ner-education-hcmut

trickstar0/ner-education-hcmut

ner-education-hcmut is a machine learning model from trickstar0. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

261

Public

Parameters

133M

4.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin532 MB · 50%

At a glance

Model type: electra
Access: Public
Created: Aug 20, 2024
Updated: Sep 2, 2024
SHA: a48c9298

Base models

NlpHUST/ner-vietnamese-electra-base

Model card

From the Hugging Face model README

ner-education-hcmut

This model is a fine-tuned version of NlpHUST/ner-vietnamese-electra-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0985
Location: {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6}
Miscellaneous: {'precision': 0.6069651741293532, 'recall': 0.7176470588235294, 'f1': 0.6576819407008085, 'number': 170}
Organization: {'precision': 0.4166666666666667, 'recall': 0.5769230769230769, 'f1': 0.48387096774193544, 'number': 26}
Person: {'precision': 0.75, 'recall': 0.6, 'f1': 0.6666666666666665, 'number': 10}
Overall Precision: 0.5863
Overall Recall: 0.6887
Overall F1: 0.6334
Overall Accuracy: 0.9702

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: 5e-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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Location	Miscellaneous	Organization	Person	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	269	0.1088	{'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6}	{'precision': 0.46311475409836067, 'recall': 0.6647058823529411, 'f1': 0.5458937198067633, 'number': 170}	{'precision': 0.3333333333333333, 'recall': 0.46153846153846156, 'f1': 0.3870967741935484, 'number': 26}	{'precision': 0.6666666666666666, 'recall': 0.6, 'f1': 0.631578947368421, 'number': 10}	0.4573	0.6321	0.5307	0.9631
0.1453	2.0	538	0.0948	{'precision': 1.0, 'recall': 0.5, 'f1': 0.6666666666666666, 'number': 6}	{'precision': 0.5525114155251142, 'recall': 0.711764705882353, 'f1': 0.622107969151671, 'number': 170}	{'precision': 0.42424242424242425, 'recall': 0.5384615384615384, 'f1': 0.47457627118644075, 'number': 26}	{'precision': 0.75, 'recall': 0.6, 'f1': 0.6666666666666665, 'number': 10}	0.5475	0.6792	0.6063	0.9654
0.1453	3.0	807	0.0985	{'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6}	{'precision': 0.6069651741293532, 'recall': 0.7176470588235294, 'f1': 0.6576819407008085, 'number': 170}	{'precision': 0.4166666666666667, 'recall': 0.5769230769230769, 'f1': 0.48387096774193544, 'number': 26}	{'precision': 0.75, 'recall': 0.6, 'f1': 0.6666666666666665, 'number': 10}	0.5863	0.6887	0.6334	0.9702

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Type: electra
Created: Aug 20, 2024
Updated: Sep 2, 2024