Files
explore-tis-minp-40-8B/training_logs/20260612_111844_metrics_explore-tis-minp_736731.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

10 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_EnvironmentStartTimeoutErrorbatch_errors/total_EnvironmentStartTimeoutErrorbatch_errors/avg_AgentTimeoutErrorbatch_errors/total_AgentTimeoutErrorbatch_errors/avg_DaytonaErrorbatch_errors/total_DaytonaErrorbatch_errors/avg_InvalidChatHistorybatch_errors/total_InvalidChatHistorytiming/save_hf_modelbatch_errors/avg_RuntimeErrorbatch_errors/total_RuntimeError
20.006451200.000.05734.45515399.29956642.77543000114576.71231947393.0105.00.95580.00.00.04420.73050.0130.1468-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2107-0.00.01.00.00.01313283.0553862080.00.00.98210.02020.81250.730513.986950.6847576.233932.8857.9676281.73360.08696.133341.705229.0827271.10393879.645824.2724229.31173578.13590.00.001127101696521460.0472440944881889766.00.370078740157480347
30.006451210.812500.81257354.9986748.48477990.6243076716563.57822649482.0134.00.92720.00.00.07280.51170.00260.0965-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2272-0.00.01.00.00.04057410.255818289152.00.00.89970.02370.67190.511714.465651.1954571.869633.3857.9676286.0980.06536.250152.8628305.7446358.88711691.669931.2186305.95851295.31110.00.0023427221015621.26470588235294114314.210325.93121.205882352941176441.00.0294117647058823531.00.0294117647058823531.0
40.006451221.734411.04784.75986311.04091.01423172416096.46951726469.083.00.95210.00.00.04790.3125-0.01360.09290.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.16670.00.01.00.00.019620498.020760209408.00.00.61830.01520.48440.312514.784251.5825570.625633.5857.9676287.3420.06095.776540.3466260.5189301.1266344.767932.7089260.71885.15310.00.0036350445815450.0158730158730158721.00.6031746031746031380.0317460317460317442.00.079365079365079365.0
50.006451232.093800.93756804.60355970.32727418.29153167515963.20012416906.0124.00.90.00.00.10.4238-0.00650.10310.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2260.00.01.00.00.057091368.049673637888.00.00.89910.02890.53120.423815.082951.8138564.932534.2857.9676293.03510.06356.765951.5237289.9821341.80611115.484731.5793290.2185735.330.00.0046148846113250.032786885245901642.00.22950819672131148140.006611.04340.1967213114754098312.0
60.006451242.078100.93757771.13097007.43488394.00353172016594.65532870810.0141.00.92190.00.00.07810.44920.00620.1098-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2474-0.00.01.00.00.014378494.015988083712.00.00.93250.02930.54690.449215.766851.9979566.086534.0857.9676291.88110.06476.915653.6929321.9671375.93881041.264427.7237322.1809630.68280.00.0056249645720290.1612903225806451610.00.4032258064516129250.064516129032258064.014.5082
70.006451252.37500.90628355.86916907.13689575.30583175717311.32342988458.0133.00.92590.00.00.07410.457-0.00220.11590.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23780.00.01.00.00.012489437.013437528064.00.00.91820.02250.59380.45716.029452.291566.988733.9857.9676290.97890.0666.35660.2323365.4923426.16061269.018134.646365.862801.85190.00.0066249645222410.048387096774193553.00.5967741935483871370.00812.97070.064516129032258064.0
80.006451252.796900.98447991.97076916.8888948.04063164416886.84812992563.0124.00.91560.00.00.08440.4707-0.00050.0910.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2520.00.01.00.00.0126512944.0185155289088.00.00.90380.02770.54690.470716.171852.4857568.402633.8857.9676289.56490.06466.881354.2482338.5812393.13271034.771730.6732338.8195604.08080.00.0075947243417380.6101694915254238360.016949152542372881.00.016949152542372881.00.10169491525423736.0
90.006451252.234400.90627648.50596225.13558670.65773174416899.62082788495.0138.00.89520.00.00.10480.4180.00780.1671-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2453-0.00.01.00.00.0302555712.0327041482752.00.00.90420.02710.64060.41816.18952.4965567.739633.8857.9676290.2280.06656.408150.3661360.6974411.40511185.103432.6171360.9721734.66940.00.0086552048915290.030769230769230772.00.4153846153846154270.007610.25460.030769230769230772.0
100.006451242.359400.95317850.69146654.60098773.62633178716458.03552796358.0120.00.91270.00.00.08730.4355-0.00410.06920.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.250.00.01.00.00.050441308.069631238144.00.00.93050.02540.51560.435516.579552.9702566.754133.9857.9676291.21350.10796.160653.0374311.5625365.02951120.461927.2652311.8839722.00270.00.0096350444528490.1587301587301587210.00.6825396825396826430.0476190476190476163.00.0476190476190476163.0
110.006451242.390600.93757607.39656702.78078127.89853179617050.48492814974.0105.00.90650.00.00.09350.3652-0.00380.18340.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.24410.00.01.00.00.0154107520.0193226620928.00.00.87630.02370.56250.365216.608752.9871565.991534.0857.9676291.97610.0656.929254.2197362.5899417.14881216.390226.4624362.8625765.8460.00.00106451246720410.0468753.00.640625410.008211.57540.031252.014.20230.0156251.0
120.006451252.218800.93757184.95316151.73318068.43123171716417.31082615742.0119.00.92330.00.00.07670.46090.0030.0920.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23890.00.01.00.00.05064779.55147700736.00.00.89920.02470.57810.460916.619153.1242565.371234.1857.9676292.59640.06396.748850.4991300.7344351.5976853.898229.4017301.0342466.14580.00.00116350445823430.0476190476190476163.00.6190476190476191390.063492063492063494.0
130.006451252.328100.8757866.756919.32718547.11413168416734.12442837449.0102.00.9250.00.00.0750.4180.00380.1009-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2509-0.00.01.00.00.03308509.04308027392.00.00.89840.02320.57810.41816.634953.1943564.911734.2857.9676293.05590.06517.163955.7894333.9905390.0611328.386229.1332334.2062902.0240.00.00126148844815290.1803278688524590211.00.4262295081967213260.007510.96110.016393442622950821.00.049180327868852463.0
140.006451242.218800.92197290.64266210.00858207.4263169016273.17472579307.0122.00.95320.00.00.04680.459-0.00230.0980.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.23260.00.01.00.00.026911360.028828094464.00.00.91130.02470.51560.45916.627353.2404564.167334.2857.9676293.80030.06556.260149.0345304.2172353.5397867.084226.9038304.4394480.37610.00.00136148843022550.049180327868852463.00.8032786885245902490.081967213114754095.00.032786885245901642.0
150.006451252.296900.89067534.44737051.57147931.40213182216845.38292790009.0142.00.87930.00.00.12070.45120.00590.1278-0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.2318-0.00.01.00.00.0123395328.0111167111168.00.00.87320.02980.65620.451217.106653.2242634.679726.0857.9676223.28780.06546.186451.4801329.1219380.86911247.691532.9105329.3226827.72080.00.00146249645717270.193548387096774212.00.3387096774193548210.007710.3440.064516129032258064.00.032258064516129032.0
160.006451252.12500.89068321.5025844.742910043.75173175816907.34133027171.0107.00.91680.00.00.08320.4102-0.01360.12560.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.26060.00.01.00.00.0120506544.0182772285440.00.00.91330.02740.56250.410217.118853.2869631.545326.4857.9676226.42230.06637.237852.7711346.9524400.04981013.075727.3806347.212578.40250.00.00156249645420420.6129032258064516380.0161290322580645161.00.048387096774193553.014.5803