Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opus-mt-es-en-GEC-spanish-merged – AI Model by Ro551 | AlphaNeural AI
You can deploy this model and start earning money today!
Ro551
/
opus-mt-es-en-GEC-spanish-merged
like
0
transformers
safetensors
marian
text2text-generation
generated_from_trainer
Helsinki-NLP/opus-mt-es-en
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
opus-mt-es-en-GEC-spanish-merged
This model is a fine-tuned version of
Helsinki-NLP/opus-mt-es-en
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.0657
Gleu: 0.7846
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: 8.441362564622899e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.09363965565984424
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Gleu
0.1137
1.0
11213
0.0792
0.7596
0.0644
2.0
22426
0.0657
0.7846
Framework versions
Transformers 5.0.0
Pytorch 2.7.0+cu126
Datasets 4.8.5
Tokenizers 0.22.2
