llama_peft_relation_classification

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the I2B2(medical) dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.0255
• Precision: 0.0007
• Recall: 0.0255
• F1: 0.0013

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: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0	1.0	4000	nan	0.0255	0.0007	0.0255	0.0013
0.0	2.0	8000	nan	0.0255	0.0007	0.0255	0.0013
0.0	3.0	12000	nan	0.0255	0.0007	0.0255	0.0013
0.0	4.0	16000	nan	0.0255	0.0007	0.0255	0.0013
0.0	5.0	20000	nan	0.0255	0.0007	0.0255	0.0013

Framework versions

• PEFT 0.13.0
• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 3.0.0
• Tokenizers 0.19.1