peft-lora-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: 0.0817
- Loc: {'precision': 0.5887445887445888, 'recall': 0.6296296296296297, 'f1': 0.6085011185682326, 'number': 216}
- Misc: {'precision': 0.6111111111111112, 'recall': 0.275, 'f1': 0.3793103448275862, 'number': 40}
- Org: {'precision': 0.7004830917874396, 'recall': 0.725, 'f1': 0.7125307125307125, 'number': 200}
- Per: {'precision': 0.7540106951871658, 'recall': 0.7193877551020408, 'f1': 0.7362924281984334, 'number': 196}
- Overall Precision: 0.6734
- Overall Recall: 0.6641
- Overall F1: 0.6687
- Overall Accuracy: 0.9772
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