llama-3.2-3B-for-ner

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0206
• Precision: 0.6597
• Recall: 0.4956
• F1: 0.5660
• Accuracy Seqeval: 0.9941

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy Seqeval
0.0277	0.2963	500	0.0220	0.6177	0.4257	0.5041	0.9936
0.0263	0.5925	1000	0.0208	0.6515	0.5102	0.5723	0.9940
0.0213	0.8888	1500	0.0206	0.6597	0.4956	0.5660	0.9941

Framework versions

• Transformers 4.50.0
• Pytorch 2.3.0+cu118
• Datasets 2.21.0
• Tokenizers 0.21.4