Files
explore-tis-untrunc-45-8B/training_logs/20260612_011815_metrics_explore-tis-untrunc_736685.csv
ModelHub XC e73842f34f 初始化项目,由ModelHub XC社区提供模型
Model: laion/explore-tis-untrunc-45-8B
Source: Original Platform
2026-08-08 15:29:19 +08:00

22 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_ContextLengthExceededErrortiming/cleanup_old_checkpointstiming/save_checkpointsbatch_errors/avg_InvalidChatHistorybatch_errors/total_InvalidChatHistorytiming/save_hf_modelbatch_errors/avg_AgentTimeoutErrorbatch_errors/total_AgentTimeoutErrorbatch_errors/avg_DaytonaErrorbatch_errors/total_DaytonaErrorbatch_errors/avg_RuntimeErrorbatch_errors/total_RuntimeError
20.006451251.671900.73448326.60747952.83968737.13933107317569.13172960120.0121.00.9420.00.00.0580.52340.02260.1032-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2594-0.00.01.00.00.013927533.013889494016.00.00.90040.02890.63160.523415.396951.1198613.202828.5857.9676244.76480.07186.820966.8578373.9145441.05372634.574224.5972374.12192162.10210.00.0043635044837130.126984126984126988.00.2063492063492063413
30.006451210.812500.81259363.38878114.939510882.06493057217640.16093410653.0130.00.93680.00.00.06320.54880.00790.127-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.295-0.00.01.00.00.09504304.016764817408.00.00.95640.03080.64060.548816.109651.8488607.438829.2857.9676250.52870.07376.978171.4945397.779469.56911469.52524.1532397.9993968.78210.00.00445947239521690.135593220338983058.01.20338983050847457165.234872.65710.050847457627118653.0
40.006451221.453111.08321.52737922.92458749.17813171517853.37353083973.0159.00.92070.00.00.07930.51760.00070.1103-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2594-0.00.01.00.00.074219600.0123335942144.00.00.83020.0340.64060.517616.643852.4284603.757629.6857.9676254.210.06577.179462.2087361.2177423.7093753.036624.8524361.433297.29230.00.004565520391331280.0153846153846153851.01.93846153846153851260.0153846153846153851.06.95260.0153846153846153851.0
50.006451232.390611.09231.33598922.06299370.64023172819175.67693504548.0165.00.89010.00.00.10990.3105-0.00250.11660.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.24880.00.01.00.00.073788528.0105385009152.00.01.14940.03630.43750.310516.865952.7457600.606930.0857.9676257.36070.07917.083473.4181441.4855515.2197744.015227.2538441.7205194.45440.00.00466350445016540.8888888888888888560.00638.71070.0158730158730158721.00.0317460317460317442.0
60.006451242.468800.96888505.25986813.66819940.36463036617832.77423156643.0152.00.92970.00.00.07030.459-0.00670.09730.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26910.00.01.00.00.019641682.024018849792.00.00.87630.03260.54690.45917.357153.2146597.043930.4857.9676260.92370.06376.788669.0088377.9705447.2693862.872223.4106378.1939385.39960.00.00476350444116550.126984126984126988.00.87301587301587355
70.006451252.437500.95319243.11727666.017210054.9973171218219.35573450700.0151.00.93260.00.00.06740.3398-0.00390.11280.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28020.00.01.00.00.0419752608.0761125273600.00.00.86710.03360.42190.339817.658353.5573595.040330.6857.9676262.92730.06687.278167.8085388.5163456.6241283.925324.9818388.7481795.03620.00.00486350444119600.0476190476190476163.00.9841269841269841620.00737.6056
80.006451252.511.08452.7526705.928810356.43273175917817.34233108231.0167.00.90460.00.00.09540.5215-0.00360.12850.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25760.00.01.00.00.0226767904.0285722640384.00.00.86220.03510.6250.521518.202454.2301592.493330.9857.9676265.47420.06877.149660.623382.8471443.7874713.265624.8084383.0952237.51530.00.00496350440430990.0158730158730158721.01.5555555555555556980.0158730158730158721.0
90.006451263.281200.98449434.73447815.650910232.47523176818936.95443553948.0161.00.90240.00.00.09760.33010.00740.0994-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2504-0.00.01.00.00.00013139078.754407439360.00.00.79340.03330.46880.330118.256854.3204591.046331.1857.9676266.92130.06987.372766.1993416.0908482.5415965.341624.8713416.272450.55110.00.00506350443422690.0158730158730158721.01.0952380952380953690.00547.32930.0158730158730158721.05.943
100.006451262.609400.98448129.33797144.88298786.71013171017815.55123012683.0138.00.92020.00.00.07980.40040.00090.12770.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26370.00.01.00.00.03889889.06269216256.00.00010.86870.0340.51560.400418.340954.3808589.955331.2857.9676268.01230.06967.216960.7573377.4714438.5432933.742123.5581377.7157464.41890.00.00516148842516550.131147540983606568.00.9180327868852459560.065573770491803284.0
110.006451252.468800.90629172.27347711.19610101.20133181618348.98593505463.0159.00.91950.00.00.08050.3887-0.00330.09770.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2870.00.01.00.00.028902766.053475737600.00.01.01270.03210.51560.388718.27454.2945637.025925.8857.9676220.94170.11867.293866.422402.489469.2571331.681326.1865402.716828.93880.00.005262496389281060.0161290322580645161.01.72580645161290321070.00768.08830.032258064516129032.0
120.006451252.812511.09384.46487890.170610127.24273176319096.82873578508.0209.00.88320.00.00.11680.332-0.00520.06710.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27560.00.01.00.00.010878717.010278622208.00.00.78360.04590.43750.33218.417454.496631.481626.4857.9676226.4860.0697.472464.0907415.2288479.59641001.508124.0183415.4363490.41540.00.00536048040322700.116666666666666677.01.05630.0166666666666666661.00.0166666666666666661.00.083333333333333335.0
130.006451252.281200.98449164.6278863.77319384.16893172818284.39553350089.0167.00.92830.00.00.07170.42190.00750.1355-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2758-0.00.01.00.00.021340412.018085134336.00.00.87180.03340.59380.421918.492354.6739627.316426.9857.9676230.65120.07047.332567.4242392.1106459.8335963.834324.3601392.3385472.30270.00.005463504391261131.69841269841269841070.00817.45070.079365079365079365.00.0317460317460317442.00.0158730158730158721.0
140.006451252.265600.90628036.56457922.09778095.49113168718266.64823006588.0164.00.89920.00.00.10080.3398-0.00350.07870.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.25180.00.01.00.00.01587253376.02730784194560.00.00010.78880.03670.42190.339818.413954.601622.804927.4857.9676235.16270.06987.124862.4713378.0579440.8531139.997124.6871378.3104667.31480.00.00556350443320660.079365079365079365.01.0317460317460319650.0158730158730158721.06.05530.0158730158730158721.0
150.006451252.265600.95319895.03719252.890610280.3253162118808.99043717098.0174.00.9110.00.00.0890.375-0.00730.12750.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28870.00.01.00.00.011329929.020180553728.00.00.85070.03910.48440.37518.847755.0626618.664227.9857.9676239.30340.1026.633865.6342424.3242490.28711156.242322.7541424.5504636.56220.00.00566451244723620.0468753.00.90625580.01278.34560.0468753.00.0156251.0
160.006451252.343800.92199604.82428021.422811069.17293181218528.60893545529.0174.00.92050.00.00.07950.4805-0.0010.11470.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27450.00.01.00.00.035328232.059539628032.00.00.86930.03220.6250.480518.751554.9365616.210828.2857.9676241.75680.0696.75271.9456413.9178486.11511122.61824.0058414.1605.73240.00.005762496350341390.112903225806451617.02.1935483870967741360.048387096774193553.0
170.006451252.718800.96888677.33598820.38568616.37053174219193.13663246117.0144.00.89810.00.00.10190.29880.00710.1513-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2442-0.00.01.00.00.017240350.017494378496.00.00.70380.03680.42190.298818.737954.9869614.940628.3857.9676243.0270.09736.562172.3759432.7694505.46021168.545823.5694432.986632.94930.00.00586249642122700.080645161290322585.01.0806451612903225670.00838.3610.0161290322580645161.00.032258064516129032.0
180.006451252.234400.93758540.77347093.288410118.23672970718302.72363116439.0145.00.93430.00.00.06570.52150.00120.089-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2538-0.00.01.00.00.076175128.0124504965120.00.00.85020.02740.59380.521518.690755.0038613.221928.5857.9676244.74570.08726.273765.8402416.3242482.48391034.466825.6212416.5558520.08290.00.00596350443120720.0158730158730158721.01.0952380952380953690.0476190476190476163.0
190.006451252.234400.98448082.18756442.40819347.48443173517874.94782969553.0131.00.9210.00.00.0790.43550.00030.09750.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2480.00.01.00.00.08421109.013449890816.00.00.87530.0310.57810.435518.700755.0133612.973128.6857.9676244.99440.06826.468659.5775400.412460.2515975.295426.2934400.6044482.27720.00.00605846438722750.051724137931034483.01.396551724137931810.00787.52166.0238
200.006451252.421900.93759141.13677065.850210549.60983171918606.77323395069.0149.00.92450.00.00.07550.4043-0.00220.11250.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26210.00.01.00.00.07228389.511749099520.00.00016.55590.03270.50.404318.786955.0738610.539728.8857.9676247.42790.06997.420964.3675400.7285465.396869.261222.9817400.9583373.45790.00.00615745638817681.1754385964912282670.035087719298245612.00.035087719298245612.0
210.006451252.312500.98447608.40236700.40668645.5693081617314.57352810785.0169.00.91450.00.00.08550.5332-0.00610.15560.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.24640.00.01.00.00.03912688.253949634048.00.02.8760.03610.67190.533218.727754.9966608.214529.1857.9676249.75310.09376.231962.252352.4498415.0057820.036822.8296352.6595375.96430.00.00626451244320570.187512.00.84375540.00647.51010.031252.0
220.006451252.37500.96888669.76566482.303910118.60393176218029.05113150434.0166.00.90440.00.00.09560.39840.01590.1117-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2687-0.00.01.00.00.028917454.049698226176.00.00.8670.03680.54690.398418.741555.0623632.793526.2857.9676225.17410.06997.355765.63393.0647458.9805981.1722.7443393.28492.08440.00.00636451244624630.0468753.00.96875620.0156251.0
230.006451262.7500.92199883.64267977.643411618.95523037818877.26773630889.0165.00.93590.00.00.06410.47660.00230.061-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2701-0.00.01.00.00.01237730.52198781184.00.00.86150.03150.53120.476618.739455.0358627.672526.8857.9676230.29510.0956.70870.8475426.7622497.94541092.734224.3698427.0024563.70550.00.00646451242028810.17187511.01.234375790.00777.22950.0156251.00.0156251.0
240.006451252.593800.92199292.04698669.24149612.66273103218318.75723458322.0143.00.91930.00.00.08070.33980.00290.1417-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2746-0.00.01.00.00.0162297.9688115119288.00.00010.84790.03080.48440.339819.066455.4644623.275627.4857.9676234.6920.07016.473663.2047411.1933474.67161081.336524.5543411.395575.63160.00.00655544036816710.018181818181818181.01.309090909090909720.018181818181818181.05.7742
250.006451252.484400.98449157.92388532.29679589.4623078018351.19433325428.0138.00.94090.00.00.05910.4082-0.00560.12380.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26410.00.01.00.00.012722544.011328970752.00.00.84990.03040.54690.408219.061155.3964620.007427.7857.9676237.96010.06827.165566.6561416.9144483.8758862.029724.8096417.1511346.17390.00.00666451240824850.29687519.01.3125840.00777.78690.0156251.0
260.006451262.562500.95318150.03917920.46238312.27333063118111.51642955727.0149.00.930.00.00.070.41410.00550.1052-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.238-0.00.01.00.00.012132366.011427261440.00.00.78790.02810.54690.414119.067355.4025617.115128.1857.9676240.85250.06817.396357.1642385.1081442.5928983.335923.0846385.3597510.25780.00.00676249642922650.032258064516129032.01.0620.064516129032258064.00.0161290322580645161.0
270.006451262.843800.968810356.03129164.982511319.81273157618723.87973807276.0181.00.91050.00.00.08950.4473-0.01050.13540.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28360.00.01.00.00.000144630904.052655632384.00.00021.59710.03750.56250.447319.09855.4295613.720928.5857.9676244.24670.09877.839667.1769433.7166501.21681192.01923.9173433.9407659.04060.00.00686249643417590.064516129032258064.00.9354838709677419580.0087.48890.032258064516129032.0
280.006451252.578111.08828.11727257.44110099.08833172518025.1423238807.0138.00.90470.00.00.09530.44730.00520.0701-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2661-0.00.01.00.00.0916306.3125789478656.00.00.86710.03390.53120.447319.537355.8289610.542128.8857.9676247.42550.06896.557763.3416386.3373449.9523779.290625.1417386.5414297.63350.00.00696048040922660.083333333333333335.01.1166666666666667670.0166666666666666661.00.0166666666666666661.0
290.006451252.562500.95319668.40828380.126210535.6833091818560.77813553099.0167.00.91470.00.00.08530.4023-0.00620.11550.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27690.00.01.00.00.02477487.253018043648.00.00010.85180.03350.51560.402319.606356.0208608.038829.1857.9676249.92880.06877.440568.7933404.897474.00581038.72925.3487405.1434531.9290.00.00706148841522710.032786885245901642.01.1475409836065573700.00798.25326.14460.016393442622950821.0
300.006451252.500.98448521.21098267.65898703.29193025117753.30293039963.0158.00.92420.00.00.07580.418-0.01490.1090.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.250.00.01.00.00.0291457120.0492940951552.00.00.84990.03220.53120.41819.525456.0049605.729529.4857.9676252.23810.06946.290160.6051359.5784420.4904874.618924.7809359.8155423.05290.00.00716451243025740.1258.01.0625680.031252.00.06254.0
310.006451262.640600.98449112.76567463.304310232.23613180218456.48683327904.0154.00.92460.00.00.07540.4043-0.01930.13670.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2530.00.01.00.00.030404792.051539357696.00.00.83320.02970.56250.404319.60556.1477634.081226.1857.9676223.88640.06997.413964.6974401.3632466.3665961.785722.5745401.5988465.4260.00.00726350442025841.253968253968254790.0087.7090.0317460317460317442.00.0158730158730158721.00.0476190476190476163.0
320.006451252.687500.90629751.27348350.300510530.5383179318555.5493642510.0153.00.90190.00.00.09810.3574-0.00730.08260.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.27490.00.01.00.00.010356052.013433537536.00.00.81970.04090.45310.357419.550956.1564631.316826.4857.9676226.65080.07127.64868.3139412.5451481.12851245.256727.4295412.743729.0450.00.00736249643817560.032258064516129032.00.8064516129032258500.032258064516129032.00.048387096774193553.00.0161290322580645161.0
330.006451252.281211.09011.40047074.146110459.38233178917997.61513227417.0158.00.9170.00.00.0830.4277-0.0120.13720.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26950.00.01.00.00.02171949.251647513984.00.00.87690.03210.60940.427719.767956.3635626.655927.0857.9676231.31170.06827.467659.7366384.5267444.5766940.112927.1738384.7713460.890.00.00746148839228760.3278688524590163720.01.1967213114754098730.00757.45550.049180327868852463.00.016393442622950821.0
340.006451252.906221.09145.0418341.32759548.07623176418610.11013316114.0140.00.91930.00.00.08070.3340.00560.1085-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2512-0.00.01.00.00.042199172.075018534912.00.00.81950.03350.45310.33419.681356.2767622.70927.4857.9676235.25860.06897.451766.2425419.816486.3568944.553527.627420.0449423.07660.00.00756249644015540.0161290322580645161.00.967741935483871600.0161290322580645161.05.81490.0161290322580645161.00.0161290322580645161.0
350.006451253.359431.08876.77737298.76889594.0543172317759.11533255590.0147.00.90780.00.00.09220.3125-0.00730.12640.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26660.00.01.00.00.02424953.252092791552.00.00.86350.03660.45310.312520.077156.6378619.573127.8857.9676238.39450.06946.565669.4328393.1418462.8608832.331923.0836393.3582339.7420.00.00766148840025790.147540983606557379.01.2950819672131149790.00677.7420.065573770491803284.0
360.006451254.093841.09669.88488858.910310025.25563155918679.56283660297.0186.00.90560.00.00.09440.3047-0.00870.14460.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28020.00.01.00.00.000110261139.013639459840.00.00.88460.03630.46880.304720.043956.5986630.715426.5857.9676227.25220.07066.764864.3533411.196475.828944.738923.0201411.4037439.04410.00.007763504352411360.2539682539682539516.02.1587301587301586136
370.006451255.051.09097.1278726.38149208.16243042218981.10893398043.0153.00.90840.00.00.09160.2305-0.00270.08750.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2550.00.01.00.00.000110683493.015361475584.00.00.91070.03860.35940.230520.052256.6308627.496826.9857.9676230.47080.06696.295366.0623416.452482.80121300.212421.3488416.6715789.67750.00.0078103824707331160.0097087378640776691.01.1456310679611651180.00797.835
380.006451200.000.05450.3734868.79957107.63912738611774704.0721832444.096.00.95420.00.00.04580.74020.00060.1544-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2195-0.00.01.00.00.01139236.5684067712.00.00.99460.02050.82810.740219.313455.9136623.840927.3857.9676234.12660.05735.319249.5479253.8246303.61241856.958325.4987254.00681522.43420.00.017965520509570.076923076923076935.00.10769230769230777
390.006451210.812500.81258502.5437905.43869703.77653047416814.3043044613.0142.00.94670.00.00.05330.668-0.00090.07760.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.28150.00.01.00.00.0805581120.01403346747392.00.00011.05560.02940.73440.66819.348355.9653618.809127.9857.9676239.15840.09516.388361.4612351.1651412.94981633.240721.6948351.39291192.20290.00.01807862456421580.025641025641025642.00.7564102564102564590.01698.52856.3987