arxiv:2502.19613
Chenlu Ye
Chenlu123
AI & ML interests
None yet
Organizations
models 697
Chenlu123/grpo_qwen3_4b_guru_n8_delta10_lam1e-11_bz128_mini_bz32_fsdp2_kl0.001
Updated
Chenlu123/shampoo_npg_tr_scale_delta40-lam1e-11_bsz512-32_qwen2_5_math_1_5b
Updated
Chenlu123/grpo_qwen_qwen2_5_math_1_5b_guru_n8_bz512_mini_bz32_fsdp2_kl0.001
Updated
Chenlu123/shampoo_npg_tr_scale_delta20_lam1e-12_warmup_1_graftTrue_qwen2_5_math_1_5b
Updated
Chenlu123/grpo_qwen_qwen2_5_math_1_5b_guru_cliph0.2_n16_bz64_mini_bz64_fsdp2
Updated
Chenlu123/shampoo_npg_tr_scale_delta0.1-lam1e-12_qwen2_5_math_1_5b
Updated
Chenlu123/grpo_warmup_graftTrue_qwen2_5_math_1_5b_guru_n16_bz64_mini_bz64_global_step_80
Updated
Chenlu123/teacher_Qwen3-4B_dapo-math-17k_n8_prompt_bsz_128_mini_bsz_32_step460
2B • Updated
Chenlu123/teacher_Qwen3-4B_dapo-math-17k_n8_prompt_bsz_128_mini_bsz_32_step440
2B • Updated
Chenlu123/teacher_Qwen3-4B_dapo-math-17k_n8_prompt_bsz_128_mini_bsz_32_step420
2B • Updated • 3
datasets 46
Chenlu123/hmmt0225
Viewer • Updated • 30 • 7
Chenlu123/aime25
Viewer • Updated • 30 • 250
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step170
Updated • 8
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step165
Updated • 7
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step160
Updated • 12
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step155
Updated • 17
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step150
Updated • 10
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step145
Updated • 10
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step140
Updated • 7
Chenlu123/ppo_is_cliph2.0_clipl0.5_clipc5.0_step135
Updated • 17