1	converged=False	diverged=False	epoch=8	gradient-norm=0.8836151655305943	learning-rate=0.0003	perplexity-train=38.04381252202547	perplexity-val=30.227864072578026	time-elapsed=523.1580488681793	used-gpu-memory=6599
2	converged=False	diverged=False	epoch=16	gradient-norm=0.9750468172101225	learning-rate=0.0003	perplexity-train=5.555957210290238	perplexity-val=30.427760293355618	time-elapsed=1050.4022963047028	used-gpu-memory=6599
3	converged=False	diverged=False	epoch=24	gradient-norm=0.8039028028762473	learning-rate=0.0003	perplexity-train=2.7617165527708862	perplexity-val=39.251052951398684	time-elapsed=1579.2481031417847	used-gpu-memory=6599
4	converged=False	diverged=False	epoch=32	gradient-norm=0.9000513771400304	learning-rate=0.0003	perplexity-train=1.9612144358382888	perplexity-val=48.6785622890793	time-elapsed=2107.2678203582764	used-gpu-memory=6599
5	converged=False	diverged=False	epoch=40	gradient-norm=0.6991692326485792	learning-rate=0.0003	perplexity-train=1.6702556952192922	perplexity-val=49.822648630924355	time-elapsed=2634.917316675186	used-gpu-memory=6599
6	converged=False	diverged=False	epoch=48	gradient-norm=0.6417045535229934	learning-rate=0.0003	perplexity-train=1.538501046853164	perplexity-val=51.82460566639749	time-elapsed=3163.1657695770264	used-gpu-memory=6599
7	converged=False	diverged=False	epoch=56	gradient-norm=0.5951994233791826	learning-rate=0.0003	perplexity-train=1.4664846984063526	perplexity-val=52.37246178635837	time-elapsed=3691.5024750232697	used-gpu-memory=6599
8	converged=False	diverged=False	epoch=64	gradient-norm=0.6173519693791125	learning-rate=0.0003	perplexity-train=1.420597829832923	perplexity-val=53.4080853599189	time-elapsed=4218.151284456253	used-gpu-memory=6599
9	converged=False	diverged=False	epoch=72	gradient-norm=0.6018696552629964	learning-rate=0.0003	perplexity-train=1.3843977280467663	perplexity-val=55.096759790129155	time-elapsed=4746.4848873615265	used-gpu-memory=0
10	converged=False	diverged=False	epoch=80	gradient-norm=0.9258776998189213	learning-rate=0.00020999999999999998	perplexity-train=5.64411009284855	perplexity-val=29.70157025517615	time-elapsed=5276.034932136536	used-gpu-memory=0
11	converged=False	diverged=False	epoch=88	gradient-norm=1.0587476408847603	learning-rate=0.00020999999999999998	perplexity-train=3.034408566087416	perplexity-val=37.927390646884845	time-elapsed=5804.936290502548	used-gpu-memory=0
12	converged=False	diverged=False	epoch=96	gradient-norm=0.9245450926426693	learning-rate=0.00020999999999999998	perplexity-train=2.140139189136013	perplexity-val=43.69682879060972	time-elapsed=6331.888612031937	used-gpu-memory=0
13	converged=False	diverged=False	epoch=104	gradient-norm=0.8496383087803367	learning-rate=0.00020999999999999998	perplexity-train=1.777008665285608	perplexity-val=48.97232441023911	time-elapsed=6859.858250141144	used-gpu-memory=0
14	converged=False	diverged=False	epoch=112	gradient-norm=0.7597487085898442	learning-rate=0.00020999999999999998	perplexity-train=1.6026739823940406	perplexity-val=50.432189155640756	time-elapsed=7391.167443037033	used-gpu-memory=0
15	converged=False	diverged=False	epoch=120	gradient-norm=0.7618488650730744	learning-rate=0.00020999999999999998	perplexity-train=1.5108512269151977	perplexity-val=53.04409996443005	time-elapsed=7919.863851308823	used-gpu-memory=0
16	converged=False	diverged=False	epoch=128	gradient-norm=0.7079114797355096	learning-rate=0.00020999999999999998	perplexity-train=1.4485929370698032	perplexity-val=54.340282028811586	time-elapsed=8446.25395488739	used-gpu-memory=0
17	converged=False	diverged=False	epoch=136	gradient-norm=0.5344071632640404	learning-rate=0.00020999999999999998	perplexity-train=1.4089341792652401	perplexity-val=53.59973744867266	time-elapsed=8974.530523061752	used-gpu-memory=0
18	converged=False	diverged=False	epoch=144	gradient-norm=0.5836508232697607	learning-rate=0.00020999999999999998	perplexity-train=1.377572547519619	perplexity-val=54.54189379624305	time-elapsed=9501.316390991211	used-gpu-memory=0
19	converged=False	diverged=False	epoch=152	gradient-norm=1.0446240245586347	learning-rate=0.00014699999999999997	perplexity-train=3.003522746583913	perplexity-val=36.32402407523389	time-elapsed=10028.993872642517	used-gpu-memory=0
20	converged=False	diverged=False	epoch=160	gradient-norm=1.009354691541988	learning-rate=0.00014699999999999997	perplexity-train=2.237453717303294	perplexity-val=42.67846987721101	time-elapsed=10559.060738563538	used-gpu-memory=0
21	converged=False	diverged=False	epoch=168	gradient-norm=0.9221786263757685	learning-rate=0.00014699999999999997	perplexity-train=1.865689513113176	perplexity-val=47.17750511120034	time-elapsed=11088.790701627731	used-gpu-memory=0
22	converged=False	diverged=False	epoch=176	gradient-norm=0.84607037954971	learning-rate=0.00014699999999999997	perplexity-train=1.6761931982183604	perplexity-val=51.0795090661632	time-elapsed=11618.452767133713	used-gpu-memory=0
23	converged=False	diverged=False	epoch=184	gradient-norm=0.8966100079080582	learning-rate=0.00014699999999999997	perplexity-train=1.559049598092738	perplexity-val=52.62689152897963	time-elapsed=12145.276107549667	used-gpu-memory=0
24	converged=False	diverged=False	epoch=192	gradient-norm=0.775960284162536	learning-rate=0.00014699999999999997	perplexity-train=1.4904417023073675	perplexity-val=53.829594854377575	time-elapsed=12674.153376102448	used-gpu-memory=0
25	converged=False	diverged=False	epoch=200	gradient-norm=0.777883967308242	learning-rate=0.00014699999999999997	perplexity-train=1.4419673046672887	perplexity-val=54.1986800622087	time-elapsed=13201.674577474594	used-gpu-memory=27
26	converged=True	diverged=False	epoch=208	gradient-norm=0.686114197409182	learning-rate=0.00014699999999999997	perplexity-train=1.403568157344946	perplexity-val=54.92508281701908	time-elapsed=13730.381585121155	used-gpu-memory=1665
