ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #4691 from codemayq/feature-suppot-eval-dataset

Browse Source 
add eval dataset support

Former-commit-id: 51eb379b44fad0336fc96c329ec98dc4528b9c2c
This commit is contained in:
hoshi-hiyouga
2024-07-15 01:00:34 +08:00
committed by GitHub
parent 20b1bd8c54 502555b65d
commit 68365045b4
17 changed files with 235 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/train/ppo/workflow.py
View File

@@ -43,7 +43,7 @@ def run_ppo(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
@@ -63,7 +63,7 @@ def run_ppo(
model=model,
reward_model=reward_model,
ref_model=ref_model,
dataset=dataset,
dataset=dataset_module["train_dataset"],
data_collator=data_collator,
**tokenizer_module,
)