{ "best_metric": null, "best_model_checkpoint": null, "epoch": 9.9906407487401, "eval_steps": 500, "global_step": 10410, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04799616030717543, "grad_norm": 0.056359845956996786, "learning_rate": 1.9903938520653218e-05, "loss": 0.1372, "step": 50 }, { "epoch": 0.09599232061435085, "grad_norm": 0.04530843606021861, "learning_rate": 1.9807877041306437e-05, "loss": 0.0026, "step": 100 }, { "epoch": 0.14398848092152627, "grad_norm": 0.048800263548022, "learning_rate": 1.9711815561959656e-05, "loss": 0.0016, "step": 150 }, { "epoch": 0.1919846412287017, "grad_norm": 0.028926716536897153, "learning_rate": 1.9615754082612875e-05, "loss": 0.0009, "step": 200 }, { "epoch": 0.23998080153587714, "grad_norm": 0.02483660911842089, "learning_rate": 1.951969260326609e-05, "loss": 0.0006, "step": 250 }, { "epoch": 0.28797696184305255, "grad_norm": 0.031592169119638684, "learning_rate": 1.942363112391931e-05, "loss": 0.0004, "step": 300 }, { "epoch": 0.33597312215022795, "grad_norm": 0.016503212175038827, "learning_rate": 1.932756964457253e-05, "loss": 0.0003, "step": 350 }, { "epoch": 0.3839692824574034, "grad_norm": 0.010211019128745821, "learning_rate": 1.9231508165225746e-05, "loss": 0.0002, "step": 400 }, { "epoch": 0.4319654427645788, "grad_norm": 0.009707429867388344, "learning_rate": 1.9135446685878965e-05, "loss": 0.0002, "step": 450 }, { "epoch": 0.4799616030717543, "grad_norm": 0.009954199033185984, "learning_rate": 1.903938520653218e-05, "loss": 0.0001, "step": 500 }, { "epoch": 0.5279577633789296, "grad_norm": 0.03019176505404075, "learning_rate": 1.89433237271854e-05, "loss": 0.0001, "step": 550 }, { "epoch": 0.5759539236861051, "grad_norm": 0.017169092945345278, "learning_rate": 1.884726224783862e-05, "loss": 0.0002, "step": 600 }, { "epoch": 0.6239500839932806, "grad_norm": 0.014050969174899489, "learning_rate": 1.875120076849184e-05, "loss": 0.0002, "step": 650 }, { "epoch": 0.6719462443004559, "grad_norm": 0.01214360409818984, "learning_rate": 1.8655139289145054e-05, "loss": 0.0001, "step": 700 }, { "epoch": 0.7199424046076314, "grad_norm": 0.007490998342783297, "learning_rate": 1.855907780979827e-05, "loss": 0.0001, "step": 750 }, { "epoch": 0.7679385649148068, "grad_norm": 0.01472168117986472, "learning_rate": 1.846301633045149e-05, "loss": 0.0001, "step": 800 }, { "epoch": 0.8159347252219823, "grad_norm": 0.004822963008007148, "learning_rate": 1.836695485110471e-05, "loss": 0.0001, "step": 850 }, { "epoch": 0.8639308855291576, "grad_norm": 0.007864662209371043, "learning_rate": 1.8270893371757928e-05, "loss": 0.0001, "step": 900 }, { "epoch": 0.9119270458363331, "grad_norm": 0.0037532241969519355, "learning_rate": 1.8174831892411144e-05, "loss": 0.0, "step": 950 }, { "epoch": 0.9599232061435086, "grad_norm": 0.025225633083551968, "learning_rate": 1.8078770413064363e-05, "loss": 0.0001, "step": 1000 }, { "epoch": 1.0076793856491482, "grad_norm": 0.0070698857815611905, "learning_rate": 1.7982708933717582e-05, "loss": 0.0001, "step": 1050 }, { "epoch": 1.0556755459563234, "grad_norm": 0.0077929016224052095, "learning_rate": 1.78866474543708e-05, "loss": 0.0001, "step": 1100 }, { "epoch": 1.1036717062634989, "grad_norm": 0.0031971035982334005, "learning_rate": 1.7790585975024018e-05, "loss": 0.0, "step": 1150 }, { "epoch": 1.1516678665706743, "grad_norm": 0.0008553018029932224, "learning_rate": 1.7694524495677234e-05, "loss": 0.0, "step": 1200 }, { "epoch": 1.1996640268778498, "grad_norm": 0.009629377240548386, "learning_rate": 1.7598463016330453e-05, "loss": 0.0, "step": 1250 }, { "epoch": 1.2476601871850252, "grad_norm": 0.015633152594491845, "learning_rate": 1.7502401536983672e-05, "loss": 0.0001, "step": 1300 }, { "epoch": 1.2956563474922005, "grad_norm": 0.006061806879093744, "learning_rate": 1.7406340057636888e-05, "loss": 0.0001, "step": 1350 }, { "epoch": 1.343652507799376, "grad_norm": 0.014919415942150202, "learning_rate": 1.7310278578290107e-05, "loss": 0.0001, "step": 1400 }, { "epoch": 1.3916486681065514, "grad_norm": 0.007840820222323987, "learning_rate": 1.7214217098943323e-05, "loss": 0.0001, "step": 1450 }, { "epoch": 1.4396448284137269, "grad_norm": 0.010102899473387241, "learning_rate": 1.7118155619596542e-05, "loss": 0.0001, "step": 1500 }, { "epoch": 1.4876409887209023, "grad_norm": 0.00821469211056164, "learning_rate": 1.702209414024976e-05, "loss": 0.0001, "step": 1550 }, { "epoch": 1.5356371490280778, "grad_norm": 0.006461620366133209, "learning_rate": 1.692603266090298e-05, "loss": 0.0, "step": 1600 }, { "epoch": 1.5836333093352533, "grad_norm": 0.0035233894828334, "learning_rate": 1.6829971181556197e-05, "loss": 0.0, "step": 1650 }, { "epoch": 1.6316294696424287, "grad_norm": 0.0013366005919697563, "learning_rate": 1.6733909702209416e-05, "loss": 0.0, "step": 1700 }, { "epoch": 1.6796256299496042, "grad_norm": 0.0008247202586656663, "learning_rate": 1.6637848222862635e-05, "loss": 0.0, "step": 1750 }, { "epoch": 1.7276217902567794, "grad_norm": 0.00138812261064544, "learning_rate": 1.654178674351585e-05, "loss": 0.0, "step": 1800 }, { "epoch": 1.7756179505639549, "grad_norm": 0.0019404034686127678, "learning_rate": 1.644572526416907e-05, "loss": 0.0, "step": 1850 }, { "epoch": 1.8236141108711303, "grad_norm": 0.0010990642036531632, "learning_rate": 1.6349663784822286e-05, "loss": 0.0, "step": 1900 }, { "epoch": 1.8716102711783056, "grad_norm": 0.0017740362762336732, "learning_rate": 1.6253602305475506e-05, "loss": 0.0, "step": 1950 }, { "epoch": 1.919606431485481, "grad_norm": 0.001563612144579101, "learning_rate": 1.6157540826128725e-05, "loss": 0.0, "step": 2000 }, { "epoch": 1.9676025917926565, "grad_norm": 0.0018909757453378412, "learning_rate": 1.606147934678194e-05, "loss": 0.0, "step": 2050 }, { "epoch": 2.0153587712982963, "grad_norm": 0.0006439448364579109, "learning_rate": 1.596541786743516e-05, "loss": 0.0, "step": 2100 }, { "epoch": 2.0633549316054713, "grad_norm": 0.0032895928351192056, "learning_rate": 1.5869356388088376e-05, "loss": 0.0, "step": 2150 }, { "epoch": 2.111351091912647, "grad_norm": 0.0027251031542751473, "learning_rate": 1.5773294908741595e-05, "loss": 0.0, "step": 2200 }, { "epoch": 2.1593472522198223, "grad_norm": 0.0008593470077862425, "learning_rate": 1.5677233429394814e-05, "loss": 0.0, "step": 2250 }, { "epoch": 2.2073434125269977, "grad_norm": 3.458426400791139e-05, "learning_rate": 1.5581171950048034e-05, "loss": 0.0, "step": 2300 }, { "epoch": 2.255339572834173, "grad_norm": 0.000981214542420656, "learning_rate": 1.548511047070125e-05, "loss": 0.0, "step": 2350 }, { "epoch": 2.3033357331413487, "grad_norm": 0.001124174063701936, "learning_rate": 1.538904899135447e-05, "loss": 0.0, "step": 2400 }, { "epoch": 2.351331893448524, "grad_norm": 0.0013095861126641674, "learning_rate": 1.5292987512007688e-05, "loss": 0.0, "step": 2450 }, { "epoch": 2.3993280537556996, "grad_norm": 0.0015182053160101795, "learning_rate": 1.5196926032660904e-05, "loss": 0.0, "step": 2500 }, { "epoch": 2.447324214062875, "grad_norm": 0.001969005538900658, "learning_rate": 1.5100864553314123e-05, "loss": 0.0, "step": 2550 }, { "epoch": 2.4953203743700505, "grad_norm": 2.6145928957516364e-05, "learning_rate": 1.500480307396734e-05, "loss": 0.0, "step": 2600 }, { "epoch": 2.543316534677226, "grad_norm": 0.0021796883079272097, "learning_rate": 1.490874159462056e-05, "loss": 0.0, "step": 2650 }, { "epoch": 2.591312694984401, "grad_norm": 0.0007661812983237169, "learning_rate": 1.4812680115273776e-05, "loss": 0.0, "step": 2700 }, { "epoch": 2.639308855291577, "grad_norm": 0.0003085627432685896, "learning_rate": 1.4716618635926993e-05, "loss": 0.0, "step": 2750 }, { "epoch": 2.687305015598752, "grad_norm": 0.00023846879150445877, "learning_rate": 1.4620557156580213e-05, "loss": 0.0, "step": 2800 }, { "epoch": 2.7353011759059274, "grad_norm": 0.0012522127595133068, "learning_rate": 1.452449567723343e-05, "loss": 0.0, "step": 2850 }, { "epoch": 2.783297336213103, "grad_norm": 0.0008184248138162355, "learning_rate": 1.442843419788665e-05, "loss": 0.0, "step": 2900 }, { "epoch": 2.8312934965202783, "grad_norm": 0.01180670902661138, "learning_rate": 1.4332372718539867e-05, "loss": 0.0001, "step": 2950 }, { "epoch": 2.8792896568274537, "grad_norm": 0.016217542686608223, "learning_rate": 1.4236311239193086e-05, "loss": 0.0002, "step": 3000 }, { "epoch": 2.927285817134629, "grad_norm": 0.010646818079507889, "learning_rate": 1.4140249759846302e-05, "loss": 0.0002, "step": 3050 }, { "epoch": 2.9752819774418047, "grad_norm": 0.007196097859297863, "learning_rate": 1.404418828049952e-05, "loss": 0.0001, "step": 3100 }, { "epoch": 3.023038156947444, "grad_norm": 0.007568758416020564, "learning_rate": 1.3948126801152739e-05, "loss": 0.0001, "step": 3150 }, { "epoch": 3.0710343172546195, "grad_norm": 0.006390579698931919, "learning_rate": 1.3852065321805957e-05, "loss": 0.0001, "step": 3200 }, { "epoch": 3.119030477561795, "grad_norm": 0.010734275211685794, "learning_rate": 1.3756003842459176e-05, "loss": 0.0, "step": 3250 }, { "epoch": 3.1670266378689704, "grad_norm": 0.004630534766497509, "learning_rate": 1.3659942363112394e-05, "loss": 0.0, "step": 3300 }, { "epoch": 3.215022798176146, "grad_norm": 0.0005952342568898498, "learning_rate": 1.3563880883765613e-05, "loss": 0.0, "step": 3350 }, { "epoch": 3.2630189584833214, "grad_norm": 0.0027613516647845954, "learning_rate": 1.3467819404418829e-05, "loss": 0.0, "step": 3400 }, { "epoch": 3.311015118790497, "grad_norm": 0.0013039145722702529, "learning_rate": 1.3371757925072046e-05, "loss": 0.0, "step": 3450 }, { "epoch": 3.3590112790976723, "grad_norm": 0.0009283601577810141, "learning_rate": 1.3275696445725266e-05, "loss": 0.0, "step": 3500 }, { "epoch": 3.4070074394048477, "grad_norm": 0.0006436371717338523, "learning_rate": 1.3179634966378483e-05, "loss": 0.0, "step": 3550 }, { "epoch": 3.455003599712023, "grad_norm": 6.599953012370843e-05, "learning_rate": 1.3083573487031702e-05, "loss": 0.0, "step": 3600 }, { "epoch": 3.5029997600191987, "grad_norm": 6.36973670822645e-05, "learning_rate": 1.298751200768492e-05, "loss": 0.0, "step": 3650 }, { "epoch": 3.5509959203263737, "grad_norm": 0.0009200029805350018, "learning_rate": 1.2891450528338136e-05, "loss": 0.0, "step": 3700 }, { "epoch": 3.5989920806335496, "grad_norm": 0.001151118667632979, "learning_rate": 1.2795389048991355e-05, "loss": 0.0, "step": 3750 }, { "epoch": 3.6469882409407246, "grad_norm": 0.00037121111713653293, "learning_rate": 1.2699327569644573e-05, "loss": 0.0, "step": 3800 }, { "epoch": 3.6949844012479, "grad_norm": 0.0021648858121127925, "learning_rate": 1.2603266090297792e-05, "loss": 0.0, "step": 3850 }, { "epoch": 3.7429805615550755, "grad_norm": 0.001600258464510773, "learning_rate": 1.250720461095101e-05, "loss": 0.0, "step": 3900 }, { "epoch": 3.790976721862251, "grad_norm": 0.0013961604090552233, "learning_rate": 1.2411143131604229e-05, "loss": 0.0, "step": 3950 }, { "epoch": 3.8389728821694264, "grad_norm": 0.00048475558523138784, "learning_rate": 1.2315081652257446e-05, "loss": 0.0, "step": 4000 }, { "epoch": 3.886969042476602, "grad_norm": 0.0017333329320903196, "learning_rate": 1.2219020172910662e-05, "loss": 0.0, "step": 4050 }, { "epoch": 3.9349652027837774, "grad_norm": 0.010707171803579559, "learning_rate": 1.2122958693563881e-05, "loss": 0.0001, "step": 4100 }, { "epoch": 3.982961363090953, "grad_norm": 0.006925594566044665, "learning_rate": 1.2026897214217099e-05, "loss": 0.0001, "step": 4150 }, { "epoch": 4.030717542596593, "grad_norm": 0.01062801757661266, "learning_rate": 1.1930835734870318e-05, "loss": 0.0001, "step": 4200 }, { "epoch": 4.078713702903768, "grad_norm": 2.7264394254701005, "learning_rate": 1.1834774255523536e-05, "loss": 0.0425, "step": 4250 }, { "epoch": 4.126709863210943, "grad_norm": 2.656886510026864, "learning_rate": 1.1738712776176755e-05, "loss": 0.0154, "step": 4300 }, { "epoch": 4.174706023518119, "grad_norm": 0.007126911273931725, "learning_rate": 1.1642651296829973e-05, "loss": 0.0028, "step": 4350 }, { "epoch": 4.222702183825294, "grad_norm": 0.00035477378217495665, "learning_rate": 1.1546589817483189e-05, "loss": 0.0, "step": 4400 }, { "epoch": 4.2706983441324695, "grad_norm": 0.0019944039322872796, "learning_rate": 1.1450528338136408e-05, "loss": 0.0, "step": 4450 }, { "epoch": 4.3186945044396445, "grad_norm": 0.0027298287000846375, "learning_rate": 1.1354466858789625e-05, "loss": 0.0, "step": 4500 }, { "epoch": 4.36669066474682, "grad_norm": 0.003286962475487846, "learning_rate": 1.1258405379442845e-05, "loss": 0.0, "step": 4550 }, { "epoch": 4.4146868250539955, "grad_norm": 0.001365637121709503, "learning_rate": 1.1162343900096062e-05, "loss": 0.0, "step": 4600 }, { "epoch": 4.462682985361171, "grad_norm": 0.00013215796860760568, "learning_rate": 1.1066282420749282e-05, "loss": 0.0, "step": 4650 }, { "epoch": 4.510679145668346, "grad_norm": 0.0018098453195765278, "learning_rate": 1.0970220941402499e-05, "loss": 0.0, "step": 4700 }, { "epoch": 4.558675305975522, "grad_norm": 0.003154487431789082, "learning_rate": 1.0874159462055715e-05, "loss": 0.0, "step": 4750 }, { "epoch": 4.606671466282697, "grad_norm": 0.0012030613779208958, "learning_rate": 1.0778097982708934e-05, "loss": 0.0, "step": 4800 }, { "epoch": 4.654667626589873, "grad_norm": 0.002984602213822321, "learning_rate": 1.0682036503362152e-05, "loss": 0.0, "step": 4850 }, { "epoch": 4.702663786897048, "grad_norm": 0.0017107235374378526, "learning_rate": 1.0585975024015371e-05, "loss": 0.0, "step": 4900 }, { "epoch": 4.750659947204223, "grad_norm": 0.0013479788753936498, "learning_rate": 1.0489913544668589e-05, "loss": 0.0, "step": 4950 }, { "epoch": 4.798656107511399, "grad_norm": 0.0013971374940015167, "learning_rate": 1.0393852065321808e-05, "loss": 0.0, "step": 5000 }, { "epoch": 4.846652267818574, "grad_norm": 0.0009174014462086613, "learning_rate": 1.0297790585975025e-05, "loss": 0.0, "step": 5050 }, { "epoch": 4.89464842812575, "grad_norm": 0.00021319385906492494, "learning_rate": 1.0201729106628241e-05, "loss": 0.0, "step": 5100 }, { "epoch": 4.942644588432925, "grad_norm": 0.0003964928400635538, "learning_rate": 1.010566762728146e-05, "loss": 0.0, "step": 5150 }, { "epoch": 4.990640748740101, "grad_norm": 0.0007846693600976504, "learning_rate": 1.0009606147934678e-05, "loss": 0.0, "step": 5200 }, { "epoch": 5.03839692824574, "grad_norm": 0.001261614819050779, "learning_rate": 9.913544668587897e-06, "loss": 0.0, "step": 5250 }, { "epoch": 5.086393088552915, "grad_norm": 0.0012098325775649194, "learning_rate": 9.817483189241115e-06, "loss": 0.0, "step": 5300 }, { "epoch": 5.134389248860091, "grad_norm": 0.0014591579618327688, "learning_rate": 9.721421709894333e-06, "loss": 0.0, "step": 5350 }, { "epoch": 5.182385409167266, "grad_norm": 0.0016037268795767395, "learning_rate": 9.625360230547552e-06, "loss": 0.0, "step": 5400 }, { "epoch": 5.230381569474442, "grad_norm": 0.0005212598226700765, "learning_rate": 9.52929875120077e-06, "loss": 0.0, "step": 5450 }, { "epoch": 5.278377729781617, "grad_norm": 0.0010553934511595387, "learning_rate": 9.433237271853987e-06, "loss": 0.0, "step": 5500 }, { "epoch": 5.326373890088793, "grad_norm": 0.00043323667380786225, "learning_rate": 9.337175792507205e-06, "loss": 0.0, "step": 5550 }, { "epoch": 5.374370050395968, "grad_norm": 0.0012194286751975318, "learning_rate": 9.241114313160424e-06, "loss": 0.0, "step": 5600 }, { "epoch": 5.422366210703144, "grad_norm": 0.000637742719517836, "learning_rate": 9.145052833813641e-06, "loss": 0.0, "step": 5650 }, { "epoch": 5.470362371010319, "grad_norm": 4.325815795263492e-05, "learning_rate": 9.048991354466859e-06, "loss": 0.0, "step": 5700 }, { "epoch": 5.518358531317495, "grad_norm": 0.0016312939508974279, "learning_rate": 8.952929875120078e-06, "loss": 0.0, "step": 5750 }, { "epoch": 5.56635469162467, "grad_norm": 0.0012246180978586572, "learning_rate": 8.856868395773296e-06, "loss": 0.0, "step": 5800 }, { "epoch": 5.614350851931846, "grad_norm": 0.0003665920238881759, "learning_rate": 8.760806916426513e-06, "loss": 0.0, "step": 5850 }, { "epoch": 5.662347012239021, "grad_norm": 0.0012525412890931756, "learning_rate": 8.664745437079731e-06, "loss": 0.0, "step": 5900 }, { "epoch": 5.710343172546196, "grad_norm": 0.0017253082668870557, "learning_rate": 8.56868395773295e-06, "loss": 0.0, "step": 5950 }, { "epoch": 5.758339332853372, "grad_norm": 2.167483489099867e-05, "learning_rate": 8.472622478386168e-06, "loss": 0.0, "step": 6000 }, { "epoch": 5.806335493160547, "grad_norm": 0.002300377575504565, "learning_rate": 8.376560999039385e-06, "loss": 0.0, "step": 6050 }, { "epoch": 5.854331653467723, "grad_norm": 0.001247309342311816, "learning_rate": 8.280499519692605e-06, "loss": 0.0, "step": 6100 }, { "epoch": 5.902327813774898, "grad_norm": 0.0018508173770747623, "learning_rate": 8.184438040345822e-06, "loss": 0.0, "step": 6150 }, { "epoch": 5.950323974082074, "grad_norm": 2.8314353686097232e-05, "learning_rate": 8.08837656099904e-06, "loss": 0.0, "step": 6200 }, { "epoch": 5.998320134389249, "grad_norm": 0.0008053281023898595, "learning_rate": 7.992315081652257e-06, "loss": 0.0, "step": 6250 }, { "epoch": 6.046076313894888, "grad_norm": 0.000246511018384193, "learning_rate": 7.896253602305477e-06, "loss": 0.0, "step": 6300 }, { "epoch": 6.094072474202064, "grad_norm": 0.001862683974136238, "learning_rate": 7.800192122958694e-06, "loss": 0.0, "step": 6350 }, { "epoch": 6.142068634509239, "grad_norm": 0.0010864233898034475, "learning_rate": 7.704130643611912e-06, "loss": 0.0, "step": 6400 }, { "epoch": 6.190064794816415, "grad_norm": 0.0011081212998509966, "learning_rate": 7.60806916426513e-06, "loss": 0.0, "step": 6450 }, { "epoch": 6.23806095512359, "grad_norm": 0.0004987385497892048, "learning_rate": 7.512007684918349e-06, "loss": 0.0, "step": 6500 }, { "epoch": 6.286057115430766, "grad_norm": 0.0006690934909146146, "learning_rate": 7.415946205571566e-06, "loss": 0.0, "step": 6550 }, { "epoch": 6.334053275737941, "grad_norm": 0.0005715255066628584, "learning_rate": 7.319884726224784e-06, "loss": 0.0, "step": 6600 }, { "epoch": 6.382049436045117, "grad_norm": 0.0002868542568900514, "learning_rate": 7.223823246878002e-06, "loss": 0.0, "step": 6650 }, { "epoch": 6.430045596352292, "grad_norm": 0.0012799016530399359, "learning_rate": 7.127761767531221e-06, "loss": 0.0, "step": 6700 }, { "epoch": 6.478041756659467, "grad_norm": 0.0006603786706831753, "learning_rate": 7.031700288184439e-06, "loss": 0.0, "step": 6750 }, { "epoch": 6.526037916966643, "grad_norm": 0.0018370243979159682, "learning_rate": 6.935638808837657e-06, "loss": 0.0, "step": 6800 }, { "epoch": 6.574034077273818, "grad_norm": 0.0005642321026490272, "learning_rate": 6.839577329490875e-06, "loss": 0.0, "step": 6850 }, { "epoch": 6.622030237580994, "grad_norm": 0.0009876585977881267, "learning_rate": 6.743515850144093e-06, "loss": 0.0, "step": 6900 }, { "epoch": 6.670026397888169, "grad_norm": 1.1312770861231675e-05, "learning_rate": 6.64745437079731e-06, "loss": 0.0, "step": 6950 }, { "epoch": 6.7180225581953446, "grad_norm": 0.001873679763596067, "learning_rate": 6.551392891450529e-06, "loss": 0.0, "step": 7000 }, { "epoch": 6.76601871850252, "grad_norm": 0.0010621236657186197, "learning_rate": 6.455331412103747e-06, "loss": 0.0, "step": 7050 }, { "epoch": 6.8140148788096955, "grad_norm": 0.0005599241094897003, "learning_rate": 6.359269932756965e-06, "loss": 0.0, "step": 7100 }, { "epoch": 6.8620110391168705, "grad_norm": 0.0020452728713900425, "learning_rate": 6.263208453410183e-06, "loss": 0.0, "step": 7150 }, { "epoch": 6.910007199424046, "grad_norm": 0.0006276694590083033, "learning_rate": 6.167146974063401e-06, "loss": 0.0, "step": 7200 }, { "epoch": 6.958003359731221, "grad_norm": 1.0943867005432958e-05, "learning_rate": 6.071085494716619e-06, "loss": 0.0, "step": 7250 }, { "epoch": 7.005759539236861, "grad_norm": 0.0003131943367904171, "learning_rate": 5.9750240153698366e-06, "loss": 0.0, "step": 7300 }, { "epoch": 7.053755699544037, "grad_norm": 0.0013394420472302832, "learning_rate": 5.878962536023055e-06, "loss": 0.0, "step": 7350 }, { "epoch": 7.101751859851212, "grad_norm": 0.0004515914279429353, "learning_rate": 5.782901056676273e-06, "loss": 0.0, "step": 7400 }, { "epoch": 7.149748020158388, "grad_norm": 0.0012371776622873765, "learning_rate": 5.686839577329492e-06, "loss": 0.0, "step": 7450 }, { "epoch": 7.197744180465563, "grad_norm": 0.0005462388990689112, "learning_rate": 5.590778097982709e-06, "loss": 0.0, "step": 7500 }, { "epoch": 7.2457403407727385, "grad_norm": 0.0012197696193749939, "learning_rate": 5.494716618635928e-06, "loss": 0.0, "step": 7550 }, { "epoch": 7.293736501079914, "grad_norm": 0.0009604127841121792, "learning_rate": 5.398655139289145e-06, "loss": 0.0, "step": 7600 }, { "epoch": 7.3417326613870895, "grad_norm": 0.0025036340230321125, "learning_rate": 5.302593659942363e-06, "loss": 0.0, "step": 7650 }, { "epoch": 7.3897288216942645, "grad_norm": 0.0005758966168119034, "learning_rate": 5.206532180595581e-06, "loss": 0.0, "step": 7700 }, { "epoch": 7.4377249820014395, "grad_norm": 0.001229882649627972, "learning_rate": 5.1104707012488e-06, "loss": 0.0, "step": 7750 }, { "epoch": 7.485721142308615, "grad_norm": 0.002120352213056407, "learning_rate": 5.014409221902018e-06, "loss": 0.0, "step": 7800 }, { "epoch": 7.53371730261579, "grad_norm": 0.0005579557634673263, "learning_rate": 4.918347742555236e-06, "loss": 0.0, "step": 7850 }, { "epoch": 7.581713462922966, "grad_norm": 0.0006140693671067026, "learning_rate": 4.822286263208454e-06, "loss": 0.0, "step": 7900 }, { "epoch": 7.629709623230141, "grad_norm": 0.0020367094428932054, "learning_rate": 4.726224783861672e-06, "loss": 0.0, "step": 7950 }, { "epoch": 7.677705783537317, "grad_norm": 0.0010086315815590796, "learning_rate": 4.630163304514889e-06, "loss": 0.0, "step": 8000 }, { "epoch": 7.725701943844492, "grad_norm": 0.0023790402017036106, "learning_rate": 4.534101825168108e-06, "loss": 0.0, "step": 8050 }, { "epoch": 7.773698104151668, "grad_norm": 0.0006267680798791626, "learning_rate": 4.438040345821326e-06, "loss": 0.0, "step": 8100 }, { "epoch": 7.821694264458843, "grad_norm": 0.001438738793669524, "learning_rate": 4.341978866474544e-06, "loss": 0.0, "step": 8150 }, { "epoch": 7.869690424766019, "grad_norm": 0.00031777905634207366, "learning_rate": 4.245917387127762e-06, "loss": 0.0, "step": 8200 }, { "epoch": 7.917686585073194, "grad_norm": 0.0007442124946473978, "learning_rate": 4.149855907780981e-06, "loss": 0.0, "step": 8250 }, { "epoch": 7.96568274538037, "grad_norm": 0.0007645340846509501, "learning_rate": 4.053794428434198e-06, "loss": 0.0, "step": 8300 }, { "epoch": 8.013438924886009, "grad_norm": 0.0012016885090594615, "learning_rate": 3.957732949087416e-06, "loss": 0.0, "step": 8350 }, { "epoch": 8.061435085193185, "grad_norm": 0.0010325640415925308, "learning_rate": 3.861671469740634e-06, "loss": 0.0, "step": 8400 }, { "epoch": 8.10943124550036, "grad_norm": 6.604070979562978e-06, "learning_rate": 3.7656099903938526e-06, "loss": 0.0, "step": 8450 }, { "epoch": 8.157427405807535, "grad_norm": 0.0012186936208813802, "learning_rate": 3.66954851104707e-06, "loss": 0.0, "step": 8500 }, { "epoch": 8.20542356611471, "grad_norm": 6.490957752970515e-06, "learning_rate": 3.5734870317002885e-06, "loss": 0.0, "step": 8550 }, { "epoch": 8.253419726421885, "grad_norm": 6.650211845109218e-06, "learning_rate": 3.4774255523535065e-06, "loss": 0.0, "step": 8600 }, { "epoch": 8.301415886729062, "grad_norm": 7.749100946178552e-06, "learning_rate": 3.381364073006724e-06, "loss": 0.0, "step": 8650 }, { "epoch": 8.349412047036237, "grad_norm": 0.0012898002261334904, "learning_rate": 3.2853025936599425e-06, "loss": 0.0, "step": 8700 }, { "epoch": 8.397408207343412, "grad_norm": 0.0011575881798726088, "learning_rate": 3.189241114313161e-06, "loss": 0.0, "step": 8750 }, { "epoch": 8.445404367650587, "grad_norm": 0.0011746103393340125, "learning_rate": 3.093179634966379e-06, "loss": 0.0, "step": 8800 }, { "epoch": 8.493400527957764, "grad_norm": 0.0018617005826680572, "learning_rate": 2.9971181556195965e-06, "loss": 0.0, "step": 8850 }, { "epoch": 8.541396688264939, "grad_norm": 0.0014304481942881476, "learning_rate": 2.901056676272815e-06, "loss": 0.0, "step": 8900 }, { "epoch": 8.589392848572114, "grad_norm": 0.0014302646357683322, "learning_rate": 2.804995196926033e-06, "loss": 0.0, "step": 8950 }, { "epoch": 8.637389008879289, "grad_norm": 0.0007299503239037535, "learning_rate": 2.708933717579251e-06, "loss": 0.0, "step": 9000 }, { "epoch": 8.685385169186466, "grad_norm": 0.0012707768875989157, "learning_rate": 2.612872238232469e-06, "loss": 0.0, "step": 9050 }, { "epoch": 8.73338132949364, "grad_norm": 0.0008222158799147773, "learning_rate": 2.5168107588856873e-06, "loss": 0.0, "step": 9100 }, { "epoch": 8.781377489800816, "grad_norm": 0.002014998964020666, "learning_rate": 2.420749279538905e-06, "loss": 0.0, "step": 9150 }, { "epoch": 8.829373650107991, "grad_norm": 0.0009001429474679398, "learning_rate": 2.324687800192123e-06, "loss": 0.0, "step": 9200 }, { "epoch": 8.877369810415168, "grad_norm": 0.0003820911843140154, "learning_rate": 2.2286263208453413e-06, "loss": 0.0, "step": 9250 }, { "epoch": 8.925365970722343, "grad_norm": 0.000856916441308612, "learning_rate": 2.1325648414985593e-06, "loss": 0.0, "step": 9300 }, { "epoch": 8.973362131029518, "grad_norm": 0.0007761779486122437, "learning_rate": 2.0365033621517773e-06, "loss": 0.0, "step": 9350 }, { "epoch": 9.021118310535158, "grad_norm": 0.0018792757159981181, "learning_rate": 1.9404418828049953e-06, "loss": 0.0, "step": 9400 }, { "epoch": 9.069114470842333, "grad_norm": 0.00041481994448875394, "learning_rate": 1.8443804034582133e-06, "loss": 0.0, "step": 9450 }, { "epoch": 9.117110631149508, "grad_norm": 1.1819367471960496e-05, "learning_rate": 1.7483189241114315e-06, "loss": 0.0, "step": 9500 }, { "epoch": 9.165106791456683, "grad_norm": 0.0017368795816472195, "learning_rate": 1.6522574447646495e-06, "loss": 0.0, "step": 9550 }, { "epoch": 9.213102951763858, "grad_norm": 0.0005401116249332524, "learning_rate": 1.5561959654178677e-06, "loss": 0.0, "step": 9600 }, { "epoch": 9.261099112071035, "grad_norm": 0.0010785311265829687, "learning_rate": 1.4601344860710855e-06, "loss": 0.0, "step": 9650 }, { "epoch": 9.30909527237821, "grad_norm": 0.0004670023483024189, "learning_rate": 1.3640730067243035e-06, "loss": 0.0, "step": 9700 }, { "epoch": 9.357091432685385, "grad_norm": 0.0006055103030654768, "learning_rate": 1.2680115273775217e-06, "loss": 0.0, "step": 9750 }, { "epoch": 9.40508759299256, "grad_norm": 0.0007597006922075478, "learning_rate": 1.17195004803074e-06, "loss": 0.0, "step": 9800 }, { "epoch": 9.453083753299737, "grad_norm": 0.00024368041193667566, "learning_rate": 1.0758885686839577e-06, "loss": 0.0, "step": 9850 }, { "epoch": 9.501079913606912, "grad_norm": 0.0016168416769906855, "learning_rate": 9.79827089337176e-07, "loss": 0.0, "step": 9900 }, { "epoch": 9.549076073914087, "grad_norm": 0.0014595362051413555, "learning_rate": 8.837656099903939e-07, "loss": 0.0, "step": 9950 }, { "epoch": 9.597072234221262, "grad_norm": 0.0019860720699641865, "learning_rate": 7.87704130643612e-07, "loss": 0.0, "step": 10000 }, { "epoch": 9.645068394528437, "grad_norm": 0.0010079036592915303, "learning_rate": 6.916426512968301e-07, "loss": 0.0, "step": 10050 }, { "epoch": 9.693064554835614, "grad_norm": 0.0018929108249355604, "learning_rate": 5.955811719500481e-07, "loss": 0.0, "step": 10100 }, { "epoch": 9.741060715142789, "grad_norm": 0.0014581536648741872, "learning_rate": 4.995196926032661e-07, "loss": 0.0, "step": 10150 }, { "epoch": 9.789056875449964, "grad_norm": 0.00042115371443740654, "learning_rate": 4.034582132564842e-07, "loss": 0.0, "step": 10200 }, { "epoch": 9.837053035757139, "grad_norm": 0.0011505748269741243, "learning_rate": 3.0739673390970224e-07, "loss": 0.0, "step": 10250 }, { "epoch": 9.885049196064315, "grad_norm": 0.0008081086815167396, "learning_rate": 2.1133525456292026e-07, "loss": 0.0, "step": 10300 }, { "epoch": 9.93304535637149, "grad_norm": 0.0013881162963304977, "learning_rate": 1.1527377521613833e-07, "loss": 0.0, "step": 10350 }, { "epoch": 9.981041516678665, "grad_norm": 0.0012547337111623964, "learning_rate": 1.921229586935639e-08, "loss": 0.0, "step": 10400 } ], "logging_steps": 50, "max_steps": 10410, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.497989908103168e+16, "train_batch_size": 6, "trial_name": null, "trial_params": null }