Prompt Format: Updated to match SFT evaluation format with detailed instructions
Token Length: Increased to 350 tokens for complete reasoning
Temperature: Reduced to 0.1 for more deterministic generation
Extraction: Fixed to work with vLLM outputs

Performance

During training at step 350, the model achieved:

Average rewards ranging from 0.05 to 0.50 across batches
Successful generation of proper <think> and <answer> tags
Correct solutions to various countdown math problems

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thomasjhuang/qwen2-rloo-countdown-step350")
model = AutoModelForCausalLM.from_pretrained("thomasjhuang/qwen2-rloo-countdown-step350")

prompt = '''Using the numbers [8, 16, 80], create an equation that equals 72. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Show your work in <think> </think> tags. And return the final answer in <answer> </answer> tags, for example <answer> (1 + 2) / 3 </answer>.'''

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=300, temperature=0.1)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Progress

This checkpoint represents an intermediate state in RLOO training where:

The model learned to follow the correct prompt format
Success rates improved from 0% to 10-50% on various problems
The model generates structured reasoning in <think> tags
Solutions are properly formatted in <answer> tags

For the latest checkpoint, see: thomasjhuang/qwen2-rloo-countdown-final