p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update workflow.py

This commit is contained in:
Yuchen Han 2023-11-17 00:16:27 -08:00 committed by GitHub
parent b24635d22b
commit eeb5249d0b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/train/ppo/workflow.py
View File

@ -45,7 +45,7 @@ def run_ppo(
mini_batch_size=training_args.per_device_train_batch_size,
batch_size=training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps,
gradient_accumulation_steps=training_args.gradient_accumulation_steps,
ppo_epochs=1,
ppo_epochs=finetuning_args.ppo_epochs,
max_grad_norm=training_args.max_grad_norm,
seed=training_args.seed,
optimize_device_cache=True,