Training Loss	Epoch	Step	Validation Loss
3.3871	0.0726	5	3.3655
3.3871	0.1452	10	3.3647
3.3803	0.2178	15	3.3565
3.3805	0.2904	20	3.3356
3.3594	0.3630	25	3.3235
3.3176	0.4356	30	3.2750
3.2745	0.5082	35	3.2223
3.2213	0.5808	40	3.1806
3.1731	0.6534	45	3.1379
3.1148	0.7260	50	3.0849
3.0721	0.7985	55	3.0357
3.0146	0.8711	60	2.9888
2.9581	0.9437	65	2.9514
2.9168	1.0163	70	2.9118
2.8825	1.0889	75	2.8696
2.815	1.1615	80	2.8313
2.7917	1.2341	85	2.7985
2.7416	1.3067	90	2.7706
2.7187	1.3793	95	2.7464
2.6782	1.4519	100	2.7241
2.6687	1.5245	105	2.7034
2.6368	1.5971	110	2.6834
2.6216	1.6697	115	2.6638
2.5897	1.7423	120	2.6442
2.566	1.8149	125	2.6251
2.5623	1.8875	130	2.6071
2.5139	1.9601	135	2.5896
2.5138	2.0327	140	2.5729
2.4781	2.1053	145	2.5577
2.4513	2.1779	150	2.5432
2.4447	2.2505	155	2.5296
2.4309	2.3230	160	2.5163
2.4089	2.3956	165	2.5033
2.386	2.4682	170	2.4912
2.3621	2.5408	175	2.4795
2.3626	2.6134	180	2.4688
2.354	2.6860	185	2.4586
2.337	2.7586	190	2.4489
2.3212	2.8312	195	2.4396
2.3032	2.9038	200	2.4311
2.3043	2.9764	205	2.4233
2.2769	3.0490	210	2.4159
2.2785	3.1216	215	2.4090
2.2591	3.1942	220	2.4018
2.2538	3.2668	225	2.3955
2.2424	3.3394	230	2.3895
2.2317	3.4120	235	2.3839
2.2209	3.4846	240	2.3779
2.2206	3.5572	245	2.3728
2.2032	3.6298	250	2.3681
2.1945	3.7024	255	2.3633
2.1829	3.7750	260	2.3588
2.1839	3.8475	265	2.3548
2.1681	3.9201	270	2.3502
2.1875	3.9927	275	2.3467
2.1551	4.0653	280	2.3428
2.1575	4.1379	285	2.3398
2.138	4.2105	290	2.3364
2.1269	4.2831	295	2.3332
2.1225	4.3557	300	2.3302
2.1403	4.4283	305	2.3270
2.115	4.5009	310	2.3246
2.1144	4.5735	315	2.3223
2.1167	4.6461	320	2.3197
2.0975	4.7187	325	2.3176
2.1161	4.7913	330	2.3151
2.0961	4.8639	335	2.3130
2.0721	4.9365	340	2.3117
2.1003	5.0091	345	2.3095
2.0827	5.0817	350	2.3080
2.0784	5.1543	355	2.3056
2.0616	5.2269	360	2.3047
2.0536	5.2995	365	2.3035
2.0656	5.3721	370	2.3012
2.0627	5.4446	375	2.3009
2.0558	5.5172	380	2.2993
2.0454	5.5898	385	2.2970
2.0547	5.6624	390	2.2960
2.0477	5.7350	395	2.2952
2.0449	5.8076	400	2.2936
2.0317	5.8802	405	2.2928
2.0234	5.9528	410	2.2916
2.0489	6.0254	415	2.2906
2.0208	6.0980	420	2.2904
2.009	6.1706	425	2.2883
2.023	6.2432	430	2.2882
2.0126	6.3158	435	2.2874
2.0229	6.3884	440	2.2862
2.012	6.4610	445	2.2859
2.0336	6.5336	450	2.2848
2.0016	6.6062	455	2.2842
2.018	6.6788	460	2.2833
1.994	6.7514	465	2.2829
2.0003	6.8240	470	2.2825
1.9893	6.8966	475	2.2816
2.0078	6.9691	480	2.2814
1.9903	7.0417	485	2.2815
1.9837	7.1143	490	2.2811
1.9765	7.1869	495	2.2802
2.0064	7.2595	500	2.2795
1.9774	7.3321	505	2.2797
1.9905	7.4047	510	2.2796
1.9814	7.4773	515	2.2788
1.9765	7.5499	520	2.2786
2.0035	7.6225	525	2.2782
1.998	7.6951	530	2.2778
1.9762	7.7677	535	2.2773
1.9899	7.8403	540	2.2770
1.9743	7.9129	545	2.2771
1.969	7.9855	550	2.2771
1.9979	8.0581	555	2.2768
1.9877	8.1307	560	2.2766
1.9519	8.2033	565	2.2767
1.9811	8.2759	570	2.2765
1.9768	8.3485	575	2.2762
1.9799	8.4211	580	2.2761
1.976	8.4936	585	2.2760
1.9621	8.5662	590	2.2761
1.9738	8.6388	595	2.2761
1.9678	8.7114	600	2.2760
1.9908	8.7840	605	2.2759
1.9666	8.8566	610	2.2758
1.9544	8.9292	615	2.2756
1.9675	9.0018	620	2.2755
1.9718	9.0744	625	2.2755
1.9626	9.1470	630	2.2754
1.9658	9.2196	635	2.2754
1.9748	9.2922	640	2.2754
1.9651	9.3648	645	2.2754
1.9778	9.4374	650	2.2754
1.963	9.5100	655	2.2754
1.9762	9.5826	660	2.2754
1.9725	9.6552	665	2.2754
1.9558	9.7278	670	2.2754
1.9865	9.8004	675	2.2754
1.974	9.8730	680	2.2754

Framework versions

Transformers 4.42.0
Pytorch 2.3.0+cu121
Datasets 3.2.0
Tokenizers 0.19.1

hZzy/qwen2.5-0.5b-sft-25-1

qwen2.5-0.5b-sft-25-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hZzy/
qwen2.5-0.5b-sft-25-1