metadata
base_model: camembert/camembert-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: birdi-finetuned-ner
results: []
language:
- fr
widget:
- text: >-
Je m'appelle Amel Douc. Je suis né le 21-12-1998 à Paris et réside au 11
impasse de la défense 75018 paris.
birdi-finetuned-ner
This model is a fine-tuned version of camembert/camembert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0378
- Precision: 0.9449
- Recall: 0.9521
- F1: 0.9485
- Accuracy: 0.9888
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 |
|---|---|---|---|---|---|---|---|
| 0.0464 | 1.0 | 7698 | 0.0419 | 0.9352 | 0.9435 | 0.9393 | 0.9875 |
| 0.0344 | 2.0 | 15396 | 0.0375 | 0.9439 | 0.9509 | 0.9474 | 0.9888 |
| 0.0256 | 3.0 | 23094 | 0.0378 | 0.9449 | 0.9521 | 0.9485 | 0.9888 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3