learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	367	0.2673	0.8862	0.9071	0.8965	0.9641
0.0058	2.0	734	0.2867	0.8698	0.9108	0.8898	0.9593
0.0058	3.0	1101	0.2704	0.8604	0.9009	0.8801	0.9635
0.0058	4.0	1468	0.2886	0.8985	0.9108	0.9046	0.9641
0.0039	5.0	1835	0.2870	0.9021	0.9133	0.9076	0.9642
0.0018	6.0	2202	0.2958	0.8837	0.9133	0.8982	0.9641
0.0009	7.0	2569	0.2912	0.8908	0.9095	0.9001	0.9651
0.0009	8.0	2936	0.3250	0.8581	0.9145	0.8854	0.9595
0.0017	9.0	3303	0.3341	0.8897	0.8897	0.8897	0.9614
0.0021	10.0	3670	0.2768	0.8772	0.9207	0.8984	0.9639
0.0015	11.0	4037	0.2907	0.8803	0.9207	0.9001	0.9665
0.0015	12.0	4404	0.3031	0.8961	0.9195	0.9076	0.9673
0.001	13.0	4771	0.2833	0.9061	0.9207	0.9133	0.9686
0.0	14.0	5138	0.2925	0.9098	0.9244	0.9170	0.9693
0.0	15.0	5505	0.2930	0.9068	0.9281	0.9173	0.9698
0.0	16.0	5872	0.2950	0.9060	0.9318	0.9188	0.9695
0.0	17.0	6239	0.2976	0.9037	0.9306	0.9170	0.9696
0.0	18.0	6606	0.3001	0.9026	0.9306	0.9164	0.9692
0.0	19.0	6973	0.3025	0.9025	0.9294	0.9158	0.9692
0.0	20.0	7340	0.3050	0.9025	0.9294	0.9158	0.9688
0.0	21.0	7707	0.3075	0.9025	0.9294	0.9158	0.9688
0.0	22.0	8074	0.3096	0.9048	0.9306	0.9175	0.9690
0.0	23.0	8441	0.3120	0.9070	0.9306	0.9187	0.9688
0.0	24.0	8808	0.3141	0.9024	0.9281	0.9151	0.9685
0.0	25.0	9175	0.3165	0.9024	0.9281	0.9151	0.9685
0.0	26.0	9542	0.3188	0.9013	0.9281	0.9145	0.9686
0.0	27.0	9909	0.3210	0.9024	0.9281	0.9151	0.9685
0.0	28.0	10276	0.3232	0.9024	0.9281	0.9151	0.9685
0.0	29.0	10643	0.3256	0.9057	0.9281	0.9168	0.9686
0.0	30.0	11010	0.3278	0.9057	0.9281	0.9168	0.9686
0.0	31.0	11377	0.3299	0.9045	0.9269	0.9155	0.9686
0.0	32.0	11744	0.3322	0.9045	0.9269	0.9155	0.9685
0.0	33.0	12111	0.3340	0.9045	0.9269	0.9155	0.9685
0.0	34.0	12478	0.3363	0.9045	0.9269	0.9155	0.9685
0.0	35.0	12845	0.3384	0.9056	0.9269	0.9161	0.9685
0.0	36.0	13212	0.3406	0.9044	0.9257	0.9149	0.9685
0.0	37.0	13579	0.3424	0.9044	0.9257	0.9149	0.9685
0.0	38.0	13946	0.3442	0.9030	0.9232	0.9130	0.9683
0.0	39.0	14313	0.3461	0.9031	0.9244	0.9137	0.9686
0.0	40.0	14680	0.3479	0.9030	0.9232	0.9130	0.9686
0.0	41.0	15047	0.3495	0.9030	0.9232	0.9130	0.9685
0.0	42.0	15414	0.3510	0.9030	0.9232	0.9130	0.9685
0.0	43.0	15781	0.3525	0.9030	0.9232	0.9130	0.9685
0.0	44.0	16148	0.3539	0.9041	0.9232	0.9135	0.9683
0.0	45.0	16515	0.3551	0.9030	0.9232	0.9130	0.9685
0.0	46.0	16882	0.3562	0.9030	0.9232	0.9130	0.9685
0.0	47.0	17249	0.3570	0.9030	0.9232	0.9130	0.9685
0.0	48.0	17616	0.3575	0.9041	0.9232	0.9135	0.9683
0.0	49.0	17983	0.3580	0.9041	0.9232	0.9135	0.9683
0.0	50.0	18350	0.3580	0.9041	0.9232	0.9135	0.9683

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu126
Datasets 3.2.0
Tokenizers 0.21.0

luohuashijieyoufengjun/ner_based_modern_bert_multilingual

my_ner_model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

luohuashijieyoufengjun/
ner_based_modern_bert_multilingual