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

33
examples/lora_multi_gpu/ds_zero3.sh
View File

@@ -1,34 +1,5 @@
#!/bin/bash
# ZeRO-3 enables weight sharding on multiple GPUs
deepspeed --num_gpus 4 ../../src/train.py \
--deepspeed ../deepspeed/ds_z3_config.json \
--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 \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--ddp_timeout 180000000 \
--plot_loss \
--fp16
deepspeed --include "localhost:0,1,2,3" \
src/train.py examples/lora_multi_gpu/llama3_lora_sft_ds.yaml

41
examples/lora_multi_gpu/llama3_lora_sft.yaml Normal file
View File

@@ -0,0 +1,41 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: sft
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# ddp
ddp_timeout: 180000000
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 2
learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

42
examples/lora_multi_gpu/llama3_lora_sft_ds.yaml Normal file
View File

@@ -0,0 +1,42 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: sft
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# ddp
ddp_timeout: 180000000
deepspeed: examples/deepspeed/ds_z3_config.json
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 2
learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

34
examples/lora_multi_gpu/multi_node.sh
View File

@@ -2,35 +2,5 @@
# also launch it on slave machine using slave_config.yaml
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
--config_file ../accelerate/master_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/master_config.yaml \
src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml

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