tok_s": 13746.257463971744}
{"step": 2450, "loss": 0.8424958288669586, "lr": 8.431973981758055e-05, "tok_s": 13293.293738765742}
{"step": 2500, "loss": 0.9209726899862289, "lr": 8.07770477715785e-05, "tok_s": 13747.157500424222}
{"step": 2500, "val": 0.9134812067879468}
{"step": 2550, "loss": 0.8361635208129883, "lr": 7.72842826492553e-05, "tok_s": 11584.133467626425}
{"step": 2600, "loss": 0.8669512271881104, "lr": 7.384741178123277e-05, "tok_s": 13114.416261832752}
{"step": 2650, "loss": 0.8654646724462509, "lr": 7.047230700373668e-05, "tok_s": 13419.95970941953}
{"step": 2700, "loss": 0.8952944874763489, "lr": 6.716473462666338e-05, "tok_s": 13436.95353593014}
{"step": 2750, "loss": 0.9335660934448242, "lr": 6.393034558193593e-05, "tok_s": 13324.176481280094}
{"step": 2750, "val": 0.9117289461993686}
{"step": 2800, "loss": 0.9363967925310135, "lr": 6.0774665768981596e-05, "tok_s": 10986.608493960011}
{"step": 2850, "loss": 0.8694444447755814, "lr": 5.770308661382557e-05, "tok_s": 13675.366939783837}
{"step": 2900, "loss": 0.8912713974714279, "lr": 5.47208558579299e-05, "tok_s": 13173.745896094406}
{"step": 2950, "loss": 0.8428374379873276, "lr": 5.183306859251531e-05, "tok_s": 13644.004792238688}
{"step": 3000, "loss": 0.8412140011787415, "lr": 4.904465855368332e-05, "tok_s": 12689.018634602156}
{"step": 3000, "val": 0.910058658253086}
{"step": 3050, "loss": 0.9083396643400192, "lr": 4.6360389693210735e-05, "tok_s": 11155.289452617022}
{"step": 3100, "loss": 0.9319025725126266, "lr": 4.378484803941816e-05, "tok_s": 12933.230281057982}
{"step": 3150, "loss": 0.8643020689487457, "lr": 4.1322433862017434e-05, "tok_s": 13496.295519980318}
{"step": 3200, "loss": 0.8731506317853928, "lr": 3.897735415432459e-05, "tok_s": 13662.19578786596}
{"step": 3250, "loss": 0.8886091113090515, "lr": 3.675361544568246e-05, "tok_s": 13301.308330241365}
{"step": 3250, "val": 0.9103011138538517}
{"step": 3300, "loss": 0.9243307262659073, "lr": 3.4655016956372436e-05, "tok_s": 11733.0935421526}
{"step": 3350, "loss": 0.962729424238205, "lr": 3.2685144106710326e-05, "tok_s": 12931.244745788112}
{"step": 3400, "loss": 0.8295830935239792, "lr": 3.084736239141599e-05, "tok_s": 13234.99045300604}
{"step": 3450, "loss": 0.9173113405704498, "lr": 2.9144811629721904e-05, "tok_s": 13146.22206137561}
{"step": 3500, "loss": 0.8023121654987335, "lr": 2.7580400601044826e-05, "tok_s": 12610.348702475221}
{"step": 3500, "val": 0.9094441443107397}
{"step": 3550, "loss": 0.9463120400905609, "lr": 2.61568020753849e-05, "tok_s": 12021.95250825366}
{"step": 3600, "loss": 0.9140679389238358, "lr": 2.4876448246942883e-05, "tok_s": 13490.121614714419}
{"step": 3650, "loss": 0.8756868541240692, "lr": 2.3741526578757258e-05, "tok_s": 13178.138536491126}
{"step": 3700, "loss": 0.8357647210359573, "lr": 2.275397606546027e-05, "tok_s": 12829.345919933914}
{"step": 3750, "loss": 0.9008111357688904, "lr": 2.1915483920538098e-05, "tok_s": 13301.522804910552}
{"step": 3750, "val": 0.9092048555369556}
{"step": 3800, "loss": 0.7628417909145355, "lr": 2.1227482693754994e-05, "tok_s": 10857.673721670162}
{"step": 3850, "loss": 0.892663449048996, "lr": 2.069114782366595e-05, "tok_s": 13126.378337194803}
{"step": 3900, "loss": 0.8581729978322983, "lr": 2.0307395629399715e-05, "tok_s": 12820.506740144414}
{"step": 3950, "loss": 0.8544314801692963, "lr": 2.007688174514291e-05, "tok_s": 13630.17653177494}
{"step": 4000, "loss": 0.8548808991909027, "lr": 2e-05, "tok_s": 12698.915496860813}
{"step": 4000, "val": 0.9084840003936713}