xlm-roberta-base-finetuned-ner-MBS-headline

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0179
• Precision: 0.4444
• Recall: 0.6667
• F1: 0.5333
• Accuracy: 0.9952

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: 1e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0973	1.0	46	0.1471	0.0	0.0	0.0	0.9719
0.0772	2.0	92	0.1025	0.0	0.0	0.0	0.9719
0.0387	3.0	138	0.1196	0.0	0.0	0.0	0.9619
0.0426	4.0	184	0.0856	0.0	0.0	0.0	0.9666
0.0215	5.0	230	0.1246	0.0303	0.0385	0.0339	0.9575
0.036	6.0	276	0.1876	0.0580	0.1026	0.0741	0.9404
0.008	7.0	322	0.1274	0.2360	0.2692	0.2515	0.9672
0.0062	8.0	368	0.1915	0.2857	0.5385	0.3733	0.9454
0.0042	9.0	414	0.2120	0.3185	0.6410	0.4255	0.9457
0.0105	10.0	460	0.1899	0.3154	0.6026	0.4141	0.9534
0.0103	11.0	506	0.2355	0.2917	0.6282	0.3984	0.9453
0.0047	12.0	552	0.1864	0.3561	0.6026	0.4476	0.9611
0.0246	13.0	598	0.2306	0.3268	0.6410	0.4329	0.9494
0.0008	14.0	644	0.2187	0.3357	0.6026	0.4312	0.9512
0.0007	15.0	690	0.2022	0.3582	0.6154	0.4528	0.9572
0.0108	16.0	736	0.1974	0.3664	0.6154	0.4593	0.9596
0.0005	17.0	782	0.2074	0.3478	0.6154	0.4444	0.9573
0.0008	18.0	828	0.2235	0.3333	0.6410	0.4386	0.9532
0.0006	19.0	874	0.2057	0.3228	0.5256	0.4	0.9579
0.0024	20.0	920	0.2130	0.3459	0.5897	0.4360	0.9567

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1