metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
model-index:
- name: bert-base-multilingual-cased-2023-11-15-16-53
results: []
bert-base-multilingual-cased-2023-11-15-16-53
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: 0.7909
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| 1.411 | 0.59 | 500 | 1.2887 |
| 1.2513 | 1.19 | 1000 | 1.1391 |
| 1.1402 | 1.78 | 1500 | 1.0585 |
| 1.0788 | 2.38 | 2000 | 1.0004 |
| 1.019 | 2.97 | 2500 | 0.9653 |
| 0.9854 | 3.56 | 3000 | 0.9326 |
| 0.9523 | 4.16 | 3500 | 0.9079 |
| 0.9186 | 4.75 | 4000 | 0.8808 |
| 0.9174 | 5.34 | 4500 | 0.8652 |
| 0.8825 | 5.94 | 5000 | 0.8428 |
| 0.8668 | 6.53 | 5500 | 0.8274 |
| 0.8118 | 7.13 | 6000 | 0.8201 |
| 0.849 | 7.72 | 6500 | 0.8051 |
| 0.8478 | 8.31 | 7000 | 0.7989 |
| 0.8073 | 8.91 | 7500 | 0.7918 |
| 0.8365 | 9.5 | 8000 | 0.7845 |
Framework versions
- Transformers 4.35.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.7
- Tokenizers 0.14.1