p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add: add test file

This commit is contained in:
wql 2024-09-05 07:07:49 +00:00
parent c6a4d43c06
commit 62a486dfc0
2 changed files with 31 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
results/lora_sft_Qwen-7B_4_gpu_50_step_20240905070656/log.txt Normal file
View File

31
results/lora_sft_Qwen-7B_4_gpu_50_step_20240905070656/lora_sft_Qwen-7B_4_gpu_50_step_20240905070656.yaml Normal file
View File

@ -0,0 +1,31 @@
bf16: true
cutoff_len: 1024
dataset: belle_1m
ddp_timeout: 180000000
do_train: true
eval_steps: 500
eval_strategy: steps
finetuning_type: lora
gradient_accumulation_steps: 8
include_num_input_tokens_seen: true
include_tokens_per_second: true
learning_rate: 0.0001
logging_steps: 3
lora_target: all
lr_scheduler_type: cosine
max_samples: 10000
max_steps: '50'
model_name_or_path: ../../models/Qwen-7B
num_train_epochs: 10.0
output_dir: ./results/lora_sft_Qwen-7B_4_gpu_50_step_20240905070656
overwrite_cache: true
overwrite_output_dir: true
per_device_eval_batch_size: 2
per_device_train_batch_size: 2
plot_loss: true
preprocessing_num_workers: 16
save_steps: 500
stage: sft
template: qwen
val_size: 0.1
warmup_ratio: 0.1