pkbiswas/Llama-2-7b-Summarization-QLoRa

Llama Summarization

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the scitldr dataset. It achieves the following results on the evaluation set:

• Loss: 2.1108

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: 1
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.0965	0.25	500	2.1496
2.0523	0.5	1000	2.1275
2.0824	0.75	1500	2.1108

Framework versions

• PEFT 0.9.0
• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2