Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbart-large-50-finetuned-gec – AI Model by smartik | AlphaNeural AI
You can deploy this model and start earning money today!
smartik
/
mbart-large-50-finetuned-gec
like
0
transformers
pytorch
tensorboard
mbart
text2text-generation
generated_from_trainer
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mbart-large-50-finetuned-gec
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: 0.2174
Rouge1: 20.9014
Rouge2: 7.5808
Rougel: 20.8964
Rougelsum: 20.8516
Gen Len: 27.3493
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
Rouge1
Rouge2
Rougel
Rougelsum
Gen Len
0.2337
1.0
2046
0.2174
20.9014
7.5808
20.8964
20.8516
27.3493
Framework versions
Transformers 4.29.2
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3
