Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step100 2B • Updated Dec 12, 2025
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step80 2B • Updated Dec 12, 2025
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step60 2B • Updated Dec 12, 2025
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step40 2B • Updated Dec 12, 2025
Chenlu123/all-perturb_sequence_inistd1e-4_clip_0.5_3.0_c5.0_alpha0_beta0_lr5e-4_qwen2-1_5b_step20 2B • Updated Dec 12, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step720 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step700 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step680 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step660 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step640 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step620 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step600 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step580 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step560 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step540 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step520 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step500 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step480 2B • Updated Dec 4, 2025 • 8
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step460 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step440 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step420 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step400 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step380 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step360 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step340 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step320 2B • Updated Dec 4, 2025 • 1
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step300 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step280 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step260 2B • Updated Dec 4, 2025
Chenlu123/grpo_tis_qwen2.5-math-1.5b_merged_openr1_guru_n8_sequence_mask_th3.0_prompt_bsz_512_step240 2B • Updated Dec 4, 2025