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-ron
results: []
bert-base-multilingual-cased-ron
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: 0.0552
- Accuracy: 0.8696
- F1 Binary: 0.8054
- Precision: 0.7226
- Recall: 0.9096
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: 37
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Binary | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 187 | 0.0957 | 0.7502 | 0.6166 | 0.5662 | 0.6768 |
| No log | 2.0 | 374 | 0.0623 | 0.7787 | 0.7014 | 0.5849 | 0.8757 |
| 0.0661 | 3.0 | 561 | 0.0603 | 0.8414 | 0.7736 | 0.6711 | 0.9130 |
| 0.0661 | 4.0 | 748 | 0.0552 | 0.8696 | 0.8054 | 0.7226 | 0.9096 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0