bert-base-multilingual-cased-finetuned-hindi

pbwinter/bert-base-multilingual-cased-finetuned-hindi

bert-base-multilingual-cased-finetuned-hindi is a fill-mask model from pbwinter. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

130

19% of all-time downloads

All-time downloads

675

Public

Parameters

178M

162 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors712 MB · 99%

At a glance

Task: Fill-Mask
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Feb 28, 2024
Updated: Mar 4, 2024
SHA: 4261ac85

Try a prompt

Base models

google-bert/bert-base-multilingual-cased

Model card

From the Hugging Face model README

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

Task: Fill-Mask
Library: transformers
Type: bert
License: apache-2.0
Created: Feb 28, 2024
Updated: Mar 4, 2024