atropos/example_trainer/configs/math_zero_shared.yaml
2026-03-02 11:18:52 -05:00

13 lines
332 B
YAML

env:
tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
rollout_server_url: "http://localhost:8001"
max_token_length: 8192
start_tok_length: 8192
group_size: 8
batch_size: 64
total_steps: 120
steps_per_eval: 20
use_wandb: true
wandb_name: "math-zero-shared-env"
eval_limit_ratio: 0.1
max_num_workers_per_node: 24