Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbart-large-50-GEC-spanish-cowsl2h – AI Model by Ro551 | AlphaNeural AI
You can deploy this model and start earning money today!
Ro551
/
mbart-large-50-GEC-spanish-cowsl2h
like
0
transformers
safetensors
mbart
text2text-generation
generated_from_trainer
facebook/mbart-large-50
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mbart-large-50-GEC-spanish-cowsl2h
This model is a fine-tuned version of
facebook/mbart-large-50
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.2795
Gleu: 0.5138
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: 9.175332375538101e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
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: 0.05586177114362126
num_epochs: 4
Training results
Training Loss
Epoch
Step
Validation Loss
Gleu
No log
1.0
97
0.0757
0.5037
47.5108
2.0
194
0.0594
0.5868
0.8048
3.0
291
0.0656
0.6126
0.3084
4.0
388
0.2795
0.5138
Framework versions
Transformers 5.12.1
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
