recipe-ner-model

ChelodoyMolovek/recipe-ner-model

recipe-ner-model is a token classification model from ChelodoyMolovek. Use it when you need labels on individual words, such as names. It is set up for transformers.

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

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

89.3M

357 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors357 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: bert
Access: Public
Created: May 1, 2026
Updated: May 2, 2026
SHA: a0b6be69

Try a prompt

Model card

From the Hugging Face model README

recipe-ner-model

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2282
Precision: 0.9155
Recall: 0.9275
F1: 0.9214
Accuracy: 0.9320

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 840
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5307	1.0	1402	0.2530	0.8961	0.9118	0.9039	0.9223
0.4613	2.0	2804	0.2298	0.9119	0.9234	0.9176	0.9292
0.3560	3.0	4206	0.2282	0.9155	0.9275	0.9214	0.9320

Framework versions

Transformers 5.7.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Task: Token Classification
Library: transformers
Type: bert
Created: May 1, 2026
Updated: May 2, 2026