metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: fias_NER
results: []
fias_NER
This model is a fine-tuned version of cointegrated/rubert-tiny2 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0033
- eval_precision: 0.9977
- eval_recall: 0.9978
- eval_f1: 0.9978
- eval_accuracy: 0.9987
- eval_runtime: 793.6688
- eval_samples_per_second: 2519.942
- eval_steps_per_second: 4.923
- epoch: 1.06
- step: 300000
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: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000000
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3