zhuokai/dapo_baseline_without_dynamic_sampling_temperature_1.2_Qwen2.5-Math-1.5B_zzk Updated 1 day ago
zhuokai/dapo_baseline_without_dynamic_sampling_temperature_1.0_Qwen2.5-Math-1.5B_zzk Updated 1 day ago
zhuokai/dapo_baseline_without_dynamic_sampling_temperature_0.6_Qwen2.5-Math-1.5B_zzk Updated 1 day ago
zhuokai/as_negexp_explore_1.2_stable_0.1_decay_freq_25_warmup_period_10_negexp_Qwen2.5-Math-1.5B_zzk Updated 2 days ago