423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

support layerwise galore

Browse Source
This commit is contained in:
hiyouga
2024-03-10 00:24:11 +08:00
parent 18ffce36b5
commit 8664262cde
14 changed files with 109 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/train/sft/workflow.py
View File

@@ -50,7 +50,7 @@ def run_sft(
training_args.generation_num_beams = data_args.eval_num_beams or training_args.generation_num_beams
# Initialize our Trainer
optimizer = create_custom_optimzer(model, training_args, finetuning_args)
optimizer = create_custom_optimzer(model, dataset, training_args, finetuning_args)
trainer = CustomSeq2SeqTrainer(
model=model,
args=training_args,