Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
dbw-bert-large-1 – AI Model by Sacralet | AlphaNeural AI
You can deploy this model and start earning money today!
Sacralet
/
dbw-bert-large-1
like
0
transformers
safetensors
bert
fill-mask
generated_from_trainer
google-bert/bert-large-uncased
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
dbw-bert-large-1
This model is a fine-tuned version of
bert-large-uncased
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.0728
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-07
train_batch_size: 64
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
3.0555
0.36
200
3.2109
1.2673
0.71
400
1.0203
0.3153
1.07
600
0.2516
0.1461
1.42
800
0.1146
0.1046
1.78
1000
0.0854
0.0929
2.13
1200
0.0762
0.085
2.49
1400
0.0734
0.0881
2.84
1600
0.0728
Framework versions
Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0
