metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
base_model: bert-base-multilingual-uncased
model-index:
- name: bert-base-multilingual-uncased-finetuned-masress
results: []
bert-base-multilingual-uncased-finetuned-masress
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0946
- Accuracy: 0.5782
- F1: 0.5769
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: 64
- eval_batch_size: 64
- 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 | F1 |
|---|---|---|---|---|---|
| 1.1646 | 1.0 | 151 | 1.0626 | 0.5588 | 0.5566 |
| 0.9281 | 2.0 | 302 | 0.9800 | 0.5869 | 0.5792 |
| 0.8269 | 3.0 | 453 | 1.0134 | 0.5911 | 0.5775 |
| 0.7335 | 4.0 | 604 | 1.0644 | 0.5861 | 0.5816 |
| 0.6786 | 5.0 | 755 | 1.0946 | 0.5782 | 0.5769 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1