metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - xtreme
metrics:
  - f1
model-index:
  - name: XLM-R-fine-tuned-for-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: xtreme
          type: xtreme
          args: PAN-X.en
        metrics:
          - name: F1
            type: f1
            value: 0.8377982238973259

XLM-R-fine-tuned-for-ner

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

Loss: 0.5679
F1: 0.8378

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: 5e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.4202	1.0	2500	0.3449	0.7963
0.2887	2.0	5000	0.2756	0.8057
0.2309	3.0	7500	0.2971	0.8040
0.1832	4.0	10000	0.3319	0.8167
0.1461	5.0	12500	0.3958	0.8350
0.114	6.0	15000	0.4087	0.8316
0.0833	7.0	17500	0.4320	0.8361
0.0614	8.0	20000	0.4885	0.8353
0.039	9.0	22500	0.5408	0.8390
0.0251	10.0	25000	0.5679	0.8378

Framework versions

Transformers 4.15.0
Pytorch 1.9.1
Datasets 1.18.3
Tokenizers 0.10.3