metadata

language:
  - mn
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-base-ner-hrl-ner-finetuning
    results: []

xlm-roberta-base-ner-hrl-ner-finetuning

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

Loss: 0.1135
Precision: 0.9290
Recall: 0.9367
F1: 0.9328
Accuracy: 0.9801

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: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1534	1.0	477	0.0870	0.9001	0.9124	0.9062	0.9740
0.077	2.0	954	0.0764	0.9187	0.9321	0.9253	0.9789
0.0529	3.0	1431	0.0845	0.9178	0.9313	0.9245	0.9791
0.0377	4.0	1908	0.0805	0.9200	0.9310	0.9255	0.9795
0.0292	5.0	2385	0.0918	0.9278	0.9346	0.9312	0.9795
0.0204	6.0	2862	0.1016	0.9222	0.9323	0.9273	0.9790
0.0167	7.0	3339	0.1066	0.9271	0.9327	0.9299	0.9790
0.0134	8.0	3816	0.1088	0.9253	0.9358	0.9305	0.9797
0.0101	9.0	4293	0.1134	0.9289	0.9357	0.9323	0.9798
0.0079	10.0	4770	0.1135	0.9290	0.9367	0.9328	0.9801

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3