Neko-Institute-of-Science/guanaco-unchained-33b-qlora

Let's see how this goes.

Training in 8 bit and at full context. Is 8bit even a qlora?

python qlora.py \
    --model_name_or_path /UI/text-generation-webui/models/llama-30b \
    --output_dir ./output/guanaco-33b \
    --logging_steps 1 \
    --save_strategy steps \
    --data_seed 42 \
    --save_steps 69 \
    --save_total_limit 999 \
    --per_device_eval_batch_size 1 \
    --dataloader_num_workers 3 \
    --group_by_length \
    --logging_strategy steps \
    --remove_unused_columns False \
    --do_train \
    --do_eval false \
    --do_mmlu_eval false \
    --lora_r 64 \
    --lora_alpha 16 \
    --lora_modules all \
    --bf16 \
    --bits 8 \
    --warmup_ratio 0.03 \
    --lr_scheduler_type constant \
    --gradient_checkpointing \
    --gradient_accumulation_steps 32 \
    --dataset oasst1 \
    --source_max_len 2048 \
    --target_max_len 2048 \
    --per_device_train_batch_size 1 \
    --num_train_epochs 3 \
    --learning_rate 0.0001 \
    --adam_beta2 0.999 \
    --max_grad_norm 0.3 \
    --lora_dropout 0.05 \
    --weight_decay 0.0 \
    --seed 0