423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 02:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

upgrade peft, fix #1088 #1411

Browse Source 
Former-commit-id: aa7d104f8e050d12cb8f585bc8a52c850995500f
This commit is contained in:
hiyouga
2023-11-07 16:13:36 +08:00
parent 37a0d62a82
commit 2eb65d21ac
15 changed files with 133 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1,5 +1,4 @@
# Inspired by:
# https://github.com/CarperAI/trlx/blob/main/examples/summarize_rlhf/reward_model/train_reward_model_gptj.py
# Inspired by: https://github.com/CarperAI/trlx/blob/main/examples/summarize_rlhf/reward_model/train_reward_model_gptj.py
from typing import TYPE_CHECKING, Optional, List
from transformers import Seq2SeqTrainingArguments
@@ -7,7 +6,7 @@ from transformers import Seq2SeqTrainingArguments
from llmtuner.dsets import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.callbacks import SavePeftModelCallback
from llmtuner.extras.ploting import plot_loss
from llmtuner.tuner.core import load_model_and_tokenizer
from llmtuner.tuner.core import generate_model_card, load_model_and_tokenizer
from llmtuner.tuner.rm.metric import compute_accuracy
from llmtuner.tuner.rm.collator import PairwiseDataCollatorWithPadding
from llmtuner.tuner.rm.trainer import PairwiseTrainer
@@ -47,13 +46,18 @@ def run_rm(
# Training
if training_args.do_train:
train_result = trainer.train()
trainer.save_model()
trainer.log_metrics("train", train_result.metrics)
trainer.save_metrics("train", train_result.metrics)
trainer.save_state()
trainer.save_model()
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())
else:
trainer.create_model_card(**generate_model_card())
# Evaluation
if training_args.do_eval:
metrics = trainer.evaluate(metric_key_prefix="eval")