Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.2048	0.03	100	0.1816	1.0172	-1.5955	0.9529	2.6127	-418.1306	-252.7848	-2.6883	-2.7595
0.1279	0.07	200	0.1099	1.8935	-2.9215	0.9621	4.8150	-431.3906	-244.0213	-2.6659	-2.7438
0.075	0.1	300	0.1084	2.6393	-3.1267	0.9790	5.7660	-433.4421	-236.5630	-2.6463	-2.7255
0.0656	0.14	400	0.0670	2.6754	-4.3127	0.9840	6.9881	-445.3022	-236.2028	-2.6321	-2.7143
0.0314	0.17	500	0.0444	2.7614	-5.7538	0.9857	8.5151	-459.7131	-235.3429	-2.6533	-2.7261
0.0569	0.2	600	0.0820	1.8055	-9.1246	0.9781	10.9302	-493.4217	-244.9012	-2.6261	-2.7256
0.0154	0.24	700	0.0703	1.5280	-13.2088	0.9857	14.7368	-534.2635	-247.6769	-2.5799	-2.6689
0.032	0.27	800	0.0583	1.4588	-11.3987	0.9891	12.8575	-516.1622	-248.3688	-2.5761	-2.6670
0.0376	0.31	900	0.0440	0.8776	-15.7795	0.9924	16.6572	-559.9705	-254.1801	-2.5745	-2.6553
0.1198	0.34	1000	0.0460	0.7615	-22.5125	0.9933	23.2740	-627.3004	-255.3416	-2.6308	-2.7357
0.0438	0.37	1100	0.0293	1.1199	-14.6644	0.9949	15.7842	-548.8188	-251.7577	-2.7728	-2.8744
0.0368	0.41	1200	0.0349	1.4988	-18.6893	0.9924	20.1881	-589.0681	-247.9686	-2.6827	-2.7834
0.0218	0.44	1300	0.1406	1.9168	-13.4986	0.9739	15.4154	-537.1611	-243.7885	-2.4356	-2.5455
0.0302	0.48	1400	0.0197	0.3550	-20.3640	0.9941	20.7190	-605.8153	-259.4061	-2.5041	-2.5799
0.0114	0.51	1500	0.0231	1.0578	-17.2156	0.9958	18.2735	-574.3317	-252.3781	-2.4380	-2.5036
0.0108	0.54	1600	0.0267	0.7739	-19.6130	0.9966	20.3868	-598.3051	-255.2180	-2.5048	-2.6017
0.0142	0.58	1700	0.0431	-0.7071	-25.1890	0.9966	24.4819	-654.0657	-270.0278	-2.6207	-2.7770
0.0367	0.61	1800	0.0242	0.5459	-19.8798	0.9966	20.4258	-600.9736	-257.4970	-2.6528	-2.8159
0.0123	0.65	1900	0.0170	0.2873	-21.3637	0.9958	21.6510	-615.8121	-260.0836	-2.7699	-2.9451
0.0279	0.68	2000	0.0238	1.3430	-17.5880	0.9941	18.9309	-578.0551	-249.5269	-2.6516	-2.8237
0.0049	0.71	2100	0.0199	-0.1106	-27.2864	0.9941	27.1758	-675.0391	-264.0627	-2.6269	-2.8199
0.0028	0.75	2200	0.0181	0.1829	-26.3264	0.9941	26.5094	-665.4396	-261.1270	-2.7200	-2.9244
0.0166	0.78	2300	0.0194	-0.3610	-25.2795	0.9958	24.9185	-654.9701	-266.5665	-2.6358	-2.7824
0.021	0.82	2400	0.0227	1.2726	-24.2662	0.9983	25.5388	-644.8376	-250.2310	-2.6171	-2.7585
0.014	0.85	2500	0.0168	0.1132	-29.5821	0.9983	29.6953	-697.9961	-261.8245	-2.6238	-2.7765
0.0035	0.88	2600	0.0267	0.7916	-24.8514	0.9983	25.6430	-650.6893	-255.0403	-2.5649	-2.7397
0.0208	0.92	2700	0.0090	0.5092	-28.5463	0.9983	29.0555	-687.6382	-257.8649	-2.5661	-2.7543
0.0253	0.95	2800	0.0103	0.8823	-30.6264	0.9966	31.5087	-708.4396	-254.1338	-2.6179	-2.8054
0.0028	0.99	2900	0.0112	1.2910	-25.2950	0.9983	26.5860	-655.1255	-250.0463	-2.6939	-2.9014
0.0019	1.02	3000	0.0149	-0.5923	-26.9350	0.9983	26.3427	-671.5254	-268.8800	-2.6026	-2.8588
0.0013	1.05	3100	0.0120	0.2408	-27.8722	0.9983	28.1130	-680.8969	-260.5484	-2.7120	-2.9730
0.0014	1.09	3200	0.0098	1.7422	-24.9625	0.9983	26.7047	-651.8002	-245.5344	-2.7375	-2.9656
0.0007	1.12	3300	0.0158	1.3878	-24.7373	0.9975	26.1251	-649.5485	-249.0786	-2.7624	-2.9950
0.0032	1.16	3400	0.0130	0.9357	-27.4065	0.9992	28.3422	-676.2398	-253.5992	-2.7870	-3.0069
0.0008	1.19	3500	0.0107	0.7496	-28.7658	0.9992	29.5154	-689.8333	-255.4606	-2.7988	-3.0340
0.0004	1.22	3600	0.0091	0.6703	-30.1929	0.9992	30.8631	-704.1040	-256.2537	-2.7427	-2.9740
0.0039	1.26	3700	0.0098	0.5756	-28.2500	0.9983	28.8255	-684.6750	-257.2008	-2.7343	-2.9647
0.0017	1.29	3800	0.0068	-0.0529	-33.0047	0.9975	32.9518	-732.2226	-263.4854	-2.7187	-2.9478
0.0043	1.33	3900	0.0061	0.2318	-31.5623	0.9983	31.7940	-717.7981	-260.6389	-2.7301	-2.9546
0.0044	1.36	4000	0.0061	-0.4835	-34.3777	0.9975	33.8941	-745.9522	-267.7920	-2.7024	-2.9245
0.0008	1.39	4100	0.0048	0.4070	-31.0079	0.9975	31.4149	-712.2544	-258.8862	-2.6586	-2.8669
0.0013	1.43	4200	0.0067	0.2262	-27.6468	0.9983	27.8730	-678.6434	-260.6947	-2.6572	-2.8776
0.0139	1.46	4300	0.0089	0.1431	-38.3175	0.9966	38.4606	-785.3500	-261.5256	-2.6647	-2.8567
0.0005	1.5	4400	0.0052	1.1567	-28.1924	0.9983	29.3490	-684.0989	-251.3895	-2.6746	-2.8756
0.0017	1.53	4500	0.0048	0.9539	-28.4808	0.9983	29.4348	-686.9838	-253.4173	-2.6321	-2.8397
0.0076	1.56	4600	0.0053	1.2200	-25.8289	0.9975	27.0489	-660.4644	-250.7563	-2.6732	-2.8768
0.0073	1.6	4700	0.0037	0.5422	-29.8961	0.9975	30.4383	-701.1363	-257.5345	-2.6687	-2.8635
0.0064	1.63	4800	0.0058	0.1897	-35.1189	0.9975	35.3086	-753.3646	-261.0594	-2.8192	-3.0418
0.0027	1.67	4900	0.0035	1.0140	-29.5701	0.9983	30.5841	-697.8760	-252.8162	-2.7731	-2.9981
0.0004	1.7	5000	0.0025	1.5574	-25.0463	0.9983	26.6037	-652.6386	-247.3826	-2.7513	-2.9753
0.008	1.73	5100	0.0026	1.1263	-30.3188	0.9983	31.4451	-705.3633	-251.6933	-2.7995	-3.0092
0.0015	1.77	5200	0.0020	1.3119	-29.0704	0.9983	30.3824	-692.8795	-249.8371	-2.7971	-3.0186
0.0021	1.8	5300	0.0024	0.7331	-31.3066	0.9975	32.0396	-715.2409	-255.6256	-2.7968	-2.9833
0.0014	1.84	5400	0.0018	1.4142	-28.7232	0.9975	30.1374	-689.4075	-248.8142	-2.8127	-2.9997
0.0002	1.87	5500	0.0036	0.2662	-33.0751	0.9975	33.3414	-732.9266	-260.2943	-2.7900	-2.9893
0.0123	1.9	5600	0.0034	0.8622	-29.0743	0.9983	29.9365	-692.9180	-254.3346	-2.7901	-2.9879
0.0022	1.94	5700	0.0027	1.4619	-26.1686	0.9983	27.6305	-663.8615	-248.3373	-2.7543	-2.9437
0.0023	1.97	5800	0.0026	1.3065	-29.0318	0.9992	30.3383	-692.4929	-249.8912	-2.7777	-2.9641
0.0002	2.01	5900	0.0024	1.3466	-31.8791	0.9992	33.2256	-720.9660	-249.4908	-2.7919	-2.9806
0.0004	2.04	6000	0.0024	1.2456	-33.3469	0.9992	34.5924	-735.6440	-250.5009	-2.7884	-2.9774
0.0002	2.07	6100	0.0051	0.8107	-37.2426	0.9983	38.0533	-774.6013	-254.8491	-2.8039	-2.9851
0.0025	2.11	6200	0.0053	1.2104	-32.6969	0.9983	33.9073	-729.1440	-250.8525	-2.7910	-2.9641
0.001	2.14	6300	0.0050	1.5723	-30.7677	0.9983	32.3400	-709.8519	-247.2332	-2.7886	-2.9728
0.0062	2.18	6400	0.0062	1.0454	-32.4375	0.9983	33.4829	-726.5503	-252.5022	-2.7689	-2.9530
0.0006	2.21	6500	0.0050	1.2958	-32.8746	0.9992	34.1704	-730.9218	-249.9990	-2.7450	-2.9272
0.0011	2.24	6600	0.0035	1.8455	-29.7702	0.9992	31.6158	-699.8776	-244.5013	-2.7935	-2.9672
0.0001	2.28	6700	0.0040	2.0206	-29.9992	0.9992	32.0197	-702.1669	-242.7507	-2.8074	-2.9801
0.0002	2.31	6800	0.0042	1.5238	-33.6284	0.9992	35.1522	-738.4594	-247.7182	-2.7943	-2.9749
0.0246	2.35	6900	0.0039	0.7561	-35.1964	0.9992	35.9525	-754.1393	-255.3954	-2.7779	-2.9606
0.0011	2.38	7000	0.0038	1.1395	-31.9450	0.9992	33.0845	-721.6255	-251.5618	-2.7762	-2.9534
0.0001	2.41	7100	0.0040	1.2345	-34.3482	0.9992	35.5827	-745.6570	-250.6111	-2.7624	-2.9515
0.0002	2.45	7200	0.0034	1.6020	-32.1494	0.9992	33.7514	-723.6697	-246.9365	-2.7747	-2.9635
0.0046	2.48	7300	0.0036	1.6314	-32.1292	0.9992	33.7605	-723.4673	-246.6430	-2.7679	-2.9556
0.0023	2.52	7400	0.0035	1.4778	-33.5251	0.9992	35.0028	-737.4260	-248.1789	-2.7722	-2.9629
0.0011	2.55	7500	0.0034	1.6981	-32.6639	0.9992	34.3620	-728.8140	-245.9752	-2.7916	-2.9806
0.0012	2.58	7600	0.0032	1.7076	-32.6830	0.9992	34.3906	-729.0056	-245.8805	-2.7888	-2.9758
0.0001	2.62	7700	0.0034	2.0561	-29.7915	0.9992	31.8476	-700.0899	-242.3954	-2.7837	-2.9656
0.0	2.65	7800	0.0033	2.0375	-30.3971	0.9992	32.4345	-706.1458	-242.5820	-2.7782	-2.9618
0.0027	2.69	7900	0.0031	1.8698	-31.1258	0.9992	32.9955	-713.4329	-244.2589	-2.7837	-2.9739
0.0001	2.72	8000	0.0029	1.8124	-32.0635	0.9992	33.8759	-722.8105	-244.8322	-2.7619	-2.9524
0.0	2.75	8100	0.0029	1.7514	-32.6143	0.9992	34.3656	-728.3180	-245.4429	-2.7594	-2.9517
0.0001	2.79	8200	0.0029	1.7056	-33.0849	0.9992	34.7904	-733.0240	-245.9009	-2.7606	-2.9530
0.0	2.82	8300	0.0030	1.6349	-32.8211	0.9992	34.4560	-730.3865	-246.6072	-2.7437	-2.9371
0.0001	2.86	8400	0.0029	1.5951	-32.9498	0.9992	34.5450	-731.6738	-247.0051	-2.7438	-2.9386
0.0001	2.89	8500	0.0029	1.5667	-32.9358	0.9992	34.5025	-731.5333	-247.2896	-2.7541	-2.9497
0.0029	2.92	8600	0.0029	1.4986	-33.3107	0.9992	34.8093	-735.2822	-247.9706	-2.7541	-2.9514
0.0013	2.96	8700	0.0029	1.4945	-33.3218	0.9992	34.8163	-735.3931	-248.0111	-2.7544	-2.9518
0.0004	2.99	8800	0.0029	1.4978	-33.2941	0.9992	34.7920	-735.1168	-247.9782	-2.7547	-2.9525

Framework versions

Transformers 4.35.0
Pytorch 2.1.1+cu121
Datasets 2.14.6
Tokenizers 0.14.1

yihang7/Mistral-7B-v0.1-dpo-full-hydrox-safe

Mistral-7B-v0.1-dpo-full-hydrox-safe

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yihang7/
Mistral-7B-v0.1-dpo-full-hydrox-safe