tarob0ba/Oolong-Llama-3-8B-lora

Oolong

This model is a fine-tuned version of unsloth/llama-3-8b-Instruct-bnb-4bit on the the identity, alpaca_gpt4_en, nectar_sft, slimorca, and wikiqa datasets.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 1
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1