simoneteglia/xlm-roberta-europarl-language-detection

model

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

• Loss: 0.0237
• Accuracy: 0.9967
• F1: 0.9967

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 256
• eval_batch_size: 512
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	821	0.0270	0.9965	0.9965
0.2372	2.0	1642	0.0237	0.9967	0.9967

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3