Quick Links
test-trainer
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3260
- Bleu: 37.9043
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: 128
- eval_batch_size: 128
- seed: 20
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 5.5534 | 1.0 | 59 | 1.3351 | 37.7388 |
| 5.4277 | 2.0 | 118 | 1.3273 | 37.6248 |
| 5.3598 | 3.0 | 177 | 1.3260 | 37.9043 |
Framework versions
- Transformers 5.5.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for kaanino/marianmt-en-fr_sft
Base model
Helsinki-NLP/opus-mt-en-fr
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kaanino/marianmt-en-fr_sft") model = AutoModelForSeq2SeqLM.from_pretrained("kaanino/marianmt-en-fr_sft", device_map="auto")