metadata
library_name: transformers
tags:
- generated_from_trainer
- translation
language:
- en
- fr
- it
- ro
- es
- pt
pipeline_tag: translation
widget:
- text: '>>ita<< This is a test'
inference:
parameters:
max_new_tokens: 80
do_sample: true
top_k: 30
top_p: 0.95
Model Card for Model ID
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-roa on a dataset of medical diagnostic technical content.
Model Description
- Developed by: Chiara Baffelli
- Language(s) (NLP): EN, FR, ES, IT, PT, RO
- Finetuned from model [optional]: Helsinki-NLP/opus-mt-en-roa
Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1