metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: results
results: []
results
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2090
- Accuracy: 0.9467
- F1: 0.9463
- Precision: 0.9469
- Recall: 0.9467
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4561 | 1.0 | 1098 | 0.3688 | 0.8738 | 0.8709 | 0.8760 | 0.8738 |
| 0.3126 | 2.0 | 2196 | 0.2254 | 0.9339 | 0.9335 | 0.9340 | 0.9339 |
| 0.3852 | 3.0 | 3294 | 0.3113 | 0.9280 | 0.9274 | 0.9284 | 0.9280 |
| 0.2341 | 4.0 | 4392 | 0.2376 | 0.9417 | 0.9417 | 0.9418 | 0.9417 |
| 0.2108 | 5.0 | 5490 | 0.2433 | 0.9408 | 0.9407 | 0.9407 | 0.9408 |
| 0.0882 | 6.0 | 6588 | 0.2353 | 0.9371 | 0.9364 | 0.9384 | 0.9371 |
| 0.127 | 7.0 | 7686 | 0.2674 | 0.9276 | 0.9270 | 0.9277 | 0.9276 |
| 0.1413 | 8.0 | 8784 | 0.2859 | 0.9339 | 0.9341 | 0.9344 | 0.9339 |
| 0.7061 | 9.0 | 9882 | 0.6121 | 0.6761 | 0.5834 | 0.7861 | 0.6761 |
| 0.2076 | 10.0 | 10980 | 0.2090 | 0.9467 | 0.9463 | 0.9469 | 0.9467 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2