metadata

base_model: camembert/camembert-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: camembert-base-finetuned-ner
    results: []
datasets:
  - Jean-Baptiste/wikiner_fr
language:
  - fr
widget:
  - text: >-
      Je m'appelle Amel Douc. Je suis né à Paris et réside au 11 impasse de la
      défense 75018 paris.

camembert-base-finetuned-ner

This model is a fine-tuned version of camembert/camembert-base on the Wikiner Dataset (enriched with new entities: date, postal adress) dataset. It achieves the following results on the evaluation set:

Loss: 0.0280
Precision: 0.9642
Recall: 0.9675
F1: 0.9658
Accuracy: 0.9921

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0316	1.0	15205	0.0300	0.9555	0.9609	0.9582	0.9906
0.0214	2.0	30410	0.0276	0.9624	0.9668	0.9646	0.9918
0.0156	3.0	45615	0.0280	0.9642	0.9675	0.9658	0.9921

Framework versions

Transformers 4.33.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3