Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
t5-small-finetuned-en-to-ro-lr_2e-6 – AI Model by eliotm | AlphaNeural AI
You can deploy this model and start earning money today!
eliotm
/
t5-small-finetuned-en-to-ro-lr_2e-6
like
0
transformers
pytorch
tensorboard
t5
text2text-generation
generated_from_trainer
wmt16
apache-2.0
model-index
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
t5-small-finetuned-en-to-ro-lr_2e-6
This model is a fine-tuned version of
t5-small
on the wmt16 dataset. It achieves the following results on the evaluation set:
Loss: 1.4232
Bleu: 7.2935
Gen Len: 18.2521
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-06
train_batch_size: 10
eval_batch_size: 10
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 0.04375
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Bleu
Gen Len
0.6703
0.04
2671
1.4232
7.2935
18.2521
Framework versions
Transformers 4.12.5
Pytorch 1.10.0+cu111
Datasets 1.16.1
Tokenizers 0.10.3
