LoPE experiment checkpoints (global_step_200)
-
shrango/qwen2.5_math_7b_simple_prompt_openr1_data_baseline_re
8B • Updated • 12 -
shrango/qwen2.5_math_7b_grpo_openr1_data_baseline_wokl
8B • Updated • 13 -
shrango/qwen2.5_math_7b_openr1_data_bs128_naive_fallback_test_MATH_wokl
8B • Updated • 13 -
shrango/qwen2.5_math_7b_openr1_data_bs128_luffy
8B • Updated • 13