metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: bert-base-multilingual-cased-rus
results: []
bert-base-multilingual-cased-rus
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0760
- Accuracy: 0.8619
- F1 Binary: 0.6526
- Precision: 0.5332
- Recall: 0.8407
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Binary | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 201 | 0.1080 | 0.7180 | 0.4526 | 0.3230 | 0.7560 |
| No log | 2.0 | 402 | 0.0889 | 0.7540 | 0.5003 | 0.3643 | 0.7984 |
| 0.0899 | 3.0 | 603 | 0.0808 | 0.8237 | 0.5815 | 0.4587 | 0.7944 |
| 0.0899 | 4.0 | 804 | 0.0760 | 0.8619 | 0.6526 | 0.5332 | 0.8407 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0