laion/ablation-pymethods2test-shaped-45-8B
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-shaped-45-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 17:31:01 +08:00
commit 68d3be9a84
35 changed files with 261550 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
training_logs/20260612_220132_metrics_job_628823.csv Normal file
View File

@@ -0,0 +1,28 @@
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_RuntimeError,batch_errors/total_RuntimeError,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,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,timing/save_hf_model,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError
0.0,0,64,512,0,0.0,0,0.0,4241.7871,4075.3858,4797.3983,23591,1316,2862.5754,0.7695,-0.0052,0.0794,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1166,0.0,0.0,1.0,0.0,0.011,0.8281,0.7695,9.7812,50.2029,557.7402,35.0,857.9676,300.2274,0.1582,3.54,30.8444,153.8172,185.0373,3057.5532,21.5959,154.0342,2847.3797,0,1,122,976,943,19,22,0.05737704918032787,7.0,0.03278688524590164,4.0,0.09016393442622951,11,0.09836065573770492,12,0.01639344262295082,2.0,,,,,,,
0.0,0,64,512,1,0.7969,0,0.7969,5136.0195,4962.6652,5267.6735,31834,1,4862.5801,0.4316,0.0011,0.134,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.131,-0.004,0.0,1.0,0.0,0.0187,0.5781,0.4316,12.7484,50.6157,552.2059,35.6,857.9676,305.7617,0.0781,4.6459,40.502,231.1003,271.9977,1974.5752,23.421,231.4172,1674.5086,0,2,57,456,406,20,41,0.03508771929824561,2.0,0.14035087719298245,8.0,0.40350877192982454,23,0.3684210526315789,21,0.03508771929824561,2.0,15.355,26.7429,,,,,
0.0,0,64,512,2,1.7656,0,0.9844,5346.2324,5970.6364,5049.3256,31778,1,5290.9126,0.3223,0.0173,0.1254,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.135,-0.0022,0.0,1.0,0.0,0.0189,0.4375,0.3223,13.0774,50.9789,551.3358,35.7,857.9676,306.6318,0.0773,4.8038,38.0803,249.186,287.5805,764.5942,23.4573,249.4225,448.7478,0,3,63,504,479,12,20,0.015873015873015872,1.0,0.06349206349206349,4.0,0.031746031746031744,2,0.23809523809523808,15,0.047619047619047616,3.0,,,,,,,
0.0,0,64,512,3,1.7188,0,0.8281,4813.1621,4440.1283,5107.9371,31784,1,3944.3059,0.4414,-0.0041,0.0914,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.132,-0.0011,0.0,1.0,0.0,0.0155,0.5625,0.4414,13.3076,51.1494,551.3209,35.7,857.9676,306.6467,0.0928,4.6191,33.0654,189.1437,222.5601,1688.5406,24.6375,189.4014,1436.7179,0,4,62,496,477,10,13,0.03225806451612903,2.0,0.08064516129032258,5.0,0.04838709677419355,3,0.16129032258064516,10,0.016129032258064516,1.0,0.0097,12.4636,0.016129032258064516,1.0,,,
0.0,0,64,512,3,1.8438,0,0.9062,5021.8789,4977.0343,5051.5812,31762,1,4320.8043,0.3984,-0.0094,0.1029,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1328,-0.0003,0.0,1.0,0.0,0.0164,0.5,0.3984,13.339,51.142,550.5958,35.8,857.9676,307.3718,0.0931,4.6241,34.9145,208.2892,243.5698,1371.9939,23.0421,208.5618,1100.7494,0,5,62,496,458,21,23,0.16129032258064516,10.0,0.08064516129032258,5.0,0.1774193548387097,11,0.16129032258064516,10,0.04838709677419355,3.0,,,0.016129032258064516,1.0,6.5931,,
0.0,0,64,512,4,2.3438,0,0.9688,5018.002,5652.1322,4449.6333,31841,1,4784.8239,0.4727,0.0138,0.0894,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1342,0.0,0.0,1.0,0.0,0.0171,0.5781,0.4727,13.5079,51.2928,550.2794,35.9,857.9676,307.6882,0.0927,4.6639,34.121,232.6051,267.1017,1345.2906,24.546,232.8873,1048.9721,0,6,63,504,482,14,13,0.031746031746031744,2.0,0.1111111111111111,7.0,0.09523809523809523,6,0.07936507936507936,5,0.031746031746031744,2.0,0.0089,12.8392,,,,,
0.0,0,64,512,3,1.8125,0,0.9531,4852.8496,4692.7007,5037.2227,31647,1,3900.6488,0.5352,-0.0007,0.0857,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1311,-0.0022,0.0,1.0,0.0,0.0132,0.625,0.5352,13.5188,51.2968,549.0931,36.0,857.9676,308.8745,0.0957,4.5759,33.3939,184.9605,218.7359,1358.4053,24.0379,185.2458,1111.0487,0,7,61,488,461,16,21,,,0.09836065573770492,6.0,0.16393442622950818,10,0.16393442622950818,10,0.01639344262295082,1.0,,,,,,,
0.0,0,64,512,4,2.0,0,0.9219,5649.5059,5423.0472,5838.6272,31788,1,4651.1216,0.4551,0.0,0.0814,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1344,-0.0016,0.0,1.0,0.0,0.0117,0.5625,0.4551,15.4496,51.3726,547.1078,36.2,857.9676,310.8597,0.0999,4.7367,37.461,232.245,270.1439,1520.6114,21.4921,232.5826,1224.2314,0,8,63,504,471,21,23,0.06349206349206349,4.0,0.07936507936507936,5.0,0.12698412698412698,8,0.14285714285714285,9,0.09523809523809523,6.0,0.0097,10.0987,0.015873015873015872,1.0,,,
0.0,0,64,512,4,2.0469,0,0.9531,4865.623,4560.4394,5058.0637,31693,1,3889.0343,0.3867,-0.0001,0.0981,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1351,-0.0025,0.0,1.0,0.0,0.0152,0.4844,0.3867,15.5833,51.5586,546.65,36.3,857.9676,311.3176,0.0664,4.7228,30.1827,183.2597,213.7875,1325.4585,23.4,183.538,1083.5439,0,9,64,512,477,22,28,0.078125,5.0,0.015625,1.0,0.15625,10,0.28125,18,,,,,0.015625,1.0,,,
0.0,0,64,512,4,1.9531,0,0.9062,5185.9395,5227.2298,5150.9097,31844,1,4598.2853,0.459,0.0051,0.1075,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1325,-0.002,0.0,1.0,0.0,0.0144,0.5625,0.459,15.7477,51.6836,541.5659,36.9,857.9676,316.4017,0.0955,4.7965,34.9537,220.1504,255.492,1527.1207,22.9993,220.4423,1243.8262,0,10,62,496,471,15,20,0.08064516129032258,5.0,,,0.1774193548387097,11,0.16129032258064516,10,,,0.0086,10.0791,,,5.9651,,
0.0,0,64,512,4,1.8438,0,0.9219,4329.0117,4218.6929,4437.6202,31713,1,3790.1917,0.4961,0.0223,0.1593,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1335,-0.002,0.0,1.0,0.0,0.0183,0.6875,0.4961,15.8199,51.8009,540.3857,37.0,857.9676,317.5818,0.1027,4.575,31.1433,184.9552,216.4595,1372.1162,23.1094,185.213,1127.9659,0,11,64,512,473,18,32,0.109375,7.0,,,0.15625,10,0.234375,15,0.109375,7.0,,,,,,,
0.0,0,64,512,4,1.9531,0,0.8906,5470.543,5430.5524,5498.351,31766,1,4969.3126,0.4102,0.0051,0.0633,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1327,0.0,0.0,1.0,0.0,0.0102,0.5,0.4102,15.836,51.9335,540.7026,37.0,857.9676,317.265,0.0636,4.7368,39.2476,233.302,272.9019,1553.8245,24.5439,233.5903,1251.6375,0,12,62,496,467,10,28,0.016129032258064516,1.0,,,0.03225806451612903,2,0.20967741935483872,13,0.1935483870967742,12.0,0.0086,10.2218,,,,,
0.0,0,64,512,4,1.8594,0,0.8906,5487.1582,5010.1456,5808.2843,31729,1,4970.1199,0.4023,0.009,0.1282,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1277,-0.0,0.0,1.0,0.0,0.0177,0.5781,0.4023,15.8658,52.0009,539.8482,37.1,857.9676,318.1194,0.0751,4.7043,37.1381,239.7455,277.2487,1401.1367,22.7271,240.035,1096.4525,0,13,63,504,464,19,40,,,,,0.14285714285714285,9,0.36507936507936506,23,0.12698412698412698,8.0,,,,,,,
0.0,0,64,512,4,1.9062,0,0.9531,4640.0664,4961.6479,4410.9799,31820,1,4384.7946,0.416,0.0148,0.163,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1246,-0.0,0.0,1.0,0.0,0.0193,0.5625,0.416,15.9154,52.0623,539.8487,37.1,857.9676,318.1189,0.1162,4.593,34.1775,207.9322,242.5469,1386.3317,25.7294,208.2527,1113.4543,0,14,62,496,467,13,26,0.04838709677419355,3.0,,,0.1935483870967742,12,0.20967741935483872,13,0.016129032258064516,1.0,0.0091,10.0526,,,,,
0.0,0,64,512,4,1.8594,0,0.875,4959.9883,4604.0645,5294.3409,31749,1,4215.4661,0.4844,0.0001,0.0559,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1272,0.0,0.0,1.0,0.0,0.0127,0.5625,0.4844,16.1625,52.2504,538.8073,37.2,857.9676,319.1603,0.0636,4.6414,35.2075,192.5546,228.0862,1415.7002,22.3144,192.8148,1160.6533,0,15,64,512,477,15,27,0.125,8.0,,,0.140625,9,0.25,16,0.03125,2.0,,,,,5.9694,,
0.0,0,64,512,4,1.9531,0,0.9375,4935.9297,4670.6494,5154.0071,31688,1,4438.984,0.4512,-0.0031,0.1282,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1259,0.0,0.0,1.0,0.0,0.0216,0.5938,0.4512,16.0255,52.1877,538.5174,37.2,857.9676,319.4502,0.0869,4.7249,35.9695,214.2222,250.5637,1435.3243,23.4955,214.5068,1156.5324,0,16,60,480,439,15,41,,,,,0.16666666666666666,10,0.55,33,0.05,3.0,0.0083,10.2996,,,,,
0.0,0,64,512,4,1.7969,0,0.9062,5206.5488,5225.9731,5195.4663,31786,1,5375.2695,0.3633,0.0198,0.1135,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1261,0.0,0.0,1.0,0.0,0.0167,0.5156,0.3633,16.2097,52.3779,538.9144,37.2,857.9676,319.0532,0.0687,4.7438,38.0638,241.4504,279.8938,1238.734,23.4055,241.761,930.6855,0,17,62,496,481,10,15,,,,,0.12903225806451613,8,0.11290322580645161,7,0.04838709677419355,3.0,,,,,,,
0.0,0,64,512,4,1.9219,0,0.8594,4874.4434,4437.0435,5301.7104,31707,1,4182.0643,0.4941,-0.0129,0.1161,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1263,0.0,0.0,1.0,0.0,0.0157,0.6094,0.4941,16.2898,52.5652,539.6708,37.1,857.9676,318.2968,0.068,4.5999,33.8542,201.1248,235.3637,1604.4634,26.2847,201.4412,1338.2106,0,18,60,480,439,17,41,,,,,0.11666666666666667,7,0.5666666666666667,34,0.03333333333333333,2.0,0.009,9.9735,,,,,
0.0,0,64,512,4,2.0781,0,0.875,5017.2695,4838.5484,5119.2393,31727,1,4684.6068,0.3633,-0.0111,0.1336,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1366,-0.0,0.0,1.0,0.0,0.0202,0.4844,0.3633,16.2083,52.4408,539.2532,37.1,857.9676,318.7144,0.1006,4.7377,35.1526,227.4842,263.0104,1704.6389,21.5753,227.7566,1415.308,0,19,63,504,466,14,36,,,,,0.06349206349206349,4,0.49206349206349204,31,0.031746031746031744,2.0,,,0.031746031746031744,2.0,,,
0.0,0,64,512,3,1.6875,0,0.9219,4813.3398,4682.4186,4879.5706,31781,1,4023.4961,0.3359,-0.002,0.0598,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1335,-0.0005,0.0,1.0,0.0,0.0148,0.4219,0.3359,16.389,52.692,539.0041,37.2,857.9676,318.9635,0.0634,4.6853,31.7718,184.2284,216.3535,1243.9949,24.9441,184.518,998.0071,0,20,62,496,452,15,39,0.06451612903225806,4.0,,,0.08064516129032258,5,0.5483870967741935,34,0.016129032258064516,1.0,0.0082,10.7804,0.016129032258064516,1.0,5.7822,,
0.0,0,64,512,4,1.875,0,0.9219,4842.0918,4761.3186,4905.9196,31794,1,4212.6536,0.4414,0.0036,0.1383,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1256,-0.0013,0.0,1.0,0.0,0.0203,0.5781,0.4414,16.4531,52.6938,538.5048,37.2,857.9676,319.4628,0.0643,4.6969,34.2897,194.8264,229.4509,1850.931,22.0367,195.0966,1594.7419,0,21,65,520,474,20,46,,,,,0.09230769230769231,6,0.6153846153846154,40,,,,,,,,,
0.0,0,64,512,3,1.4688,0,0.8281,4904.0176,4757.8386,5016.8131,31774,1,5193.9333,0.4355,0.0091,0.0904,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1243,-0.0,0.0,1.0,0.0,0.0108,0.5156,0.4355,16.7661,53.0065,538.0942,37.3,857.9676,319.8734,0.0718,4.7325,38.9414,247.2972,286.6118,1397.2504,25.3533,247.5984,1080.5473,0,22,64,512,461,16,49,0.015625,1.0,,,0.109375,7,0.609375,39,0.046875,3.0,0.0087,10.301,0.015625,1.0,,,
0.0,0,64,512,3,1.7656,0,0.9531,4420.6699,4579.8023,4340.1676,31656,1,4118.4741,0.3359,0.0061,0.1162,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1221,-0.0006,0.0,1.0,0.0,0.0226,0.5,0.3359,17.1543,53.3796,536.8373,37.4,857.9676,321.1303,0.0927,4.5604,29.1154,184.7184,214.174,1504.7633,24.6211,184.9654,1261.4005,0,23,63,504,452,15,43,0.12698412698412698,8.0,,,0.06349206349206349,4,0.5714285714285714,36,0.047619047619047616,3.0,,,0.015873015873015872,1.0,,,
0.0,0,64,512,3,1.7969,0,0.9531,4574.207,4892.4115,4286.7584,31701,1,3895.9681,0.4746,-0.001,0.1171,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1198,-0.0,0.0,1.0,0.0,0.0165,0.5625,0.4746,17.1777,53.3798,538.1989,37.3,857.9676,319.7687,0.094,4.6418,30.5187,182.2819,213.1498,1700.5271,21.8175,182.5366,1460.9109,0,24,61,488,423,25,55,0.14754098360655737,9.0,,,0.14754098360655737,9,0.5245901639344263,32,0.22950819672131148,14.0,0.0094,10.6318,0.01639344262295082,1.0,,,
0.0,0,64,512,3,1.6719,0,0.9219,4631.207,5387.3656,4199.7791,31761,1,4549.8186,0.3633,0.0269,0.1247,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.119,-0.0036,0.0,1.0,0.0,0.0181,0.5,0.3633,17.1838,53.3813,537.2989,37.4,857.9676,320.6687,0.0787,4.5345,32.4627,208.7999,241.6056,1624.9161,19.6067,209.0637,1359.1612,0,25,53,424,376,16,45,0.05660377358490566,3.0,,,0.37735849056603776,20,0.6415094339622641,34,0.03773584905660377,2.0,,,,,5.9782,0.018867924528301886,1.0
0.0,0,64,512,4,1.7344,0,0.9844,3893.377,3932.6115,3846.765,31762,1,3658.4465,0.543,0.0189,0.1012,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1126,-0.0039,0.0,1.0,0.0,0.0164,0.6719,0.543,17.183,53.3804,537.6219,37.3,857.9676,320.3456,0.0913,4.5212,25.6794,169.8466,195.8585,995.4217,21.6119,170.0873,773.4247,0,26,58,464,433,13,26,0.05172413793103448,3.0,,,0.13793103448275862,8,0.29310344827586204,17,0.034482758620689655,2.0,0.0086,10.3518,0.034482758620689655,2.0,,,
0.0,0,64,512,4,2.0781,0,0.9375,4736.4414,5049.1301,4390.2963,20191,1,3483.9669,0.5254,0.0145,0.1444,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1249,-0.0042,0.0,1.0,0.0,0.0159,0.6406,0.5254,16.9689,53.1663,537.6146,37.3,857.9676,320.353,0.0664,3.2159,28.0361,184.7269,213.0974,1234.7892,24.6173,184.9943,993.8523,0,27,44,352,283,23,48,0.38636363636363635,17.0,,,0.3181818181818182,14,0.5909090909090909,26,0.9090909090909091,40.0,,,0.06818181818181818,3.0,,0.022727272727272728,1.0
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_VerifierTimeoutError batch_errors/total_VerifierTimeoutError batch_errors/avg_RuntimeError batch_errors/total_RuntimeError 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 batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError timing/save_hf_model batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError
2 0.0 0 64 512 0 0.0 0 0.0 4241.7871 4075.3858 4797.3983 23591 1316 2862.5754 0.7695 -0.0052 0.0794 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1166 0.0 0.0 1.0 0.0 0.011 0.8281 0.7695 9.7812 50.2029 557.7402 35.0 857.9676 300.2274 0.1582 3.54 30.8444 153.8172 185.0373 3057.5532 21.5959 154.0342 2847.3797 0 1 122 976 943 19 22 0.05737704918032787 7.0 0.03278688524590164 4.0 0.09016393442622951 11 0.09836065573770492 12 0.01639344262295082 2.0
3 0.0 0 64 512 1 0.7969 0 0.7969 5136.0195 4962.6652 5267.6735 31834 1 4862.5801 0.4316 0.0011 0.134 -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 0.131 -0.004 0.0 1.0 0.0 0.0187 0.5781 0.4316 12.7484 50.6157 552.2059 35.6 857.9676 305.7617 0.0781 4.6459 40.502 231.1003 271.9977 1974.5752 23.421 231.4172 1674.5086 0 2 57 456 406 20 41 0.03508771929824561 2.0 0.14035087719298245 8.0 0.40350877192982454 23 0.3684210526315789 21 0.03508771929824561 2.0 15.355 26.7429
4 0.0 0 64 512 2 1.7656 0 0.9844 5346.2324 5970.6364 5049.3256 31778 1 5290.9126 0.3223 0.0173 0.1254 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.135 -0.0022 0.0 1.0 0.0 0.0189 0.4375 0.3223 13.0774 50.9789 551.3358 35.7 857.9676 306.6318 0.0773 4.8038 38.0803 249.186 287.5805 764.5942 23.4573 249.4225 448.7478 0 3 63 504 479 12 20 0.015873015873015872 1.0 0.06349206349206349 4.0 0.031746031746031744 2 0.23809523809523808 15 0.047619047619047616 3.0
5 0.0 0 64 512 3 1.7188 0 0.8281 4813.1621 4440.1283 5107.9371 31784 1 3944.3059 0.4414 -0.0041 0.0914 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.132 -0.0011 0.0 1.0 0.0 0.0155 0.5625 0.4414 13.3076 51.1494 551.3209 35.7 857.9676 306.6467 0.0928 4.6191 33.0654 189.1437 222.5601 1688.5406 24.6375 189.4014 1436.7179 0 4 62 496 477 10 13 0.03225806451612903 2.0 0.08064516129032258 5.0 0.04838709677419355 3 0.16129032258064516 10 0.016129032258064516 1.0 0.0097 12.4636 0.016129032258064516 1.0
6 0.0 0 64 512 3 1.8438 0 0.9062 5021.8789 4977.0343 5051.5812 31762 1 4320.8043 0.3984 -0.0094 0.1029 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1328 -0.0003 0.0 1.0 0.0 0.0164 0.5 0.3984 13.339 51.142 550.5958 35.8 857.9676 307.3718 0.0931 4.6241 34.9145 208.2892 243.5698 1371.9939 23.0421 208.5618 1100.7494 0 5 62 496 458 21 23 0.16129032258064516 10.0 0.08064516129032258 5.0 0.1774193548387097 11 0.16129032258064516 10 0.04838709677419355 3.0 0.016129032258064516 1.0 6.5931
7 0.0 0 64 512 4 2.3438 0 0.9688 5018.002 5652.1322 4449.6333 31841 1 4784.8239 0.4727 0.0138 0.0894 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1342 0.0 0.0 1.0 0.0 0.0171 0.5781 0.4727 13.5079 51.2928 550.2794 35.9 857.9676 307.6882 0.0927 4.6639 34.121 232.6051 267.1017 1345.2906 24.546 232.8873 1048.9721 0 6 63 504 482 14 13 0.031746031746031744 2.0 0.1111111111111111 7.0 0.09523809523809523 6 0.07936507936507936 5 0.031746031746031744 2.0 0.0089 12.8392
8 0.0 0 64 512 3 1.8125 0 0.9531 4852.8496 4692.7007 5037.2227 31647 1 3900.6488 0.5352 -0.0007 0.0857 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1311 -0.0022 0.0 1.0 0.0 0.0132 0.625 0.5352 13.5188 51.2968 549.0931 36.0 857.9676 308.8745 0.0957 4.5759 33.3939 184.9605 218.7359 1358.4053 24.0379 185.2458 1111.0487 0 7 61 488 461 16 21 0.09836065573770492 6.0 0.16393442622950818 10 0.16393442622950818 10 0.01639344262295082 1.0
9 0.0 0 64 512 4 2.0 0 0.9219 5649.5059 5423.0472 5838.6272 31788 1 4651.1216 0.4551 0.0 0.0814 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1344 -0.0016 0.0 1.0 0.0 0.0117 0.5625 0.4551 15.4496 51.3726 547.1078 36.2 857.9676 310.8597 0.0999 4.7367 37.461 232.245 270.1439 1520.6114 21.4921 232.5826 1224.2314 0 8 63 504 471 21 23 0.06349206349206349 4.0 0.07936507936507936 5.0 0.12698412698412698 8 0.14285714285714285 9 0.09523809523809523 6.0 0.0097 10.0987 0.015873015873015872 1.0
10 0.0 0 64 512 4 2.0469 0 0.9531 4865.623 4560.4394 5058.0637 31693 1 3889.0343 0.3867 -0.0001 0.0981 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1351 -0.0025 0.0 1.0 0.0 0.0152 0.4844 0.3867 15.5833 51.5586 546.65 36.3 857.9676 311.3176 0.0664 4.7228 30.1827 183.2597 213.7875 1325.4585 23.4 183.538 1083.5439 0 9 64 512 477 22 28 0.078125 5.0 0.015625 1.0 0.15625 10 0.28125 18 0.015625 1.0
11 0.0 0 64 512 4 1.9531 0 0.9062 5185.9395 5227.2298 5150.9097 31844 1 4598.2853 0.459 0.0051 0.1075 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1325 -0.002 0.0 1.0 0.0 0.0144 0.5625 0.459 15.7477 51.6836 541.5659 36.9 857.9676 316.4017 0.0955 4.7965 34.9537 220.1504 255.492 1527.1207 22.9993 220.4423 1243.8262 0 10 62 496 471 15 20 0.08064516129032258 5.0 0.1774193548387097 11 0.16129032258064516 10 0.0086 10.0791 5.9651
12 0.0 0 64 512 4 1.8438 0 0.9219 4329.0117 4218.6929 4437.6202 31713 1 3790.1917 0.4961 0.0223 0.1593 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1335 -0.002 0.0 1.0 0.0 0.0183 0.6875 0.4961 15.8199 51.8009 540.3857 37.0 857.9676 317.5818 0.1027 4.575 31.1433 184.9552 216.4595 1372.1162 23.1094 185.213 1127.9659 0 11 64 512 473 18 32 0.109375 7.0 0.15625 10 0.234375 15 0.109375 7.0
13 0.0 0 64 512 4 1.9531 0 0.8906 5470.543 5430.5524 5498.351 31766 1 4969.3126 0.4102 0.0051 0.0633 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1327 0.0 0.0 1.0 0.0 0.0102 0.5 0.4102 15.836 51.9335 540.7026 37.0 857.9676 317.265 0.0636 4.7368 39.2476 233.302 272.9019 1553.8245 24.5439 233.5903 1251.6375 0 12 62 496 467 10 28 0.016129032258064516 1.0 0.03225806451612903 2 0.20967741935483872 13 0.1935483870967742 12.0 0.0086 10.2218
14 0.0 0 64 512 4 1.8594 0 0.8906 5487.1582 5010.1456 5808.2843 31729 1 4970.1199 0.4023 0.009 0.1282 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1277 -0.0 0.0 1.0 0.0 0.0177 0.5781 0.4023 15.8658 52.0009 539.8482 37.1 857.9676 318.1194 0.0751 4.7043 37.1381 239.7455 277.2487 1401.1367 22.7271 240.035 1096.4525 0 13 63 504 464 19 40 0.14285714285714285 9 0.36507936507936506 23 0.12698412698412698 8.0
15 0.0 0 64 512 4 1.9062 0 0.9531 4640.0664 4961.6479 4410.9799 31820 1 4384.7946 0.416 0.0148 0.163 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1246 -0.0 0.0 1.0 0.0 0.0193 0.5625 0.416 15.9154 52.0623 539.8487 37.1 857.9676 318.1189 0.1162 4.593 34.1775 207.9322 242.5469 1386.3317 25.7294 208.2527 1113.4543 0 14 62 496 467 13 26 0.04838709677419355 3.0 0.1935483870967742 12 0.20967741935483872 13 0.016129032258064516 1.0 0.0091 10.0526
16 0.0 0 64 512 4 1.8594 0 0.875 4959.9883 4604.0645 5294.3409 31749 1 4215.4661 0.4844 0.0001 0.0559 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1272 0.0 0.0 1.0 0.0 0.0127 0.5625 0.4844 16.1625 52.2504 538.8073 37.2 857.9676 319.1603 0.0636 4.6414 35.2075 192.5546 228.0862 1415.7002 22.3144 192.8148 1160.6533 0 15 64 512 477 15 27 0.125 8.0 0.140625 9 0.25 16 0.03125 2.0 5.9694
17 0.0 0 64 512 4 1.9531 0 0.9375 4935.9297 4670.6494 5154.0071 31688 1 4438.984 0.4512 -0.0031 0.1282 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1259 0.0 0.0 1.0 0.0 0.0216 0.5938 0.4512 16.0255 52.1877 538.5174 37.2 857.9676 319.4502 0.0869 4.7249 35.9695 214.2222 250.5637 1435.3243 23.4955 214.5068 1156.5324 0 16 60 480 439 15 41 0.16666666666666666 10 0.55 33 0.05 3.0 0.0083 10.2996
18 0.0 0 64 512 4 1.7969 0 0.9062 5206.5488 5225.9731 5195.4663 31786 1 5375.2695 0.3633 0.0198 0.1135 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1261 0.0 0.0 1.0 0.0 0.0167 0.5156 0.3633 16.2097 52.3779 538.9144 37.2 857.9676 319.0532 0.0687 4.7438 38.0638 241.4504 279.8938 1238.734 23.4055 241.761 930.6855 0 17 62 496 481 10 15 0.12903225806451613 8 0.11290322580645161 7 0.04838709677419355 3.0
19 0.0 0 64 512 4 1.9219 0 0.8594 4874.4434 4437.0435 5301.7104 31707 1 4182.0643 0.4941 -0.0129 0.1161 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1263 0.0 0.0 1.0 0.0 0.0157 0.6094 0.4941 16.2898 52.5652 539.6708 37.1 857.9676 318.2968 0.068 4.5999 33.8542 201.1248 235.3637 1604.4634 26.2847 201.4412 1338.2106 0 18 60 480 439 17 41 0.11666666666666667 7 0.5666666666666667 34 0.03333333333333333 2.0 0.009 9.9735
20 0.0 0 64 512 4 2.0781 0 0.875 5017.2695 4838.5484 5119.2393 31727 1 4684.6068 0.3633 -0.0111 0.1336 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1366 -0.0 0.0 1.0 0.0 0.0202 0.4844 0.3633 16.2083 52.4408 539.2532 37.1 857.9676 318.7144 0.1006 4.7377 35.1526 227.4842 263.0104 1704.6389 21.5753 227.7566 1415.308 0 19 63 504 466 14 36 0.06349206349206349 4 0.49206349206349204 31 0.031746031746031744 2.0 0.031746031746031744 2.0
21 0.0 0 64 512 3 1.6875 0 0.9219 4813.3398 4682.4186 4879.5706 31781 1 4023.4961 0.3359 -0.002 0.0598 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1335 -0.0005 0.0 1.0 0.0 0.0148 0.4219 0.3359 16.389 52.692 539.0041 37.2 857.9676 318.9635 0.0634 4.6853 31.7718 184.2284 216.3535 1243.9949 24.9441 184.518 998.0071 0 20 62 496 452 15 39 0.06451612903225806 4.0 0.08064516129032258 5 0.5483870967741935 34 0.016129032258064516 1.0 0.0082 10.7804 0.016129032258064516 1.0 5.7822
22 0.0 0 64 512 4 1.875 0 0.9219 4842.0918 4761.3186 4905.9196 31794 1 4212.6536 0.4414 0.0036 0.1383 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1256 -0.0013 0.0 1.0 0.0 0.0203 0.5781 0.4414 16.4531 52.6938 538.5048 37.2 857.9676 319.4628 0.0643 4.6969 34.2897 194.8264 229.4509 1850.931 22.0367 195.0966 1594.7419 0 21 65 520 474 20 46 0.09230769230769231 6 0.6153846153846154 40
23 0.0 0 64 512 3 1.4688 0 0.8281 4904.0176 4757.8386 5016.8131 31774 1 5193.9333 0.4355 0.0091 0.0904 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1243 -0.0 0.0 1.0 0.0 0.0108 0.5156 0.4355 16.7661 53.0065 538.0942 37.3 857.9676 319.8734 0.0718 4.7325 38.9414 247.2972 286.6118 1397.2504 25.3533 247.5984 1080.5473 0 22 64 512 461 16 49 0.015625 1.0 0.109375 7 0.609375 39 0.046875 3.0 0.0087 10.301 0.015625 1.0
24 0.0 0 64 512 3 1.7656 0 0.9531 4420.6699 4579.8023 4340.1676 31656 1 4118.4741 0.3359 0.0061 0.1162 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1221 -0.0006 0.0 1.0 0.0 0.0226 0.5 0.3359 17.1543 53.3796 536.8373 37.4 857.9676 321.1303 0.0927 4.5604 29.1154 184.7184 214.174 1504.7633 24.6211 184.9654 1261.4005 0 23 63 504 452 15 43 0.12698412698412698 8.0 0.06349206349206349 4 0.5714285714285714 36 0.047619047619047616 3.0 0.015873015873015872 1.0
25 0.0 0 64 512 3 1.7969 0 0.9531 4574.207 4892.4115 4286.7584 31701 1 3895.9681 0.4746 -0.001 0.1171 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1198 -0.0 0.0 1.0 0.0 0.0165 0.5625 0.4746 17.1777 53.3798 538.1989 37.3 857.9676 319.7687 0.094 4.6418 30.5187 182.2819 213.1498 1700.5271 21.8175 182.5366 1460.9109 0 24 61 488 423 25 55 0.14754098360655737 9.0 0.14754098360655737 9 0.5245901639344263 32 0.22950819672131148 14.0 0.0094 10.6318 0.01639344262295082 1.0
26 0.0 0 64 512 3 1.6719 0 0.9219 4631.207 5387.3656 4199.7791 31761 1 4549.8186 0.3633 0.0269 0.1247 -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 0.119 -0.0036 0.0 1.0 0.0 0.0181 0.5 0.3633 17.1838 53.3813 537.2989 37.4 857.9676 320.6687 0.0787 4.5345 32.4627 208.7999 241.6056 1624.9161 19.6067 209.0637 1359.1612 0 25 53 424 376 16 45 0.05660377358490566 3.0 0.37735849056603776 20 0.6415094339622641 34 0.03773584905660377 2.0 5.9782 0.018867924528301886 1.0
27 0.0 0 64 512 4 1.7344 0 0.9844 3893.377 3932.6115 3846.765 31762 1 3658.4465 0.543 0.0189 0.1012 -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 0.1126 -0.0039 0.0 1.0 0.0 0.0164 0.6719 0.543 17.183 53.3804 537.6219 37.3 857.9676 320.3456 0.0913 4.5212 25.6794 169.8466 195.8585 995.4217 21.6119 170.0873 773.4247 0 26 58 464 433 13 26 0.05172413793103448 3.0 0.13793103448275862 8 0.29310344827586204 17 0.034482758620689655 2.0 0.0086 10.3518 0.034482758620689655 2.0
28 0.0 0 64 512 4 2.0781 0 0.9375 4736.4414 5049.1301 4390.2963 20191 1 3483.9669 0.5254 0.0145 0.1444 -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 0.1249 -0.0042 0.0 1.0 0.0 0.0159 0.6406 0.5254 16.9689 53.1663 537.6146 37.3 857.9676 320.353 0.0664 3.2159 28.0361 184.7269 213.0974 1234.7892 24.6173 184.9943 993.8523 0 27 44 352 283 23 48 0.38636363636363635 17.0 0.3181818181818182 14 0.5909090909090909 26 0.9090909090909091 40.0 0.06818181818181818 3.0 0.022727272727272728 1.0