metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: russian-BERT
results: []
russian-BERT
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5708
- Accuracy: 0.8933
- Precision: 0.8933
- Recall: 0.8933
- Micro-avg-recall: 0.8933
- Micro-avg-precision: 0.8933
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
|---|---|---|---|---|---|---|---|---|
| 0.4304 | 1.0 | 750 | 0.3997 | 0.8397 | 0.8399 | 0.8397 | 0.8397 | 0.8397 |
| 0.3907 | 2.0 | 1500 | 0.3305 | 0.873 | 0.8791 | 0.873 | 0.873 | 0.873 |
| 0.1386 | 3.0 | 2250 | 0.3770 | 0.888 | 0.8898 | 0.888 | 0.888 | 0.888 |
| 0.0631 | 4.0 | 3000 | 0.5419 | 0.8887 | 0.8887 | 0.8887 | 0.8887 | 0.8887 |
| 0.1276 | 5.0 | 3750 | 0.5708 | 0.8933 | 0.8933 | 0.8933 | 0.8933 | 0.8933 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1