llama-3.1-base-kg-extraction

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1757

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.05
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1416	0.5891	200	0.1828
0.1225	1.1767	400	0.1698
0.1326	1.7658	600	0.1573
0.0792	2.3535	800	0.1576
0.0658	2.9426	1000	0.1479
0.0240	3.5302	1200	0.1613
0.0235	4.1178	1400	0.1746
0.0115	4.7069	1600	0.1756
0.0276	5.0	1700	0.1757

Framework versions

• PEFT 0.18.1
• Transformers 5.5.0
• Pytorch 2.6.0+cu124
• Datasets 4.8.4
• Tokenizers 0.22.2