Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbart-large-50-many-to-many-mmt-finetuned-skr-en_2.8k – AI Model by Shamus | AlphaNeural AI
You can deploy this model and start earning money today!
Shamus
/
mbart-large-50-many-to-many-mmt-finetuned-skr-en_2.8k
like
0
transformers
pytorch
tensorboard
mbart
text2text-generation
generated_from_trainer
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mbart-large-50-many-to-many-mmt-finetuned-ar_AR-to-en_XX
This model is a fine-tuned version of
facebook/mbart-large-50-many-to-many-mmt
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.2315
Bleu: 28.2149
Gen Len: 35.188
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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
Gen Len
1.3194
1.0
2759
1.2315
28.2149
35.188
Framework versions
Transformers 4.21.2
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1
