This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the YuchenLi01/MATH_Qwen2.5-1.5BInstruct_DPO_MoreUniqueResponseNoGTv2 dataset. It achieves the following results on the evaluation set:

Loss: 0.4980
Rewards/chosen: -1.0101
Rewards/rejected: -2.5543
Rewards/accuracies: 0.7527
Rewards/margins: 1.5442
Logps/rejected: -63.2592
Logps/chosen: -47.0377
Logits/rejected: -2.1942
Logits/chosen: -2.3520

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Logits/chosen	Logits/rejected	Logps/chosen	Logps/rejected	Validation Loss	Rewards/accuracies	Rewards/chosen	Rewards/margins	Rewards/rejected
0.7055	0.0060	20	-2.2853	-2.1676	-44.5251	-56.8689	0.6989	0.4906	-0.0051	-0.0068	0.0018
0.7347	0.0120	40	-2.2894	-2.1717	-44.5162	-56.8775	0.7004	0.5	-0.0015	0.0001	-0.0017
0.6985	0.0180	60	-2.2883	-2.1709	-44.5074	-56.8714	0.6984	0.5040	0.0020	0.0012	0.0008
0.7376	0.0240	80	-2.2852	-2.1679	-44.5384	-56.8756	0.6983	0.4920	-0.0104	-0.0095	-0.0009
0.6794	0.0300	100	-2.2843	-2.1664	-44.5352	-56.9094	0.6955	0.4893	-0.0091	0.0053	-0.0144
0.693	0.0360	120	-2.2837	-2.1660	-44.5292	-56.9220	0.6941	0.5227	-0.0067	0.0128	-0.0195
0.6569	0.0420	140	-2.2794	-2.1614	-44.5414	-56.9484	0.6926	0.5348	-0.0116	0.0184	-0.0300
0.7148	0.0480	160	-2.2789	-2.1605	-44.5783	-57.0017	0.6892	0.5348	-0.0264	0.0250	-0.0514
0.6548	0.0540	180	-2.2777	-2.1586	-44.5839	-57.0147	0.6840	0.5361	-0.0286	0.0280	-0.0566
0.6874	0.0600	200	-2.2758	-2.1558	-44.6327	-57.1196	0.6790	0.5802	-0.0481	0.0504	-0.0985
0.6756	0.0660	220	-2.2752	-2.1543	-44.6956	-57.2031	0.6728	0.5749	-0.0733	0.0587	-0.1319
0.6556	0.0720	240	-2.2737	-2.1516	-44.7817	-57.3411	0.6680	0.5789	-0.1077	0.0794	-0.1871
0.6646	0.0780	260	-2.2716	-2.1482	-44.8510	-57.4670	0.6610	0.5949	-0.1355	0.1020	-0.2375
0.6122	0.0840	280	-2.2704	-2.1458	-44.9103	-57.6078	0.6521	0.5963	-0.1592	0.1346	-0.2938
0.6396	0.0900	300	-2.2626	-2.1370	-44.9711	-57.7097	0.6467	0.6070	-0.1835	0.1510	-0.3345
0.6777	0.0960	320	-2.2720	-2.1447	-44.9279	-57.7590	0.6382	0.6377	-0.1662	0.1881	-0.3543
0.5935	0.1019	340	-2.2653	-2.1370	-45.0083	-57.9337	0.6281	0.6430	-0.1984	0.2258	-0.4242
0.5894	0.1079	360	-2.2665	-2.1360	-45.1063	-58.1190	0.6208	0.6551	-0.2376	0.2607	-0.4983
0.5787	0.1139	380	-2.2825	-2.1501	-44.9472	-58.0529	0.6146	0.6537	-0.1739	0.2979	-0.4718
0.5208	0.1199	400	-2.2917	-2.1576	-44.8895	-58.1091	0.6079	0.6872	-0.1508	0.3435	-0.4943
0.5457	0.1259	420	-2.3037	-2.1675	-44.8602	-58.1506	0.6018	0.6791	-0.1391	0.3718	-0.5109
0.5948	0.1319	440	-2.3075	-2.1697	-44.8820	-58.2543	0.5951	0.6898	-0.1479	0.4045	-0.5524
0.6303	0.1379	460	-2.3009	-2.1623	-45.0218	-58.4718	0.5907	0.6898	-0.2038	0.4356	-0.6394
0.6042	0.1439	480	-2.3024	-2.1624	-45.1078	-58.6329	0.5848	0.6805	-0.2382	0.4657	-0.7038
0.5795	0.1499	500	-2.3103	-2.1688	-45.1718	-58.8106	0.5803	0.6925	-0.2638	0.5112	-0.7749
0.6283	0.1559	520	-2.3191	-2.1763	-45.1456	-58.9082	0.5787	0.6979	-0.2533	0.5607	-0.8139
0.5894	0.1619	540	-2.3203	-2.1767	-45.1997	-59.0099	0.5750	0.7072	-0.2749	0.5797	-0.8546
0.5024	0.1679	560	-2.3043	-2.1609	-45.3104	-59.1969	0.5711	0.7112	-0.3192	0.6102	-0.9294
0.5222	0.1739	580	-2.3162	-2.1722	-45.2430	-59.1395	0.5646	0.7219	-0.2922	0.6142	-0.9065
0.557	0.1799	600	-2.3230	-2.1782	-45.1342	-59.0866	0.5619	0.7193	-0.2487	0.6366	-0.8853
0.5182	0.1859	620	-2.3259	-2.1797	-45.2064	-59.2183	0.5613	0.7166	-0.2776	0.6604	-0.9380
0.5388	0.1919	640	-2.3464	-2.1989	-45.0701	-59.1088	0.5601	0.7126	-0.2231	0.6711	-0.8942
0.6442	0.1979	660	-2.3387	-2.1911	-45.0646	-59.1116	0.5553	0.7045	-0.2209	0.6744	-0.8953
0.5381	0.2039	680	-2.3470	-2.1991	-45.0472	-59.2349	0.5525	0.7219	-0.2139	0.7307	-0.9446
0.4719	0.2099	700	-2.3596	-2.2103	-45.0439	-59.2720	0.5536	0.7179	-0.2126	0.7469	-0.9595
0.5042	0.2159	720	-2.3614	-2.2116	-45.0492	-59.2903	0.5501	0.7112	-0.2147	0.7521	-0.9668
0.4937	0.2219	740	-2.3665	-2.2168	-44.9583	-59.2415	0.5484	0.7193	-0.1784	0.7689	-0.9473
0.4953	0.2279	760	-2.3541	-2.2044	-45.1939	-59.5528	0.5439	0.7313	-0.2726	0.7992	-1.0718
0.6932	0.2339	780	-2.3317	-2.1820	-45.4534	-59.9212	0.5424	0.7313	-0.3764	0.8427	-1.2191
0.5613	0.2399	800	-2.3197	-2.1699	-45.6725	-60.2706	0.5382	0.7420	-0.4640	0.8949	-1.3589
0.4921	0.2459	820	-2.3361	-2.1862	-45.6399	-60.2098	0.5372	0.7366	-0.4510	0.8836	-1.3346
0.4707	0.2519	840	-2.3126	-2.1637	-45.8031	-60.4152	0.5340	0.7366	-0.5163	0.9005	-1.4167
0.6715	0.2579	860	-2.3273	-2.1779	-45.7153	-60.3435	0.5318	0.7380	-0.4812	0.9069	-1.3881
0.4829	0.2639	880	-2.3043	-2.1557	-45.9375	-60.6541	0.5242	0.7353	-0.5700	0.9423	-1.5123
0.5206	0.2699	900	-2.2747	-2.1266	-46.2625	-61.0452	0.5255	0.7406	-0.7000	0.9687	-1.6688
0.4731	0.2759	920	-2.3080	-2.1588	-45.9313	-60.7659	0.5219	0.7393	-0.5676	0.9895	-1.5570
0.608	0.2819	940	-2.3047	-2.1559	-46.0119	-60.9249	0.5195	0.7460	-0.5998	1.0208	-1.6206
0.5473	0.2879	960	-2.3037	-2.1554	-46.0484	-61.0074	0.5163	0.7353	-0.6144	1.0392	-1.6536
0.576	0.2939	980	-2.2989	-2.1513	-46.0990	-61.0760	0.5158	0.7473	-0.6347	1.0464	-1.6811
0.4638	0.2999	1000	-2.3046	-2.1562	-46.0012	-61.0225	0.5118	0.7473	-0.5955	1.0641	-1.6597
0.5638	0.3058	1020	-2.3204	-2.1714	-45.9103	-60.9969	0.5101	0.7513	-0.5592	1.0903	-1.6494
0.4404	0.3118	1040	-2.3089	-2.1602	-46.0712	-61.2083	0.5080	0.7393	-0.6235	1.1105	-1.7340
0.4169	0.3178	1060	-2.3104	-2.1608	-46.2581	-61.5088	0.5086	0.7540	-0.6983	1.1559	-1.8542
0.5807	0.3238	1080	-2.2968	-2.1473	-46.4681	-61.8251	0.5075	0.7473	-0.7823	1.1985	-1.9807
0.3628	0.3298	1100	-2.2956	-2.1457	-46.7017	-62.1204	0.5075	0.7460	-0.8757	1.2231	-2.0988
0.4541	0.3358	1120	-2.3096	-2.1593	-46.3961	-61.8117	0.5048	0.7607	-0.7535	1.2219	-1.9753
0.4558	0.3418	1140	-2.3086	-2.1571	-46.4655	-61.9408	0.5036	0.75	-0.7813	1.2457	-2.0270
0.422	0.3478	1160	-2.3094	-2.1570	-46.5396	-62.0587	0.5063	0.7513	-0.8109	1.2633	-2.0742
0.5166	0.3538	1180	-2.2981	-2.1469	-46.5314	-62.0585	0.5029	0.7567	-0.8076	1.2664	-2.0741
0.5129	0.3598	1200	-2.3024	-2.1515	-46.4118	-61.9098	0.5024	0.7567	-0.7598	1.2548	-2.0146
0.3801	0.3658	1220	-2.3168	-2.1659	-46.3080	-61.7956	0.5000	0.7553	-0.7183	1.2506	-1.9689
0.6569	0.3718	1240	-2.3143	-2.1627	-46.3528	-61.8228	0.5006	0.7513	-0.7362	1.2436	-1.9798
0.5909	0.3778	1260	-2.2866	-2.1353	-46.6661	-62.1919	0.5013	0.7567	-0.8615	1.2659	-2.1274
0.4925	0.3838	1280	-2.2758	-2.1246	-46.8812	-62.4268	0.5053	0.7473	-0.9475	1.2739	-2.2214
0.3376	0.3898	1300	-2.3138	-2.1617	-46.6289	-62.2246	0.5052	0.7393	-0.8466	1.2939	-2.1405
0.3896	0.3958	1320	-2.3102	-2.1581	-46.7721	-62.3966	0.5061	0.7406	-0.9039	1.3054	-2.2093
0.3296	0.4018	1340	-2.3286	-2.1755	-46.5980	-62.2929	0.5062	0.7433	-0.8342	1.3336	-2.1678
0.5057	0.4078	1360	-2.3189	-2.1657	-46.7016	-62.3379	0.5058	0.7460	-0.8757	1.3101	-2.1858
0.4089	0.4138	1380	-2.3247	-2.1710	-46.7301	-62.4120	0.5052	0.7420	-0.8871	1.3284	-2.2155
0.4226	0.4198	1400	-2.3181	-2.1644	-46.8809	-62.6319	0.5037	0.7460	-0.9474	1.3560	-2.3034
0.5396	0.4258	1420	-2.3080	-2.1541	-47.0223	-62.8065	0.5028	0.7420	-1.0040	1.3693	-2.3733
0.6297	0.4318	1440	-2.3226	-2.1678	-46.8789	-62.7082	0.5042	0.7460	-0.9466	1.3873	-2.3339
0.5291	0.4378	1460	-2.3132	-2.1590	-47.0730	-62.8941	0.5052	0.7513	-1.0243	1.3840	-2.4083
0.4537	0.4438	1480	-2.3011	-2.1471	-47.1581	-63.0492	0.5028	0.7473	-1.0583	1.4121	-2.4704
0.5215	0.4498	1500	-2.3069	-2.1530	-46.9732	-62.8052	0.5015	0.7527	-0.9843	1.3884	-2.3727
0.4856	0.4558	1520	-2.3373	-2.1822	-46.7356	-62.5993	0.5006	0.7580	-0.8893	1.4011	-2.2904
0.474	0.4618	1540	-2.3509	-2.1948	-46.6816	-62.6358	0.5028	0.75	-0.8677	1.4373	-2.3050
0.4017	0.4678	1560	-2.3523	-2.1963	-46.6682	-62.6566	0.5039	0.7513	-0.8623	1.4510	-2.3133
0.4437	0.4738	1580	-2.3700	-2.2135	-46.5801	-62.5242	0.5034	0.7513	-0.8271	1.4332	-2.2603
0.4739	0.4798	1600	-2.3654	-2.2094	-46.6273	-62.5651	0.5046	0.7634	-0.8460	1.4307	-2.2767
0.322	0.4858	1620	-2.3496	-2.1939	-46.6648	-62.5624	0.5027	0.7527	-0.8610	1.4147	-2.2756
0.4128	0.4918	1640	-2.3499	-2.1944	-46.7243	-62.6358	0.5026	0.7447	-0.8848	1.4202	-2.3050
0.4874	0.4978	1660	-2.3534	-2.1980	-46.6724	-62.5818	0.5030	0.7567	-0.8640	1.4194	-2.2834
0.4118	0.5037	1680	-2.3485	-2.1926	-46.7124	-62.6410	0.5017	0.7553	-0.8800	1.4271	-2.3071
0.4362	0.5097	1700	-2.3315	-2.1754	-46.9111	-62.8265	0.5007	0.7527	-0.9595	1.4218	-2.3813
0.3746	0.5157	1720	-2.3182	-2.1626	-46.9114	-62.8130	0.4997	0.7580	-0.9596	1.4163	-2.3759
0.3743	0.5217	1740	-2.3332	-2.1770	-46.8019	-62.6633	0.4997	0.75	-0.9158	1.4002	-2.3160
0.5101	0.5277	1760	-2.3405	-2.1848	-46.7468	-62.5720	0.5002	0.75	-0.8938	1.3857	-2.2795
0.4247	0.5337	1780	-2.3494	-2.1935	-46.6656	-62.5013	0.4996	0.7594	-0.8613	1.3899	-2.2512
0.5874	0.5397	1800	-2.3540	-2.1976	-46.6201	-62.5506	0.5001	0.7567	-0.8431	1.4278	-2.2709
0.491	0.5457	1820	-2.3623	-2.2055	-46.5554	-62.4651	0.5004	0.7553	-0.8172	1.4195	-2.2367
0.4323	0.5517	1840	-2.3775	-2.2207	-46.4602	-62.3548	0.5020	0.7527	-0.7791	1.4135	-2.1926
0.3788	0.5577	1860	-2.3774	-2.2210	-46.4423	-62.3485	0.5006	0.7620	-0.7720	1.4181	-2.1901
0.6079	0.5637	1880	-2.3634	-2.2073	-46.5585	-62.4633	0.4996	0.7580	-0.8184	1.4176	-2.2360
0.3904	0.5697	1900	-2.3577	-2.2016	-46.7091	-62.6016	0.4995	0.7447	-0.8787	1.4126	-2.2913
0.5989	0.5757	1920	-2.3527	-2.1965	-46.6279	-62.5435	0.4973	0.7473	-0.8462	1.4218	-2.2681
0.5609	0.5817	1940	-2.3544	-2.1980	-46.7169	-62.6271	0.4976	0.75	-0.8818	1.4197	-2.3015
0.5269	0.5877	1960	-2.3586	-2.2021	-46.6514	-62.5399	0.4956	0.7460	-0.8556	1.4110	-2.2666
0.5666	0.5937	1980	-2.3638	-2.2070	-46.5906	-62.5074	0.4986	0.7513	-0.8313	1.4223	-2.2536
0.3576	0.5997	2000	-2.3686	-2.2117	-46.5180	-62.4090	0.4990	0.7553	-0.8022	1.4120	-2.2143
0.3778	0.6057	2020	0.4990	-0.8234	-2.2447	0.75	1.4213	-62.4851	-46.5709	-2.2096	-2.3663
0.3999	0.6117	2040	0.4996	-0.8418	-2.2611	0.7473	1.4193	-62.5261	-46.6169	-2.2054	-2.3619
0.5654	0.6177	2060	0.4994	-0.8743	-2.2987	0.7420	1.4244	-62.6201	-46.6982	-2.1961	-2.3522
0.3711	0.6237	2080	0.5022	-0.8796	-2.3146	0.7393	1.4350	-62.6599	-46.7114	-2.2002	-2.3567
0.4373	0.6297	2100	0.5032	-0.8625	-2.2934	0.7433	1.4309	-62.6068	-46.6686	-2.2069	-2.3634
0.5001	0.6357	2120	0.4997	-0.8932	-2.3287	0.7473	1.4356	-62.6951	-46.7453	-2.2014	-2.3580
0.5004	0.6417	2140	0.5004	-0.9389	-2.3688	0.7594	1.4299	-62.7954	-46.8596	-2.1860	-2.3419
0.3028	0.6477	2160	0.5008	-0.9374	-2.3621	0.7447	1.4246	-62.7784	-46.8559	-2.1927	-2.3490
0.3098	0.6537	2180	0.5010	-0.9487	-2.4117	0.7540	1.4631	-62.9026	-46.8840	-2.1948	-2.3515
0.4898	0.6597	2200	0.5035	-0.9652	-2.4244	0.7527	1.4593	-62.9344	-46.9253	-2.2074	-2.3643
0.4337	0.6657	2220	0.5023	-0.9542	-2.4257	0.7527	1.4715	-62.9376	-46.8979	-2.1982	-2.3549
0.3089	0.6717	2240	0.5047	-0.9240	-2.3781	0.7393	1.4541	-62.8186	-46.8223	-2.2114	-2.3685
0.4041	0.6777	2260	0.5032	-0.9119	-2.3898	0.7406	1.4779	-62.8479	-46.7922	-2.2123	-2.3694
0.3195	0.6837	2280	0.5018	-0.9343	-2.4248	0.7447	1.4905	-62.9353	-46.8481	-2.2056	-2.3626
0.3049	0.6897	2300	0.5019	-0.9488	-2.4335	0.7460	1.4846	-62.9570	-46.8845	-2.2035	-2.3609
0.2605	0.6957	2320	0.5023	-0.9590	-2.4455	0.7513	1.4864	-62.9870	-46.9099	-2.2039	-2.3613
0.5969	0.7016	2340	0.5026	-0.9351	-2.4207	0.7420	1.4856	-62.9250	-46.8501	-2.2121	-2.3696
0.4384	0.7076	2360	0.5009	-0.9264	-2.4294	0.7487	1.5030	-62.9469	-46.8283	-2.2179	-2.3759
0.3705	0.7136	2380	0.4998	-0.9137	-2.4146	0.7473	1.5008	-62.9097	-46.7967	-2.2191	-2.3771
0.5251	0.7196	2400	0.5015	-0.9100	-2.4043	0.7567	1.4943	-62.8842	-46.7874	-2.2186	-2.3766
0.6183	0.7256	2420	0.5020	-0.9256	-2.4276	0.75	1.5020	-62.9423	-46.8263	-2.2122	-2.3698
0.5566	0.7316	2440	0.5019	-0.9236	-2.4138	0.7406	1.4902	-62.9079	-46.8214	-2.2155	-2.3735
0.2601	0.7376	2460	0.5012	-0.9025	-2.4075	0.7380	1.5050	-62.8920	-46.7685	-2.2146	-2.3729
0.5823	0.7436	2480	0.4996	-0.9134	-2.4161	0.7460	1.5027	-62.9135	-46.7959	-2.2129	-2.3712
0.6226	0.7496	2500	0.5008	-0.9326	-2.4280	0.7540	1.4953	-62.9432	-46.8440	-2.2066	-2.3645
0.3423	0.7556	2520	0.5004	-0.9682	-2.4463	0.7487	1.4781	-62.9891	-46.9329	-2.2030	-2.3607
0.4267	0.7616	2540	0.5011	-0.9619	-2.4668	0.7553	1.5048	-63.0402	-46.9172	-2.2000	-2.3578
0.4629	0.7676	2560	0.5008	-0.9768	-2.4837	0.7433	1.5068	-63.0825	-46.9545	-2.1994	-2.3574
0.5683	0.7736	2580	0.5002	-0.9858	-2.4965	0.7487	1.5107	-63.1145	-46.9768	-2.2013	-2.3594
0.2467	0.7796	2600	0.5002	-0.9820	-2.4955	0.7487	1.5134	-63.1120	-46.9675	-2.1970	-2.3549
0.4684	0.7856	2620	0.4985	-1.0035	-2.5271	0.7527	1.5236	-63.1911	-47.0211	-2.1962	-2.3541
0.4296	0.7916	2640	0.5019	-0.9901	-2.5128	0.7567	1.5227	-63.1552	-46.9876	-2.1993	-2.3575
0.3726	0.7976	2660	0.5019	-1.0055	-2.5212	0.7313	1.5157	-63.1764	-47.0262	-2.2006	-2.3587
0.3626	0.8036	2680	0.5007	-0.9967	-2.5259	0.75	1.5292	-63.1880	-47.0042	-2.2001	-2.3581
0.4846	0.8096	2700	0.5010	-0.9904	-2.5142	0.7567	1.5238	-63.1588	-46.9883	-2.2065	-2.3649
0.3206	0.8156	2720	0.5018	-0.9954	-2.5254	0.7447	1.5299	-63.1867	-47.0009	-2.2060	-2.3641
0.4232	0.8216	2740	0.5010	-0.9998	-2.5309	0.75	1.5311	-63.2004	-47.0118	-2.2108	-2.3691
0.3124	0.8276	2760	0.4991	-0.9982	-2.5247	0.7527	1.5265	-63.1851	-47.0079	-2.2032	-2.3612
0.6006	0.8336	2780	0.5012	-1.0010	-2.5311	0.7473	1.5302	-63.2011	-47.0148	-2.2035	-2.3615
0.4001	0.8396	2800	0.5006	-1.0123	-2.5344	0.7433	1.5221	-63.2092	-47.0431	-2.2032	-2.3613
0.2956	0.8456	2820	0.4991	-1.0133	-2.5414	0.75	1.5281	-63.2268	-47.0455	-2.1966	-2.3544
0.324	0.8516	2840	0.5005	-1.0131	-2.5234	0.7460	1.5103	-63.1818	-47.0451	-2.1950	-2.3528
0.449	0.8576	2860	0.4993	-1.0130	-2.5371	0.75	1.5240	-63.2160	-47.0449	-2.1997	-2.3579
0.4486	0.8636	2880	0.4997	-1.0105	-2.5331	0.7460	1.5225	-63.2060	-47.0387	-2.2006	-2.3586
0.3344	0.8696	2900	0.4986	-1.0053	-2.5299	0.7460	1.5246	-63.1981	-47.0256	-2.2036	-2.3616
0.4127	0.8756	2920	0.5001	-1.0177	-2.5352	0.7473	1.5174	-63.2112	-47.0567	-2.2012	-2.3595
0.3386	0.8816	2940	0.5000	-1.0114	-2.5373	0.7433	1.5259	-63.2166	-47.0410	-2.1961	-2.3539
0.3315	0.8876	2960	0.5000	-1.0077	-2.5379	0.7460	1.5302	-63.2180	-47.0315	-2.1989	-2.3569
0.3969	0.8936	2980	0.4998	-1.0208	-2.5367	0.7460	1.5158	-63.2150	-47.0645	-2.1978	-2.3558
0.3992	0.8996	3000	0.5008	-1.0073	-2.5375	0.7447	1.5302	-63.2170	-47.0306	-2.2016	-2.3599
0.5569	0.9055	3020	0.5001	-1.0161	-2.5394	0.7433	1.5232	-63.2217	-47.0527	-2.2005	-2.3588
0.4103	0.9115	3040	0.4998	-1.0076	-2.5406	0.7513	1.5329	-63.2248	-47.0315	-2.1997	-2.3580
0.3535	0.9175	3060	0.4999	-1.0124	-2.5368	0.7473	1.5244	-63.2154	-47.0435	-2.1993	-2.3576
0.321	0.9235	3080	0.5005	-1.0080	-2.5326	0.7473	1.5246	-63.2049	-47.0325	-2.1986	-2.3567
0.4006	0.9295	3100	0.4993	-1.0193	-2.5416	0.75	1.5222	-63.2273	-47.0607	-2.1963	-2.3543
0.2845	0.9355	3120	0.4997	-1.0138	-2.5372	0.7460	1.5234	-63.2162	-47.0468	-2.1971	-2.3552
0.3671	0.9415	3140	0.4999	-1.0219	-2.5399	0.7420	1.5179	-63.2229	-47.0672	-2.1984	-2.3566
0.3564	0.9475	3160	0.5000	-1.0195	-2.5522	0.7380	1.5326	-63.2537	-47.0612	-2.1938	-2.3517
0.3708	0.9535	3180	0.4996	-1.0142	-2.5488	0.7433	1.5346	-63.2453	-47.0479	-2.1942	-2.3521
0.502	0.9595	3200	0.5011	-1.0239	-2.5450	0.7540	1.5211	-63.2357	-47.0721	-2.1970	-2.3551
0.3105	0.9655	3220	0.5012	-1.0237	-2.5544	0.7406	1.5306	-63.2593	-47.0717	-2.1919	-2.3495
0.3818	0.9715	3240	0.5001	-1.0161	-2.5546	0.7406	1.5385	-63.2597	-47.0526	-2.1936	-2.3517
0.4288	0.9775	3260	0.5004	-1.0141	-2.5463	0.75	1.5322	-63.2390	-47.0476	-2.1946	-2.3527
0.3683	0.9835	3280	0.4986	-1.0155	-2.5503	0.75	1.5348	-63.2490	-47.0511	-2.1916	-2.3494
0.5055	0.9895	3300	0.4989	-1.0205	-2.5595	0.7540	1.5390	-63.2721	-47.0637	-2.1933	-2.3513
0.5467	0.9955	3320	0.5001	-1.0257	-2.5502	0.7553	1.5245	-63.2488	-47.0765	-2.1941	-2.3522

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu121
Datasets 3.5.0
Tokenizers 0.20.3

YuchenLi01/generatedMoreUniqueResponseNoGTv2_Qwen2.5-1.5BInstruct_dpo_ebs32_lr5e-07_beta0.4_42

generatedMoreUniqueResponseNoGTv2_Qwen2.5-1.5BInstruct_dpo_ebs32_lr5e-07_beta0.4_42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

YuchenLi01/
generatedMoreUniqueResponseNoGTv2_Qwen2.5-1.5BInstruct_dpo_ebs32_lr5e-07_beta0.4_42