ner-coin-v3

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0147
• Precision: 0.9941
• Recall: 0.9931
• F1: 0.9936
• Accuracy: 0.9978

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: 64
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	52	0.1916	0.9775	0.9777	0.9776	0.9935
No log	2.0	104	0.1443	0.9815	0.9823	0.9819	0.9948
No log	3.0	156	0.1142	0.9844	0.9844	0.9844	0.9953
No log	4.0	208	0.0938	0.9852	0.9834	0.9843	0.9952
No log	5.0	260	0.0764	0.9870	0.9870	0.9870	0.9959
No log	6.0	312	0.0649	0.9876	0.9874	0.9875	0.9962
No log	7.0	364	0.0552	0.9903	0.9893	0.9898	0.9968
No log	8.0	416	0.0500	0.9884	0.9876	0.988	0.9962
No log	9.0	468	0.0443	0.9882	0.9878	0.9880	0.9963
0.1249	10.0	520	0.0402	0.9882	0.9880	0.9881	0.9962
0.1249	11.0	572	0.0351	0.9901	0.9884	0.9893	0.9967
0.1249	12.0	624	0.0315	0.9909	0.9882	0.9896	0.9969
0.1249	13.0	676	0.0307	0.9897	0.9888	0.9893	0.9966
0.1249	14.0	728	0.0268	0.9897	0.9895	0.9896	0.9967
0.1249	15.0	780	0.0277	0.9897	0.9861	0.9879	0.9962
0.1249	16.0	832	0.0242	0.9916	0.9893	0.9904	0.9971
0.1249	17.0	884	0.0214	0.9920	0.9901	0.9910	0.9973
0.1249	18.0	936	0.0216	0.9920	0.9895	0.9907	0.9972
0.1249	19.0	988	0.0211	0.9922	0.9899	0.9910	0.9972
0.0243	20.0	1040	0.0183	0.9930	0.9912	0.9921	0.9975
0.0243	21.0	1092	0.0161	0.9922	0.9907	0.9915	0.9974
0.0243	22.0	1144	0.0169	0.9935	0.9914	0.9924	0.9975
0.0243	23.0	1196	0.0176	0.9914	0.9897	0.9905	0.9972
0.0243	24.0	1248	0.0160	0.9918	0.9905	0.9912	0.9973
0.0243	25.0	1300	0.0150	0.9928	0.9918	0.9923	0.9974
0.0243	26.0	1352	0.0143	0.9935	0.9918	0.9926	0.9977
0.0243	27.0	1404	0.0140	0.9920	0.9918	0.9919	0.9973
0.0243	28.0	1456	0.0152	0.9909	0.9905	0.9907	0.9970
0.0111	29.0	1508	0.0147	0.9916	0.9907	0.9912	0.9972
0.0111	30.0	1560	0.0146	0.9920	0.9912	0.9916	0.9973
0.0111	31.0	1612	0.0143	0.9912	0.9905	0.9908	0.9970
0.0111	32.0	1664	0.0139	0.9907	0.9905	0.9906	0.9970
0.0111	33.0	1716	0.0144	0.9912	0.9912	0.9912	0.9970
0.0111	34.0	1768	0.0137	0.9922	0.9916	0.9919	0.9973
0.0111	35.0	1820	0.0139	0.9937	0.9926	0.9932	0.9977
0.0111	36.0	1872	0.0146	0.9912	0.9914	0.9913	0.9970
0.0111	37.0	1924	0.0138	0.9928	0.9920	0.9924	0.9975
0.0111	38.0	1976	0.0125	0.9933	0.9928	0.9931	0.9977
0.0062	39.0	2028	0.0138	0.9922	0.9914	0.9918	0.9973
0.0062	40.0	2080	0.0131	0.9918	0.9910	0.9914	0.9972
0.0062	41.0	2132	0.0141	0.9914	0.9912	0.9913	0.9971
0.0062	42.0	2184	0.0137	0.9930	0.9922	0.9926	0.9975
0.0062	43.0	2236	0.0139	0.9920	0.9910	0.9915	0.9973
0.0062	44.0	2288	0.0146	0.9924	0.9920	0.9922	0.9974
0.0062	45.0	2340	0.0134	0.9933	0.9924	0.9928	0.9977
0.0062	46.0	2392	0.0149	0.9935	0.9924	0.9929	0.9977
0.0062	47.0	2444	0.0124	0.9933	0.9926	0.9929	0.9977
0.0062	48.0	2496	0.0125	0.9931	0.9924	0.9927	0.9976
0.0037	49.0	2548	0.0130	0.9916	0.9910	0.9913	0.9972
0.0037	50.0	2600	0.0129	0.9928	0.9924	0.9926	0.9975
0.0037	51.0	2652	0.0128	0.9935	0.9926	0.9931	0.9975
0.0037	52.0	2704	0.0136	0.9922	0.9918	0.9920	0.9973
0.0037	53.0	2756	0.0141	0.9926	0.9916	0.9921	0.9974
0.0037	54.0	2808	0.0135	0.9933	0.9926	0.9929	0.9978
0.0037	55.0	2860	0.0147	0.9935	0.9922	0.9928	0.9975
0.0037	56.0	2912	0.0142	0.9935	0.9926	0.9931	0.9977
0.0037	57.0	2964	0.0139	0.9931	0.9926	0.9928	0.9975
0.0027	58.0	3016	0.0136	0.9935	0.9928	0.9932	0.9977
0.0027	59.0	3068	0.0143	0.9935	0.9926	0.9931	0.9976
0.0027	60.0	3120	0.0141	0.9933	0.9926	0.9929	0.9975
0.0027	61.0	3172	0.0129	0.9939	0.9931	0.9935	0.9978
0.0027	62.0	3224	0.0137	0.9939	0.9931	0.9935	0.9978
0.0027	63.0	3276	0.0136	0.9935	0.9924	0.9929	0.9977
0.0027	64.0	3328	0.0141	0.9933	0.9926	0.9929	0.9977
0.0027	65.0	3380	0.0141	0.9939	0.9931	0.9935	0.9978
0.0027	66.0	3432	0.0137	0.9939	0.9928	0.9934	0.9978
0.0027	67.0	3484	0.0145	0.9924	0.9916	0.992	0.9973
0.0019	68.0	3536	0.0150	0.9937	0.9924	0.9931	0.9977
0.0019	69.0	3588	0.0152	0.9930	0.9920	0.9925	0.9975
0.0019	70.0	3640	0.0149	0.9926	0.9918	0.9922	0.9973
0.0019	71.0	3692	0.0143	0.9935	0.9924	0.9929	0.9976
0.0019	72.0	3744	0.0152	0.9937	0.9924	0.9931	0.9977
0.0019	73.0	3796	0.0149	0.9933	0.9922	0.9927	0.9975
0.0019	74.0	3848	0.0158	0.9935	0.9922	0.9928	0.9976
0.0019	75.0	3900	0.0153	0.9928	0.9918	0.9923	0.9975
0.0019	76.0	3952	0.0154	0.9928	0.9920	0.9924	0.9975
0.0015	77.0	4004	0.0145	0.9937	0.9928	0.9933	0.9977
0.0015	78.0	4056	0.0158	0.9928	0.9920	0.9924	0.9975
0.0015	79.0	4108	0.0161	0.9933	0.9922	0.9927	0.9975
0.0015	80.0	4160	0.0155	0.9935	0.9924	0.9929	0.9976
0.0015	81.0	4212	0.0157	0.9933	0.9922	0.9927	0.9975
0.0015	82.0	4264	0.0155	0.9933	0.9922	0.9927	0.9975
0.0015	83.0	4316	0.0144	0.9939	0.9931	0.9935	0.9978
0.0015	84.0	4368	0.0142	0.9939	0.9931	0.9935	0.9978
0.0015	85.0	4420	0.0145	0.9941	0.9931	0.9936	0.9978
0.0015	86.0	4472	0.0151	0.9935	0.9924	0.9929	0.9977
0.0013	87.0	4524	0.0143	0.9935	0.9924	0.9929	0.9977
0.0013	88.0	4576	0.0145	0.9933	0.9924	0.9928	0.9976
0.0013	89.0	4628	0.0142	0.9935	0.9926	0.9931	0.9976
0.0013	90.0	4680	0.0142	0.9941	0.9933	0.9937	0.9978
0.0013	91.0	4732	0.0145	0.9941	0.9931	0.9936	0.9978
0.0013	92.0	4784	0.0146	0.9941	0.9931	0.9936	0.9978
0.0013	93.0	4836	0.0146	0.9939	0.9931	0.9935	0.9978
0.0013	94.0	4888	0.0147	0.9941	0.9931	0.9936	0.9978
0.0013	95.0	4940	0.0148	0.9941	0.9931	0.9936	0.9978
0.0013	96.0	4992	0.0147	0.9941	0.9931	0.9936	0.9978
0.0011	97.0	5044	0.0147	0.9939	0.9931	0.9935	0.9978
0.0011	98.0	5096	0.0147	0.9939	0.9931	0.9935	0.9978
0.0011	99.0	5148	0.0147	0.9939	0.9931	0.9935	0.9978
0.0011	100.0	5200	0.0147	0.9941	0.9931	0.9936	0.9978

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1