Keyurjotaniya007/xlm-roberta-base-xnli-multilingual

Multilingual Natural Language Inference (XNLI) – XLM-R Tokenizer

This model is a fine-tuned version of xlm-roberta-base on an xnli[all_languages]. It achieves the following results on the evaluation set:

• Loss: 0.8065

• F1: 0.6668

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-5

• train_batch_size: 8

• eval_batch_size: 8

• seed: 42

• weight_decay=0.01

• warmup_ratio=0.1

• num_epochs: 1

Training results

Training Loss | Epoch | Validation Loss | F1

0.6133    |   1   |      0.8065     |  0.6668

Framework versions

• Transformers 4.38.2

• Pytorch 2.2.1+cu121

• Datasets 2.18.0

• Tokenizers 0.15.2