metadata
library_name: transformers
license: mit
base_model: Gherman/bert-base-NER-Russian
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert_base_ner_rus_2e-05_bs4_ep3_span_detection
results: []
bert_base_ner_rus_2e-05_bs4_ep3_span_detection
This model is a fine-tuned version of Gherman/bert-base-NER-Russian on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4728
- Precision: 0.6591
- Recall: 0.5538
- F1: 0.6019
- Accuracy: 0.7746
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|
| 0.641 | 1.0 | 377 | 0.5038 | 0.6430 | 0.4447 | 0.5258 | 0.7532 |
| 0.5588 | 2.0 | 754 | 0.4863 | 0.7196 | 0.3447 | 0.4661 | 0.7570 |
| 0.4776 | 3.0 | 1131 | 0.4728 | 0.6591 | 0.5538 | 0.6019 | 0.7746 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1