nerugm-base-4

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3325
• Location Precision: 0.7922
• Location Recall: 0.8356
• Location F1: 0.8133
• Location Number: 73
• Organization Precision: 0.7013
• Organization Recall: 0.8308
• Organization F1: 0.7606
• Organization Number: 65
• Person Precision: 0.9226
• Person Recall: 0.9533
• Person F1: 0.9377
• Person Number: 150
• Quantity Precision: 0.6667
• Quantity Recall: 0.7586
• Quantity F1: 0.7097
• Quantity Number: 29
• Time Precision: 0.8378
• Time Recall: 0.9118
• Time F1: 0.8732
• Time Number: 34
• Overall Precision: 0.8206
• Overall Recall: 0.8860
• Overall F1: 0.8521
• Overall Accuracy: 0.9670

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-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100.0

Training results

Training Loss	Epoch	Step	Validation Loss	Location Precision	Location Recall	Location F1	Location Number	Organization Precision	Organization Recall	Organization F1	Organization Number	Person Precision	Person Recall	Person F1	Person Number	Quantity Precision	Quantity Recall	Quantity F1	Quantity Number	Time Precision	Time Recall	Time F1	Time Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.3326	1.0	106	0.1188	0.8052	0.8493	0.8267	73	0.6184	0.7231	0.6667	65	0.8662	0.9067	0.8860	150	0.6667	0.7586	0.7097	29	0.9667	0.8529	0.9062	34	0.7936	0.8433	0.8177	0.9621
0.1192	2.0	212	0.1727	0.6702	0.8630	0.7545	73	0.4597	0.8769	0.6032	65	0.8688	0.9267	0.8968	150	0.6098	0.8621	0.7143	29	0.6905	0.8529	0.7632	34	0.6790	0.8917	0.7709	0.9397
0.0772	3.0	318	0.1291	0.7356	0.8767	0.8	73	0.6883	0.8154	0.7465	65	0.8688	0.9267	0.8968	150	0.7742	0.8276	0.8000	29	0.8529	0.8529	0.8529	34	0.7943	0.8803	0.8351	0.9626
0.051	4.0	424	0.1436	0.7561	0.8493	0.8000	73	0.6022	0.8615	0.7089	65	0.8797	0.9267	0.9026	150	0.7941	0.9310	0.8571	29	0.7692	0.8824	0.8219	34	0.7734	0.8946	0.8296	0.9589
0.0341	5.0	530	0.1558	0.7564	0.8082	0.7815	73	0.6962	0.8462	0.7639	65	0.8903	0.92	0.9049	150	0.7941	0.9310	0.8571	29	0.7143	0.8824	0.7895	34	0.7964	0.8803	0.8363	0.9651
0.0289	6.0	636	0.1820	0.7619	0.8767	0.8153	73	0.625	0.7692	0.6897	65	0.8415	0.92	0.8790	150	0.7941	0.9310	0.8571	29	0.8108	0.8824	0.8451	34	0.7744	0.8803	0.824	0.9606
0.0223	7.0	742	0.1874	0.7683	0.8630	0.8129	73	0.6486	0.7385	0.6906	65	0.9026	0.9267	0.9145	150	0.7742	0.8276	0.8000	29	0.7632	0.8529	0.8056	34	0.7995	0.8632	0.8301	0.9621
0.0154	8.0	848	0.2203	0.8289	0.8630	0.8456	73	0.6353	0.8308	0.7200	65	0.8846	0.92	0.9020	150	0.75	0.8276	0.7869	29	0.7895	0.8824	0.8333	34	0.7984	0.8803	0.8374	0.9623
0.0122	9.0	954	0.2047	0.8101	0.8767	0.8421	73	0.7368	0.8615	0.7943	65	0.8924	0.94	0.9156	150	0.7742	0.8276	0.8000	29	0.7632	0.8529	0.8056	34	0.8220	0.8946	0.8568	0.9658
0.0125	10.0	1060	0.2343	0.8493	0.8493	0.8493	73	0.725	0.8923	0.8	65	0.9097	0.94	0.9246	150	0.6842	0.8966	0.7761	29	0.6744	0.8529	0.7532	34	0.8123	0.9003	0.8541	0.9619
0.0086	11.0	1166	0.3140	0.6421	0.8356	0.7262	73	0.6512	0.8615	0.7417	65	0.8765	0.9467	0.9103	150	0.6757	0.8621	0.7576	29	0.6591	0.8529	0.7436	34	0.7382	0.8917	0.8077	0.9520
0.0069	12.0	1272	0.2598	0.8592	0.8356	0.8472	73	0.7108	0.9077	0.7973	65	0.8642	0.9333	0.8974	150	0.6842	0.8966	0.7761	29	0.6522	0.8824	0.75	34	0.79	0.9003	0.8415	0.9619
0.0069	13.0	1378	0.2524	0.7595	0.8219	0.7895	73	0.7123	0.8	0.7536	65	0.8981	0.94	0.9186	150	0.7879	0.8966	0.8387	29	0.6905	0.8529	0.7632	34	0.8021	0.8775	0.8381	0.9623
0.0048	14.0	1484	0.2733	0.7294	0.8493	0.7848	73	0.7368	0.8615	0.7943	65	0.9103	0.9467	0.9281	150	0.7188	0.7931	0.7541	29	0.775	0.9118	0.8378	34	0.8072	0.8946	0.8486	0.9633
0.0069	15.0	1590	0.2588	0.7875	0.8630	0.8235	73	0.6914	0.8615	0.7671	65	0.9103	0.9467	0.9281	150	0.75	0.8276	0.7869	29	0.8649	0.9412	0.9014	34	0.8212	0.9031	0.8602	0.9665
0.0047	16.0	1696	0.2755	0.7143	0.8219	0.7643	73	0.6875	0.8462	0.7586	65	0.9091	0.9333	0.9211	150	0.7576	0.8621	0.8065	29	0.9412	0.9412	0.9412	34	0.8104	0.8889	0.8478	0.9638
0.0049	17.0	1802	0.2742	0.8052	0.8493	0.8267	73	0.7083	0.7846	0.7445	65	0.8758	0.94	0.9068	150	0.7143	0.8621	0.7813	29	0.7209	0.9118	0.8052	34	0.7990	0.8832	0.8390	0.9646
0.0049	18.0	1908	0.2764	0.7848	0.8493	0.8158	73	0.7671	0.8615	0.8116	65	0.8938	0.9533	0.9226	150	0.7647	0.8966	0.8254	29	0.75	0.8824	0.8108	34	0.8212	0.9031	0.8602	0.9653
0.0033	19.0	2014	0.2768	0.7922	0.8356	0.8133	73	0.7606	0.8308	0.7941	65	0.8812	0.94	0.9097	150	0.7941	0.9310	0.8571	29	0.7949	0.9118	0.8493	34	0.8241	0.8946	0.8579	0.9670
0.0042	20.0	2120	0.3033	0.7241	0.8630	0.7875	73	0.7324	0.8	0.7647	65	0.9038	0.94	0.9216	150	0.7647	0.8966	0.8254	29	0.7045	0.9118	0.7949	34	0.7985	0.8917	0.8425	0.9633
0.0036	21.0	2226	0.2692	0.8133	0.8356	0.8243	73	0.7297	0.8308	0.7770	65	0.9045	0.9467	0.9251	150	0.7941	0.9310	0.8571	29	0.8205	0.9412	0.8767	34	0.8338	0.9003	0.8658	0.9655
0.0073	22.0	2332	0.3261	0.6923	0.8630	0.7683	73	0.6429	0.8308	0.7248	65	0.8868	0.94	0.9126	150	0.8065	0.8621	0.8333	29	0.7381	0.9118	0.8158	34	0.7715	0.8946	0.8285	0.9574
0.0024	23.0	2438	0.2863	0.7949	0.8493	0.8212	73	0.7125	0.8769	0.7862	65	0.8968	0.9267	0.9115	150	0.7143	0.8621	0.7813	29	0.7805	0.9412	0.8533	34	0.8098	0.8974	0.8514	0.9646
0.0031	24.0	2544	0.3045	0.7590	0.8630	0.8077	73	0.6591	0.8923	0.7582	65	0.8994	0.9533	0.9256	150	0.7941	0.9310	0.8571	29	0.7692	0.8824	0.8219	34	0.7965	0.9145	0.8515	0.9631
0.0033	25.0	2650	0.3293	0.7326	0.8630	0.7925	73	0.6974	0.8154	0.7518	65	0.8868	0.94	0.9126	150	0.7353	0.8621	0.7937	29	0.7561	0.9118	0.8267	34	0.7904	0.8917	0.8380	0.9609
0.0029	26.0	2756	0.2977	0.8025	0.8904	0.8442	73	0.6706	0.8769	0.76	65	0.9045	0.9467	0.9251	150	0.7576	0.8621	0.8065	29	0.7805	0.9412	0.8533	34	0.8086	0.9145	0.8583	0.9636
0.0035	27.0	2862	0.3316	0.8158	0.8493	0.8322	73	0.6517	0.8923	0.7532	65	0.9103	0.9467	0.9281	150	0.7576	0.8621	0.8065	29	0.7805	0.9412	0.8533	34	0.8076	0.9088	0.8552	0.9631
0.0076	28.0	2968	0.2618	0.8	0.8767	0.8366	73	0.7667	0.7077	0.736	65	0.8917	0.9333	0.9121	150	0.8065	0.8621	0.8333	29	0.8205	0.9412	0.8767	34	0.8365	0.8746	0.8552	0.9646
0.0027	29.0	3074	0.3309	0.75	0.8630	0.8025	73	0.6552	0.8769	0.75	65	0.8924	0.94	0.9156	150	0.75	0.8276	0.7869	29	0.6596	0.9118	0.7654	34	0.7745	0.9003	0.8327	0.9589
0.0025	30.0	3180	0.3092	0.8	0.8767	0.8366	73	0.6951	0.8769	0.7755	65	0.9038	0.94	0.9216	150	0.7812	0.8621	0.8197	29	0.8108	0.8824	0.8451	34	0.8191	0.9031	0.8591	0.9648
0.003	31.0	3286	0.3234	0.7848	0.8493	0.8158	73	0.7	0.8615	0.7724	65	0.8981	0.94	0.9186	150	0.75	0.9310	0.8308	29	0.6977	0.8824	0.7792	34	0.8	0.9003	0.8472	0.9591
0.0061	32.0	3392	0.2889	0.8077	0.8630	0.8344	73	0.6548	0.8462	0.7383	65	0.8917	0.9333	0.9121	150	0.7353	0.8621	0.7937	29	0.8611	0.9118	0.8857	34	0.8072	0.8946	0.8486	0.9638
0.0028	33.0	3498	0.2616	0.8514	0.8630	0.8571	73	0.6625	0.8154	0.7310	65	0.8910	0.9267	0.9085	150	0.6857	0.8276	0.75	29	0.8649	0.9412	0.9014	34	0.8141	0.8860	0.8486	0.9660
0.0024	34.0	3604	0.2858	0.7821	0.8356	0.8079	73	0.6512	0.8615	0.7417	65	0.9097	0.94	0.9246	150	0.7647	0.8966	0.8254	29	0.8857	0.9118	0.8986	34	0.8119	0.8974	0.8525	0.9658
0.0016	35.0	3710	0.3019	0.8182	0.8630	0.8400	73	0.6951	0.8769	0.7755	65	0.9216	0.94	0.9307	150	0.7353	0.8621	0.7937	29	0.8571	0.8824	0.8696	34	0.8294	0.9003	0.8634	0.9660
0.0017	36.0	3816	0.2798	0.7875	0.8630	0.8235	73	0.6986	0.7846	0.7391	65	0.9167	0.9533	0.9346	150	0.7188	0.7931	0.7541	29	0.8857	0.9118	0.8986	34	0.8271	0.8860	0.8556	0.9665
0.0012	37.0	3922	0.3007	0.75	0.8630	0.8025	73	0.7656	0.7538	0.7597	65	0.9103	0.9467	0.9281	150	0.7273	0.8276	0.7742	29	0.7949	0.9118	0.8493	34	0.8218	0.8803	0.8501	0.9655
0.002	38.0	4028	0.3204	0.8052	0.8493	0.8267	73	0.6707	0.8462	0.7483	65	0.9281	0.9467	0.9373	150	0.7353	0.8621	0.7937	29	0.7209	0.9118	0.8052	34	0.8098	0.8974	0.8514	0.9626
0.0017	39.0	4134	0.2832	0.8267	0.8493	0.8378	73	0.6279	0.8308	0.7152	65	0.8987	0.9467	0.9221	150	0.6562	0.7241	0.6885	29	0.8857	0.9118	0.8986	34	0.8031	0.8832	0.8412	0.9638
0.0019	40.0	4240	0.3074	0.7619	0.8767	0.8153	73	0.65	0.8	0.7172	65	0.9167	0.9533	0.9346	150	0.6857	0.8276	0.75	29	0.7632	0.8529	0.8056	34	0.7939	0.8889	0.8387	0.9646
0.0007	41.0	4346	0.3130	0.8158	0.8493	0.8322	73	0.6506	0.8308	0.7297	65	0.9108	0.9533	0.9316	150	0.6667	0.8276	0.7385	29	0.8649	0.9412	0.9014	34	0.8098	0.8974	0.8514	0.9643
0.0013	42.0	4452	0.2825	0.8077	0.8630	0.8344	73	0.7015	0.7231	0.7121	65	0.9226	0.9533	0.9377	150	0.6667	0.7586	0.7097	29	0.8857	0.9118	0.8986	34	0.8315	0.8718	0.8512	0.9683
0.0008	43.0	4558	0.3163	0.7625	0.8356	0.7974	73	0.7333	0.8462	0.7857	65	0.9167	0.9533	0.9346	150	0.7429	0.8966	0.8125	29	0.8611	0.9118	0.8857	34	0.8272	0.9003	0.8622	0.9673
0.0035	44.0	4664	0.3363	0.7470	0.8493	0.7949	73	0.7051	0.8462	0.7692	65	0.9091	0.9333	0.9211	150	0.6667	0.7586	0.7097	29	0.7692	0.8824	0.8219	34	0.7984	0.8803	0.8374	0.9623
0.0032	45.0	4770	0.2655	0.7875	0.8630	0.8235	73	0.7067	0.8154	0.7571	65	0.8974	0.9333	0.9150	150	0.75	0.8276	0.7869	29	0.9394	0.9118	0.9254	34	0.8271	0.8860	0.8556	0.9660
0.0029	46.0	4876	0.2898	0.8026	0.8356	0.8188	73	0.7215	0.8769	0.7917	65	0.8987	0.9467	0.9221	150	0.6	0.7241	0.6562	29	0.8108	0.8824	0.8451	34	0.8078	0.8860	0.8451	0.9631
0.0011	47.0	4982	0.2948	0.8133	0.8356	0.8243	73	0.7333	0.8462	0.7857	65	0.9161	0.9467	0.9311	150	0.6111	0.7586	0.6769	29	0.75	0.8824	0.8108	34	0.8136	0.8832	0.8470	0.9648
0.0019	48.0	5088	0.2978	0.7470	0.8493	0.7949	73	0.6923	0.8308	0.7552	65	0.9051	0.9533	0.9286	150	0.6389	0.7931	0.7077	29	0.8649	0.9412	0.9014	34	0.8010	0.8946	0.8452	0.9646
0.0012	49.0	5194	0.3064	0.8158	0.8493	0.8322	73	0.675	0.8308	0.7448	65	0.9097	0.94	0.9246	150	0.6944	0.8621	0.7692	29	0.8378	0.9118	0.8732	34	0.8151	0.8917	0.8517	0.9628
0.0005	50.0	5300	0.3279	0.8108	0.8219	0.8163	73	0.6627	0.8462	0.7432	65	0.9103	0.9467	0.9281	150	0.6944	0.8621	0.7692	29	0.7692	0.8824	0.8219	34	0.8041	0.8889	0.8444	0.9623
0.0022	51.0	5406	0.2888	0.8493	0.8493	0.8493	73	0.7368	0.8615	0.7943	65	0.9161	0.9467	0.9311	150	0.7333	0.7586	0.7458	29	0.8824	0.8824	0.8824	34	0.8478	0.8889	0.8679	0.9665
0.0018	52.0	5512	0.3415	0.7778	0.8630	0.8182	73	0.6585	0.8308	0.7347	65	0.9161	0.9467	0.9311	150	0.7059	0.8276	0.7619	29	0.6	0.8824	0.7143	34	0.7786	0.8917	0.8313	0.9579
0.0024	53.0	5618	0.3337	0.7349	0.8356	0.7821	73	0.7051	0.8462	0.7692	65	0.9156	0.94	0.9276	150	0.7273	0.8276	0.7742	29	0.7317	0.8824	0.8	34	0.7995	0.8860	0.8405	0.9591
0.0012	54.0	5724	0.3097	0.7922	0.8356	0.8133	73	0.6883	0.8154	0.7465	65	0.9045	0.9467	0.9251	150	0.6970	0.7931	0.7419	29	0.775	0.9118	0.8378	34	0.8073	0.8832	0.8435	0.9643
0.0016	55.0	5830	0.3207	0.7662	0.8082	0.7867	73	0.7183	0.7846	0.75	65	0.9108	0.9533	0.9316	150	0.6970	0.7931	0.7419	29	0.7895	0.8824	0.8333	34	0.8138	0.8718	0.8418	0.9631
0.0013	56.0	5936	0.3148	0.7792	0.8219	0.8000	73	0.7231	0.7231	0.7231	65	0.9108	0.9533	0.9316	150	0.7188	0.7931	0.7541	29	0.7692	0.8824	0.8219	34	0.8189	0.8632	0.8405	0.9636
0.0012	57.0	6042	0.3097	0.7895	0.8219	0.8054	73	0.7162	0.8154	0.7626	65	0.9108	0.9533	0.9316	150	0.6562	0.7241	0.6885	29	0.8788	0.8529	0.8657	34	0.8226	0.8718	0.8465	0.9643
0.0005	58.0	6148	0.3341	0.7848	0.8493	0.8158	73	0.6753	0.8	0.7324	65	0.8704	0.94	0.9038	150	0.7059	0.8276	0.7619	29	0.75	0.8824	0.8108	34	0.7883	0.8803	0.8318	0.9633
0.0013	59.0	6254	0.3232	0.8133	0.8356	0.8243	73	0.7013	0.8308	0.7606	65	0.8868	0.94	0.9126	150	0.6970	0.7931	0.7419	29	0.7317	0.8824	0.8	34	0.8026	0.8803	0.8397	0.9638
0.0012	60.0	6360	0.3059	0.7949	0.8493	0.8212	73	0.68	0.7846	0.7286	65	0.9045	0.9467	0.9251	150	0.6875	0.7586	0.7213	29	0.8108	0.8824	0.8451	34	0.8100	0.8746	0.8411	0.9653
0.0014	61.0	6466	0.3144	0.7590	0.8630	0.8077	73	0.6790	0.8462	0.7534	65	0.9167	0.9533	0.9346	150	0.6765	0.7931	0.7302	29	0.8421	0.9412	0.8889	34	0.8061	0.9003	0.8506	0.9663
0.0002	62.0	6572	0.3230	0.7176	0.8356	0.7722	73	0.6709	0.8154	0.7361	65	0.9226	0.9533	0.9377	150	0.6286	0.7586	0.6875	29	0.8	0.9412	0.8649	34	0.7893	0.8860	0.8349	0.9653
0.0007	63.0	6678	0.3489	0.7722	0.8356	0.8026	73	0.7125	0.8769	0.7862	65	0.9167	0.9533	0.9346	150	0.6471	0.7586	0.6984	29	0.7619	0.9412	0.8421	34	0.8056	0.8974	0.8491	0.9636
0.0001	64.0	6784	0.3458	0.7722	0.8356	0.8026	73	0.7179	0.8615	0.7832	65	0.9167	0.9533	0.9346	150	0.6471	0.7586	0.6984	29	0.7692	0.8824	0.8219	34	0.8083	0.8889	0.8467	0.9638
0.001	65.0	6890	0.3409	0.7439	0.8356	0.7871	73	0.6667	0.8	0.7273	65	0.9167	0.9533	0.9346	150	0.6286	0.7586	0.6875	29	0.7692	0.8824	0.8219	34	0.7897	0.8775	0.8313	0.9638
0.001	66.0	6996	0.3137	0.7895	0.8219	0.8054	73	0.7051	0.8462	0.7692	65	0.9167	0.9533	0.9346	150	0.7576	0.8621	0.8065	29	0.9091	0.8824	0.8955	34	0.8324	0.8917	0.8611	0.9665
0.0007	67.0	7102	0.3459	0.7922	0.8356	0.8133	73	0.6875	0.8462	0.7586	65	0.9108	0.9533	0.9316	150	0.7143	0.8621	0.7813	29	0.7317	0.8824	0.8	34	0.8051	0.8946	0.8475	0.9633
0.0004	68.0	7208	0.3155	0.7922	0.8356	0.8133	73	0.68	0.7846	0.7286	65	0.9103	0.9467	0.9281	150	0.6765	0.7931	0.7302	29	0.8571	0.8824	0.8696	34	0.8143	0.8746	0.8434	0.9648
0.0004	69.0	7314	0.3485	0.7722	0.8356	0.8026	73	0.6582	0.8	0.7222	65	0.8987	0.9467	0.9221	150	0.6857	0.8276	0.75	29	0.8571	0.8824	0.8696	34	0.8005	0.8803	0.8385	0.9631
0.0003	70.0	7420	0.3382	0.7692	0.8219	0.7947	73	0.6625	0.8154	0.7310	65	0.9161	0.9467	0.9311	150	0.6970	0.7931	0.7419	29	0.8571	0.8824	0.8696	34	0.8084	0.8775	0.8415	0.9638
0.001	71.0	7526	0.3148	0.8052	0.8493	0.8267	73	0.6842	0.8	0.7376	65	0.9221	0.9467	0.9342	150	0.6765	0.7931	0.7302	29	0.8333	0.8824	0.8571	34	0.8196	0.8803	0.8489	0.9658
0.0003	72.0	7632	0.3217	0.8158	0.8493	0.8322	73	0.7246	0.7692	0.7463	65	0.9281	0.9467	0.9373	150	0.6857	0.8276	0.75	29	0.8333	0.8824	0.8571	34	0.8347	0.8775	0.8556	0.9660
0.0007	73.0	7738	0.3234	0.7848	0.8493	0.8158	73	0.6875	0.8462	0.7586	65	0.9156	0.94	0.9276	150	0.6765	0.7931	0.7302	29	0.8571	0.8824	0.8696	34	0.8141	0.8860	0.8486	0.9655
0.0003	74.0	7844	0.3176	0.7821	0.8356	0.8079	73	0.6707	0.8462	0.7483	65	0.8981	0.94	0.9186	150	0.6765	0.7931	0.7302	29	0.8571	0.8824	0.8696	34	0.8031	0.8832	0.8412	0.9646
0.0005	75.0	7950	0.3431	0.7654	0.8493	0.8052	73	0.6835	0.8308	0.75	65	0.9103	0.9467	0.9281	150	0.7059	0.8276	0.7619	29	0.7895	0.8824	0.8333	34	0.8041	0.8889	0.8444	0.9646
0.0005	76.0	8056	0.3416	0.8026	0.8356	0.8188	73	0.6875	0.8462	0.7586	65	0.9167	0.9533	0.9346	150	0.6765	0.7931	0.7302	29	0.7895	0.8824	0.8333	34	0.8125	0.8889	0.8490	0.9643
0.0002	77.0	8162	0.3295	0.75	0.8219	0.7843	73	0.6835	0.8308	0.75	65	0.9045	0.9467	0.9251	150	0.6765	0.7931	0.7302	29	0.8108	0.8824	0.8451	34	0.7984	0.8803	0.8374	0.9646
0.0001	78.0	8268	0.3368	0.7848	0.8493	0.8158	73	0.6835	0.8308	0.75	65	0.9103	0.9467	0.9281	150	0.7188	0.7931	0.7541	29	0.8108	0.8824	0.8451	34	0.8120	0.8860	0.8474	0.9651
0.0004	79.0	8374	0.3212	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9161	0.9467	0.9311	150	0.7188	0.7931	0.7541	29	0.8108	0.8824	0.8451	34	0.8201	0.8832	0.8505	0.9663
0.0001	80.0	8480	0.3227	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.7188	0.7931	0.7541	29	0.8108	0.8824	0.8451	34	0.8228	0.8860	0.8532	0.9663
0.0003	81.0	8586	0.3216	0.8052	0.8493	0.8267	73	0.6923	0.8308	0.7552	65	0.9045	0.9467	0.9251	150	0.6667	0.7586	0.7097	29	0.8158	0.9118	0.8611	34	0.8120	0.8860	0.8474	0.9663
0.0004	82.0	8692	0.3134	0.7792	0.8219	0.8000	73	0.6923	0.8308	0.7552	65	0.9045	0.9467	0.9251	150	0.6471	0.7586	0.6984	29	0.8421	0.9412	0.8889	34	0.8073	0.8832	0.8435	0.9670
0.0003	83.0	8798	0.3101	0.8289	0.8630	0.8456	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.6970	0.7931	0.7419	29	0.8421	0.9412	0.8889	34	0.8311	0.8974	0.8630	0.9700
0.0002	84.0	8904	0.3153	0.8158	0.8493	0.8322	73	0.7105	0.8308	0.7660	65	0.9221	0.9467	0.9342	150	0.6970	0.7931	0.7419	29	0.8421	0.9412	0.8889	34	0.8302	0.8917	0.8599	0.9683
0.0005	85.0	9010	0.3358	0.8133	0.8356	0.8243	73	0.6914	0.8615	0.7671	65	0.9103	0.9467	0.9281	150	0.6765	0.7931	0.7302	29	0.8378	0.9118	0.8732	34	0.8172	0.8917	0.8529	0.9655
0.0001	86.0	9116	0.3357	0.8026	0.8356	0.8188	73	0.7089	0.8615	0.7778	65	0.9103	0.9467	0.9281	150	0.6765	0.7931	0.7302	29	0.8378	0.9118	0.8732	34	0.8194	0.8917	0.8540	0.9665
0.0002	87.0	9222	0.3371	0.7895	0.8219	0.8054	73	0.7051	0.8462	0.7692	65	0.9226	0.9533	0.9377	150	0.6970	0.7931	0.7419	29	0.7895	0.8824	0.8333	34	0.8184	0.8860	0.8509	0.9655
0.0001	88.0	9328	0.3303	0.7895	0.8219	0.8054	73	0.7051	0.8462	0.7692	65	0.9216	0.94	0.9307	150	0.6970	0.7931	0.7419	29	0.7895	0.8824	0.8333	34	0.8175	0.8803	0.8477	0.9648
0.0001	89.0	9434	0.3300	0.7895	0.8219	0.8054	73	0.7013	0.8308	0.7606	65	0.9156	0.94	0.9276	150	0.7273	0.8276	0.7742	29	0.7949	0.9118	0.8493	34	0.8179	0.8832	0.8493	0.9665
0.0001	90.0	9540	0.3355	0.7792	0.8219	0.8000	73	0.7013	0.8308	0.7606	65	0.9221	0.9467	0.9342	150	0.6970	0.7931	0.7419	29	0.7949	0.9118	0.8493	34	0.8158	0.8832	0.8482	0.9660
0.0002	91.0	9646	0.3345	0.7792	0.8219	0.8000	73	0.7013	0.8308	0.7606	65	0.9156	0.94	0.9276	150	0.6970	0.7931	0.7419	29	0.8158	0.9118	0.8611	34	0.8153	0.8803	0.8466	0.9658
0.0006	92.0	9752	0.3235	0.7895	0.8219	0.8054	73	0.7013	0.8308	0.7606	65	0.9216	0.94	0.9307	150	0.6765	0.7931	0.7302	29	0.8158	0.9118	0.8611	34	0.8175	0.8803	0.8477	0.9660
0.0002	93.0	9858	0.3225	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9216	0.94	0.9307	150	0.6471	0.7586	0.6984	29	0.8378	0.9118	0.8732	34	0.8175	0.8803	0.8477	0.9665
0.0001	94.0	9964	0.3228	0.8026	0.8356	0.8188	73	0.7013	0.8308	0.7606	65	0.9216	0.94	0.9307	150	0.6970	0.7931	0.7419	29	0.8378	0.9118	0.8732	34	0.8245	0.8832	0.8528	0.9665
0.0001	95.0	10070	0.3265	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9216	0.94	0.9307	150	0.6970	0.7931	0.7419	29	0.8378	0.9118	0.8732	34	0.8223	0.8832	0.8516	0.9663
0.0001	96.0	10176	0.3283	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9156	0.94	0.9276	150	0.6970	0.7931	0.7419	29	0.8378	0.9118	0.8732	34	0.8201	0.8832	0.8505	0.9668
0.0002	97.0	10282	0.3329	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.6667	0.7586	0.7097	29	0.8378	0.9118	0.8732	34	0.8206	0.8860	0.8521	0.9670
0.0001	98.0	10388	0.3322	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.6667	0.7586	0.7097	29	0.8378	0.9118	0.8732	34	0.8206	0.8860	0.8521	0.9670
0.0001	99.0	10494	0.3324	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.6667	0.7586	0.7097	29	0.8378	0.9118	0.8732	34	0.8206	0.8860	0.8521	0.9670
0.0003	100.0	10600	0.3325	0.7922	0.8356	0.8133	73	0.7013	0.8308	0.7606	65	0.9226	0.9533	0.9377	150	0.6667	0.7586	0.7097	29	0.8378	0.9118	0.8732	34	0.8206	0.8860	0.8521	0.9670

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2