Classification Report for LLaMa3.1 70B

Invalid Model Output Count

Test	Invalid Count
0%_512	1
25%_64	2
25%_512	1
50%_64	1
50%_1024	1
50%_4096	2
50%_32768	1
75%_64	1
75%_512	1
75%_32768	1
100%_64	1
100%_128	1
100%_256	1
100%_512	1
100%_2048	1

Consolidated Classification Report

Test	Total Samples	True Violations	Predicted Violations	Accuracy	Precision (macro)	Recall (macro)	F1-score (macro)	Precision (weighted)	Recall (weighted)	F1-score (weighted)
base	411	248	243	0.856	0.849	0.853	0.851	0.857	0.856	0.857
0%_64	411	248	225	0.798	0.791	0.801	0.793	0.807	0.798	0.8
0%_128	411	248	233	0.793	0.784	0.792	0.787	0.798	0.793	0.795
0%_256	411	248	225	0.808	0.801	0.811	0.803	0.816	0.808	0.809
0%_512	410	247	208	0.768	0.767	0.778	0.765	0.787	0.768	0.771
0%_1024	411	248	197	0.715	0.72	0.729	0.713	0.743	0.715	0.718
0%_2048	411	248	72	0.513	0.639	0.584	0.488	0.679	0.513	0.465
0%_4096	411	248	86	0.543	0.655	0.607	0.526	0.695	0.543	0.508
0%_8192	411	248	110	0.616	0.709	0.671	0.609	0.75	0.616	0.599
0%_16384	411	248	125	0.618	0.687	0.666	0.615	0.724	0.618	0.607
0%_32768	411	248	80	0.543	0.669	0.61	0.523	0.711	0.543	0.503
25%_64	409	247	259	0.848	0.845	0.835	0.839	0.848	0.848	0.847
25%_128	411	248	266	0.835	0.833	0.818	0.823	0.834	0.835	0.833
25%_256	411	248	264	0.844	0.843	0.829	0.834	0.844	0.844	0.843
25%_512	410	247	259	0.854	0.851	0.841	0.845	0.853	0.854	0.853
25%_1024	411	248	273	0.808	0.807	0.786	0.793	0.807	0.808	0.804
25%_2048	411	248	258	0.805	0.798	0.791	0.794	0.804	0.805	0.804
25%_4096	411	248	279	0.754	0.749	0.727	0.733	0.752	0.754	0.749
25%_8192	411	248	286	0.766	0.767	0.736	0.743	0.767	0.766	0.759
25%_16384	411	248	310	0.723	0.729	0.678	0.682	0.727	0.723	0.705
25%_32768	411	248	265	0.652	0.633	0.628	0.629	0.647	0.652	0.648
50%_64	410	247	266	0.851	0.852	0.835	0.841	0.851	0.851	0.849
50%_128	411	248	263	0.847	0.845	0.832	0.837	0.846	0.847	0.845
50%_256	411	248	261	0.847	0.844	0.833	0.837	0.846	0.847	0.845
50%_512	411	248	261	0.842	0.839	0.828	0.832	0.841	0.842	0.841
50%_1024	410	247	262	0.807	0.802	0.791	0.795	0.806	0.807	0.806
50%_2048	411	248	269	0.764	0.757	0.742	0.747	0.762	0.764	0.761
50%_4096	409	247	280	0.773	0.771	0.745	0.752	0.772	0.773	0.767
50%_8192	411	248	275	0.745	0.737	0.719	0.724	0.741	0.745	0.74
50%_16384	411	248	277	0.662	0.643	0.631	0.634	0.654	0.662	0.655
50%_32768	410	247	175	0.663	0.682	0.686	0.663	0.709	0.663	0.665
75%_64	410	247	264	0.846	0.845	0.831	0.836	0.846	0.846	0.845
75%_128	411	248	265	0.847	0.846	0.831	0.837	0.846	0.847	0.845
75%_256	411	248	262	0.844	0.842	0.83	0.835	0.844	0.844	0.843
75%_512	410	247	265	0.834	0.833	0.817	0.823	0.834	0.834	0.832
75%_1024	411	248	269	0.813	0.81	0.793	0.799	0.812	0.813	0.81
75%_2048	411	248	263	0.798	0.792	0.781	0.785	0.796	0.798	0.796
75%_4096	411	248	274	0.752	0.745	0.727	0.732	0.749	0.752	0.747
75%_8192	411	248	235	0.701	0.69	0.694	0.691	0.706	0.701	0.702
75%_16384	411	248	186	0.64	0.651	0.656	0.639	0.675	0.64	0.643
75%_32768	410	247	171	0.639	0.66	0.663	0.639	0.687	0.639	0.64
100%_64	410	247	259	0.839	0.835	0.826	0.83	0.838	0.839	0.838
100%_128	410	247	264	0.846	0.845	0.831	0.836	0.846	0.846	0.845
100%_256	410	247	256	0.837	0.832	0.825	0.828	0.836	0.837	0.836
100%_512	410	247	263	0.839	0.837	0.824	0.829	0.838	0.839	0.837
100%_1024	411	248	254	0.83	0.823	0.819	0.821	0.829	0.83	0.829
100%_2048	410	248	274	0.79	0.788	0.767	0.773	0.789	0.79	0.786
100%_4096	411	248	305	0.725	0.729	0.683	0.688	0.727	0.725	0.71
100%_8192	411	248	270	0.757	0.749	0.734	0.739	0.754	0.757	0.753
100%_16384	411	248	229	0.706	0.696	0.702	0.698	0.713	0.706	0.708
100%_32768	411	248	305	0.701	0.697	0.657	0.66	0.698	0.701	0.684