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

1. add custom eval dataset support

Browse Source 
2. merge load dataset and split dataset function


Former-commit-id: 963d97ba07e7efa3a4544c4d077283d9e112b3ad
This commit is contained in:
codingma
2024-07-05 15:52:10 +08:00
parent 9a1a5f9778
commit 5f2bd04799
15 changed files with 93 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llamafactory/train/rm/workflow.py
View File

@@ -41,7 +41,7 @@ def run_rm(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
@@ -57,7 +57,7 @@ def run_rm(
callbacks=callbacks,
compute_metrics=compute_accuracy,
**tokenizer_module,
**split_dataset(dataset, data_args, training_args),
**dataset_module,
)
# Training
@@ -81,7 +81,7 @@ def run_rm(
# Predict
if training_args.do_predict:
predict_results = trainer.predict(dataset, metric_key_prefix="predict")
predict_results = trainer.predict(dataset_module["eval_dataset"], metric_key_prefix="predict")
trainer.log_metrics("predict", predict_results.metrics)
trainer.save_metrics("predict", predict_results.metrics)
trainer.save_predictions(predict_results)