1 line
11 KiB
JSON
1 line
11 KiB
JSON
|
|
{"rollout_corr/ppl_ratio":1.0011649164371192,"val-aux/sciknoweval/acc/std@16":0.1705123962141389,"timing_s/agent_loop/slowest/tool_calls":0,"val-aux/sciknoweval/score/maj@4/mean":0.55496,"val-aux/sciknoweval/reward/worst@8/std":0.08117633716216308,"val-aux/sciknoweval/reward/best@8/std":0.06916601903650618,"val-aux/sciknoweval/reward/maj@2/mean":0.55058,"val-aux/sciknoweval/acc/maj@8/mean":0.5593400000000001,"val-aux/sciknoweval/score/best@4/mean":0.674,"critic/score/max":1,"_runtime":5519.500528115,"global_seqlen/min":15201,"rollout_corr/rollout_is_seq_fraction_high":0,"val-aux/sciknoweval/incorrect_format/mean@16":0.99875,"timing_s/agent_loop/tool_calls/mean":0,"rollout_corr/kl":0.0011583137813406807,"timing_s/reward":0.05930858105421066,"val-aux/sciknoweval/reward/best@4/mean":0.674,"val-core/sciknoweval/acc/best@16/mean":0.73856,"val-aux/sciknoweval/incorrect_format/worst@4/std":0.008311822904754409,"rollout_corr/rollout_is_seq_max_deviation":0.008629322052001953,"rollout_corr/chi2_token":0.003004896454513073,"timing_s/gen":18.558317134156823,"val-aux/sciknoweval/acc/worst@2/std":0.147132195408043,"val-aux/sciknoweval/reward/maj@16/mean":0.55908,"timing_s/agent_loop/slowest/generate_sequences":11.257305985316634,"val-core/sciknoweval/acc/maj@16/std":0.06533731091763299,"timing_s/agent_loop/generate_sequences/min":1.9916328880935907,"val-aux/sciknoweval/incorrect_format/worst@2/mean":0.9977199999999999,"val-aux/sciknoweval/incorrect_format/std@16":0.004841229182759271,"val-aux/sciknoweval/score/best@4/std":0.09758132520114339,"self_distillation/token_reweight_context_sample_fraction":0.83984375,"val-aux/sciknoweval/reward/maj@16/std":0.06533731091763299,"val-aux/sciknoweval/incorrect_format/worst@16/mean":0.9875,"timing_s/agent_loop/tool_calls/min":0,"val-aux/sciknoweval/acc/maj@2/mean":0.55058,"rollout_corr/rollout_is_seq_std":0.0027923036832362413,"val-aux/num_turns/min":2,"val-aux/sciknoweval/incorrect_format/worst@8/std":0.009763933633531108,"timing_s/agent_loop/generate_sequences/max":11.257305985316634,"self_distillation/token_reweight_w_clip_frac":0.13672411735751666,"val-aux/sciknoweval/incorrect_format/maj@8/std":0,"val-aux/sciknoweval/reward/worst@16/std":0.048294469414788314,"val-aux/sciknoweval/score/mean@16":0.55,"_step":100,"val-aux/sciknoweval/score/worst@16/std":0.048294469414788314,"val-aux/sciknoweval/score/maj@4/std":0.1354735155461244,"val-aux/sciknoweval/incorrect_format/best@2/std":0.0008935323161475471,"actor/pg_loss":0.007820420083589852,"val-aux/sciknoweval/incorrect_format/best@4/std":0,"critic/returns/min":-0.875,"val-core/sciknoweval/acc/maj@16/mean":0.55908,"_wandb":{"runtime":5519},"self_distillation/token_reweight_lambda":0.5,"actor/kl_loss":0,"val-aux/sciknoweval/reward/best@16/std":0.04218677040162369,"training/rollout_probs_diff_mean":0.005966469645500183,"response_length_non_aborted/clip_ratio":0,"training/rollout_actor_probs_pearson_corr":0.9986874461174011,"val-aux/sciknoweval/acc/best@2/mean":0.61904,"global_seqlen/balanced_min":19240,"rollout_corr/rollout_log_ppl":0.3697861341643147,"num_turns/max":2,"val-aux/sciknoweval/incorrect_format/maj@4/mean":0.99972,"timing_s/testing":78.02890569157898,"rollout_corr/rollout_is_min":0.3131374716758728,"prompt_length/min":180,"timing_s/adv":0.669283602386713,"val-aux/sciknoweval/reward/maj@4/mean":0.55496,"val-aux/sciknoweval/reward/worst@8/mean":0.3761,"val-aux/sciknoweval/reward/worst@4/std":0.11484012157584442,"val-aux/sciknoweval/acc/best@2/std":0.1400715293582534,"val-aux/sciknoweval/incorrect_format/maj@16/mean":1,"val-core/sciknoweval/acc/best@16/std":0.04218677040162369,"self_distillation/correct_sample_fraction":0.671875,"val-aux/sciknoweval/acc/maj@8/std":0.09364957204441302,"val-aux/sciknoweval/incorrect_format/best@2/mean":0.9999600000000001,"val-aux/sciknoweval/acc/best@8/mean":0.71124,"val-aux/sciknoweval/score/worst@4/mean":0.4220399999999999,"val-aux/sciknoweval/score/worst@2/mean":0.48004,"val-aux/sciknoweval/reward/worst@16/mean":0.3436,"self_distillation/success_sample_fraction":0.83984375,"val-aux/sciknoweval/incorrect_
|