JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_diverse6k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_repeat7.2k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_unique3.6k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_unique7.2k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_unique10.8k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_repeat10.8k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 6, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch10_on_sci_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch10_on_st_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_on_sci_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_on_st_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_fixed_nr_prm_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_fixed_nr_prm_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 5, 2025
JingweiNi/uhead_claim_Qwen3-8B_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3 Updated Sep 5, 2025
JingweiNi/uhead_claim_Qwen3-8B_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch10 Updated Sep 5, 2025
JingweiNi/ue_manager_fixed_prm28k_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_fixed_prm28k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 5, 2025
JingweiNi/ue_manager_fixed_prm24k_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm24k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm20k_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm20k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm12k_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm12k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm24k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 4, 2025 • 2