HanningZhang/scalebio_deepseek_distill_llama3_math_20k_uw2e-5_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_deepseek_distill_llama3_math_20k_uw1e-5_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_deepseek_distill_llama3_math_20k_uw5e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 4
HanningZhang/scalebio_deepseek_distill_llama3_math_20k_uw2e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_deepseek_distill_llama3_math_20k_uw1e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 4
HanningZhang/scalebio_qwen_math_20k_uw5e-5_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 4
HanningZhang/scalebio_qwen_math_20k_uw2e-5_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_qwen_math_20k_uw1e-5_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_qwen_math_20k_uw5e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 4
HanningZhang/scalebio_qwen_math_20k_uw2e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_qwen_math_20k_uw1e-6_alpha100_lambda1e-2 Viewer • Updated Feb 8, 2025 • 21.4k • 5
HanningZhang/scalebio_qwen_math_20k_uw1e-4_alpha100_lambda1e-2 Viewer • Updated Feb 6, 2025 • 21.4k • 4
HanningZhang/scalebio_qwen_math_20k_uw2e-4_alpha100_lambda1e-2 Viewer • Updated Feb 6, 2025 • 21.4k • 5
HanningZhang/scalebio_qwen_math_20k_uw5e-4_alpha100_lambda1e-2 Viewer • Updated Feb 6, 2025 • 21.4k • 4
HanningZhang/llama3_openmath_1m_ep1_gsm8k_gold_tmp07_external_rewards_prompt Viewer • Updated Jan 24, 2025 • 5.28k • 5
HanningZhang/llama3_openmath_1m_ep1_gsm8k_gold_tmp07_external_rewards Viewer • Updated Jan 24, 2025 • 5.28k • 4
HanningZhang/llama3_openmath_1m_ep1_gsm8k_gold_tmp10_external_rewards_prompt Viewer • Updated Jan 24, 2025 • 5.28k • 4
HanningZhang/llama3_openmath_1m_ep1_gsm8k_gold_tmp10_external_rewards Viewer • Updated Jan 24, 2025 • 5.28k • 5