423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

update examples

Browse Source 
Former-commit-id: 0a690ada6f
This commit is contained in:
hiyouga
2024-08-09 20:13:46 +08:00
parent 5eacd17090
commit f8c11bd540
3 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/extras/adam_mini/llama3_full_sft.yaml → examples/extras/adam_mini/qwen2_full_sft.yaml
View File

@@ -1,5 +1,5 @@
### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
model_name_or_path: Qwen/Qwen2-1.5B-Instruct
### method
stage: sft
@@ -9,14 +9,14 @@ use_adam_mini: true
### dataset
dataset: identity,alpaca_en_demo
template: llama3
template: qwen
cutoff_len: 1024
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
### output
output_dir: saves/llama3-8b/full/sft
output_dir: saves/qwen2-1_5b/full/sft
logging_steps: 10
save_steps: 500
plot_loss: true