Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
bert-base-multilingual-cased-finetuned-hindi – AI Model by pbwinter | AlphaNeural AI
You can deploy this model and start earning money today!
pbwinter
/
bert-base-multilingual-cased-finetuned-hindi
like
0
transformers
tensorboard
safetensors
bert
fill-mask
generated_from_trainer
google-bert/bert-base-multilingual-cased
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bert-base-multilingual-cased-finetuned-hindi
This model is a fine-tuned version of
google-bert/bert-base-multilingual-cased
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.4288
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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.7495
1.0
31250
0.5444
0.5264
2.0
62500
0.4633
0.4477
3.0
93750
0.4288
Framework versions
Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2
