XLM-RoBERTa-Large-PANX-WikiAnn-en
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the google/xtreme dataset (English split of the PAN-X). It achieves the following results on the evaluation set:
- Loss: 0.2569
- Precision: 0.8347
- Recall: 0.8529
- F1: 0.8437
- Accuracy: 0.9357
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 111
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for ShkalikovOleh/xlm-roberta-large-panx-wikiann-en
Base model
FacebookAI/xlm-roberta-largeDataset used to train ShkalikovOleh/xlm-roberta-large-panx-wikiann-en
Evaluation results
- Precision on google/xtremevalidation set self-reported0.835
- Recall on google/xtremevalidation set self-reported0.853
- F1 on google/xtremevalidation set self-reported0.844
- Accuracy on google/xtremevalidation set self-reported0.936