metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
model-index:
- name: training_output
results: []
training_output
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: 7.1415
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: 55
- eval_batch_size: 55
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.1623 | 0.2237 | 100 | 7.1515 |
| 7.1515 | 0.4474 | 200 | 7.1525 |
| 7.1559 | 0.6711 | 300 | 7.1439 |
| 7.1529 | 0.8949 | 400 | 7.1464 |
| 7.1468 | 1.1186 | 500 | 7.1469 |
| 7.1405 | 1.3423 | 600 | 7.1417 |
| 7.1446 | 1.5660 | 700 | 7.1403 |
| 7.1459 | 1.7897 | 800 | 7.1419 |
| 7.1484 | 2.0134 | 900 | 7.1437 |
| 7.1426 | 2.2371 | 1000 | 7.1377 |
| 7.1426 | 2.4609 | 1100 | 7.1353 |
| 7.1441 | 2.6846 | 1200 | 7.1382 |
| 7.1393 | 2.9083 | 1300 | 7.1415 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Tokenizers 0.19.1