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 examples

Browse Source 
Former-commit-id: 4c00bcdcaeb675c9fdb3e977c27c3604d7895ae2
This commit is contained in:
hiyouga 2024-03-09 02:30:37 +08:00
parent c561b268ef
commit eb363b04b9
6 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/extras/llama_pro/expand.sh
View File

@ -1,7 +1,5 @@
#!/bin/bash #!/bin/bash
pip install -e ../../../.
python ../../../scripts/llama_pro.py \ python ../../../scripts/llama_pro.py \
--model_name_or_path meta-llama/Llama-2-7b-hf \ --model_name_or_path meta-llama/Llama-2-7b-hf \
--output_dir ../../../models/llama2-7b-pro \ --output_dir ../../../models/llama2-7b-pro \

1
examples/extras/llama_pro/sft.sh
View File

@ -10,6 +10,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--finetuning_type freeze \ --finetuning_type freeze \
--name_module_trainable all \ --name_module_trainable all \
--num_layer_trainable 8 \ --num_layer_trainable 8 \
--use_llama_pro \
--output_dir ../../../saves/LLaMA2-7B-Pro/lora/sft \ --output_dir ../../../saves/LLaMA2-7B-Pro/lora/sft \
--overwrite_cache \ --overwrite_cache \
--overwrite_output_dir \ --overwrite_output_dir \

1
examples/full_multi_gpu/multi_node.sh
View File

@ -33,5 +33,6 @@ python -m torch.distributed.run \
--num_train_epochs 3.0 \ --num_train_epochs 3.0 \
--max_samples 3000 \ --max_samples 3000 \
--val_size 0.1 \ --val_size 0.1 \
--ddp_timeout 1800000 \
--plot_loss \ --plot_loss \
--fp16 --fp16

1
examples/full_multi_gpu/single_node.sh
View File

@ -27,5 +27,6 @@ deepspeed --num_gpus 4 ../../src/train_bash.py \
--num_train_epochs 3.0 \ --num_train_epochs 3.0 \
--max_samples 3000 \ --max_samples 3000 \
--val_size 0.1 \ --val_size 0.1 \
--ddp_timeout 1800000 \
--plot_loss \ --plot_loss \
--fp16 --fp16

1
examples/lora_multi_gpu/multi_node.sh
View File

@ -30,5 +30,6 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
--num_train_epochs 3.0 \ --num_train_epochs 3.0 \
--max_samples 3000 \ --max_samples 3000 \
--val_size 0.1 \ --val_size 0.1 \
--ddp_timeout 1800000 \
--plot_loss \ --plot_loss \
--fp16 --fp16

1
examples/lora_multi_gpu/single_node.sh
View File

@ -30,5 +30,6 @@ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch \
--num_train_epochs 3.0 \ --num_train_epochs 3.0 \
--max_samples 3000 \ --max_samples 3000 \
--val_size 0.1 \ --val_size 0.1 \
--ddp_timeout 1800000 \
--plot_loss \ --plot_loss \
--fp16 --fp16