Files
explore-tis-minp-40-8B/training_logs/20260612_111844_metrics_explore-tis-minp_736733.csv
ModelHub XC cab2418769 初始化项目,由ModelHub XC社区提供模型
Model: laion/explore-tis-minp-40-8B
Source: Original Platform
2026-08-09 12:53:53 +08:00

18 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_tokensgenerate/tis/aligned_tokensgenerate/tis/alignment_fail_countgenerate/tis/exact_match_fractiongenerate/tis/lcs_fallback_fractiongenerate/tis/lcs_fallback_messagesgenerate/tis/unaligned_fractionloss/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_normpolicy/rollout_train_prob_diff_meanpolicy/rollout_train_prob_diff_stdpolicy/tis/imp_ratio_capped_fractionpolicy/tis/imp_ratio_meanpolicy/tis/log_ratio_abs_meanreward/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_buffertis/batch_skipped_no_logprobstis/skipped_fractiontrainer/epochtrainer/global_stepbatch_errors/total_batchesbatch_errors/total_instancesbatch_errors/total_successfulbatch_errors/total_failedbatch_errors/total_maskedbatch_errors/avg_VerifierTimeoutErrorbatch_errors/total_VerifierTimeoutErrorbatch_errors/avg_ContextLengthExceededErrorbatch_errors/total_ContextLengthExceededErrorbatch_errors/avg_InvalidChatHistorybatch_errors/total_InvalidChatHistorybatch_errors/avg_AgentTimeoutErrorbatch_errors/total_AgentTimeoutErrortiming/cleanup_old_checkpointstiming/save_checkpointstiming/save_hf_modelbatch_errors/avg_DaytonaErrorbatch_errors/total_DaytonaErrorbatch_errors/avg_EnvironmentStartTimeoutErrorbatch_errors/total_EnvironmentStartTimeoutErrorbatch_errors/avg_AgentSetupTimeoutErrorbatch_errors/total_AgentSetupTimeoutErrorbatch_errors/avg_DaytonaAuthenticationErrorbatch_errors/total_DaytonaAuthenticationError
20.006451251.015600.3757870.25986315.62069388.88423163716785.042896175.0133.00.91520.00.00.08480.49410.00630.0694-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2567-0.00.01.00.00.027557782.021387087872.00.00.9370.02370.57890.494114.234751.1202631.096926.4857.9675226.87070.13467.068158.9995333.6066392.98243508.937927.2008333.84733081.68620.00.00516350441828760.1587301587301587210.01.1111111111111112700.079365079365079365.00.0158730158730158721.0
30.006451210.859400.85948808.22076710.84529718.84593168618370.52283290132.0159.00.90090.00.00.09910.3027-0.00640.09170.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25640.00.01.00.00.0501408064.0826448674816.00.00.81750.02740.42190.302715.138251.7656621.524227.6857.9675236.44330.07327.117357.4233385.1163442.90041919.072829.1921385.40291439.84030.00.00525947237838941.6779661016949152990.050847457627118653.00.033898305084745762.018.534628.4804
40.006451221.765611.08967.19737329.91679684.65733182518954.14853389605.0153.00.89210.00.00.10790.3047-0.00940.14220.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2670.00.01.00.00.0119342128.0163474669568.00.00.78770.03230.46880.304716.671452.1664614.870528.3857.9675243.0970.07297.071560.5892415.1575476.1278770.915827.5132415.4649260.20.00.00536350445715410.095238095238095236.00.6031746031746031380.0476190476190476163.00.0476190476190476163.0
50.006451231.937500.93758510.03919127.69618100.94163172916954.54113177723.0131.00.90990.00.00.09010.39840.00770.1448-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2826-0.00.01.00.00.044137072.067892584448.00.00.89190.02730.51560.398417.493852.8479612.381528.6857.9675245.5860.06957.249554.4807350.8659405.72231262.580427.5799351.1717822.02560.00.00546249642722690.9838709677419355610.080645161290322585.00.048387096774193553.00.01129.6942
60.006451242.015600.98448230.39847046.868989.07693166717452.81863007679.0124.00.92630.00.00.07370.3906-0.02440.140.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25820.00.01.00.00.0001388513.125265224640.00.00.85490.02640.50.390617.975753.397630.445826.5857.9675227.52170.12616.832756.0921363.642420.14941293.980727.1413363.9305839.85120.00.00556350442227800.0317460317460317442.01.1111111111111112700.11111111111111117.00.0317460317460317442.07.17850.0158730158730158721.0
70.006451242.359400.98448966.5028608.93669205.26713170017904.80263298465.0121.00.9370.00.00.0630.4004-0.00090.07590.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26070.00.01.00.00.01056077.1251463281152.00.00.830.02580.50.400418.067853.523626.671827.0857.9675231.29570.09536.765460.3737389.4993450.35021192.387128.6912389.8807706.57540.00.00566048041922540.116666666666666677.00.8166666666666667490.053.00.033333333333333332.00.00938.62940.16.0
80.006451252.281200.92197928.84186918.72458555.37033176717428.25182878353.0126.00.91540.00.00.08460.38280.0150.1297-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2498-0.00.01.00.00.0316321.4062464556032.00.00.85130.02560.51560.382818.125953.5624621.8627.5857.9675236.10750.07086.526457.4952370.6284428.4908997.645526.1954370.9244536.42830.00.00575846439225660.12068965517241387.01.0580.051724137931034483.00.068965517241379314.00.0172413793103448271.0
90.006451242.234400.85948289.85167226.87889163.68333178317971.96863019580.0126.00.92360.00.00.07640.4512-0.00310.11680.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25490.00.01.00.00.08359105.59869331456.00.00.84640.02420.57810.451218.127953.56631.652626.4857.9675226.31490.07066.764662.9581371.9187435.2621202.893129.609372.2313731.25280.00.00586451243223740.093756.01.015625650.1258.00.0156251.00.00989.0087
100.006451242.171900.89067678.62896389.31948619.47643171617483.8552819034.0101.00.91530.00.00.08470.42190.00810.0654-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2446-0.00.01.00.00.015090150.018138132480.00.00.84470.02360.50.421918.09753.5286626.800826.9857.9675231.16670.0677.341658.0421335.9809394.4061097.740728.5027336.2963667.48570.00.00596350445316510.7777777777777778490.0158730158730158721.00.0158730158730158721.0
110.006451251.937500.92197886.16216185.0589875.5893180317492.99072873153.091.00.93790.00.00.06210.53910.00480.0613-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2545-0.00.01.00.00.02512598.02894422784.00.00.89410.01910.64060.539118.073353.5681634.926526.0857.9675223.04110.07166.664656.3787339.1088395.8569887.959730.0973339.406455.33590.00.00605947239922630.169491525423728810.00.9830508474576272580.033898305084745762.00.050847457627118653.00.00969.33735.9004
120.006451252.296900.90628045.94737391.28928479.55193179417732.98982952883.0119.00.9210.00.00.0790.39840.00450.1135-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2499-0.00.01.00.00.011887833.014399760384.00.00.83630.02490.54690.398418.062853.5536630.146126.6857.9675227.82150.09887.728256.8569359.4173416.5881009.795426.9969359.6318558.46740.00.00616451244324630.093756.00.984375630.031252.00.031252.0
130.006451252.265600.93757866.41026193.81189747.21583176317580.88172812573.0108.00.91520.00.00.08480.52930.00440.075-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2366-0.00.01.00.00.03286020.04137315840.00.00.86110.02190.60940.529318.253253.719626.027927.0857.9675231.93960.09926.337157.09375.2038432.67921031.178530.8831375.4894561.27080.00.00626249646712270.032258064516129032.00.43548387096774194270.01029.4744
140.006451252.296900.98448345.5827030.6889452.36333178116818.0453030904.0129.00.92250.00.00.07750.457-0.00870.07750.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28170.00.01.00.00.0241912784.0417147617280.00.00.93160.02980.53120.45718.472553.9944622.456327.4857.9675235.51120.08517.381259.9224346.7063406.9456948.620328.449346.9377505.83920.00.00635846439820640.0344827586206896552.01.0172413793103448590.137931034482758628.0
150.006451252.593800.98448185.92386971.70289043.97332877617335.04492990929.0140.00.92860.00.00.07140.41410.00140.1607-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2569-0.00.01.00.00.033933668.058283196416.00.00.85430.02730.53120.414118.429653.9512618.933827.9857.9675239.03380.07056.479760.8046369.5409430.7071886.371527.1861369.8315421.99380.00.00646552045124630.092307692307692316.00.9384615384615385610.030769230769230772.00.00969.3516
160.006451252.500.95318215.1667136.28168941.47393176717748.71282996243.0106.00.94020.00.00.05980.4023-0.01240.08220.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2680.00.01.00.00.0137453728.0199630422016.00.00.85630.02430.46880.402318.483854.0696615.563728.3857.9675242.40390.06886.607457.5453380.0598437.9317999.964225.3128380.3155530.10770.00.00656048041223590.159.00.9666666666666667580.033333333333333332.06.0611
170.006451252.312500.90629058.19537603.75429840.0123177518155.67463387602.0122.00.91240.00.00.08760.3496-0.00960.14670.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26670.00.01.00.00.050127176.086130425856.00.00.85620.0240.53120.349618.778454.3023612.03828.7857.9675245.92950.07116.776763.358388.6325452.33351109.48223.3265388.9039627.04060.00.00666451246420400.1258.00.59375380.031252.00.00979.1281
180.006451252.62500.95318916.38678937.73458899.51753172517735.07883280818.0138.00.92260.00.00.07740.44140.00810.1255-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2689-0.00.01.00.00.01199515904.02167201857536.00.00.89540.02770.57810.441420.173954.6961629.861926.6857.9675228.10570.07087.676763.0972382.2914445.73291090.941130.9422382.5644606.58420.00.00676451244624590.1093757.00.8125520.093756.00.0156251.0
190.006451252.203100.90628760.49027494.40279760.9653065918047.68013216293.0135.00.93070.00.00.06930.44140.00570.1044-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2693-0.00.01.00.00.045548172.068329947136.00.00.86340.02150.54690.441420.174454.7505624.650927.2857.9675233.31670.06926.668267.7818380.6045448.74951094.972626.5021380.898613.0480.00.00686148842918570.032786885245901642.00.9344262295081968570.032786885245901642.00.00969.1096
200.006451252.218800.98448931.11336863.163110658.11113172318233.88183253256.0105.00.94510.00.00.05490.4551-0.00320.12810.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25790.00.01.00.00.032555162.038332309504.00.00.87360.02110.59380.455120.239254.7967629.890426.6857.9675228.07710.07026.869762.5117383.7066446.5409886.633529.3036383.9583403.91480.00.00695544038324540.054545454545454543.01.0545454545454545580.036363636363636362.0
210.006451252.937500.96889616.36529535.76099661.58232981018058.80653454848.0142.00.93360.00.00.06640.3594-0.0080.06830.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2810.00.01.00.00.06871682.09161223168.00.00.86560.02890.45310.359420.218154.8271624.02827.3857.9675233.93950.06696.42571.5317392.2035464.10261316.854721.8599392.5029824.46260.00.00705140838214240.03921568627450982.00.4117647058823529210.01960784313725491.00.01960784313725491.00.00998.90387.43720.117647058823529416.0
220.006451252.234400.8758491.14267429.42449413.3653177317079.063149661.0136.00.9060.00.00.0940.46480.00090.15110.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28640.00.01.00.00.0417150016.0650419437568.00.00.92740.03020.60940.464820.257954.8594619.257827.8857.9675238.70970.06986.975956.8808361.0704418.28491442.120526.2071361.3338990.6480.00.00715947243613350.016949152542372881.00.6101694915254238360.033898305084745762.00.067796610169491534.00.050847457627118653.0
230.006451252.078100.96888947.07380.710910044.96353180017599.94463241496.0114.00.93990.00.00.06010.4121-0.01230.12010.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27570.00.01.00.00.027795898.041081733120.00.00.90070.02540.51560.412120.265754.9316615.435328.3857.9675242.53220.07047.385960.7795381.2023442.35761035.290125.3711381.5072560.17040.00.00725644833635960.2678571428571428515.01.1607142857142858650.089285714285714295.00.607142857142857134.00.00948.67060.053571428571428573.00.107142857142857146.0
240.006451252.984400.96887466.11336245.35167873.03392998517623.65412755246.078.00.94710.00.00.05290.25-0.00220.0480.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23630.00.01.00.00.093860.609452988604.00.00.74390.01770.34380.2520.399955.0114612.612728.6857.9675245.35480.1166.313455.0451340.6213396.06352000.912527.6949340.90181570.83090.00.00736148842718410.114754098360655747.00.3770491803278688230.098360655737704926.00.2622950819672131316.00.245901639344262315.0
250.006451252.031200.89067738.5416320.20378773.54393096417101.6672764759.093.00.94690.00.00.05310.4219-0.00120.10230.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.24550.00.01.00.00.04534978.55788017152.00.00.86190.02040.53120.421920.278554.9511631.346826.4857.9675226.62070.06857.762753.8795354.1889408.40681155.827632.2103354.4583707.44310.00.00745644840014350.3214285714285714518.00.75420.089285714285714295.00.00939.5730.035714285714285712.0
260.006451252.234411.08235.02737651.37068600.04443174117006.64193020874.0127.00.93350.00.00.06650.3848-0.00530.1350.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27110.00.01.00.00.01985231.753241389312.00.00.85890.02680.56250.384820.305755.1479624.83927.2857.9675233.12850.06996.927458.4233340.2451398.94991615.829622.4649340.45181187.44210.00.00755040037210240.15.00.46230.126.00.084.06.4841
270.006451252.859421.08298.77547126.28934.5093180216776.56763060598.0130.00.91990.00.00.08010.3516-0.01290.11730.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28070.00.01.00.00.01496190.01879559936.00.00.91360.03030.48440.351620.301955.2075621.447927.6857.9675236.51960.06846.781259.4714335.7446395.5757868.168523.4662336.0353442.24790.00.0076635044889140.0317460317460317442.00.20634920634920634130.0158730158730158721.00.00978.5027
280.006451253.2531.09377.21097364.222810595.10033148316802.29583408762.0134.00.93070.00.00.06930.3770.00490.118-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.3047-0.00.01.00.00.07307401.013289908224.00.00.95890.02640.50.37720.277255.1826617.880828.0857.9675240.08670.09897.620365.4424354.8663420.65041422.875323.3439355.1087971.17670.00.00775947238628710.2372881355932203514.01.4067796610169492830.033898305084745762.00.016949152542372881.0
290.006451254.031241.09627.609410207.64869467.04993113517819.34013603987.0136.00.92820.00.00.07180.21680.00520.1105-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2914-0.00.01.00.00.07302476.58430315520.00.00.79120.03240.3750.216820.8455.7192613.813428.5857.9675244.15420.07136.537362.2255371.1345433.73721385.816921.9136371.4399923.50150.00.007810281671333940.088235294117647069.00.8627450980392157880.009803921568627451.00.009803921568627451.00.00918.6378
300.006451200.000.05379.00984644.53917582.42192788712254540.52251822160.073.00.95560.00.00.04440.75-0.00380.11540.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22910.00.01.00.00.02944163.53634247168.00.00.9950.01670.84380.7519.944154.9266611.476128.7857.9675246.49140.0885.600939.0434215.0646254.51652052.863626.1622215.38331766.48070.00.017964512505320.187512.00.031252
310.006451210.87500.8757544.35557007.72618322.33972972415990.30352650674.0114.00.94780.00.00.05220.5918-0.01390.08450.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25940.00.01.00.00.0408883744.0662388080640.00.00.96960.02140.68750.591819.92254.9688608.4229.1857.9675249.54750.06726.733557.0994307.8566365.31981231.155426.793308.1528832.30450.00.01806451248313210.1258.00.328125210.009311.17746.3491