metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: peft-prefix-jul
results: []
peft-prefix-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: 0.0834
- Loc: {'precision': 0.7203389830508474, 'recall': 0.7870370370370371, 'f1': 0.752212389380531, 'number': 216}
- Misc: {'precision': 0.6923076923076923, 'recall': 0.45, 'f1': 0.5454545454545455, 'number': 40}
- Org: {'precision': 0.8309178743961353, 'recall': 0.86, 'f1': 0.8452088452088452, 'number': 200}
- Per: {'precision': 0.819672131147541, 'recall': 0.7653061224489796, 'f1': 0.7915567282321899, 'number': 196}
- Overall Precision: 0.7822
- Overall Recall: 0.7822
- Overall F1: 0.7822
- Overall Accuracy: 0.9827
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: 0.0002
- 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
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3