wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen2.5-7B-Instruct_bw1p6_fw0p4_ema0p999_ep30 Text Generation • Updated about 2 hours ago
wgcyeo/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen2.5-7B-Instruct_bw1p0_fw1p0_ema0p999_ep30 Text Generation • Updated about 2 hours ago
wgcyeo/ci-feedback_both_ema_plus_interp_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_stw0p3_ep30 Text Generation • Updated about 2 hours ago
wgcyeo/ci-feedback_allowed_ema_Qwen2.5-7B-Instruct_forward_kl_ema0p999_ep30 Text Generation • Updated about 2 hours ago
wgcyeo/ci-feedback_disallowed_none_Qwen2.5-7B-Instruct_from_Qwen2.5-7B-Instruct_jsd_b0p8_ep30 Text Generation • Updated about 18 hours ago • 11
wgcyeo/ci-feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated about 18 hours ago • 11
wgcyeo/ci-feedback_disallowed_ema_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_ep30 Text Generation • Updated about 18 hours ago • 10
wgcyeo/ci-feedback_both_none_Qwen2.5-7B-Instruct_from_Qwen2.5-7B-Instruct_jsd_b0p8_ep30 Text Generation • Updated about 18 hours ago • 12
wgcyeo/ci-feedback_both_interp_Qwen2.5-7B-Instruct_from_Qwen2.5-7B-Instruct_jsd_b0p8_stw0p3_ep30 Text Generation • Updated about 18 hours ago • 12
wgcyeo/ci-feedback_both_ema_plus_interp_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_stw0p3_ep30 Text Generation • Updated about 18 hours ago • 12
wgcyeo/ci-feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated about 18 hours ago • 12
wgcyeo/ci-feedback_both_ema_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_ep30 Text Generation • Updated about 18 hours ago • 11