Files
ablation-pymethods2test-seq…/training_logs/20260612_220124_metrics_job_661735.csv
ModelHub XC 0c293fc953 初始化项目,由ModelHub XC社区提供模型
Model: laion/ablation-pymethods2test-seqmean-arm0-30-8B
Source: Original Platform
2026-07-18 18:02:02 +08:00

5.8 KiB

1async/discard_rateasync/discarded_countasync/effective_batch_groupsasync/effective_batch_samplesasync/staleness_maxasync/staleness_meanasync/staleness_minasync/staleness_ratiogenerate/avg_num_tokensgenerate/avg_tokens_non_zero_rewardsgenerate/avg_tokens_zero_rewardsgenerate/max_num_tokensgenerate/min_num_tokensgenerate/std_num_tokensloss/avg_final_rewardsloss/avg_raw_advantagesloss/avg_raw_advantages_abspolicy/final_losspolicy/log_ratio_abs_maxpolicy/log_ratio_abs_meanpolicy/log_ratio_abs_p99policy/log_ratio_abs_pos00policy/log_ratio_abs_pos10policy/log_ratio_abs_pos20policy/log_ratio_abs_pos30policy/log_ratio_abs_pos40policy/log_ratio_abs_pos50policy/log_ratio_abs_pos60policy/log_ratio_abs_pos70policy/log_ratio_abs_pos80policy/log_ratio_abs_pos90policy/n_tokens_dp_gt_10pctpolicy/n_tokens_dp_gt_1pctpolicy/n_tokens_dp_gt_50pctpolicy/policy_entropypolicy/policy_losspolicy/policy_lrpolicy/policy_update_stepspolicy/ppo_clip_ratiopolicy/raw_grad_normreward/avg_pass_at_8reward/avg_raw_rewardsystem/process_rss_gbsystem/process_vms_gbsystem/ram_available_gbsystem/ram_percentsystem/ram_total_gbsystem/ram_used_gbtiming/compute_advantages_and_returnstiming/convert_to_training_inputtiming/fwd_logprobs_values_rewardtiming/policy_traintiming/run_trainingtiming/steptiming/sync_weightstiming/train_critic_and_policytiming/wait_for_generation_buffertrainer/epochtrainer/global_stepbatch_errors/total_batchesbatch_errors/total_instancesbatch_errors/total_successfulbatch_errors/total_failedbatch_errors/total_maskedbatch_errors/avg_InvalidChatHistorybatch_errors/total_InvalidChatHistorybatch_errors/avg_ContextLengthExceededErrorbatch_errors/total_ContextLengthExceededErrorbatch_errors/avg_VerifierTimeoutErrorbatch_errors/total_VerifierTimeoutErrortiming/cleanup_old_checkpointstiming/save_checkpointsbatch_errors/avg_AgentTimeoutErrorbatch_errors/total_AgentTimeoutErrorbatch_errors/avg_DaytonaErrorbatch_errors/total_DaytonaErrortiming/save_hf_modelbatch_errors/avg_AgentSetupTimeoutErrorbatch_errors/total_AgentSetupTimeoutError
20.006451230.328100.21884521.94734333.51934758.51983166313365.27850.55660.00740.094-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0996-0.00.01.00.00.01310.59650.556612.597850.5919579.34532.5857.9676278.62260.15694.513332.1738167.8055200.363675.934521.9439168.02873449.11690715846437529881.4137931034482758820.20689655172413793120.0172413793103448271.0
30.006451210.937500.93755361.25985767.9935205.16223169915207.45330.2773-0.0130.13230.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.11510.00.01.00.00.0170.42190.277312.866250.7994576.802932.8857.9676281.16470.06484.643737.3367229.2593266.87761642.303325.4393229.47551345.33660725644836424801.3392857142857142750.1607142857142857390.071428571428571424.011.42421.28490.160714285714285739.00.053571428571428573.0
40.006451221.640611.04303.74024841.99414036.18713177814623.56140.3320.00230.08250.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.09770.00.01.00.00.00950.40620.33213.20151.0858576.441632.8857.9676281.5260.06494.647532.7604195.3408228.4104875.42123.4598195.5846618.89950736350447112330.47619047619047616300.0793650793650793650.0476190476190476163.0
50.006451231.640600.89065242.77734926.20555552.01543176114678.99520.49410.01380.1243-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.1009-0.00.01.00.00.01450.59380.494113.443151.3293575.880232.9857.9676282.08740.0624.649837.0456231.3918268.72011733.977123.6881231.61221436.91610745947240123560.847457627118644500.1864406779661017110.254237288135593215.00.00710.0130.033898305084745762.00.050847457627118653.0
60.006451241.984411.04678.01374390.894862.06733172014446.39430.3906-0.01620.1412-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.1014-0.0020.01.00.00.01430.56250.390613.591551.5202575.615432.9857.9676282.35220.06364.524134.8828208.4871243.67661567.802322.6625208.72991296.92230756148842225660.7704918032786885470.21311475409836064130.065573770491803284.00.098360655737704926.06.424
70.006451242.421921.04572.68954582.6794568.06573179914302.66020.3164-0.00230.1120.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.1030.00.01.00.00.01290.45310.316413.685851.5748574.566533.0857.9676283.40110.06634.691330.5968200.2044231.09961415.547624.2091200.43621155.52660766148841522640.7868852459016393480.21311475409836064130.147540983606557379.00.00749.87980.049180327868852463.00.114754098360655747.0
80.006451243.031231.04597.78124086.66674944.66893175914559.73750.40430.00130.0431-0.00010.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0996-0.00330.01.00.00.00680.46880.404314.399451.5634573.705533.1857.9676284.26210.06424.503932.7244196.2376229.28471161.945421.4738196.4958906.66290776350441432860.8095238095238095510.4603174603174603290.1587301587301587210.00.095238095238095236.00.0158730158730158721.0
90.006451244.041.05291.91416195.00865027.37122889814117.80950.22660.00720.10520.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.11430.00.01.00.00.01050.3750.226614.296151.5109573.112133.2857.9676284.85550.14854.442833.4904188.476222.32171837.794617.1266188.68251593.86760786753646624640.6567164179104478440.23880597014925373160.089552238805970146.00.058810.93740.0298507462686567162.00.0298507462686567162.0