bert-finetuned-ner-2

FabianJennrich/bert-finetuned-ner-2

bert-finetuned-ner-2 is a token classification model from FabianJennrich. 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

17% of all-time downloads

All-time downloads

Public

Parameters

108M

4.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors431 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Nov 7, 2023
Updated: Nov 7, 2023
SHA: 1fcc74b9

Try a prompt

Base models

Model card

From the Hugging Face model README

bert-finetuned-ner-2

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3606
Precision: 0.5849
Recall: 0.4821
F1: 0.5285
Accuracy: 0.9259
By Entity: {'corporation': {'precision': 0.1724137931034483, 'recall': 0.29411764705882354, 'f1': 0.2173913043478261, 'number': 34}, 'creative-work': {'precision': 0.2962962962962963, 'recall': 0.1523809523809524, 'f1': 0.20125786163522014, 'number': 105}, 'group': {'precision': 0.21621621621621623, 'recall': 0.20512820512820512, 'f1': 0.21052631578947367, 'number': 39}, 'location': {'precision': 0.5492957746478874, 'recall': 0.527027027027027, 'f1': 0.5379310344827587, 'number': 74}, 'person': {'precision': 0.7525510204081632, 'recall': 0.6276595744680851, 'f1': 0.6844547563805105, 'number': 470}, 'product': {'precision': 0.45454545454545453, 'recall': 0.30701754385964913, 'f1': 0.36649214659685864, 'number': 114}}

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: 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	By Entity
No log	1.0	425	0.3129	0.5078	0.3900	0.4411	0.9185	{'corporation': {'precision': 0.0989010989010989, 'recall': 0.2647058823529412, 'f1': 0.14400000000000002, 'number': 34}, 'creative-work': {'precision': 0.09090909090909091, 'recall': 0.02857142857142857, 'f1': 0.043478260869565216, 'number': 105}, 'group': {'precision': 0.0851063829787234, 'recall': 0.10256410256410256, 'f1': 0.09302325581395349, 'number': 39}, 'location': {'precision': 0.49411764705882355, 'recall': 0.5675675675675675, 'f1': 0.5283018867924529, 'number': 74}, 'person': {'precision': 0.7346368715083799, 'recall': 0.5595744680851064, 'f1': 0.6352657004830918, 'number': 470}, 'product': {'precision': 0.17857142857142858, 'recall': 0.043859649122807015, 'f1': 0.0704225352112676, 'number': 114}}
0.2031	2.0	850	0.3736	0.5983	0.4294	0.5	0.9226	{'corporation': {'precision': 0.13636363636363635, 'recall': 0.2647058823529412, 'f1': 0.18, 'number': 34}, 'creative-work': {'precision': 0.2903225806451613, 'recall': 0.08571428571428572, 'f1': 0.13235294117647062, 'number': 105}, 'group': {'precision': 0.2857142857142857, 'recall': 0.10256410256410256, 'f1': 0.1509433962264151, 'number': 39}, 'location': {'precision': 0.5483870967741935, 'recall': 0.4594594594594595, 'f1': 0.5, 'number': 74}, 'person': {'precision': 0.7553191489361702, 'recall': 0.6042553191489362, 'f1': 0.6713947990543735, 'number': 470}, 'product': {'precision': 0.37254901960784315, 'recall': 0.16666666666666666, 'f1': 0.23030303030303031, 'number': 114}}
0.0825	3.0	1275	0.3606	0.5849	0.4821	0.5285	0.9259	{'corporation': {'precision': 0.1724137931034483, 'recall': 0.29411764705882354, 'f1': 0.2173913043478261, 'number': 34}, 'creative-work': {'precision': 0.2962962962962963, 'recall': 0.1523809523809524, 'f1': 0.20125786163522014, 'number': 105}, 'group': {'precision': 0.21621621621621623, 'recall': 0.20512820512820512, 'f1': 0.21052631578947367, 'number': 39}, 'location': {'precision': 0.5492957746478874, 'recall': 0.527027027027027, 'f1': 0.5379310344827587, 'number': 74}, 'person': {'precision': 0.7525510204081632, 'recall': 0.6276595744680851, 'f1': 0.6844547563805105, 'number': 470}, 'product': {'precision': 0.45454545454545453, 'recall': 0.30701754385964913, 'f1': 0.36649214659685864, 'number': 114}}

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Task: Token Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Nov 7, 2023
Updated: Nov 7, 2023