mindreader/llama-recipe-7b-1epoch-8batch

!python llama-recipes/llama_finetuning.py
--use_peft
--num_epochs 1
--peft_method lora
--run_validation false
--quantization
--dataset alpaca_dataset
--model_name meta-llama/Llama-2-7b-chat-hf
--save_model
--save_optimizer
--batch_size_training 8
--output_dir ./save

Training procedure

The following bitsandbytes quantization config was used during training:

• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.5.0.dev0