34 lines
961 B
Bash
34 lines
961 B
Bash
|
#!/bin/bash
|
||
|
|
|
||
|
|
CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
|
||
|
|
--config_file ../accelerate/fsdp_config.yaml \
|
||
|
|
../../src/train_bash.py \
|
||
|
|
--stage sft \
|
||
|
|
--do_train \
|
||
|
|
--model_name_or_path meta-llama/Llama-2-70b-hf \
|
||
|
|
--dataset alpaca_gpt4_en,glaive_toolcall \
|
||
|
|
--dataset_dir ../../data \
|
||
|
|
--template default \
|
||
|
|
--finetuning_type lora \
|
||
|
|
--lora_target q_proj,v_proj \
|
||
|
|
--output_dir ../../saves/LLaMA2-70B/lora/sft \
|
||
|
|
--overwrite_cache \
|
||
|
|
--overwrite_output_dir \
|
||
|
|
--cutoff_len 1024 \
|
||
|
|
--per_device_train_batch_size 1 \
|
||
|
|
--per_device_eval_batch_size 1 \
|
||
|
|
--gradient_accumulation_steps 8 \
|
||
|
|
--lr_scheduler_type cosine \
|
||
|
|
--logging_steps 10 \
|
||
|
|
--save_steps 100 \
|
||
|
|
--eval_steps 100 \
|
||
|
|
--evaluation_strategy steps \
|
||
|
|
--load_best_model_at_end \
|
||
|
|
--learning_rate 5e-5 \
|
||
|
|
--num_train_epochs 3.0 \
|
||
|
|
--max_samples 3000 \
|
||
|
|
--val_size 0.1 \
|
||
|
|
--quantization_bit 4 \
|
||
|
|
--plot_loss \
|
||
|
|
--fp16
|