metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: bert-base-multilingual-cased
metrics:
- accuracy
model-index:
- name: fine-tune-berta-TNR-split-headline1
results: []
fine-tune-berta-TNR-split-headline1
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: 1.0587
- Accuracy: 0.4737
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.081 | 1.0 | 5 | 1.0624 | 0.4737 |
| 1.0833 | 2.0 | 10 | 1.0596 | 0.4737 |
| 1.0903 | 3.0 | 15 | 1.0605 | 0.4737 |
| 1.0672 | 4.0 | 20 | 1.0587 | 0.4737 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1