初始化项目，由ModelHub XC社区提供模型

Model: michaelbzhu/Qwen2.5-Math-1.5B-GSM8K-GRPO
Source: Original Platform

README.md

@@ -0,0 +1,49 @@
+---
+library_name: transformers
+license: mit
+datasets:
+- openai/gsm8k
+base_model:
+- Qwen/Qwen2.5-Math-1.5B
+---
+
+used GRPO on top of Qwen/Qwen2.5-Math-1.5B model on the gsm8k training set 
+
+- used REINFORCE loss with baseline
+- used [per-sample length normalization for loss aggregation](https://rlhfbook.com/c/11-policy-gradients#loss-aggregation)
+
+[wandb training run metrics](https://api.wandb.ai/links/teammapo-mapo-labs/l6awailg)
+
+hyperparameters:
+```
+lr = 3e-5
+n_grpo_steps = 100
+advantage_eps = 1e-6
+rollout_batch_size = 256
+group_size = 8
+gradient_accumulation_steps = 128
+epochs_per_rollout_batch = 1
+train_batch_size = 256 # on policy since same as rollout_batch_size
+use_std_normalization = True
+
+optim = torch.optim.AdamW(
+    hf_model.parameters(), lr=lr, weight_decay=0.0, betas=(0.9, 0.95)
+)
+scheduler = LinearLR(optim, start_factor=1.0, end_factor=0.1, total_iters=n_grpo_steps)
+
+```
+
+prompt template:
+```
+A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.
+User: {question}
+Assistant: <think>
+```
+
+reward format checks for proper use of `<think></think>` and `<answer></answer>` tags
+
+performance on GSM8K test set
+```
+correct format: 1172/1319
+correct reward: 966/1319
+```