Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
t5-small-finetuned-cnndm1-wikihow0 – AI Model by Chikashi | AlphaNeural AI
You can deploy this model and start earning money today!
Chikashi
/
t5-small-finetuned-cnndm1-wikihow0
like
0
transformers
pytorch
tensorboard
t5
text2text-generation
generated_from_trainer
cnn_dailymail
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-cnndm1-wikihow0
This model is a fine-tuned version of
t5-small
on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
Loss: 1.6436
Rouge1: 24.6116
Rouge2: 11.8788
Rougel: 20.3665
Rougelsum: 23.2474
Gen Len: 18.9998
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: 0.0003
train_batch_size: 4
eval_batch_size: 4
seed: 42
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
Rouge1
Rouge2
Rougel
Rougelsum
Gen Len
1.8208
1.0
71779
1.6436
24.6116
11.8788
20.3665
23.2474
18.9998
Framework versions
Transformers 4.18.0
Pytorch 1.10.0+cu111
Datasets 2.1.0
Tokenizers 0.12.1
