423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-20 13:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

support layerwise galore

Browse Source 
Former-commit-id: d43a4da0947897d0be3f62fad3107754d4c89f2b
This commit is contained in:
hiyouga
2024-03-10 00:24:11 +08:00
parent 7538d8e726
commit 0aacc41252
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/pt/workflow.py
View File

@@ -30,7 +30,7 @@ def run_pt(
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
# Initialize our Trainer
optimizer = create_custom_optimzer(model, training_args, finetuning_args)
optimizer = create_custom_optimzer(model, dataset, training_args, finetuning_args)
trainer = Trainer(
model=model,
args=training_args,