Llama-3.2-1B-Summarization-QLoRa

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the scitldr dataset. It achieves the following results on the evaluation set:

• Loss: 2.5948

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.5121	0.2008	200	2.5718
2.485	0.4016	400	2.5652
2.4865	0.6024	600	2.5660
2.4767	0.8032	800	2.5562
2.4744	1.0040	1000	2.5508
2.137	1.2048	1200	2.5899
2.1268	1.4056	1400	2.5914
2.108	1.6064	1600	2.5874
2.0804	1.8072	1800	2.5948

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1