Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
fnet-large-finetuned-qqp – AI Model by gchhablani | AlphaNeural AI
You can deploy this model and start earning money today!
gchhablani
/
fnet-large-finetuned-qqp
like
0
transformers
pytorch
tensorboard
fnet
text-classification
generated_from_trainer
en
glue
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
fnet-large-finetuned-qqp
This model is a fine-tuned version of
google/fnet-large
on the GLUE QQP dataset. It achieves the following results on the evaluation set:
Loss: 0.5515
Accuracy: 0.8943
F1: 0.8557
Combined Score: 0.8750
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: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
F1
Combined Score
0.4574
1.0
90962
0.4946
0.8694
0.8297
0.8496
0.3387
2.0
181924
0.4745
0.8874
0.8437
0.8655
0.2029
3.0
272886
0.5515
0.8943
0.8557
0.8750
Framework versions
Transformers 4.11.0.dev0
Pytorch 1.9.0
Datasets 1.12.1
Tokenizers 0.10.3
