423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix mod stuff

Browse Source 
Former-commit-id: cf3988226e6398c67bb2955578e436fc505aa5c5
This commit is contained in:
hiyouga
2024-04-21 18:11:10 +08:00
parent 5c3922713a
commit 366c0eb1c5
16 changed files with 63 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/extras/galore/sft.sh
View File

@@ -11,6 +11,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--use_galore \
--galore_layerwise \
--galore_target mlp,self_attn \
--galore_scale 2.0 \
--galore_rank 128 \
--output_dir ../../../saves/LLaMA2-7B/galore/sft \
--overwrite_cache \
@@ -28,8 +29,8 @@ CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--num_train_epochs 30.0 \
--max_samples 300 \
--val_size 0.1 \
--plot_loss \
--pure_bf16