legalbert-ner-finetuned

This model is a fine-tuned version of casehold/legalbert on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8558
• Precision: 0.2266
• Recall: 0.2907
• F1-score: 0.2531

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: 1e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1-score
No log	1.0	43	2.0326	0.0	0.0	0.0
No log	2.0	86	1.4580	0.0898	0.0447	0.0523
No log	3.0	129	1.0766	0.2122	0.2013	0.1871
No log	4.0	172	0.9024	0.2275	0.2843	0.2495
No log	5.0	215	0.8558	0.2266	0.2907	0.2531

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0