--- library_name: transformers license: apache-2.0 base_model: Geotrend/distilbert-base-ru-cased tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: nerus-distilbert results: [] --- # nerus-distilbert This model is a fine-tuned version of [Geotrend/distilbert-base-ru-cased](https://huggingface.co/Geotrend/distilbert-base-ru-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0208 - Precision: 0.9553 - Recall: 0.9578 - F1: 0.9566 - Accuracy: 0.9948 ## 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: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0187 | 1.0 | 10000 | 0.0174 | 0.9518 | 0.9505 | 0.9511 | 0.9945 | | 0.0095 | 2.0 | 20000 | 0.0188 | 0.9541 | 0.9580 | 0.9560 | 0.9947 | | 0.0052 | 3.0 | 30000 | 0.0208 | 0.9553 | 0.9578 | 0.9566 | 0.9948 | ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1