Training Loss	Epoch	Step	Accuracy	F1	Validation Loss	Precision	Recall
1.6465	1.0	963	0.9618	0.8738	0.4191	0.8922	0.8561
0.3862	2.0	1926	0.9790	0.9456	0.2318	0.9496	0.9417
0.2326	3.0	2889	0.9854	0.9723	0.1554	0.9751	0.9696
0.1607	4.0	3852	0.9901	0.9788	0.1137	0.9797	0.9780
0.1188	5.0	4815	0.9927	0.9839	0.0863	0.9853	0.9825
0.0921	6.0	5778	0.9934	0.9832	0.0686	0.9842	0.9822
0.0726	7.0	6741	0.9941	0.9848	0.0568	0.9857	0.9839
0.06	8.0	7704	0.9956	0.9886	0.0494	0.9909	0.9864
0.0496	9.0	8667	0.9960	0.9897	0.0421	0.9912	0.9881
0.0406	10.0	9630	0.9970	0.9916	0.0372	0.9920	0.9913
0.0351	11.0	10593	0.9965	0.9890	0.0359	0.9916	0.9864
0.0301	12.0	11556	0.9969	0.9888	0.0331	0.9905	0.9871
0.0251	13.0	12519	0.9975	0.9914	0.0306	0.9926	0.9902
0.0226	14.0	13482	0.9973	0.9913	0.0286	0.9930	0.9895
0.0195	15.0	14445	0.9972	0.9897	0.0271	0.9909	0.9885
0.0168	16.0	15408	0.9977	0.9925	0.0243	0.9937	0.9913
0.0145	17.0	16371	0.9977	0.9916	0.0249	0.9923	0.9909
0.0128	18.0	17334	0.9977	0.9925	0.0226	0.9934	0.9916
0.0116	19.0	18297	0.9975	0.9904	0.0234	0.9926	0.9881
0.0096	20.0	19260	0.9977	0.9918	0.0226	0.9930	0.9906
0.0082	21.0	20223	0.9977	0.9920	0.0248	0.9930	0.9909
0.0075	22.0	21186	0.9978	0.9925	0.0214	0.9934	0.9916
0.0066	23.0	22149	0.9975	0.9907	0.0238	0.9930	0.9885
0.006	24.0	23112	0.9975	0.9904	0.0243	0.9919	0.9888
0.005	25.0	24075	0.9977	0.9930	0.0226	0.9937	0.9923
0.0044	26.0	25038	0.9978	0.9923	0.0212	0.9933	0.9913
0.0037	27.0	26001	0.9978	0.9918	0.0242	0.9933	0.9902
0.0032	28.0	26964	0.9978	0.9921	0.0215	0.9923	0.9920
0.0029	29.0	27927	0.9977	0.9928	0.0226	0.9944	0.9913
0.0024	30.0	28890	0.9977	0.9925	0.0218	0.9930	0.9920
0.0022	31.0	29853	0.9979	0.9930	0.0218	0.9930	0.9930
0.002	32.0	30816	0.9978	0.9934	0.0224	0.9930	0.9937
0.0017	33.0	31779	0.9982	0.9949	0.0216	0.9951	0.9948
0.0015	34.0	32742	0.9982	0.9941	0.0225	0.9944	0.9937
0.0015	35.0	33705	0.9978	0.9939	0.0227	0.9944	0.9934
0.0014	36.0	34668	0.9980	0.9937	0.0224	0.9941	0.9934
0.001	37.0	35631	0.9980	0.9937	0.0228	0.9947	0.9927
0.0009	38.0	36594	0.9980	0.9937	0.0228	0.9941	0.9934
0.0008	39.0	37557	0.9979	0.9934	0.0224	0.9944	0.9923
0.0007	40.0	38520	0.9979	0.9925	0.0245	0.9944	0.9906
0.0007	41.0	39483	0.9980	0.9934	0.0222	0.9941	0.9927
0.0005	42.0	40446	0.9977	0.9927	0.0237	0.9934	0.9920
0.0005	43.0	41409	0.9977	0.9921	0.0229	0.9937	0.9906
0.0006	44.0	42372	0.9978	0.9934	0.0237	0.9944	0.9923
0.0005	45.0	43335	0.9979	0.9935	0.0227	0.9944	0.9927
0.0004	46.0	44298	0.9979	0.9934	0.0228	0.9937	0.9930
0.0004	47.0	45261	0.9979	0.9941	0.0241	0.9948	0.9934
0.0003	48.0	46224	0.9977	0.9921	0.0242	0.9937	0.9906
0.0004	49.0	47187	0.9979	0.9937	0.0235	0.9944	0.9930
0.0003	50.0	48150	0.9978	0.9930	0.0234	0.9934	0.9927
0.0003	51.0	49113	0.9979	0.9934	0.0239	0.9944	0.9923
0.0003	52.0	50076	0.9978	0.9927	0.0240	0.9940	0.9913
0.0002	53.0	51039	0.9976	0.9923	0.0242	0.9930	0.9916
0.0003	54.0	52002	0.9978	0.9927	0.0239	0.9934	0.9920
0.0002	55.0	52965	0.9978	0.9927	0.0240	0.9934	0.9920
0.0002	56.0	53928	0.9979	0.9934	0.0238	0.9944	0.9923
0.0002	57.0	54891	0.9978	0.9927	0.0240	0.9940	0.9913
0.0002	58.0	55854	0.9978	0.9927	0.0240	0.9940	0.9913
0.0002	59.0	56817	0.9978	0.9927	0.0240	0.9940	0.9913
0.0002	60.0	57780	0.9978	0.9927	0.0240	0.9940	0.9913
0.0011	61.0	58743	0.9999	0.9993	0.0002	0.9996	0.9989
0.0006	62.0	59706	0.9999	1.0	0.0005	1.0	1.0
0.0004	63.0	60669	0.9999	0.9993	0.0004	0.9996	0.9989
0.0005	64.0	61632	1.0	1.0	0.0001	1.0	1.0
0.0004	65.0	62595	1.0	1.0	0.0000	1.0	1.0
0.0003	66.0	63558	1.0	1.0	0.0001	1.0	1.0
0.0003	67.0	64521	1.0	1.0	0.0001	1.0	1.0
0.0003	68.0	65484	1.0	1.0	0.0001	1.0	1.0
0.0003	69.0	66447	1.0	1.0	0.0001	1.0	1.0
0.0002	70.0	67410	1.0	1.0	0.0001	1.0	1.0
0.0002	71.0	68373	1.0	1.0	0.0001	1.0	1.0
0.0005	72.0	69336	1.0	1.0	0.0001	1.0	1.0
0.0003	73.0	70299	0.9999	1.0	0.0003	1.0	1.0
0.0003	74.0	71262	0.9999	1.0	0.0003	1.0	1.0
0.0002	75.0	72225	0.9999	1.0	0.0004	1.0	1.0
0.0001	76.0	73188	1.0	1.0	0.0002	1.0	1.0
0.0002	77.0	74151	1.0	1.0	0.0003	1.0	1.0
0.0002	78.0	75114	1.0	1.0	0.0003	1.0	1.0
0.0002	79.0	76077	1.0	1.0	0.0003	1.0	1.0
0.0002	80.0	77040	0.9999	0.9996	0.0006	0.9996	0.9996
0.0001	81.0	78003	1.0	1.0	0.0003	1.0	1.0
0.0001	82.0	78966	0.9998	0.9996	0.0006	0.9996	0.9996
0.0001	83.0	79929	1.0	1.0	0.0003	1.0	1.0
0.0001	84.0	80892	0.9999	0.9996	0.0004	0.9996	0.9996
0.0001	85.0	81855	0.9998	0.9993	0.0004	0.9993	0.9993
0.0002	86.0	82818	0.9998	0.9989	0.0011	0.9989	0.9989
0.0001	87.0	83781	1.0	1.0	0.0004	1.0	1.0
0.0002	88.0	84744	0.9999	0.9996	0.0004	0.9996	0.9996
0.0001	89.0	85707	1.0	1.0	0.0004	1.0	1.0
0.0001	90.0	86670	0.9998	0.9993	0.0005	0.9993	0.9993
0.0001	91.0	87633	0.9999	0.9996	0.0005	0.9996	0.9996
0.0001	92.0	88596	0.9999	0.9996	0.0005	0.9996	0.9996
0.0001	93.0	89559	0.9999	0.9996	0.0005	0.9996	0.9996
0.0001	94.0	90522	0.9999	0.9996	0.0005	0.9996	0.9996
0.0	95.0	91485	0.9999	0.9996	0.0006	0.9996	0.9996
0.0	96.0	92448	0.9997	0.9989	0.0008	0.9985	0.9993
0.0001	97.0	93411	0.9997	0.9993	0.0009	0.9993	0.9993
0.0	98.0	94374	0.9997	0.9993	0.0008	0.9993	0.9993
0.0001	99.0	95337	0.9997	0.9993	0.0008	0.9993	0.9993
0.0001	100.0	96300	0.9996	0.9989	0.0007	0.9989	0.9989
0.0	101.0	97263	0.9994	0.9989	0.0012	0.9989	0.9989
0.0001	102.0	98226	0.9995	0.9989	0.0008	0.9989	0.9989
0.0	103.0	99189	0.9996	0.9989	0.0012	0.9989	0.9989
0.0	104.0	100152	0.9996	0.9989	0.0011	0.9989	0.9989
0.0	105.0	101115	0.9995	0.9989	0.0013	0.9989	0.9989
0.0	106.0	102078	0.9995	0.9989	0.0011	0.9989	0.9989
0.0001	107.0	103041	0.9995	0.9989	0.0008	0.9989	0.9989
0.0001	108.0	104004	0.9996	0.9993	0.0008	0.9993	0.9993
0.0	109.0	104967	0.9996	0.9989	0.0009	0.9989	0.9989
0.0	110.0	105930	1.0	1.0	0.0000	1.0	1.0

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1

opengl106/roberta-base-hangul-2-hanja

roberta-base-hangul-2-hanja

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

opengl106/
roberta-base-hangul-2-hanja