Files
a3-rl-laion_nemotron-gym-kn…/training_logs/20260604_042832_metrics_job_561773.csv
ModelHub XC e38b6cff77 初始化项目,由ModelHub XC社区提供模型
Model: laion/a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa-25-8B
Source: Original Platform
2026-08-10 00:48:55 +08:00

20 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_maskedtiming/cleanup_old_checkpointstiming/save_checkpointstiming/save_hf_modelbatch_errors/avg_InvalidChatHistorybatch_errors/total_InvalidChatHistorybatch_errors/avg_DaytonaErrorbatch_errors/total_DaytonaErrorbatch_errors/avg_ContextLengthExceededErrorbatch_errors/total_ContextLengthExceededErrorbatch_errors/avg_RuntimeErrorbatch_errors/total_RuntimeErrorbatch_errors/avg_AgentTimeoutErrorbatch_errors/total_AgentTimeoutErrorbatch_errors/avg_AgentSetupTimeoutErrorbatch_errors/total_AgentSetupTimeoutError
20.006451200.000.01577.60941603.33211547.28945922727718.02220.5410.0040.1402-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.1972-0.00.01.00.00.02710.70310.5413.938449.7056622.733527.4857.9675235.2340.12471.02814.248364.329378.79121394.753622.111764.41781292.8223019676876800
30.006451210.890600.89061607.82031554.28111672.94816093777738.2570.54880.00720.109-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.219-0.00.01.00.00.02680.70310.54884.146649.8756618.553727.9857.9675239.41380.02251.054310.398561.451472.006486.313119.383561.5847393.868202604804800011.681519.2498
40.006451221.359400.82811711.86521669.91341753.166710399664899.99160.4961-0.00670.2623-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2197-0.00.01.00.00.03410.78120.49615.787750.1002614.907428.3857.9675243.06010.03151.587910.755265.664376.5887658.773223.439765.8015557.1559035342442400
50.006451231.859400.89061689.30661647.16991755.0410982656959.52010.60940.00930.1790.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22080.00.01.00.00.02960.81250.60946.16350.2513612.759628.6857.9675245.20790.03011.650211.862966.936378.9843692.584523.832367.0909588.11610456448448000.006313.1318
60.006451241.906200.89061730.03911721.8241737.877910844792940.00.4883-0.00790.2440.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23060.00.01.00.00.03860.750.48836.411250.5601611.774728.7857.9675246.19290.04161.651811.623667.334679.1532954.404626.331767.4876847.266205514083897197.74340.4509803921568627523.0
70.006451252.968800.95311852.81641920.84131786.88461610711299.44460.49220.01410.27150.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22320.00.01.00.00.03520.84380.49228.012550.7285608.436229.1857.9675249.53140.03852.31211.452376.37788.0205465.143420.034276.5292354.7749065443240811240.006711.61850.4814814814814814526.00.0185185185185185171.0
80.006451263.281200.95311815.25391898.33331748.55631531111252.38140.44530.02550.21340.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21480.00.01.00.00.03670.67190.44538.381750.8661606.930329.3857.9675251.03720.03752.209811.894472.913884.9902603.87623.505173.0578493.168707534244088160.283018867924528315.00.0188679245283018861.0
90.006451272.781200.92191748.18551659.8591822.53241994311317.10250.457-0.01430.25370.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21910.00.01.00.00.03440.78120.4579.600851.0066605.080529.5857.9675252.8870.05652.762411.591173.287685.0919684.132225.515573.444570.7605085644840214450.006711.51140.732142857142857141.00.071428571428571424.00.0178571428571428561.0
100.006451273.390600.92191806.02152022.54981654.23591078011288.51940.41210.00040.26970.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21360.00.01.00.00.04380.70310.41219.382350.8111605.685729.4857.9675252.28180.02931.632111.343176.038787.5628868.381224.047976.19755.1357095342439711270.622641509433962233.0
110.006451263.046900.90621837.51761903.66091783.5709730811119.25730.44920.0040.26720.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22330.00.01.00.00.03280.76560.44929.292250.7571605.460829.4857.9675252.50670.02351.273612.038774.297586.5053756.58325.06574.4428643.73760106249646810280.00610.49546.56990.4516129032258064428.0
120.006451272.593800.95311759.83011750.83811768.21131450911212.51650.48240.00010.19790.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21460.00.01.00.00.0280.68750.48249.49650.9597604.371329.6857.9675253.59620.03612.06711.44171.89483.5355706.988923.556772.058597.8290115644842212260.517857142857142929.0
130.006451272.7500.8751698.32421794.70231628.5556948411139.33520.41990.01970.20570.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21360.00.01.00.00.0320.70310.41999.393750.8776604.112729.6857.9675253.85480.0291.465111.369972.042583.601739.930522.682472.2017632.17950125241639412220.006310.57990.4615384615384615624.0
140.006451263.296900.96881895.96481914.1871879.11283162511813.09460.4805-0.0150.31510.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22270.00.01.00.00.03740.82810.480513.38751.2301598.47230.2857.9675259.49550.06364.198615.291986.3893101.9243710.360321.959686.5684582.27620134838435916250.604166666666666629.00.0208333333333333321.0
150.006451263.515600.95311772.76561821.59811737.6981693311390.2190.4180.0030.23070.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22270.00.01.00.00.03090.73440.41813.133350.9749597.837630.3857.9675260.12990.06742.42712.198876.802789.2352765.782125.740976.9687648.37490145644840521430.006610.00570.767857142857142943.0
160.006451263.421900.95311762.83981898.11791637.7331953711245.20920.48050.00410.20590.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2050.00.01.00.00.03450.750.480512.989950.8943597.968930.3857.9675259.99860.02771.512611.382473.581385.1477674.788923.201273.7373564.92480156148845120376.29340.606557377049180337.0
170.006451263.390600.92191671.48241817.04661583.41382444111400.62970.3770.01260.18610.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2240.00.01.00.00.03010.6250.37713.255651.1605596.655730.5857.9675261.31180.05363.253711.782373.26385.248887.228423.379573.4117775.34550165443239419380.006611.58310.777777777777777842.0
180.006451263.187500.93751711.08011791.93251632.71543188411676.28380.4922-0.02140.2322-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2152-0.00.01.00.00.02970.750.492214.420851.3439593.815630.8857.9675264.15190.07894.148512.744279.822892.7884831.82522.15679.9649712.72880175846443119330.655172413793103438.00.0172413793103448271.00.0172413793103448271.0
190.006451263.171900.89061592.72461777.99511471.009766901959.41370.3965-0.0090.22960.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21710.00.01.00.00.13380.70310.396514.074550.9991594.218930.7857.9675263.74870.02671.146310.833165.37376.3619880.027123.136765.5017779.37790185947241621560.00610.53391.059.0
200.006451263.296900.95311575.37891793.48871409.7354738611036.99140.4316-0.00110.21350.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.20710.00.01.00.00.03230.68750.431614.234451.1267594.01330.8857.9675263.95450.02541.22969.926266.02476.1099683.000223.389266.1578582.27019554404157250.490909090909090927.00.054545454545454543.0
210.006451262.765600.95311684.41211749.74881637.114582501955.71350.4199-0.00090.2070.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2340.00.01.00.00.03530.71880.419914.321251.2136593.444630.8857.9675264.52290.0241.336610.844868.329479.3431637.40122.172668.474534.54730206048045914210.006211.51256.16180.4527.00.0166666666666666661.0
220.006451262.968800.92191692.86721827.85991556.81571430911163.47640.5020.00080.20150.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21920.00.01.00.00.0320.78120.50214.460351.3871592.47230.9857.9675265.49550.04792.043311.097770.433981.7265857.767222.845770.5805751.14980215544040321370.709090909090909139.0
230.006451263.468800.96881757.93551908.97521622.55931069411117.11920.4727-0.02080.1875-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2237-0.00.01.00.00.03010.67190.472714.258651.2142592.224631.0857.9675265.74290.03611.600711.324771.62983.1327667.742822.383771.7716560.62280225644843310150.007211.37760.285714285714285716.0
240.006451262.562500.89061661.83791708.19941587.09181364011076.41730.6172-0.00970.23370.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23340.00.01.00.00.0350.85940.617214.481851.3908591.697131.0857.9675266.27040.03481.971911.421167.89479.4971596.981723.179368.0408492.33220236048045514250.4333333333333333526.0
250.006451263.156200.85941798.24412013.0631611.64963174911719.9270.46480.0140.20640.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22150.00.01.00.00.03080.68750.464814.941151.9023590.200331.2857.9675267.76720.06764.318215.620782.707598.5657896.7122.559682.8769771.26360245947243218400.00710.59650.677966101694915240.0
260.006451263.406211.01826.34181867.27391767.03190511842.65360.5918-0.01060.1989-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2178-0.00.01.00.00.02940.85940.591814.7751.7829589.531431.3857.9675268.43610.06894.143114.84185.4151100.4975597.062421.275685.5872471.14150255947243715356.37180.610169491525423836.00.016949152542372881.0
270.006451272.890600.92191649.35741808.65241516.326260791913.25380.45510.0150.1933-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2204-0.00.01.00.00.03060.70310.455114.427651.4484589.869131.2857.9675268.09840.02361.068510.259864.458574.8803807.640121.609964.5966710.07820265947243320390.007211.04320.677966101694915240.00.016949152542372881.0
280.006451263.468800.93751711.84381920.45251553.41582372211406.47820.4316-0.00070.20470.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21760.00.01.00.00.03330.65620.431614.662551.6764588.200931.4857.9675269.76670.05063.245411.603372.848384.6491696.762422.130772.9948586.73620275443241314190.592592592592592632.0
290.006451263.062500.96881616.45311630.0141599.42731023211004.95660.55660.00210.1942-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2186-0.00.01.00.00.0310.78120.556614.387151.3503588.58431.4857.9675269.38350.03591.53210.981666.427977.5913784.552223.422166.5734682.00150285140838912190.007111.31810.529411764705882427.0
300.006451262.734400.92191530.9571458.62891603.285297021900.73180.5-0.00470.1990.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22590.00.01.00.00.03090.71880.514.463151.486588.443431.4857.9675269.52420.0371.473110.027762.845773.0527707.010124.203562.9876608.27830295443242010120.222222222222222212.0
310.006451263.468800.96881862.13091916.41181820.90721474611251.13280.43160.00390.23440.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23180.00.01.00.00.03150.67190.431614.730151.7281587.616931.5857.9675270.35060.05182.108811.903777.041989.1569610.565125.08977.2009494.20710305040036018400.007110.67446.67080.9246.0
320.006451273.828100.96881736.72661961.43651518.9308731711049.43660.49220.00620.22590.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21210.00.01.00.00.03440.81250.492214.547351.462588.041531.5857.9675269.9260.0291.255710.330569.059879.5613589.500521.937769.2015486.74250315745643212240.526315789473684230.0
330.006451273.12500.95311693.44921785.17451628.631812211275.4240.4141-0.00420.18630.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22720.00.01.00.00.03020.65620.414114.708151.6823586.829931.6857.9675271.13760.04422.525612.354670.141582.6971750.301121.970970.298643.1060325342438316410.007310.64740.792452830188679342.0
340.006451273.281200.95311765.72071953.87741632.75672809611861.43410.4141-0.01740.2210.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22080.00.01.00.00.03450.76560.414115.048152.0246585.412531.8857.9675272.55510.06813.69613.232583.810697.2739777.061825.001583.9728651.08730336148845814300.590163934426229536.0
350.006451263.187500.93751739.44531822.56271651.65461917611209.72080.51370.00320.19490.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22630.00.01.00.00.03130.750.513714.914551.8902585.029931.8857.9675272.93760.05712.65811.702274.92686.8303979.855323.745175.0705866.61790345644843314150.007110.7680.3214285714285714518.0
360.006451263.484400.98441798.58791894.15061700.758966991960.85860.50590.00650.23880.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22570.00.01.00.00.03010.78120.505914.548551.5986585.443231.8857.9675272.52440.02591.166511.452268.268679.8857713.432322.893368.4072609.48170355443239322396.34190.851851851851851946.0
370.006451263.37500.95311738.9181981.74121497.98441275511389.07250.4980.0070.25080.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21280.00.01.00.00.04110.79690.49814.644551.6943584.783831.8857.9675273.18380.03341.874512.805678.263291.2733775.40521.481578.4338660.77350365544039419460.006210.80440.945454545454545452.00.018181818181818181.0
380.006451262.843800.90621613.75781726.12171522.11351054911054.97220.4492-0.00330.23350.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21570.00.01.00.00.03340.750.449214.603351.6338584.899431.8857.9675273.06820.0311.599910.376667.037277.5951757.636522.729667.1871655.710375443239719350.870370370370370347.0
390.006451262.765600.90621607.85551662.26151551.72222342911335.86740.5078-0.00250.22070.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2140.00.01.00.00.03060.78120.507814.862551.9769584.173231.9857.9675273.79430.0523.132812.580471.692884.483692.190522.973171.8502581.59820386048043414460.00738.83390.783333333333333347.00.0166666666666666661.00.0166666666666666661.0
400.006451262.781200.96881692.69341793.32681593.6202943311162.98470.49610.00210.2301-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2096-0.00.01.00.00.03280.76560.496114.613351.7112584.288631.9857.9675273.6790.02681.462810.599870.516381.2979848.580923.772570.6709742.04150395846442814360.620689655172413836.00.0344827586206896552.0
410.006451262.812500.98441657.77731787.3951500.1039944511095.17870.54880.00230.2637-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2165-0.00.01.00.00.03310.84380.548814.838152.006583.681332.0857.9675274.28620.02681.489510.772269.934480.8601893.072423.381970.0608787.33870406048045318270.00769.08585.88280.4527.00.0166666666666666661.0
420.006451263.171911.01727.92971783.60471671.37861471830.49770.5039-0.00350.23150.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22660.00.01.00.00.03250.76560.503914.842151.9625583.66332.0857.9675274.30450.02021.07739.950663.83873.9489885.233224.505463.9777785.69470415947241027621.101694915254237265.0
430.006451263.593821.01924.73242257.26071691.63123192311931.34630.41210.00240.22960.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.21090.00.01.00.00.03120.71880.412115.702952.769581.762332.2857.9675276.20530.06584.225914.098487.2532101.56271271.085223.604587.39811141.67590426249645129450.00878.34420.790322580645161349.0
440.006451253.734431.01564.98631665.10531484.609265801945.02150.4453-0.00630.22470.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.22050.00.01.00.00.03250.750.445315.2252.3207582.799732.1857.9675275.16780.04361.120610.535763.614274.34261012.126719.302263.7629917.34240436148843034580.918032786885245956.00.032786885245901642.0
450.006451254.109441.01744.88281957.12251604.30841642211289.05920.3984-0.01230.2180.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.20850.00.01.00.00.03090.71880.398415.448752.5494582.002732.2857.9675275.96480.06172.365411.119475.08486.39051307.162917.889675.20891200.50670446249642840680.00899.28781.080645161290322567.00.032258064516129032.00.0161290322580645161.0
460.006451255.051.01972.39262121.96521850.40071513611792.94410.44920.01310.25130.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.20140.00.01.00.00.02910.750.449215.407752.434581.874132.2857.9675276.09340.03792.205313.102690.6293103.94023038.231917.598990.79932914.470204557456455116.02470.0175438596491228061.0
470.006451200.000.01419.39651391.42411467.20114339776474.89590.6309-0.00830.11740.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.230.00.01.00.00.0240.73440.630915.081652.1969582.653432.1857.9675275.31410.01710.82348.412353.906662.46781619.03322.032154.03811533.69114658464464000.00928.4566
480.006451210.890600.89061676.03911628.34691772.83435783743686.89470.6699-0.00550.17970.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2360.00.01.00.00.03090.8750.669915.085852.1717582.722132.1857.9675275.24540.03691.02859.738560.451670.35481133.391624.607660.5791037.414746368351700.369565217391304317.0