camembert-ner-finetuned-jul

fgiauna/camembert-ner-finetuned-jul

camembert-ner-finetuned-jul is a token classification model from fgiauna. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

13% of all-time downloads

All-time downloads

627

Public

Parameters

110M

41.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin440 MB · 50%

Parameter types

How the weights are stored.

F32110M · 100%

Try a prompt

Model card

From the Hugging Face model README

camembert-ner-finetuned-jul

This model is a fine-tuned version of Jean-Baptiste/camembert-ner on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1177
Loc: {'precision': 0.7309417040358744, 'recall': 0.7546296296296297, 'f1': 0.7425968109339408, 'number': 216}
Misc: {'precision': 0.5862068965517241, 'recall': 0.425, 'f1': 0.4927536231884058, 'number': 40}
Org: {'precision': 0.8333333333333334, 'recall': 0.825, 'f1': 0.8291457286432161, 'number': 200}
Per: {'precision': 0.7823834196891192, 'recall': 0.7704081632653061, 'f1': 0.776349614395887, 'number': 196}
Overall Precision: 0.7714
Overall Recall: 0.7607
Overall F1: 0.7660
Overall Accuracy: 0.9812

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Loc	Misc	Org	Per	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	408	0.0602	{'precision': 0.6894977168949772, 'recall': 0.7330097087378641, 'f1': 0.7105882352941175, 'number': 206}	{'precision': 0.8461538461538461, 'recall': 0.2972972972972973, 'f1': 0.44000000000000006, 'number': 37}	{'precision': 0.7472527472527473, 'recall': 0.7472527472527473, 'f1': 0.7472527472527473, 'number': 182}	{'precision': 0.8195876288659794, 'recall': 0.7571428571428571, 'f1': 0.787128712871287, 'number': 210}	0.7516	0.7197	0.7353	0.9830
0.0903	2.0	816	0.0568	{'precision': 0.776255707762557, 'recall': 0.8252427184466019, 'f1': 0.7999999999999999, 'number': 206}	{'precision': 0.5217391304347826, 'recall': 0.32432432432432434, 'f1': 0.4, 'number': 37}	{'precision': 0.7731958762886598, 'recall': 0.8241758241758241, 'f1': 0.7978723404255318, 'number': 182}	{'precision': 0.822429906542056, 'recall': 0.8380952380952381, 'f1': 0.830188679245283, 'number': 210}	0.7815	0.8	0.7907	0.9845
0.0357	3.0	1224	0.0631	{'precision': 0.7339055793991416, 'recall': 0.8300970873786407, 'f1': 0.7790432801822323, 'number': 206}	{'precision': 0.6363636363636364, 'recall': 0.3783783783783784, 'f1': 0.4745762711864407, 'number': 37}	{'precision': 0.7969543147208121, 'recall': 0.8626373626373627, 'f1': 0.8284960422163589, 'number': 182}	{'precision': 0.8317757009345794, 'recall': 0.8476190476190476, 'f1': 0.839622641509434, 'number': 210}	0.7808	0.8189	0.7994	0.9851
0.0201	4.0	1632	0.0761	{'precision': 0.772093023255814, 'recall': 0.8058252427184466, 'f1': 0.7885985748218527, 'number': 206}	{'precision': 0.6, 'recall': 0.32432432432432434, 'f1': 0.4210526315789474, 'number': 37}	{'precision': 0.8263157894736842, 'recall': 0.8626373626373627, 'f1': 0.8440860215053764, 'number': 182}	{'precision': 0.8293838862559242, 'recall': 0.8333333333333334, 'f1': 0.8313539192399049, 'number': 210}	0.8019	0.8031	0.8025	0.9846
0.0113	5.0	2040	0.0745	{'precision': 0.7477876106194691, 'recall': 0.8203883495145631, 'f1': 0.7824074074074074, 'number': 206}	{'precision': 0.4666666666666667, 'recall': 0.3783783783783784, 'f1': 0.417910447761194, 'number': 37}	{'precision': 0.8229166666666666, 'recall': 0.8681318681318682, 'f1': 0.8449197860962567, 'number': 182}	{'precision': 0.8388625592417062, 'recall': 0.8428571428571429, 'f1': 0.840855106888361, 'number': 210}	0.7860	0.8157	0.8006	0.9849
0.0113	6.0	2448	0.0815	{'precision': 0.7654867256637168, 'recall': 0.8398058252427184, 'f1': 0.8009259259259259, 'number': 206}	{'precision': 0.43333333333333335, 'recall': 0.35135135135135137, 'f1': 0.3880597014925374, 'number': 37}	{'precision': 0.8253968253968254, 'recall': 0.8571428571428571, 'f1': 0.8409703504043127, 'number': 182}	{'precision': 0.8673469387755102, 'recall': 0.8095238095238095, 'f1': 0.8374384236453202, 'number': 210}	0.7988	0.8063	0.8025	0.9844
0.0085	7.0	2856	0.0850	{'precision': 0.7579908675799086, 'recall': 0.8058252427184466, 'f1': 0.7811764705882352, 'number': 206}	{'precision': 0.5416666666666666, 'recall': 0.35135135135135137, 'f1': 0.4262295081967213, 'number': 37}	{'precision': 0.828125, 'recall': 0.8736263736263736, 'f1': 0.8502673796791443, 'number': 182}	{'precision': 0.8805970149253731, 'recall': 0.8428571428571429, 'f1': 0.8613138686131387, 'number': 210}	0.8097	0.8110	0.8104	0.9853
0.0045	8.0	3264	0.0846	{'precision': 0.7321428571428571, 'recall': 0.7961165048543689, 'f1': 0.7627906976744185, 'number': 206}	{'precision': 0.4642857142857143, 'recall': 0.35135135135135137, 'f1': 0.39999999999999997, 'number': 37}	{'precision': 0.8172043010752689, 'recall': 0.8351648351648352, 'f1': 0.8260869565217392, 'number': 182}	{'precision': 0.8756218905472637, 'recall': 0.8380952380952381, 'f1': 0.856447688564477, 'number': 210}	0.7903	0.7953	0.7928	0.9847
0.0044	9.0	3672	0.0845	{'precision': 0.7614678899082569, 'recall': 0.8058252427184466, 'f1': 0.7830188679245284, 'number': 206}	{'precision': 0.48148148148148145, 'recall': 0.35135135135135137, 'f1': 0.40625, 'number': 37}	{'precision': 0.8297872340425532, 'recall': 0.8571428571428571, 'f1': 0.8432432432432433, 'number': 182}	{'precision': 0.8811881188118812, 'recall': 0.8476190476190476, 'f1': 0.8640776699029127, 'number': 210}	0.8079	0.8079	0.8079	0.9854
0.0031	10.0	4080	0.0855	{'precision': 0.7568807339449541, 'recall': 0.8009708737864077, 'f1': 0.7783018867924528, 'number': 206}	{'precision': 0.4482758620689655, 'recall': 0.35135135135135137, 'f1': 0.393939393939394, 'number': 37}	{'precision': 0.8297872340425532, 'recall': 0.8571428571428571, 'f1': 0.8432432432432433, 'number': 182}	{'precision': 0.8855721393034826, 'recall': 0.8476190476190476, 'f1': 0.8661800486618005, 'number': 210}	0.8050	0.8063	0.8057	0.9852

Framework versions

Transformers 4.29.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: camembert
License: mit
Created: Apr 28, 2023
Updated: Apr 3, 2025