videberta-large-ner-ghtk-hirach_NER-first_1000_data-3090-15Nov

This model is a fine-tuned version of Fsoft-AIC/videberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0976
• Accuracy: 0.9816
• F1: 0.0
• Precision: 0.0
• Recall: 0.0

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: 2.5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	250	0.0903	0.9825	0.0	0.0	0.0
0.1532	2.0	500	0.0942	0.9825	0.0	0.0	0.0
0.1532	3.0	750	0.0947	0.9825	0.0	0.0	0.0
0.0772	4.0	1000	0.0956	0.9825	0.0	0.0	0.0
0.0772	5.0	1250	0.0964	0.9825	0.0	0.0	0.0
0.0769	6.0	1500	0.0952	0.9825	0.0	0.0	0.0
0.0769	7.0	1750	0.0988	0.9825	0.0	0.0	0.0
0.0766	8.0	2000	0.0983	0.9825	0.0	0.0	0.0
0.0766	9.0	2250	0.0971	0.9825	0.0	0.0	0.0
0.0769	10.0	2500	0.0984	0.9825	0.0	0.0	0.0
0.0769	11.0	2750	0.1002	0.9825	0.0	0.0	0.0
0.0768	12.0	3000	0.0989	0.9825	0.0	0.0	0.0
0.0768	13.0	3250	0.0994	0.9825	0.0	0.0	0.0
0.0766	14.0	3500	0.0994	0.9825	0.0	0.0	0.0
0.0766	15.0	3750	0.0994	0.9825	0.0	0.0	0.0
0.0763	16.0	4000	0.0991	0.9825	0.0	0.0	0.0
0.0763	17.0	4250	0.1011	0.9825	0.0	0.0	0.0
0.0766	18.0	4500	0.0995	0.9825	0.0	0.0	0.0
0.0766	19.0	4750	0.1003	0.9825	0.0	0.0	0.0
0.0761	20.0	5000	0.0996	0.9825	0.0	0.0	0.0
0.0761	21.0	5250	0.1004	0.9825	0.0	0.0	0.0
0.0757	22.0	5500	0.1002	0.9825	0.0	0.0	0.0
0.0757	23.0	5750	0.0993	0.9825	0.0	0.0	0.0
0.0749	24.0	6000	0.0981	0.9825	0.0	0.0	0.0
0.0749	25.0	6250	0.0986	0.9825	0.0	0.0	0.0
0.0739	26.0	6500	0.0991	0.9825	0.0	0.0	0.0
0.0739	27.0	6750	0.0983	0.9825	0.0	0.0	0.0
0.0723	28.0	7000	0.0985	0.9808	0.0	0.0	0.0
0.0723	29.0	7250	0.1009	0.9800	0.0	0.0	0.0
0.0713	30.0	7500	0.0995	0.9812	0.0	0.0	0.0
0.0713	31.0	7750	0.0983	0.9816	0.0	0.0	0.0
0.0699	32.0	8000	0.0969	0.9820	0.0	0.0	0.0
0.0699	33.0	8250	0.0982	0.9816	0.0	0.0	0.0
0.0691	34.0	8500	0.0973	0.9816	0.0	0.0	0.0
0.0691	35.0	8750	0.0984	0.9812	0.0	0.0	0.0
0.0684	36.0	9000	0.0977	0.9816	0.0	0.0	0.0
0.0684	37.0	9250	0.0978	0.9816	0.0	0.0	0.0
0.0676	38.0	9500	0.0972	0.9820	0.0	0.0	0.0
0.0676	39.0	9750	0.0977	0.9816	0.0	0.0	0.0
0.0671	40.0	10000	0.0976	0.9816	0.0	0.0	0.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1