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

fix reward model loading

Browse Source 
Former-commit-id: 9709ca501180a1afce32e9043aedb359762b437d
This commit is contained in:
hiyouga
2023-11-07 17:20:51 +08:00
parent 857696ed9c
commit f23e5b602a
6 changed files with 34 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/llmtuner/tuner/dpo/workflow.py
View File

@@ -59,13 +59,15 @@ def run_dpo(
if trainer.is_world_process_zero() and model_args.plot_loss:
plot_loss(training_args.output_dir, keys=["loss", "eval_loss"])
if training_args.push_to_hub:
trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
else:
trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
# Evaluation
if training_args.do_eval:
metrics = trainer.evaluate(metric_key_prefix="eval")
trainer.log_metrics("eval", metrics)
trainer.save_metrics("eval", metrics)
# Create model card
if training_args.do_train:
if training_args.push_to_hub:
trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
else:
trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))