laion/ablation-pymethods2test-seqmean-arm0-30-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/ablation-pymethods2test-seqmean-arm0-30-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 18:02:02 +08:00
commit 0c293fc953
47 changed files with 292406 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
training_logs/20260612_220124_metrics_job_630127.csv Normal file
View File

@@ -0,0 +1,29 @@
async/discard_rate,async/discarded_count,async/effective_batch_groups,async/effective_batch_samples,async/staleness_max,async/staleness_mean,async/staleness_min,async/staleness_ratio,generate/avg_num_tokens,generate/avg_tokens_non_zero_rewards,generate/avg_tokens_zero_rewards,generate/max_num_tokens,generate/min_num_tokens,generate/std_num_tokens,loss/avg_final_rewards,loss/avg_raw_advantages,loss/avg_raw_advantages_abs,policy/final_loss,policy/log_ratio_abs_max,policy/log_ratio_abs_mean,policy/log_ratio_abs_p99,policy/log_ratio_abs_pos00,policy/log_ratio_abs_pos10,policy/log_ratio_abs_pos20,policy/log_ratio_abs_pos30,policy/log_ratio_abs_pos40,policy/log_ratio_abs_pos50,policy/log_ratio_abs_pos60,policy/log_ratio_abs_pos70,policy/log_ratio_abs_pos80,policy/log_ratio_abs_pos90,policy/n_tokens_dp_gt_10pct,policy/n_tokens_dp_gt_1pct,policy/n_tokens_dp_gt_50pct,policy/policy_entropy,policy/policy_loss,policy/policy_lr,policy/policy_update_steps,policy/ppo_clip_ratio,policy/raw_grad_norm,reward/avg_pass_at_8,reward/avg_raw_reward,system/process_rss_gb,system/process_vms_gb,system/ram_available_gb,system/ram_percent,system/ram_total_gb,system/ram_used_gb,timing/compute_advantages_and_returns,timing/convert_to_training_input,timing/fwd_logprobs_values_reward,timing/policy_train,timing/run_training,timing/step,timing/sync_weights,timing/train_critic_and_policy,timing/wait_for_generation_buffer,trainer/epoch,trainer/global_step,batch_errors/total_batches,batch_errors/total_instances,batch_errors/total_successful,batch_errors/total_failed,batch_errors/total_masked,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_InvalidChatHistory,batch_errors/total_InvalidChatHistory,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError
0.0,0,64,512,5,0.8125,0,0.2031,5219.4023,5279.0935,5148.4872,24019,1,3593.1869,0.543,0.0174,0.1093,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.127,-0.0059,0.0,1.0,0.0,0.0136,0.661,0.543,9.9914,50.291,594.6118,30.7,857.9675,263.3557,0.2443,3.7877,34.8635,181.2173,216.5936,3907.0864,25.2212,181.4851,3661.4836,0,29,54,432,397,20,35,0.18518518518518517,10,0.48148148148148145,26,0.05555555555555555,3.0,,,,,,,
0.0,0,64,512,1,0.875,0,0.875,6119.2617,5371.9608,6614.2273,31787,1,5360.732,0.3984,0.0066,0.11,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1391,-0.0,0.0,1.0,0.0,0.0133,0.5156,0.3984,12.6683,50.5745,589.7981,31.3,857.9675,268.1694,0.0668,4.853,45.3325,249.4957,295.1659,1561.0798,22.8392,249.7659,1238.2155,0,30,51,408,360,18,48,0.19607843137254902,10,0.9803921568627451,50,0.0784313725490196,4.0,17.6986,25.6657,6.5413,0.0784313725490196,4.0,,
0.0,0,64,512,2,1.7031,1,1.0,5416.0312,5191.9848,5493.8579,31782,1,5258.8542,0.2578,0.0188,0.1227,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1224,-0.0045,0.0,1.0,0.0,0.0132,0.3906,0.2578,13.0473,50.9899,588.6119,31.4,857.9675,269.3556,0.0915,4.9642,38.9391,242.4843,281.7563,558.6231,24.3077,242.7249,247.5902,0,31,62,496,450,16,38,0.03225806451612903,2,0.5806451612903226,36,,,,,,0.06451612903225806,4.0,,
0.0,0,64,512,3,1.8438,0,0.8438,4876.5957,4321.0181,5298.5292,31788,1,4349.0068,0.4316,0.008,0.1024,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1299,-0.0033,0.0,1.0,0.0,0.0147,0.5469,0.4316,13.3226,51.1669,587.694,31.5,857.9675,270.2736,0.0969,4.6902,32.9398,184.8866,218.1917,1881.6998,22.4991,185.1545,1636.313,0,32,61,488,435,20,50,0.26229508196721313,16,0.5245901639344263,32,0.04918032786885246,3.0,0.0086,8.4163,,0.04918032786885246,3.0,,
0.0,0,64,512,4,1.9688,0,0.8906,5456.2109,4808.7673,5878.0935,31806,1,4961.1718,0.3945,0.0083,0.1325,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1254,0.0,0.0,1.0,0.0,0.0126,0.5469,0.3945,13.4299,51.223,587.0558,31.6,857.9675,270.9117,0.067,4.9084,36.655,238.8678,275.8322,1516.0964,23.2669,239.1098,1212.085,0,33,62,496,436,21,55,0.27419354838709675,17,0.5806451612903226,36,0.03225806451612903,2.0,,,,0.08064516129032258,5.0,,
0.0,0,64,512,4,2.125,0,0.9844,5502.4434,5212.8122,5708.7692,31765,1,5396.2041,0.416,-0.004,0.0835,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1286,-0.0,0.0,1.0,0.0,0.0137,0.5156,0.416,13.5508,51.3198,587.3987,31.5,857.9675,270.5688,0.0691,5.493,44.4908,256.2057,301.0644,1068.5266,22.5088,256.5041,739.4567,0,34,63,504,462,14,41,0.23809523809523808,15,0.3968253968253968,25,0.015873015873015872,1.0,0.0088,8.3216,,0.015873015873015872,1.0,,
0.0,0,64,512,3,1.8594,0,0.9219,5384.9941,5343.019,5414.1821,31664,1,4412.7671,0.4102,0.0025,0.0519,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1331,-0.002,0.0,1.0,0.0,0.0142,0.5,0.4102,13.7969,51.3292,586.7628,31.6,857.9675,271.2047,0.0906,4.7764,33.1627,211.1102,244.5902,1384.0633,22.1442,211.3362,1112.5444,0,35,61,488,463,8,17,0.04918032786885246,3,0.26229508196721313,16,,,,,5.8995,0.13114754098360656,8.0,,
0.0,0,64,512,4,1.9219,0,0.9062,5825.4473,5333.0212,6246.5072,31794,1,4498.7568,0.4609,0.0027,0.1742,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1384,-0.0,0.0,1.0,0.0,0.0171,0.6406,0.4609,13.8943,51.4631,586.2767,31.7,857.9675,271.6909,0.5695,4.8349,37.7488,223.605,262.1992,1464.7075,20.515,223.8804,1177.1535,0,36,64,512,471,15,40,0.109375,7,0.515625,33,,,0.009,7.9437,,0.015625,1.0,,
0.0,0,64,512,4,1.8438,0,0.9062,5148.5137,4631.637,5834.55,31764,1,4648.1595,0.5703,-0.0029,0.1133,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1253,-0.0011,0.0,1.0,0.0,0.0167,0.6875,0.5703,14.5586,51.6496,584.9858,31.8,857.9675,272.9817,0.0919,4.8241,38.277,222.4597,261.0628,1077.7825,26.2516,222.6934,785.6361,0,37,61,488,451,15,35,0.14754098360655737,9,0.4262295081967213,26,0.09836065573770492,6.0,,,,0.03278688524590164,2.0,,
0.0,0,64,512,4,2.1875,0,0.9375,5691.4238,5458.8718,5887.1691,31763,1,4985.511,0.457,0.0025,0.1314,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1239,-0.0,0.0,1.0,0.0,0.0158,0.6094,0.457,14.4333,51.5906,584.4034,31.9,857.9675,273.5641,0.8661,4.8087,37.1183,229.9869,268.1954,1281.4976,24.0319,230.2106,984.4536,0,38,63,504,457,20,44,0.1111111111111111,7,0.5238095238095238,33,,,0.0082,8.3888,,0.047619047619047616,3.0,,
0.0,0,64,512,4,1.875,0,0.9219,4852.4375,4700.9213,4963.0034,31721,1,3852.6075,0.4219,-0.0118,0.1369,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1297,-0.0025,0.0,1.0,0.0,0.0151,0.5625,0.4219,14.8096,51.9002,584.34,31.9,857.9675,273.6276,0.1019,4.7148,35.3281,188.2665,223.9309,1220.1543,22.2426,188.5005,969.2585,0,39,63,504,446,22,48,0.09523809523809523,6,0.6666666666666666,42,0.031746031746031744,2.0,,,,0.15873015873015872,10.0,,
0.0,0,64,512,4,1.8906,0,0.8438,4717.9707,4944.8443,4511.4142,31770,1,4317.3591,0.4766,0.0072,0.086,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1232,0.0,0.0,1.0,0.0,0.0143,0.5938,0.4766,14.7138,51.7721,583.8667,31.9,857.9675,274.1008,0.0992,4.8622,31.9697,193.9941,226.3482,1608.4681,22.3175,194.2789,1354.9332,0,40,60,480,456,10,24,0.05,3,0.36666666666666664,22,0.03333333333333333,2.0,0.0074,8.3081,6.0239,,,,
0.0,0,64,512,4,1.6875,0,0.9531,5037.7695,5312.8784,4764.8016,27138,1,3679.8466,0.498,-0.0001,0.0849,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1349,-0.0,0.0,1.0,0.0,0.0122,0.5781,0.498,14.5892,51.6475,583.7137,32.0,857.9675,274.2538,0.0824,4.1919,29.9247,176.4747,206.7121,1037.8229,24.3689,176.7045,802.5427,0,41,60,480,441,19,37,0.18333333333333332,11,0.43333333333333335,26,,,,,,0.016666666666666666,1.0,0.016666666666666666,1.0
0.0,0,64,512,4,1.9844,0,0.8906,5756.3848,5835.0311,5708.8025,31761,1,4473.6908,0.377,0.0069,0.1087,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1346,0.0,0.0,1.0,0.0,0.013,0.4531,0.377,14.9636,52.1455,583.6249,32.0,857.9675,274.3426,0.0719,4.8088,36.9135,222.7902,260.0054,1385.1388,21.7016,223.0196,1098.6195,0,42,61,488,424,20,50,0.22950819672131148,14,0.5573770491803278,34,0.03278688524590164,2.0,0.0076,7.9965,,0.22950819672131148,14.0,,
0.0,0,64,512,4,1.5781,0,0.8281,4886.5996,4211.4396,5344.823,31794,1,4658.4948,0.4043,0.003,0.0477,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.119,-0.0014,0.0,1.0,0.0,0.0109,0.4844,0.4043,14.9648,52.146,583.4162,32.0,857.9675,274.5513,0.0932,4.8883,35.3553,210.4627,246.1689,1473.9582,23.9821,210.7199,1198.9132,0,43,61,488,441,16,45,0.16393442622950818,10,0.5081967213114754,31,0.06557377049180328,4.0,,,,0.03278688524590164,2.0,,
0.0,0,64,512,4,1.9375,0,0.9844,5006.252,5006.7137,5005.7938,31832,1,4198.283,0.498,0.0058,0.1318,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1302,-0.0013,0.0,1.0,0.0,0.0142,0.625,0.498,15.1405,52.1464,582.1508,32.1,857.9675,275.8167,0.0701,4.8376,37.1394,204.9028,242.3402,995.3073,21.6574,205.1302,726.4685,0,44,63,504,464,15,40,0.2698412698412698,17,0.3492063492063492,22,0.015873015873015872,1.0,0.0087,8.5306,,,,,
0.0,0,64,512,4,1.9688,0,0.9531,5307.5059,4945.0996,5629.7934,31811,1,4502.6994,0.4707,0.0034,0.0645,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1244,0.0,0.0,1.0,0.0,0.0087,0.5156,0.4707,15.2917,52.3331,581.6784,32.2,857.9675,276.2891,0.0713,4.8688,35.6411,219.1314,255.1244,1030.1018,22.2906,219.4115,747.8149,0,45,57,456,419,11,20,0.07017543859649122,4,0.3508771929824561,20,0.03508771929824561,2.0,,,7.1117,0.2982456140350877,17.0,,
0.0,0,64,512,4,2.3281,0,0.9531,5162.7871,4802.6639,5490.6604,31759,1,4252.9044,0.4766,-0.0039,0.0939,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1296,0.0,0.0,1.0,0.0,0.0135,0.5625,0.4766,15.655,52.6444,580.4724,32.3,857.9675,277.4952,0.1001,4.9649,38.1605,200.0621,238.5392,1116.6096,24.6502,200.2781,848.4495,0,46,62,496,452,18,44,0.14516129032258066,9,0.5483870967741935,34,0.016129032258064516,1.0,0.0077,8.5628,,,,,
0.0,0,64,512,4,2.1094,0,0.9375,5453.8691,5448.0192,5459.9522,31779,1,4423.535,0.5098,0.01,0.1256,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1244,0.0,0.0,1.0,0.0,0.0129,0.625,0.5098,15.5344,52.5839,580.0443,32.4,857.9675,277.9232,0.0896,4.8374,35.3367,219.7689,255.4572,1436.5679,22.4966,220.0305,1153.7719,0,47,61,488,451,18,36,0.16393442622950818,10,0.3770491803278688,23,0.04918032786885246,3.0,,,,0.01639344262295082,1.0,,
0.0,0,64,512,4,1.875,0,0.875,5230.4609,4627.1281,5626.8252,31716,1,4361.9157,0.3965,-0.0025,0.057,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1316,-0.0,0.0,1.0,0.0,0.0113,0.5,0.3965,15.6175,52.7105,579.3495,32.5,857.9675,278.618,0.0831,4.8056,35.7289,205.2303,241.3389,1388.9346,24.246,205.5265,1118.5394,0,48,63,504,448,25,55,0.1746031746031746,11,0.6666666666666666,42,0.031746031746031744,2.0,0.0078,8.0292,,0.015873015873015872,1.0,,
0.0,0,64,512,4,1.9688,0,0.9062,5567.3223,3973.2919,6469.1437,31784,1,5829.7172,0.3613,-0.0074,0.1077,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1253,0.0,0.0,1.0,0.0,0.0168,0.4844,0.3613,15.5988,52.7747,578.7762,32.5,857.9675,279.1913,0.1107,4.8687,41.1551,269.7094,311.286,1674.2094,22.9805,270.0198,1335.0696,0,49,60,480,440,17,39,0.13333333333333333,8,0.5166666666666667,31,,,,,,0.016666666666666666,1.0,,
0.0,0,64,512,3,1.6875,0,0.9375,5274.1113,4738.0175,5707.9117,31829,1,4398.882,0.4473,0.008,0.0793,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1253,0.0,0.0,1.0,0.0,0.0132,0.5469,0.4473,15.6793,52.8362,578.3136,32.6,857.9675,279.6539,0.0972,4.7852,34.4386,207.8657,242.6571,1060.2084,23.4244,208.1209,789.3372,0,50,65,520,431,21,76,0.12307692307692308,8,0.9538461538461539,62,0.09230769230769231,6.0,0.0081,9.1305,5.9495,0.18461538461538463,12.0,0.015384615384615385,1.0
0.0,0,64,512,4,1.9219,0,0.8906,5243.7461,5174.6447,5286.9619,31743,1,5188.684,0.3848,-0.0033,0.0945,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1207,0.0,0.0,1.0,0.0,0.0967,0.4531,0.3848,15.6188,52.7762,577.5959,32.7,857.9675,280.3716,0.076,4.7495,40.1813,238.4651,278.9729,1686.7408,24.1315,238.7151,1378.8824,0,51,62,496,446,22,49,0.20967741935483872,13,0.5645161290322581,35,0.016129032258064516,1.0,,,,0.016129032258064516,1.0,,
0.0,0,64,512,4,1.7812,0,0.8438,5252.4961,5411.8429,5141.6921,31823,1,4683.711,0.4102,0.0062,0.0796,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.133,-0.002,0.0,1.0,0.0,0.0124,0.5312,0.4102,15.7651,52.9658,577.1581,32.7,857.9675,280.8094,0.0944,4.7678,38.5332,214.205,253.0737,1600.439,23.268,214.4456,1319.3232,0,52,61,488,451,14,37,0.08196721311475409,5,0.4918032786885246,30,0.03278688524590164,2.0,0.0082,8.7241,,,,,
0.0,0,64,512,3,1.8125,0,0.9531,5107.9043,4684.3886,5450.6078,31689,1,4035.9699,0.4473,-0.0001,0.0667,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.132,0.0,0.0,1.0,0.0,0.0132,0.5312,0.4473,15.7054,52.9061,577.4001,32.7,857.9675,280.5674,0.097,4.8708,33.9418,188.7929,223.0849,1082.9166,25.281,189.0458,829.6739,0,53,63,504,454,17,47,0.015873015873015872,1,0.6984126984126984,44,0.031746031746031744,2.0,,,,0.047619047619047616,3.0,,
0.0,0,64,512,3,1.7969,0,0.875,5634.0664,5882.4221,5476.1661,31801,1,5198.4542,0.3887,0.0101,0.0932,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1305,0.0,0.0,1.0,0.0,0.0144,0.5156,0.3887,15.8018,52.9791,576.4988,32.8,857.9675,281.4687,0.0964,4.9065,40.1938,233.8941,274.5002,1827.1928,24.3101,234.2096,1523.4687,0,54,61,488,434,19,52,0.13114754098360656,8,0.6557377049180327,40,0.08196721311475409,5.0,0.0084,8.6128,,0.03278688524590164,2.0,,
0.0,0,64,512,4,1.9375,0,0.9531,5371.4082,5022.761,5604.2182,31785,1,4782.3049,0.4004,-0.0082,0.1177,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1222,-0.0007,0.0,1.0,0.0,0.0128,0.5156,0.4004,15.8948,53.0398,576.6206,32.8,857.9675,281.3469,0.0653,4.8129,41.537,228.2535,270.096,1483.9509,23.783,228.4932,1185.2547,0,55,62,496,429,19,64,0.0967741935483871,6,0.9032258064516129,56,0.04838709677419355,3.0,,,6.0259,0.04838709677419355,3.0,,
0.0,0,64,512,4,1.6094,0,0.9062,4940.75,4904.8341,4965.9269,31836,1,4570.0348,0.4121,-0.0024,0.1498,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.124,-0.0,0.0,1.0,0.0,0.0148,0.5156,0.4121,16.2064,53.3552,575.7253,32.9,857.9675,282.2422,0.0989,4.7645,34.0253,209.3135,243.7093,1375.7686,22.7461,209.5845,1104.5439,0,56,59,472,390,33,69,0.288135593220339,17,0.5084745762711864,30,0.3728813559322034,22.0,0.0075,15.5646,,0.22033898305084745,13.0,,
1 async/discard_rate async/discarded_count async/effective_batch_groups async/effective_batch_samples async/staleness_max async/staleness_mean async/staleness_min async/staleness_ratio generate/avg_num_tokens generate/avg_tokens_non_zero_rewards generate/avg_tokens_zero_rewards generate/max_num_tokens generate/min_num_tokens generate/std_num_tokens loss/avg_final_rewards loss/avg_raw_advantages loss/avg_raw_advantages_abs policy/final_loss policy/log_ratio_abs_max policy/log_ratio_abs_mean policy/log_ratio_abs_p99 policy/log_ratio_abs_pos00 policy/log_ratio_abs_pos10 policy/log_ratio_abs_pos20 policy/log_ratio_abs_pos30 policy/log_ratio_abs_pos40 policy/log_ratio_abs_pos50 policy/log_ratio_abs_pos60 policy/log_ratio_abs_pos70 policy/log_ratio_abs_pos80 policy/log_ratio_abs_pos90 policy/n_tokens_dp_gt_10pct policy/n_tokens_dp_gt_1pct policy/n_tokens_dp_gt_50pct policy/policy_entropy policy/policy_loss policy/policy_lr policy/policy_update_steps policy/ppo_clip_ratio policy/raw_grad_norm reward/avg_pass_at_8 reward/avg_raw_reward system/process_rss_gb system/process_vms_gb system/ram_available_gb system/ram_percent system/ram_total_gb system/ram_used_gb timing/compute_advantages_and_returns timing/convert_to_training_input timing/fwd_logprobs_values_reward timing/policy_train timing/run_training timing/step timing/sync_weights timing/train_critic_and_policy timing/wait_for_generation_buffer trainer/epoch trainer/global_step batch_errors/total_batches batch_errors/total_instances batch_errors/total_successful batch_errors/total_failed batch_errors/total_masked batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_InvalidChatHistory batch_errors/total_InvalidChatHistory batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError
2 0.0 0 64 512 5 0.8125 0 0.2031 5219.4023 5279.0935 5148.4872 24019 1 3593.1869 0.543 0.0174 0.1093 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.127 -0.0059 0.0 1.0 0.0 0.0136 0.661 0.543 9.9914 50.291 594.6118 30.7 857.9675 263.3557 0.2443 3.7877 34.8635 181.2173 216.5936 3907.0864 25.2212 181.4851 3661.4836 0 29 54 432 397 20 35 0.18518518518518517 10 0.48148148148148145 26 0.05555555555555555 3.0
3 0.0 0 64 512 1 0.875 0 0.875 6119.2617 5371.9608 6614.2273 31787 1 5360.732 0.3984 0.0066 0.11 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1391 -0.0 0.0 1.0 0.0 0.0133 0.5156 0.3984 12.6683 50.5745 589.7981 31.3 857.9675 268.1694 0.0668 4.853 45.3325 249.4957 295.1659 1561.0798 22.8392 249.7659 1238.2155 0 30 51 408 360 18 48 0.19607843137254902 10 0.9803921568627451 50 0.0784313725490196 4.0 17.6986 25.6657 6.5413 0.0784313725490196 4.0
4 0.0 0 64 512 2 1.7031 1 1.0 5416.0312 5191.9848 5493.8579 31782 1 5258.8542 0.2578 0.0188 0.1227 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1224 -0.0045 0.0 1.0 0.0 0.0132 0.3906 0.2578 13.0473 50.9899 588.6119 31.4 857.9675 269.3556 0.0915 4.9642 38.9391 242.4843 281.7563 558.6231 24.3077 242.7249 247.5902 0 31 62 496 450 16 38 0.03225806451612903 2 0.5806451612903226 36 0.06451612903225806 4.0
5 0.0 0 64 512 3 1.8438 0 0.8438 4876.5957 4321.0181 5298.5292 31788 1 4349.0068 0.4316 0.008 0.1024 -0.0001 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1299 -0.0033 0.0 1.0 0.0 0.0147 0.5469 0.4316 13.3226 51.1669 587.694 31.5 857.9675 270.2736 0.0969 4.6902 32.9398 184.8866 218.1917 1881.6998 22.4991 185.1545 1636.313 0 32 61 488 435 20 50 0.26229508196721313 16 0.5245901639344263 32 0.04918032786885246 3.0 0.0086 8.4163 0.04918032786885246 3.0
6 0.0 0 64 512 4 1.9688 0 0.8906 5456.2109 4808.7673 5878.0935 31806 1 4961.1718 0.3945 0.0083 0.1325 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1254 0.0 0.0 1.0 0.0 0.0126 0.5469 0.3945 13.4299 51.223 587.0558 31.6 857.9675 270.9117 0.067 4.9084 36.655 238.8678 275.8322 1516.0964 23.2669 239.1098 1212.085 0 33 62 496 436 21 55 0.27419354838709675 17 0.5806451612903226 36 0.03225806451612903 2.0 0.08064516129032258 5.0
7 0.0 0 64 512 4 2.125 0 0.9844 5502.4434 5212.8122 5708.7692 31765 1 5396.2041 0.416 -0.004 0.0835 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1286 -0.0 0.0 1.0 0.0 0.0137 0.5156 0.416 13.5508 51.3198 587.3987 31.5 857.9675 270.5688 0.0691 5.493 44.4908 256.2057 301.0644 1068.5266 22.5088 256.5041 739.4567 0 34 63 504 462 14 41 0.23809523809523808 15 0.3968253968253968 25 0.015873015873015872 1.0 0.0088 8.3216 0.015873015873015872 1.0
8 0.0 0 64 512 3 1.8594 0 0.9219 5384.9941 5343.019 5414.1821 31664 1 4412.7671 0.4102 0.0025 0.0519 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1331 -0.002 0.0 1.0 0.0 0.0142 0.5 0.4102 13.7969 51.3292 586.7628 31.6 857.9675 271.2047 0.0906 4.7764 33.1627 211.1102 244.5902 1384.0633 22.1442 211.3362 1112.5444 0 35 61 488 463 8 17 0.04918032786885246 3 0.26229508196721313 16 5.8995 0.13114754098360656 8.0
9 0.0 0 64 512 4 1.9219 0 0.9062 5825.4473 5333.0212 6246.5072 31794 1 4498.7568 0.4609 0.0027 0.1742 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1384 -0.0 0.0 1.0 0.0 0.0171 0.6406 0.4609 13.8943 51.4631 586.2767 31.7 857.9675 271.6909 0.5695 4.8349 37.7488 223.605 262.1992 1464.7075 20.515 223.8804 1177.1535 0 36 64 512 471 15 40 0.109375 7 0.515625 33 0.009 7.9437 0.015625 1.0
10 0.0 0 64 512 4 1.8438 0 0.9062 5148.5137 4631.637 5834.55 31764 1 4648.1595 0.5703 -0.0029 0.1133 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1253 -0.0011 0.0 1.0 0.0 0.0167 0.6875 0.5703 14.5586 51.6496 584.9858 31.8 857.9675 272.9817 0.0919 4.8241 38.277 222.4597 261.0628 1077.7825 26.2516 222.6934 785.6361 0 37 61 488 451 15 35 0.14754098360655737 9 0.4262295081967213 26 0.09836065573770492 6.0 0.03278688524590164 2.0
11 0.0 0 64 512 4 2.1875 0 0.9375 5691.4238 5458.8718 5887.1691 31763 1 4985.511 0.457 0.0025 0.1314 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1239 -0.0 0.0 1.0 0.0 0.0158 0.6094 0.457 14.4333 51.5906 584.4034 31.9 857.9675 273.5641 0.8661 4.8087 37.1183 229.9869 268.1954 1281.4976 24.0319 230.2106 984.4536 0 38 63 504 457 20 44 0.1111111111111111 7 0.5238095238095238 33 0.0082 8.3888 0.047619047619047616 3.0
12 0.0 0 64 512 4 1.875 0 0.9219 4852.4375 4700.9213 4963.0034 31721 1 3852.6075 0.4219 -0.0118 0.1369 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1297 -0.0025 0.0 1.0 0.0 0.0151 0.5625 0.4219 14.8096 51.9002 584.34 31.9 857.9675 273.6276 0.1019 4.7148 35.3281 188.2665 223.9309 1220.1543 22.2426 188.5005 969.2585 0 39 63 504 446 22 48 0.09523809523809523 6 0.6666666666666666 42 0.031746031746031744 2.0 0.15873015873015872 10.0
13 0.0 0 64 512 4 1.8906 0 0.8438 4717.9707 4944.8443 4511.4142 31770 1 4317.3591 0.4766 0.0072 0.086 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1232 0.0 0.0 1.0 0.0 0.0143 0.5938 0.4766 14.7138 51.7721 583.8667 31.9 857.9675 274.1008 0.0992 4.8622 31.9697 193.9941 226.3482 1608.4681 22.3175 194.2789 1354.9332 0 40 60 480 456 10 24 0.05 3 0.36666666666666664 22 0.03333333333333333 2.0 0.0074 8.3081 6.0239
14 0.0 0 64 512 4 1.6875 0 0.9531 5037.7695 5312.8784 4764.8016 27138 1 3679.8466 0.498 -0.0001 0.0849 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1349 -0.0 0.0 1.0 0.0 0.0122 0.5781 0.498 14.5892 51.6475 583.7137 32.0 857.9675 274.2538 0.0824 4.1919 29.9247 176.4747 206.7121 1037.8229 24.3689 176.7045 802.5427 0 41 60 480 441 19 37 0.18333333333333332 11 0.43333333333333335 26 0.016666666666666666 1.0 0.016666666666666666 1.0
15 0.0 0 64 512 4 1.9844 0 0.8906 5756.3848 5835.0311 5708.8025 31761 1 4473.6908 0.377 0.0069 0.1087 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1346 0.0 0.0 1.0 0.0 0.013 0.4531 0.377 14.9636 52.1455 583.6249 32.0 857.9675 274.3426 0.0719 4.8088 36.9135 222.7902 260.0054 1385.1388 21.7016 223.0196 1098.6195 0 42 61 488 424 20 50 0.22950819672131148 14 0.5573770491803278 34 0.03278688524590164 2.0 0.0076 7.9965 0.22950819672131148 14.0
16 0.0 0 64 512 4 1.5781 0 0.8281 4886.5996 4211.4396 5344.823 31794 1 4658.4948 0.4043 0.003 0.0477 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.119 -0.0014 0.0 1.0 0.0 0.0109 0.4844 0.4043 14.9648 52.146 583.4162 32.0 857.9675 274.5513 0.0932 4.8883 35.3553 210.4627 246.1689 1473.9582 23.9821 210.7199 1198.9132 0 43 61 488 441 16 45 0.16393442622950818 10 0.5081967213114754 31 0.06557377049180328 4.0 0.03278688524590164 2.0
17 0.0 0 64 512 4 1.9375 0 0.9844 5006.252 5006.7137 5005.7938 31832 1 4198.283 0.498 0.0058 0.1318 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1302 -0.0013 0.0 1.0 0.0 0.0142 0.625 0.498 15.1405 52.1464 582.1508 32.1 857.9675 275.8167 0.0701 4.8376 37.1394 204.9028 242.3402 995.3073 21.6574 205.1302 726.4685 0 44 63 504 464 15 40 0.2698412698412698 17 0.3492063492063492 22 0.015873015873015872 1.0 0.0087 8.5306
18 0.0 0 64 512 4 1.9688 0 0.9531 5307.5059 4945.0996 5629.7934 31811 1 4502.6994 0.4707 0.0034 0.0645 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1244 0.0 0.0 1.0 0.0 0.0087 0.5156 0.4707 15.2917 52.3331 581.6784 32.2 857.9675 276.2891 0.0713 4.8688 35.6411 219.1314 255.1244 1030.1018 22.2906 219.4115 747.8149 0 45 57 456 419 11 20 0.07017543859649122 4 0.3508771929824561 20 0.03508771929824561 2.0 7.1117 0.2982456140350877 17.0
19 0.0 0 64 512 4 2.3281 0 0.9531 5162.7871 4802.6639 5490.6604 31759 1 4252.9044 0.4766 -0.0039 0.0939 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1296 0.0 0.0 1.0 0.0 0.0135 0.5625 0.4766 15.655 52.6444 580.4724 32.3 857.9675 277.4952 0.1001 4.9649 38.1605 200.0621 238.5392 1116.6096 24.6502 200.2781 848.4495 0 46 62 496 452 18 44 0.14516129032258066 9 0.5483870967741935 34 0.016129032258064516 1.0 0.0077 8.5628
20 0.0 0 64 512 4 2.1094 0 0.9375 5453.8691 5448.0192 5459.9522 31779 1 4423.535 0.5098 0.01 0.1256 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1244 0.0 0.0 1.0 0.0 0.0129 0.625 0.5098 15.5344 52.5839 580.0443 32.4 857.9675 277.9232 0.0896 4.8374 35.3367 219.7689 255.4572 1436.5679 22.4966 220.0305 1153.7719 0 47 61 488 451 18 36 0.16393442622950818 10 0.3770491803278688 23 0.04918032786885246 3.0 0.01639344262295082 1.0
21 0.0 0 64 512 4 1.875 0 0.875 5230.4609 4627.1281 5626.8252 31716 1 4361.9157 0.3965 -0.0025 0.057 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1316 -0.0 0.0 1.0 0.0 0.0113 0.5 0.3965 15.6175 52.7105 579.3495 32.5 857.9675 278.618 0.0831 4.8056 35.7289 205.2303 241.3389 1388.9346 24.246 205.5265 1118.5394 0 48 63 504 448 25 55 0.1746031746031746 11 0.6666666666666666 42 0.031746031746031744 2.0 0.0078 8.0292 0.015873015873015872 1.0
22 0.0 0 64 512 4 1.9688 0 0.9062 5567.3223 3973.2919 6469.1437 31784 1 5829.7172 0.3613 -0.0074 0.1077 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1253 0.0 0.0 1.0 0.0 0.0168 0.4844 0.3613 15.5988 52.7747 578.7762 32.5 857.9675 279.1913 0.1107 4.8687 41.1551 269.7094 311.286 1674.2094 22.9805 270.0198 1335.0696 0 49 60 480 440 17 39 0.13333333333333333 8 0.5166666666666667 31 0.016666666666666666 1.0
23 0.0 0 64 512 3 1.6875 0 0.9375 5274.1113 4738.0175 5707.9117 31829 1 4398.882 0.4473 0.008 0.0793 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1253 0.0 0.0 1.0 0.0 0.0132 0.5469 0.4473 15.6793 52.8362 578.3136 32.6 857.9675 279.6539 0.0972 4.7852 34.4386 207.8657 242.6571 1060.2084 23.4244 208.1209 789.3372 0 50 65 520 431 21 76 0.12307692307692308 8 0.9538461538461539 62 0.09230769230769231 6.0 0.0081 9.1305 5.9495 0.18461538461538463 12.0 0.015384615384615385 1.0
24 0.0 0 64 512 4 1.9219 0 0.8906 5243.7461 5174.6447 5286.9619 31743 1 5188.684 0.3848 -0.0033 0.0945 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1207 0.0 0.0 1.0 0.0 0.0967 0.4531 0.3848 15.6188 52.7762 577.5959 32.7 857.9675 280.3716 0.076 4.7495 40.1813 238.4651 278.9729 1686.7408 24.1315 238.7151 1378.8824 0 51 62 496 446 22 49 0.20967741935483872 13 0.5645161290322581 35 0.016129032258064516 1.0 0.016129032258064516 1.0
25 0.0 0 64 512 4 1.7812 0 0.8438 5252.4961 5411.8429 5141.6921 31823 1 4683.711 0.4102 0.0062 0.0796 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.133 -0.002 0.0 1.0 0.0 0.0124 0.5312 0.4102 15.7651 52.9658 577.1581 32.7 857.9675 280.8094 0.0944 4.7678 38.5332 214.205 253.0737 1600.439 23.268 214.4456 1319.3232 0 52 61 488 451 14 37 0.08196721311475409 5 0.4918032786885246 30 0.03278688524590164 2.0 0.0082 8.7241
26 0.0 0 64 512 3 1.8125 0 0.9531 5107.9043 4684.3886 5450.6078 31689 1 4035.9699 0.4473 -0.0001 0.0667 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.132 0.0 0.0 1.0 0.0 0.0132 0.5312 0.4473 15.7054 52.9061 577.4001 32.7 857.9675 280.5674 0.097 4.8708 33.9418 188.7929 223.0849 1082.9166 25.281 189.0458 829.6739 0 53 63 504 454 17 47 0.015873015873015872 1 0.6984126984126984 44 0.031746031746031744 2.0 0.047619047619047616 3.0
27 0.0 0 64 512 3 1.7969 0 0.875 5634.0664 5882.4221 5476.1661 31801 1 5198.4542 0.3887 0.0101 0.0932 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1305 0.0 0.0 1.0 0.0 0.0144 0.5156 0.3887 15.8018 52.9791 576.4988 32.8 857.9675 281.4687 0.0964 4.9065 40.1938 233.8941 274.5002 1827.1928 24.3101 234.2096 1523.4687 0 54 61 488 434 19 52 0.13114754098360656 8 0.6557377049180327 40 0.08196721311475409 5.0 0.0084 8.6128 0.03278688524590164 2.0
28 0.0 0 64 512 4 1.9375 0 0.9531 5371.4082 5022.761 5604.2182 31785 1 4782.3049 0.4004 -0.0082 0.1177 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1222 -0.0007 0.0 1.0 0.0 0.0128 0.5156 0.4004 15.8948 53.0398 576.6206 32.8 857.9675 281.3469 0.0653 4.8129 41.537 228.2535 270.096 1483.9509 23.783 228.4932 1185.2547 0 55 62 496 429 19 64 0.0967741935483871 6 0.9032258064516129 56 0.04838709677419355 3.0 6.0259 0.04838709677419355 3.0
29 0.0 0 64 512 4 1.6094 0 0.9062 4940.75 4904.8341 4965.9269 31836 1 4570.0348 0.4121 -0.0024 0.1498 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.124 -0.0 0.0 1.0 0.0 0.0148 0.5156 0.4121 16.2064 53.3552 575.7253 32.9 857.9675 282.2422 0.0989 4.7645 34.0253 209.3135 243.7093 1375.7686 22.7461 209.5845 1104.5439 0 56 59 472 390 33 69 0.288135593220339 17 0.5084745762711864 30 0.3728813559322034 22.0 0.0075 15.5646 0.22033898305084745 13.0