peft-lora-jul

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

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