JingweiNi/uhead_claim_Qwen3-8B_fixed_prm24k_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 4, 2025 • 2
JingweiNi/ue_manager_fixed_nr_after_prm_layer1_dim512_head16_e5_lr2e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_nr_after_prm_layer1_dim512_head16_e5_lr2e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm_after_nr_layer1_dim512_head16_e5_lr2e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm_after_nr_layer1_dim512_head16_e5_lr2e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch5_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch5_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_nr_after_prm_layer1_dim512_head16_e5_lr2e-4_pos3 Updated Sep 4, 2025 • 1
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 4, 2025
JingweiNi/ue_manager_self_fixed_prm_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 4, 2025
JingweiNi/uhead_claim_Qwen3-8B_self_fixed_prm_layer1_dim512_head16_e5_lr5e-4_pos3 Updated Sep 4, 2025 • 1
JingweiNi/uhead_claim_Qwen3-8B_self_fixed_prm_layer1_dim512_head16_e10_lr5e-4_pos3_epoch5 Updated Sep 4, 2025
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_after_nr_layer1_dim512_head16_e5_lr2e-4_pos3 Updated Sep 4, 2025
JingweiNi/ue_manager_fixed_prm16k_layer1_dim512_head16_e5_lr5e-4_pos3_on_st_qa_cr Updated Sep 3, 2025
JingweiNi/ue_manager_fixed_prm16k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 3, 2025
JingweiNi/ue_manager_fixed_prm8k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 3, 2025
JingweiNi/ue_manager_fixed_prm4k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 3, 2025
JingweiNi/ue_manager_fixed_prm2k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 3, 2025
JingweiNi/ue_manager_fixed_prm1k_layer1_dim512_head16_e5_lr5e-4_pos3_on_sci_qa_cr Updated Sep 3, 2025