Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6949	0.2	25	0.6922	-0.0089	-0.0113	0.5600	0.0023	-18.5922	-18.5640	-1.0661	-1.0649
0.689	0.4	50	0.6902	-0.0743	-0.0808	0.5700	0.0065	-18.8241	-18.7820	-1.0662	-1.0650
0.6966	0.6	75	0.6990	-0.0262	-0.0204	0.4500	-0.0058	-18.6227	-18.6216	-1.0666	-1.0653
0.6628	0.8	100	0.7163	-0.1175	-0.1132	0.4600	-0.0042	-18.9322	-18.9257	-1.0693	-1.0680
0.692	1.0	125	0.6770	-0.4575	-0.5466	0.5400	0.0891	-20.3768	-20.0594	-1.0732	-1.0720
0.6693	1.2	150	0.6778	0.0628	0.0073	0.4600	0.0556	-18.5305	-18.3248	-1.0700	-1.0688
0.6358	1.4	175	0.6447	-0.0808	-0.1871	0.7200	0.1063	-19.1785	-18.8037	-1.0724	-1.0710
0.627	1.6	200	0.6223	-0.0635	-0.2328	0.6900	0.1694	-19.3307	-18.7457	-1.0750	-1.0734
0.6163	1.8	225	0.6078	0.1586	-0.0295	0.8300	0.1881	-18.6531	-18.0056	-1.0740	-1.0727
0.5879	2.0	250	0.5946	0.2347	0.0161	0.8600	0.2186	-18.5009	-17.7518	-1.0749	-1.0735
0.588	2.2	275	0.5825	0.2732	0.0240	0.8800	0.2492	-18.4746	-17.6235	-1.0745	-1.0730
0.5607	2.4	300	0.5795	0.3193	0.0624	0.8700	0.2569	-18.3468	-17.4698	-1.0740	-1.0725
0.5638	2.6	325	0.5721	0.2799	0.0027	0.8500	0.2773	-18.5457	-17.6011	-1.0737	-1.0720
0.5517	2.8	350	0.5692	0.2893	0.0067	0.8700	0.2827	-18.5325	-17.5698	-1.0736	-1.0721
0.5583	3.0	375	0.5723	0.3229	0.0461	0.8600	0.2769	-18.4011	-17.4578	-1.0740	-1.0725
0.5788	3.2	400	0.5717	0.3320	0.0544	0.8700	0.2777	-18.3734	-17.4274	-1.0742	-1.0727
0.5539	3.4	425	0.5717	0.3320	0.0544	0.8700	0.2777	-18.3734	-17.4274	-1.0742	-1.0727