metadata
license: mit
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: camembert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: fr
split: validation
args: fr
metrics:
- name: Precision
type: precision
value: 0.8826469710534169
- name: Recall
type: recall
value: 0.8992854971115841
- name: F1
type: f1
value: 0.8908885542168675
- name: Accuracy
type: accuracy
value: 0.9472222222222222
camembert-finetuned-ner
This model is a fine-tuned version of camembert-base on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.2199
- Precision: 0.8826
- Recall: 0.8993
- F1: 0.8909
- Accuracy: 0.9472
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 |
|---|---|---|---|---|---|---|---|
| 0.2955 | 1.0 | 2500 | 0.2667 | 0.8603 | 0.8784 | 0.8693 | 0.9369 |
| 0.2089 | 2.0 | 5000 | 0.2269 | 0.8680 | 0.8953 | 0.8814 | 0.9443 |
| 0.1617 | 3.0 | 7500 | 0.2199 | 0.8826 | 0.8993 | 0.8909 | 0.9472 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3