xlm-roberta-large-finetuned-ner

This model is a fine-tuned version of xlm-roberta-large on the hi_ner-original dataset. It achieves the following results on the evaluation set:

• Loss: 0.1611
• Precision: 0.8739
• Recall: 0.8901
• F1: 0.8819
• Accuracy: 0.9663

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1139	1.4768	7000	0.1289	0.8508	0.8893	0.8696	0.9627
0.0838	2.9536	14000	0.1221	0.8740	0.8895	0.8817	0.9668
0.0481	4.4304	21000	0.1460	0.8688	0.8929	0.8807	0.9657
0.0372	5.9072	28000	0.1619	0.8737	0.8902	0.8819	0.9664

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0