Llama3-8B-LoRA/README.md

metadata

license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: ../../model/Llama3-8B
model-index:
  - name: sft
    results: []

sft

This model is a fine-tuned version of ../../model/Llama3-8B on the role_in_novel_50, the RoleLLM and the Haruhi54K datasets. It achieves the following results on the evaluation set:

• Loss: 2.0695

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• total_eval_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 10.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2