423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-03 04:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update sft.sh

Browse Source 
Former-commit-id: 57dcd91e17833a0eeb8d99af92ac73c132a77648
This commit is contained in:
hoshi-hiyouga 2024-04-16 17:25:40 +08:00 committed by GitHub
parent 4133811434
commit 507ab397f5
1 changed files with 34 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
examples/extras/badam/sft.sh
View File

@ -1,35 +1,35 @@
# BAdam layer-wise #!/bin/bash
export CUDA_VISIBLE_DEVICES=0
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
python ../../../src/train_bash.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 full \
--output_dir ../../../saves/LLaMA2-7B/badam \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 32 \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 5 \
--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 \
--val_size 0.1 \
--plot_loss \
--use_badam \
--switch_mode descending \
--badam_verbose 2 \
--switch_block_every 50
CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.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 full \
--use_badam \
--badam_switch_mode descending \
--badam_switch_block_every 50 \
--badam_verbose 2 \
--output_dir ../../../saves/LLaMA2-7B/badam/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 8 \
--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 \
--plot_loss \
--pure_bf16