Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
my-bert-base-uncased-finetuned-CNN-cola-model – AI Model by aysin | AlphaNeural AI
You can deploy this model and start earning money today!
aysin
/
my-bert-base-uncased-finetuned-CNN-cola-model
like
0
transformers
pytorch
generated_from_trainer
glue
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bert-base-uncased-finetuned-cola
This model is a fine-tuned version of
bert-base-uncased
and CNN on the glue dataset.
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: 1.8141004193400237e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
dropout: 0.5979031154399792
max_length: 32
Training results
Training Loss
Epoch
Step
Validation Loss
Matthews Correlation
0.57043
15.0
-
-
0.5233213
Average Training Accuracy: 72.0026% Average Validation Accuracy: 81.240%
Framework versions
Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3
