distilbert-base-uncased-finetuned-ag-news-v2

miggwp/distilbert-base-uncased-finetuned-ag-news-v2

distilbert-base-uncased-finetuned-ag-news-v2 is a fill-mask model from miggwp. 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

3% of all-time downloads

All-time downloads

Public

Parameters

67M

2.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors268 MB · 100%

At a glance

Task: Fill-Mask
Library: transformers
License: apache-2.0
Model type: distilbert
Access: Public
Created: Jul 4, 2024
Updated: Jul 4, 2024
SHA: 72be6ce8

Try a prompt

Base models

Model card

From the Hugging Face model README

distilbert-base-uncased-finetuned-ag-news-v2

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.1945

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
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.6962	1.0	1384	2.3348
2.3631	2.0	2768	2.2128
2.2947	3.0	4152	2.1748

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Task: Fill-Mask
Library: transformers
Type: distilbert
License: apache-2.0
Created: Jul 4, 2024
Updated: Jul 4, 2024