metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-base-multilingual-cased-yor
results: []
bert-base-multilingual-cased-yor
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0970
- Accuracy: 0.8912
- F1: 0.8399
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 187 | 0.1010 | 0.8912 | 0.8399 |
| No log | 2.0 | 374 | 0.0983 | 0.8912 | 0.8399 |
| 0.1112 | 3.0 | 561 | 0.0971 | 0.8912 | 0.8399 |
| 0.1112 | 4.0 | 748 | 0.0970 | 0.8912 | 0.8399 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1