RoBERTa_conll_learning_rate6e5

ICT2214Team7/RoBERTa_conll_learning_rate6e5

RoBERTa_conll_learning_rate6e5 is a token classification model from ICT2214Team7. Use it when you need labels on individual words, such as names. 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

33% of all-time downloads

All-time downloads

Public

Parameters

81.5M

978 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors326 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: roberta
Access: Public
Created: Jul 3, 2024
Updated: Jul 3, 2024
SHA: 63b6e3fe

Try a prompt

Base models

Datasets

conll2003

Model card

From the Hugging Face model README

RoBERTa_conll_learning_rate6e5

This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:

Loss: 0.0563
Precision: 0.9423
Recall: 0.9544
F1: 0.9483
Accuracy: 0.9879

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: 6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0817	1.0	1756	0.0691	0.9078	0.9345	0.9210	0.9824
0.0366	2.0	3512	0.0639	0.9346	0.9450	0.9397	0.9857
0.0194	3.0	5268	0.0563	0.9423	0.9544	0.9483	0.9879

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Task: Token Classification
Library: transformers
Type: roberta
License: apache-2.0
Created: Jul 3, 2024
Updated: Jul 3, 2024