Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bart-base-finetuned-en-to-ro – AI Model by nmb-paperspace-hf | AlphaNeural AI
You can deploy this model and start earning money today!
nmb-paperspace-hf
/
bart-base-finetuned-en-to-ro
like
0
transformers
pytorch
optimum_graphcore
bart
text-generation
generated_from_trainer
wmt16
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bart-base-finetuned-en-to-ro
This model is a fine-tuned version of
facebook/bart-base
on the wmt16 dataset. It achieves the following results on the evaluation set:
Loss: 1.6768
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
distributed_type: IPU
gradient_accumulation_steps: 128
total_train_batch_size: 128
total_eval_batch_size: 6
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1
training precision: Mixed Precision
Training results
Training Loss
Epoch
Step
Validation Loss
0.9521
1.0
4768
1.6768
Framework versions
Transformers 4.20.1
Pytorch 1.10.0+cpu
Datasets 2.7.1
Tokenizers 0.12.1
