neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_2_0_iter_5_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_2_0_iter_4_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_6_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_2_0_iter_4_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_2_0_iter_2_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_5_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_2_0_iter_1_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_4_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_2_0_iter_0_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_2_0_iter_3_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_3_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_2_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_2_0_iter_2_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_1_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_1_0_iter_1_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_slow_and_steady_1_0_iter_0_verif Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_2_0_iter_1_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_slow_and_steady_1_0_iter_0_provers_g Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_2_0_iter_0_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_test_trl_1_0_iter_0_provers_group_17 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_mixed_1_0_iter_0_verifier_175275 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_5_verifier_1752751 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_4_verifier_1752749 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_3_verifier_1752748 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_2_verifier_1752747 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_1_verifier_1752746 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-1_5b-instruct_cv_qwen2.5-1.5B_verifier_nip_test_2_0_iter_0_verifier_1752744 Updated Jul 17
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_lr_1e-3_1_0_iter_8_provers_group_175 Updated Jul 16
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_lr_1e-3_1_0_iter_7_provers_group_175 Updated Jul 16
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5-32B_prover_nip_lr_1e-3_1_0_iter_6_provers_group_175 Updated Jul 16