Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
bert-base-uncased_wnli – AI Model by gokulsrinivasagan | AlphaNeural AI
You can deploy this model and start earning money today!
gokulsrinivasagan
/
bert-base-uncased_wnli
like
0
transformers
tensorboard
safetensors
bert
text-classification
generated_from_trainer
en
glue
google-bert/bert-base-uncased
finetune
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bert-base-uncased_wnli
This model is a fine-tuned version of
google-bert/bert-base-uncased
on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
Loss: 0.6960
Accuracy: 0.5634
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: 5e-05
train_batch_size: 256
eval_batch_size: 256
seed: 10
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.7038
1.0
3
0.6960
0.5634
0.695
2.0
6
0.6983
0.5634
0.7035
3.0
9
0.7152
0.2113
0.6978
4.0
12
0.7334
0.2535
0.6949
5.0
15
0.7602
0.2535
0.6916
6.0
18
0.7999
0.2254
Framework versions
Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3
