laion/ablation-pymethods2test-seqnorm-15-8B
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-seqnorm-15-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-08 06:25:19 +08:00
commit 67edc8d5a6
56 changed files with 433951 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
training_logs/20260608_210110_metrics_job_639470.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_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_InvalidChatHistory,batch_errors/total_InvalidChatHistory,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError,batch_errors/avg_RuntimeError,batch_errors/total_RuntimeError,batch_errors/avg_Timeout,batch_errors/total_Timeout
0.0,0,64,512,0,0.0,0,0.0,4204.6133,3980.0401,4997.5752,27880,1,2753.0192,0.7793,-0.0112,0.1056,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1167,0.0,0.0,1.0,0.0,0.0,0.8438,0.7793,12.2631,50.3984,585.1565,31.8,857.9676,272.8111,0.1765,4.0466,31.755,151.813,183.9451,2948.9375,21.9869,152.0133,2738.9586,0,1,125,1000,979,14,16,0.032,4.0,0.08,10,0.008,1.0,0.04,5,0.008,1.0,,,,,,,,,
0.0,0,64,512,1,0.8125,0,0.8125,5306.6934,5657.698,4984.6105,31779,1,4492.8588,0.4785,0.0293,0.129,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1394,-0.0,0.0,1.0,0.0,0.0,0.625,0.4785,12.7607,50.6826,576.8641,32.8,857.9676,281.1035,0.0756,4.7377,39.2039,228.2368,267.76,1838.1447,22.259,228.4801,1543.3857,0,2,58,464,418,20,39,0.10344827586206896,6.0,0.1896551724137931,11,0.06896551724137931,4.0,0.5517241379310345,32,0.017241379310344827,1.0,11.9772,23.0244,,,,,,,
0.0,0,64,512,2,1.6406,1,1.0,5116.0566,5485.2443,4989.1181,31748,1,5080.3634,0.2559,0.0172,0.1066,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1377,-0.0,0.0,1.0,0.0,0.0,0.3594,0.2559,12.9185,50.7878,575.0807,33.0,857.9676,282.8868,0.1134,4.8467,36.4005,233.6667,270.4372,828.5581,22.9816,233.9229,530.29,0,3,63,504,481,13,20,0.031746031746031744,2.0,0.12698412698412698,8,0.015873015873015872,1.0,0.1746031746031746,11,0.015873015873015872,1.0,,,,,,,,,
0.0,0,64,512,3,1.7188,0,0.8594,4765.7383,4558.2788,4995.3951,31815,1,4154.9884,0.5254,-0.0022,0.0986,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1334,0.0,0.0,1.0,0.0,0.0,0.625,0.5254,13.0012,50.838,574.6276,33.0,857.9676,283.34,0.0786,4.6187,33.8366,202.053,236.1893,1643.3116,23.5376,202.2738,1378.9625,0,4,61,488,453,15,29,0.08196721311475409,5.0,0.14754098360655737,9,0.03278688524590164,2.0,0.29508196721311475,18,0.01639344262295082,1.0,0.007,11.8014,,,,,,,
0.0,0,64,512,4,1.8594,0,0.8906,4864.7266,5293.4787,4615.9444,31633,1,4252.8392,0.3672,0.0121,0.1054,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1324,-0.0,0.0,1.0,0.0,0.0,0.4844,0.3672,13.094,50.8868,574.0699,33.1,857.9676,283.8977,0.0636,4.5964,36.9763,209.4955,246.7664,1591.9611,23.9136,209.726,1316.6818,0,5,58,464,442,15,22,,,0.22413793103448276,13,0.017241379310344827,1.0,0.1724137931034483,10,,,,,8.9801,,,,,,
0.0,0,64,512,4,2.125,0,0.9688,5790.6836,5796.5498,5785.0421,31796,1,5065.3921,0.4902,0.0026,0.1038,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1329,-0.0,0.0,1.0,0.0,0.0,0.5781,0.4902,13.1595,50.9821,573.3127,33.2,857.9676,284.6549,0.0652,4.8477,38.9466,242.4056,281.6225,968.7238,25.1848,242.6104,657.0663,0,6,62,496,464,15,21,0.1774193548387097,11.0,0.12903225806451613,8,0.06451612903225806,4.0,0.1774193548387097,11,,,0.0074,12.5554,,,,,,,
0.0,0,64,512,4,1.8906,0,0.9219,5076.3281,4580.6522,5480.6028,31841,1,4655.3477,0.4492,-0.0017,0.0668,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1365,0.0,0.0,1.0,0.0,0.0,0.5625,0.4492,13.1735,50.9979,572.762,33.2,857.9676,285.2056,0.0629,4.6355,34.4,220.7394,255.4282,1394.3532,22.6359,220.965,1111.6508,0,7,63,504,478,15,25,0.015873015873015872,1.0,0.12698412698412698,8,,,0.2698412698412698,17,,,,,,,,,,,
0.0,0,64,512,4,2.1094,0,0.8906,6032.8496,5776.6962,6253.6073,31766,1,5542.4923,0.4629,-0.0002,0.1325,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1434,0.0,0.0,1.0,0.0,0.0,0.625,0.4629,13.1891,51.0035,571.7978,33.4,857.9676,286.1698,0.0656,4.7759,41.5188,266.819,308.6626,1826.314,24.5452,267.0779,1488.327,0,8,62,496,461,18,32,0.04838709677419355,3.0,0.14516129032258066,9,0.08064516129032258,5.0,0.2903225806451613,18,,,0.0078,13.2713,,,,,,,
0.0,0,64,512,4,1.9219,0,0.9062,5214.0684,4609.1528,5655.4932,31811,1,4602.8614,0.4219,-0.006,0.1127,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.138,0.0,0.0,1.0,0.0,0.0,0.5625,0.4219,13.1974,51.0071,571.1542,33.4,857.9676,286.8134,0.0623,4.7115,36.4913,219.5474,256.316,1383.5879,21.2289,219.762,1101.328,0,9,61,488,459,16,27,0.03278688524590164,2.0,0.13114754098360656,8,0.01639344262295082,1.0,0.29508196721311475,18,,,,,,,,,,,
0.0,0,64,512,3,1.8438,0,0.9531,4883.5527,4809.5297,4946.8478,31765,1,4293.3557,0.4609,0.0117,0.1251,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1369,-0.0,0.0,1.0,0.0,0.0,0.5938,0.4609,14.1407,51.0665,564.7126,34.2,857.9676,293.255,0.0946,4.751,37.1062,205.8864,243.3256,1131.1312,24.7025,206.1244,858.3488,0,10,61,488,460,15,23,0.08196721311475409,5.0,0.09836065573770492,6,0.01639344262295082,1.0,0.26229508196721313,16,,,0.0075,12.9056,8.8306,,,,,,
0.0,0,64,512,3,1.7812,0,0.9062,4549.2324,4530.1362,4568.4784,31819,1,3818.3797,0.502,0.0195,0.157,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1388,-0.0,0.0,1.0,0.0,0.0,0.6719,0.502,14.1364,51.0617,563.7548,34.3,857.9676,294.2128,0.0871,4.7176,34.0193,184.8761,219.1954,1502.0577,23.6183,185.0886,1254.5217,0,11,63,504,474,17,29,0.015873015873015872,1.0,0.15873015873015872,10,,,0.30158730158730157,19,,,,,,,,,,,
0.0,0,64,512,4,2.1562,0,0.875,5296.7969,4698.2873,5624.0785,31847,1,4178.7928,0.3535,0.0064,0.0936,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1414,-0.0,0.0,1.0,0.0,0.0,0.4375,0.3535,14.1368,51.059,563.1395,34.4,857.9676,294.8281,0.0852,4.7881,36.8212,203.0982,240.2245,1268.0385,21.8286,203.3178,1001.1932,0,12,63,504,453,20,42,0.14285714285714285,9.0,0.31746031746031744,20,0.1111111111111111,7.0,0.23809523809523808,15,,,0.0075,12.3179,,,,,,,
0.0,0,64,512,4,1.9688,0,0.8438,4750.25,4750.5154,4750.0386,31807,1,4514.3945,0.4434,-0.0169,0.1051,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.124,0.0,0.0,1.0,0.0,0.0,0.5938,0.4434,14.1379,51.1242,562.4609,34.4,857.9676,295.5067,0.0878,4.6646,34.6581,200.5881,235.5732,1478.8349,21.9149,200.8269,1216.6776,0,13,64,512,461,19,42,0.125,8.0,0.109375,7,0.171875,11.0,0.375,24,0.015625,1.0,,,,,,,,,
0.0,0,64,512,4,1.8281,0,0.9062,4798.502,4904.2,4721.9865,20821,1,4021.2985,0.4199,0.0107,0.1478,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1326,-0.0,0.0,1.0,0.0,0.0,0.6094,0.4199,13.9293,50.9799,562.1901,34.5,857.9676,295.7775,0.0499,3.3116,33.3015,194.2488,227.806,1529.1316,20.1055,194.4542,1277.9038,0,14,61,488,477,7,11,,,0.03278688524590164,2,0.03278688524590164,2.0,0.14754098360655737,9,,,0.0075,13.2883,,,,,,,
0.0,0,64,512,4,1.7969,0,0.8906,5064.6367,4590.1661,5650.9913,31722,1,3612.7922,0.5527,0.0086,0.1079,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1393,-0.0,0.0,1.0,0.0,0.0,0.625,0.5527,14.5292,51.5609,560.838,34.6,857.9676,297.1296,0.1119,4.7729,30.2506,177.5966,208.1631,1397.2363,22.9002,177.8003,1161.3976,0,15,59,472,368,33,68,0.3559322033898305,21.0,0.2033898305084746,12,0.8135593220338984,48.0,0.2542372881355932,15,0.23728813559322035,14.0,,,8.7705,0.01694915254237288,1.0,,,,
0.0,0,64,512,4,2.125,0,0.8906,4274.1406,4573.4162,4121.413,31809,1,4387.0225,0.3379,0.0301,0.1177,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1111,-0.0,0.0,1.0,0.0,0.0,0.5,0.3379,14.5318,51.5632,560.3275,34.7,857.9676,297.6401,0.1121,4.5533,30.9684,197.875,229.1899,2136.448,25.0381,198.109,1877.6589,0,16,60,480,435,18,36,0.13333333333333333,8.0,0.35,21,0.016666666666666666,1.0,0.36666666666666664,22,0.016666666666666666,1.0,0.0077,13.2783,,,,,,,
0.0,0,64,512,4,2.0,0,0.9688,4734.5156,5008.1053,4573.0807,20674,1,3774.2358,0.3711,0.0059,0.0758,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1229,-0.0,0.0,1.0,0.0,0.0,0.4531,0.3711,14.6272,51.7075,560.1359,34.7,857.9676,297.8317,0.081,3.4166,30.0522,179.5794,209.9197,1116.7953,19.6398,179.7862,883.8122,0,17,57,456,435,11,19,0.017543859649122806,1.0,0.15789473684210525,9,0.017543859649122806,1.0,0.24561403508771928,14,0.017543859649122806,1.0,,,,,,,,,
0.0,0,64,512,4,1.7031,0,0.8281,4471.5098,4470.4851,4472.3791,31766,1,3869.9902,0.459,0.0336,0.1621,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1329,-0.0,0.0,1.0,0.0,0.0,0.6094,0.459,14.7954,51.8759,559.9256,34.7,857.9676,298.042,0.1127,4.6919,30.7942,184.653,215.7859,2036.849,23.8428,184.8787,1792.5224,0,18,58,464,419,26,40,0.08620689655172414,5.0,0.22413793103448276,13,,,0.4827586206896552,28,,,0.0073,13.3234,,,,,,,
0.0,0,64,512,5,2.0312,0,0.9531,4740.6719,4578.8382,4823.2596,31842,1,4293.5827,0.3379,-0.002,0.1209,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1469,0.0,0.0,1.0,0.0,0.0,0.4688,0.3379,14.7972,51.8773,559.5532,34.8,857.9676,298.4144,0.1151,4.6856,35.8461,193.9452,230.1248,1344.6664,23.0847,194.1632,1086.7632,0,19,60,480,461,9,16,0.03333333333333333,2.0,0.016666666666666666,1,0.06666666666666667,4.0,0.23333333333333334,14,,,,,,,,0.016666666666666666,1.0,,
0.0,0,64,512,4,1.7031,0,0.8594,4880.1914,4838.5936,4911.2833,31680,1,3718.5085,0.4277,0.0027,0.0566,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.142,-0.0,0.0,1.0,0.0,0.0,0.5,0.4277,14.8422,51.875,558.8903,34.9,857.9676,299.0773,0.1142,4.6474,32.816,178.6089,211.7893,1843.2328,20.1983,178.8585,1606.5913,0,20,64,512,471,19,41,,,0.171875,11,,,0.46875,30,,,0.0073,12.4239,8.7038,,,,,,
0.0,0,64,512,3,1.7969,0,0.9062,4588.334,4493.3441,4642.5307,31717,1,3962.6762,0.3633,0.0029,0.1589,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1395,0.0,0.0,1.0,0.0,0.0,0.5156,0.3633,14.8433,51.876,558.6581,34.9,857.9676,299.3095,0.1126,4.5229,33.0721,192.653,226.0719,1421.8711,21.8044,192.8868,1169.4651,0,21,57,456,428,15,26,0.017543859649122806,1.0,0.07017543859649122,4,0.017543859649122806,1.0,0.38596491228070173,22,0.017543859649122806,1.0,,,,,,,,,
0.0,0,64,512,4,1.7656,0,0.875,4870.873,5241.0396,4629.6677,31739,1,4219.8385,0.3945,0.0013,0.1305,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1352,0.0,0.0,1.0,0.0,0.0,0.5312,0.3945,14.8431,51.9402,558.3341,34.9,857.9676,299.6335,0.1085,4.6972,33.7789,196.7163,230.8154,1494.0327,21.1779,196.9276,1237.3356,0,22,61,488,449,18,38,0.01639344262295082,1.0,0.13114754098360656,8,,,0.5245901639344263,32,,,0.0075,12.276,,,,,,,
0.0,0,64,512,3,1.7344,0,0.875,4640.7969,4846.2115,4500.25,31768,1,4044.2257,0.4062,0.0139,0.096,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1285,-0.0,0.0,1.0,0.0,0.0,0.5156,0.4062,15.2382,52.3806,557.8073,35.0,857.9676,300.1603,0.1114,4.6277,30.466,192.71,223.5157,1293.9556,24.0146,192.938,1041.7923,0,23,63,504,445,19,46,0.1746031746031746,11.0,0.14285714285714285,9,0.06349206349206349,4.0,0.5238095238095238,33,,,,,,0.015873015873015872,1.0,,,0.015873015873015872,1.0
0.0,0,64,512,5,2.0781,0,0.9219,4341.1699,5158.0,3913.3065,31757,1,4123.9554,0.3438,0.0106,0.1051,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1264,-0.0,0.0,1.0,0.0,0.0,0.4531,0.3438,15.2377,52.3799,556.5636,35.1,857.9676,301.404,0.1106,4.5859,32.4505,188.7186,221.4767,1641.4602,21.8273,188.9153,1393.5632,0,24,60,480,451,12,25,0.06666666666666667,4.0,0.16666666666666666,10,0.11666666666666667,7.0,0.15,9,,,0.0076,11.67,,,,,,,
0.0,0,64,512,4,1.5625,0,0.8281,4450.6797,4570.1978,4319.4057,22934,1,3289.9179,0.5234,0.0061,0.096,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1266,-0.0,0.0,1.0,0.0,0.0,0.6406,0.5234,15.0594,52.2661,557.0922,35.1,857.9676,300.8754,0.0845,3.4762,30.0472,159.5092,189.8417,1090.4692,20.7836,159.7097,876.3605,0,25,62,496,455,15,26,0.24193548387096775,15.0,0.20967741935483872,13,0.06451612903225806,4.0,0.16129032258064516,10,,,,,8.7814,,,,,,
0.0,0,64,512,4,2.0,0,0.9375,5077.3633,4987.4731,5170.1071,31764,1,4875.2722,0.5078,0.0036,0.0731,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1211,-0.0,0.0,1.0,0.0,0.0,0.5781,0.5078,15.2418,52.4453,556.3601,35.2,857.9676,301.6075,0.1143,4.8282,36.5507,227.4206,264.3124,1169.9258,21.9494,227.6469,878.8315,0,26,63,504,483,12,19,0.031746031746031744,2.0,0.06349206349206349,4,0.031746031746031744,2.0,0.20634920634920634,13,,,0.0084,11.212,,,,,,,
0.0,0,64,512,4,1.8281,0,0.875,4673.9082,4273.9848,5096.3173,31755,1,3635.6011,0.5137,0.0092,0.0966,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1351,-0.0,0.0,1.0,0.0,0.0,0.6406,0.5137,15.2407,52.4443,555.6974,35.2,857.9676,302.2701,0.1106,4.6972,30.1187,177.3769,207.8291,1096.7705,23.892,177.5995,860.3458,0,27,61,488,449,15,37,0.01639344262295082,1.0,0.19672131147540983,12,0.04918032786885246,3.0,0.3770491803278688,23,,,,,,0.01639344262295082,1.0,,,,
0.0,0,64,512,4,1.9688,0,0.8594,4745.1426,4807.2651,4700.1717,31484,1,3794.1737,0.4199,-0.0062,0.1298,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1313,0.0,0.0,1.0,0.0,0.0,0.5469,0.4199,15.2377,52.5056,554.7346,35.3,857.9676,303.233,0.1099,4.5698,33.2127,183.796,217.3223,1415.0287,21.5982,183.9994,1171.5333,0,28,59,472,421,19,41,0.1694915254237288,10.0,0.11864406779661017,7,0.0847457627118644,5.0,0.5084745762711864,30,,,0.0085,13.2233,,,,,,,
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_VerifierTimeoutError batch_errors/total_VerifierTimeoutError batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_InvalidChatHistory batch_errors/total_InvalidChatHistory batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError batch_errors/avg_RuntimeError batch_errors/total_RuntimeError batch_errors/avg_Timeout batch_errors/total_Timeout
2 0.0 0 64 512 0 0.0 0 0.0 4204.6133 3980.0401 4997.5752 27880 1 2753.0192 0.7793 -0.0112 0.1056 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1167 0.0 0.0 1.0 0.0 0.0 0.8438 0.7793 12.2631 50.3984 585.1565 31.8 857.9676 272.8111 0.1765 4.0466 31.755 151.813 183.9451 2948.9375 21.9869 152.0133 2738.9586 0 1 125 1000 979 14 16 0.032 4.0 0.08 10 0.008 1.0 0.04 5 0.008 1.0
3 0.0 0 64 512 1 0.8125 0 0.8125 5306.6934 5657.698 4984.6105 31779 1 4492.8588 0.4785 0.0293 0.129 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1394 -0.0 0.0 1.0 0.0 0.0 0.625 0.4785 12.7607 50.6826 576.8641 32.8 857.9676 281.1035 0.0756 4.7377 39.2039 228.2368 267.76 1838.1447 22.259 228.4801 1543.3857 0 2 58 464 418 20 39 0.10344827586206896 6.0 0.1896551724137931 11 0.06896551724137931 4.0 0.5517241379310345 32 0.017241379310344827 1.0 11.9772 23.0244
4 0.0 0 64 512 2 1.6406 1 1.0 5116.0566 5485.2443 4989.1181 31748 1 5080.3634 0.2559 0.0172 0.1066 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1377 -0.0 0.0 1.0 0.0 0.0 0.3594 0.2559 12.9185 50.7878 575.0807 33.0 857.9676 282.8868 0.1134 4.8467 36.4005 233.6667 270.4372 828.5581 22.9816 233.9229 530.29 0 3 63 504 481 13 20 0.031746031746031744 2.0 0.12698412698412698 8 0.015873015873015872 1.0 0.1746031746031746 11 0.015873015873015872 1.0
5 0.0 0 64 512 3 1.7188 0 0.8594 4765.7383 4558.2788 4995.3951 31815 1 4154.9884 0.5254 -0.0022 0.0986 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1334 0.0 0.0 1.0 0.0 0.0 0.625 0.5254 13.0012 50.838 574.6276 33.0 857.9676 283.34 0.0786 4.6187 33.8366 202.053 236.1893 1643.3116 23.5376 202.2738 1378.9625 0 4 61 488 453 15 29 0.08196721311475409 5.0 0.14754098360655737 9 0.03278688524590164 2.0 0.29508196721311475 18 0.01639344262295082 1.0 0.007 11.8014
6 0.0 0 64 512 4 1.8594 0 0.8906 4864.7266 5293.4787 4615.9444 31633 1 4252.8392 0.3672 0.0121 0.1054 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1324 -0.0 0.0 1.0 0.0 0.0 0.4844 0.3672 13.094 50.8868 574.0699 33.1 857.9676 283.8977 0.0636 4.5964 36.9763 209.4955 246.7664 1591.9611 23.9136 209.726 1316.6818 0 5 58 464 442 15 22 0.22413793103448276 13 0.017241379310344827 1.0 0.1724137931034483 10 8.9801
7 0.0 0 64 512 4 2.125 0 0.9688 5790.6836 5796.5498 5785.0421 31796 1 5065.3921 0.4902 0.0026 0.1038 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1329 -0.0 0.0 1.0 0.0 0.0 0.5781 0.4902 13.1595 50.9821 573.3127 33.2 857.9676 284.6549 0.0652 4.8477 38.9466 242.4056 281.6225 968.7238 25.1848 242.6104 657.0663 0 6 62 496 464 15 21 0.1774193548387097 11.0 0.12903225806451613 8 0.06451612903225806 4.0 0.1774193548387097 11 0.0074 12.5554
8 0.0 0 64 512 4 1.8906 0 0.9219 5076.3281 4580.6522 5480.6028 31841 1 4655.3477 0.4492 -0.0017 0.0668 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1365 0.0 0.0 1.0 0.0 0.0 0.5625 0.4492 13.1735 50.9979 572.762 33.2 857.9676 285.2056 0.0629 4.6355 34.4 220.7394 255.4282 1394.3532 22.6359 220.965 1111.6508 0 7 63 504 478 15 25 0.015873015873015872 1.0 0.12698412698412698 8 0.2698412698412698 17
9 0.0 0 64 512 4 2.1094 0 0.8906 6032.8496 5776.6962 6253.6073 31766 1 5542.4923 0.4629 -0.0002 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 0.1434 0.0 0.0 1.0 0.0 0.0 0.625 0.4629 13.1891 51.0035 571.7978 33.4 857.9676 286.1698 0.0656 4.7759 41.5188 266.819 308.6626 1826.314 24.5452 267.0779 1488.327 0 8 62 496 461 18 32 0.04838709677419355 3.0 0.14516129032258066 9 0.08064516129032258 5.0 0.2903225806451613 18 0.0078 13.2713
10 0.0 0 64 512 4 1.9219 0 0.9062 5214.0684 4609.1528 5655.4932 31811 1 4602.8614 0.4219 -0.006 0.1127 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.138 0.0 0.0 1.0 0.0 0.0 0.5625 0.4219 13.1974 51.0071 571.1542 33.4 857.9676 286.8134 0.0623 4.7115 36.4913 219.5474 256.316 1383.5879 21.2289 219.762 1101.328 0 9 61 488 459 16 27 0.03278688524590164 2.0 0.13114754098360656 8 0.01639344262295082 1.0 0.29508196721311475 18
11 0.0 0 64 512 3 1.8438 0 0.9531 4883.5527 4809.5297 4946.8478 31765 1 4293.3557 0.4609 0.0117 0.1251 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1369 -0.0 0.0 1.0 0.0 0.0 0.5938 0.4609 14.1407 51.0665 564.7126 34.2 857.9676 293.255 0.0946 4.751 37.1062 205.8864 243.3256 1131.1312 24.7025 206.1244 858.3488 0 10 61 488 460 15 23 0.08196721311475409 5.0 0.09836065573770492 6 0.01639344262295082 1.0 0.26229508196721313 16 0.0075 12.9056 8.8306
12 0.0 0 64 512 3 1.7812 0 0.9062 4549.2324 4530.1362 4568.4784 31819 1 3818.3797 0.502 0.0195 0.157 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1388 -0.0 0.0 1.0 0.0 0.0 0.6719 0.502 14.1364 51.0617 563.7548 34.3 857.9676 294.2128 0.0871 4.7176 34.0193 184.8761 219.1954 1502.0577 23.6183 185.0886 1254.5217 0 11 63 504 474 17 29 0.015873015873015872 1.0 0.15873015873015872 10 0.30158730158730157 19
13 0.0 0 64 512 4 2.1562 0 0.875 5296.7969 4698.2873 5624.0785 31847 1 4178.7928 0.3535 0.0064 0.0936 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1414 -0.0 0.0 1.0 0.0 0.0 0.4375 0.3535 14.1368 51.059 563.1395 34.4 857.9676 294.8281 0.0852 4.7881 36.8212 203.0982 240.2245 1268.0385 21.8286 203.3178 1001.1932 0 12 63 504 453 20 42 0.14285714285714285 9.0 0.31746031746031744 20 0.1111111111111111 7.0 0.23809523809523808 15 0.0075 12.3179
14 0.0 0 64 512 4 1.9688 0 0.8438 4750.25 4750.5154 4750.0386 31807 1 4514.3945 0.4434 -0.0169 0.1051 0.0 0.0 0.0 0.0 0.0 0.0 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 0.0 0.5938 0.4434 14.1379 51.1242 562.4609 34.4 857.9676 295.5067 0.0878 4.6646 34.6581 200.5881 235.5732 1478.8349 21.9149 200.8269 1216.6776 0 13 64 512 461 19 42 0.125 8.0 0.109375 7 0.171875 11.0 0.375 24 0.015625 1.0
15 0.0 0 64 512 4 1.8281 0 0.9062 4798.502 4904.2 4721.9865 20821 1 4021.2985 0.4199 0.0107 0.1478 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1326 -0.0 0.0 1.0 0.0 0.0 0.6094 0.4199 13.9293 50.9799 562.1901 34.5 857.9676 295.7775 0.0499 3.3116 33.3015 194.2488 227.806 1529.1316 20.1055 194.4542 1277.9038 0 14 61 488 477 7 11 0.03278688524590164 2 0.03278688524590164 2.0 0.14754098360655737 9 0.0075 13.2883
16 0.0 0 64 512 4 1.7969 0 0.8906 5064.6367 4590.1661 5650.9913 31722 1 3612.7922 0.5527 0.0086 0.1079 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1393 -0.0 0.0 1.0 0.0 0.0 0.625 0.5527 14.5292 51.5609 560.838 34.6 857.9676 297.1296 0.1119 4.7729 30.2506 177.5966 208.1631 1397.2363 22.9002 177.8003 1161.3976 0 15 59 472 368 33 68 0.3559322033898305 21.0 0.2033898305084746 12 0.8135593220338984 48.0 0.2542372881355932 15 0.23728813559322035 14.0 8.7705 0.01694915254237288 1.0
17 0.0 0 64 512 4 2.125 0 0.8906 4274.1406 4573.4162 4121.413 31809 1 4387.0225 0.3379 0.0301 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 0.1111 -0.0 0.0 1.0 0.0 0.0 0.5 0.3379 14.5318 51.5632 560.3275 34.7 857.9676 297.6401 0.1121 4.5533 30.9684 197.875 229.1899 2136.448 25.0381 198.109 1877.6589 0 16 60 480 435 18 36 0.13333333333333333 8.0 0.35 21 0.016666666666666666 1.0 0.36666666666666664 22 0.016666666666666666 1.0 0.0077 13.2783
18 0.0 0 64 512 4 2.0 0 0.9688 4734.5156 5008.1053 4573.0807 20674 1 3774.2358 0.3711 0.0059 0.0758 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1229 -0.0 0.0 1.0 0.0 0.0 0.4531 0.3711 14.6272 51.7075 560.1359 34.7 857.9676 297.8317 0.081 3.4166 30.0522 179.5794 209.9197 1116.7953 19.6398 179.7862 883.8122 0 17 57 456 435 11 19 0.017543859649122806 1.0 0.15789473684210525 9 0.017543859649122806 1.0 0.24561403508771928 14 0.017543859649122806 1.0
19 0.0 0 64 512 4 1.7031 0 0.8281 4471.5098 4470.4851 4472.3791 31766 1 3869.9902 0.459 0.0336 0.1621 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1329 -0.0 0.0 1.0 0.0 0.0 0.6094 0.459 14.7954 51.8759 559.9256 34.7 857.9676 298.042 0.1127 4.6919 30.7942 184.653 215.7859 2036.849 23.8428 184.8787 1792.5224 0 18 58 464 419 26 40 0.08620689655172414 5.0 0.22413793103448276 13 0.4827586206896552 28 0.0073 13.3234
20 0.0 0 64 512 5 2.0312 0 0.9531 4740.6719 4578.8382 4823.2596 31842 1 4293.5827 0.3379 -0.002 0.1209 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1469 0.0 0.0 1.0 0.0 0.0 0.4688 0.3379 14.7972 51.8773 559.5532 34.8 857.9676 298.4144 0.1151 4.6856 35.8461 193.9452 230.1248 1344.6664 23.0847 194.1632 1086.7632 0 19 60 480 461 9 16 0.03333333333333333 2.0 0.016666666666666666 1 0.06666666666666667 4.0 0.23333333333333334 14 0.016666666666666666 1.0
21 0.0 0 64 512 4 1.7031 0 0.8594 4880.1914 4838.5936 4911.2833 31680 1 3718.5085 0.4277 0.0027 0.0566 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.142 -0.0 0.0 1.0 0.0 0.0 0.5 0.4277 14.8422 51.875 558.8903 34.9 857.9676 299.0773 0.1142 4.6474 32.816 178.6089 211.7893 1843.2328 20.1983 178.8585 1606.5913 0 20 64 512 471 19 41 0.171875 11 0.46875 30 0.0073 12.4239 8.7038
22 0.0 0 64 512 3 1.7969 0 0.9062 4588.334 4493.3441 4642.5307 31717 1 3962.6762 0.3633 0.0029 0.1589 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1395 0.0 0.0 1.0 0.0 0.0 0.5156 0.3633 14.8433 51.876 558.6581 34.9 857.9676 299.3095 0.1126 4.5229 33.0721 192.653 226.0719 1421.8711 21.8044 192.8868 1169.4651 0 21 57 456 428 15 26 0.017543859649122806 1.0 0.07017543859649122 4 0.017543859649122806 1.0 0.38596491228070173 22 0.017543859649122806 1.0
23 0.0 0 64 512 4 1.7656 0 0.875 4870.873 5241.0396 4629.6677 31739 1 4219.8385 0.3945 0.0013 0.1305 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1352 0.0 0.0 1.0 0.0 0.0 0.5312 0.3945 14.8431 51.9402 558.3341 34.9 857.9676 299.6335 0.1085 4.6972 33.7789 196.7163 230.8154 1494.0327 21.1779 196.9276 1237.3356 0 22 61 488 449 18 38 0.01639344262295082 1.0 0.13114754098360656 8 0.5245901639344263 32 0.0075 12.276
24 0.0 0 64 512 3 1.7344 0 0.875 4640.7969 4846.2115 4500.25 31768 1 4044.2257 0.4062 0.0139 0.096 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1285 -0.0 0.0 1.0 0.0 0.0 0.5156 0.4062 15.2382 52.3806 557.8073 35.0 857.9676 300.1603 0.1114 4.6277 30.466 192.71 223.5157 1293.9556 24.0146 192.938 1041.7923 0 23 63 504 445 19 46 0.1746031746031746 11.0 0.14285714285714285 9 0.06349206349206349 4.0 0.5238095238095238 33 0.015873015873015872 1.0 0.015873015873015872 1.0
25 0.0 0 64 512 5 2.0781 0 0.9219 4341.1699 5158.0 3913.3065 31757 1 4123.9554 0.3438 0.0106 0.1051 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1264 -0.0 0.0 1.0 0.0 0.0 0.4531 0.3438 15.2377 52.3799 556.5636 35.1 857.9676 301.404 0.1106 4.5859 32.4505 188.7186 221.4767 1641.4602 21.8273 188.9153 1393.5632 0 24 60 480 451 12 25 0.06666666666666667 4.0 0.16666666666666666 10 0.11666666666666667 7.0 0.15 9 0.0076 11.67
26 0.0 0 64 512 4 1.5625 0 0.8281 4450.6797 4570.1978 4319.4057 22934 1 3289.9179 0.5234 0.0061 0.096 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1266 -0.0 0.0 1.0 0.0 0.0 0.6406 0.5234 15.0594 52.2661 557.0922 35.1 857.9676 300.8754 0.0845 3.4762 30.0472 159.5092 189.8417 1090.4692 20.7836 159.7097 876.3605 0 25 62 496 455 15 26 0.24193548387096775 15.0 0.20967741935483872 13 0.06451612903225806 4.0 0.16129032258064516 10 8.7814
27 0.0 0 64 512 4 2.0 0 0.9375 5077.3633 4987.4731 5170.1071 31764 1 4875.2722 0.5078 0.0036 0.0731 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1211 -0.0 0.0 1.0 0.0 0.0 0.5781 0.5078 15.2418 52.4453 556.3601 35.2 857.9676 301.6075 0.1143 4.8282 36.5507 227.4206 264.3124 1169.9258 21.9494 227.6469 878.8315 0 26 63 504 483 12 19 0.031746031746031744 2.0 0.06349206349206349 4 0.031746031746031744 2.0 0.20634920634920634 13 0.0084 11.212
28 0.0 0 64 512 4 1.8281 0 0.875 4673.9082 4273.9848 5096.3173 31755 1 3635.6011 0.5137 0.0092 0.0966 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1351 -0.0 0.0 1.0 0.0 0.0 0.6406 0.5137 15.2407 52.4443 555.6974 35.2 857.9676 302.2701 0.1106 4.6972 30.1187 177.3769 207.8291 1096.7705 23.892 177.5995 860.3458 0 27 61 488 449 15 37 0.01639344262295082 1.0 0.19672131147540983 12 0.04918032786885246 3.0 0.3770491803278688 23 0.01639344262295082 1.0
29 0.0 0 64 512 4 1.9688 0 0.8594 4745.1426 4807.2651 4700.1717 31484 1 3794.1737 0.4199 -0.0062 0.1298 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1313 0.0 0.0 1.0 0.0 0.0 0.5469 0.4199 15.2377 52.5056 554.7346 35.3 857.9676 303.233 0.1099 4.5698 33.2127 183.796 217.3223 1415.0287 21.5982 183.9994 1171.5333 0 28 59 472 421 19 41 0.1694915254237288 10.0 0.11864406779661017 7 0.0847457627118644 5.0 0.5084745762711864 30 0.0085 13.2233