books_text_class_roBERTa_ru_base

This model is a fine-tuned version of DeepPavlov/xlm-roberta-large-en-ru-mnli on the dataset containing 64 russian books in fb2 format.

It achieves the following results on the evaluation set:

• eval_loss: 0.1550
• eval_accuracy: 0.9824
• eval_f1-score: 0.9804
• eval_mcc: 0.9234
• eval_runtime: 175.3993
• eval_samples_per_second: 90.838
• eval_steps_per_second: 18.17
• epoch: 4.0
• step: 29744

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0