chinese-lert-small-ner

This model is a fine-tuned version of hfl/chinese-lert-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0515
• Overall Precision: 0.9025
• Overall Recall: 0.9137
• Overall F1: 0.9081
• Overall Accuracy: 0.9888
• Ucm: 0.8877
• Lcm: 0.8832

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: 0.0001
• train_batch_size: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Ucm	Lcm
0.8943	0.08	10	0.7196	0.0	0.0	0.0	0.8993	0.4668	0.4668
0.5957	0.16	20	0.5575	0.0	0.0	0.0	0.8993	0.4668	0.4668
0.6037	0.24	30	0.5471	0.0	0.0	0.0	0.8993	0.4668	0.4668
0.5671	0.32	40	0.5040	0.0	0.0	0.0	0.8993	0.4668	0.4668
0.4556	0.4	50	0.4299	0.0	0.0	0.0	0.8993	0.4668	0.4668
0.4169	0.48	60	0.3465	0.0700	0.0497	0.0581	0.9048	0.4707	0.4571
0.3508	0.56	70	0.3040	0.0657	0.0563	0.0606	0.9077	0.4490	0.4393
0.3154	0.64	80	0.2654	0.1816	0.2953	0.2249	0.9282	0.4327	0.4309
0.2339	0.72	90	0.2073	0.3894	0.5246	0.4470	0.9515	0.5806	0.5670
0.1968	0.8	100	0.1686	0.5405	0.6360	0.5844	0.9598	0.6226	0.6072
0.1735	0.88	110	0.1382	0.6907	0.7131	0.7017	0.9694	0.7473	0.7231
0.1437	0.96	120	0.1212	0.7216	0.7537	0.7373	0.9714	0.7657	0.7428
0.1291	1.04	130	0.1025	0.7340	0.7621	0.7478	0.9741	0.7844	0.7639
0.1257	1.12	140	0.0909	0.7417	0.7807	0.7607	0.9767	0.7808	0.7657
0.0992	1.2	150	0.0811	0.7482	0.7876	0.7674	0.9792	0.7838	0.7720
0.1277	1.28	160	0.0751	0.7677	0.7996	0.7833	0.9807	0.7929	0.7823
0.1016	1.3600	170	0.0713	0.7950	0.8131	0.8039	0.9818	0.8068	0.7968
0.0999	1.44	180	0.0697	0.8171	0.8009	0.8089	0.9814	0.8152	0.8062
0.0945	1.52	190	0.0632	0.8157	0.8471	0.8311	0.9839	0.8137	0.8007
0.1008	1.6	200	0.0667	0.8013	0.8557	0.8276	0.9817	0.8098	0.7938
0.0812	1.6800	210	0.0611	0.8335	0.8595	0.8463	0.9835	0.8370	0.8234
0.0958	1.76	220	0.0578	0.8436	0.8593	0.8514	0.9849	0.8427	0.8279
0.0791	1.8400	230	0.0575	0.8362	0.8634	0.8496	0.9844	0.8457	0.8255
0.0675	1.92	240	0.0535	0.8493	0.8690	0.8590	0.9861	0.8638	0.8454
0.0687	2.0	250	0.0522	0.8620	0.8732	0.8676	0.9868	0.8650	0.8530
0.0608	2.08	260	0.0514	0.8662	0.8737	0.8699	0.9868	0.8711	0.8536
0.0682	2.16	270	0.0524	0.8516	0.8724	0.8619	0.9859	0.8617	0.8457
0.0668	2.24	280	0.0544	0.8630	0.8700	0.8665	0.9859	0.8632	0.8481
0.0605	2.32	290	0.0507	0.8629	0.8737	0.8683	0.9860	0.8632	0.8496
0.0566	2.4	300	0.0502	0.8710	0.8762	0.8736	0.9872	0.8771	0.8566
0.0621	2.48	310	0.0493	0.8725	0.8737	0.8731	0.9872	0.8732	0.8578
0.0613	2.56	320	0.0495	0.8646	0.8698	0.8672	0.9866	0.8687	0.8518
0.056	2.64	330	0.0492	0.8629	0.8867	0.8746	0.9865	0.8678	0.8533
0.0615	2.7200	340	0.0463	0.8623	0.8812	0.8716	0.9873	0.8741	0.8599
0.0562	2.8	350	0.0466	0.8621	0.8901	0.8759	0.9871	0.8671	0.8557
0.0624	2.88	360	0.0469	0.8671	0.8884	0.8776	0.9874	0.875	0.8629
0.0516	2.96	370	0.0476	0.8712	0.8818	0.8764	0.9872	0.8723	0.8611
0.0588	3.04	380	0.0466	0.8674	0.8936	0.8803	0.9872	0.8753	0.8629
0.0532	3.12	390	0.0490	0.8699	0.8919	0.8807	0.9863	0.8705	0.8584
0.0551	3.2	400	0.0463	0.8828	0.8901	0.8864	0.9878	0.8835	0.8723
0.0606	3.2800	410	0.0468	0.8756	0.8874	0.8814	0.9871	0.8768	0.8650
0.0521	3.36	420	0.0480	0.8632	0.8929	0.8778	0.9869	0.8726	0.8545
0.0456	3.44	430	0.0470	0.8796	0.8668	0.8732	0.9870	0.8747	0.8590
0.057	3.52	440	0.0459	0.8712	0.8904	0.8807	0.9878	0.8816	0.8653
0.0533	3.6	450	0.0455	0.8749	0.8940	0.8843	0.9874	0.8744	0.8581
0.0493	3.68	460	0.0452	0.8679	0.9021	0.8847	0.9870	0.8717	0.8593
0.0564	3.76	470	0.0463	0.8824	0.8820	0.8822	0.9871	0.8798	0.8629
0.0509	3.84	480	0.0432	0.8802	0.9002	0.8901	0.9879	0.8838	0.8729
0.0455	3.92	490	0.0432	0.8724	0.8934	0.8828	0.9880	0.8825	0.8687
0.0494	4.0	500	0.0446	0.8701	0.8996	0.8846	0.9872	0.8786	0.8611
0.0469	4.08	510	0.0445	0.8805	0.8981	0.8892	0.9876	0.8819	0.8668
0.0456	4.16	520	0.0433	0.8746	0.9032	0.8887	0.9879	0.8762	0.8678
0.0431	4.24	530	0.0460	0.8827	0.8929	0.8878	0.9875	0.8795	0.8678
0.0371	4.32	540	0.0442	0.8727	0.8981	0.8852	0.9877	0.8801	0.8675
0.0409	4.4	550	0.0455	0.8744	0.8934	0.8838	0.9872	0.8810	0.8638
0.0476	4.48	560	0.0446	0.8675	0.9002	0.8836	0.9871	0.8789	0.8635
0.038	4.5600	570	0.0446	0.8692	0.9124	0.8903	0.9876	0.8783	0.8693
0.0483	4.64	580	0.0438	0.8658	0.9120	0.8883	0.9875	0.8732	0.8626
0.0484	4.72	590	0.0435	0.8908	0.9051	0.8979	0.9885	0.8862	0.8759
0.0392	4.8	600	0.0453	0.8813	0.9045	0.8927	0.9875	0.8825	0.8723
0.0416	4.88	610	0.0451	0.8865	0.8914	0.8890	0.9873	0.8807	0.8702
0.0417	4.96	620	0.0459	0.8835	0.8784	0.8809	0.9869	0.8693	0.8620
0.0284	5.04	630	0.0456	0.8812	0.8910	0.8861	0.9872	0.8765	0.8687
0.0355	5.12	640	0.0459	0.8802	0.9096	0.8947	0.9876	0.8819	0.8720
0.0433	5.2	650	0.0440	0.8795	0.9017	0.8905	0.9877	0.8822	0.8702
0.032	5.28	660	0.0445	0.8876	0.9047	0.8961	0.9880	0.8825	0.8711
0.0382	5.36	670	0.0441	0.8815	0.9002	0.8908	0.9879	0.8819	0.8696
0.0326	5.44	680	0.0445	0.8776	0.9047	0.8910	0.9877	0.8832	0.8711
0.0391	5.52	690	0.0430	0.8896	0.9009	0.8952	0.9883	0.8883	0.8771
0.0377	5.6	700	0.0429	0.8934	0.9024	0.8978	0.9886	0.8907	0.8825
0.0417	5.68	710	0.0453	0.8800	0.9135	0.8964	0.9877	0.8807	0.8711
0.0402	5.76	720	0.0427	0.8937	0.9109	0.9022	0.9889	0.8919	0.8819
0.0351	5.84	730	0.0450	0.8837	0.8951	0.8894	0.9876	0.8798	0.8714
0.0295	5.92	740	0.0430	0.8945	0.8983	0.8964	0.9882	0.8835	0.8762
0.0379	6.0	750	0.0438	0.8876	0.9062	0.8968	0.9882	0.8874	0.8789
0.0314	6.08	760	0.0448	0.8831	0.9094	0.8961	0.9878	0.8822	0.8726
0.026	6.16	770	0.0452	0.8805	0.9154	0.8976	0.9882	0.8841	0.875
0.0277	6.24	780	0.0443	0.8874	0.8996	0.8934	0.9881	0.8819	0.8741
0.0329	6.32	790	0.0459	0.8987	0.9024	0.9005	0.9883	0.8868	0.8795
0.0334	6.4	800	0.0446	0.8939	0.9088	0.9013	0.9883	0.8886	0.8783
0.0263	6.48	810	0.0474	0.8857	0.9073	0.8963	0.9875	0.8871	0.8753
0.0415	6.5600	820	0.0432	0.8854	0.9116	0.8983	0.9886	0.8883	0.8786
0.0322	6.64	830	0.0424	0.8871	0.9101	0.8984	0.9887	0.8868	0.8786
0.0317	6.72	840	0.0444	0.8964	0.9064	0.9014	0.9883	0.8868	0.8801
0.0342	6.8	850	0.0457	0.8927	0.9011	0.8968	0.9873	0.8798	0.8744
0.0296	6.88	860	0.0451	0.8921	0.9069	0.8994	0.9882	0.8859	0.8789
0.0353	6.96	870	0.0442	0.8870	0.9096	0.8982	0.9880	0.8829	0.8747
0.027	7.04	880	0.0465	0.8880	0.9099	0.8988	0.9877	0.8871	0.8774
0.0265	7.12	890	0.0488	0.8835	0.9060	0.8946	0.9872	0.8816	0.8747
0.0272	7.2	900	0.0474	0.8909	0.8974	0.8942	0.9873	0.8813	0.8720
0.0272	7.28	910	0.0474	0.8822	0.9060	0.8939	0.9876	0.8822	0.8738
0.0309	7.36	920	0.0448	0.8909	0.9075	0.8991	0.9884	0.8816	0.8756
0.0295	7.44	930	0.0442	0.8934	0.9049	0.8991	0.9885	0.8877	0.8795
0.032	7.52	940	0.0473	0.8856	0.9154	0.9003	0.9876	0.8829	0.875
0.0244	7.6	950	0.0440	0.8949	0.9154	0.9050	0.9884	0.8859	0.8789
0.0231	7.68	960	0.0451	0.8995	0.9088	0.9041	0.9885	0.8895	0.8810
0.0285	7.76	970	0.0455	0.8978	0.9049	0.9014	0.9883	0.8871	0.8792
0.0245	7.84	980	0.0451	0.8872	0.9099	0.8984	0.9882	0.8853	0.8768
0.0299	7.92	990	0.0460	0.8861	0.9060	0.8959	0.9879	0.8841	0.8744
0.0245	8.0	1000	0.0452	0.8886	0.9105	0.8994	0.9880	0.8816	0.8741
0.021	8.08	1010	0.0464	0.8929	0.9051	0.8990	0.9880	0.8841	0.8738
0.0297	8.16	1020	0.0460	0.8882	0.9165	0.9021	0.9883	0.8825	0.875
0.0254	8.24	1030	0.0455	0.8947	0.9120	0.9033	0.9889	0.8910	0.8838
0.0233	8.32	1040	0.0473	0.8949	0.9011	0.8980	0.9884	0.8883	0.8792
0.0243	8.4	1050	0.0458	0.9009	0.9015	0.9012	0.9887	0.8895	0.8825
0.028	8.48	1060	0.0445	0.8981	0.9139	0.9060	0.9891	0.8901	0.8838
0.027	8.56	1070	0.0446	0.9045	0.9090	0.9068	0.9893	0.8937	0.8865
0.0196	8.64	1080	0.0441	0.9027	0.9099	0.9063	0.9891	0.8916	0.8838
0.0352	8.72	1090	0.0447	0.8980	0.9143	0.9061	0.9891	0.8955	0.8874
0.0275	8.8	1100	0.0446	0.9011	0.9128	0.9069	0.9892	0.8943	0.8868
0.0233	8.88	1110	0.0461	0.8999	0.9051	0.9025	0.9885	0.8822	0.8765
0.0292	8.96	1120	0.0461	0.8960	0.9131	0.9044	0.9885	0.8868	0.8801
0.0144	9.04	1130	0.0456	0.8991	0.9141	0.9066	0.9886	0.8886	0.8804
0.024	9.12	1140	0.0471	0.9030	0.9113	0.9072	0.9891	0.8946	0.8868
0.0239	9.2	1150	0.0468	0.8941	0.9056	0.8998	0.9886	0.8883	0.8789
0.0282	9.28	1160	0.0483	0.8995	0.9062	0.9028	0.9887	0.8931	0.8822
0.0189	9.36	1170	0.0468	0.8997	0.8974	0.8986	0.9885	0.8880	0.8807
0.0232	9.44	1180	0.0449	0.9041	0.9128	0.9085	0.9891	0.8955	0.8889
0.0242	9.52	1190	0.0477	0.9082	0.9113	0.9098	0.9890	0.8986	0.8898
0.0245	9.6	1200	0.0456	0.9002	0.9058	0.9030	0.9885	0.8892	0.8804
0.0231	9.68	1210	0.0463	0.8967	0.9122	0.9044	0.9885	0.8886	0.8810
0.0231	9.76	1220	0.0445	0.8963	0.9199	0.9080	0.9888	0.8910	0.8850
0.0212	9.84	1230	0.0455	0.8931	0.9122	0.9025	0.9887	0.8898	0.8816
0.0217	9.92	1240	0.0483	0.8990	0.9056	0.9023	0.9881	0.8886	0.8816
0.0221	10.0	1250	0.0490	0.8960	0.9060	0.9010	0.9882	0.8898	0.8810
0.0236	10.08	1260	0.0498	0.8953	0.9028	0.8990	0.9882	0.8835	0.8753
0.0229	10.16	1270	0.0483	0.89	0.9148	0.9022	0.9886	0.8856	0.8780
0.0224	10.24	1280	0.0478	0.8990	0.9116	0.9053	0.9888	0.8883	0.8795
0.0163	10.32	1290	0.0488	0.9023	0.9073	0.9048	0.9886	0.8865	0.8792
0.0213	10.4	1300	0.0474	0.8986	0.9073	0.9029	0.9888	0.8838	0.8774
0.0206	10.48	1310	0.0515	0.8910	0.9069	0.8989	0.9878	0.8822	0.8723
0.0212	10.56	1320	0.0484	0.8923	0.9150	0.9035	0.9885	0.8865	0.8798
0.023	10.64	1330	0.0487	0.8934	0.9131	0.9031	0.9885	0.8868	0.8783
0.0221	10.72	1340	0.0472	0.9016	0.9141	0.9078	0.9888	0.8901	0.8847
0.017	10.8	1350	0.0471	0.8937	0.9167	0.9051	0.9885	0.8874	0.8780
0.0246	10.88	1360	0.0470	0.9004	0.9017	0.9010	0.9885	0.8856	0.8795
0.0186	10.96	1370	0.0472	0.9006	0.9094	0.9050	0.9884	0.8892	0.8819
0.018	11.04	1380	0.0485	0.8961	0.9176	0.9067	0.9882	0.8859	0.8786
0.0205	11.12	1390	0.0509	0.8968	0.9079	0.9023	0.9879	0.8847	0.8753
0.0157	11.2	1400	0.0491	0.8996	0.9058	0.9027	0.9883	0.8835	0.8771
0.0202	11.28	1410	0.0481	0.8923	0.9193	0.9056	0.9886	0.8868	0.8807
0.016	11.36	1420	0.0484	0.8984	0.9150	0.9066	0.9887	0.8883	0.8804
0.0219	11.44	1430	0.0474	0.8996	0.9191	0.9092	0.9889	0.8880	0.8813
0.0193	11.52	1440	0.0484	0.8951	0.9096	0.9023	0.9886	0.8853	0.8774
0.0191	11.6	1450	0.0462	0.9006	0.9062	0.9034	0.9888	0.8822	0.8774
0.0187	11.68	1460	0.0470	0.9002	0.9113	0.9057	0.9888	0.8907	0.8829
0.0152	11.76	1470	0.0492	0.9021	0.9096	0.9059	0.9885	0.8862	0.8804
0.0182	11.84	1480	0.0508	0.8947	0.9135	0.9040	0.9881	0.8862	0.8768
0.0277	11.92	1490	0.0481	0.8985	0.9171	0.9077	0.9886	0.8895	0.8838
0.0193	12.0	1500	0.0484	0.8993	0.9086	0.9039	0.9887	0.8874	0.8813
0.0146	12.08	1510	0.0477	0.9038	0.9116	0.9077	0.9891	0.8916	0.8856
0.0173	12.16	1520	0.0494	0.9001	0.9126	0.9063	0.9887	0.8871	0.8813
0.0134	12.24	1530	0.0483	0.9033	0.9165	0.9099	0.9889	0.8892	0.8841
0.0193	12.32	1540	0.0482	0.9019	0.9171	0.9094	0.9890	0.8904	0.8853
0.0219	12.4	1550	0.0487	0.9006	0.9118	0.9062	0.9886	0.8892	0.8813
0.0145	12.48	1560	0.0482	0.9057	0.9131	0.9094	0.9889	0.8904	0.8841
0.0179	12.56	1570	0.0492	0.9006	0.9135	0.9070	0.9888	0.8883	0.8804
0.0167	12.64	1580	0.0490	0.9013	0.9171	0.9091	0.9888	0.8895	0.8819
0.0203	12.72	1590	0.0483	0.9055	0.9126	0.9090	0.9891	0.8940	0.8865
0.0196	12.8	1600	0.0489	0.8997	0.9120	0.9058	0.9888	0.8889	0.8832
0.0197	12.88	1610	0.0494	0.8982	0.9141	0.9061	0.9887	0.8886	0.8810
0.0132	12.96	1620	0.0489	0.9081	0.9094	0.9087	0.9887	0.8886	0.8822
0.0202	13.04	1630	0.0495	0.9021	0.9173	0.9097	0.9887	0.8877	0.8813
0.0113	13.12	1640	0.0487	0.9033	0.9180	0.9106	0.9889	0.8937	0.8871
0.0167	13.2	1650	0.0505	0.9028	0.9128	0.9078	0.9887	0.8895	0.8822
0.0141	13.28	1660	0.0509	0.9004	0.9135	0.9069	0.9886	0.8883	0.8822
0.0209	13.36	1670	0.0501	0.8960	0.9135	0.9047	0.9883	0.8871	0.8804
0.0163	13.44	1680	0.0501	0.9015	0.9099	0.9057	0.9886	0.8901	0.8832
0.0177	13.52	1690	0.0504	0.9028	0.9167	0.9097	0.9888	0.8895	0.8829
0.0211	13.6	1700	0.0511	0.8987	0.9120	0.9053	0.9882	0.8847	0.8783
0.0255	13.68	1710	0.0494	0.8955	0.9152	0.9052	0.9884	0.8844	0.8801
0.0179	13.76	1720	0.0504	0.9036	0.9077	0.9057	0.9887	0.8910	0.8847
0.0122	13.84	1730	0.0494	0.8976	0.9143	0.9059	0.9891	0.8907	0.8850
0.0119	13.92	1740	0.0497	0.8961	0.9139	0.9049	0.9886	0.8859	0.8804
0.0126	14.0	1750	0.0495	0.9024	0.9143	0.9083	0.9886	0.8883	0.8822
0.0155	14.08	1760	0.0500	0.9055	0.9131	0.9093	0.9888	0.8919	0.8856
0.0175	14.16	1770	0.0506	0.9003	0.9131	0.9067	0.9885	0.8898	0.8832
0.0178	14.24	1780	0.0507	0.9007	0.9128	0.9067	0.9887	0.8856	0.8795
0.0176	14.32	1790	0.0521	0.9005	0.9092	0.9048	0.9885	0.8871	0.8807
0.0209	14.4	1800	0.0520	0.8971	0.9131	0.9050	0.9883	0.8868	0.8810
0.0121	14.48	1810	0.0503	0.9014	0.9101	0.9057	0.9886	0.8865	0.8816
0.0164	14.56	1820	0.0505	0.9043	0.9182	0.9112	0.9890	0.8913	0.8853
0.0162	14.64	1830	0.0503	0.9035	0.9137	0.9085	0.9889	0.8898	0.8844
0.0113	14.72	1840	0.0500	0.9023	0.9156	0.9089	0.9888	0.8877	0.8822
0.0155	14.8	1850	0.0509	0.8998	0.9133	0.9065	0.9887	0.8886	0.8832
0.0136	14.88	1860	0.0511	0.9005	0.9124	0.9064	0.9888	0.8889	0.8832
0.0131	14.96	1870	0.0501	0.9048	0.9141	0.9095	0.9890	0.8898	0.8847
0.013	15.04	1880	0.0506	0.9017	0.9154	0.9085	0.9889	0.8889	0.8832
0.0171	15.12	1890	0.0502	0.9032	0.9154	0.9093	0.9889	0.8901	0.8859
0.0142	15.2	1900	0.0499	0.9011	0.9135	0.9073	0.9888	0.8892	0.8847
0.0151	15.28	1910	0.0507	0.9021	0.9137	0.9079	0.9889	0.8889	0.8825
0.0169	15.36	1920	0.0510	0.9057	0.9109	0.9083	0.9890	0.8907	0.8847
0.0154	15.44	1930	0.0509	0.9017	0.9137	0.9077	0.9891	0.8916	0.8850
0.0104	15.52	1940	0.0506	0.9021	0.9154	0.9087	0.9890	0.8898	0.8850
0.0135	15.6	1950	0.0505	0.9057	0.9111	0.9084	0.9890	0.8907	0.8865
0.0145	15.68	1960	0.0511	0.9022	0.9141	0.9081	0.9890	0.8883	0.8841
0.0178	15.76	1970	0.0507	0.9029	0.9137	0.9083	0.9891	0.8907	0.8862
0.0125	15.84	1980	0.0510	0.9018	0.9105	0.9061	0.9888	0.8895	0.8841
0.0134	15.92	1990	0.0516	0.8994	0.9173	0.9083	0.9888	0.8871	0.8813
0.0163	16.0	2000	0.0509	0.9025	0.9101	0.9063	0.9888	0.8865	0.8816
0.0135	16.08	2010	0.0507	0.9018	0.9128	0.9073	0.9889	0.8874	0.8825
0.0102	16.16	2020	0.0510	0.9032	0.9116	0.9074	0.9888	0.8883	0.8829
0.0103	16.24	2030	0.0515	0.9047	0.9152	0.9099	0.9888	0.8892	0.8844
0.0194	16.32	2040	0.0517	0.9059	0.9137	0.9098	0.9888	0.8895	0.8850
0.0119	16.4	2050	0.0515	0.9043	0.9148	0.9095	0.9888	0.8880	0.8832
0.015	16.48	2060	0.0518	0.8993	0.9141	0.9067	0.9886	0.8853	0.8801
0.0118	16.56	2070	0.0514	0.9015	0.9116	0.9065	0.9887	0.8868	0.8813
0.0107	16.64	2080	0.0516	0.8981	0.9137	0.9058	0.9887	0.8865	0.8807
0.0142	16.72	2090	0.0521	0.8980	0.9124	0.9052	0.9886	0.8865	0.8795
0.0189	16.8	2100	0.0514	0.9043	0.9126	0.9085	0.9888	0.8877	0.8816
0.0143	16.88	2110	0.0510	0.9036	0.9131	0.9083	0.9889	0.8871	0.8825
0.0107	16.96	2120	0.0514	0.8978	0.9161	0.9068	0.9888	0.8862	0.8813
0.0137	17.04	2130	0.0511	0.9039	0.9124	0.9081	0.9887	0.8889	0.8829
0.0115	17.12	2140	0.0513	0.9031	0.9099	0.9065	0.9887	0.8892	0.8829
0.0113	17.2	2150	0.0518	0.9004	0.9133	0.9068	0.9887	0.8880	0.8810
0.0151	17.28	2160	0.0517	0.9025	0.9135	0.9079	0.9888	0.8886	0.8819
0.0192	17.36	2170	0.0515	0.9043	0.9141	0.9092	0.9889	0.8883	0.8829
0.0104	17.44	2180	0.0513	0.9027	0.9141	0.9084	0.9888	0.8877	0.8822
0.0122	17.52	2190	0.0512	0.9032	0.9152	0.9092	0.9889	0.8871	0.8822
0.0142	17.6	2200	0.0510	0.9046	0.9141	0.9094	0.9889	0.8874	0.8829
0.0145	17.68	2210	0.0511	0.9042	0.9139	0.9091	0.9888	0.8871	0.8829
0.0129	17.76	2220	0.0512	0.9025	0.9137	0.9081	0.9888	0.8883	0.8838
0.0115	17.84	2230	0.0513	0.9044	0.9141	0.9093	0.9888	0.8889	0.8841
0.0119	17.92	2240	0.0516	0.9014	0.9158	0.9086	0.9889	0.8877	0.8822
0.0162	18.0	2250	0.0515	0.9033	0.9143	0.9088	0.9888	0.8895	0.8841
0.0091	18.08	2260	0.0515	0.9026	0.9131	0.9078	0.9888	0.8883	0.8829
0.0115	18.16	2270	0.0515	0.9027	0.9137	0.9082	0.9888	0.8883	0.8832
0.0121	18.24	2280	0.0514	0.9022	0.9146	0.9083	0.9888	0.8874	0.8829
0.012	18.32	2290	0.0512	0.9028	0.9131	0.9079	0.9888	0.8868	0.8825
0.0188	18.4	2300	0.0512	0.9021	0.9113	0.9067	0.9887	0.8859	0.8816
0.0132	18.48	2310	0.0513	0.9021	0.9131	0.9075	0.9888	0.8871	0.8825
0.0157	18.56	2320	0.0514	0.9016	0.9141	0.9078	0.9888	0.8877	0.8825
0.0146	18.64	2330	0.0515	0.9018	0.9143	0.9080	0.9888	0.8886	0.8835
0.0122	18.72	2340	0.0515	0.9016	0.9148	0.9082	0.9888	0.8889	0.8838
0.0135	18.8	2350	0.0516	0.9014	0.9146	0.9080	0.9888	0.8886	0.8835
0.0166	18.88	2360	0.0516	0.9016	0.9139	0.9077	0.9888	0.8886	0.8838
0.0117	18.96	2370	0.0516	0.9012	0.9141	0.9076	0.9888	0.8883	0.8835
0.0107	19.04	2380	0.0516	0.9024	0.9143	0.9083	0.9888	0.8886	0.8841
0.0108	19.12	2390	0.0515	0.9026	0.9143	0.9084	0.9888	0.8883	0.8838
0.0108	19.2	2400	0.0515	0.9023	0.9141	0.9082	0.9888	0.8880	0.8835
0.0116	19.28	2410	0.0515	0.9033	0.9139	0.9086	0.9888	0.8880	0.8835
0.013	19.36	2420	0.0515	0.9029	0.9137	0.9083	0.9888	0.8880	0.8835
0.0127	19.44	2430	0.0515	0.9027	0.9137	0.9082	0.9888	0.8880	0.8835
0.0119	19.52	2440	0.0515	0.9025	0.9137	0.9081	0.9888	0.8877	0.8832
0.0148	19.6	2450	0.0515	0.9023	0.9137	0.9080	0.9888	0.8877	0.8832
0.0151	19.68	2460	0.0515	0.9023	0.9137	0.9080	0.9888	0.8877	0.8832
0.0095	19.76	2470	0.0515	0.9023	0.9137	0.9080	0.9888	0.8877	0.8832
0.0132	19.84	2480	0.0515	0.9023	0.9137	0.9080	0.9888	0.8877	0.8832
0.0117	19.92	2490	0.0515	0.9025	0.9137	0.9081	0.9888	0.8877	0.8832
0.0126	20.0	2500	0.0515	0.9025	0.9137	0.9081	0.9888	0.8877	0.8832

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu126
• Datasets 3.4.1
• Tokenizers 0.21.1