ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update example docs

Browse Source 
Former-commit-id: 102cd42768d9eb2cf1219309a25b41e26149067e
This commit is contained in:
hiyouga
2024-05-06 22:51:02 +08:00
parent 5c9da798b5
commit 50c71dd29f
33 changed files with 962 additions and 508 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
examples/lora_multi_gpu/single_node.sh
View File

@@ -1,35 +1,5 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
--config_file ../accelerate/single_config.yaml \
../../src/train.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../data \
--template default \
--finetuning_type lora \
--lora_target q_proj,v_proj \
--output_dir ../../saves/LLaMA2-7B/lora/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 2 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--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 \
--ddp_timeout 180000000 \
--plot_loss \
--fp16
--config_file examples/accelerate/single_config.yaml \
src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml