chomeed's picture
Full fine-tune of Robometer-4B on mimicgen threading_d0 (best ckpt, step 500)
8e0d74a verified
Raw
History Blame Contribute Delete
3.63 kB
{
"step": 500,
"metrics": {
"eval_rew_align/success_auprc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.16177469536688965,
"eval_rew_align/positive_success_acc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.05,
"eval_rew_align/negative_success_acc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_rew_align/loss_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 3.2358126759529116,
"eval_rew_align/pearson_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.980422842373061,
"eval_p_rank/kendall_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/kendall_rewind_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/avg_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/min_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/max_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/ranking_acc_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_all_pairs_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_failure_vs_successful_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/kendall_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/kendall_rewind_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/avg_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/min_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/max_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/ranking_acc_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_all_pairs_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_failure_vs_successful_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/kendall_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/kendall_rewind_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/avg_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/min_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/max_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
"eval_p_rank/ranking_acc_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_all_pairs_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"eval_p_rank/ranking_acc_failure_vs_successful_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
"time/custom_evaluations": 96.72939321910962
}
}