bert-base-multilingual-uncased-finetuned-Wikipedia
This model is a fine-tuned version of bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5849
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: 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8871 | 1.0 | 4245 | 1.7547 |
| 1.7724 | 2.0 | 8490 | 1.6908 |
| 1.7043 | 3.0 | 12735 | 1.6484 |
| 1.6498 | 4.0 | 16980 | 1.6286 |
| 1.6111 | 5.0 | 21225 | 1.5932 |
| 1.5868 | 6.0 | 25470 | 1.5744 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 33
Model tree for rman-rahimi-29/bert-base-multilingual-uncased-finetuned-Wikipedia
Base model
google-bert/bert-base-multilingual-uncased