Sangsang/feedback_both_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/feedback_both_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/feedback_allowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_allowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_disallowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/feedback_disallowed_ema_Qwen3-4B_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 12
Sangsang/grpo_Qwen3-4B-Instruct-2507_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/grpo_Qwen3-4B-Instruct-2507_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_asymmetric_fixed_ema_Qwen3-4B-Instruct-2507_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_disallowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 23
Sangsang/feedback_both_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_both_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_allowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_allowed_ema_Qwen3-4B-Instruct-2507_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_asymmetric_fixed_ema_Qwen2.5-7B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_asymmetric_fixed_ema_Qwen2.5-7B-Instruct_bw0p5_fw0p5_ema0p999_ep30 Text Generation • Updated 1 day ago • 13
Sangsang/feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 Text Generation • Updated 1 day ago • 12