Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bert-base-uncased-finetuned-wikitext – AI Model by peteryushunli | AlphaNeural AI
You can deploy this model and start earning money today!
peteryushunli
/
bert-base-uncased-finetuned-wikitext
like
0
transformers
pytorch
bert
fill-mask
generated_from_trainer
wikitext
google-bert/bert-base-uncased
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bert-base-uncased-finetuned-wikitext
This model is a fine-tuned version of
bert-base-uncased
on the wikitext dataset. It achieves the following results on the evaluation set:
Loss: 1.8657
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: 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: 3.0
Training results
Training Loss
Epoch
Step
Validation Loss
2.143
1.0
157
1.9046
1.9852
2.0
314
1.8427
1.9432
3.0
471
1.8492
Framework versions
Transformers 4.32.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3
