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_630124.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_RuntimeError,batch_errors/total_RuntimeError,batch_errors/avg_VerifierTimeoutError,batch_errors/total_VerifierTimeoutError,batch_errors/avg_AgentTimeoutError,batch_errors/total_AgentTimeoutError,batch_errors/avg_InvalidChatHistory,batch_errors/total_InvalidChatHistory,batch_errors/avg_ContextLengthExceededError,batch_errors/total_ContextLengthExceededError,timing/cleanup_old_checkpoints,timing/save_checkpoints,timing/save_hf_model,batch_errors/avg_DaytonaError,batch_errors/total_DaytonaError,batch_errors/avg_AgentSetupTimeoutError,batch_errors/total_AgentSetupTimeoutError,batch_errors/avg_DaytonaAuthenticationError,batch_errors/total_DaytonaAuthenticationError
0.0,0,64,512,0,0.0,0,0.0,4169.1133,3891.7792,5095.1271,29264,1263,2914.3086,0.7695,-0.0069,0.0744,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1189,0.0,0.0,1.0,0.0,0.0105,0.8125,0.7695,11.6896,50.3563,578.7643,32.5,857.9675,279.2032,0.1941,4.3043,30.7211,146.6405,177.747,3371.9765,22.9409,146.8314,3166.9842,0,1,119,952,918,22,26,0.04201680672268908,5.0,0.025210084033613446,3.0,0.008403361344537815,1.0,0.10084033613445378,12,0.14285714285714285,17,,,,,,,,,
0.0,0,64,512,1,0.8594,0,0.8594,5688.084,5824.2419,5589.5185,31885,1,5477.7731,0.4199,0.0464,0.1255,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1361,-0.005,0.0,1.0,0.0,0.0161,0.5781,0.4199,12.6834,50.5541,574.2212,33.1,857.9675,283.7463,0.0641,4.8042,39.1437,260.9703,300.4542,1718.0337,24.4369,261.2461,1388.3356,0,2,63,504,454,24,37,0.15873015873015872,10.0,0.047619047619047616,3.0,0.06349206349206349,4.0,0.36507936507936506,23,0.15873015873015872,10,14.2681,24.8089,,,,,,,
0.0,0,64,512,2,1.5625,0,0.9375,5287.3867,5200.8475,5333.1104,31817,1,5758.917,0.3457,0.0073,0.0951,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1283,-0.0021,0.0,1.0,0.0,0.0171,0.4688,0.3457,12.9334,50.6717,572.7552,33.2,857.9675,285.2123,0.1003,4.7883,38.0045,267.5741,305.9524,1220.661,24.4652,267.8472,885.4504,0,3,62,496,468,14,23,0.08064516129032258,5.0,,,,,0.3064516129032258,19,0.0967741935483871,6,,,,,,,,,
0.0,0,64,512,3,1.8438,0,0.875,5684.4512,4907.0708,6233.8,31815,1,5008.2154,0.4141,-0.0061,0.0833,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1411,-0.004,0.0,1.0,0.0,0.0121,0.4844,0.4141,13.7453,50.795,563.5295,34.3,857.9675,294.438,0.0673,4.9105,37.4051,234.7096,272.4655,1357.8902,20.825,234.9927,1059.6856,0,4,62,496,451,21,36,0.0967741935483871,6.0,0.04838709677419355,3.0,,,0.3709677419354839,23,0.22580645161290322,14,0.008,12.7181,,,,,,,
0.0,0,64,512,4,1.875,0,0.9219,5039.3906,5546.9962,4499.0363,31714,1,4334.7369,0.5156,0.0318,0.1173,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1279,-0.0036,0.0,1.0,0.0,0.0141,0.625,0.5156,13.8122,50.8325,562.6003,34.4,857.9675,295.3672,0.0989,4.6928,39.1023,199.9551,239.4905,1224.4331,24.7234,200.2888,955.52,0,5,62,496,449,22,32,0.11290322580645161,7.0,0.12903225806451613,8.0,,,0.3387096774193548,21,0.1935483870967742,12,,,8.2216,,,,,,
0.0,0,64,512,4,2.1719,0,0.9375,5591.9941,5830.8641,5431.1863,31798,1,4994.2618,0.4023,0.0066,0.0843,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1286,-0.0004,0.0,1.0,0.0,0.0111,0.4844,0.4023,13.8712,50.9265,561.6264,34.5,857.9675,296.3411,0.0653,4.9236,37.4489,233.3771,271.219,1281.0159,22.6774,233.7045,982.1918,0,6,62,496,435,23,51,0.12903225806451613,8.0,0.03225806451612903,2.0,0.04838709677419355,3.0,0.5161290322580645,32,0.25806451612903225,16,0.0067,13.924,,0.016129032258064516,1.0,,,,
0.0,0,64,512,4,2.1094,0,0.9062,4851.3477,5205.5652,4562.4468,31817,1,4336.985,0.4492,0.0059,0.0777,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1271,-0.0014,0.0,1.0,0.0,0.0139,0.5469,0.4492,13.9109,50.9409,561.0771,34.6,857.9675,296.8904,0.0644,4.6898,33.9517,197.6421,231.9494,1559.2848,23.4677,197.9329,1299.1744,0,7,63,504,457,15,42,,,0.07936507936507936,5.0,0.031746031746031744,2.0,0.5555555555555556,35,0.07936507936507936,5,,,,,,,,,
0.0,0,64,512,4,2.1094,0,0.9219,5596.0137,5715.5123,5487.2164,31840,1,5416.4656,0.4766,0.0199,0.145,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1283,0.0,0.0,1.0,0.0,0.0136,0.625,0.4766,13.9023,50.9439,561.6647,34.5,857.9675,296.3028,0.0672,4.797,43.3436,268.6347,312.3633,1610.273,22.6954,268.9523,1270.4134,0,8,62,496,457,18,38,,,,,0.016129032258064516,1.0,0.4032258064516129,25,0.20967741935483872,13,0.0071,12.1975,,,,0.016129032258064516,1.0,,
0.0,0,64,512,4,1.9844,0,0.9531,5326.7715,5167.9342,5454.2887,31758,1,4691.8758,0.4453,0.0119,0.0971,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1268,0.0,0.0,1.0,0.0,0.0137,0.5469,0.4453,13.8936,50.9354,559.6754,34.8,857.9675,298.2921,0.0782,4.7117,38.0949,222.0535,260.5136,1321.2856,23.5801,222.3401,1032.476,0,9,61,488,449,18,38,,,0.01639344262295082,1.0,0.03278688524590164,2.0,0.4426229508196721,27,0.22950819672131148,14,,,,,,,,,
0.0,0,64,512,3,1.8906,0,0.9062,4968.5547,4853.8377,5036.8131,31768,1,4721.9898,0.373,0.0139,0.118,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1359,0.0,0.0,1.0,0.0,0.0144,0.5312,0.373,13.9257,51.0073,560.3441,34.7,857.9675,297.6235,0.0714,4.8344,33.5456,220.0195,253.8928,1294.919,24.3901,220.2753,1011.7949,0,10,62,496,442,18,46,,,0.12903225806451613,8.0,0.016129032258064516,1.0,0.6451612903225806,40,0.12903225806451613,8,0.0084,14.0711,8.8277,,,,,,
0.0,0,64,512,4,1.7812,0,0.9219,4462.5332,4532.996,4394.2385,31762,1,4298.9711,0.4922,0.0008,0.1662,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1254,-0.0056,0.0,1.0,0.0,0.0183,0.6562,0.4922,14.0333,51.1276,559.0244,34.8,857.9675,298.9431,0.0938,4.6549,32.2602,198.6454,231.2913,1475.0347,24.5599,198.9368,1214.5237,0,11,64,512,471,16,33,,,0.125,8.0,0.046875,3.0,0.328125,21,0.140625,9,,,,,,,,,
0.0,0,64,512,4,2.0938,0,0.8906,5849.1094,5035.9944,6282.4461,31797,1,4813.1067,0.3477,-0.0072,0.0606,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1327,0.0,0.0,1.0,0.0,0.013,0.4219,0.3477,14.0347,51.1288,558.5858,34.9,857.9675,299.3817,0.0732,5.2651,38.6448,224.9423,263.9456,1559.3505,25.6632,225.2273,1264.4721,0,12,57,456,426,14,30,,,,,0.07017543859649122,4.0,0.42105263157894735,24,0.14035087719298245,8,0.0084,14.0752,,,,,,,
0.0,0,64,512,4,1.8125,0,0.875,4866.082,5038.6537,4692.1569,31760,1,4066.2403,0.502,-0.0034,0.1269,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1255,-0.0,0.0,1.0,0.0,0.0186,0.625,0.502,14.0677,51.1943,557.1813,35.1,857.9675,300.7862,0.0704,4.6745,31.6351,183.7078,215.6617,1431.9056,23.0843,183.9558,1188.48,0,13,64,512,450,21,49,,,0.203125,13.0,0.25,16.0,0.46875,30,0.09375,6,,,,,,,,,
0.0,0,64,512,4,2.0469,0,0.9375,4926.5117,4839.1749,4993.9031,31751,1,4266.9039,0.4355,0.0028,0.0804,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1228,-0.0013,0.0,1.0,0.0,0.0162,0.5469,0.4355,14.322,51.506,557.3558,35.0,857.9675,300.6118,0.0972,4.7529,33.9188,193.7138,228.0319,1142.7788,24.0818,194.0154,885.9041,0,14,63,504,473,18,30,,,,,,,0.3333333333333333,21,0.14285714285714285,9,0.0084,13.3568,,,,,,0.015873015873015872,1.0
0.0,0,64,512,4,2.0312,0,0.9219,5025.9766,4558.8924,5475.1648,31707,1,4544.2113,0.4902,0.0047,0.108,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1336,-0.0,0.0,1.0,0.0,0.0154,0.6094,0.4902,14.6948,51.8791,556.9661,35.1,857.9675,301.0014,0.0749,4.7275,31.8001,218.695,250.8643,1313.9526,22.5691,218.989,1035.7868,0,15,64,512,477,18,28,,,0.109375,7.0,,,0.296875,19,0.1875,12,,,8.2163,,,,,,
0.0,0,64,512,4,1.9375,0,0.8906,5304.2988,4924.3203,5616.6655,31702,1,4477.752,0.4512,0.0092,0.1087,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1249,-0.0,0.0,1.0,0.0,0.0148,0.5781,0.4512,14.4315,51.6356,556.9907,35.1,857.9675,300.9769,0.1006,4.7795,36.8211,219.4484,256.6458,1308.8006,22.9796,219.7236,1024.3882,0,16,61,488,421,21,66,,,,,0.09836065573770492,6.0,0.8360655737704918,51,0.16393442622950818,10,0.0077,14.8915,,,,0.01639344262295082,1.0,,
0.0,0,64,512,4,2.3594,0,0.9375,5391.4434,6104.0653,4938.3706,31758,1,5320.6865,0.3887,0.0223,0.0896,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1221,-0.002,0.0,1.0,0.0,0.0108,0.5156,0.3887,14.5796,51.7618,556.1977,35.2,857.9675,301.7698,0.0974,5.3524,38.0588,253.8113,292.2721,1220.8525,24.0951,254.1154,899.1259,0,17,57,456,419,17,35,,,0.017543859649122806,1.0,0.03508771929824561,2.0,0.38596491228070173,22,0.24561403508771928,14,,,,,,0.017543859649122806,1.0,,
0.0,0,64,512,4,1.7188,0,0.875,5066.6953,5047.4764,5082.7455,31770,1,4672.0163,0.4551,0.0005,0.1098,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1223,-0.0028,0.0,1.0,0.0,0.0154,0.5625,0.4551,14.7728,51.9543,556.2234,35.2,857.9675,301.7441,0.0991,4.843,39.5878,215.8858,255.888,1582.6579,22.1364,216.2007,1299.7832,0,18,60,480,437,18,41,,,0.03333333333333333,2.0,0.016666666666666666,1.0,0.5333333333333333,32,0.16666666666666666,10,0.0075,16.3173,,,,,,,
0.0,0,64,512,4,1.8281,0,0.8906,5320.7246,4968.5291,5526.808,31825,1,4635.3488,0.3691,-0.0052,0.097,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1408,-0.0,0.0,1.0,0.0,0.0136,0.4531,0.3691,14.7764,51.9575,554.7101,35.3,857.9675,303.2574,0.0666,4.8474,33.322,217.0675,250.7206,1533.2708,23.3393,217.3317,1254.3583,0,19,62,496,453,17,43,,,,,,,0.6129032258064516,38,0.0967741935483871,6,,,,,,,,,
0.0,0,64,512,4,1.6875,0,0.8906,4981.0215,5122.7233,4885.6275,31734,1,4443.4633,0.4023,-0.0006,0.0906,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1347,0.0,0.0,1.0,0.0,0.0168,0.5156,0.4023,14.7832,52.0205,554.9844,35.3,857.9675,302.9831,0.0665,4.7337,34.0494,210.2643,244.6153,1501.26,23.3047,210.499,1228.6018,0,20,63,504,461,18,38,,,0.047619047619047616,3.0,0.06349206349206349,4.0,0.5396825396825397,34,0.06349206349206349,4,0.0078,13.3388,8.0322,,,0.031746031746031744,2.0,,
0.0,0,64,512,4,1.7969,0,0.8906,5089.5234,5337.2258,4948.1963,31834,1,4103.7515,0.3633,-0.0098,0.0985,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1382,-0.0055,0.0,1.0,0.0,0.0123,0.4688,0.3633,14.7559,51.9613,554.3621,35.4,857.9675,303.6055,0.0721,4.8151,32.0319,197.6414,230.0275,1384.6688,23.9344,197.9232,1125.887,0,21,61,488,432,21,46,,,0.13114754098360656,8.0,,,0.6229508196721312,38,0.13114754098360656,8,,,,,,0.03278688524590164,2.0,,
0.0,0,64,512,3,1.5156,0,0.8281,4888.4629,4445.7686,5246.6855,31774,1,4638.3152,0.4473,0.0144,0.0967,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1277,0.0,0.0,1.0,0.0,0.0135,0.5781,0.4473,15.1406,52.3359,554.3356,35.4,857.9675,303.6319,0.0672,4.8409,37.4714,213.0209,250.8158,1341.0965,22.4572,213.2768,1062.9785,0,22,64,512,452,21,60,,,,,0.046875,3.0,0.734375,47,0.15625,10,0.0085,14.204,,,,,,,
0.0,0,64,512,4,1.6094,0,0.8594,5010.1426,5339.5915,4775.4515,31738,1,5125.7203,0.416,0.0029,0.123,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1269,-0.0,0.0,1.0,0.0,0.0161,0.5781,0.416,15.1399,52.3352,554.2477,35.4,857.9675,303.7198,0.0666,4.7525,38.7094,241.3185,280.3783,1636.7829,23.2267,241.602,1328.421,0,23,61,488,423,17,65,,,,,0.04918032786885246,3.0,0.639344262295082,39,0.3770491803278688,23,,,,,,,,,
0.0,0,64,512,3,1.5156,0,0.8281,4957.0039,5145.7238,4853.8066,31744,1,4792.2542,0.3535,-0.005,0.139,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1197,0.0,0.0,1.0,0.0,0.0118,0.4531,0.3535,15.2222,52.591,552.66,35.6,857.9675,305.3075,0.0667,4.8036,34.8997,225.7814,261.0063,1813.0727,21.5017,226.0394,1525.7569,0,24,53,424,405,10,17,,,0.1509433962264151,8.0,0.09433962264150944,5.0,0.1320754716981132,7,0.24528301886792453,13,0.0085,13.7903,,,,,,,
0.0,0,64,512,4,1.8281,0,0.9062,4999.9961,4608.5735,5274.3821,31665,1,3727.2595,0.4121,0.0076,0.0996,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1278,-0.0,0.0,1.0,0.0,0.0129,0.4844,0.4121,15.4929,52.9026,551.8461,35.7,857.9675,306.1215,0.0644,4.6949,29.2144,181.8811,211.389,988.3901,25.1751,182.1098,747.1268,0,25,54,432,406,12,19,,,0.12962962962962962,7.0,0.07407407407407407,4.0,0.2777777777777778,15,0.1111111111111111,6,,,8.7088,,,,,,
0.0,0,64,512,4,1.7344,0,0.875,4801.6133,4766.3344,4852.3476,31766,1,3813.5277,0.5898,-0.0032,0.1052,-0.0001,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1273,-0.0035,0.0,1.0,0.0,0.0164,0.6875,0.5898,15.8889,53.344,552.8224,35.6,857.9675,305.1451,0.0946,4.7486,31.8278,188.1649,220.5231,1031.4949,22.9306,188.6001,783.2847,0,26,59,472,410,26,50,,,0.11864406779661017,7.0,0.3050847457627119,18.0,0.3220338983050847,19,0.23728813559322035,14,0.009,12.6671,,,,0.288135593220339,17.0,,
0.0,0,64,512,4,2.1875,0,0.9688,5055.6387,4951.9907,5130.67,31763,1,4942.405,0.4199,0.0045,0.1012,-0.0002,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1162,-0.01,0.0,1.0,0.0,0.0135,0.5469,0.4199,16.046,53.4671,552.5507,35.6,857.9675,305.4168,0.0766,4.8488,33.5052,219.951,253.8289,2130.9697,18.5315,220.2467,1853.7559,0,27,52,416,390,13,6,,,0.28846153846153844,15.0,,,0.2692307692307692,14,0.057692307692307696,3,,,,,,0.19230769230769232,10.0,0.019230769230769232,1.0
0.0,0,64,512,4,1.6719,0,0.8281,4799.998,4474.8537,5214.7378,21478,1,3336.6768,0.5605,0.0081,0.0474,-0.0003,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1169,-0.0193,0.0,1.0,0.0,0.0089,0.625,0.5605,15.7877,53.2084,552.8907,35.6,857.9675,305.0768,0.0486,3.4809,28.5303,161.7902,190.6488,998.4337,25.9964,162.0695,778.3023,0,28,44,352,335,11,15,,,0.13636363636363635,6.0,0.022727272727272728,1.0,0.4772727272727273,21,0.45454545454545453,20,0.0082,11.9058,,,,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_RuntimeError batch_errors/total_RuntimeError batch_errors/avg_VerifierTimeoutError batch_errors/total_VerifierTimeoutError batch_errors/avg_AgentTimeoutError batch_errors/total_AgentTimeoutError batch_errors/avg_InvalidChatHistory batch_errors/total_InvalidChatHistory batch_errors/avg_ContextLengthExceededError batch_errors/total_ContextLengthExceededError timing/cleanup_old_checkpoints timing/save_checkpoints timing/save_hf_model batch_errors/avg_DaytonaError batch_errors/total_DaytonaError batch_errors/avg_AgentSetupTimeoutError batch_errors/total_AgentSetupTimeoutError batch_errors/avg_DaytonaAuthenticationError batch_errors/total_DaytonaAuthenticationError
2 0.0 0 64 512 0 0.0 0 0.0 4169.1133 3891.7792 5095.1271 29264 1263 2914.3086 0.7695 -0.0069 0.0744 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1189 0.0 0.0 1.0 0.0 0.0105 0.8125 0.7695 11.6896 50.3563 578.7643 32.5 857.9675 279.2032 0.1941 4.3043 30.7211 146.6405 177.747 3371.9765 22.9409 146.8314 3166.9842 0 1 119 952 918 22 26 0.04201680672268908 5.0 0.025210084033613446 3.0 0.008403361344537815 1.0 0.10084033613445378 12 0.14285714285714285 17
3 0.0 0 64 512 1 0.8594 0 0.8594 5688.084 5824.2419 5589.5185 31885 1 5477.7731 0.4199 0.0464 0.1255 -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 0.1361 -0.005 0.0 1.0 0.0 0.0161 0.5781 0.4199 12.6834 50.5541 574.2212 33.1 857.9675 283.7463 0.0641 4.8042 39.1437 260.9703 300.4542 1718.0337 24.4369 261.2461 1388.3356 0 2 63 504 454 24 37 0.15873015873015872 10.0 0.047619047619047616 3.0 0.06349206349206349 4.0 0.36507936507936506 23 0.15873015873015872 10 14.2681 24.8089
4 0.0 0 64 512 2 1.5625 0 0.9375 5287.3867 5200.8475 5333.1104 31817 1 5758.917 0.3457 0.0073 0.0951 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1283 -0.0021 0.0 1.0 0.0 0.0171 0.4688 0.3457 12.9334 50.6717 572.7552 33.2 857.9675 285.2123 0.1003 4.7883 38.0045 267.5741 305.9524 1220.661 24.4652 267.8472 885.4504 0 3 62 496 468 14 23 0.08064516129032258 5.0 0.3064516129032258 19 0.0967741935483871 6
5 0.0 0 64 512 3 1.8438 0 0.875 5684.4512 4907.0708 6233.8 31815 1 5008.2154 0.4141 -0.0061 0.0833 -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 0.1411 -0.004 0.0 1.0 0.0 0.0121 0.4844 0.4141 13.7453 50.795 563.5295 34.3 857.9675 294.438 0.0673 4.9105 37.4051 234.7096 272.4655 1357.8902 20.825 234.9927 1059.6856 0 4 62 496 451 21 36 0.0967741935483871 6.0 0.04838709677419355 3.0 0.3709677419354839 23 0.22580645161290322 14 0.008 12.7181
6 0.0 0 64 512 4 1.875 0 0.9219 5039.3906 5546.9962 4499.0363 31714 1 4334.7369 0.5156 0.0318 0.1173 -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 0.1279 -0.0036 0.0 1.0 0.0 0.0141 0.625 0.5156 13.8122 50.8325 562.6003 34.4 857.9675 295.3672 0.0989 4.6928 39.1023 199.9551 239.4905 1224.4331 24.7234 200.2888 955.52 0 5 62 496 449 22 32 0.11290322580645161 7.0 0.12903225806451613 8.0 0.3387096774193548 21 0.1935483870967742 12 8.2216
7 0.0 0 64 512 4 2.1719 0 0.9375 5591.9941 5830.8641 5431.1863 31798 1 4994.2618 0.4023 0.0066 0.0843 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1286 -0.0004 0.0 1.0 0.0 0.0111 0.4844 0.4023 13.8712 50.9265 561.6264 34.5 857.9675 296.3411 0.0653 4.9236 37.4489 233.3771 271.219 1281.0159 22.6774 233.7045 982.1918 0 6 62 496 435 23 51 0.12903225806451613 8.0 0.03225806451612903 2.0 0.04838709677419355 3.0 0.5161290322580645 32 0.25806451612903225 16 0.0067 13.924 0.016129032258064516 1.0
8 0.0 0 64 512 4 2.1094 0 0.9062 4851.3477 5205.5652 4562.4468 31817 1 4336.985 0.4492 0.0059 0.0777 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1271 -0.0014 0.0 1.0 0.0 0.0139 0.5469 0.4492 13.9109 50.9409 561.0771 34.6 857.9675 296.8904 0.0644 4.6898 33.9517 197.6421 231.9494 1559.2848 23.4677 197.9329 1299.1744 0 7 63 504 457 15 42 0.07936507936507936 5.0 0.031746031746031744 2.0 0.5555555555555556 35 0.07936507936507936 5
9 0.0 0 64 512 4 2.1094 0 0.9219 5596.0137 5715.5123 5487.2164 31840 1 5416.4656 0.4766 0.0199 0.145 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1283 0.0 0.0 1.0 0.0 0.0136 0.625 0.4766 13.9023 50.9439 561.6647 34.5 857.9675 296.3028 0.0672 4.797 43.3436 268.6347 312.3633 1610.273 22.6954 268.9523 1270.4134 0 8 62 496 457 18 38 0.016129032258064516 1.0 0.4032258064516129 25 0.20967741935483872 13 0.0071 12.1975 0.016129032258064516 1.0
10 0.0 0 64 512 4 1.9844 0 0.9531 5326.7715 5167.9342 5454.2887 31758 1 4691.8758 0.4453 0.0119 0.0971 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1268 0.0 0.0 1.0 0.0 0.0137 0.5469 0.4453 13.8936 50.9354 559.6754 34.8 857.9675 298.2921 0.0782 4.7117 38.0949 222.0535 260.5136 1321.2856 23.5801 222.3401 1032.476 0 9 61 488 449 18 38 0.01639344262295082 1.0 0.03278688524590164 2.0 0.4426229508196721 27 0.22950819672131148 14
11 0.0 0 64 512 3 1.8906 0 0.9062 4968.5547 4853.8377 5036.8131 31768 1 4721.9898 0.373 0.0139 0.118 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1359 0.0 0.0 1.0 0.0 0.0144 0.5312 0.373 13.9257 51.0073 560.3441 34.7 857.9675 297.6235 0.0714 4.8344 33.5456 220.0195 253.8928 1294.919 24.3901 220.2753 1011.7949 0 10 62 496 442 18 46 0.12903225806451613 8.0 0.016129032258064516 1.0 0.6451612903225806 40 0.12903225806451613 8 0.0084 14.0711 8.8277
12 0.0 0 64 512 4 1.7812 0 0.9219 4462.5332 4532.996 4394.2385 31762 1 4298.9711 0.4922 0.0008 0.1662 -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 0.1254 -0.0056 0.0 1.0 0.0 0.0183 0.6562 0.4922 14.0333 51.1276 559.0244 34.8 857.9675 298.9431 0.0938 4.6549 32.2602 198.6454 231.2913 1475.0347 24.5599 198.9368 1214.5237 0 11 64 512 471 16 33 0.125 8.0 0.046875 3.0 0.328125 21 0.140625 9
13 0.0 0 64 512 4 2.0938 0 0.8906 5849.1094 5035.9944 6282.4461 31797 1 4813.1067 0.3477 -0.0072 0.0606 0.0 0.0 0.0 0.0 0.0 0.0 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 0.013 0.4219 0.3477 14.0347 51.1288 558.5858 34.9 857.9675 299.3817 0.0732 5.2651 38.6448 224.9423 263.9456 1559.3505 25.6632 225.2273 1264.4721 0 12 57 456 426 14 30 0.07017543859649122 4.0 0.42105263157894735 24 0.14035087719298245 8 0.0084 14.0752
14 0.0 0 64 512 4 1.8125 0 0.875 4866.082 5038.6537 4692.1569 31760 1 4066.2403 0.502 -0.0034 0.1269 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1255 -0.0 0.0 1.0 0.0 0.0186 0.625 0.502 14.0677 51.1943 557.1813 35.1 857.9675 300.7862 0.0704 4.6745 31.6351 183.7078 215.6617 1431.9056 23.0843 183.9558 1188.48 0 13 64 512 450 21 49 0.203125 13.0 0.25 16.0 0.46875 30 0.09375 6
15 0.0 0 64 512 4 2.0469 0 0.9375 4926.5117 4839.1749 4993.9031 31751 1 4266.9039 0.4355 0.0028 0.0804 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1228 -0.0013 0.0 1.0 0.0 0.0162 0.5469 0.4355 14.322 51.506 557.3558 35.0 857.9675 300.6118 0.0972 4.7529 33.9188 193.7138 228.0319 1142.7788 24.0818 194.0154 885.9041 0 14 63 504 473 18 30 0.3333333333333333 21 0.14285714285714285 9 0.0084 13.3568 0.015873015873015872 1.0
16 0.0 0 64 512 4 2.0312 0 0.9219 5025.9766 4558.8924 5475.1648 31707 1 4544.2113 0.4902 0.0047 0.108 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1336 -0.0 0.0 1.0 0.0 0.0154 0.6094 0.4902 14.6948 51.8791 556.9661 35.1 857.9675 301.0014 0.0749 4.7275 31.8001 218.695 250.8643 1313.9526 22.5691 218.989 1035.7868 0 15 64 512 477 18 28 0.109375 7.0 0.296875 19 0.1875 12 8.2163
17 0.0 0 64 512 4 1.9375 0 0.8906 5304.2988 4924.3203 5616.6655 31702 1 4477.752 0.4512 0.0092 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 0.1249 -0.0 0.0 1.0 0.0 0.0148 0.5781 0.4512 14.4315 51.6356 556.9907 35.1 857.9675 300.9769 0.1006 4.7795 36.8211 219.4484 256.6458 1308.8006 22.9796 219.7236 1024.3882 0 16 61 488 421 21 66 0.09836065573770492 6.0 0.8360655737704918 51 0.16393442622950818 10 0.0077 14.8915 0.01639344262295082 1.0
18 0.0 0 64 512 4 2.3594 0 0.9375 5391.4434 6104.0653 4938.3706 31758 1 5320.6865 0.3887 0.0223 0.0896 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1221 -0.002 0.0 1.0 0.0 0.0108 0.5156 0.3887 14.5796 51.7618 556.1977 35.2 857.9675 301.7698 0.0974 5.3524 38.0588 253.8113 292.2721 1220.8525 24.0951 254.1154 899.1259 0 17 57 456 419 17 35 0.017543859649122806 1.0 0.03508771929824561 2.0 0.38596491228070173 22 0.24561403508771928 14 0.017543859649122806 1.0
19 0.0 0 64 512 4 1.7188 0 0.875 5066.6953 5047.4764 5082.7455 31770 1 4672.0163 0.4551 0.0005 0.1098 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1223 -0.0028 0.0 1.0 0.0 0.0154 0.5625 0.4551 14.7728 51.9543 556.2234 35.2 857.9675 301.7441 0.0991 4.843 39.5878 215.8858 255.888 1582.6579 22.1364 216.2007 1299.7832 0 18 60 480 437 18 41 0.03333333333333333 2.0 0.016666666666666666 1.0 0.5333333333333333 32 0.16666666666666666 10 0.0075 16.3173
20 0.0 0 64 512 4 1.8281 0 0.8906 5320.7246 4968.5291 5526.808 31825 1 4635.3488 0.3691 -0.0052 0.097 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1408 -0.0 0.0 1.0 0.0 0.0136 0.4531 0.3691 14.7764 51.9575 554.7101 35.3 857.9675 303.2574 0.0666 4.8474 33.322 217.0675 250.7206 1533.2708 23.3393 217.3317 1254.3583 0 19 62 496 453 17 43 0.6129032258064516 38 0.0967741935483871 6
21 0.0 0 64 512 4 1.6875 0 0.8906 4981.0215 5122.7233 4885.6275 31734 1 4443.4633 0.4023 -0.0006 0.0906 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1347 0.0 0.0 1.0 0.0 0.0168 0.5156 0.4023 14.7832 52.0205 554.9844 35.3 857.9675 302.9831 0.0665 4.7337 34.0494 210.2643 244.6153 1501.26 23.3047 210.499 1228.6018 0 20 63 504 461 18 38 0.047619047619047616 3.0 0.06349206349206349 4.0 0.5396825396825397 34 0.06349206349206349 4 0.0078 13.3388 8.0322 0.031746031746031744 2.0
22 0.0 0 64 512 4 1.7969 0 0.8906 5089.5234 5337.2258 4948.1963 31834 1 4103.7515 0.3633 -0.0098 0.0985 -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 0.1382 -0.0055 0.0 1.0 0.0 0.0123 0.4688 0.3633 14.7559 51.9613 554.3621 35.4 857.9675 303.6055 0.0721 4.8151 32.0319 197.6414 230.0275 1384.6688 23.9344 197.9232 1125.887 0 21 61 488 432 21 46 0.13114754098360656 8.0 0.6229508196721312 38 0.13114754098360656 8 0.03278688524590164 2.0
23 0.0 0 64 512 3 1.5156 0 0.8281 4888.4629 4445.7686 5246.6855 31774 1 4638.3152 0.4473 0.0144 0.0967 0.0 0.0 0.0 0.0 0.0 0.0 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 0.0135 0.5781 0.4473 15.1406 52.3359 554.3356 35.4 857.9675 303.6319 0.0672 4.8409 37.4714 213.0209 250.8158 1341.0965 22.4572 213.2768 1062.9785 0 22 64 512 452 21 60 0.046875 3.0 0.734375 47 0.15625 10 0.0085 14.204
24 0.0 0 64 512 4 1.6094 0 0.8594 5010.1426 5339.5915 4775.4515 31738 1 5125.7203 0.416 0.0029 0.123 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1269 -0.0 0.0 1.0 0.0 0.0161 0.5781 0.416 15.1399 52.3352 554.2477 35.4 857.9675 303.7198 0.0666 4.7525 38.7094 241.3185 280.3783 1636.7829 23.2267 241.602 1328.421 0 23 61 488 423 17 65 0.04918032786885246 3.0 0.639344262295082 39 0.3770491803278688 23
25 0.0 0 64 512 3 1.5156 0 0.8281 4957.0039 5145.7238 4853.8066 31744 1 4792.2542 0.3535 -0.005 0.139 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1197 0.0 0.0 1.0 0.0 0.0118 0.4531 0.3535 15.2222 52.591 552.66 35.6 857.9675 305.3075 0.0667 4.8036 34.8997 225.7814 261.0063 1813.0727 21.5017 226.0394 1525.7569 0 24 53 424 405 10 17 0.1509433962264151 8.0 0.09433962264150944 5.0 0.1320754716981132 7 0.24528301886792453 13 0.0085 13.7903
26 0.0 0 64 512 4 1.8281 0 0.9062 4999.9961 4608.5735 5274.3821 31665 1 3727.2595 0.4121 0.0076 0.0996 -0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1278 -0.0 0.0 1.0 0.0 0.0129 0.4844 0.4121 15.4929 52.9026 551.8461 35.7 857.9675 306.1215 0.0644 4.6949 29.2144 181.8811 211.389 988.3901 25.1751 182.1098 747.1268 0 25 54 432 406 12 19 0.12962962962962962 7.0 0.07407407407407407 4.0 0.2777777777777778 15 0.1111111111111111 6 8.7088
27 0.0 0 64 512 4 1.7344 0 0.875 4801.6133 4766.3344 4852.3476 31766 1 3813.5277 0.5898 -0.0032 0.1052 -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 0.1273 -0.0035 0.0 1.0 0.0 0.0164 0.6875 0.5898 15.8889 53.344 552.8224 35.6 857.9675 305.1451 0.0946 4.7486 31.8278 188.1649 220.5231 1031.4949 22.9306 188.6001 783.2847 0 26 59 472 410 26 50 0.11864406779661017 7.0 0.3050847457627119 18.0 0.3220338983050847 19 0.23728813559322035 14 0.009 12.6671 0.288135593220339 17.0
28 0.0 0 64 512 4 2.1875 0 0.9688 5055.6387 4951.9907 5130.67 31763 1 4942.405 0.4199 0.0045 0.1012 -0.0002 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1162 -0.01 0.0 1.0 0.0 0.0135 0.5469 0.4199 16.046 53.4671 552.5507 35.6 857.9675 305.4168 0.0766 4.8488 33.5052 219.951 253.8289 2130.9697 18.5315 220.2467 1853.7559 0 27 52 416 390 13 6 0.28846153846153844 15.0 0.2692307692307692 14 0.057692307692307696 3 0.19230769230769232 10.0 0.019230769230769232 1.0
29 0.0 0 64 512 4 1.6719 0 0.8281 4799.998 4474.8537 5214.7378 21478 1 3336.6768 0.5605 0.0081 0.0474 -0.0003 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.1169 -0.0193 0.0 1.0 0.0 0.0089 0.625 0.5605 15.7877 53.2084 552.8907 35.6 857.9675 305.0768 0.0486 3.4809 28.5303 161.7902 190.6488 998.4337 25.9964 162.0695 778.3023 0 28 44 352 335 11 15 0.13636363636363635 6.0 0.022727272727272728 1.0 0.4772727272727273 21 0.45454545454545453 20 0.0082 11.9058 0.022727272727272728 1.0