metadata
base_model: camembert/camembert-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: relatives_psr-cbert_finetuned
results: []
datasets:
- djamina/relatives_psr
language:
- fr
pipeline_tag: token-classification
relatives_psr-cbert_finetuned
This model is a fine-tuned version of camembert/camembert-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0532
- Precision: 0.6127
- Recall: 0.5628
- F1: 0.5835
- Accuracy: 0.9789
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.1420 | 0.9906 | 0.3333 | 0.3286 | 0.9718 |
| No log | 2.0 | 98 | 0.0846 | 0.7921 | 0.6010 | 0.5037 | 0.9733 |
| No log | 3.0 | 147 | 0.0590 | 0.6117 | 0.5888 | 0.5891 | 0.9782 |
| No log | 4.0 | 196 | 0.0555 | 0.6077 | 0.6158 | 0.5861 | 0.9794 |
| No log | 5.0 | 245 | 0.0532 | 0.6127 | 0.5628 | 0.5835 | 0.9789 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1