metadata
library_name: transformers
license: mit
base_model: NIRVLab/bartede
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: ViEde
results: []
ViEde
This model is a fine-tuned version of NIRVLab/bartede on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4809
- Bleu: 22.833
- Chrf++: 46.2491
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: 100
- eval_batch_size: 100
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf++ |
|---|---|---|---|---|---|
| 0.273 | 1.0 | 2080 | 0.4809 | 22.833 | 46.2491 |
| 0.1331 | 2.0 | 4160 | 0.5284 | 24.6028 | 48.483 |
| 0.0964 | 3.0 | 6240 | 0.5543 | 25.6692 | 49.2306 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2