diff options
| author | Zitian Gao <zitian.gao@outlook.com> | 2025-05-29 19:21:15 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-29 19:21:15 +0800 |
| commit | dae929ac3f187b48fd3c9b29cf1e0442708a30c9 (patch) | |
| tree | 0a01d4c94d87e26ec1a1fefef2e9a40d26819734 | |
| parent | 1fa309de8e63c6ac41d89505e451a9aff18ec49f (diff) | |
update params
| -rw-r--r-- | README.md | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -19,7 +19,7 @@ accelerate launch train.py \ --model_path /path/to/Qwen2.5-Math-7B \ --train_data dataset/1shot_rlvr/pi1_r1280.parquet \ --effective_batch 64 \ - --micro_batch_size auto \ + --micro_batch_size 2 \ --temperature 0.5 \ --learning_rate 2e-5 \ --max_steps 50 \ @@ -39,7 +39,7 @@ accelerate launch train.py \ --model_path /path/to/Qwen2.5-Math-7B \ --train_data dataset/numina/numina_00.parquet \ --effective_batch 64 \ - --micro_batch_size auto \ + --micro_batch_size 2 \ --temperature 0.5 \ --learning_rate 2e-5 \ --max_steps 50 \ |
