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
