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

8
src/llamafactory/train/sft/workflow.py
View File

@@ -43,7 +43,7 @@ def run_sft(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
if training_args.predict_with_generate:
@@ -76,7 +76,7 @@ def run_sft(
compute_metrics=ComputeMetrics(tokenizer) if training_args.predict_with_generate else compute_accuracy,
preprocess_logits_for_metrics=None if training_args.predict_with_generate else eval_logit_processor,
**tokenizer_module,
**split_dataset(dataset, data_args, training_args),
**dataset_module,
)
# Keyword arguments for `model.generate`
@@ -105,12 +105,12 @@ def run_sft(
# Predict
if training_args.do_predict:
predict_results = trainer.predict(dataset, metric_key_prefix="predict", **gen_kwargs)
predict_results = trainer.predict(dataset_module["eval_dataset"], metric_key_prefix="predict", **gen_kwargs)
if training_args.predict_with_generate: # predict_loss will be wrong if predict_with_generate is enabled
predict_results.metrics.pop("predict_loss", None)
trainer.log_metrics("predict", predict_results.metrics)
trainer.save_metrics("predict", predict_results.metrics)
trainer.save_predictions(dataset, predict_results)
trainer.save_predictions(dataset_module["eval_dataset"], predict_results)
# Create model card
create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)