language detection fine tuned on xlm roberta base This model is a fine tuned version of xlm roberta base on the common language dataset. It achieves the following results on the evaluation set: Loss: 0.1886 Accuracy: 0.9738 Training hyperparameters The following hyperparameters were used during training: learning rate: 3e 05 train batch size: 1 eval batch size: 1 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 lr scheduler type: linear lr scheduler warmup steps: 500 num epochs: 1 mixed precision training: Native AMP Training results Training Loss Epoch Step Validation Loss Accuracy : : : : : : : : : : 0.1 1.0 22194 0.1886 0.9738 Framework versions Transformers 4.12.5 Pytorch 1.10.0+cu111 Datasets 1.15.1 Tokenizers 0.10.3 Notebook notebook
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy