# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("anarodrdi/traductor-de-en")
model = AutoModelForSeq2SeqLM.from_pretrained("anarodrdi/traductor-de-en", device_map="auto")Quick Links
traductor-de-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-de-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9462
- Bleu: 22.8119
- Gen Len: 28.2148
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: 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
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.0710 | 1.0 | 1563 | 1.9678 | 22.5921 | 28.1746 |
| 1.9293 | 2.0 | 3126 | 1.9462 | 22.8119 | 28.2148 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.9.0+cu126
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- 12
Model tree for anarodrdi/traductor-de-en
Base model
Helsinki-NLP/opus-mt-de-en
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="anarodrdi/traductor-de-en")