Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step120 2B • Updated Dec 4, 2025
Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step100 2B • Updated Dec 4, 2025
Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step80 2B • Updated Dec 4, 2025
Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step60 2B • Updated Dec 4, 2025
Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step40 2B • Updated Dec 4, 2025
Chenlu123/grpo_baseline_qwen2.5-math-1.5b_merged_openr1_guru_n8_prompt_bsz_512_mini_bsz_32_step20 2B • Updated Dec 4, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step700 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step680 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step660 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step640 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step620 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step600 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step580 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step560 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step540 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step520 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step500 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step480 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step460 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step440 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step420 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step400 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step380 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step360 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step340 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step320 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step300 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step280 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step260 2B • Updated Dec 2, 2025
Chenlu123/all-perturb_sequence_inistd1e-3_clip_0.5_3.0_c5.0_alpha0_beta0_lr1e-4_qwen2-1_5b_step240 2B • Updated Dec 2, 2025