metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-multilingual-uncased-thesis_arian
results: []
bert-base-multilingual-uncased-thesis_arian
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1946
- Accuracy: 0.9677
- Macro f1 score: 0.9677
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro f1 score |
|---|---|---|---|---|---|
| 0.216 | 1.0 | 102 | 0.2649 | 0.9097 | 0.9094 |
| 0.1246 | 2.0 | 204 | 0.1364 | 0.9398 | 0.9398 |
| 0.0888 | 3.0 | 306 | 0.1634 | 0.9462 | 0.9462 |
| 0.0522 | 4.0 | 408 | 0.1550 | 0.9656 | 0.9656 |
| 0.0227 | 5.0 | 510 | 0.2073 | 0.9591 | 0.9591 |
| 0.0065 | 6.0 | 612 | 0.2140 | 0.9677 | 0.9677 |
| 0.0028 | 7.0 | 714 | 0.2005 | 0.9656 | 0.9656 |
| 0.0017 | 8.0 | 816 | 0.1946 | 0.9677 | 0.9677 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2