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/dpo/workflow.py
View File

@@ -41,7 +41,7 @@ def run_dpo(
):
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)
data_collator = PairwiseDataCollatorWithPadding(
@@ -71,7 +71,7 @@ def run_dpo(
data_collator=data_collator,
callbacks=callbacks,
**tokenizer_module,
**split_dataset(dataset, data_args, training_args),
**dataset_module,
)
# Training

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

@@ -41,7 +41,7 @@ def run_kto(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="kto", **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage="kto", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
data_collator = KTODataCollatorWithPadding(
@@ -68,7 +68,7 @@ def run_kto(
data_collator=data_collator,
callbacks=callbacks,
**tokenizer_module,
**split_dataset(dataset, data_args, training_args),
**dataset_module,
)
# Training

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,
)

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

@@ -42,7 +42,7 @@ def run_pt(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="pt", **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage="pt", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
@@ -54,7 +54,7 @@ def run_pt(
data_collator=data_collator,
callbacks=callbacks,
**tokenizer_module,
**split_dataset(dataset, data_args, training_args),
**dataset_module,
)
# Training

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)

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)